diff options
721 files changed, 28559 insertions, 11972 deletions
@@ -130,6 +130,7 @@ Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Ed L. Cashin <ecashin@coraid.com> Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com> +Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com> Evgeniy Polyakov <johnpol@2ka.mipt.ru> Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com> Felipe W Damasio <felipewd@terra.com.br> diff --git a/Documentation/ABI/testing/sysfs-class-net-peak_usb b/Documentation/ABI/testing/sysfs-class-net-peak_usb new file mode 100644 index 000000000000..9e3d0bf4d4b2 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-peak_usb @@ -0,0 +1,19 @@ + +What: /sys/class/net/<iface>/peak_usb/can_channel_id +Date: November 2022 +KernelVersion: 6.2 +Contact: Stephane Grosjean <s.grosjean@peak-system.com> +Description: + PEAK PCAN-USB devices support user-configurable CAN channel + identifiers. Contrary to a USB serial number, these identifiers + are writable and can be set per CAN interface. This means that + if a USB device exports multiple CAN interfaces, each of them + can be assigned a unique channel ID. + This attribute provides read-only access to the currently + configured value of the channel identifier. Depending on the + device type, the identifier has a length of 8 or 32 bit. The + value read from this attribute is always an 8 digit 32 bit + hexadecimal value in big endian format. If the device only + supports an 8 bit identifier, the upper 24 bit of the value are + set to zero. + diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index c8ae7c897f14..74cec76be9f2 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. - This file accepts a string which contains the number of bytes to - reclaim. + This file accepts a single key, the number of bytes to reclaim. + No nested keys are currently supported. Example:: echo "1G" > memory.reclaim + The interface can be later extended with nested keys to + configure the reclaim behavior. For example, specify the + type of memory to reclaim from (anon, file, ..). + Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. - This file also allows the user to specify the nodes to reclaim from, - via the 'nodes=' key, for example:: - - echo "1G nodes=0,1" > memory.reclaim - - The above instructs the kernel to reclaim memory from nodes 0,1. - memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 6394f5dc2303..466c560b0c30 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -215,6 +215,12 @@ rmem_max The maximum receive socket buffer size in bytes. +rps_default_mask +---------------- + +The default RPS CPU mask used on newly created network devices. An empty +mask means RPS disabled by default. + tstamp_allow_data ----------------- Allow processes to receive tx timestamps looped together with the original diff --git a/Documentation/bpf/bpf_design_QA.rst b/Documentation/bpf/bpf_design_QA.rst index cec2371173d7..bfff0e7e37c2 100644 --- a/Documentation/bpf/bpf_design_QA.rst +++ b/Documentation/bpf/bpf_design_QA.rst @@ -208,6 +208,10 @@ data structures and compile with kernel internal headers. Both of these kernel internals are subject to change and can break with newer kernels such that the program needs to be adapted accordingly. +New BPF functionality is generally added through the use of kfuncs instead of +new helpers. Kfuncs are not considered part of the stable API, and have their own +lifecycle expectations as described in :ref:`BPF_kfunc_lifecycle_expectations`. + Q: Are tracepoints part of the stable ABI? ------------------------------------------ A: NO. Tracepoints are tied to internal implementation details hence they are @@ -236,8 +240,8 @@ A: NO. Classic BPF programs are converted into extend BPF instructions. Q: Can BPF call arbitrary kernel functions? ------------------------------------------- -A: NO. BPF programs can only call a set of helper functions which -is defined for every program type. +A: NO. BPF programs can only call specific functions exposed as BPF helpers or +kfuncs. The set of available functions is defined for every program type. Q: Can BPF overwrite arbitrary kernel memory? --------------------------------------------- @@ -263,7 +267,12 @@ Q: New functionality via kernel modules? Q: Can BPF functionality such as new program or map types, new helpers, etc be added out of kernel module code? -A: NO. +A: Yes, through kfuncs and kptrs + +The core BPF functionality such as program types, maps and helpers cannot be +added to by modules. However, modules can expose functionality to BPF programs +by exporting kfuncs (which may return pointers to module-internal data +structures as kptrs). Q: Directly calling kernel function is an ABI? ---------------------------------------------- @@ -278,7 +287,8 @@ kernel functions have already been used by other kernel tcp cc (congestion-control) implementations. If any of these kernel functions has changed, both the in-tree and out-of-tree kernel tcp cc implementations have to be changed. The same goes for the bpf -programs and they have to be adjusted accordingly. +programs and they have to be adjusted accordingly. See +:ref:`BPF_kfunc_lifecycle_expectations` for details. Q: Attaching to arbitrary kernel functions is an ABI? ----------------------------------------------------- @@ -340,6 +350,7 @@ compatibility for these features? A: NO. -Unlike map value types, there are no stability guarantees for this case. The -whole API to work with allocated objects and any support for special fields -inside them is unstable (since it is exposed through kfuncs). +Unlike map value types, the API to work with allocated objects and any support +for special fields inside them is exposed through kfuncs, and thus has the same +lifecycle expectations as the kfuncs themselves. See +:ref:`BPF_kfunc_lifecycle_expectations` for details. diff --git a/Documentation/bpf/instruction-set.rst b/Documentation/bpf/instruction-set.rst index 2d3fe59bd260..af515de5fc38 100644 --- a/Documentation/bpf/instruction-set.rst +++ b/Documentation/bpf/instruction-set.rst @@ -7,6 +7,11 @@ eBPF Instruction Set Specification, v1.0 This document specifies version 1.0 of the eBPF instruction set. +Documentation conventions +========================= + +For brevity, this document uses the type notion "u64", "u32", etc. +to mean an unsigned integer whose width is the specified number of bits. Registers and calling convention ================================ @@ -30,20 +35,56 @@ Instruction encoding eBPF has two instruction encodings: * the basic instruction encoding, which uses 64 bits to encode an instruction -* the wide instruction encoding, which appends a second 64-bit immediate value - (imm64) after the basic instruction for a total of 128 bits. +* the wide instruction encoding, which appends a second 64-bit immediate (i.e., + constant) value after the basic instruction for a total of 128 bits. + +The basic instruction encoding is as follows, where MSB and LSB mean the most significant +bits and least significant bits, respectively: + +============= ======= ======= ======= ============ +32 bits (MSB) 16 bits 4 bits 4 bits 8 bits (LSB) +============= ======= ======= ======= ============ +imm offset src_reg dst_reg opcode +============= ======= ======= ======= ============ + +**imm** + signed integer immediate value -The basic instruction encoding looks as follows: +**offset** + signed integer offset used with pointer arithmetic -============= ======= =============== ==================== ============ -32 bits (MSB) 16 bits 4 bits 4 bits 8 bits (LSB) -============= ======= =============== ==================== ============ -immediate offset source register destination register opcode -============= ======= =============== ==================== ============ +**src_reg** + the source register number (0-10), except where otherwise specified + (`64-bit immediate instructions`_ reuse this field for other purposes) + +**dst_reg** + destination register number (0-10) + +**opcode** + operation to perform Note that most instructions do not use all of the fields. Unused fields shall be cleared to zero. +As discussed below in `64-bit immediate instructions`_, a 64-bit immediate +instruction uses a 64-bit immediate value that is constructed as follows. +The 64 bits following the basic instruction contain a pseudo instruction +using the same format but with opcode, dst_reg, src_reg, and offset all set to zero, +and imm containing the high 32 bits of the immediate value. + +================= ================== +64 bits (MSB) 64 bits (LSB) +================= ================== +basic instruction pseudo instruction +================= ================== + +Thus the 64-bit immediate value is constructed as follows: + + imm64 = (next_imm << 32) | imm + +where 'next_imm' refers to the imm value of the pseudo instruction +following the basic instruction. + Instruction classes ------------------- @@ -71,27 +112,32 @@ For arithmetic and jump instructions (``BPF_ALU``, ``BPF_ALU64``, ``BPF_JMP`` an ============== ====== ================= 4 bits (MSB) 1 bit 3 bits (LSB) ============== ====== ================= -operation code source instruction class +code source instruction class ============== ====== ================= -The 4th bit encodes the source operand: +**code** + the operation code, whose meaning varies by instruction class - ====== ===== ======================================== - source value description - ====== ===== ======================================== - BPF_K 0x00 use 32-bit immediate as source operand - BPF_X 0x08 use 'src_reg' register as source operand - ====== ===== ======================================== +**source** + the source operand location, which unless otherwise specified is one of: -The four MSB bits store the operation code. + ====== ===== ============================================== + source value description + ====== ===== ============================================== + BPF_K 0x00 use 32-bit 'imm' value as source operand + BPF_X 0x08 use 'src_reg' register value as source operand + ====== ===== ============================================== +**instruction class** + the instruction class (see `Instruction classes`_) Arithmetic instructions ----------------------- ``BPF_ALU`` uses 32-bit wide operands while ``BPF_ALU64`` uses 64-bit wide operands for otherwise identical operations. -The 'code' field encodes the operation as below: +The 'code' field encodes the operation as below, where 'src' and 'dst' refer +to the values of the source and destination registers, respectively. ======== ===== ========================================================== code value description @@ -121,19 +167,21 @@ the destination register is unchanged whereas for ``BPF_ALU`` the upper ``BPF_ADD | BPF_X | BPF_ALU`` means:: - dst_reg = (u32) dst_reg + (u32) src_reg; + dst = (u32) ((u32) dst + (u32) src) + +where '(u32)' indicates that the upper 32 bits are zeroed. ``BPF_ADD | BPF_X | BPF_ALU64`` means:: - dst_reg = dst_reg + src_reg + dst = dst + src ``BPF_XOR | BPF_K | BPF_ALU`` means:: - dst_reg = (u32) dst_reg ^ (u32) imm32 + dst = (u32) dst ^ (u32) imm32 ``BPF_XOR | BPF_K | BPF_ALU64`` means:: - dst_reg = dst_reg ^ imm32 + dst = dst ^ imm32 Also note that the division and modulo operations are unsigned. Thus, for ``BPF_ALU``, 'imm' is first interpreted as an unsigned 32-bit value, whereas @@ -167,11 +215,11 @@ Examples: ``BPF_ALU | BPF_TO_LE | BPF_END`` with imm = 16 means:: - dst_reg = htole16(dst_reg) + dst = htole16(dst) ``BPF_ALU | BPF_TO_BE | BPF_END`` with imm = 64 means:: - dst_reg = htobe64(dst_reg) + dst = htobe64(dst) Jump instructions ----------------- @@ -246,15 +294,15 @@ instructions that transfer data between a register and memory. ``BPF_MEM | <size> | BPF_STX`` means:: - *(size *) (dst_reg + off) = src_reg + *(size *) (dst + offset) = src ``BPF_MEM | <size> | BPF_ST`` means:: - *(size *) (dst_reg + off) = imm32 + *(size *) (dst + offset) = imm32 ``BPF_MEM | <size> | BPF_LDX`` means:: - dst_reg = *(size *) (src_reg + off) + dst = *(size *) (src + offset) Where size is one of: ``BPF_B``, ``BPF_H``, ``BPF_W``, or ``BPF_DW``. @@ -288,11 +336,11 @@ BPF_XOR 0xa0 atomic xor ``BPF_ATOMIC | BPF_W | BPF_STX`` with 'imm' = BPF_ADD means:: - *(u32 *)(dst_reg + off16) += src_reg + *(u32 *)(dst + offset) += src ``BPF_ATOMIC | BPF_DW | BPF_STX`` with 'imm' = BPF ADD means:: - *(u64 *)(dst_reg + off16) += src_reg + *(u64 *)(dst + offset) += src In addition to the simple atomic operations, there also is a modifier and two complex atomic operations: @@ -307,16 +355,16 @@ BPF_CMPXCHG 0xf0 | BPF_FETCH atomic compare and exchange The ``BPF_FETCH`` modifier is optional for simple atomic operations, and always set for the complex atomic operations. If the ``BPF_FETCH`` flag -is set, then the operation also overwrites ``src_reg`` with the value that +is set, then the operation also overwrites ``src`` with the value that was in memory before it was modified. -The ``BPF_XCHG`` operation atomically exchanges ``src_reg`` with the value -addressed by ``dst_reg + off``. +The ``BPF_XCHG`` operation atomically exchanges ``src`` with the value +addressed by ``dst + offset``. The ``BPF_CMPXCHG`` operation atomically compares the value addressed by -``dst_reg + off`` with ``R0``. If they match, the value addressed by -``dst_reg + off`` is replaced with ``src_reg``. In either case, the -value that was at ``dst_reg + off`` before the operation is zero-extended +``dst + offset`` with ``R0``. If they match, the value addressed by +``dst + offset`` is replaced with ``src``. In either case, the +value that was at ``dst + offset`` before the operation is zero-extended and loaded back to ``R0``. 64-bit immediate instructions @@ -329,7 +377,7 @@ There is currently only one such instruction. ``BPF_LD | BPF_DW | BPF_IMM`` means:: - dst_reg = imm64 + dst = imm64 Legacy BPF Packet access instructions diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index 1a683225d080..ca96ef3f6896 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -13,7 +13,7 @@ BPF Kernel Functions or more commonly known as kfuncs are functions in the Linux kernel which are exposed for use by BPF programs. Unlike normal BPF helpers, kfuncs do not have a stable interface and can change from one kernel release to another. Hence, BPF programs need to be updated in response to changes in the -kernel. +kernel. See :ref:`BPF_kfunc_lifecycle_expectations` for more information. 2. Defining a kfunc =================== @@ -41,7 +41,7 @@ An example is given below:: __diag_ignore_all("-Wmissing-prototypes", "Global kfuncs as their definitions will be in BTF"); - struct task_struct *bpf_find_get_task_by_vpid(pid_t nr) + __bpf_kfunc struct task_struct *bpf_find_get_task_by_vpid(pid_t nr) { return find_get_task_by_vpid(nr); } @@ -66,7 +66,7 @@ kfunc with a __tag, where tag may be one of the supported annotations. This annotation is used to indicate a memory and size pair in the argument list. An example is given below:: - void bpf_memzero(void *mem, int mem__sz) + __bpf_kfunc void bpf_memzero(void *mem, int mem__sz) { ... } @@ -86,7 +86,7 @@ safety of the program. An example is given below:: - void *bpf_obj_new(u32 local_type_id__k, ...) + __bpf_kfunc void *bpf_obj_new(u32 local_type_id__k, ...) { ... } @@ -125,6 +125,20 @@ flags on a set of kfuncs as follows:: This set encodes the BTF ID of each kfunc listed above, and encodes the flags along with it. Ofcourse, it is also allowed to specify no flags. +kfunc definitions should also always be annotated with the ``__bpf_kfunc`` +macro. This prevents issues such as the compiler inlining the kfunc if it's a +static kernel function, or the function being elided in an LTO build as it's +not used in the rest of the kernel. Developers should not manually add +annotations to their kfunc to prevent these issues. If an annotation is +required to prevent such an issue with your kfunc, it is a bug and should be +added to the definition of the macro so that other kfuncs are similarly +protected. An example is given below:: + + __bpf_kfunc struct task_struct *bpf_get_task_pid(s32 pid) + { + ... + } + 2.4.1 KF_ACQUIRE flag --------------------- @@ -224,6 +238,28 @@ single argument which must be a trusted argument or a MEM_RCU pointer. The argument may have reference count of 0 and the kfunc must take this into consideration. +.. _KF_deprecated_flag: + +2.4.9 KF_DEPRECATED flag +------------------------ + +The KF_DEPRECATED flag is used for kfuncs which are scheduled to be +changed or removed in a subsequent kernel release. A kfunc that is +marked with KF_DEPRECATED should also have any relevant information +captured in its kernel doc. Such information typically includes the +kfunc's expected remaining lifespan, a recommendation for new +functionality that can replace it if any is available, and possibly a +rationale for why it is being removed. + +Note that while on some occasions, a KF_DEPRECATED kfunc may continue to be +supported and have its KF_DEPRECATED flag removed, it is likely to be far more +difficult to remove a KF_DEPRECATED flag after it's been added than it is to +prevent it from being added in the first place. As described in +:ref:`BPF_kfunc_lifecycle_expectations`, users that rely on specific kfuncs are +encouraged to make their use-cases known as early as possible, and participate +in upstream discussions regarding whether to keep, change, deprecate, or remove +those kfuncs if and when such discussions occur. + 2.5 Registering the kfuncs -------------------------- @@ -290,14 +326,107 @@ In order to accommodate such requirements, the verifier will enforce strict PTR_TO_BTF_ID type matching if two types have the exact same name, with one being suffixed with ``___init``. -3. Core kfuncs +.. _BPF_kfunc_lifecycle_expectations: + +3. kfunc lifecycle expectations +=============================== + +kfuncs provide a kernel <-> kernel API, and thus are not bound by any of the +strict stability restrictions associated with kernel <-> user UAPIs. This means +they can be thought of as similar to EXPORT_SYMBOL_GPL, and can therefore be +modified or removed by a maintainer of the subsystem they're defined in when +it's deemed necessary. + +Like any other change to the kernel, maintainers will not change or remove a +kfunc without having a reasonable justification. Whether or not they'll choose +to change a kfunc will ultimately depend on a variety of factors, such as how +widely used the kfunc is, how long the kfunc has been in the kernel, whether an +alternative kfunc exists, what the norm is in terms of stability for the +subsystem in question, and of course what the technical cost is of continuing +to support the kfunc. + +There are several implications of this: + +a) kfuncs that are widely used or have been in the kernel for a long time will + be more difficult to justify being changed or removed by a maintainer. In + other words, kfuncs that are known to have a lot of users and provide + significant value provide stronger incentives for maintainers to invest the + time and complexity in supporting them. It is therefore important for + developers that are using kfuncs in their BPF programs to communicate and + explain how and why those kfuncs are being used, and to participate in + discussions regarding those kfuncs when they occur upstream. + +b) Unlike regular kernel symbols marked with EXPORT_SYMBOL_GPL, BPF programs + that call kfuncs are generally not part of the kernel tree. This means that + refactoring cannot typically change callers in-place when a kfunc changes, + as is done for e.g. an upstreamed driver being updated in place when a + kernel symbol is changed. + + Unlike with regular kernel symbols, this is expected behavior for BPF + symbols, and out-of-tree BPF programs that use kfuncs should be considered + relevant to discussions and decisions around modifying and removing those + kfuncs. The BPF community will take an active role in participating in + upstream discussions when necessary to ensure that the perspectives of such + users are taken into account. + +c) A kfunc will never have any hard stability guarantees. BPF APIs cannot and + will not ever hard-block a change in the kernel purely for stability + reasons. That being said, kfuncs are features that are meant to solve + problems and provide value to users. The decision of whether to change or + remove a kfunc is a multivariate technical decision that is made on a + case-by-case basis, and which is informed by data points such as those + mentioned above. It is expected that a kfunc being removed or changed with + no warning will not be a common occurrence or take place without sound + justification, but it is a possibility that must be accepted if one is to + use kfuncs. + +3.1 kfunc deprecation +--------------------- + +As described above, while sometimes a maintainer may find that a kfunc must be +changed or removed immediately to accommodate some changes in their subsystem, +usually kfuncs will be able to accommodate a longer and more measured +deprecation process. For example, if a new kfunc comes along which provides +superior functionality to an existing kfunc, the existing kfunc may be +deprecated for some period of time to allow users to migrate their BPF programs +to use the new one. Or, if a kfunc has no known users, a decision may be made +to remove the kfunc (without providing an alternative API) after some +deprecation period so as to provide users with a window to notify the kfunc +maintainer if it turns out that the kfunc is actually being used. + +It's expected that the common case will be that kfuncs will go through a +deprecation period rather than being changed or removed without warning. As +described in :ref:`KF_deprecated_flag`, the kfunc framework provides the +KF_DEPRECATED flag to kfunc developers to signal to users that a kfunc has been +deprecated. Once a kfunc has been marked with KF_DEPRECATED, the following +procedure is followed for removal: + +1. Any relevant information for deprecated kfuncs is documented in the kfunc's + kernel docs. This documentation will typically include the kfunc's expected + remaining lifespan, a recommendation for new functionality that can replace + the usage of the deprecated function (or an explanation as to why no such + replacement exists), etc. + +2. The deprecated kfunc is kept in the kernel for some period of time after it + was first marked as deprecated. This time period will be chosen on a + case-by-case basis, and will typically depend on how widespread the use of + the kfunc is, how long it has been in the kernel, and how hard it is to move + to alternatives. This deprecation time period is "best effort", and as + described :ref:`above<BPF_kfunc_lifecycle_expectations>`, circumstances may + sometimes dictate that the kfunc be removed before the full intended + deprecation period has elapsed. + +3. After the deprecation period the kfunc will be removed. At this point, BPF + programs calling the kfunc will be rejected by the verifier. + +4. Core kfuncs ============== The BPF subsystem provides a number of "core" kfuncs that are potentially applicable to a wide variety of different possible use cases and programs. Those kfuncs are documented here. -3.1 struct task_struct * kfuncs +4.1 struct task_struct * kfuncs ------------------------------- There are a number of kfuncs that allow ``struct task_struct *`` objects to be @@ -373,7 +502,7 @@ Here is an example of it being used: return 0; } -3.2 struct cgroup * kfuncs +4.2 struct cgroup * kfuncs -------------------------- ``struct cgroup *`` objects also have acquire and release functions: @@ -488,7 +617,7 @@ the verifier. bpf_cgroup_ancestor() can be used as follows: return 0; } -3.3 struct cpumask * kfuncs +4.3 struct cpumask * kfuncs --------------------------- BPF provides a set of kfuncs that can be used to query, allocate, mutate, and diff --git a/Documentation/bpf/libbpf/libbpf_naming_convention.rst b/Documentation/bpf/libbpf/libbpf_naming_convention.rst index c5ac97f3d4c4..b5b41b61b3c0 100644 --- a/Documentation/bpf/libbpf/libbpf_naming_convention.rst +++ b/Documentation/bpf/libbpf/libbpf_naming_convention.rst @@ -83,8 +83,8 @@ This prevents from accidentally exporting a symbol, that is not supposed to be a part of ABI what, in turn, improves both libbpf developer- and user-experiences. -ABI versionning ---------------- +ABI versioning +-------------- To make future ABI extensions possible libbpf ABI is versioned. Versioning is implemented by ``libbpf.map`` version script that is @@ -148,7 +148,7 @@ API documentation convention The libbpf API is documented via comments above definitions in header files. These comments can be rendered by doxygen and sphinx for well organized html output. This section describes the -convention in which these comments should be formated. +convention in which these comments should be formatted. Here is an example from btf.h: diff --git a/Documentation/bpf/map_xskmap.rst b/Documentation/bpf/map_xskmap.rst index 7093b8208451..dc143edd9233 100644 --- a/Documentation/bpf/map_xskmap.rst +++ b/Documentation/bpf/map_xskmap.rst @@ -178,7 +178,7 @@ The following code snippet shows how to update an XSKMAP with an XSK entry. For an example on how create AF_XDP sockets, please see the AF_XDP-example and AF_XDP-forwarding programs in the `bpf-examples`_ directory in the `libxdp`_ repository. -For a detailed explaination of the AF_XDP interface please see: +For a detailed explanation of the AF_XDP interface please see: - `libxdp-readme`_. - `AF_XDP`_ kernel documentation. diff --git a/Documentation/bpf/ringbuf.rst b/Documentation/bpf/ringbuf.rst index 6a615cd62bda..a99cd05d79d4 100644 --- a/Documentation/bpf/ringbuf.rst +++ b/Documentation/bpf/ringbuf.rst @@ -124,7 +124,7 @@ buffer. Currently 4 are supported: - ``BPF_RB_AVAIL_DATA`` returns amount of unconsumed data in ring buffer; - ``BPF_RB_RING_SIZE`` returns the size of ring buffer; -- ``BPF_RB_CONS_POS``/``BPF_RB_PROD_POS`` returns current logical possition +- ``BPF_RB_CONS_POS``/``BPF_RB_PROD_POS`` returns current logical position of consumer/producer, respectively. Returned values are momentarily snapshots of ring buffer state and could be @@ -146,7 +146,7 @@ Design and Implementation This reserve/commit schema allows a natural way for multiple producers, either on different CPUs or even on the same CPU/in the same BPF program, to reserve independent records and work with them without blocking other producers. This -means that if BPF program was interruped by another BPF program sharing the +means that if BPF program was interrupted by another BPF program sharing the same ring buffer, they will both get a record reserved (provided there is enough space left) and can work with it and submit it independently. This applies to NMI context as well, except that due to using a spinlock during diff --git a/Documentation/bpf/verifier.rst b/Documentation/bpf/verifier.rst index d4326caf01f9..f0ec19db301c 100644 --- a/Documentation/bpf/verifier.rst +++ b/Documentation/bpf/verifier.rst @@ -192,7 +192,7 @@ checked and found to be non-NULL, all copies can become PTR_TO_MAP_VALUEs. As well as range-checking, the tracked information is also used for enforcing alignment of pointer accesses. For instance, on most systems the packet pointer is 2 bytes after a 4-byte alignment. If a program adds 14 bytes to that to jump -over the Ethernet header, then reads IHL and addes (IHL * 4), the resulting +over the Ethernet header, then reads IHL and adds (IHL * 4), the resulting pointer will have a variable offset known to be 4n+2 for some n, so adding the 2 bytes (NET_IP_ALIGN) gives a 4-byte alignment and so word-sized accesses through that pointer are safe. @@ -316,6 +316,301 @@ Pruning considers not only the registers but also the stack (and any spilled registers it may hold). They must all be safe for the branch to be pruned. This is implemented in states_equal(). +Some technical details about state pruning implementation could be found below. + +Register liveness tracking +-------------------------- + +In order to make state pruning effective, liveness state is tracked for each +register and stack slot. The basic idea is to track which registers and stack +slots are actually used during subseqeuent execution of the program, until +program exit is reached. Registers and stack slots that were never used could be +removed from the cached state thus making more states equivalent to a cached +state. This could be illustrated by the following program:: + + 0: call bpf_get_prandom_u32() + 1: r1 = 0 + 2: if r0 == 0 goto +1 + 3: r0 = 1 + --- checkpoint --- + 4: r0 = r1 + 5: exit + +Suppose that a state cache entry is created at instruction #4 (such entries are +also called "checkpoints" in the text below). The verifier could reach the +instruction with one of two possible register states: + +* r0 = 1, r1 = 0 +* r0 = 0, r1 = 0 + +However, only the value of register ``r1`` is important to successfully finish +verification. The goal of the liveness tracking algorithm is to spot this fact +and figure out that both states are actually equivalent. + +Data structures +~~~~~~~~~~~~~~~ + +Liveness is tracked using the following data structures:: + + enum bpf_reg_liveness { + REG_LIVE_NONE = 0, + REG_LIVE_READ32 = 0x1, + REG_LIVE_READ64 = 0x2, + REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64, + REG_LIVE_WRITTEN = 0x4, + REG_LIVE_DONE = 0x8, + }; + + struct bpf_reg_state { + ... + struct bpf_reg_state *parent; + ... + enum bpf_reg_liveness live; + ... + }; + + struct bpf_stack_state { + struct bpf_reg_state spilled_ptr; + ... + }; + + struct bpf_func_state { + struct bpf_reg_state regs[MAX_BPF_REG]; + ... + struct bpf_stack_state *stack; + } + + struct bpf_verifier_state { + struct bpf_func_state *frame[MAX_CALL_FRAMES]; + struct bpf_verifier_state *parent; + ... + } + +* ``REG_LIVE_NONE`` is an initial value assigned to ``->live`` fields upon new + verifier state creation; + +* ``REG_LIVE_WRITTEN`` means that the value of the register (or stack slot) is + defined by some instruction verified between this verifier state's parent and + verifier state itself; + +* ``REG_LIVE_READ{32,64}`` means that the value of the register (or stack slot) + is read by a some child state of this verifier state; + +* ``REG_LIVE_DONE`` is a marker used by ``clean_verifier_state()`` to avoid + processing same verifier state multiple times and for some sanity checks; + +* ``->live`` field values are formed by combining ``enum bpf_reg_liveness`` + values using bitwise or. + +Register parentage chains +~~~~~~~~~~~~~~~~~~~~~~~~~ + +In order to propagate information between parent and child states, a *register +parentage chain* is established. Each register or stack slot is linked to a +corresponding register or stack slot in its parent state via a ``->parent`` +pointer. This link is established upon state creation in ``is_state_visited()`` +and might be modified by ``set_callee_state()`` called from +``__check_func_call()``. + +The rules for correspondence between registers / stack slots are as follows: + +* For the current stack frame, registers and stack slots of the new state are + linked to the registers and stack slots of the parent state with the same + indices. + +* For the outer stack frames, only caller saved registers (r6-r9) and stack + slots are linked to the registers and stack slots of the parent state with the + same indices. + +* When function call is processed a new ``struct bpf_func_state`` instance is + allocated, it encapsulates a new set of registers and stack slots. For this + new frame, parent links for r6-r9 and stack slots are set to nil, parent links + for r1-r5 are set to match caller r1-r5 parent links. + +This could be illustrated by the following diagram (arrows stand for +``->parent`` pointers):: + + ... ; Frame #0, some instructions + --- checkpoint #0 --- + 1 : r6 = 42 ; Frame #0 + --- checkpoint #1 --- + 2 : call foo() ; Frame #0 + ... ; Frame #1, instructions from foo() + --- checkpoint #2 --- + ... ; Frame #1, instructions from foo() + --- checkpoint #3 --- + exit ; Frame #1, return from foo() + 3 : r1 = r6 ; Frame #0 <- current state + + +-------------------------------+-------------------------------+ + | Frame #0 | Frame #1 | + Checkpoint +-------------------------------+-------------------------------+ + #0 | r0 | r1-r5 | r6-r9 | fp-8 ... | + +-------------------------------+ + ^ ^ ^ ^ + | | | | + Checkpoint +-------------------------------+ + #1 | r0 | r1-r5 | r6-r9 | fp-8 ... | + +-------------------------------+ + ^ ^ ^ + |_______|_______|_______________ + | | | + nil nil | | | nil nil + | | | | | | | + Checkpoint +-------------------------------+-------------------------------+ + #2 | r0 | r1-r5 | r6-r9 | fp-8 ... | r0 | r1-r5 | r6-r9 | fp-8 ... | + +-------------------------------+-------------------------------+ + ^ ^ ^ ^ ^ + nil nil | | | | | + | | | | | | | + Checkpoint +-------------------------------+-------------------------------+ + #3 | r0 | r1-r5 | r6-r9 | fp-8 ... | r0 | r1-r5 | r6-r9 | fp-8 ... | + +-------------------------------+-------------------------------+ + ^ ^ + nil nil | | + | | | | + Current +-------------------------------+ + state | r0 | r1-r5 | r6-r9 | fp-8 ... | + +-------------------------------+ + \ + r6 read mark is propagated via these links + all the way up to checkpoint #1. + The checkpoint #1 contains a write mark for r6 + because of instruction (1), thus read propagation + does not reach checkpoint #0 (see section below). + +Liveness marks tracking +~~~~~~~~~~~~~~~~~~~~~~~ + +For each processed instruction, the verifier tracks read and written registers +and stack slots. The main idea of the algorithm is that read marks propagate +back along the state parentage chain until they hit a write mark, which 'screens +off' earlier states from the read. The information about reads is propagated by +function ``mark_reg_read()`` which could be summarized as follows:: + + mark_reg_read(struct bpf_reg_state *state, ...): + parent = state->parent + while parent: + if state->live & REG_LIVE_WRITTEN: + break + if parent->live & REG_LIVE_READ64: + break + parent->live |= REG_LIVE_READ64 + state = parent + parent = state->parent + +Notes: + +* The read marks are applied to the **parent** state while write marks are + applied to the **current** state. The write mark on a register or stack slot + means that it is updated by some instruction in the straight-line code leading + from the parent state to the current state. + +* Details about REG_LIVE_READ32 are omitted. + +* Function ``propagate_liveness()`` (see section :ref:`read_marks_for_cache_hits`) + might override the first parent link. Please refer to the comments in the + ``propagate_liveness()`` and ``mark_reg_read()`` source code for further + details. + +Because stack writes could have different sizes ``REG_LIVE_WRITTEN`` marks are +applied conservatively: stack slots are marked as written only if write size +corresponds to the size of the register, e.g. see function ``save_register_state()``. + +Consider the following example:: + + 0: (*u64)(r10 - 8) = 0 ; define 8 bytes of fp-8 + --- checkpoint #0 --- + 1: (*u32)(r10 - 8) = 1 ; redefine lower 4 bytes + 2: r1 = (*u32)(r10 - 8) ; read lower 4 bytes defined at (1) + 3: r2 = (*u32)(r10 - 4) ; read upper 4 bytes defined at (0) + +As stated above, the write at (1) does not count as ``REG_LIVE_WRITTEN``. Should +it be otherwise, the algorithm above wouldn't be able to propagate the read mark +from (3) to checkpoint #0. + +Once the ``BPF_EXIT`` instruction is reached ``update_branch_counts()`` is +called to update the ``->branches`` counter for each verifier state in a chain +of parent verifier states. When the ``->branches`` counter reaches zero the +verifier state becomes a valid entry in a set of cached verifier states. + +Each entry of the verifier states cache is post-processed by a function +``clean_live_states()``. This function marks all registers and stack slots +without ``REG_LIVE_READ{32,64}`` marks as ``NOT_INIT`` or ``STACK_INVALID``. +Registers/stack slots marked in this way are ignored in function ``stacksafe()`` +called from ``states_equal()`` when a state cache entry is considered for +equivalence with a current state. + +Now it is possible to explain how the example from the beginning of the section +works:: + + 0: call bpf_get_prandom_u32() + 1: r1 = 0 + 2: if r0 == 0 goto +1 + 3: r0 = 1 + --- checkpoint[0] --- + 4: r0 = r1 + 5: exit + +* At instruction #2 branching point is reached and state ``{ r0 == 0, r1 == 0, pc == 4 }`` + is pushed to states processing queue (pc stands for program counter). + +* At instruction #4: + + * ``checkpoint[0]`` states cache entry is created: ``{ r0 == 1, r1 == 0, pc == 4 }``; + * ``checkpoint[0].r0`` is marked as written; + * ``checkpoint[0].r1`` is marked as read; + +* At instruction #5 exit is reached and ``checkpoint[0]`` can now be processed + by ``clean_live_states()``. After this processing ``checkpoint[0].r0`` has a + read mark and all other registers and stack slots are marked as ``NOT_INIT`` + or ``STACK_INVALID`` + +* The state ``{ r0 == 0, r1 == 0, pc == 4 }`` is popped from the states queue + and is compared against a cached state ``{ r1 == 0, pc == 4 }``, the states + are considered equivalent. + +.. _read_marks_for_cache_hits: + +Read marks propagation for cache hits +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Another point is the handling of read marks when a previously verified state is +found in the states cache. Upon cache hit verifier must behave in the same way +as if the current state was verified to the program exit. This means that all +read marks, present on registers and stack slots of the cached state, must be +propagated over the parentage chain of the current state. Example below shows +why this is important. Function ``propagate_liveness()`` handles this case. + +Consider the following state parentage chain (S is a starting state, A-E are +derived states, -> arrows show which state is derived from which):: + + r1 read + <------------- A[r1] == 0 + C[r1] == 0 + S ---> A ---> B ---> exit E[r1] == 1 + | + ` ---> C ---> D + | + ` ---> E ^ + |___ suppose all these + ^ states are at insn #Y + | + suppose all these + states are at insn #X + +* Chain of states ``S -> A -> B -> exit`` is verified first. + +* While ``B -> exit`` is verified, register ``r1`` is read and this read mark is + propagated up to state ``A``. + +* When chain of states ``C -> D`` is verified the state ``D`` turns out to be + equivalent to state ``B``. + +* The read mark for ``r1`` has to be propagated to state ``C``, otherwise state + ``C`` might get mistakenly marked as equivalent to state ``E`` even though + values for register ``r1`` differ between ``C`` and ``E``. + Understanding eBPF verifier messages ==================================== diff --git a/Documentation/conf.py b/Documentation/conf.py index d927737e3c10..8b4e5451a02d 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -116,6 +116,9 @@ if major >= 3: # include/linux/linkage.h: "asmlinkage", + + # include/linux/btf.h + "__bpf_kfunc", ] else: diff --git a/Documentation/devicetree/bindings/.gitignore b/Documentation/devicetree/bindings/.gitignore index a77719968a7e..51ddb26d93f0 100644 --- a/Documentation/devicetree/bindings/.gitignore +++ b/Documentation/devicetree/bindings/.gitignore @@ -2,3 +2,8 @@ *.example.dts /processed-schema*.yaml /processed-schema*.json + +# +# We don't want to ignore the following even if they are dot-files +# +!.yamllint diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml index 9f7d3e11aacb..8449e14af9f3 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.yaml @@ -108,7 +108,7 @@ properties: msi-controller: description: - Only present if the Message Based Interrupt functionnality is + Only present if the Message Based Interrupt functionality is being exposed by the HW, and the mbi-ranges property present. mbi-ranges: diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml index 1eb98c9a1a26..d3f45d29fa0a 100644 --- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml @@ -30,13 +30,17 @@ properties: - items: - enum: + - renesas,r8a779a0-canfd # R-Car V3U + - renesas,r8a779g0-canfd # R-Car V4H + - const: renesas,rcar-gen4-canfd # R-Car Gen4 + + - items: + - enum: - renesas,r9a07g043-canfd # RZ/G2UL and RZ/Five - renesas,r9a07g044-canfd # RZ/G2{L,LC} - renesas,r9a07g054-canfd # RZ/V2L - const: renesas,rzg2l-canfd # RZ/G2L family - - const: renesas,r8a779a0-canfd # R-Car V3U - reg: maxItems: 1 @@ -60,7 +64,7 @@ properties: $ref: /schemas/types.yaml#/definitions/flag description: The controller can operate in either CAN FD only mode (default) or - Classical CAN only mode. The mode is global to both the channels. + Classical CAN only mode. The mode is global to all channels. Specify this property to put the controller in Classical CAN only mode. assigned-clocks: @@ -80,6 +84,10 @@ patternProperties: The controller supports multiple channels and each is represented as a child node. Each channel can be enabled/disabled individually. + properties: + phys: + maxItems: 1 + additionalProperties: false required: @@ -159,7 +167,7 @@ allOf: properties: compatible: contains: - const: renesas,r8a779a0-canfd + const: renesas,rcar-gen4-canfd then: patternProperties: "^channel[2-7]$": false diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt index df9e844dd6bc..2681168777a1 100644 --- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -158,6 +158,7 @@ KSZ9031: no link will be established. KSZ9131: +LAN8841: All skew control options are specified in picoseconds. The increment step is 100ps. Unlike KSZ9031, the values represent picoseccond delays. diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml index 0a7aa29563c1..21c8ea08ff0a 100644 --- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml @@ -40,6 +40,8 @@ properties: description: Indicates that the setting of RTC time is allowed by the host CPU. + wakeup-source: true + required: - compatible - reg diff --git a/Documentation/isdn/interface_capi.rst b/Documentation/isdn/interface_capi.rst index fe2421444b76..4d63b34b35cf 100644 --- a/Documentation/isdn/interface_capi.rst +++ b/Documentation/isdn/interface_capi.rst @@ -323,7 +323,7 @@ If the lowest bit of showcapimsgs is set, kernelcapi logs controller and application up and down events. In addition, every registered CAPI controller has an associated traceflag -parameter controlling how CAPI messages sent from and to tha controller are +parameter controlling how CAPI messages sent from and to the controller are logged. The traceflag parameter is initialized with the value of the showcapimsgs parameter when the controller is registered, but can later be changed via the MANUFACTURER_REQ command KCAPI_CMD_TRACE. diff --git a/Documentation/isdn/m_isdn.rst b/Documentation/isdn/m_isdn.rst index 9957de349e69..5847a164287e 100644 --- a/Documentation/isdn/m_isdn.rst +++ b/Documentation/isdn/m_isdn.rst @@ -3,7 +3,7 @@ mISDN Driver ============ mISDN is a new modular ISDN driver, in the long term it should replace -the old I4L driver architecture for passiv ISDN cards. +the old I4L driver architecture for passive ISDN cards. It was designed to allow a broad range of applications and interfaces but only have the basic function in kernel, the interface to the user space is based on sockets with a own address family AF_ISDN. diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml new file mode 100644 index 000000000000..b4dcdae54ffd --- /dev/null +++ b/Documentation/netlink/specs/netdev.yaml @@ -0,0 +1,100 @@ +name: netdev + +doc: + netdev configuration over generic netlink. + +definitions: + - + type: flags + name: xdp-act + entries: + - + name: basic + doc: + XDP feautues set supported by all drivers + (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + - + name: redirect + doc: + The netdev supports XDP_REDIRECT + - + name: ndo-xmit + doc: + This feature informs if netdev implements ndo_xdp_xmit callback. + - + name: xsk-zerocopy + doc: + This feature informs if netdev supports AF_XDP in zero copy mode. + - + name: hw-offload + doc: + This feature informs if netdev supports XDP hw oflloading. + - + name: rx-sg + doc: + This feature informs if netdev implements non-linear XDP buffer + support in the driver napi callback. + - + name: ndo-xmit-sg + doc: + This feature informs if netdev implements non-linear XDP buffer + support in ndo_xdp_xmit callback. + +attribute-sets: + - + name: dev + attributes: + - + name: ifindex + doc: netdev ifindex + type: u32 + value: 1 + checks: + min: 1 + - + name: pad + type: pad + - + name: xdp-features + doc: Bitmask of enabled xdp-features. + type: u64 + enum: xdp-act + enum-as-flags: true + +operations: + list: + - + name: dev-get + doc: Get / dump information about a netdev. + value: 1 + attribute-set: dev + do: + request: + attributes: + - ifindex + reply: &dev-all + attributes: + - ifindex + - xdp-features + dump: + reply: *dev-all + - + name: dev-add-ntf + doc: Notification about device appearing. + notify: dev-get + mcgrp: mgmt + - + name: dev-del-ntf + doc: Notification about device disappearing. + notify: dev-get + mcgrp: mgmt + - + name: dev-change-ntf + doc: Notification about device configuration being changed. + notify: dev-get + mcgrp: mgmt + +mcast-groups: + list: + - + name: mgmt diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst index 5196905582c5..392969ac88ad 100644 --- a/Documentation/networking/device_drivers/ethernet/index.rst +++ b/Documentation/networking/device_drivers/ethernet/index.rst @@ -39,7 +39,7 @@ Contents: intel/ice marvell/octeontx2 marvell/octeon_ep - mellanox/mlx5 + mellanox/mlx5/index microsoft/netvsc neterion/s2io netronome/nfp diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst deleted file mode 100644 index 6969652f593c..000000000000 --- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5.rst +++ /dev/null @@ -1,746 +0,0 @@ -.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB - -================================================= -Mellanox ConnectX(R) mlx5 core VPI Network Driver -================================================= - -Copyright (c) 2019, Mellanox Technologies LTD. - -Contents -======== - -- `Enabling the driver and kconfig options`_ -- `Devlink info`_ -- `Devlink parameters`_ -- `Bridge offload`_ -- `mlx5 subfunction`_ -- `mlx5 function attributes`_ -- `Devlink health reporters`_ -- `mlx5 tracepoints`_ - -Enabling the driver and kconfig options -======================================= - -| mlx5 core is modular and most of the major mlx5 core driver features can be selected (compiled in/out) -| at build time via kernel Kconfig flags. -| Basic features, ethernet net device rx/tx offloads and XDP, are available with the most basic flags -| CONFIG_MLX5_CORE=y/m and CONFIG_MLX5_CORE_EN=y. -| For the list of advanced features, please see below. - -**CONFIG_MLX5_CORE=(y/m/n)** (module mlx5_core.ko) - -| The driver can be enabled by choosing CONFIG_MLX5_CORE=y/m in kernel config. -| This will provide mlx5 core driver for mlx5 ulps to interface with (mlx5e, mlx5_ib). - - -**CONFIG_MLX5_CORE_EN=(y/n)** - -| Choosing this option will allow basic ethernet netdevice support with all of the standard rx/tx offloads. -| mlx5e is the mlx5 ulp driver which provides netdevice kernel interface, when chosen, mlx5e will be -| built-in into mlx5_core.ko. - - -**CONFIG_MLX5_EN_ARFS=(y/n)** - -| Enables Hardware-accelerated receive flow steering (arfs) support, and ntuple filtering. -| https://community.mellanox.com/s/article/howto-configure-arfs-on-connectx-4 - - -**CONFIG_MLX5_EN_RXNFC=(y/n)** - -| Enables ethtool receive network flow classification, which allows user defined -| flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc API. - - -**CONFIG_MLX5_CORE_EN_DCB=(y/n)**: - -| Enables `Data Center Bridging (DCB) Support <https://community.mellanox.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_. - - -**CONFIG_MLX5_MPFS=(y/n)** - -| Ethernet Multi-Physical Function Switch (MPFS) support in ConnectX NIC. -| MPFs is required for when `Multi-Host <http://www.mellanox.com/page/multihost>`_ configuration is enabled to allow passing -| user configured unicast MAC addresses to the requesting PF. - - -**CONFIG_MLX5_ESWITCH=(y/n)** - -| Ethernet SRIOV E-Switch support in ConnectX NIC. E-Switch provides internal SRIOV packet steering -| and switching for the enabled VFs and PF in two available modes: -| 1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://community.mellanox.com/s/article/howto-configure-sr-iov-for-connectx-4-connectx-5-with-kvm--ethernet-x>`_. -| 2) `Switchdev mode (eswitch offloads) <https://www.mellanox.com/related-docs/prod_software/ASAP2_Hardware_Offloading_for_vSwitches_User_Manual_v4.4.pdf>`_. - - -**CONFIG_MLX5_CORE_IPOIB=(y/n)** - -| IPoIB offloads & acceleration support. -| Requires CONFIG_MLX5_CORE_EN to provide an accelerated interface for the rdma -| IPoIB ulp netdevice. - - -**CONFIG_MLX5_FPGA=(y/n)** - -| Build support for the Innova family of network cards by Mellanox Technologies. -| Innova network cards are comprised of a ConnectX chip and an FPGA chip on one board. -| If you select this option, the mlx5_core driver will include the Innova FPGA core and allow -| building sandbox-specific client drivers. - - -**CONFIG_MLX5_EN_IPSEC=(y/n)** - -| Enables `IPSec XFRM cryptography-offload acceleration <http://www.mellanox.com/related-docs/prod_software/Mellanox_Innova_IPsec_Ethernet_Adapter_Card_User_Manual.pdf>`_. - -**CONFIG_MLX5_EN_TLS=(y/n)** - -| TLS cryptography-offload acceleration. - - -**CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko) - -| Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support. - -**CONFIG_MLX5_SF=(y/n)** - -| Build support for subfunction. -| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option -| will enable support for creating subfunction devices. - -**External options** ( Choose if the corresponding mlx5 feature is required ) - -- CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled -- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. -- CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). - -Devlink info -============ - -The devlink info reports the running and stored firmware versions on device. -It also prints the device PSID which represents the HCA board type ID. - -User command example:: - - $ devlink dev info pci/0000:00:06.0 - pci/0000:00:06.0: - driver mlx5_core - versions: - fixed: - fw.psid MT_0000000009 - running: - fw.version 16.26.0100 - stored: - fw.version 16.26.0100 - -Devlink parameters -================== - -flow_steering_mode: Device flow steering mode ---------------------------------------------- -The flow steering mode parameter controls the flow steering mode of the driver. -Two modes are supported: -1. 'dmfs' - Device managed flow steering. -2. 'smfs' - Software/Driver managed flow steering. - -In DMFS mode, the HW steering entities are created and managed through the -Firmware. -In SMFS mode, the HW steering entities are created and managed though by -the driver directly into hardware without firmware intervention. - -SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. - -User command examples: - -- Set SMFS flow steering mode:: - - $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime - -- Read device flow steering mode:: - - $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode - pci/0000:06:00.0: - name flow_steering_mode type driver-specific - values: - cmode runtime value smfs - -enable_roce: RoCE enablement state ----------------------------------- -RoCE enablement state controls driver support for RoCE traffic. -When RoCE is disabled, there is no gid table, only raw ethernet QPs are supported and traffic on the well-known UDP RoCE port is handled as raw ethernet traffic. - -To change RoCE enablement state, a user must change the driverinit cmode value and run devlink reload. - -User command examples: - -- Disable RoCE:: - - $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit - $ devlink dev reload pci/0000:06:00.0 - -- Read RoCE enablement state:: - - $ devlink dev param show pci/0000:06:00.0 name enable_roce - pci/0000:06:00.0: - name enable_roce type generic - values: - cmode driverinit value true - -esw_port_metadata: Eswitch port metadata state ----------------------------------------------- -When applicable, disabling eswitch metadata can increase packet rate -up to 20% depending on the use case and packet sizes. - -Eswitch port metadata state controls whether to internally tag packets with -metadata. Metadata tagging must be enabled for multi-port RoCE, failover -between representors and stacked devices. -By default metadata is enabled on the supported devices in E-switch. -Metadata is applicable only for E-switch in switchdev mode and -users may disable it when NONE of the below use cases will be in use: -1. HCA is in Dual/multi-port RoCE mode. -2. VF/SF representor bonding (Usually used for Live migration) -3. Stacked devices - -When metadata is disabled, the above use cases will fail to initialize if -users try to enable them. - -- Show eswitch port metadata:: - - $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata - pci/0000:06:00.0: - name esw_port_metadata type driver-specific - values: - cmode runtime value true - -- Disable eswitch port metadata:: - - $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime - -- Change eswitch mode to switchdev mode where after choosing the metadata value:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -Bridge offload -============== -The mlx5 driver implements support for offloading bridge rules when in switchdev -mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev -representor is attached to bridge. - -- Change device to switchdev mode:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1':: - - $ ip link set enp8s0f0 master bridge1 - -VLANs ------ -Following bridge VLAN functions are supported by mlx5: - -- VLAN filtering (including multiple VLANs per port):: - - $ ip link set bridge1 type bridge vlan_filtering 1 - $ bridge vlan add dev enp8s0f0 vid 2-3 - -- VLAN push on bridge ingress:: - - $ bridge vlan add dev enp8s0f0 vid 3 pvid - -- VLAN pop on bridge egress:: - - $ bridge vlan add dev enp8s0f0 vid 3 untagged - -mlx5 subfunction -================ -mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. - -A subfunction has its own function capabilities and its own resources. This -means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These -queues are neither shared nor stolen from the parent PCI function. - -When a subfunction is RDMA capable, it has its own QP1, GID table, and RDMA -resources neither shared nor stolen from the parent PCI function. - -A subfunction has a dedicated window in PCI BAR space that is not shared -with the other subfunctions or the parent PCI function. This ensures that all -devices (netdev, rdma, vdpa, etc.) of the subfunction accesses only assigned -PCI BAR space. - -A subfunction supports eswitch representation through which it supports tc -offloads. The user configures eswitch to send/receive packets from/to -the subfunction port. - -Subfunctions share PCI level resources such as PCI MSI-X IRQs with -other subfunctions and/or with its parent PCI function. - -Example mlx5 software, system, and device view:: - - _______ - | admin | - | user |---------- - |_______| | - | | - ____|____ __|______ _________________ - | | | | | | - | devlink | | tc tool | | user | - | tool | |_________| | applications | - |_________| | |_________________| - | | | | - | | | | Userspace - +---------|-------------|-------------------|----------|--------------------+ - | | +----------+ +----------+ Kernel - | | | netdev | | rdma dev | - | | +----------+ +----------+ - (devlink port add/del | ^ ^ - port function set) | | | - | | +---------------| - _____|___ | | _______|_______ - | | | | | mlx5 class | - | devlink | +------------+ | | drivers | - | kernel | | rep netdev | | |(mlx5_core,ib) | - |_________| +------------+ | |_______________| - | | | ^ - (devlink ops) | | (probe/remove) - _________|________ | | ____|________ - | subfunction | | +---------------+ | subfunction | - | management driver|----- | subfunction |---| driver | - | (mlx5_core) | | auxiliary dev | | (mlx5_core) | - |__________________| +---------------+ |_____________| - | ^ - (sf add/del, vhca events) | - | (device add/del) - _____|____ ____|________ - | | | subfunction | - | PCI NIC |--- activate/deactivate events--->| host driver | - |__________| | (mlx5_core) | - |_____________| - -Subfunction is created using devlink port interface. - -- Change device to switchdev mode:: - - $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev - -- Add a devlink port of subfunction flavour:: - - $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 - pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:00:00 state inactive opstate detached - -- Show a devlink port of the subfunction:: - - $ devlink port show pci/0000:06:00.0/32768 - pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 - function: - hw_addr 00:00:00:00:00:00 state inactive opstate detached - -- Delete a devlink port of subfunction after use:: - - $ devlink port del pci/0000:06:00.0/32768 - -mlx5 function attributes -======================== -The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in -a unified way for SmartNIC and non-SmartNIC. - -This is supported only when the eswitch mode is set to switchdev. Port function -configuration of the PCI VF/SF is supported through devlink eswitch port. - -Port function attributes should be set before PCI VF/SF is enumerated by the -driver. - -MAC address setup ------------------ -mlx5 driver support devlink port function attr mechanism to setup MAC -address. (refer to Documentation/networking/devlink/devlink-port.rst) - -RoCE capability setup ---------------------- -Not all mlx5 PCI devices/SFs require RoCE capability. - -When RoCE capability is disabled, it saves 1 Mbytes worth of system memory per -PCI devices/SF. - -mlx5 driver support devlink port function attr mechanism to setup RoCE -capability. (refer to Documentation/networking/devlink/devlink-port.rst) - -migratable capability setup ---------------------------- -User who wants mlx5 PCI VFs to be able to perform live migration need to -explicitly enable the VF migratable capability. - -mlx5 driver support devlink port function attr mechanism to setup migratable -capability. (refer to Documentation/networking/devlink/devlink-port.rst) - -SF state setup --------------- -To use the SF, the user must activate the SF using the SF function state -attribute. - -- Get the state of the SF identified by its unique devlink port index:: - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state inactive opstate detached - -- Activate the function and verify its state is active:: - - $ devlink port function set ens2f0npf0sf88 state active - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state active opstate detached - -Upon function activation, the PF driver instance gets the event from the device -that a particular SF was activated. It's the cue to put the device on bus, probe -it and instantiate the devlink instance and class specific auxiliary devices -for it. - -- Show the auxiliary device and port of the subfunction:: - - $ devlink dev show - devlink dev show auxiliary/mlx5_core.sf.4 - - $ devlink port show auxiliary/mlx5_core.sf.4/1 - auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false - - $ rdma link show mlx5_0/1 - link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 - - $ rdma dev show - 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 - 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 - -- Subfunction auxiliary device and class device hierarchy:: - - mlx5_core.sf.4 - (subfunction auxiliary device) - /\ - / \ - / \ - / \ - / \ - mlx5_core.eth.4 mlx5_core.rdma.4 - (sf eth aux dev) (sf rdma aux dev) - | | - | | - p0sf88 mlx5_0 - (sf netdev) (sf rdma device) - -Additionally, the SF port also gets the event when the driver attaches to the -auxiliary device of the subfunction. This results in changing the operational -state of the function. This provides visibility to the user to decide when is it -safe to delete the SF port for graceful termination of the subfunction. - -- Show the SF port operational state:: - - $ devlink port show ens2f0npf0sf88 - pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false - function: - hw_addr 00:00:00:00:88:88 state active opstate attached - -Devlink health reporters -======================== - -tx reporter ------------ -The tx reporter is responsible for reporting and recovering of the following two error scenarios: - -- tx timeout - Report on kernel tx timeout detection. - Recover by searching lost interrupts. -- tx error completion - Report on error tx completion. - Recover by flushing the tx queue and reset it. - -tx reporter also support on demand diagnose callback, on which it provides -real time information of its send queues status. - -User commands examples: - -- Diagnose send queues status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter tx - -NOTE: This command has valid output only when interface is up, otherwise the command has empty output. - -- Show number of tx errors indicated, number of recover flows ended successfully, - is autorecover enabled and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter tx - -rx reporter ------------ -The rx reporter is responsible for reporting and recovering of the following two error scenarios: - -- rx queues' initialization (population) timeout - Population of rx queues' descriptors on ring initialization is done - in napi context via triggering an irq. In case of a failure to get - the minimum amount of descriptors, a timeout would occur, and - descriptors could be recovered by polling the EQ (Event Queue). -- rx completions with errors (reported by HW on interrupt context) - Report on rx completion error. - Recover (if needed) by flushing the related queue and reset it. - -rx reporter also supports on demand diagnose callback, on which it -provides real time information of its receive queues' status. - -- Diagnose rx queues' status and corresponding completion queue:: - - $ devlink health diagnose pci/0000:82:00.0 reporter rx - -NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output. - -- Show number of rx errors indicated, number of recover flows ended successfully, - is autorecover enabled, and graceful period from last recover:: - - $ devlink health show pci/0000:82:00.0 reporter rx - -fw reporter ------------ -The fw reporter implements `diagnose` and `dump` callbacks. -It follows symptoms of fw error such as fw syndrome by triggering -fw core dump and storing it into the dump buffer. -The fw reporter diagnose command can be triggered any time by the user to check -current fw status. - -User commands examples: - -- Check fw heath status:: - - $ devlink health diagnose pci/0000:82:00.0 reporter fw - -- Read FW core dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.0 reporter fw - -NOTE: This command can run only on the PF which has fw tracer ownership, -running it on other PF or any VF will return "Operation not permitted". - -fw fatal reporter ------------------ -The fw fatal reporter implements `dump` and `recover` callbacks. -It follows fatal errors indications by CR-space dump and recover flow. -The CR-space dump uses vsc interface which is valid even if the FW command -interface is not functional, which is the case in most FW fatal errors. -The recover function runs recover flow which reloads the driver and triggers fw -reset if needed. -On firmware error, the health buffer is dumped into the dmesg. The log -level is derived from the error's severity (given in health buffer). - -User commands examples: - -- Run fw recover flow manually:: - - $ devlink health recover pci/0000:82:00.0 reporter fw_fatal - -- Read FW CR-space dump if already stored or trigger new one:: - - $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal - -NOTE: This command can run only on PF. - -mlx5 tracepoints -================ - -mlx5 driver provides internal tracepoints for tracking and debugging using -kernel tracepoints interfaces (refer to Documentation/trace/ftrace.rst). - -For the list of support mlx5 events, check `/sys/kernel/debug/tracing/events/mlx5/`. - -tc and eswitch offloads tracepoints: - -- mlx5e_configure_flower: trace flower filter actions and cookies offloaded to mlx5:: - - $ echo mlx5:mlx5e_configure_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6535 [019] ...1 2672.404466: mlx5e_configure_flower: cookie=0000000067874a55 actions= REDIRECT - -- mlx5e_delete_flower: trace flower filter actions and cookies deleted from mlx5:: - - $ echo mlx5:mlx5e_delete_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6569 [010] .N.1 2686.379075: mlx5e_delete_flower: cookie=0000000067874a55 actions= NULL - -- mlx5e_stats_flower: trace flower stats request:: - - $ echo mlx5:mlx5e_stats_flower >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - tc-6546 [010] ...1 2679.704889: mlx5e_stats_flower: cookie=0000000060eb3d6a bytes=0 packets=0 lastused=4295560217 - -- mlx5e_tc_update_neigh_used_value: trace tunnel rule neigh update value offloaded to mlx5:: - - $ echo mlx5:mlx5e_tc_update_neigh_used_value >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u48:4-8806 [009] ...1 55117.882428: mlx5e_tc_update_neigh_used_value: netdev: ens1f0 IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_used=1 - -- mlx5e_rep_neigh_update: trace neigh update tasks scheduled due to neigh state change events:: - - $ echo mlx5:mlx5e_rep_neigh_update >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u48:7-2221 [009] ...1 1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1 - -Bridge offloads tracepoints: - -- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u20:9-2217 [003] ...1 318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0 - -- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2581 [005] ...1 318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16 - -- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in - mlx5:: - - $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u20:8-3849 [003] ...1 466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0 - -- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5 - representor:: - - $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2560 [007] ...1 318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6 - -- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5 - representor:: - - $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - bridge-2582 [007] ...1 318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8 - -- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper - device:: - - $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-2560 [007] ...1 318.458915: mlx5_esw_bridge_vport_init: vport_num=1 - -- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper - device:: - - $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event - $ cat /sys/kernel/debug/tracing/trace - ... - ip-5387 [000] ...1 573713: mlx5_esw_bridge_vport_cleanup: vport_num=1 - -Eswitch QoS tracepoints: - -- mlx5_esw_vport_qos_create: trace creation of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_create >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-23496 [018] .... 73136.838831: mlx5_esw_vport_qos_create: (0000:82:00.0) vport=2 tsar_ix=4 bw_share=0, max_rate=0 group=000000007b576bb3 - -- mlx5_esw_vport_qos_config: trace configuration of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_config >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-26548 [023] .... 75754.223823: mlx5_esw_vport_qos_config: (0000:82:00.0) vport=1 tsar_ix=3 bw_share=34, max_rate=10000 group=000000007b576bb3 - -- mlx5_esw_vport_qos_destroy: trace deletion of transmit scheduler arbiter for vport:: - - $ echo mlx5:mlx5_esw_vport_qos_destroy >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27418 [004] .... 76546.680901: mlx5_esw_vport_qos_destroy: (0000:82:00.0) vport=1 tsar_ix=3 - -- mlx5_esw_group_qos_create: trace creation of transmit scheduler arbiter for rate group:: - - $ echo mlx5:mlx5_esw_group_qos_create >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-26578 [008] .... 75776.022112: mlx5_esw_group_qos_create: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 - -- mlx5_esw_group_qos_config: trace configuration of transmit scheduler arbiter for rate group:: - - $ echo mlx5:mlx5_esw_group_qos_config >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27303 [020] .... 76461.455356: mlx5_esw_group_qos_config: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 bw_share=100 max_rate=20000 - -- mlx5_esw_group_qos_destroy: trace deletion of transmit scheduler arbiter for group:: - - $ echo mlx5:mlx5_esw_group_qos_destroy >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - <...>-27418 [006] .... 76547.187258: mlx5_esw_group_qos_destroy: (0000:82:00.0) group=000000007b576bb3 tsar_ix=1 - -SF tracepoints: - -- mlx5_sf_add: trace addition of the SF port:: - - $ echo mlx5:mlx5_sf_add >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9363 [031] ..... 24610.188722: mlx5_sf_add: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 sfnum=88 - -- mlx5_sf_free: trace freeing of the SF port:: - - $ echo mlx5:mlx5_sf_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9830 [038] ..... 26300.404749: mlx5_sf_free: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 - -- mlx5_sf_hwc_alloc: trace allocating of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_alloc >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9775 [031] ..... 26296.385259: mlx5_sf_hwc_alloc: (0000:06:00.0) controller=0 hw_id=0x8000 sfnum=88 - -- mlx5_sf_hwc_free: trace freeing of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [046] ..... 24625.365771: mlx5_sf_hwc_free: (0000:06:00.0) hw_id=0x8000 - -- mlx5_sf_hwc_deferred_free : trace deferred freeing of the hardware SF context:: - - $ echo mlx5:mlx5_sf_hwc_deferred_free >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - devlink-9519 [046] ..... 24624.400271: mlx5_sf_hwc_deferred_free: (0000:06:00.0) hw_id=0x8000 - -- mlx5_sf_vhca_event: trace SF vhca event and state:: - - $ echo mlx5:mlx5_sf_vhca_event >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [046] ..... 24625.365525: mlx5_sf_vhca_event: (0000:06:00.0) hw_id=0x8000 sfnum=88 vhca_state=1 - -- mlx5_sf_dev_add : trace SF device add event:: - - $ echo mlx5:mlx5_sf_dev_add>> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [000] ..... 24616.524495: mlx5_sf_dev_add: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 - -- mlx5_sf_dev_del : trace SF device delete event:: - - $ echo mlx5:mlx5_sf_dev_del >> /sys/kernel/debug/tracing/set_event - $ cat /sys/kernel/debug/tracing/trace - ... - kworker/u128:3-9093 [044] ..... 24624.400749: mlx5_sf_dev_del: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst new file mode 100644 index 000000000000..4cd8e869762b --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst @@ -0,0 +1,1302 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +================ +Ethtool counters +================ + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents +======== + +- `Overview`_ +- `Groups`_ +- `Types`_ +- `Descriptions`_ + +Overview +======== + +There are several counter groups based on where the counter is being counted. In +addition, each group of counters may have different counter types. + +These counter groups are based on which component in a networking setup, +illustrated below, that they describe:: + + ---------------------------------------- + | | + ---------------------------------------- ---------------------------------------- | + | Hypervisor | | VM | | + | | | | | + | ------------------- --------------- | | ------------------- --------------- | | + | | Ethernet driver | | RDMA driver | | | | Ethernet driver | | RDMA driver | | | + | ------------------- --------------- | | ------------------- --------------- | | + | | | | | | | | | + | ------------------- | | ------------------- | | + | | | | | |-- + ---------------------------------------- ---------------------------------------- + | | + ------------- ----------------------------- + | | + ------ ------ ------ ------ ------ ------ ------ + -----| PF |----------------------| VF |-| VF |-| VF |----- --| PF |--- --| PF |--- --| PF |--- + | ------ ------ ------ ------ | | ------ | | ------ | | ------ | + | | | | | | | | + | | | | | | | | + | | | | | | | | + | eSwitch | | eSwitch | | eSwitch | | eSwitch | + ---------------------------------------------------------- ----------- ----------- ----------- + ------------------------------------------------------------------------------- + | | + | | + | Uplink (no counters) | + ------------------------------------------------------------------------------- + --------------------------------------------------------------- + | | + | | + | MPFS (no counters) | + --------------------------------------------------------------- + | + | + | Port + +Groups +====== + +Ring + Software counters populated by the driver stack. + +Netdev + An aggregation of software ring counters. + +vPort counters + Traffic counters and drops due to steering or no buffers. May indicate issues + with NIC. These counters include Ethernet traffic counters (including Raw + Ethernet) and RDMA/RoCE traffic counters. + +Physical port counters + Counters that collect statistics about the PFs and VFs. May indicate issues + with NIC, link, or network. This measuring point holds information on + standardized counters like IEEE 802.3, RFC2863, RFC 2819, RFC 3635 and + additional counters like flow control, FEC and more. Physical port counters + are not exposed to virtual machines. + +Priority Port Counters + A set of the physical port counters, per priority per port. + +Types +===== + +Counters are divided into three types. + +Traffic Informative Counters + Counters which count traffic. These counters can be used for load estimation + or for general debug. + +Traffic Acceleration Counters + Counters which count traffic that was accelerated by Mellanox driver or by + hardware. The counters are an additional layer to the informative counter set, + and the same traffic is counted in both informative and acceleration counters. + +.. [#accel] Traffic acceleration counter. + +Error Counters + Increment of these counters might indicate a problem. Each of these counters + has an explanation and correction action. + +Statistic can be fetched via the `ip link` or `ethtool` commands. `ethtool` +provides more detailed information.:: + + ip –s link show <if-name> + ethtool -S <if-name> + +Descriptions +============ + +XSK, PTP, and QoS counters that are similar to counters defined previously will +not be separately listed. For example, `ptp_tx[i]_packets` will not be +explicitly documented since `tx[i]_packets` describes the behavior of both +counters, except `ptp_tx[i]_packets` is only counted when precision time +protocol is used. + +Ring / Netdev Counter +---------------------------- +The following counters are available per ring or software port. + +These counters provide information on the amount of traffic that was accelerated +by the NIC. The counters are counting the accelerated traffic in addition to the +standard counters which counts it (i.e. accelerated traffic is counted twice). + +The counter names in the table below refers to both ring and port counters. The +notation for ring counters includes the [i] index without the braces. The +notation for port counters doesn't include the [i]. A counter name +`rx[i]_packets` will be printed as `rx0_packets` for ring 0 and `rx_packets` for +the software port. + +.. flat-table:: Ring / Software Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx[i]_packets` + - The number of packets received on ring i. + - Informative + + * - `rx[i]_bytes` + - The number of bytes received on ring i. + - Informative + + * - `tx[i]_packets` + - The number of packets transmitted on ring i. + - Informative + + * - `tx[i]_bytes` + - The number of bytes transmitted on ring i. + - Informative + + * - `tx[i]_recover` + - The number of times the SQ was recovered. + - Error + + * - `tx[i]_cqes` + - Number of CQEs events on SQ issued on ring i. + - Informative + + * - `tx[i]_cqe_err` + - The number of error CQEs encountered on the SQ for ring i. + - Error + + * - `tx[i]_tso_packets` + - The number of TSO packets transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_bytes` + - The number of TSO bytes transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_inner_packets` + - The number of TSO packets which are indicated to be carry internal + encapsulation transmitted on ring i [#accel]_. + - Acceleration + + * - `tx[i]_tso_inner_bytes` + - The number of TSO bytes which are indicated to be carry internal + encapsulation transmitted on ring i [#accel]_. + - Acceleration + + * - `rx[i]_gro_packets` + - Number of received packets processed using hardware-accelerated GRO. The + number of hardware GRO offloaded packets received on ring i. + - Acceleration + + * - `rx[i]_gro_bytes` + - Number of received bytes processed using hardware-accelerated GRO. The + number of hardware GRO offloaded bytes received on ring i. + - Acceleration + + * - `rx[i]_gro_skbs` + - The number of receive SKBs constructed while performing + hardware-accelerated GRO. + - Informative + + * - `rx[i]_gro_match_packets` + - Number of received packets processed using hardware-accelerated GRO that + met the flow table match criteria. + - Informative + + * - `rx[i]_gro_large_hds` + - Number of receive packets using hardware-accelerated GRO that have large + headers that require additional memory to be allocated. + - Informative + + * - `rx[i]_lro_packets` + - The number of LRO packets received on ring i [#accel]_. + - Acceleration + + * - `rx[i]_lro_bytes` + - The number of LRO bytes received on ring i [#accel]_. + - Acceleration + + * - `rx[i]_ecn_mark` + - The number of received packets where the ECN mark was turned on. + - Informative + + * - `rx_oversize_pkts_buffer` + - The number of dropped received packets due to length which arrived to RQ + and exceed software buffer size allocated by the device for incoming + traffic. It might imply that the device MTU is larger than the software + buffers size. + - Error + + * - `rx_oversize_pkts_sw_drop` + - Number of received packets dropped in software because the CQE data is + larger than the MTU size. + - Error + + * - `rx[i]_csum_unnecessary` + - Packets received with a `CHECKSUM_UNNECESSARY` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_unnecessary_inner` + - Packets received with inner encapsulation with a `CHECKSUM_UNNECESSARY` + on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_none` + - Packets received with a `CHECKSUM_NONE` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_complete` + - Packets received with a `CHECKSUM_COMPLETE` on ring i [#accel]_. + - Acceleration + + * - `rx[i]_csum_complete_tail` + - Number of received packets that had checksum calculation computed, + potentially needed padding, and were able to do so with + `CHECKSUM_PARTIAL`. + - Informative + + * - `rx[i]_csum_complete_tail_slow` + - Number of received packets that need padding larger than eight bytes for + the checksum. + - Informative + + * - `tx[i]_csum_partial` + - Packets transmitted with a `CHECKSUM_PARTIAL` on ring i [#accel]_. + - Acceleration + + * - `tx[i]_csum_partial_inner` + - Packets transmitted with inner encapsulation with a `CHECKSUM_PARTIAL` on + ring i [#accel]_. + - Acceleration + + * - `tx[i]_csum_none` + - Packets transmitted with no hardware checksum acceleration on ring i. + - Informative + + * - `tx[i]_stopped` / `tx_queue_stopped` [#ring_global]_ + - Events where SQ was full on ring i. If this counter is increased, check + the amount of buffers allocated for transmission. + - Informative + + * - `tx[i]_wake` / `tx_queue_wake` [#ring_global]_ + - Events where SQ was full and has become not full on ring i. + - Informative + + * - `tx[i]_dropped` / `tx_queue_dropped` [#ring_global]_ + - Packets transmitted that were dropped due to DMA mapping failure on + ring i. If this counter is increased, check the amount of buffers + allocated for transmission. + - Error + + * - `tx[i]_nop` + - The number of nop WQEs (empty WQEs) inserted to the SQ (related to + ring i) due to the reach of the end of the cyclic buffer. When reaching + near to the end of cyclic buffer the driver may add those empty WQEs to + avoid handling a state the a WQE start in the end of the queue and ends + in the beginning of the queue. This is a normal condition. + - Informative + + * - `tx[i]_added_vlan_packets` + - The number of packets sent where vlan tag insertion was offloaded to the + hardware. + - Acceleration + + * - `rx[i]_removed_vlan_packets` + - The number of packets received where vlan tag stripping was offloaded to + the hardware. + - Acceleration + + * - `rx[i]_wqe_err` + - The number of wrong opcodes received on ring i. + - Error + + * - `rx[i]_mpwqe_frag` + - The number of WQEs that failed to allocate compound page and hence + fragmented MPWQE’s (Multi Packet WQEs) were used on ring i. If this + counter raise, it may suggest that there is no enough memory for large + pages, the driver allocated fragmented pages. This is not abnormal + condition. + - Informative + + * - `rx[i]_mpwqe_filler_cqes` + - The number of filler CQEs events that were issued on ring i. + - Informative + + * - `rx[i]_mpwqe_filler_strides` + - The number of strides consumed by filler CQEs on ring i. + - Informative + + * - `tx[i]_mpwqe_blks` + - The number of send blocks processed from Multi-Packet WQEs (mpwqe). + - Informative + + * - `tx[i]_mpwqe_pkts` + - The number of send packets processed from Multi-Packet WQEs (mpwqe). + - Informative + + * - `rx[i]_cqe_compress_blks` + - The number of receive blocks with CQE compression on ring i [#accel]_. + - Acceleration + + * - `rx[i]_cqe_compress_pkts` + - The number of receive packets with CQE compression on ring i [#accel]_. + - Acceleration + + * - `rx[i]_cache_reuse` + - The number of events of successful reuse of a page from a driver's + internal page cache. + - Acceleration + + * - `rx[i]_cache_full` + - The number of events of full internal page cache where driver can't put a + page back to the cache for recycling (page will be freed). + - Acceleration + + * - `rx[i]_cache_empty` + - The number of events where cache was empty - no page to give. Driver + shall allocate new page. + - Acceleration + + * - `rx[i]_cache_busy` + - The number of events where cache head was busy and cannot be recycled. + Driver allocated new page. + - Acceleration + + * - `rx[i]_cache_waive` + - The number of cache evacuation. This can occur due to page move to + another NUMA node or page was pfmemalloc-ed and should be freed as soon + as possible. + - Acceleration + + * - `rx[i]_arfs_err` + - Number of flow rules that failed to be added to the flow table. + - Error + + * - `rx[i]_recover` + - The number of times the RQ was recovered. + - Error + + * - `tx[i]_xmit_more` + - The number of packets sent with `xmit_more` indication set on the skbuff + (no doorbell). + - Acceleration + + * - `ch[i]_poll` + - The number of invocations of NAPI poll of channel i. + - Informative + + * - `ch[i]_arm` + - The number of times the NAPI poll function completed and armed the + completion queues on channel i. + - Informative + + * - `ch[i]_aff_change` + - The number of times the NAPI poll function explicitly stopped execution + on a CPU due to a change in affinity, on channel i. + - Informative + + * - `ch[i]_events` + - The number of hard interrupt events on the completion queues of channel i. + - Informative + + * - `ch[i]_eq_rearm` + - The number of times the EQ was recovered. + - Error + + * - `ch[i]_force_irq` + - Number of times NAPI is triggered by XSK wakeups by posting a NOP to + ICOSQ. + - Acceleration + + * - `rx[i]_congst_umr` + - The number of times an outstanding UMR request is delayed due to + congestion, on ring i. + - Informative + + * - `rx_pp_alloc_fast` + - Number of successful fast path allocations. + - Informative + + * - `rx_pp_alloc_slow` + - Number of slow path order-0 allocations. + - Informative + + * - `rx_pp_alloc_slow_high_order` + - Number of slow path high order allocations. + - Informative + + * - `rx_pp_alloc_empty` + - Counter is incremented when ptr ring is empty, so a slow path allocation + was forced. + - Informative + + * - `rx_pp_alloc_refill` + - Counter is incremented when an allocation which triggered a refill of the + cache. + - Informative + + * - `rx_pp_alloc_waive` + - Counter is incremented when pages obtained from the ptr ring that cannot + be added to the cache due to a NUMA mismatch. + - Informative + + * - `rx_pp_recycle_cached` + - Counter is incremented when recycling placed page in the page pool cache. + - Informative + + * - `rx_pp_recycle_cache_full` + - Counter is incremented when page pool cache was full. + - Informative + + * - `rx_pp_recycle_ring` + - Counter is incremented when page placed into the ptr ring. + - Informative + + * - `rx_pp_recycle_ring_full` + - Counter is incremented when page released from page pool because the ptr + ring was full. + - Informative + + * - `rx_pp_recycle_released_ref` + - Counter is incremented when page released (and not recycled) because + refcnt > 1. + - Informative + + * - `rx[i]_xsk_buff_alloc_err` + - The number of times allocating an skb or XSK buffer failed in the XSK RQ + context. + - Error + + * - `rx[i]_xsk_arfs_err` + - aRFS (accelerated Receive Flow Steering) does not occur in the XSK RQ + context, so this counter should never increment. + - Error + + * - `rx[i]_xdp_tx_xmit` + - The number of packets forwarded back to the port due to XDP program + `XDP_TX` action (bouncing). these packets are not counted by other + software counters. These packets are counted by physical port and vPort + counters. + - Informative + + * - `rx[i]_xdp_tx_mpwqe` + - Number of multi-packet WQEs transmitted by the netdev and `XDP_TX`-ed by + the netdev during the RQ context. + - Acceleration + + * - `rx[i]_xdp_tx_inlnw` + - Number of WQE data segments transmitted where the data could be inlined + in the WQE and then `XDP_TX`-ed during the RQ context. + - Acceleration + + * - `rx[i]_xdp_tx_nops` + - Number of NOP WQEBBs (WQE building blocks) received posted to the XDP SQ. + - Acceleration + + * - `rx[i]_xdp_tx_full` + - The number of packets that should have been forwarded back to the port + due to `XDP_TX` action but were dropped due to full tx queue. These packets + are not counted by other software counters. These packets are counted by + physical port and vPort counters. You may open more rx queues and spread + traffic rx over all queues and/or increase rx ring size. + - Error + + * - `rx[i]_xdp_tx_err` + - The number of times an `XDP_TX` error such as frame too long and frame + too short occurred on `XDP_TX` ring of RX ring. + - Error + + * - `rx[i]_xdp_tx_cqes` / `rx_xdp_tx_cqe` [#ring_global]_ + - The number of completions received on the CQ of the `XDP_TX` ring. + - Informative + + * - `rx[i]_xdp_drop` + - The number of packets dropped due to XDP program `XDP_DROP` action. these + packets are not counted by other software counters. These packets are + counted by physical port and vPort counters. + - Informative + + * - `rx[i]_xdp_redirect` + - The number of times an XDP redirect action was triggered on ring i. + - Acceleration + + * - `tx[i]_xdp_xmit` + - The number of packets redirected to the interface(due to XDP redirect). + These packets are not counted by other software counters. These packets + are counted by physical port and vPort counters. + - Informative + + * - `tx[i]_xdp_full` + - The number of packets redirected to the interface(due to XDP redirect), + but were dropped due to full tx queue. these packets are not counted by + other software counters. you may enlarge tx queues. + - Informative + + * - `tx[i]_xdp_mpwqe` + - Number of multi-packet WQEs offloaded onto the NIC that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_inlnw` + - Number of WQE data segments where the data could be inlined in the WQE + where the data segments were `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_nops` + - Number of NOP WQEBBs (WQE building blocks) posted to the SQ that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xdp_err` + - The number of packets redirected to the interface(due to XDP redirect) + but were dropped due to error such as frame too long and frame too short. + - Error + + * - `tx[i]_xdp_cqes` + - The number of completions received for packets redirected to the + interface(due to XDP redirect) on the CQ. + - Informative + + * - `tx[i]_xsk_xmit` + - The number of packets transmitted using XSK zerocopy functionality. + - Acceleration + + * - `tx[i]_xsk_mpwqe` + - Number of multi-packet WQEs offloaded onto the NIC that were + `XDP_REDIRECT`-ed from other netdevs. + - Acceleration + + * - `tx[i]_xsk_inlnw` + - Number of WQE data segments where the data could be inlined in the WQE + that are transmitted using XSK zerocopy. + - Acceleration + + * - `tx[i]_xsk_full` + - Number of times doorbell is rung in XSK zerocopy mode when SQ is full. + - Error + + * - `tx[i]_xsk_err` + - Number of errors that occurred in XSK zerocopy mode such as if the data + size is larger than the MTU size. + - Error + + * - `tx[i]_xsk_cqes` + - Number of CQEs processed in XSK zerocopy mode. + - Acceleration + + * - `tx_tls_ctx` + - Number of TLS TX HW offload contexts added to device for encryption. + - Acceleration + + * - `tx_tls_del` + - Number of TLS TX HW offload contexts removed from device (connection + closed). + - Acceleration + + * - `tx_tls_pool_alloc` + - Number of times a unit of work is successfully allocated in the TLS HW + offload pool. + - Acceleration + + * - `tx_tls_pool_free` + - Number of times a unit of work is freed in the TLS HW offload pool. + - Acceleration + + * - `rx_tls_ctx` + - Number of TLS RX HW offload contexts added to device for decryption. + - Acceleration + + * - `rx_tls_del` + - Number of TLS RX HW offload contexts deleted from device (connection has + finished). + - Acceleration + + * - `rx[i]_tls_decrypted_packets` + - Number of successfully decrypted RX packets which were part of a TLS + stream. + - Acceleration + + * - `rx[i]_tls_decrypted_bytes` + - Number of TLS payload bytes in RX packets which were successfully + decrypted. + - Acceleration + + * - `rx[i]_tls_resync_req_pkt` + - Number of received TLS packets with a resync request. + - Acceleration + + * - `rx[i]_tls_resync_req_start` + - Number of times the TLS async resync request was started. + - Acceleration + + * - `rx[i]_tls_resync_req_end` + - Number of times the TLS async resync request properly ended with + providing the HW tracked tcp-seq. + - Acceleration + + * - `rx[i]_tls_resync_req_skip` + - Number of times the TLS async resync request procedure was started but + not properly ended. + - Error + + * - `rx[i]_tls_resync_res_ok` + - Number of times the TLS resync response call to the driver was + successfully handled. + - Acceleration + + * - `rx[i]_tls_resync_res_retry` + - Number of times the TLS resync response call to the driver was + reattempted when ICOSQ is full. + - Error + + * - `rx[i]_tls_resync_res_skip` + - Number of times the TLS resync response call to the driver was terminated + unsuccessfully. + - Error + + * - `rx[i]_tls_err` + - Number of times when CQE TLS offload was problematic. + - Error + + * - `tx[i]_tls_encrypted_packets` + - The number of send packets that are TLS encrypted by the kernel. + - Acceleration + + * - `tx[i]_tls_encrypted_bytes` + - The number of send bytes that are TLS encrypted by the kernel. + - Acceleration + + * - `tx[i]_tls_ooo` + - Number of times out of order TLS SQE fragments were handled on ring i. + - Acceleration + + * - `tx[i]_tls_dump_packets` + - Number of TLS decrypted packets copied over from NIC over DMA. + - Acceleration + + * - `tx[i]_tls_dump_bytes` + - Number of TLS decrypted bytes copied over from NIC over DMA. + - Acceleration + + * - `tx[i]_tls_resync_bytes` + - Number of TLS bytes requested to be resynchronized in order to be + decrypted. + - Acceleration + + * - `tx[i]_tls_skip_no_sync_data` + - Number of TLS send data that can safely be skipped / do not need to be + decrypted. + - Acceleration + + * - `tx[i]_tls_drop_no_sync_data` + - Number of TLS send data that were dropped due to retransmission of TLS + data. + - Acceleration + + * - `ptp_cq[i]_abort` + - Number of times a CQE has to be skipped in precision time protocol due to + a skew between the port timestamp and CQE timestamp being greater than + 128 seconds. + - Error + + * - `ptp_cq[i]_abort_abs_diff_ns` + - Accumulation of time differences between the port timestamp and CQE + timestamp when the difference is greater than 128 seconds in precision + time protocol. + - Error + +.. [#ring_global] The corresponding ring and global counters do not share the + same name (i.e. do not follow the common naming scheme). + +vPort Counters +-------------- +Counters on the NIC port that is connected to a eSwitch. + +.. flat-table:: vPort Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_vport_unicast_packets` + - Unicast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_unicast_bytes` + - Unicast bytes received, steered to a port including Raw Ethernet QP/DPDK + traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_unicast_packets` + - Unicast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_unicast_bytes` + - Unicast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_multicast_packets` + - Multicast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_multicast_bytes` + - Multicast bytes received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_multicast_packets` + - Multicast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_multicast_bytes` + - Multicast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_broadcast_packets` + - Broadcast packets received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_broadcast_bytes` + - Broadcast bytes received, steered to a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_broadcast_packets` + - Broadcast packets transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `tx_vport_broadcast_bytes` + - Broadcast bytes transmitted, steered from a port including Raw Ethernet + QP/DPDK traffic, excluding RDMA traffic. + - Informative + + * - `rx_vport_rdma_unicast_packets` + - RDMA unicast packets received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_unicast_bytes` + - RDMA unicast bytes received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_unicast_packets` + - RDMA unicast packets transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_unicast_bytes` + - RDMA unicast bytes transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_multicast_packets` + - RDMA multicast packets received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_vport_rdma_multicast_bytes` + - RDMA multicast bytes received, steered to a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_multicast_packets` + - RDMA multicast packets transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `tx_vport_rdma_multicast_bytes` + - RDMA multicast bytes transmitted, steered from a port (counters counts + RoCE/UD/RC traffic) [#accel]_. + - Acceleration + + * - `rx_steer_missed_packets` + - Number of packets that was received by the NIC, however was discarded + because it did not match any flow in the NIC flow table. + - Error + + * - `rx_packets` + - Representor only: packets received, that were handled by the hypervisor. + - Informative + + * - `rx_bytes` + - Representor only: bytes received, that were handled by the hypervisor. + - Informative + + * - `tx_packets` + - Representor only: packets transmitted, that were handled by the + hypervisor. + - Informative + + * - `tx_bytes` + - Representor only: bytes transmitted, that were handled by the hypervisor. + - Informative + + * - `dev_internal_queue_oob` + - The number of dropped packets due to lack of receive WQEs for an internal + device RQ. + - Error + +Physical Port Counters +---------------------- +The physical port counters are the counters on the external port connecting the +adapter to the network. This measuring point holds information on standardized +counters like IEEE 802.3, RFC2863, RFC 2819, RFC 3635 and additional counters +like flow control, FEC and more. + +.. flat-table:: Physical Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_packets_phy` + - The number of packets received on the physical port. This counter doesn’t + include packets that were discarded due to FCS, frame size and similar + errors. + - Informative + + * - `tx_packets_phy` + - The number of packets transmitted on the physical port. + - Informative + + * - `rx_bytes_phy` + - The number of bytes received on the physical port, including Ethernet + header and FCS. + - Informative + + * - `tx_bytes_phy` + - The number of bytes transmitted on the physical port. + - Informative + + * - `rx_multicast_phy` + - The number of multicast packets received on the physical port. + - Informative + + * - `tx_multicast_phy` + - The number of multicast packets transmitted on the physical port. + - Informative + + * - `rx_broadcast_phy` + - The number of broadcast packets received on the physical port. + - Informative + + * - `tx_broadcast_phy` + - The number of broadcast packets transmitted on the physical port. + - Informative + + * - `rx_crc_errors_phy` + - The number of dropped received packets due to FCS (Frame Check Sequence) + error on the physical port. If this counter is increased in high rate, + check the link quality using `rx_symbol_error_phy` and + `rx_corrected_bits_phy` counters below. + - Error + + * - `rx_in_range_len_errors_phy` + - The number of received packets dropped due to length/type errors on a + physical port. + - Error + + * - `rx_out_of_range_len_phy` + - The number of received packets dropped due to length greater than allowed + on a physical port. If this counter is increasing, it implies that the + peer connected to the adapter has a larger MTU configured. Using same MTU + configuration shall resolve this issue. + - Error + + * - `rx_oversize_pkts_phy` + - The number of dropped received packets due to length which exceed MTU + size on a physical port. If this counter is increasing, it implies that + the peer connected to the adapter has a larger MTU configured. Using same + MTU configuration shall resolve this issue. + - Error + + * - `rx_symbol_err_phy` + - The number of received packets dropped due to physical coding errors + (symbol errors) on a physical port. + - Error + + * - `rx_mac_control_phy` + - The number of MAC control packets received on the physical port. + - Informative + + * - `tx_mac_control_phy` + - The number of MAC control packets transmitted on the physical port. + - Informative + + * - `rx_pause_ctrl_phy` + - The number of link layer pause packets received on a physical port. If + this counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from to the adapter. + - Informative + + * - `tx_pause_ctrl_phy` + - The number of link layer pause packets transmitted on a physical port. If + this counter is increasing, it implies that the NIC is congested and + cannot absorb the traffic coming from the network. + - Informative + + * - `rx_unsupported_op_phy` + - The number of MAC control packets received with unsupported opcode on a + physical port. + - Error + + * - `rx_discards_phy` + - The number of received packets dropped due to lack of buffers on a + physical port. If this counter is increasing, it implies that the adapter + is congested and cannot absorb the traffic coming from the network. + - Error + + * - `tx_discards_phy` + - The number of packets which were discarded on transmission, even no + errors were detected. the drop might occur due to link in down state, + head of line drop, pause from the network, etc. + - Error + + * - `tx_errors_phy` + - The number of transmitted packets dropped due to a length which exceed + MTU size on a physical port. + - Error + + * - `rx_undersize_pkts_phy` + - The number of received packets dropped due to length which is shorter + than 64 bytes on a physical port. If this counter is increasing, it + implies that the peer connected to the adapter has a non-standard MTU + configured or malformed packet had arrived. + - Error + + * - `rx_fragments_phy` + - The number of received packets dropped due to a length which is shorter + than 64 bytes and has FCS error on a physical port. If this counter is + increasing, it implies that the peer connected to the adapter has a + non-standard MTU configured. + - Error + + * - `rx_jabbers_phy` + - The number of received packets d due to a length which is longer than 64 + bytes and had FCS error on a physical port. + - Error + + * - `rx_64_bytes_phy` + - The number of packets received on the physical port with size of 64 bytes. + - Informative + + * - `rx_65_to_127_bytes_phy` + - The number of packets received on the physical port with size of 65 to + 127 bytes. + - Informative + + * - `rx_128_to_255_bytes_phy` + - The number of packets received on the physical port with size of 128 to + 255 bytes. + - Informative + + * - `rx_256_to_511_bytes_phy` + - The number of packets received on the physical port with size of 256 to + 512 bytes. + - Informative + + * - `rx_512_to_1023_bytes_phy` + - The number of packets received on the physical port with size of 512 to + 1023 bytes. + - Informative + + * - `rx_1024_to_1518_bytes_phy` + - The number of packets received on the physical port with size of 1024 to + 1518 bytes. + - Informative + + * - `rx_1519_to_2047_bytes_phy` + - The number of packets received on the physical port with size of 1519 to + 2047 bytes. + - Informative + + * - `rx_2048_to_4095_bytes_phy` + - The number of packets received on the physical port with size of 2048 to + 4095 bytes. + - Informative + + * - `rx_4096_to_8191_bytes_phy` + - The number of packets received on the physical port with size of 4096 to + 8191 bytes. + - Informative + + * - `rx_8192_to_10239_bytes_phy` + - The number of packets received on the physical port with size of 8192 to + 10239 bytes. + - Informative + + * - `link_down_events_phy` + - The number of times where the link operative state changed to down. In + case this counter is increasing it may imply on port flapping. You may + need to replace the cable/transceiver. + - Error + + * - `rx_out_of_buffer` + - Number of times receive queue had no software buffers allocated for the + adapter's incoming traffic. + - Error + + * - `module_bus_stuck` + - The number of times that module's I\ :sup:`2`\C bus (data or clock) + short-wire was detected. You may need to replace the cable/transceiver. + - Error + + * - `module_high_temp` + - The number of times that the module temperature was too high. If this + issue persist, you may need to check the ambient temperature or replace + the cable/transceiver module. + - Error + + * - `module_bad_shorted` + - The number of times that the module cables were shorted. You may need to + replace the cable/transceiver module. + - Error + + * - `module_unplug` + - The number of times that module was ejected. + - Informative + + * - `rx_buffer_passed_thres_phy` + - The number of events where the port receive buffer was over 85% full. + - Informative + + * - `tx_pause_storm_warning_events` + - The number of times the device was sending pauses for a long period of + time. + - Informative + + * - `tx_pause_storm_error_events` + - The number of times the device was sending pauses for a long period of + time, reaching time out and disabling transmission of pause frames. on + the period where pause frames were disabled, drop could have been + occurred. + - Error + + * - `rx[i]_buff_alloc_err` + - Failed to allocate a buffer to received packet (or SKB) on ring i. + - Error + + * - `rx_bits_phy` + - This counter provides information on the total amount of traffic that + could have been received and can be used as a guideline to measure the + ratio of errored traffic in `rx_pcs_symbol_err_phy` and + `rx_corrected_bits_phy`. + - Informative + + * - `rx_pcs_symbol_err_phy` + - This counter counts the number of symbol errors that wasn’t corrected by + FEC correction algorithm or that FEC algorithm was not active on this + interface. If this counter is increasing, it implies that the link + between the NIC and the network is suffering from high BER, and that + traffic is lost. You may need to replace the cable/transceiver. The error + rate is the number of `rx_pcs_symbol_err_phy` divided by the number of + `rx_bits_phy` on a specific time frame. + - Error + + * - `rx_corrected_bits_phy` + - The number of corrected bits on this port according to active FEC + (RS/FC). If this counter is increasing, it implies that the link between + the NIC and the network is suffering from high BER. The corrected bit + rate is the number of `rx_corrected_bits_phy` divided by the number of + `rx_bits_phy` on a specific time frame. + - Error + + * - `rx_err_lane_[l]_phy` + - This counter counts the number of physical raw errors per lane l index. + The counter counts errors before FEC corrections. If this counter is + increasing, it implies that the link between the NIC and the network is + suffering from high BER, and that traffic might be lost. You may need to + replace the cable/transceiver. Please check in accordance with + `rx_corrected_bits_phy`. + - Error + + * - `rx_global_pause` + - The number of pause packets received on the physical port. If this + counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from the adapter. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `rx_global_pause_duration` + - The duration of pause received (in microSec) on the physical port. The + counter represents the time the port did not send any traffic. If this + counter is increasing, it implies that the network is congested and + cannot absorb the traffic coming from the adapter. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `tx_global_pause` + - The number of pause packets transmitted on a physical port. If this + counter is increasing, it implies that the adapter is congested and + cannot absorb the traffic coming from the network. Note: This counter is + only enabled when global pause mode is enabled. + - Informative + + * - `tx_global_pause_duration` + - The duration of pause transmitter (in microSec) on the physical port. + Note: This counter is only enabled when global pause mode is enabled. + - Informative + + * - `rx_global_pause_transition` + - The number of times a transition from Xoff to Xon on the physical port + has occurred. Note: This counter is only enabled when global pause mode + is enabled. + - Informative + + * - `rx_if_down_packets` + - The number of received packets that were dropped due to interface down. + - Informative + +Priority Port Counters +---------------------- +The following counters are physical port counters that are counted per L2 +priority (0-7). + +**Note:** `p` in the counter name represents the priority. + +.. flat-table:: Priority Port Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_prio[p]_bytes` + - The number of bytes received with priority p on the physical port. + - Informative + + * - `rx_prio[p]_packets` + - The number of packets received with priority p on the physical port. + - Informative + + * - `tx_prio[p]_bytes` + - The number of bytes transmitted on priority p on the physical port. + - Informative + + * - `tx_prio[p]_packets` + - The number of packets transmitted on priority p on the physical port. + - Informative + + * - `rx_prio[p]_pause` + - The number of pause packets received with priority p on a physical port. + If this counter is increasing, it implies that the network is congested + and cannot absorb the traffic coming from the adapter. Note: This counter + is available only if PFC was enabled on priority p. + - Informative + + * - `rx_prio[p]_pause_duration` + - The duration of pause received (in microSec) on priority p on the + physical port. The counter represents the time the port did not send any + traffic on this priority. If this counter is increasing, it implies that + the network is congested and cannot absorb the traffic coming from the + adapter. Note: This counter is available only if PFC was enabled on + priority p. + - Informative + + * - `rx_prio[p]_pause_transition` + - The number of times a transition from Xoff to Xon on priority p on the + physical port has occurred. Note: This counter is available only if PFC + was enabled on priority p. + - Informative + + * - `tx_prio[p]_pause` + - The number of pause packets transmitted on priority p on a physical port. + If this counter is increasing, it implies that the adapter is congested + and cannot absorb the traffic coming from the network. Note: This counter + is available only if PFC was enabled on priority p. + - Informative + + * - `tx_prio[p]_pause_duration` + - The duration of pause transmitter (in microSec) on priority p on the + physical port. Note: This counter is available only if PFC was enabled on + priority p. + - Informative + + * - `rx_prio[p]_buf_discard` + - The number of packets discarded by device due to lack of per host receive + buffers. + - Informative + + * - `rx_prio[p]_cong_discard` + - The number of packets discarded by device due to per host congestion. + - Informative + + * - `rx_prio[p]_marked` + - The number of packets ecn marked by device due to per host congestion. + - Informative + + * - `rx_prio[p]_discards` + - The number of packets discarded by device due to lack of receive buffers. + - Informative + +Device Counters +--------------- +.. flat-table:: Device Counter Table + :widths: 2 3 1 + + * - Counter + - Description + - Type + + * - `rx_pci_signal_integrity` + - Counts physical layer PCIe signal integrity errors, the number of + transitions to recovery due to Framing errors and CRC (dlp and tlp). If + this counter is raising, try moving the adapter card to a different slot + to rule out a bad PCI slot. Validate that you are running with the latest + firmware available and latest server BIOS version. + - Error + + * - `tx_pci_signal_integrity` + - Counts physical layer PCIe signal integrity errors, the number of + transition to recovery initiated by the other side (moving to recovery + due to getting TS/EIEOS). If this counter is raising, try moving the + adapter card to a different slot to rule out a bad PCI slot. Validate + that you are running with the latest firmware available and latest server + BIOS version. + - Error + + * - `outbound_pci_buffer_overflow` + - The number of packets dropped due to pci buffer overflow. If this counter + is raising in high rate, it might indicate that the receive traffic rate + for a host is larger than the PCIe bus and therefore a congestion occurs. + - Informative + + * - `outbound_pci_stalled_rd` + - The percentage (in the range 0...100) of time within the last second that + the NIC had outbound non-posted reads requests but could not perform the + operation due to insufficient posted credits. + - Informative + + * - `outbound_pci_stalled_wr` + - The percentage (in the range 0...100) of time within the last second that + the NIC had outbound posted writes requests but could not perform the + operation due to insufficient posted credits. + - Informative + + * - `outbound_pci_stalled_rd_events` + - The number of seconds where `outbound_pci_stalled_rd` was above 30%. + - Informative + + * - `outbound_pci_stalled_wr_events` + - The number of seconds where `outbound_pci_stalled_wr` was above 30%. + - Informative + + * - `dev_out_of_buffer` + - The number of times the device owned queue had not enough buffers + allocated. + - Error diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst new file mode 100644 index 000000000000..9b5c40ba7f0d --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst @@ -0,0 +1,224 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +======= +Devlink +======= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents +======== + +- `Info`_ +- `Parameters`_ +- `Health reporters`_ + +Info +==== + +The devlink info reports the running and stored firmware versions on device. +It also prints the device PSID which represents the HCA board type ID. + +User command example:: + + $ devlink dev info pci/0000:00:06.0 + pci/0000:00:06.0: + driver mlx5_core + versions: + fixed: + fw.psid MT_0000000009 + running: + fw.version 16.26.0100 + stored: + fw.version 16.26.0100 + +Parameters +========== + +flow_steering_mode: Device flow steering mode +--------------------------------------------- +The flow steering mode parameter controls the flow steering mode of the driver. +Two modes are supported: +1. 'dmfs' - Device managed flow steering. +2. 'smfs' - Software/Driver managed flow steering. + +In DMFS mode, the HW steering entities are created and managed through the +Firmware. +In SMFS mode, the HW steering entities are created and managed though by +the driver directly into hardware without firmware intervention. + +SMFS mode is faster and provides better rule insertion rate compared to default DMFS mode. + +User command examples: + +- Set SMFS flow steering mode:: + + $ devlink dev param set pci/0000:06:00.0 name flow_steering_mode value "smfs" cmode runtime + +- Read device flow steering mode:: + + $ devlink dev param show pci/0000:06:00.0 name flow_steering_mode + pci/0000:06:00.0: + name flow_steering_mode type driver-specific + values: + cmode runtime value smfs + +enable_roce: RoCE enablement state +---------------------------------- +If the device supports RoCE disablement, RoCE enablement state controls device +support for RoCE capability. Otherwise, the control occurs in the driver stack. +When RoCE is disabled at the driver level, only raw ethernet QPs are supported. + +To change RoCE enablement state, a user must change the driverinit cmode value +and run devlink reload. + +User command examples: + +- Disable RoCE:: + + $ devlink dev param set pci/0000:06:00.0 name enable_roce value false cmode driverinit + $ devlink dev reload pci/0000:06:00.0 + +- Read RoCE enablement state:: + + $ devlink dev param show pci/0000:06:00.0 name enable_roce + pci/0000:06:00.0: + name enable_roce type generic + values: + cmode driverinit value true + +esw_port_metadata: Eswitch port metadata state +---------------------------------------------- +When applicable, disabling eswitch metadata can increase packet rate +up to 20% depending on the use case and packet sizes. + +Eswitch port metadata state controls whether to internally tag packets with +metadata. Metadata tagging must be enabled for multi-port RoCE, failover +between representors and stacked devices. +By default metadata is enabled on the supported devices in E-switch. +Metadata is applicable only for E-switch in switchdev mode and +users may disable it when NONE of the below use cases will be in use: +1. HCA is in Dual/multi-port RoCE mode. +2. VF/SF representor bonding (Usually used for Live migration) +3. Stacked devices + +When metadata is disabled, the above use cases will fail to initialize if +users try to enable them. + +- Show eswitch port metadata:: + + $ devlink dev param show pci/0000:06:00.0 name esw_port_metadata + pci/0000:06:00.0: + name esw_port_metadata type driver-specific + values: + cmode runtime value true + +- Disable eswitch port metadata:: + + $ devlink dev param set pci/0000:06:00.0 name esw_port_metadata value false cmode runtime + +- Change eswitch mode to switchdev mode where after choosing the metadata value:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +Health reporters +================ + +tx reporter +----------- +The tx reporter is responsible for reporting and recovering of the following two error scenarios: + +- tx timeout + Report on kernel tx timeout detection. + Recover by searching lost interrupts. +- tx error completion + Report on error tx completion. + Recover by flushing the tx queue and reset it. + +tx reporter also support on demand diagnose callback, on which it provides +real time information of its send queues status. + +User commands examples: + +- Diagnose send queues status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter tx + +NOTE: This command has valid output only when interface is up, otherwise the command has empty output. + +- Show number of tx errors indicated, number of recover flows ended successfully, + is autorecover enabled and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter tx + +rx reporter +----------- +The rx reporter is responsible for reporting and recovering of the following two error scenarios: + +- rx queues' initialization (population) timeout + Population of rx queues' descriptors on ring initialization is done + in napi context via triggering an irq. In case of a failure to get + the minimum amount of descriptors, a timeout would occur, and + descriptors could be recovered by polling the EQ (Event Queue). +- rx completions with errors (reported by HW on interrupt context) + Report on rx completion error. + Recover (if needed) by flushing the related queue and reset it. + +rx reporter also supports on demand diagnose callback, on which it +provides real time information of its receive queues' status. + +- Diagnose rx queues' status and corresponding completion queue:: + + $ devlink health diagnose pci/0000:82:00.0 reporter rx + +NOTE: This command has valid output only when interface is up. Otherwise, the command has empty output. + +- Show number of rx errors indicated, number of recover flows ended successfully, + is autorecover enabled, and graceful period from last recover:: + + $ devlink health show pci/0000:82:00.0 reporter rx + +fw reporter +----------- +The fw reporter implements `diagnose` and `dump` callbacks. +It follows symptoms of fw error such as fw syndrome by triggering +fw core dump and storing it into the dump buffer. +The fw reporter diagnose command can be triggered any time by the user to check +current fw status. + +User commands examples: + +- Check fw heath status:: + + $ devlink health diagnose pci/0000:82:00.0 reporter fw + +- Read FW core dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.0 reporter fw + +NOTE: This command can run only on the PF which has fw tracer ownership, +running it on other PF or any VF will return "Operation not permitted". + +fw fatal reporter +----------------- +The fw fatal reporter implements `dump` and `recover` callbacks. +It follows fatal errors indications by CR-space dump and recover flow. +The CR-space dump uses vsc interface which is valid even if the FW command +interface is not functional, which is the case in most FW fatal errors. +The recover function runs recover flow which reloads the driver and triggers fw +reset if needed. +On firmware error, the health buffer is dumped into the dmesg. The log +level is derived from the error's severity (given in health buffer). + +User commands examples: + +- Run fw recover flow manually:: + + $ devlink health recover pci/0000:82:00.0 reporter fw_fatal + +- Read FW CR-space dump if already stored or trigger new one:: + + $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal + +NOTE: This command can run only on PF. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst new file mode 100644 index 000000000000..3fdcd6b61ccf --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/index.rst @@ -0,0 +1,26 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +Mellanox ConnectX(R) mlx5 core VPI Network Driver +================================================= + +:Copyright: |copy| 2019, Mellanox Technologies LTD. +:Copyright: |copy| 2020-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +Contents: + +.. toctree:: + :maxdepth: 2 + + kconfig + devlink + switchdev + tracepoints + counters + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst new file mode 100644 index 000000000000..43b1f7e87ec4 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/kconfig.rst @@ -0,0 +1,168 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +======================================= +Enabling the driver and kconfig options +======================================= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +| mlx5 core is modular and most of the major mlx5 core driver features can be selected (compiled in/out) +| at build time via kernel Kconfig flags. +| Basic features, ethernet net device rx/tx offloads and XDP, are available with the most basic flags +| CONFIG_MLX5_CORE=y/m and CONFIG_MLX5_CORE_EN=y. +| For the list of advanced features, please see below. + +**CONFIG_MLX5_BRIDGE=(y/n)** + +| Enable :ref:`Ethernet Bridging (BRIDGE) offloading support <mlx5_bridge_offload>`. +| This will provide the ability to add representors of mlx5 uplink and VF +| ports to Bridge and offloading rules for traffic between such ports. +| Supports VLANs (trunk and access modes). + + +**CONFIG_MLX5_CORE=(y/m/n)** (module mlx5_core.ko) + +| The driver can be enabled by choosing CONFIG_MLX5_CORE=y/m in kernel config. +| This will provide mlx5 core driver for mlx5 ulps to interface with (mlx5e, mlx5_ib). + + +**CONFIG_MLX5_CORE_EN=(y/n)** + +| Choosing this option will allow basic ethernet netdevice support with all of the standard rx/tx offloads. +| mlx5e is the mlx5 ulp driver which provides netdevice kernel interface, when chosen, mlx5e will be +| built-in into mlx5_core.ko. + + +**CONFIG_MLX5_CORE_EN_DCB=(y/n)**: + +| Enables `Data Center Bridging (DCB) Support <https://community.mellanox.com/s/article/howto-auto-config-pfc-and-ets-on-connectx-4-via-lldp-dcbx>`_. + + +**CONFIG_MLX5_CORE_IPOIB=(y/n)** + +| IPoIB offloads & acceleration support. +| Requires CONFIG_MLX5_CORE_EN to provide an accelerated interface for the rdma +| IPoIB ulp netdevice. + + +**CONFIG_MLX5_CLS_ACT=(y/n)** + +| Enables offload support for TC classifier action (NET_CLS_ACT). +| Works in both native NIC mode and Switchdev SRIOV mode. +| Flow-based classifiers, such as those registered through +| `tc-flower(8)`, are processed by the device, rather than the +| host. Actions that would then overwrite matching classification +| results would then be instant due to the offload. + + +**CONFIG_MLX5_EN_ARFS=(y/n)** + +| Enables Hardware-accelerated receive flow steering (arfs) support, and ntuple filtering. +| https://community.mellanox.com/s/article/howto-configure-arfs-on-connectx-4 + + +**CONFIG_MLX5_EN_IPSEC=(y/n)** + +| Enables `IPSec XFRM cryptography-offload acceleration <https://support.mellanox.com/s/article/ConnectX-6DX-Bluefield-2-IPsec-HW-Full-Offload-Configuration-Guide>`_. + + +**CONFIG_MLX5_EN_MACSEC=(y/n)** + +| Build support for MACsec cryptography-offload acceleration in the NIC. + + +**CONFIG_MLX5_EN_RXNFC=(y/n)** + +| Enables ethtool receive network flow classification, which allows user defined +| flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc API. + + +**CONFIG_MLX5_EN_TLS=(y/n)** + +| TLS cryptography-offload acceleration. + + +**CONFIG_MLX5_ESWITCH=(y/n)** + +| Ethernet SRIOV E-Switch support in ConnectX NIC. E-Switch provides internal SRIOV packet steering +| and switching for the enabled VFs and PF in two available modes: +| 1) `Legacy SRIOV mode (L2 mac vlan steering based) <https://community.mellanox.com/s/article/howto-configure-sr-iov-for-connectx-4-connectx-5-with-kvm--ethernet-x>`_. +| 2) `Switchdev mode (eswitch offloads) <https://www.mellanox.com/related-docs/prod_software/ASAP2_Hardware_Offloading_for_vSwitches_User_Manual_v4.4.pdf>`_. + + +**CONFIG_MLX5_FPGA=(y/n)** + +| Build support for the Innova family of network cards by Mellanox Technologies. +| Innova network cards are comprised of a ConnectX chip and an FPGA chip on one board. +| If you select this option, the mlx5_core driver will include the Innova FPGA core and allow +| building sandbox-specific client drivers. + + +**CONFIG_MLX5_INFINIBAND=(y/n/m)** (module mlx5_ib.ko) + +| Provides low-level InfiniBand/RDMA and `RoCE <https://community.mellanox.com/s/article/recommended-network-configuration-examples-for-roce-deployment>`_ support. + + +**CONFIG_MLX5_MPFS=(y/n)** + +| Ethernet Multi-Physical Function Switch (MPFS) support in ConnectX NIC. +| MPFs is required for when `Multi-Host <http://www.mellanox.com/page/multihost>`_ configuration is enabled to allow passing +| user configured unicast MAC addresses to the requesting PF. + + +**CONFIG_MLX5_SF=(y/n)** + +| Build support for subfunction. +| Subfunctons are more light weight than PCI SRIOV VFs. Choosing this option +| will enable support for creating subfunction devices. + + +**CONFIG_MLX5_SF_MANAGER=(y/n)** + +| Build support for subfuction port in the NIC. A Mellanox subfunction +| port is managed through devlink. A subfunction supports RDMA, netdevice +| and vdpa device. It is similar to a SRIOV VF but it doesn't require +| SRIOV support. + + +**CONFIG_MLX5_SW_STEERING=(y/n)** + +| Build support for software-managed steering in the NIC. + + +**CONFIG_MLX5_TC_CT=(y/n)** + +| Support offloading connection tracking rules via tc ct action. + + +**CONFIG_MLX5_TC_SAMPLE=(y/n)** + +| Support offloading sample rules via tc sample action. + + +**CONFIG_MLX5_VDPA=(y/n)** + +| Support library for Mellanox VDPA drivers. Provides code that is +| common for all types of VDPA drivers. The following drivers are planned: +| net, block. + + +**CONFIG_MLX5_VDPA_NET=(y/n)** + +| VDPA network driver for ConnectX6 and newer. Provides offloading +| of virtio net datapath such that descriptors put on the ring will +| be executed by the hardware. It also supports a variety of stateless +| offloads depending on the actual device used and firmware version. + + +**CONFIG_MLX5_VFIO_PCI=(y/n)** + +| This provides migration support for MLX5 devices using the VFIO framework. + + +**External options** ( Choose if the corresponding mlx5 feature is required ) + +- CONFIG_MLXFW: When chosen, mlx5 firmware flashing support will be enabled (via devlink and ethtool). +- CONFIG_PTP_1588_CLOCK: When chosen, mlx5 ptp support will be enabled +- CONFIG_VXLAN: When chosen, mlx5 vxlan support will be enabled. diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst new file mode 100644 index 000000000000..01deedb71597 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/switchdev.rst @@ -0,0 +1,239 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +========= +Switchdev +========= + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +.. _mlx5_bridge_offload: + +Bridge offload +============== + +The mlx5 driver implements support for offloading bridge rules when in switchdev +mode. Linux bridge FDBs are automatically offloaded when mlx5 switchdev +representor is attached to bridge. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Attach mlx5 switchdev representor 'enp8s0f0' to bridge netdev 'bridge1':: + + $ ip link set enp8s0f0 master bridge1 + +VLANs +----- + +Following bridge VLAN functions are supported by mlx5: + +- VLAN filtering (including multiple VLANs per port):: + + $ ip link set bridge1 type bridge vlan_filtering 1 + $ bridge vlan add dev enp8s0f0 vid 2-3 + +- VLAN push on bridge ingress:: + + $ bridge vlan add dev enp8s0f0 vid 3 pvid + +- VLAN pop on bridge egress:: + + $ bridge vlan add dev enp8s0f0 vid 3 untagged + +Subfunction +=========== + +mlx5 supports subfunction management using devlink port (see :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>`) interface. + +A subfunction has its own function capabilities and its own resources. This +means a subfunction has its own dedicated queues (txq, rxq, cq, eq). These +queues are neither shared nor stolen from the parent PCI function. + +When a subfunction is RDMA capable, it has its own QP1, GID table, and RDMA +resources neither shared nor stolen from the parent PCI function. + +A subfunction has a dedicated window in PCI BAR space that is not shared +with the other subfunctions or the parent PCI function. This ensures that all +devices (netdev, rdma, vdpa, etc.) of the subfunction accesses only assigned +PCI BAR space. + +A subfunction supports eswitch representation through which it supports tc +offloads. The user configures eswitch to send/receive packets from/to +the subfunction port. + +Subfunctions share PCI level resources such as PCI MSI-X IRQs with +other subfunctions and/or with its parent PCI function. + +Example mlx5 software, system, and device view:: + + _______ + | admin | + | user |---------- + |_______| | + | | + ____|____ __|______ _________________ + | | | | | | + | devlink | | tc tool | | user | + | tool | |_________| | applications | + |_________| | |_________________| + | | | | + | | | | Userspace + +---------|-------------|-------------------|----------|--------------------+ + | | +----------+ +----------+ Kernel + | | | netdev | | rdma dev | + | | +----------+ +----------+ + (devlink port add/del | ^ ^ + port function set) | | | + | | +---------------| + _____|___ | | _______|_______ + | | | | | mlx5 class | + | devlink | +------------+ | | drivers | + | kernel | | rep netdev | | |(mlx5_core,ib) | + |_________| +------------+ | |_______________| + | | | ^ + (devlink ops) | | (probe/remove) + _________|________ | | ____|________ + | subfunction | | +---------------+ | subfunction | + | management driver|----- | subfunction |---| driver | + | (mlx5_core) | | auxiliary dev | | (mlx5_core) | + |__________________| +---------------+ |_____________| + | ^ + (sf add/del, vhca events) | + | (device add/del) + _____|____ ____|________ + | | | subfunction | + | PCI NIC |--- activate/deactivate events--->| host driver | + |__________| | (mlx5_core) | + |_____________| + +Subfunction is created using devlink port interface. + +- Change device to switchdev mode:: + + $ devlink dev eswitch set pci/0000:06:00.0 mode switchdev + +- Add a devlink port of subfunction flavour:: + + $ devlink port add pci/0000:06:00.0 flavour pcisf pfnum 0 sfnum 88 + pci/0000:06:00.0/32768: type eth netdev eth6 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Show a devlink port of the subfunction:: + + $ devlink port show pci/0000:06:00.0/32768 + pci/0000:06:00.0/32768: type eth netdev enp6s0pf0sf88 flavour pcisf pfnum 0 sfnum 88 + function: + hw_addr 00:00:00:00:00:00 state inactive opstate detached + +- Delete a devlink port of subfunction after use:: + + $ devlink port del pci/0000:06:00.0/32768 + +Function attributes +=================== + +The mlx5 driver provides a mechanism to setup PCI VF/SF function attributes in +a unified way for SmartNIC and non-SmartNIC. + +This is supported only when the eswitch mode is set to switchdev. Port function +configuration of the PCI VF/SF is supported through devlink eswitch port. + +Port function attributes should be set before PCI VF/SF is enumerated by the +driver. + +MAC address setup +----------------- + +mlx5 driver support devlink port function attr mechanism to setup MAC +address. (refer to Documentation/networking/devlink/devlink-port.rst) + +RoCE capability setup +~~~~~~~~~~~~~~~~~~~~~ +Not all mlx5 PCI devices/SFs require RoCE capability. + +When RoCE capability is disabled, it saves 1 Mbytes worth of system memory per +PCI devices/SF. + +mlx5 driver support devlink port function attr mechanism to setup RoCE +capability. (refer to Documentation/networking/devlink/devlink-port.rst) + +migratable capability setup +~~~~~~~~~~~~~~~~~~~~~~~~~~~ +User who wants mlx5 PCI VFs to be able to perform live migration need to +explicitly enable the VF migratable capability. + +mlx5 driver support devlink port function attr mechanism to setup migratable +capability. (refer to Documentation/networking/devlink/devlink-port.rst) + +SF state setup +-------------- + +To use the SF, the user must activate the SF using the SF function state +attribute. + +- Get the state of the SF identified by its unique devlink port index:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state inactive opstate detached + +- Activate the function and verify its state is active:: + + $ devlink port function set ens2f0npf0sf88 state active + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate detached + +Upon function activation, the PF driver instance gets the event from the device +that a particular SF was activated. It's the cue to put the device on bus, probe +it and instantiate the devlink instance and class specific auxiliary devices +for it. + +- Show the auxiliary device and port of the subfunction:: + + $ devlink dev show + devlink dev show auxiliary/mlx5_core.sf.4 + + $ devlink port show auxiliary/mlx5_core.sf.4/1 + auxiliary/mlx5_core.sf.4/1: type eth netdev p0sf88 flavour virtual port 0 splittable false + + $ rdma link show mlx5_0/1 + link mlx5_0/1 state ACTIVE physical_state LINK_UP netdev p0sf88 + + $ rdma dev show + 8: rocep6s0f1: node_type ca fw 16.29.0550 node_guid 248a:0703:00b3:d113 sys_image_guid 248a:0703:00b3:d112 + 13: mlx5_0: node_type ca fw 16.29.0550 node_guid 0000:00ff:fe00:8888 sys_image_guid 248a:0703:00b3:d112 + +- Subfunction auxiliary device and class device hierarchy:: + + mlx5_core.sf.4 + (subfunction auxiliary device) + /\ + / \ + / \ + / \ + / \ + mlx5_core.eth.4 mlx5_core.rdma.4 + (sf eth aux dev) (sf rdma aux dev) + | | + | | + p0sf88 mlx5_0 + (sf netdev) (sf rdma device) + +Additionally, the SF port also gets the event when the driver attaches to the +auxiliary device of the subfunction. This results in changing the operational +state of the function. This provides visibility to the user to decide when is it +safe to delete the SF port for graceful termination of the subfunction. + +- Show the SF port operational state:: + + $ devlink port show ens2f0npf0sf88 + pci/0000:06:00.0/32768: type eth netdev ens2f0npf0sf88 flavour pcisf controller 0 pfnum 0 sfnum 88 external false splittable false + function: + hw_addr 00:00:00:00:88:88 state active opstate attached diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst new file mode 100644 index 000000000000..a9d3e123adc4 --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/tracepoints.rst @@ -0,0 +1,229 @@ +.. SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +.. include:: <isonum.txt> + +=========== +Tracepoints +=========== + +:Copyright: |copy| 2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. + +mlx5 driver provides internal tracepoints for tracking and debugging using +kernel tracepoints interfaces (refer to Documentation/trace/ftrace.rst). + +For the list of support mlx5 events, check `/sys/kernel/debug/tracing/events/mlx5/`. + +tc and eswitch offloads tracepoints: + +- mlx5e_configure_flower: trace flower filter actions and cookies offloaded to mlx5:: + + $ echo mlx5:mlx5e_configure_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6535 [019] ...1 2672.404466: mlx5e_configure_flower: cookie=0000000067874a55 actions= REDIRECT + +- mlx5e_delete_flower: trace flower filter actions and cookies deleted from mlx5:: + + $ echo mlx5:mlx5e_delete_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6569 [010] .N.1 2686.379075: mlx5e_delete_flower: cookie=0000000067874a55 actions= NULL + +- mlx5e_stats_flower: trace flower stats request:: + + $ echo mlx5:mlx5e_stats_flower >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + tc-6546 [010] ...1 2679.704889: mlx5e_stats_flower: cookie=0000000060eb3d6a bytes=0 packets=0 lastused=4295560217 + +- mlx5e_tc_update_neigh_used_value: trace tunnel rule neigh update value offloaded to mlx5:: + + $ echo mlx5:mlx5e_tc_update_neigh_used_value >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u48:4-8806 [009] ...1 55117.882428: mlx5e_tc_update_neigh_used_value: netdev: ens1f0 IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_used=1 + +- mlx5e_rep_neigh_update: trace neigh update tasks scheduled due to neigh state change events:: + + $ echo mlx5:mlx5e_rep_neigh_update >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u48:7-2221 [009] ...1 1475.387435: mlx5e_rep_neigh_update: netdev: ens1f0 MAC: 24:8a:07:9a:17:9a IPv4: 1.1.1.10 IPv6: ::ffff:1.1.1.10 neigh_connected=1 + +Bridge offloads tracepoints: + +- mlx5_esw_bridge_fdb_entry_init: trace bridge FDB entry offloaded to mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:9-2217 [003] ...1 318.582243: mlx5_esw_bridge_fdb_entry_init: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=0 flags=0 used=0 + +- mlx5_esw_bridge_fdb_entry_cleanup: trace bridge FDB entry deleted from mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2581 [005] ...1 318.629871: mlx5_esw_bridge_fdb_entry_cleanup: net_device=enp8s0f0_1 addr=e4:fd:05:08:00:03 vid=0 flags=0 used=16 + +- mlx5_esw_bridge_fdb_entry_refresh: trace bridge FDB entry offload refreshed in + mlx5:: + + $ echo mlx5:mlx5_esw_bridge_fdb_entry_refresh >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:8-3849 [003] ...1 466716: mlx5_esw_bridge_fdb_entry_refresh: net_device=enp8s0f0_0 addr=e4:fd:05:08:00:02 vid=3 flags=0 used=0 + +- mlx5_esw_bridge_vlan_create: trace bridge VLAN object add on mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_create >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.460258: mlx5_esw_bridge_vlan_create: vid=1 flags=6 + +- mlx5_esw_bridge_vlan_cleanup: trace bridge VLAN object delete from mlx5 + representor:: + + $ echo mlx5:mlx5_esw_bridge_vlan_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + bridge-2582 [007] ...1 318.653496: mlx5_esw_bridge_vlan_cleanup: vid=2 flags=8 + +- mlx5_esw_bridge_vport_init: trace mlx5 vport assigned with bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_init >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-2560 [007] ...1 318.458915: mlx5_esw_bridge_vport_init: vport_num=1 + +- mlx5_esw_bridge_vport_cleanup: trace mlx5 vport removed from bridge upper + device:: + + $ echo mlx5:mlx5_esw_bridge_vport_cleanup >> set_event + $ cat /sys/kernel/debug/tracing/trace + ... + ip-5387 [000] ...1 573713: mlx5_esw_bridge_vport_cleanup: vport_num=1 + +Eswitch QoS tracepoints: + +- mlx5_esw_vport_qos_create: trace creation of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_create >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-23496 [018] .... 73136.838831: mlx5_esw_vport_qos_create: (0000:82:00.0) vport=2 tsar_ix=4 bw_share=0, max_rate=0 group=000000007b576bb3 + +- mlx5_esw_vport_qos_config: trace configuration of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_config >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-26548 [023] .... 75754.223823: mlx5_esw_vport_qos_config: (0000:82:00.0) vport=1 tsar_ix=3 bw_share=34, max_rate=10000 group=000000007b576bb3 + +- mlx5_esw_vport_qos_destroy: trace deletion of transmit scheduler arbiter for vport:: + + $ echo mlx5:mlx5_esw_vport_qos_destroy >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27418 [004] .... 76546.680901: mlx5_esw_vport_qos_destroy: (0000:82:00.0) vport=1 tsar_ix=3 + +- mlx5_esw_group_qos_create: trace creation of transmit scheduler arbiter for rate group:: + + $ echo mlx5:mlx5_esw_group_qos_create >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-26578 [008] .... 75776.022112: mlx5_esw_group_qos_create: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 + +- mlx5_esw_group_qos_config: trace configuration of transmit scheduler arbiter for rate group:: + + $ echo mlx5:mlx5_esw_group_qos_config >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27303 [020] .... 76461.455356: mlx5_esw_group_qos_config: (0000:82:00.0) group=000000008dac63ea tsar_ix=5 bw_share=100 max_rate=20000 + +- mlx5_esw_group_qos_destroy: trace deletion of transmit scheduler arbiter for group:: + + $ echo mlx5:mlx5_esw_group_qos_destroy >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + <...>-27418 [006] .... 76547.187258: mlx5_esw_group_qos_destroy: (0000:82:00.0) group=000000007b576bb3 tsar_ix=1 + +SF tracepoints: + +- mlx5_sf_add: trace addition of the SF port:: + + $ echo mlx5:mlx5_sf_add >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9363 [031] ..... 24610.188722: mlx5_sf_add: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 sfnum=88 + +- mlx5_sf_free: trace freeing of the SF port:: + + $ echo mlx5:mlx5_sf_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9830 [038] ..... 26300.404749: mlx5_sf_free: (0000:06:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_activate: trace activation of the SF port:: + + $ echo mlx5:mlx5_sf_activate >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-29841 [008] ..... 3669.635095: mlx5_sf_activate: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_deactivate: trace deactivation of the SF port:: + + $ echo mlx5:mlx5_sf_deactivate >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-29994 [008] ..... 4015.969467: mlx5_sf_deactivate: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 + +- mlx5_sf_hwc_alloc: trace allocating of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_alloc >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9775 [031] ..... 26296.385259: mlx5_sf_hwc_alloc: (0000:06:00.0) controller=0 hw_id=0x8000 sfnum=88 + +- mlx5_sf_hwc_free: trace freeing of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [046] ..... 24625.365771: mlx5_sf_hwc_free: (0000:06:00.0) hw_id=0x8000 + +- mlx5_sf_hwc_deferred_free: trace deferred freeing of the hardware SF context:: + + $ echo mlx5:mlx5_sf_hwc_deferred_free >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + devlink-9519 [046] ..... 24624.400271: mlx5_sf_hwc_deferred_free: (0000:06:00.0) hw_id=0x8000 + +- mlx5_sf_update_state: trace state updates for SF contexts:: + + $ echo mlx5:mlx5_sf_update_state >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u20:3-29490 [009] ..... 4141.453530: mlx5_sf_update_state: (0000:08:00.0) port_index=32768 controller=0 hw_id=0x8000 state=2 + +- mlx5_sf_vhca_event: trace SF vhca event and state:: + + $ echo mlx5:mlx5_sf_vhca_event >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [046] ..... 24625.365525: mlx5_sf_vhca_event: (0000:06:00.0) hw_id=0x8000 sfnum=88 vhca_state=1 + +- mlx5_sf_dev_add: trace SF device add event:: + + $ echo mlx5:mlx5_sf_dev_add>> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [000] ..... 24616.524495: mlx5_sf_dev_add: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 + +- mlx5_sf_dev_del: trace SF device delete event:: + + $ echo mlx5:mlx5_sf_dev_del >> /sys/kernel/debug/tracing/set_event + $ cat /sys/kernel/debug/tracing/trace + ... + kworker/u128:3-9093 [044] ..... 24624.400749: mlx5_sf_dev_del: (0000:06:00.0) sfdev=00000000fc5d96fd aux_id=4 hw_id=0x8000 sfnum=88 diff --git a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst index eaa87dbe8848..d052ef40fe36 100644 --- a/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst +++ b/Documentation/networking/device_drivers/ethernet/wangxun/txgbe.rst @@ -16,5 +16,5 @@ Contents Support ======= -If you got any problem, contact Wangxun support team via support@trustnetic.com +If you got any problem, contact Wangxun support team via nic-support@net-swift.com and Cc: netdev. diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9807b05a1b57..0a67cb738013 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8070,9 +8070,13 @@ considering the state as complete. VMM needs to ensure that the dirty state is final and avoid missing dirty pages from another ioctl ordered after the bitmap collection. -NOTE: One example of using the backup bitmap is saving arm64 vgic/its -tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on -KVM device "kvm-arm-vgic-its" when dirty ring is enabled. +NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its +tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on +KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through +command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device +"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save +vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES} +command on KVM device "kvm-arm-vgic-v3". 8.30 KVM_CAP_XEN_HVM -------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 2cf9eb43ed8f..f2bd469ffae5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15679,7 +15679,7 @@ OPENRISC ARCHITECTURE M: Jonas Bonn <jonas@southpole.se> M: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> M: Stafford Horne <shorne@gmail.com> -L: openrisc@lists.librecores.org +L: linux-openrisc@vger.kernel.org S: Maintained W: http://openrisc.io T: git https://github.com/openrisc/linux.git @@ -21752,6 +21752,7 @@ F: include/uapi/linux/uvcvideo.h USB WEBCAM GADGET M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> +M: Daniel Scally <dan.scally@ideasonboard.com> L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/gadget/function/*uvc* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 94a666dd1443..2642e9ce2819 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2187,7 +2187,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); + return vgic_write_guest_lock(kvm, gpa, &val, ite_esz); } /** @@ -2339,7 +2339,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); + return vgic_write_guest_lock(kvm, ptr, &val, dte_esz); } /** @@ -2526,7 +2526,7 @@ static int vgic_its_save_cte(struct vgic_its *its, ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); - return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); + return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz); } /* @@ -2607,7 +2607,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) */ val = 0; BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); + ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } @@ -2743,7 +2743,6 @@ static int vgic_its_has_attr(struct kvm_device *dev, static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); - struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ @@ -2763,9 +2762,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: - dist->save_its_tables_in_progress = true; ret = abi->save_tables(its); - dist->save_its_tables_in_progress = false; break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); @@ -2792,7 +2789,7 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - return dist->save_its_tables_in_progress; + return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 2624963cb95b..684bdfaad4a9 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -339,7 +339,7 @@ retry: if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } @@ -434,7 +434,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) else val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 23e280fa0a16..7f7f3c5ed85a 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -6,6 +6,7 @@ #define __KVM_ARM_VGIC_NEW_H__ #include <linux/irqchip/arm-gic-common.h> +#include <asm/kvm_mmu.h> #define PRODUCT_ID_KVM 0x4b /* ASCII code K */ #define IMPLEMENTER_ARM 0x43b @@ -131,6 +132,19 @@ static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) return vgic_irq_get_lr_count(irq) > 1; } +static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret; + + dist->table_write_in_progress = true; + ret = kvm_write_guest_lock(kvm, gpa, data, len); + dist->table_write_in_progress = false; + + return ret; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index f6a502e8f02c..6e948d015332 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u asmlinkage long ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp) { + struct timespec64 rtn_tp; + s64 tick_ns; + /* * ia64's clock_gettime() syscall is implemented as a vdso call * fsys_clock_gettime(). Currently it handles only @@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user * switch (which_clock) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: - s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); - struct timespec64 rtn_tp = ns_to_timespec64(tick_ns); + tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); + rtn_tp = ns_to_timespec64(tick_ns); return put_timespec64(&rtn_tp, tp); } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 4dfe1f49c5c8..6817892a2c58 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1303,7 +1303,7 @@ static char iodc_dbuf[4096] __page_aligned_bss; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; count = min_t(unsigned int, count, sizeof(iodc_dbuf)); @@ -1315,6 +1315,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1330,7 +1331,7 @@ print: __pa(pdc_result), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 69c62933e952..ceb45f51d52e 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -126,6 +126,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -166,7 +172,7 @@ long arch_ptrace(struct task_struct *child, long request, addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || @@ -181,14 +187,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -285,7 +291,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, if (addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ @@ -302,6 +308,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); @@ -484,7 +495,7 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val) case RI(iaoq[0]): case RI(iaoq[1]): /* set 2 lowest bits to ensure userspace privilege: */ - regs->iaoq[num - RI(iaoq[0])] = val | 3; + regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER; return; case RI(sar): regs->sar = val; return; diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dd39313242b4..d5cd16270c5d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -97,6 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) radix__tlb_flush(tlb); + + return hash__tlb_flush(tlb); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 77fa88c2aed0..eb6d094083fd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -173,6 +173,15 @@ static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) return flags; } +static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask) +{ + unsigned long flags = irq_soft_mask_return(); + + irq_soft_mask_set(flags & ~mask); + + return flags; +} + static inline unsigned long arch_local_save_flags(void) { return irq_soft_mask_return(); @@ -192,7 +201,7 @@ static inline void arch_local_irq_enable(void) static inline unsigned long arch_local_irq_save(void) { - return irq_soft_mask_set_return(IRQS_DISABLED); + return irq_soft_mask_or_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -331,10 +340,11 @@ bool power_pmu_wants_prompt_pmi(void); * is a different soft-masked interrupt pending that requires hard * masking. */ -static inline bool should_hard_irq_enable(void) +static inline bool should_hard_irq_enable(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS)); WARN_ON(mfmsr() & MSR_EE); } @@ -347,8 +357,17 @@ static inline bool should_hard_irq_enable(void) * * TODO: Add test for 64e */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi()) - return false; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (!power_pmu_wants_prompt_pmi()) + return false; + /* + * If PMIs are disabled then IRQs should be disabled as well, + * so we shouldn't see this condition, check for it just in + * case because we are about to enable PMIs. + */ + if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED)) + return false; + } if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK) return false; @@ -358,18 +377,16 @@ static inline bool should_hard_irq_enable(void) /* * Do the hard enabling, only call this if should_hard_irq_enable is true. + * This allows PMI interrupts to profile irq handlers. */ static inline void do_hard_irq_enable(void) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); - WARN_ON(mfmsr() & MSR_EE); - } /* - * This allows PMI interrupts (and watchdog soft-NMIs) through. - * There is no other reason to enable this way. + * Asynch interrupts come in with IRQS_ALL_DISABLED, + * PACA_IRQ_HARD_DIS, and MSR[EE]=0. */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + irq_soft_mask_andc_return(IRQS_PMI_DISABLED); get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; __hard_irq_enable(); } @@ -452,7 +469,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static __always_inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(struct pt_regs *regs) { return false; } diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f55c6fb34a3a..5712dd846263 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) ppc_msgsync(); - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index d438ca74e96c..fdbee1093e2b 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -864,7 +864,7 @@ _GLOBAL(load_up_spe) * SPE unavailable trap from kernel - print a message, but let * the task use SPE in the kernel until it returns to user mode. */ -KernelSPE: +SYM_FUNC_START_LOCAL(KernelSPE) lwz r3,_MSR(r1) oris r3,r3,MSR_SPE@h stw r3,_MSR(r1) /* enable use of SPE after return */ @@ -881,6 +881,7 @@ KernelSPE: #endif .align 4,0 +SYM_FUNC_END(KernelSPE) #endif /* CONFIG_SPE */ /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c5b9ce887483..c9535f2760b5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -238,7 +238,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp) irq = static_call(ppc_get_irq)(); /* We can hard enable interrupts now to allow perf interrupts */ - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); /* And finally process it */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index d68de3618741..e26eb6618ae5 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -515,7 +515,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { + if (should_hard_irq_enable(regs)) { /* * Ensure a positive value is written to the decrementer, or * else some CPUs will continue to take decrementer exceptions. diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index af8854f9eae3..52085751f5f4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -989,10 +989,13 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) * linux,drconf-usable-memory properties. Get an approximate on the * number of usable memory entries and use for FDT size estimation. */ - usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) + - (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); - - extra_size = (unsigned int)(usm_entries * sizeof(u64)); + if (drmem_lmb_size()) { + usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) + + (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); + extra_size = (unsigned int)(usm_entries * sizeof(u64)); + } else { + extra_size = 0; + } /* * Get the number of CPU nodes in the current DT. This allows to diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 0dce93ccaadf..e89281d3ba28 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -912,16 +912,15 @@ static int kvmppc_handle_debug(struct kvm_vcpu *vcpu) static void kvmppc_fill_pt_regs(struct pt_regs *regs) { - ulong r1, ip, msr, lr; + ulong r1, msr, lr; asm("mr %0, 1" : "=r"(r1)); asm("mflr %0" : "=r"(lr)); asm("mfmsr %0" : "=r"(msr)); - asm("bl 1f; 1: mflr %0" : "=r"(ip)); memset(regs, 0, sizeof(*regs)); regs->gpr[1] = r1; - regs->nip = ip; + regs->nip = _THIS_IP_; regs->msr = msr; regs->link = lr; } diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index cac727b01799..26245aaf12b8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -234,6 +234,14 @@ void radix__mark_rodata_ro(void) end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); + + for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) { + end = start + PAGE_SIZE; + if (overlaps_interrupt_vector_text(start, end)) + radix__change_memory_range(start, end, _PAGE_WRITE); + else + break; + } } void radix__mark_initmem_nx(void) @@ -262,6 +270,22 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX + unsigned long stext_phys; + + stext_phys = __pa_symbol(_stext); + + // Relocatable kernel running at non-zero real address + if (stext_phys != 0) { + // The end of interrupts code at zero is a rodata boundary + unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys; + if (addr < end_intr) + return end_intr; + + // Start of relocated kernel text is a rodata boundary + if (addr < stext_phys) + return stext_phys; + } + if (addr < __pa_symbol(__srwx_boundary)) return __pa_symbol(__srwx_boundary); #endif diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 100e97daf76b..9d229ef7f86e 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -22,7 +22,7 @@ * Used to avoid races in counting the nest-pmu units during hotplug * register and unregister */ -static DEFINE_SPINLOCK(nest_init_lock); +static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; @@ -1629,7 +1629,7 @@ static void imc_common_mem_free(struct imc_pmu *pmu_ptr) static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) { if (pmu_ptr->domain == IMC_DOMAIN_NEST) { - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); @@ -1639,7 +1639,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus > 0) nest_pmus--; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); } /* Free core_imc memory */ @@ -1796,11 +1796,11 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id * rest. To handle the cpuhotplug callback unregister, we track * the number of nest pmus in "nest_pmus". */ - spin_lock(&nest_init_lock); + mutex_lock(&nest_init_lock); if (nest_pmus == 0) { ret = init_nest_pmu_ref(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; goto err_free_mem; @@ -1808,7 +1808,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id /* Register for cpu hotplug notification. */ ret = nest_pmu_cpumask_init(); if (ret) { - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); kfree(nest_imc_refc); kfree(per_nest_pmu_arr); per_nest_pmu_arr = NULL; @@ -1816,7 +1816,7 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id } } nest_pmus++; - spin_unlock(&nest_init_lock); + mutex_unlock(&nest_init_lock); break; case IMC_DOMAIN_CORE: ret = core_imc_pmu_cpumask_init(); diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index faf2c2177094..82153960ac00 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -80,6 +80,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 86328e3acb02..64ad1937e714 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -70,7 +70,6 @@ static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX); */ enum riscv_isa_ext_key { RISCV_ISA_EXT_KEY_FPU, /* For 'F' and 'D' */ - RISCV_ISA_EXT_KEY_ZIHINTPAUSE, RISCV_ISA_EXT_KEY_SVINVAL, RISCV_ISA_EXT_KEY_MAX, }; @@ -91,8 +90,6 @@ static __always_inline int riscv_isa_ext2key(int num) return RISCV_ISA_EXT_KEY_FPU; case RISCV_ISA_EXT_d: return RISCV_ISA_EXT_KEY_FPU; - case RISCV_ISA_EXT_ZIHINTPAUSE: - return RISCV_ISA_EXT_KEY_ZIHINTPAUSE; case RISCV_ISA_EXT_SVINVAL: return RISCV_ISA_EXT_KEY_SVINVAL; default: diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index fa70cfe507aa..14f5d27783b8 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,30 +4,26 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> #include <asm/barrier.h> -#include <asm/hwcap.h> static inline void cpu_relax(void) { - if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) { #ifdef __riscv_muldiv - int dummy; - /* In lieu of a halt instruction, induce a long-latency stall. */ - __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); + int dummy; + /* In lieu of a halt instruction, induce a long-latency stall. */ + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif - } else { - /* - * Reduce instruction retirement. - * This assumes the PC changes. - */ -#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE - __asm__ __volatile__ ("pause"); + +#ifdef __riscv_zihintpause + /* + * Reduce instruction retirement. + * This assumes the PC changes. + */ + __asm__ __volatile__ ("pause"); #else - /* Encoding of the pause instruction */ - __asm__ __volatile__ (".4byte 0x100000F"); + /* Encoding of the pause instruction */ + __asm__ __volatile__ (".4byte 0x100000F"); #endif - } barrier(); } diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index f21592d20306..41c7481afde3 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -48,6 +48,21 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) post_kprobe_handler(p, kcb, regs); } +static bool __kprobes arch_check_kprobe(struct kprobe *p) +{ + unsigned long tmp = (unsigned long)p->addr - p->offset; + unsigned long addr = (unsigned long)p->addr; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long probe_addr = (unsigned long)p->addr; @@ -55,6 +70,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (probe_addr & 0x1) return -EILSEQ; + if (!arch_check_kprobe(p)) + return -EILSEQ; + /* copy instruction */ p->opcode = *p->addr; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index af35052d06ed..d0846ba818ee 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -30,6 +30,7 @@ #include <asm/facility.h> #include <asm/nospec-branch.h> #include <asm/set_memory.h> +#include <asm/text-patching.h> #include "bpf_jit.h" struct bpf_jit { @@ -50,12 +51,13 @@ struct bpf_jit { int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */ int tail_call_start; /* Tail call start offset */ int excnt; /* Number of exception table entries */ + int prologue_plt_ret; /* Return address for prologue hotpatch PLT */ + int prologue_plt; /* Start of prologue hotpatch PLT */ }; #define SEEN_MEM BIT(0) /* use mem[] for temporary storage */ #define SEEN_LITERAL BIT(1) /* code uses literals */ #define SEEN_FUNC BIT(2) /* calls C functions */ -#define SEEN_TAIL_CALL BIT(3) /* code uses tail calls */ #define SEEN_STACK (SEEN_FUNC | SEEN_MEM) /* @@ -68,6 +70,10 @@ struct bpf_jit { #define REG_0 REG_W0 /* Register 0 */ #define REG_1 REG_W1 /* Register 1 */ #define REG_2 BPF_REG_1 /* Register 2 */ +#define REG_3 BPF_REG_2 /* Register 3 */ +#define REG_4 BPF_REG_3 /* Register 4 */ +#define REG_7 BPF_REG_6 /* Register 7 */ +#define REG_8 BPF_REG_7 /* Register 8 */ #define REG_14 BPF_REG_0 /* Register 14 */ /* @@ -507,20 +513,58 @@ static void bpf_skip(struct bpf_jit *jit, int size) } /* + * PLT for hotpatchable calls. The calling convention is the same as for the + * ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered. + */ +extern const char bpf_plt[]; +extern const char bpf_plt_ret[]; +extern const char bpf_plt_target[]; +extern const char bpf_plt_end[]; +#define BPF_PLT_SIZE 32 +asm( + ".pushsection .rodata\n" + " .align 8\n" + "bpf_plt:\n" + " lgrl %r0,bpf_plt_ret\n" + " lgrl %r1,bpf_plt_target\n" + " br %r1\n" + " .align 8\n" + "bpf_plt_ret: .quad 0\n" + "bpf_plt_target: .quad 0\n" + "bpf_plt_end:\n" + " .popsection\n" +); + +static void bpf_jit_plt(void *plt, void *ret, void *target) +{ + memcpy(plt, bpf_plt, BPF_PLT_SIZE); + *(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret; + *(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target; +} + +/* * Emit function prologue * * Save registers and create stack frame if necessary. - * See stack frame layout desription in "bpf_jit.h"! + * See stack frame layout description in "bpf_jit.h"! */ -static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) +static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp, + u32 stack_depth) { - if (jit->seen & SEEN_TAIL_CALL) { + /* No-op for hotpatching */ + /* brcl 0,prologue_plt */ + EMIT6_PCREL_RILC(0xc0040000, 0, jit->prologue_plt); + jit->prologue_plt_ret = jit->prg; + + if (fp->aux->func_idx == 0) { + /* Initialize the tail call counter in the main program. */ /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */ _EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT); } else { /* - * There are no tail calls. Insert nops in order to have - * tail_call_start at a predictable offset. + * Skip the tail call counter initialization in subprograms. + * Insert nops in order to have tail_call_start at a + * predictable offset. */ bpf_skip(jit, 6); } @@ -558,6 +602,43 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) } /* + * Emit an expoline for a jump that follows + */ +static void emit_expoline(struct bpf_jit *jit) +{ + /* exrl %r0,.+10 */ + EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10); + /* j . */ + EMIT4_PCREL(0xa7f40000, 0); +} + +/* + * Emit __s390_indirect_jump_r1 thunk if necessary + */ +static void emit_r1_thunk(struct bpf_jit *jit) +{ + if (nospec_uses_trampoline()) { + jit->r1_thunk_ip = jit->prg; + emit_expoline(jit); + /* br %r1 */ + _EMIT2(0x07f1); + } +} + +/* + * Call r1 either directly or via __s390_indirect_jump_r1 thunk + */ +static void call_r1(struct bpf_jit *jit) +{ + if (nospec_uses_trampoline()) + /* brasl %r14,__s390_indirect_jump_r1 */ + EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip); + else + /* basr %r14,%r1 */ + EMIT2(0x0d00, REG_14, REG_1); +} + +/* * Function epilogue */ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) @@ -570,25 +651,20 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) if (nospec_uses_trampoline()) { jit->r14_thunk_ip = jit->prg; /* Generate __s390_indirect_jump_r14 thunk */ - /* exrl %r0,.+10 */ - EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10); - /* j . */ - EMIT4_PCREL(0xa7f40000, 0); + emit_expoline(jit); } /* br %r14 */ _EMIT2(0x07fe); - if ((nospec_uses_trampoline()) && - (is_first_pass(jit) || (jit->seen & SEEN_FUNC))) { - jit->r1_thunk_ip = jit->prg; - /* Generate __s390_indirect_jump_r1 thunk */ - /* exrl %r0,.+10 */ - EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10); - /* j . */ - EMIT4_PCREL(0xa7f40000, 0); - /* br %r1 */ - _EMIT2(0x07f1); - } + if (is_first_pass(jit) || (jit->seen & SEEN_FUNC)) + emit_r1_thunk(jit); + + jit->prg = ALIGN(jit->prg, 8); + jit->prologue_plt = jit->prg; + if (jit->prg_buf) + bpf_jit_plt(jit->prg_buf + jit->prg, + jit->prg_buf + jit->prologue_plt_ret, NULL); + jit->prg += BPF_PLT_SIZE; } static int get_probe_mem_regno(const u8 *insn) @@ -663,6 +739,34 @@ static int bpf_jit_probe_mem(struct bpf_jit *jit, struct bpf_prog *fp, } /* + * Sign-extend the register if necessary + */ +static int sign_extend(struct bpf_jit *jit, int r, u8 size, u8 flags) +{ + if (!(flags & BTF_FMODEL_SIGNED_ARG)) + return 0; + + switch (size) { + case 1: + /* lgbr %r,%r */ + EMIT4(0xb9060000, r, r); + return 0; + case 2: + /* lghr %r,%r */ + EMIT4(0xb9070000, r, r); + return 0; + case 4: + /* lgfr %r,%r */ + EMIT4(0xb9140000, r, r); + return 0; + case 8: + return 0; + default: + return -1; + } +} + +/* * Compile one eBPF instruction into s390x code * * NOTE: Use noinline because for gcov (-fprofile-arcs) gcc allocates a lot of @@ -1297,9 +1401,10 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, */ case BPF_JMP | BPF_CALL: { - u64 func; + const struct btf_func_model *m; bool func_addr_fixed; - int ret; + int j, ret; + u64 func; ret = bpf_jit_get_func_addr(fp, insn, extra_pass, &func, &func_addr_fixed); @@ -1308,15 +1413,38 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, REG_SET_SEEN(BPF_REG_5); jit->seen |= SEEN_FUNC; + /* + * Copy the tail call counter to where the callee expects it. + * + * Note 1: The callee can increment the tail call counter, but + * we do not load it back, since the x86 JIT does not do this + * either. + * + * Note 2: We assume that the verifier does not let us call the + * main program, which clears the tail call counter on entry. + */ + /* mvc STK_OFF_TCCNT(4,%r15),N(%r15) */ + _EMIT6(0xd203f000 | STK_OFF_TCCNT, + 0xf000 | (STK_OFF_TCCNT + STK_OFF + stack_depth)); + + /* Sign-extend the kfunc arguments. */ + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + m = bpf_jit_find_kfunc_model(fp, insn); + if (!m) + return -1; + + for (j = 0; j < m->nr_args; j++) { + if (sign_extend(jit, BPF_REG_1 + j, + m->arg_size[j], + m->arg_flags[j])) + return -1; + } + } + /* lgrl %w1,func */ EMIT6_PCREL_RILB(0xc4080000, REG_W1, _EMIT_CONST_U64(func)); - if (nospec_uses_trampoline()) { - /* brasl %r14,__s390_indirect_jump_r1 */ - EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip); - } else { - /* basr %r14,%w1 */ - EMIT2(0x0d00, REG_14, REG_W1); - } + /* %r1() */ + call_r1(jit); /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); break; @@ -1329,10 +1457,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, * B1: pointer to ctx * B2: pointer to bpf_array * B3: index in bpf_array - */ - jit->seen |= SEEN_TAIL_CALL; - - /* + * * if (index >= array->map.max_entries) * goto out; */ @@ -1393,8 +1518,16 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, /* lg %r1,bpf_func(%r1) */ EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, REG_1, REG_0, offsetof(struct bpf_prog, bpf_func)); - /* bc 0xf,tail_call_start(%r1) */ - _EMIT4(0x47f01000 + jit->tail_call_start); + if (nospec_uses_trampoline()) { + jit->seen |= SEEN_FUNC; + /* aghi %r1,tail_call_start */ + EMIT4_IMM(0xa70b0000, REG_1, jit->tail_call_start); + /* brcl 0xf,__s390_indirect_jump_r1 */ + EMIT6_PCREL_RILC(0xc0040000, 0xf, jit->r1_thunk_ip); + } else { + /* bc 0xf,tail_call_start(%r1) */ + _EMIT4(0x47f01000 + jit->tail_call_start); + } /* out: */ if (jit->prg_buf) { *(u16 *)(jit->prg_buf + patch_1_clrj + 2) = @@ -1688,7 +1821,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp, jit->prg = 0; jit->excnt = 0; - bpf_jit_prologue(jit, stack_depth); + bpf_jit_prologue(jit, fp, stack_depth); if (bpf_set_addr(jit, 0) < 0) return -1; for (i = 0; i < fp->len; i += insn_count) { @@ -1768,6 +1901,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) struct bpf_jit jit; int pass; + if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE)) + return orig_fp; + if (!fp->jit_requested) return orig_fp; @@ -1859,3 +1995,508 @@ out: tmp : orig_fp); return fp; } + +bool bpf_jit_supports_kfunc_call(void) +{ + return true; +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *old_addr, void *new_addr) +{ + struct { + u16 opc; + s32 disp; + } __packed insn; + char expected_plt[BPF_PLT_SIZE]; + char current_plt[BPF_PLT_SIZE]; + char *plt; + int err; + + /* Verify the branch to be patched. */ + err = copy_from_kernel_nofault(&insn, ip, sizeof(insn)); + if (err < 0) + return err; + if (insn.opc != (0xc004 | (old_addr ? 0xf0 : 0))) + return -EINVAL; + + if (t == BPF_MOD_JUMP && + insn.disp == ((char *)new_addr - (char *)ip) >> 1) { + /* + * The branch already points to the destination, + * there is no PLT. + */ + } else { + /* Verify the PLT. */ + plt = (char *)ip + (insn.disp << 1); + err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE); + if (err < 0) + return err; + bpf_jit_plt(expected_plt, (char *)ip + 6, old_addr); + if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE)) + return -EINVAL; + /* Adjust the call address. */ + s390_kernel_write(plt + (bpf_plt_target - bpf_plt), + &new_addr, sizeof(void *)); + } + + /* Adjust the mask of the branch. */ + insn.opc = 0xc004 | (new_addr ? 0xf0 : 0); + s390_kernel_write((char *)ip + 1, (char *)&insn.opc + 1, 1); + + /* Make the new code visible to the other CPUs. */ + text_poke_sync_lock(); + + return 0; +} + +struct bpf_tramp_jit { + struct bpf_jit common; + int orig_stack_args_off;/* Offset of arguments placed on stack by the + * func_addr's original caller + */ + int stack_size; /* Trampoline stack size */ + int stack_args_off; /* Offset of stack arguments for calling + * func_addr, has to be at the top + */ + int reg_args_off; /* Offset of register arguments for calling + * func_addr + */ + int ip_off; /* For bpf_get_func_ip(), has to be at + * (ctx - 16) + */ + int arg_cnt_off; /* For bpf_get_func_arg_cnt(), has to be at + * (ctx - 8) + */ + int bpf_args_off; /* Offset of BPF_PROG context, which consists + * of BPF arguments followed by return value + */ + int retval_off; /* Offset of return value (see above) */ + int r7_r8_off; /* Offset of saved %r7 and %r8, which are used + * for __bpf_prog_enter() return value and + * func_addr respectively + */ + int r14_off; /* Offset of saved %r14 */ + int run_ctx_off; /* Offset of struct bpf_tramp_run_ctx */ + int do_fexit; /* do_fexit: label */ +}; + +static void load_imm64(struct bpf_jit *jit, int dst_reg, u64 val) +{ + /* llihf %dst_reg,val_hi */ + EMIT6_IMM(0xc00e0000, dst_reg, (val >> 32)); + /* oilf %rdst_reg,val_lo */ + EMIT6_IMM(0xc00d0000, dst_reg, val); +} + +static int invoke_bpf_prog(struct bpf_tramp_jit *tjit, + const struct btf_func_model *m, + struct bpf_tramp_link *tlink, bool save_ret) +{ + struct bpf_jit *jit = &tjit->common; + int cookie_off = tjit->run_ctx_off + + offsetof(struct bpf_tramp_run_ctx, bpf_cookie); + struct bpf_prog *p = tlink->link.prog; + int patch; + + /* + * run_ctx.cookie = tlink->cookie; + */ + + /* %r0 = tlink->cookie */ + load_imm64(jit, REG_W0, tlink->cookie); + /* stg %r0,cookie_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W0, REG_0, REG_15, cookie_off); + + /* + * if ((start = __bpf_prog_enter(p, &run_ctx)) == 0) + * goto skip; + */ + + /* %r1 = __bpf_prog_enter */ + load_imm64(jit, REG_1, (u64)bpf_trampoline_enter(p)); + /* %r2 = p */ + load_imm64(jit, REG_2, (u64)p); + /* la %r3,run_ctx_off(%r15) */ + EMIT4_DISP(0x41000000, REG_3, REG_15, tjit->run_ctx_off); + /* %r1() */ + call_r1(jit); + /* ltgr %r7,%r2 */ + EMIT4(0xb9020000, REG_7, REG_2); + /* brcl 8,skip */ + patch = jit->prg; + EMIT6_PCREL_RILC(0xc0040000, 8, 0); + + /* + * retval = bpf_func(args, p->insnsi); + */ + + /* %r1 = p->bpf_func */ + load_imm64(jit, REG_1, (u64)p->bpf_func); + /* la %r2,bpf_args_off(%r15) */ + EMIT4_DISP(0x41000000, REG_2, REG_15, tjit->bpf_args_off); + /* %r3 = p->insnsi */ + if (!p->jited) + load_imm64(jit, REG_3, (u64)p->insnsi); + /* %r1() */ + call_r1(jit); + /* stg %r2,retval_off(%r15) */ + if (save_ret) { + if (sign_extend(jit, REG_2, m->ret_size, m->ret_flags)) + return -1; + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_2, REG_0, REG_15, + tjit->retval_off); + } + + /* skip: */ + if (jit->prg_buf) + *(u32 *)&jit->prg_buf[patch + 2] = (jit->prg - patch) >> 1; + + /* + * __bpf_prog_exit(p, start, &run_ctx); + */ + + /* %r1 = __bpf_prog_exit */ + load_imm64(jit, REG_1, (u64)bpf_trampoline_exit(p)); + /* %r2 = p */ + load_imm64(jit, REG_2, (u64)p); + /* lgr %r3,%r7 */ + EMIT4(0xb9040000, REG_3, REG_7); + /* la %r4,run_ctx_off(%r15) */ + EMIT4_DISP(0x41000000, REG_4, REG_15, tjit->run_ctx_off); + /* %r1() */ + call_r1(jit); + + return 0; +} + +static int alloc_stack(struct bpf_tramp_jit *tjit, size_t size) +{ + int stack_offset = tjit->stack_size; + + tjit->stack_size += size; + return stack_offset; +} + +/* ABI uses %r2 - %r6 for parameter passing. */ +#define MAX_NR_REG_ARGS 5 + +/* The "L" field of the "mvc" instruction is 8 bits. */ +#define MAX_MVC_SIZE 256 +#define MAX_NR_STACK_ARGS (MAX_MVC_SIZE / sizeof(u64)) + +/* -mfentry generates a 6-byte nop on s390x. */ +#define S390X_PATCH_SIZE 6 + +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, + struct bpf_tramp_jit *tjit, + const struct btf_func_model *m, + u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) +{ + struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN]; + struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY]; + struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT]; + int nr_bpf_args, nr_reg_args, nr_stack_args; + struct bpf_jit *jit = &tjit->common; + int arg, bpf_arg_off; + int i, j; + + /* Support as many stack arguments as "mvc" instruction can handle. */ + nr_reg_args = min_t(int, m->nr_args, MAX_NR_REG_ARGS); + nr_stack_args = m->nr_args - nr_reg_args; + if (nr_stack_args > MAX_NR_STACK_ARGS) + return -ENOTSUPP; + + /* Return to %r14, since func_addr and %r0 are not available. */ + if (!func_addr && !(flags & BPF_TRAMP_F_ORIG_STACK)) + flags |= BPF_TRAMP_F_SKIP_FRAME; + + /* + * Compute how many arguments we need to pass to BPF programs. + * BPF ABI mirrors that of x86_64: arguments that are 16 bytes or + * smaller are packed into 1 or 2 registers; larger arguments are + * passed via pointers. + * In s390x ABI, arguments that are 8 bytes or smaller are packed into + * a register; larger arguments are passed via pointers. + * We need to deal with this difference. + */ + nr_bpf_args = 0; + for (i = 0; i < m->nr_args; i++) { + if (m->arg_size[i] <= 8) + nr_bpf_args += 1; + else if (m->arg_size[i] <= 16) + nr_bpf_args += 2; + else + return -ENOTSUPP; + } + + /* + * Calculate the stack layout. + */ + + /* Reserve STACK_FRAME_OVERHEAD bytes for the callees. */ + tjit->stack_size = STACK_FRAME_OVERHEAD; + tjit->stack_args_off = alloc_stack(tjit, nr_stack_args * sizeof(u64)); + tjit->reg_args_off = alloc_stack(tjit, nr_reg_args * sizeof(u64)); + tjit->ip_off = alloc_stack(tjit, sizeof(u64)); + tjit->arg_cnt_off = alloc_stack(tjit, sizeof(u64)); + tjit->bpf_args_off = alloc_stack(tjit, nr_bpf_args * sizeof(u64)); + tjit->retval_off = alloc_stack(tjit, sizeof(u64)); + tjit->r7_r8_off = alloc_stack(tjit, 2 * sizeof(u64)); + tjit->r14_off = alloc_stack(tjit, sizeof(u64)); + tjit->run_ctx_off = alloc_stack(tjit, + sizeof(struct bpf_tramp_run_ctx)); + /* The caller has already reserved STACK_FRAME_OVERHEAD bytes. */ + tjit->stack_size -= STACK_FRAME_OVERHEAD; + tjit->orig_stack_args_off = tjit->stack_size + STACK_FRAME_OVERHEAD; + + /* aghi %r15,-stack_size */ + EMIT4_IMM(0xa70b0000, REG_15, -tjit->stack_size); + /* stmg %r2,%rN,fwd_reg_args_off(%r15) */ + if (nr_reg_args) + EMIT6_DISP_LH(0xeb000000, 0x0024, REG_2, + REG_2 + (nr_reg_args - 1), REG_15, + tjit->reg_args_off); + for (i = 0, j = 0; i < m->nr_args; i++) { + if (i < MAX_NR_REG_ARGS) + arg = REG_2 + i; + else + arg = tjit->orig_stack_args_off + + (i - MAX_NR_REG_ARGS) * sizeof(u64); + bpf_arg_off = tjit->bpf_args_off + j * sizeof(u64); + if (m->arg_size[i] <= 8) { + if (i < MAX_NR_REG_ARGS) + /* stg %arg,bpf_arg_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, arg, + REG_0, REG_15, bpf_arg_off); + else + /* mvc bpf_arg_off(8,%r15),arg(%r15) */ + _EMIT6(0xd207f000 | bpf_arg_off, + 0xf000 | arg); + j += 1; + } else { + if (i < MAX_NR_REG_ARGS) { + /* mvc bpf_arg_off(16,%r15),0(%arg) */ + _EMIT6(0xd20ff000 | bpf_arg_off, + reg2hex[arg] << 12); + } else { + /* lg %r1,arg(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0004, REG_1, REG_0, + REG_15, arg); + /* mvc bpf_arg_off(16,%r15),0(%r1) */ + _EMIT6(0xd20ff000 | bpf_arg_off, 0x1000); + } + j += 2; + } + } + /* stmg %r7,%r8,r7_r8_off(%r15) */ + EMIT6_DISP_LH(0xeb000000, 0x0024, REG_7, REG_8, REG_15, + tjit->r7_r8_off); + /* stg %r14,r14_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_14, REG_0, REG_15, tjit->r14_off); + + if (flags & BPF_TRAMP_F_ORIG_STACK) { + /* + * The ftrace trampoline puts the return address (which is the + * address of the original function + S390X_PATCH_SIZE) into + * %r0; see ftrace_shared_hotpatch_trampoline_br and + * ftrace_init_nop() for details. + */ + + /* lgr %r8,%r0 */ + EMIT4(0xb9040000, REG_8, REG_0); + } else { + /* %r8 = func_addr + S390X_PATCH_SIZE */ + load_imm64(jit, REG_8, (u64)func_addr + S390X_PATCH_SIZE); + } + + /* + * ip = func_addr; + * arg_cnt = m->nr_args; + */ + + if (flags & BPF_TRAMP_F_IP_ARG) { + /* %r0 = func_addr */ + load_imm64(jit, REG_0, (u64)func_addr); + /* stg %r0,ip_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_0, REG_0, REG_15, + tjit->ip_off); + } + /* lghi %r0,nr_bpf_args */ + EMIT4_IMM(0xa7090000, REG_0, nr_bpf_args); + /* stg %r0,arg_cnt_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_0, REG_0, REG_15, + tjit->arg_cnt_off); + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* + * __bpf_tramp_enter(im); + */ + + /* %r1 = __bpf_tramp_enter */ + load_imm64(jit, REG_1, (u64)__bpf_tramp_enter); + /* %r2 = im */ + load_imm64(jit, REG_2, (u64)im); + /* %r1() */ + call_r1(jit); + } + + for (i = 0; i < fentry->nr_links; i++) + if (invoke_bpf_prog(tjit, m, fentry->links[i], + flags & BPF_TRAMP_F_RET_FENTRY_RET)) + return -EINVAL; + + if (fmod_ret->nr_links) { + /* + * retval = 0; + */ + + /* xc retval_off(8,%r15),retval_off(%r15) */ + _EMIT6(0xd707f000 | tjit->retval_off, + 0xf000 | tjit->retval_off); + + for (i = 0; i < fmod_ret->nr_links; i++) { + if (invoke_bpf_prog(tjit, m, fmod_ret->links[i], true)) + return -EINVAL; + + /* + * if (retval) + * goto do_fexit; + */ + + /* ltg %r0,retval_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0002, REG_0, REG_0, REG_15, + tjit->retval_off); + /* brcl 7,do_fexit */ + EMIT6_PCREL_RILC(0xc0040000, 7, tjit->do_fexit); + } + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* + * retval = func_addr(args); + */ + + /* lmg %r2,%rN,reg_args_off(%r15) */ + if (nr_reg_args) + EMIT6_DISP_LH(0xeb000000, 0x0004, REG_2, + REG_2 + (nr_reg_args - 1), REG_15, + tjit->reg_args_off); + /* mvc stack_args_off(N,%r15),orig_stack_args_off(%r15) */ + if (nr_stack_args) + _EMIT6(0xd200f000 | + (nr_stack_args * sizeof(u64) - 1) << 16 | + tjit->stack_args_off, + 0xf000 | tjit->orig_stack_args_off); + /* lgr %r1,%r8 */ + EMIT4(0xb9040000, REG_1, REG_8); + /* %r1() */ + call_r1(jit); + /* stg %r2,retval_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0024, REG_2, REG_0, REG_15, + tjit->retval_off); + + im->ip_after_call = jit->prg_buf + jit->prg; + + /* + * The following nop will be patched by bpf_tramp_image_put(). + */ + + /* brcl 0,im->ip_epilogue */ + EMIT6_PCREL_RILC(0xc0040000, 0, (u64)im->ip_epilogue); + } + + /* do_fexit: */ + tjit->do_fexit = jit->prg; + for (i = 0; i < fexit->nr_links; i++) + if (invoke_bpf_prog(tjit, m, fexit->links[i], false)) + return -EINVAL; + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = jit->prg_buf + jit->prg; + + /* + * __bpf_tramp_exit(im); + */ + + /* %r1 = __bpf_tramp_exit */ + load_imm64(jit, REG_1, (u64)__bpf_tramp_exit); + /* %r2 = im */ + load_imm64(jit, REG_2, (u64)im); + /* %r1() */ + call_r1(jit); + } + + /* lmg %r2,%rN,reg_args_off(%r15) */ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && nr_reg_args) + EMIT6_DISP_LH(0xeb000000, 0x0004, REG_2, + REG_2 + (nr_reg_args - 1), REG_15, + tjit->reg_args_off); + /* lgr %r1,%r8 */ + if (!(flags & BPF_TRAMP_F_SKIP_FRAME)) + EMIT4(0xb9040000, REG_1, REG_8); + /* lmg %r7,%r8,r7_r8_off(%r15) */ + EMIT6_DISP_LH(0xeb000000, 0x0004, REG_7, REG_8, REG_15, + tjit->r7_r8_off); + /* lg %r14,r14_off(%r15) */ + EMIT6_DISP_LH(0xe3000000, 0x0004, REG_14, REG_0, REG_15, tjit->r14_off); + /* lg %r2,retval_off(%r15) */ + if (flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET)) + EMIT6_DISP_LH(0xe3000000, 0x0004, REG_2, REG_0, REG_15, + tjit->retval_off); + /* aghi %r15,stack_size */ + EMIT4_IMM(0xa70b0000, REG_15, tjit->stack_size); + /* Emit an expoline for the following indirect jump. */ + if (nospec_uses_trampoline()) + emit_expoline(jit); + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* br %r14 */ + _EMIT2(0x07fe); + else + /* br %r1 */ + _EMIT2(0x07f1); + + emit_r1_thunk(jit); + + return 0; +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, + void *image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_links *tlinks, + void *func_addr) +{ + struct bpf_tramp_jit tjit; + int ret; + int i; + + for (i = 0; i < 2; i++) { + if (i == 0) { + /* Compute offsets, check whether the code fits. */ + memset(&tjit, 0, sizeof(tjit)); + } else { + /* Generate the code. */ + tjit.common.prg = 0; + tjit.common.prg_buf = image; + } + ret = __arch_prepare_bpf_trampoline(im, &tjit, m, flags, + tlinks, func_addr); + if (ret < 0) + return ret; + if (tjit.common.prg > (char *)image_end - (char *)image) + /* + * Use the same error code as for exceeding + * BPF_MAX_TRAMP_LINKS. + */ + return -E2BIG; + } + + return ret; +} + +bool bpf_jit_supports_subprog_tailcalls(void) +{ + return true; +} diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 3161b9ccd2a5..b6276a3521d7 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ * Written by Niibe Yutaka and Paul Mundt */ OUTPUT_ARCH(sh) +#define RUNTIME_DISCARD_EXIT #include <asm/thread_info.h> #include <asm/cache.h> #include <asm/vmlinux.lds.h> diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b049d950612f..ca97442e8d49 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 7d9b15f0dbd5..0fbde0fc0628 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -769,8 +769,8 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, * request from the old cgroup. */ bfq_put_cooperator(sync_bfqq); - bfq_release_process_ref(bfqd, sync_bfqq); bic_set_bfqq(bic, NULL, true); + bfq_release_process_ref(bfqd, sync_bfqq); } } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ccf2204477a5..380e9bda2e57 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5425,9 +5425,11 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - bfq_release_process_ref(bfqd, bfqq); + struct bfq_queue *old_bfqq = bfqq; + bfqq = bfq_get_queue(bfqd, bio, false, bic, true); bic_set_bfqq(bic, bfqq, false); + bfq_release_process_ref(bfqd, old_bfqq); } bfqq = bic_to_bfqq(bic, true); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4c94a6560f62..9ac1efb053e0 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -2001,6 +2001,10 @@ void blk_cgroup_bio_start(struct bio *bio) struct blkg_iostat_set *bis; unsigned long flags; + /* Root-level stats are sourced from system-wide IO stats */ + if (!cgroup_parent(blkcg->css.cgroup)) + return; + cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); diff --git a/block/blk-mq.c b/block/blk-mq.c index 9d463f7563bc..9c8dc70020bc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4069,8 +4069,9 @@ EXPORT_SYMBOL(blk_mq_init_queue); * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * - * This shuts down a request queue allocated by blk_mq_init_queue() and drops - * the initial reference. All future requests will failed with -ENODEV. + * This shuts down a request queue allocated by blk_mq_init_queue(). All future + * requests will be failed with -ENODEV. The caller is responsible for dropping + * the reference from blk_mq_init_queue() by calling blk_put_queue(). * * Context: can sleep */ diff --git a/certs/Makefile b/certs/Makefile index 9486ed924731..799ad7b9e68a 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -23,8 +23,8 @@ $(obj)/blacklist_hash_list: $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) FORCE targets += blacklist_hash_list quiet_cmd_extract_certs = CERT $@ - cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@ -extract-cert-in = $(or $(filter-out $(obj)/extract-cert, $(real-prereqs)),"") + cmd_extract_certs = $(obj)/extract-cert "$(extract-cert-in)" $@ +extract-cert-in = $(filter-out $(obj)/extract-cert, $(real-prereqs)) $(obj)/system_certificates.o: $(obj)/x509_certificate_list diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 884ae73b11ea..2ea572628b1c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3109,7 +3109,7 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; - else + else if (link->sata_spd) return -EINVAL; /* were we already at the bottom? */ diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index e54693204630..6368b56eacf1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -137,7 +137,7 @@ struct ublk_device { char *__queues; - unsigned short queue_size; + unsigned int queue_size; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index d4e2cb9a4eb4..bede8b005594 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/firmware.h> #include <linux/regmap.h> +#include <linux/acpi.h> #include <asm/unaligned.h> #include <net/bluetooth/bluetooth.h> @@ -24,6 +25,9 @@ #define ECDSA_OFFSET 644 #define ECDSA_HEADER_LEN 320 +#define BTINTEL_PPAG_NAME "PPAG" +#define BTINTEL_PPAG_PREFIX "\\_SB_.PCI0.XHCI.RHUB" + #define CMD_WRITE_BOOT_PARAMS 0xfc0e struct cmd_write_boot_params { __le32 boot_addr; @@ -1278,6 +1282,63 @@ static int btintel_read_debug_features(struct hci_dev *hdev, return 0; } +static acpi_status btintel_ppag_callback(acpi_handle handle, u32 lvl, void *data, + void **ret) +{ + acpi_status status; + size_t len; + struct btintel_ppag *ppag = data; + union acpi_object *p, *elements; + struct acpi_buffer string = {ACPI_ALLOCATE_BUFFER, NULL}; + struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL}; + struct hci_dev *hdev = ppag->hdev; + + status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &string); + if (ACPI_FAILURE(status)) { + bt_dev_warn(hdev, "ACPI Failure: %s", acpi_format_exception(status)); + return status; + } + + if (strncmp(BTINTEL_PPAG_PREFIX, string.pointer, + strlen(BTINTEL_PPAG_PREFIX))) { + kfree(string.pointer); + return AE_OK; + } + + len = strlen(string.pointer); + if (strncmp((char *)string.pointer + len - 4, BTINTEL_PPAG_NAME, 4)) { + kfree(string.pointer); + return AE_OK; + } + kfree(string.pointer); + + status = acpi_evaluate_object(handle, NULL, NULL, &buffer); + if (ACPI_FAILURE(status)) { + bt_dev_warn(hdev, "ACPI Failure: %s", acpi_format_exception(status)); + return status; + } + + p = buffer.pointer; + ppag = (struct btintel_ppag *)data; + + if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 2) { + kfree(buffer.pointer); + bt_dev_warn(hdev, "Invalid object type: %d or package count: %d", + p->type, p->package.count); + return AE_ERROR; + } + + elements = p->package.elements; + + /* PPAG table is located at element[1] */ + p = &elements[1]; + + ppag->domain = (u32)p->package.elements[0].integer.value; + ppag->mode = (u32)p->package.elements[1].integer.value; + kfree(buffer.pointer); + return AE_CTRL_TERMINATE; +} + static int btintel_set_debug_features(struct hci_dev *hdev, const struct intel_debug_features *features) { @@ -2251,6 +2312,58 @@ error: return err; } +static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver) +{ + acpi_status status; + struct btintel_ppag ppag; + struct sk_buff *skb; + struct btintel_loc_aware_reg ppag_cmd; + + /* PPAG is not supported if CRF is HrP2, Jfp2, JfP1 */ + switch (ver->cnvr_top & 0xFFF) { + case 0x504: /* Hrp2 */ + case 0x202: /* Jfp2 */ + case 0x201: /* Jfp1 */ + return; + } + + memset(&ppag, 0, sizeof(ppag)); + + ppag.hdev = hdev; + status = acpi_walk_namespace(ACPI_TYPE_ANY, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, NULL, + btintel_ppag_callback, &ppag, NULL); + + if (ACPI_FAILURE(status)) { + /* Do not log warning message if ACPI entry is not found */ + if (status == AE_NOT_FOUND) + return; + bt_dev_warn(hdev, "PPAG: ACPI Failure: %s", acpi_format_exception(status)); + return; + } + + if (ppag.domain != 0x12) { + bt_dev_warn(hdev, "PPAG-BT Domain disabled"); + return; + } + + /* PPAG mode, BIT0 = 0 Disabled, BIT0 = 1 Enabled */ + if (!(ppag.mode & BIT(0))) { + bt_dev_dbg(hdev, "PPAG disabled"); + return; + } + + ppag_cmd.mcc = cpu_to_le32(0); + ppag_cmd.sel = cpu_to_le32(0); /* 0 - Enable , 1 - Disable, 2 - Testing mode */ + ppag_cmd.delta = cpu_to_le32(0); + skb = __hci_cmd_sync(hdev, 0xfe19, sizeof(ppag_cmd), &ppag_cmd, HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_warn(hdev, "Failed to send PPAG Enable (%ld)", PTR_ERR(skb)); + return; + } + kfree_skb(skb); +} + static int btintel_bootloader_setup_tlv(struct hci_dev *hdev, struct intel_version_tlv *ver) { @@ -2297,6 +2410,9 @@ static int btintel_bootloader_setup_tlv(struct hci_dev *hdev, hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); + /* Set PPAG feature */ + btintel_set_ppag(hdev, ver); + /* Read the Intel version information after loading the FW */ err = btintel_read_version_tlv(hdev, &new_ver); if (err) diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index e0060e58573c..8e7da877efae 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -137,6 +137,19 @@ struct intel_offload_use_cases { __u8 preset[8]; } __packed; +/* structure to store the PPAG data read from ACPI table */ +struct btintel_ppag { + u32 domain; + u32 mode; + struct hci_dev *hdev; +}; + +struct btintel_loc_aware_reg { + __le32 mcc; + __le32 sel; + __le32 delta; +} __packed; + #define INTEL_HW_PLATFORM(cnvx_bt) ((u8)(((cnvx_bt) & 0x0000ff00) >> 8)) #define INTEL_HW_VARIANT(cnvx_bt) ((u8)(((cnvx_bt) & 0x003f0000) >> 16)) #define INTEL_CNVX_TOP_TYPE(cnvx_top) ((cnvx_top) & 0x00000fff) diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 2ad4efdd9e40..18bc94718711 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -64,6 +64,7 @@ static struct usb_driver btusb_driver; #define BTUSB_INTEL_BROKEN_SHUTDOWN_LED BIT(24) #define BTUSB_INTEL_BROKEN_INITIAL_NCMD BIT(25) #define BTUSB_INTEL_NO_WBS_SUPPORT BIT(26) +#define BTUSB_ACTIONS_SEMI BIT(27) static const struct usb_device_id btusb_table[] = { /* Generic Bluetooth USB device */ @@ -492,6 +493,10 @@ static const struct usb_device_id blacklist_table[] = { { USB_VENDOR_AND_INTERFACE_INFO(0x8087, 0xe0, 0x01, 0x01), .driver_info = BTUSB_IGNORE }, + /* Realtek 8821CE Bluetooth devices */ + { USB_DEVICE(0x13d3, 0x3529), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + /* Realtek 8822CE Bluetooth devices */ { USB_DEVICE(0x0bda, 0xb00c), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, @@ -566,6 +571,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe0e0), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x0489, 0xe0f2), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, { USB_DEVICE(0x04ca, 0x3802), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, @@ -677,6 +685,9 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0cb5, 0xc547), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + /* Actions Semiconductor ATS2851 based devices */ + { USB_DEVICE(0x10d7, 0xb012), .driver_info = BTUSB_ACTIONS_SEMI }, + /* Silicon Wave based devices */ { USB_DEVICE(0x0c10, 0x0000), .driver_info = BTUSB_SWAVE }, @@ -4098,6 +4109,11 @@ static int btusb_probe(struct usb_interface *intf, set_bit(BTUSB_USE_ALT3_FOR_WBS, &data->flags); } + if (id->driver_info & BTUSB_ACTIONS_SEMI) { + /* Support is advertised, but not implemented */ + set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks); + } + if (!reset) set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index bbe9cf1cae27..3df8c3606e93 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -128,13 +128,13 @@ struct qca_memdump_event_hdr { __u8 evt; __u8 plen; __u16 opcode; - __u16 seq_no; + __le16 seq_no; __u8 reserved; } __packed; struct qca_dump_size { - u32 dump_size; + __le32 dump_size; } __packed; struct qca_data { @@ -1588,10 +1588,11 @@ static bool qca_wakeup(struct hci_dev *hdev) struct hci_uart *hu = hci_get_drvdata(hdev); bool wakeup; - /* UART driver handles the interrupt from BT SoC.So we need to use - * device handle of UART driver to get the status of device may wakeup. + /* BT SoC attached through the serial bus is handled by the serdev driver. + * So we need to use the device handle of the serdev driver to get the + * status of device may wakeup. */ - wakeup = device_may_wakeup(hu->serdev->ctrl->dev.parent); + wakeup = device_may_wakeup(&hu->serdev->ctrl->dev); bt_dev_dbg(hu->hdev, "wakeup status : %d", wakeup); return wakeup; diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 406b4e26f538..0de0482cd36e 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -167,7 +167,7 @@ struct dma_fence *dma_fence_allocate_private_stub(void) 0, 0); set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &dma_fence_stub.flags); + &fence->flags); dma_fence_signal(fence); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index a2b0cbc8741c..1e0b016fdc2b 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -1007,6 +1007,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); + if (!rsv) + return -ENOMEM; index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 0a9aba5f9cef..f178b2984dfb 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -33,7 +33,7 @@ int __init efi_memattr_init(void) return -ENOMEM; } - if (tbl->version > 1) { + if (tbl->version > 2) { pr_warn("Unexpected EFI Memory Attributes table version %d\n", tbl->version); goto unmap; diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 79d48852825e..03f1bd81c434 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -574,20 +574,27 @@ static int m10bmc_sec_probe(struct platform_device *pdev) len = scnprintf(buf, SEC_UPDATE_LEN_MAX, "secure-update%d", sec->fw_name_id); sec->fw_name = kmemdup_nul(buf, len, GFP_KERNEL); - if (!sec->fw_name) - return -ENOMEM; + if (!sec->fw_name) { + ret = -ENOMEM; + goto fw_name_fail; + } fwl = firmware_upload_register(THIS_MODULE, sec->dev, sec->fw_name, &m10bmc_ops, sec); if (IS_ERR(fwl)) { dev_err(sec->dev, "Firmware Upload driver failed to start\n"); - kfree(sec->fw_name); - xa_erase(&fw_upload_xa, sec->fw_name_id); - return PTR_ERR(fwl); + ret = PTR_ERR(fwl); + goto fw_uploader_fail; } sec->fwl = fwl; return 0; + +fw_uploader_fail: + kfree(sec->fw_name); +fw_name_fail: + xa_erase(&fw_upload_xa, sec->fw_name_id); + return ret; } static int m10bmc_sec_remove(struct platform_device *pdev) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 357cea58ec98..f7f01982a512 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -213,9 +213,9 @@ static int s10_ops_write_init(struct fpga_manager *mgr, /* Allocate buffers from the service layer's pool. */ for (i = 0; i < NUM_SVC_BUFS; i++) { kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE); - if (!kbuf) { + if (IS_ERR(kbuf)) { s10_free_buffers(mgr); - ret = -ENOMEM; + ret = PTR_ERR(kbuf); goto init_done; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index b9b57a66e113..66eb102cd88f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -790,8 +790,8 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, * zero here */ WARN_ON(simd != 0); - /* type 2 wave data */ - dst[(*no_fields)++] = 2; + /* type 3 wave data */ + dst[(*no_fields)++] = 3; dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 15eb3658d70e..09fdcd20cb91 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -337,7 +337,13 @@ const struct nbio_hdp_flush_reg nbio_v4_3_hdp_flush_reg = { static void nbio_v4_3_init_registers(struct amdgpu_device *adev) { - return; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) { + uint32_t data; + + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2); + data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); + } } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 5562670b7b52..9eff5f41df9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -640,7 +640,8 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | - AMD_CG_SUPPORT_GFX_MGCG; + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_HDP_SD; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index af37bc6ed1f5..31bce529f685 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4501,6 +4501,17 @@ DEVICE_ATTR_WO(s3_debug); static int dm_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_mode_info *mode_info = &adev->mode_info; + struct atom_context *ctx = mode_info->atom_context; + int index = GetIndexIntoMasterTable(DATA, Object_Header); + u16 data_offset; + + /* if there is no object header, skip DM */ + if (!amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + dev_info(adev->dev, "No object header, skipping DM\n"); + return -ENOENT; + } switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index f9ea1e86707f..79850a68f62a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -874,8 +874,9 @@ static const struct dc_plane_cap plane_cap = { }, // 6:1 downscaling ratio: 1000/6 = 166.666 + // 4:1 downscaling ratio for ARGB888 to prevent underflow during P010 playback: 1000/4 = 250 .max_downscale_factor = { - .argb8888 = 167, + .argb8888 = 250, .nv12 = 167, .fp16 = 167 }, @@ -1763,7 +1764,7 @@ static bool dcn314_resource_construct( pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE; pool->base.pipe_count = pool->base.res_cap->num_timing_generator; pool->base.mpcc_count = pool->base.res_cap->num_timing_generator; - dc->caps.max_downscale_ratio = 600; + dc->caps.max_downscale_ratio = 400; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; dc->caps.max_cursor_size = 256; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index dc4649458567..a4e9fd5307c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -94,7 +94,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, .apply_idle_power_optimizations = dcn32_apply_idle_power_optimizations, - .does_plane_fit_in_mall = dcn30_does_plane_fit_in_mall, + .does_plane_fit_in_mall = NULL, .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 950669f2c10d..cb7c0c878423 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -3183,7 +3183,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman } else { v->MIN_DST_Y_NEXT_START[k] = v->VTotal[k] - v->VFrontPorch[k] + v->VTotal[k] - v->VActive[k] - v->VStartup[k]; } - v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / (double)v->HTotal[k] / v->PixelClock[k], 1.0) / 4.0; + v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / ((double)v->HTotal[k] / v->PixelClock[k]), 1.0) / 4.0; if (((v->VUpdateOffsetPix[k] + v->VUpdateWidthPix[k] + v->VReadyOffsetPix[k]) / v->HTotal[k]) <= (isInterlaceTiming ? dml_floor((v->VTotal[k] - v->VActive[k] - v->VFrontPorch[k] - v->VStartup[k]) / 2.0, 1.0) : diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 4a122925c3ae..92c18bfb98b3 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -532,6 +532,9 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* reset the cache of the last wptr as well now that hw is reset */ + dmub->inbox1_last_wptr = 0; + cw0.offset.quad_part = inst_fb->gpu_addr; cw0.region.base = DMUB_CW0_BASE; cw0.region.top = cw0.region.base + inst_fb->size - 1; @@ -649,6 +652,15 @@ enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub) if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* mailboxes have been reset in hw, so reset the sw state as well */ + dmub->inbox1_last_wptr = 0; + dmub->inbox1_rb.wrpt = 0; + dmub->inbox1_rb.rptr = 0; + dmub->outbox0_rb.wrpt = 0; + dmub->outbox0_rb.rptr = 0; + dmub->outbox1_rb.wrpt = 0; + dmub->outbox1_rb.rptr = 0; + dmub->hw_init = false; return DMUB_STATUS_OK; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 236657eece47..a9170360d7e8 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2007,14 +2007,16 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_dclk)) { if (!(gc_ver == IP_VERSION(10, 3, 1) || gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_power_profile_mode)) { if (amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ca3beb5d8f27..6ab155023592 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1500,6 +1500,20 @@ static int smu_disable_dpms(struct smu_context *smu) } /* + * For SMU 13.0.4/11, PMFW will handle the features disablement properly + * for gpu reset case. Driver involvement is unnecessary. + */ + if (amdgpu_in_reset(adev)) { + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): + return 0; + default: + break; + } + } + + /* * For gpu reset, runpm and hibernation through BACO, * BACO feature has to be kept enabled. */ diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index b74e36d76013..407a477939e5 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -1319,7 +1319,7 @@ static const struct intel_cdclk_vals adlp_cdclk_table[] = { { .refclk = 24000, .cdclk = 192000, .divider = 2, .ratio = 16 }, { .refclk = 24000, .cdclk = 312000, .divider = 2, .ratio = 26 }, { .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 46 }, - { .refclk = 24400, .cdclk = 648000, .divider = 2, .ratio = 54 }, + { .refclk = 24000, .cdclk = 648000, .divider = 2, .ratio = 54 }, { .refclk = 38400, .cdclk = 179200, .divider = 3, .ratio = 14 }, { .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 }, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 6250de9b9196..e4b78ab4773b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1861,11 +1861,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv, vm = ctx->vm; GEM_BUG_ON(!vm); + /* + * Get a reference for the allocated handle. Once the handle is + * visible in the vm_xa table, userspace could try to close it + * from under our feet, so we need to hold the extra reference + * first. + */ + i915_vm_get(vm); + err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL); - if (err) + if (err) { + i915_vm_put(vm); return err; - - i915_vm_get(vm); + } GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */ args->value = id; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index fd42b89b7162..bc21b1c2350a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index e94365b08f1e..2aa63ec521b8 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -528,7 +528,7 @@ retry: return rq; } -struct i915_request *intel_context_find_active_request(struct intel_context *ce) +struct i915_request *intel_context_get_active_request(struct intel_context *ce) { struct intel_context *parent = intel_context_to_parent(ce); struct i915_request *rq, *active = NULL; @@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce) active = rq; } + if (active) + active = i915_request_get_rcu(active); spin_unlock_irqrestore(&parent->guc_state.lock, flags); return active; diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index fb62b7b8cbcd..0a8d553da3f4 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce, struct i915_request *intel_context_create_request(struct intel_context *ce); -struct i915_request * -intel_context_find_active_request(struct intel_context *ce); +struct i915_request *intel_context_get_active_request(struct intel_context *ce); static inline bool intel_context_is_barrier(const struct intel_context *ce) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index cbc8b857d5f7..7a4504ea35c3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -248,8 +248,8 @@ void intel_engine_dump_active_requests(struct list_head *requests, ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now); -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine); +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq); u32 intel_engine_context_size(struct intel_gt *gt, u8 class); struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index c33e0d72d670..d37931e16fd9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } -static unsigned long list_count(struct list_head *list) -{ - struct list_head *pos; - unsigned long count = 0; - - list_for_each(pos, list) - count++; - - return count; -} - static unsigned long read_ul(void *p, size_t x) { return *(unsigned long *)(p + x); @@ -2196,11 +2185,11 @@ void intel_engine_dump_active_requests(struct list_head *requests, } } -static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m) +static void engine_dump_active_requests(struct intel_engine_cs *engine, + struct drm_printer *m) { + struct intel_context *hung_ce = NULL; struct i915_request *hung_rq = NULL; - struct intel_context *ce; - bool guc; /* * No need for an engine->irq_seqno_barrier() before the seqno reads. @@ -2209,27 +2198,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d * But the intention here is just to report an instantaneous snapshot * so that's fine. */ - lockdep_assert_held(&engine->sched_engine->lock); + intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq); drm_printf(m, "\tRequests:\n"); - guc = intel_uc_uses_guc_submission(&engine->gt->uc); - if (guc) { - ce = intel_engine_get_hung_context(engine); - if (ce) - hung_rq = intel_context_find_active_request(ce); - } else { - hung_rq = intel_engine_execlist_find_hung_request(engine); - } - if (hung_rq) engine_dump_request(hung_rq, m, "\t\thung"); + else if (hung_ce) + drm_printf(m, "\t\tGot hung ce but no hung rq!\n"); - if (guc) + if (intel_uc_uses_guc_submission(&engine->gt->uc)) intel_guc_dump_active_requests(engine, hung_rq, m); else - intel_engine_dump_active_requests(&engine->sched_engine->requests, - hung_rq, m); + intel_execlists_dump_active_requests(engine, hung_rq, m); + + if (hung_rq) + i915_request_put(hung_rq); } void intel_engine_dump(struct intel_engine_cs *engine, @@ -2239,7 +2223,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; - unsigned long flags; ktime_t dummy; if (header) { @@ -2276,13 +2259,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_count(error)); print_properties(engine, m); - spin_lock_irqsave(&engine->sched_engine->lock, flags); engine_dump_active_requests(engine, m); - drm_printf(m, "\tOn hold?: %lu\n", - list_count(&engine->sched_engine->hold)); - spin_unlock_irqrestore(&engine->sched_engine->lock, flags); - drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm); if (wakeref) { @@ -2328,8 +2306,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings, return siblings[0]->cops->create_virtual(siblings, count, flags); } -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) +static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; @@ -2381,6 +2358,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) return active; } +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq) +{ + unsigned long flags; + + *ce = intel_engine_get_hung_context(engine); + if (*ce) { + intel_engine_clear_hung_context(engine); + + *rq = intel_context_get_active_request(*ce); + return; + } + + /* + * Getting here with GuC enabled means it is a forced error capture + * with no actual hang. So, no need to attempt the execlist search. + */ + if (intel_uc_uses_guc_submission(&engine->gt->uc)) + return; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + *rq = engine_execlist_find_hung_request(engine); + if (*rq) + *rq = i915_request_get_rcu(*rq); + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + void xehp_enable_ccs_engines(struct intel_engine_cs *engine) { /* diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 2daffa7c7dfd..21cb5b69d82e 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -4148,6 +4148,33 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, spin_unlock_irqrestore(&sched_engine->lock, flags); } +static unsigned long list_count(struct list_head *list) +{ + struct list_head *pos; + unsigned long count = 0; + + list_for_each(pos, list) + count++; + + return count; +} + +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m) +{ + unsigned long flags; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + + intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m); + + drm_printf(m, "\tOn hold?: %lu\n", + list_count(&engine->sched_engine->hold)); + + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_execlists.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a1aa92c983a5..d2c7d45ea062 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, int indent), unsigned int max); +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m); + bool intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 0a42f1807f52..c10977cb06b9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st goto next_context; guilty = false; - rq = intel_context_find_active_request(ce); + rq = intel_context_get_active_request(ce); if (!rq) { head = ce->ring->tail; goto out_replay; @@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st head = intel_ring_wrap(ce->ring, rq->head); __i915_request_reset(rq, guilty); + i915_request_put(rq); out_replay: guc_reset_state(ce, head, guilty); next_context: @@ -4817,6 +4818,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock_irqsave(&guc->context_lookup, flags); xa_for_each(&guc->context_lookup, index, ce) { + bool found; + if (!kref_get_unless_zero(&ce->ref)) continue; @@ -4833,10 +4836,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) goto next; } + found = false; + spin_lock(&ce->guc_state.lock); list_for_each_entry(rq, &ce->guc_state.requests, sched.link) { if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE) continue; + found = true; + break; + } + spin_unlock(&ce->guc_state.lock); + + if (found) { intel_engine_set_hung_context(engine, ce); /* Can only cope with one hang at a time... */ @@ -4844,6 +4855,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock(&guc->context_lookup); goto done; } + next: intel_context_put(ce); xa_lock(&guc->context_lookup); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 9d5d5a397b64..b20bd6365615 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1596,43 +1596,20 @@ capture_engine(struct intel_engine_cs *engine, { struct intel_engine_capture_vma *capture = NULL; struct intel_engine_coredump *ee; - struct intel_context *ce; + struct intel_context *ce = NULL; struct i915_request *rq = NULL; - unsigned long flags; ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags); if (!ee) return NULL; - ce = intel_engine_get_hung_context(engine); - if (ce) { - intel_engine_clear_hung_context(engine); - rq = intel_context_find_active_request(ce); - if (!rq || !i915_request_started(rq)) - goto no_request_capture; - } else { - /* - * Getting here with GuC enabled means it is a forced error capture - * with no actual hang. So, no need to attempt the execlist search. - */ - if (!intel_uc_uses_guc_submission(&engine->gt->uc)) { - spin_lock_irqsave(&engine->sched_engine->lock, flags); - rq = intel_engine_execlist_find_hung_request(engine); - spin_unlock_irqrestore(&engine->sched_engine->lock, - flags); - } - } - if (rq) - rq = i915_request_get_rcu(rq); - - if (!rq) + intel_engine_get_hung_entity(engine, &ce, &rq); + if (!rq || !i915_request_started(rq)) goto no_request_capture; capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); - if (!capture) { - i915_request_put(rq); + if (!capture) goto no_request_capture; - } if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE) intel_guc_capture_get_matching_node(engine->gt, ee, ce); @@ -1642,6 +1619,8 @@ capture_engine(struct intel_engine_cs *engine, return ee; no_request_capture: + if (rq) + i915_request_put(rq); kfree(ee); return NULL; } diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index 40768373cdd9..c5a4f49ee206 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -97,6 +97,7 @@ int gp100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct n int gp102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gp10b_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gv100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); +int tu102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index fcf2a002f6cb..91fb494d4009 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -151,6 +151,9 @@ nvkm_firmware_mem_page(struct nvkm_memory *memory) static enum nvkm_memory_target nvkm_firmware_mem_target(struct nvkm_memory *memory) { + if (nvkm_firmware_mem(memory)->device->func->tegra) + return NVKM_MEM_TARGET_NCOH; + return NVKM_MEM_TARGET_HOST; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 364fea320cb3..1c81e5b34d29 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2405,7 +2405,7 @@ nv162_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2440,7 +2440,7 @@ nv164_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2475,7 +2475,7 @@ nv166_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2510,7 +2510,7 @@ nv167_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2545,7 +2545,7 @@ nv168_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index 393ade9f7e6c..b7da3ab44c27 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -48,6 +48,16 @@ gm200_flcn_pio_dmem_rd(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + /* Sigh. Tegra PMU FW's init message... */ + if (len) { + u32 data = nvkm_falcon_rd32(falcon, 0x1c4 + (port * 8)); + + while (len--) { + *(u8 *)img++ = data & 0xff; + data >>= 8; + } + } } static void @@ -64,6 +74,8 @@ gm200_flcn_pio_dmem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + WARN_ON(len); } static void @@ -74,7 +86,7 @@ gm200_flcn_pio_dmem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 d const struct nvkm_falcon_func_pio gm200_flcn_dmem_pio = { - .min = 4, + .min = 1, .max = 0x100, .wr_init = gm200_flcn_pio_dmem_wr_init, .wr = gm200_flcn_pio_dmem_wr, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c index 634f64f88fc8..81a1ad2c88a7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c @@ -65,10 +65,33 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq) return ret; } +static int +tu102_devinit_wait(struct nvkm_device *device) +{ + unsigned timeout = 50 + 2000; + + do { + if (nvkm_rd32(device, 0x118128) & 0x00000001) { + if ((nvkm_rd32(device, 0x118234) & 0x000000ff) == 0xff) + return 0; + } + + usleep_range(1000, 2000); + } while (timeout--); + + return -ETIMEDOUT; +} + int tu102_devinit_post(struct nvkm_devinit *base, bool post) { struct nv50_devinit *init = nv50_devinit(base); + int ret; + + ret = tu102_devinit_wait(init->base.subdev.device); + if (ret) + return ret; + gm200_devinit_preos(init, post); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild index 5d0bab8ecb43..6ba5120a2ebe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild @@ -32,6 +32,7 @@ nvkm-y += nvkm/subdev/fb/gp100.o nvkm-y += nvkm/subdev/fb/gp102.o nvkm-y += nvkm/subdev/fb/gp10b.o nvkm-y += nvkm/subdev/fb/gv100.o +nvkm-y += nvkm/subdev/fb/tu102.o nvkm-y += nvkm/subdev/fb/ga100.o nvkm-y += nvkm/subdev/fb/ga102.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c index 8b7c8ea5e8a5..5a21b0ae4595 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c @@ -40,12 +40,6 @@ ga102_fb_vpr_scrub(struct nvkm_fb *fb) return ret; } -static bool -ga102_fb_vpr_scrub_required(struct nvkm_fb *fb) -{ - return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; -} - static const struct nvkm_fb_func ga102_fb = { .dtor = gf100_fb_dtor, @@ -56,7 +50,7 @@ ga102_fb = { .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = ga102_ram_new, .default_bigpage = 16, - .vpr.scrub_required = ga102_fb_vpr_scrub_required, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, .vpr.scrub = ga102_fb_vpr_scrub, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 1f0126437c1a..0e3c0a8f5d71 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -49,8 +49,3 @@ gv100_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, s } MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index ac03eac0f261..f517751f94ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -89,4 +89,6 @@ bool gp102_fb_vpr_scrub_required(struct nvkm_fb *); int gp102_fb_vpr_scrub(struct nvkm_fb *); int gv100_fb_init_page(struct nvkm_fb *); + +bool tu102_fb_vpr_scrub_required(struct nvkm_fb *); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c new file mode 100644 index 000000000000..be82af0364ee --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c @@ -0,0 +1,55 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#include "gf100.h" +#include "ram.h" + +bool +tu102_fb_vpr_scrub_required(struct nvkm_fb *fb) +{ + return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; +} + +static const struct nvkm_fb_func +tu102_fb = { + .dtor = gf100_fb_dtor, + .oneinit = gf100_fb_oneinit, + .init = gm200_fb_init, + .init_page = gv100_fb_init_page, + .init_unkn = gp100_fb_init_unkn, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, + .vpr.scrub = gp102_fb_vpr_scrub, + .ram_new = gp100_ram_new, + .default_bigpage = 16, +}; + +int +tu102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) +{ + return gp102_fb_new_(&tu102_fb, device, type, inst, pfb); +} + +MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index a72403777329..2ed04da3621d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -225,7 +225,7 @@ gm20b_pmu_init(struct nvkm_pmu *pmu) pmu->initmsg_received = false; - nvkm_falcon_load_dmem(falcon, &args, addr_args, sizeof(args), 0); + nvkm_falcon_pio_wr(falcon, (u8 *)&args, 0, 0, DMEM, addr_args, sizeof(args), 0, false); nvkm_falcon_start(falcon); return 0; } diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 857a2f0420d7..c924f1124ebc 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1193,14 +1193,11 @@ static int boe_panel_enter_sleep_mode(struct boe_panel *boe) return 0; } -static int boe_panel_unprepare(struct drm_panel *panel) +static int boe_panel_disable(struct drm_panel *panel) { struct boe_panel *boe = to_boe_panel(panel); int ret; - if (!boe->prepared) - return 0; - ret = boe_panel_enter_sleep_mode(boe); if (ret < 0) { dev_err(panel->dev, "failed to set panel off: %d\n", ret); @@ -1209,6 +1206,16 @@ static int boe_panel_unprepare(struct drm_panel *panel) msleep(150); + return 0; +} + +static int boe_panel_unprepare(struct drm_panel *panel) +{ + struct boe_panel *boe = to_boe_panel(panel); + + if (!boe->prepared) + return 0; + if (boe->desc->discharge_on_disable) { regulator_disable(boe->avee); regulator_disable(boe->avdd); @@ -1528,6 +1535,7 @@ static enum drm_panel_orientation boe_panel_get_orientation(struct drm_panel *pa } static const struct drm_panel_funcs boe_panel_funcs = { + .disable = boe_panel_disable, .unprepare = boe_panel_unprepare, .prepare = boe_panel_prepare, .enable = boe_panel_enable, diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 53464afc2b9a..91f69e62430b 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -656,18 +656,8 @@ static const struct drm_crtc_helper_funcs ssd130x_crtc_helper_funcs = { .atomic_check = drm_crtc_helper_atomic_check, }; -static void ssd130x_crtc_reset(struct drm_crtc *crtc) -{ - struct drm_device *drm = crtc->dev; - struct ssd130x_device *ssd130x = drm_to_ssd130x(drm); - - ssd130x_init(ssd130x); - - drm_atomic_helper_crtc_reset(crtc); -} - static const struct drm_crtc_funcs ssd130x_crtc_funcs = { - .reset = ssd130x_crtc_reset, + .reset = drm_atomic_helper_crtc_reset, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -686,6 +676,12 @@ static void ssd130x_encoder_helper_atomic_enable(struct drm_encoder *encoder, if (ret) return; + ret = ssd130x_init(ssd130x); + if (ret) { + ssd130x_power_off(ssd130x); + return; + } + ssd130x_write_cmd(ssd130x, 1, SSD130X_DISPLAY_ON); backlight_enable(ssd130x->bl_dev); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 12a00d644b61..55744216392b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -3018,7 +3018,8 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi) } vc4_hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops, - vc4_hdmi, "vc4", + vc4_hdmi, + vc4_hdmi->variant->card_name, CEC_CAP_DEFAULTS | CEC_CAP_CONNECTOR_INFO, 1); ret = PTR_ERR_OR_ZERO(vc4_hdmi->cec_adap); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index 1fb0f7105fb2..c751d12f5df8 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -227,6 +227,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->num_hid_devices = amd_mp2_get_sensor_num(privdata, &cl_data->sensor_idx[0]); if (cl_data->num_hid_devices == 0) return -ENODEV; + cl_data->is_any_sensor_enabled = false; INIT_DELAYED_WORK(&cl_data->work, amd_sfh_work); INIT_DELAYED_WORK(&cl_data->work_buffer, amd_sfh_work_buffer); @@ -287,6 +288,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) status = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED); if (status == SENSOR_ENABLED) { + cl_data->is_any_sensor_enabled = true; cl_data->sensor_sts[i] = SENSOR_ENABLED; rc = amdtp_hid_probe(cl_data->cur_hid_dev, cl_data); if (rc) { @@ -301,19 +303,26 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->sensor_sts[i]); goto cleanup; } + } else { + cl_data->sensor_sts[i] = SENSOR_DISABLED; + dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", + cl_data->sensor_idx[i], + get_sensor_name(cl_data->sensor_idx[i]), + cl_data->sensor_sts[i]); } dev_dbg(dev, "sid 0x%x (%s) status 0x%x\n", cl_data->sensor_idx[i], get_sensor_name(cl_data->sensor_idx[i]), cl_data->sensor_sts[i]); } - if (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0) { + if (!cl_data->is_any_sensor_enabled || + (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { amd_sfh_hid_client_deinit(privdata); for (i = 0; i < cl_data->num_hid_devices; i++) { devm_kfree(dev, cl_data->feature_report[i]); devm_kfree(dev, in_data->input_report[i]); devm_kfree(dev, cl_data->report_descr[i]); } - dev_warn(dev, "Failed to discover, sensors not enabled\n"); + dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled); return -EOPNOTSUPP; } schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h index 3754fb423e3a..528036892c9d 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.h @@ -32,6 +32,7 @@ struct amd_input_data { struct amdtp_cl_data { u8 init_done; u32 cur_hid_dev; + bool is_any_sensor_enabled; u32 hid_dev_count; u32 num_hid_devices; struct device_info *hid_devices; diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3e1803592bd4..5c72aef3d3dd 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1202,6 +1202,7 @@ int hid_open_report(struct hid_device *device) __u8 *end; __u8 *next; int ret; + int i; static int (*dispatch_type[])(struct hid_parser *parser, struct hid_item *item) = { hid_parser_main, @@ -1252,6 +1253,8 @@ int hid_open_report(struct hid_device *device) goto err; } device->collection_size = HID_DEFAULT_NUM_COLLECTIONS; + for (i = 0; i < HID_DEFAULT_NUM_COLLECTIONS; i++) + device->collection[i].parent_idx = -1; ret = -EINVAL; while ((next = fetch_item(start, end, &item)) != NULL) { diff --git a/drivers/hid/hid-elecom.c b/drivers/hid/hid-elecom.c index e59e9911fc37..4fa45ee77503 100644 --- a/drivers/hid/hid-elecom.c +++ b/drivers/hid/hid-elecom.c @@ -12,6 +12,7 @@ * Copyright (c) 2017 Alex Manoussakis <amanou@gnu.org> * Copyright (c) 2017 Tomasz Kramkowski <tk@the-tk.com> * Copyright (c) 2020 YOSHIOKA Takuma <lo48576@hard-wi.red> + * Copyright (c) 2022 Takahiro Fujii <fujii@xaxxi.net> */ /* @@ -89,7 +90,7 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, case USB_DEVICE_ID_ELECOM_M_DT1URBK: case USB_DEVICE_ID_ELECOM_M_DT1DRBK: case USB_DEVICE_ID_ELECOM_M_HT1URBK: - case USB_DEVICE_ID_ELECOM_M_HT1DRBK: + case USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D: /* * Report descriptor format: * 12: button bit count @@ -99,6 +100,16 @@ static __u8 *elecom_report_fixup(struct hid_device *hdev, __u8 *rdesc, */ mouse_button_fixup(hdev, rdesc, *rsize, 12, 30, 14, 20, 8); break; + case USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C: + /* + * Report descriptor format: + * 22: button bit count + * 30: padding bit count + * 24: button report size + * 16: button usage maximum + */ + mouse_button_fixup(hdev, rdesc, *rsize, 22, 30, 24, 16, 8); + break; } return rdesc; } @@ -112,7 +123,8 @@ static const struct hid_device_id elecom_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) }, { } }; MODULE_DEVICE_TABLE(hid, elecom_devices); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0f8c11842a3a..9e36b4cd905e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -413,6 +413,8 @@ #define I2C_DEVICE_ID_HP_ENVY_X360_15T_DR100 0x29CF #define I2C_DEVICE_ID_HP_ENVY_X360_EU0009NV 0x2CF9 #define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817 +#define I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG 0x29DF +#define I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN 0x2BC8 #define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544 #define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706 #define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A @@ -428,7 +430,8 @@ #define USB_DEVICE_ID_ELECOM_M_DT1URBK 0x00fe #define USB_DEVICE_ID_ELECOM_M_DT1DRBK 0x00ff #define USB_DEVICE_ID_ELECOM_M_HT1URBK 0x010c -#define USB_DEVICE_ID_ELECOM_M_HT1DRBK 0x010d +#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D 0x010d +#define USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C 0x011c #define USB_VENDOR_ID_DREAM_CHEEKY 0x1d34 #define USB_DEVICE_ID_DREAM_CHEEKY_WN 0x0004 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 9b59e436df0a..77c8c49852b5 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -370,6 +370,8 @@ static const struct hid_device_id hid_battery_quirks[] = { { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_DINOVO_EDGE_KBD), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_ASUS_TP420IA_TOUCHSCREEN), + HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN), @@ -384,6 +386,8 @@ static const struct hid_device_id hid_battery_quirks[] = { HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15), HID_BATTERY_QUIRK_IGNORE }, + { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_13_AW0020NG), + HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN), HID_BATTERY_QUIRK_IGNORE }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_SURFACE_GO2_TOUCHSCREEN), diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c index abf2c95e4d0b..9c1ee8e91e0c 100644 --- a/drivers/hid/hid-logitech-hidpp.c +++ b/drivers/hid/hid-logitech-hidpp.c @@ -3978,7 +3978,8 @@ static void hidpp_connect_event(struct hidpp_device *hidpp) } hidpp_initialize_battery(hidpp); - hidpp_initialize_hires_scroll(hidpp); + if (!hid_is_usb(hidpp->hid_dev)) + hidpp_initialize_hires_scroll(hidpp); /* forward current battery state */ if (hidpp->capabilities & HIDPP_CAPABILITY_HIDPP10_BATTERY) { diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index be3ad02573de..5bc91f68b374 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -393,7 +393,8 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1URBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_DT1DRBK) }, { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1URBK) }, - { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_010D) }, + { HID_USB_DEVICE(USB_VENDOR_ID_ELECOM, USB_DEVICE_ID_ELECOM_M_HT1DRBK_011C) }, #endif #if IS_ENABLED(CONFIG_HID_ELO) { HID_USB_DEVICE(USB_VENDOR_ID_ELO, 0x0009) }, diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index cbe43e2567a7..64ac5bdee3a6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1963,7 +1963,7 @@ static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) { - debugfs_remove(debugfs_lookup("hv-balloon", NULL)); + debugfs_lookup_and_remove("hv-balloon", NULL); } #else diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index a2def6f9380a..5eac7ea19993 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -280,6 +280,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev, hid_sensor_convert_timestamp( &accel_state->common_attributes, *(int64_t *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/adc/berlin2-adc.c b/drivers/iio/adc/berlin2-adc.c index 3d2e8b4db61a..a4e7c7eff5ac 100644 --- a/drivers/iio/adc/berlin2-adc.c +++ b/drivers/iio/adc/berlin2-adc.c @@ -298,8 +298,10 @@ static int berlin2_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv)); - if (!indio_dev) + if (!indio_dev) { + of_node_put(parent_np); return -ENOMEM; + } priv = iio_priv(indio_dev); diff --git a/drivers/iio/adc/imx8qxp-adc.c b/drivers/iio/adc/imx8qxp-adc.c index 36777b827165..f5a0fc9e64c5 100644 --- a/drivers/iio/adc/imx8qxp-adc.c +++ b/drivers/iio/adc/imx8qxp-adc.c @@ -86,6 +86,8 @@ #define IMX8QXP_ADC_TIMEOUT msecs_to_jiffies(100) +#define IMX8QXP_ADC_MAX_FIFO_SIZE 16 + struct imx8qxp_adc { struct device *dev; void __iomem *regs; @@ -95,6 +97,7 @@ struct imx8qxp_adc { /* Serialise ADC channel reads */ struct mutex lock; struct completion completion; + u32 fifo[IMX8QXP_ADC_MAX_FIFO_SIZE]; }; #define IMX8QXP_ADC_CHAN(_idx) { \ @@ -238,8 +241,7 @@ static int imx8qxp_adc_read_raw(struct iio_dev *indio_dev, return ret; } - *val = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, - readl(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + *val = adc->fifo[0]; mutex_unlock(&adc->lock); return IIO_VAL_INT; @@ -265,10 +267,15 @@ static irqreturn_t imx8qxp_adc_isr(int irq, void *dev_id) { struct imx8qxp_adc *adc = dev_id; u32 fifo_count; + int i; fifo_count = FIELD_GET(IMX8QXP_ADC_FCTRL_FCOUNT_MASK, readl(adc->regs + IMX8QXP_ADR_ADC_FCTRL)); + for (i = 0; i < fifo_count; i++) + adc->fifo[i] = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, + readl_relaxed(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + if (fifo_count) complete(&adc->completion); diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 6d21ea84fa82..a428bdb567d5 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -1520,6 +1520,7 @@ static const struct of_device_id stm32_dfsdm_adc_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match); static int stm32_dfsdm_adc_probe(struct platform_device *pdev) { diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index f53e8558b560..32873fb5f367 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -57,6 +57,18 @@ #define TWL6030_GPADCS BIT(1) #define TWL6030_GPADCR BIT(0) +#define USB_VBUS_CTRL_SET 0x04 +#define USB_ID_CTRL_SET 0x06 + +#define TWL6030_MISC1 0xE4 +#define VBUS_MEAS 0x01 +#define ID_MEAS 0x01 + +#define VAC_MEAS 0x04 +#define VBAT_MEAS 0x02 +#define BB_MEAS 0x01 + + /** * struct twl6030_chnl_calib - channel calibration * @gain: slope coefficient for ideal curve @@ -927,6 +939,26 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) return ret; } + ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, + VBAT_MEAS | BB_MEAS | VAC_MEAS, + TWL6030_MISC1); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + indio_dev->name = DRIVER_NAME; indio_dev->info = &twl6030_gpadc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; diff --git a/drivers/iio/adc/xilinx-ams.c b/drivers/iio/adc/xilinx-ams.c index 5b4bdf3a26bb..a507d2e17079 100644 --- a/drivers/iio/adc/xilinx-ams.c +++ b/drivers/iio/adc/xilinx-ams.c @@ -1329,7 +1329,7 @@ static int ams_parse_firmware(struct iio_dev *indio_dev) dev_channels = devm_krealloc(dev, ams_channels, dev_size, GFP_KERNEL); if (!dev_channels) - ret = -ENOMEM; + return -ENOMEM; indio_dev->channels = dev_channels; indio_dev->num_channels = num_channels; diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 8f0ad022c7f1..698c50da1f10 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -231,6 +231,7 @@ static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev, gyro_state->timestamp = hid_sensor_convert_timestamp(&gyro_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 423cfe526f2a..6d189c4b9ff9 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -10,6 +10,7 @@ #include <linux/regmap.h> #include <linux/acpi.h> #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> @@ -144,9 +145,8 @@ #define FXOS8700_NVM_DATA_BNK0 0xa7 /* Bit definitions for FXOS8700_CTRL_REG1 */ -#define FXOS8700_CTRL_ODR_MSK 0x38 #define FXOS8700_CTRL_ODR_MAX 0x00 -#define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3) +#define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3) /* Bit definitions for FXOS8700_M_CTRL_REG1 */ #define FXOS8700_HMS_MASK GENMASK(1, 0) @@ -320,7 +320,7 @@ static enum fxos8700_sensor fxos8700_to_sensor(enum iio_chan_type iio_type) switch (iio_type) { case IIO_ACCEL: return FXOS8700_ACCEL; - case IIO_ANGL_VEL: + case IIO_MAGN: return FXOS8700_MAGN; default: return -EINVAL; @@ -345,15 +345,35 @@ static int fxos8700_set_active_mode(struct fxos8700_data *data, static int fxos8700_set_scale(struct fxos8700_data *data, enum fxos8700_sensor t, int uscale) { - int i; + int i, ret, val; + bool active_mode; static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); struct device *dev = regmap_get_device(data->regmap); if (t == FXOS8700_MAGN) { - dev_err(dev, "Magnetometer scale is locked at 1200uT\n"); + dev_err(dev, "Magnetometer scale is locked at 0.001Gs\n"); return -EINVAL; } + /* + * When device is in active mode, it failed to set an ACCEL + * full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG. + * This is not align with the datasheet, but it is a fxos8700 + * chip behavier. Set the device in standby mode before setting + * an ACCEL full-scale range. + */ + ret = regmap_read(data->regmap, FXOS8700_CTRL_REG1, &val); + if (ret) + return ret; + + active_mode = val & FXOS8700_ACTIVE; + if (active_mode) { + ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, + val & ~FXOS8700_ACTIVE); + if (ret) + return ret; + } + for (i = 0; i < scale_num; i++) if (fxos8700_accel_scale[i].uscale == uscale) break; @@ -361,8 +381,12 @@ static int fxos8700_set_scale(struct fxos8700_data *data, if (i == scale_num) return -EINVAL; - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, fxos8700_accel_scale[i].bits); + if (ret) + return ret; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, + active_mode); } static int fxos8700_get_scale(struct fxos8700_data *data, @@ -372,7 +396,7 @@ static int fxos8700_get_scale(struct fxos8700_data *data, static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); if (t == FXOS8700_MAGN) { - *uscale = 1200; /* Magnetometer is locked at 1200uT */ + *uscale = 1000; /* Magnetometer is locked at 0.001Gs */ return 0; } @@ -394,22 +418,61 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, int axis, int *val) { u8 base, reg; + s16 tmp; int ret; - enum fxos8700_sensor type = fxos8700_to_sensor(chan_type); - base = type ? FXOS8700_OUT_X_MSB : FXOS8700_M_OUT_X_MSB; + /* + * Different register base addresses varies with channel types. + * This bug hasn't been noticed before because using an enum is + * really hard to read. Use an a switch statement to take over that. + */ + switch (chan_type) { + case IIO_ACCEL: + base = FXOS8700_OUT_X_MSB; + break; + case IIO_MAGN: + base = FXOS8700_M_OUT_X_MSB; + break; + default: + return -EINVAL; + } /* Block read 6 bytes of device output registers to avoid data loss */ ret = regmap_bulk_read(data->regmap, base, data->buf, - FXOS8700_DATA_BUF_SIZE); + sizeof(data->buf)); if (ret) return ret; /* Convert axis to buffer index */ reg = axis - IIO_MOD_X; + /* + * Convert to native endianness. The accel data and magn data + * are signed, so a forced type conversion is needed. + */ + tmp = be16_to_cpu(data->buf[reg]); + + /* + * ACCEL output data registers contain the X-axis, Y-axis, and Z-axis + * 14-bit left-justified sample data and MAGN output data registers + * contain the X-axis, Y-axis, and Z-axis 16-bit sample data. Apply + * a signed 2 bits right shift to the readback raw data from ACCEL + * output data register and keep that from MAGN sensor as the origin. + * Value should be extended to 32 bit. + */ + switch (chan_type) { + case IIO_ACCEL: + tmp = tmp >> 2; + break; + case IIO_MAGN: + /* Nothing to do */ + break; + default: + return -EINVAL; + } + /* Convert to native endianness */ - *val = sign_extend32(be16_to_cpu(data->buf[reg]), 15); + *val = sign_extend32(tmp, 15); return 0; } @@ -445,10 +508,9 @@ static int fxos8700_set_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (i >= odr_num) return -EINVAL; - return regmap_update_bits(data->regmap, - FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MSK + FXOS8700_ACTIVE, - fxos8700_odr[i].bits << 3 | active_mode); + val &= ~FXOS8700_CTRL_ODR_MSK; + val |= FIELD_PREP(FXOS8700_CTRL_ODR_MSK, fxos8700_odr[i].bits) | FXOS8700_ACTIVE; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, val); } static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, @@ -461,7 +523,7 @@ static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (ret) return ret; - val &= FXOS8700_CTRL_ODR_MSK; + val = FIELD_GET(FXOS8700_CTRL_ODR_MSK, val); for (i = 0; i < odr_num; i++) if (val == fxos8700_odr[i].bits) @@ -526,7 +588,7 @@ static IIO_CONST_ATTR(in_accel_sampling_frequency_available, static IIO_CONST_ATTR(in_magn_sampling_frequency_available, "1.5625 6.25 12.5 50 100 200 400 800"); static IIO_CONST_ATTR(in_accel_scale_available, "0.000244 0.000488 0.000976"); -static IIO_CONST_ATTR(in_magn_scale_available, "0.000001200"); +static IIO_CONST_ATTR(in_magn_scale_available, "0.001000"); static struct attribute *fxos8700_attrs[] = { &iio_const_attr_in_accel_sampling_frequency_available.dev_attr.attr, @@ -592,14 +654,19 @@ static int fxos8700_chip_init(struct fxos8700_data *data, bool use_spi) if (ret) return ret; - /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ - ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); + /* + * Set max full-scale range (+/-8G) for ACCEL sensor in chip + * initialization then activate the device. + */ + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); if (ret) return ret; - /* Set for max full-scale range (+/-8G) */ - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); + /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ + return regmap_update_bits(data->regmap, FXOS8700_CTRL_REG1, + FXOS8700_CTRL_ODR_MSK | FXOS8700_ACTIVE, + FIELD_PREP(FXOS8700_CTRL_ODR_MSK, FXOS8700_CTRL_ODR_MAX) | + FXOS8700_ACTIVE); } static void fxos8700_chip_uninit(void *data) diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig index f6660847fb58..8c16cdacf2f2 100644 --- a/drivers/iio/imu/st_lsm6dsx/Kconfig +++ b/drivers/iio/imu/st_lsm6dsx/Kconfig @@ -4,6 +4,7 @@ config IIO_ST_LSM6DSX tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors" depends on (I2C || SPI || I3C) select IIO_BUFFER + select IIO_TRIGGERED_BUFFER select IIO_KFIFO_BUF select IIO_ST_LSM6DSX_I2C if (I2C) select IIO_ST_LSM6DSX_SPI if (SPI_MASTER) diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index 001055d09750..b1674a5bfa36 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -440,6 +440,8 @@ static int cm32181_probe(struct i2c_client *client) if (!indio_dev) return -ENOMEM; + i2c_set_clientdata(client, indio_dev); + /* * Some ACPI systems list 2 I2C resources for the CM3218 sensor, the * SMBus Alert Response Address (ARA, 0x0c) and the actual I2C address. @@ -460,8 +462,6 @@ static int cm32181_probe(struct i2c_client *client) return PTR_ERR(client); } - i2c_set_clientdata(client, indio_dev); - cm32181 = iio_priv(indio_dev); cm32181->client = client; cm32181->dev = dev; @@ -490,7 +490,8 @@ static int cm32181_probe(struct i2c_client *client) static int cm32181_suspend(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); + struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, CM32181_CMD_ALS_DISABLE); @@ -498,8 +499,8 @@ static int cm32181_suspend(struct device *dev) static int cm32181_resume(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, cm32181->conf_regs[CM32181_REG_ADDR_CMD]); diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h index 785c37cae3c0..5a2baf49ecaa 100644 --- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h +++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h @@ -89,13 +89,6 @@ struct bnxt_re_ring_attr { u8 mode; }; -struct bnxt_re_work { - struct work_struct work; - unsigned long event; - struct bnxt_re_dev *rdev; - struct net_device *vlan_dev; -}; - struct bnxt_re_sqp_entries { struct bnxt_qplib_sge sge; u64 wrid; @@ -132,10 +125,10 @@ struct bnxt_re_dev { #define BNXT_RE_FLAG_ERR_DEVICE_DETACHED 17 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29 struct net_device *netdev; + struct notifier_block nb; unsigned int version, major, minor; struct bnxt_qplib_chip_ctx *chip_ctx; struct bnxt_en_dev *en_dev; - struct bnxt_msix_entry msix_entries[BNXT_RE_MAX_MSIX]; int num_msix; int id; @@ -194,5 +187,4 @@ static inline struct device *rdev_to_dev(struct bnxt_re_dev *rdev) return &rdev->ibdev.dev; return NULL; } - #endif diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index 8c0c80a8d338..c5867e78f231 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -48,6 +48,7 @@ #include <net/ipv6.h> #include <net/addrconf.h> #include <linux/if_ether.h> +#include <linux/auxiliary_bus.h> #include <rdma/ib_verbs.h> #include <rdma/ib_user_verbs.h> @@ -74,14 +75,14 @@ MODULE_DESCRIPTION(BNXT_RE_DESC " Driver"); MODULE_LICENSE("Dual BSD/GPL"); /* globals */ -static struct list_head bnxt_re_dev_list = LIST_HEAD_INIT(bnxt_re_dev_list); -/* Mutex to protect the list of bnxt_re devices added */ -static DEFINE_MUTEX(bnxt_re_dev_lock); -static struct workqueue_struct *bnxt_re_wq; -static void bnxt_re_remove_device(struct bnxt_re_dev *rdev); -static void bnxt_re_dealloc_driver(struct ib_device *ib_dev); +static DEFINE_MUTEX(bnxt_re_mutex); + static void bnxt_re_stop_irq(void *handle); static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev); +static int bnxt_re_netdev_event(struct notifier_block *notifier, + unsigned long event, void *ptr); +static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev); +static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev); static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode) { @@ -111,16 +112,14 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) { struct bnxt_qplib_chip_ctx *chip_ctx; struct bnxt_en_dev *en_dev; - struct bnxt *bp; en_dev = rdev->en_dev; - bp = netdev_priv(en_dev->net); chip_ctx = kzalloc(sizeof(*chip_ctx), GFP_KERNEL); if (!chip_ctx) return -ENOMEM; - chip_ctx->chip_num = bp->chip_num; - chip_ctx->hw_stats_size = bp->hw_ring_stats_size; + chip_ctx->chip_num = en_dev->chip_num; + chip_ctx->hw_stats_size = en_dev->hw_ring_stats_size; rdev->chip_ctx = chip_ctx; /* rest members to follow eventually */ @@ -128,7 +127,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) rdev->qplib_res.cctx = rdev->chip_ctx; rdev->rcfw.res = &rdev->qplib_res; rdev->qplib_res.dattr = &rdev->dev_attr; - rdev->qplib_res.is_vf = BNXT_VF(bp); + rdev->qplib_res.is_vf = BNXT_EN_VF(en_dev); bnxt_re_set_drv_mode(rdev, wqe_mode); if (bnxt_qplib_determine_atomics(en_dev->pdev)) @@ -141,10 +140,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode) static void bnxt_re_get_sriov_func_type(struct bnxt_re_dev *rdev) { - struct bnxt *bp; - - bp = netdev_priv(rdev->en_dev->net); - if (BNXT_VF(bp)) + if (BNXT_EN_VF(rdev->en_dev)) rdev->is_virtfn = 1; } @@ -225,56 +221,12 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev) bnxt_re_limit_vf_res(&rdev->qplib_ctx, num_vfs); } -/* for handling bnxt_en callbacks later */ -static void bnxt_re_stop(void *p) -{ - struct bnxt_re_dev *rdev = p; - struct bnxt *bp; - - if (!rdev) - return; - ASSERT_RTNL(); - - /* L2 driver invokes this callback during device error/crash or device - * reset. Current RoCE driver doesn't recover the device in case of - * error. Handle the error by dispatching fatal events to all qps - * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as - * L2 driver want to modify the MSIx table. - */ - bp = netdev_priv(rdev->netdev); - - ibdev_info(&rdev->ibdev, "Handle device stop call from L2 driver"); - /* Check the current device state from L2 structure and move the - * device to detached state if FW_FATAL_COND is set. - * This prevents more commands to HW during clean-up, - * in case the device is already in error. - */ - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) - set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); - - bnxt_re_dev_stop(rdev); - bnxt_re_stop_irq(rdev); - /* Move the device states to detached and avoid sending any more - * commands to HW - */ - set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags); - set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); -} - -static void bnxt_re_start(void *p) -{ -} - -static void bnxt_re_sriov_config(void *p, int num_vfs) +static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) { - struct bnxt_re_dev *rdev = p; - - if (!rdev) - return; if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags)) return; - rdev->num_vfs = num_vfs; + rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev); if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) { bnxt_re_set_resource_limits(rdev); bnxt_qplib_set_func_resources(&rdev->qplib_res, &rdev->rcfw, @@ -282,16 +234,14 @@ static void bnxt_re_sriov_config(void *p, int num_vfs) } } -static void bnxt_re_shutdown(void *p) +static void bnxt_re_shutdown(struct auxiliary_device *adev) { - struct bnxt_re_dev *rdev = p; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); if (!rdev) return; - ASSERT_RTNL(); - /* Release the MSIx vectors before queuing unregister */ - bnxt_re_stop_irq(rdev); - ib_unregister_device_queued(&rdev->ibdev); + ib_unregister_device(&rdev->ibdev); + bnxt_re_dev_uninit(rdev); } static void bnxt_re_stop_irq(void *handle) @@ -312,7 +262,7 @@ static void bnxt_re_stop_irq(void *handle) static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) { struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle; - struct bnxt_msix_entry *msix_ent = rdev->msix_entries; + struct bnxt_msix_entry *msix_ent = rdev->en_dev->msix_entries; struct bnxt_qplib_rcfw *rcfw = &rdev->rcfw; struct bnxt_qplib_nq *nq; int indx, rc; @@ -331,7 +281,7 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) * in device sctructure. */ for (indx = 0; indx < rdev->num_msix; indx++) - rdev->msix_entries[indx].vector = ent[indx].vector; + rdev->en_dev->msix_entries[indx].vector = ent[indx].vector; bnxt_qplib_rcfw_start_irq(rcfw, msix_ent[BNXT_RE_AEQ_IDX].vector, false); @@ -346,93 +296,22 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent) } static struct bnxt_ulp_ops bnxt_re_ulp_ops = { - .ulp_async_notifier = NULL, - .ulp_stop = bnxt_re_stop, - .ulp_start = bnxt_re_start, - .ulp_sriov_config = bnxt_re_sriov_config, - .ulp_shutdown = bnxt_re_shutdown, .ulp_irq_stop = bnxt_re_stop_irq, .ulp_irq_restart = bnxt_re_start_irq }; /* RoCE -> Net driver */ -/* Driver registration routines used to let the networking driver (bnxt_en) - * to know that the RoCE driver is now installed - */ -static int bnxt_re_unregister_netdev(struct bnxt_re_dev *rdev) -{ - struct bnxt_en_dev *en_dev; - int rc; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - rc = en_dev->en_ops->bnxt_unregister_device(rdev->en_dev, - BNXT_ROCE_ULP); - return rc; -} - static int bnxt_re_register_netdev(struct bnxt_re_dev *rdev) { struct bnxt_en_dev *en_dev; int rc = 0; - if (!rdev) - return -EINVAL; - en_dev = rdev->en_dev; - rc = en_dev->en_ops->bnxt_register_device(en_dev, BNXT_ROCE_ULP, - &bnxt_re_ulp_ops, rdev); - rdev->qplib_res.pdev = rdev->en_dev->pdev; - return rc; -} - -static int bnxt_re_free_msix(struct bnxt_re_dev *rdev) -{ - struct bnxt_en_dev *en_dev; - int rc; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - - rc = en_dev->en_ops->bnxt_free_msix(rdev->en_dev, BNXT_ROCE_ULP); - - return rc; -} - -static int bnxt_re_request_msix(struct bnxt_re_dev *rdev) -{ - int rc = 0, num_msix_want = BNXT_RE_MAX_MSIX, num_msix_got; - struct bnxt_en_dev *en_dev; - - if (!rdev) - return -EINVAL; - - en_dev = rdev->en_dev; - - num_msix_want = min_t(u32, BNXT_RE_MAX_MSIX, num_online_cpus()); - - num_msix_got = en_dev->en_ops->bnxt_request_msix(en_dev, BNXT_ROCE_ULP, - rdev->msix_entries, - num_msix_want); - if (num_msix_got < BNXT_RE_MIN_MSIX) { - rc = -EINVAL; - goto done; - } - if (num_msix_got != num_msix_want) { - ibdev_warn(&rdev->ibdev, - "Requested %d MSI-X vectors, got %d\n", - num_msix_want, num_msix_got); - } - rdev->num_msix = num_msix_got; -done: + rc = bnxt_register_dev(en_dev, &bnxt_re_ulp_ops, rdev); + if (!rc) + rdev->qplib_res.pdev = rdev->en_dev->pdev; return rc; } @@ -458,12 +337,17 @@ static void bnxt_re_fill_fw_msg(struct bnxt_fw_msg *fw_msg, void *msg, static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, u16 fw_ring_id, int type) { - struct bnxt_en_dev *en_dev = rdev->en_dev; + struct bnxt_en_dev *en_dev; struct hwrm_ring_free_input req = {0}; struct hwrm_ring_free_output resp; struct bnxt_fw_msg fw_msg; int rc = -EINVAL; + if (!rdev) + return rc; + + en_dev = rdev->en_dev; + if (!en_dev) return rc; @@ -477,7 +361,7 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev, req.ring_id = cpu_to_le16(fw_ring_id); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) ibdev_err(&rdev->ibdev, "Failed to free HW ring:%d :%#x", req.ring_id, rc); @@ -514,7 +398,7 @@ static int bnxt_re_net_ring_alloc(struct bnxt_re_dev *rdev, req.int_mode = ring_attr->mode; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (!rc) *fw_ring_id = le16_to_cpu(resp.ring_id); @@ -542,7 +426,7 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev, req.stat_ctx_id = cpu_to_le32(fw_stats_ctx_id); bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) ibdev_err(&rdev->ibdev, "Failed to free HW stats context %#x", rc); @@ -575,7 +459,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (!rc) *fw_stats_ctx_id = le32_to_cpu(resp.stat_ctx_id); @@ -584,21 +468,6 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev, /* Device */ -static bool is_bnxt_re_dev(struct net_device *netdev) -{ - struct ethtool_drvinfo drvinfo; - - if (netdev->ethtool_ops && netdev->ethtool_ops->get_drvinfo) { - memset(&drvinfo, 0, sizeof(drvinfo)); - netdev->ethtool_ops->get_drvinfo(netdev, &drvinfo); - - if (strcmp(drvinfo.driver, "bnxt_en")) - return false; - return true; - } - return false; -} - static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev) { struct ib_device *ibdev = @@ -609,31 +478,6 @@ static struct bnxt_re_dev *bnxt_re_from_netdev(struct net_device *netdev) return container_of(ibdev, struct bnxt_re_dev, ibdev); } -static struct bnxt_en_dev *bnxt_re_dev_probe(struct net_device *netdev) -{ - struct bnxt_en_dev *en_dev; - struct pci_dev *pdev; - - en_dev = bnxt_ulp_probe(netdev); - if (IS_ERR(en_dev)) - return en_dev; - - pdev = en_dev->pdev; - if (!pdev) - return ERR_PTR(-EINVAL); - - if (!(en_dev->flags & BNXT_EN_FLAG_ROCE_CAP)) { - dev_info(&pdev->dev, - "%s: probe error: RoCE is not supported on this device", - ROCE_DRV_MODULE_NAME); - return ERR_PTR(-ENODEV); - } - - dev_hold(netdev); - - return en_dev; -} - static ssize_t hw_rev_show(struct device *device, struct device_attribute *attr, char *buf) { @@ -679,7 +523,6 @@ static const struct ib_device_ops bnxt_re_dev_ops = { .create_qp = bnxt_re_create_qp, .create_srq = bnxt_re_create_srq, .create_user_ah = bnxt_re_create_ah, - .dealloc_driver = bnxt_re_dealloc_driver, .dealloc_pd = bnxt_re_dealloc_pd, .dealloc_ucontext = bnxt_re_dealloc_ucontext, .del_gid = bnxt_re_del_gid, @@ -744,18 +587,7 @@ static int bnxt_re_register_ib(struct bnxt_re_dev *rdev) return ib_register_device(ibdev, "bnxt_re%d", &rdev->en_dev->pdev->dev); } -static void bnxt_re_dev_remove(struct bnxt_re_dev *rdev) -{ - dev_put(rdev->netdev); - rdev->netdev = NULL; - mutex_lock(&bnxt_re_dev_lock); - list_del_rcu(&rdev->list); - mutex_unlock(&bnxt_re_dev_lock); - - synchronize_rcu(); -} - -static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, +static struct bnxt_re_dev *bnxt_re_dev_add(struct bnxt_aux_priv *aux_priv, struct bnxt_en_dev *en_dev) { struct bnxt_re_dev *rdev; @@ -768,8 +600,8 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, return NULL; } /* Default values */ - rdev->netdev = netdev; - dev_hold(rdev->netdev); + rdev->nb.notifier_call = NULL; + rdev->netdev = en_dev->net; rdev->en_dev = en_dev; rdev->id = rdev->en_dev->pdev->devfn; INIT_LIST_HEAD(&rdev->qp_list); @@ -784,9 +616,6 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct net_device *netdev, rdev->cosq[0] = 0xFFFF; rdev->cosq[1] = 0xFFFF; - mutex_lock(&bnxt_re_dev_lock); - list_add_tail_rcu(&rdev->list, &bnxt_re_dev_list); - mutex_unlock(&bnxt_re_dev_lock); return rdev; } @@ -930,7 +759,7 @@ static u32 bnxt_re_get_nqdb_offset(struct bnxt_re_dev *rdev, u16 indx) return bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx) ? (rdev->is_virtfn ? BNXT_RE_GEN_P5_VF_NQ_DB : BNXT_RE_GEN_P5_PF_NQ_DB) : - rdev->msix_entries[indx].db_offset; + rdev->en_dev->msix_entries[indx].db_offset; } static void bnxt_re_cleanup_res(struct bnxt_re_dev *rdev) @@ -955,7 +784,7 @@ static int bnxt_re_init_res(struct bnxt_re_dev *rdev) for (i = 1; i < rdev->num_msix ; i++) { db_offt = bnxt_re_get_nqdb_offset(rdev, i); rc = bnxt_qplib_enable_nq(rdev->en_dev->pdev, &rdev->nq[i - 1], - i - 1, rdev->msix_entries[i].vector, + i - 1, rdev->en_dev->msix_entries[i].vector, db_offt, &bnxt_re_cqn_handler, &bnxt_re_srqn_handler); if (rc) { @@ -1042,7 +871,7 @@ static int bnxt_re_alloc_res(struct bnxt_re_dev *rdev) rattr.type = type; rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX; rattr.depth = BNXT_QPLIB_NQE_MAX_CNT - 1; - rattr.lrid = rdev->msix_entries[i + 1].ring_idx; + rattr.lrid = rdev->en_dev->msix_entries[i + 1].ring_idx; rc = bnxt_re_net_ring_alloc(rdev, &rattr, &nq->ring_id); if (rc) { ibdev_err(&rdev->ibdev, @@ -1095,7 +924,6 @@ static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir, u64 *cid_map) { struct hwrm_queue_pri2cos_qcfg_input req = {0}; - struct bnxt *bp = netdev_priv(rdev->netdev); struct hwrm_queue_pri2cos_qcfg_output resp; struct bnxt_en_dev *en_dev = rdev->en_dev; struct bnxt_fw_msg fw_msg; @@ -1112,11 +940,11 @@ static int bnxt_re_query_hwrm_pri2cos(struct bnxt_re_dev *rdev, u8 dir, flags |= (dir & 0x01); flags |= HWRM_QUEUE_PRI2COS_QCFG_INPUT_FLAGS_IVLAN; req.flags = cpu_to_le32(flags); - req.port_id = bp->pf.port_id; + req.port_id = en_dev->pf_port_id; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) return rc; @@ -1299,7 +1127,7 @@ static void bnxt_re_query_hwrm_intf_version(struct bnxt_re_dev *rdev) req.hwrm_intf_upd = HWRM_VERSION_UPDATE; bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp, sizeof(resp), DFLT_HWRM_CMD_TIMEOUT); - rc = en_dev->en_ops->bnxt_send_fw_msg(en_dev, BNXT_ROCE_ULP, &fw_msg); + rc = bnxt_send_msg(en_dev, &fw_msg); if (rc) { ibdev_err(&rdev->ibdev, "Failed to query HW version, rc = 0x%x", rc); @@ -1323,7 +1151,7 @@ static int bnxt_re_ib_init(struct bnxt_re_dev *rdev) pr_err("Failed to register with IB: %#x\n", rc); return rc; } - dev_info(rdev_to_dev(rdev), "Device registered successfully"); + dev_info(rdev_to_dev(rdev), "Device registered with IB successfully"); ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, &rdev->active_width); set_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS, &rdev->flags); @@ -1362,20 +1190,12 @@ static void bnxt_re_dev_uninit(struct bnxt_re_dev *rdev) bnxt_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type); bnxt_qplib_free_rcfw_channel(&rdev->rcfw); } - if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) { - rc = bnxt_re_free_msix(rdev); - if (rc) - ibdev_warn(&rdev->ibdev, - "Failed to free MSI-X vectors: %#x", rc); - } + if (test_and_clear_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags)) + rdev->num_msix = 0; bnxt_re_destroy_chip_ctx(rdev); - if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) { - rc = bnxt_re_unregister_netdev(rdev); - if (rc) - ibdev_warn(&rdev->ibdev, - "Failed to unregister with netdev: %#x", rc); - } + if (test_and_clear_bit(BNXT_RE_FLAG_NETDEV_REGISTERED, &rdev->flags)) + bnxt_unregister_dev(rdev->en_dev); } /* worker thread for polling periodic events. Now used for QoS programming*/ @@ -1416,13 +1236,15 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) /* Check whether VF or PF */ bnxt_re_get_sriov_func_type(rdev); - rc = bnxt_re_request_msix(rdev); - if (rc) { + if (!rdev->en_dev->ulp_tbl->msix_requested) { ibdev_err(&rdev->ibdev, "Failed to get MSI-X vectors: %#x\n", rc); rc = -EINVAL; goto fail; } + ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n", + rdev->en_dev->ulp_tbl->msix_requested); + rdev->num_msix = rdev->en_dev->ulp_tbl->msix_requested; set_bit(BNXT_RE_FLAG_GOT_MSIX, &rdev->flags); bnxt_re_query_hwrm_intf_version(rdev); @@ -1446,14 +1268,14 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) rattr.type = type; rattr.mode = RING_ALLOC_REQ_INT_MODE_MSIX; rattr.depth = BNXT_QPLIB_CREQE_MAX_CNT - 1; - rattr.lrid = rdev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx; + rattr.lrid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].ring_idx; rc = bnxt_re_net_ring_alloc(rdev, &rattr, &creq->ring_id); if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate CREQ: %#x\n", rc); goto free_rcfw; } db_offt = bnxt_re_get_nqdb_offset(rdev, BNXT_RE_AEQ_IDX); - vid = rdev->msix_entries[BNXT_RE_AEQ_IDX].vector; + vid = rdev->en_dev->msix_entries[BNXT_RE_AEQ_IDX].vector; rc = bnxt_qplib_enable_rcfw_channel(&rdev->rcfw, vid, db_offt, rdev->is_virtfn, &bnxt_re_aeq_handler); @@ -1521,6 +1343,11 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 wqe_mode) INIT_DELAYED_WORK(&rdev->worker, bnxt_re_worker); set_bit(BNXT_RE_FLAG_QOS_WORK_REG, &rdev->flags); schedule_delayed_work(&rdev->worker, msecs_to_jiffies(30000)); + /* + * Use the total VF count since the actual VF count may not be + * available at this point. + */ + bnxt_re_vf_res_config(rdev); } return 0; @@ -1541,135 +1368,43 @@ fail: return rc; } -static void bnxt_re_dev_unreg(struct bnxt_re_dev *rdev) -{ - struct net_device *netdev = rdev->netdev; - - bnxt_re_dev_remove(rdev); - - if (netdev) - dev_put(netdev); -} - -static int bnxt_re_dev_reg(struct bnxt_re_dev **rdev, struct net_device *netdev) +static int bnxt_re_add_device(struct auxiliary_device *adev, u8 wqe_mode) { + struct bnxt_aux_priv *aux_priv = + container_of(adev, struct bnxt_aux_priv, aux_dev); struct bnxt_en_dev *en_dev; + struct bnxt_re_dev *rdev; int rc = 0; - if (!is_bnxt_re_dev(netdev)) - return -ENODEV; + /* en_dev should never be NULL as long as adev and aux_dev are valid. */ + en_dev = aux_priv->edev; - en_dev = bnxt_re_dev_probe(netdev); - if (IS_ERR(en_dev)) { - if (en_dev != ERR_PTR(-ENODEV)) - ibdev_err(&(*rdev)->ibdev, "%s: Failed to probe\n", - ROCE_DRV_MODULE_NAME); - rc = PTR_ERR(en_dev); - goto exit; - } - *rdev = bnxt_re_dev_add(netdev, en_dev); - if (!*rdev) { + rdev = bnxt_re_dev_add(aux_priv, en_dev); + if (!rdev || !rdev_to_dev(rdev)) { rc = -ENOMEM; - dev_put(netdev); goto exit; } -exit: - return rc; -} -static void bnxt_re_remove_device(struct bnxt_re_dev *rdev) -{ - bnxt_re_dev_uninit(rdev); - pci_dev_put(rdev->en_dev->pdev); - bnxt_re_dev_unreg(rdev); -} - -static int bnxt_re_add_device(struct bnxt_re_dev **rdev, - struct net_device *netdev, u8 wqe_mode) -{ - int rc; - - rc = bnxt_re_dev_reg(rdev, netdev); - if (rc == -ENODEV) - return rc; - if (rc) { - pr_err("Failed to register with the device %s: %#x\n", - netdev->name, rc); - return rc; - } + rc = bnxt_re_dev_init(rdev, wqe_mode); + if (rc) + goto re_dev_dealloc; - pci_dev_get((*rdev)->en_dev->pdev); - rc = bnxt_re_dev_init(*rdev, wqe_mode); + rc = bnxt_re_ib_init(rdev); if (rc) { - pci_dev_put((*rdev)->en_dev->pdev); - bnxt_re_dev_unreg(*rdev); + pr_err("Failed to register with IB: %s", + aux_priv->aux_dev.name); + goto re_dev_uninit; } + auxiliary_set_drvdata(adev, rdev); - return rc; -} - -static void bnxt_re_dealloc_driver(struct ib_device *ib_dev) -{ - struct bnxt_re_dev *rdev = - container_of(ib_dev, struct bnxt_re_dev, ibdev); - - dev_info(rdev_to_dev(rdev), "Unregistering Device"); - - rtnl_lock(); - bnxt_re_remove_device(rdev); - rtnl_unlock(); -} - -/* Handle all deferred netevents tasks */ -static void bnxt_re_task(struct work_struct *work) -{ - struct bnxt_re_work *re_work; - struct bnxt_re_dev *rdev; - int rc = 0; - - re_work = container_of(work, struct bnxt_re_work, work); - rdev = re_work->rdev; - - if (re_work->event == NETDEV_REGISTER) { - rc = bnxt_re_ib_init(rdev); - if (rc) { - ibdev_err(&rdev->ibdev, - "Failed to register with IB: %#x", rc); - rtnl_lock(); - bnxt_re_remove_device(rdev); - rtnl_unlock(); - goto exit; - } - goto exit; - } - - if (!ib_device_try_get(&rdev->ibdev)) - goto exit; + return 0; - switch (re_work->event) { - case NETDEV_UP: - bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, - IB_EVENT_PORT_ACTIVE); - break; - case NETDEV_DOWN: - bnxt_re_dev_stop(rdev); - break; - case NETDEV_CHANGE: - if (!netif_carrier_ok(rdev->netdev)) - bnxt_re_dev_stop(rdev); - else if (netif_carrier_ok(rdev->netdev)) - bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, - IB_EVENT_PORT_ACTIVE); - ib_get_eth_speed(&rdev->ibdev, 1, &rdev->active_speed, - &rdev->active_width); - break; - default: - break; - } - ib_device_put(&rdev->ibdev); +re_dev_uninit: + bnxt_re_dev_uninit(rdev); +re_dev_dealloc: + ib_dealloc_device(&rdev->ibdev); exit: - put_device(&rdev->ibdev.dev); - kfree(re_work); + return rc; } /* @@ -1690,109 +1425,189 @@ static int bnxt_re_netdev_event(struct notifier_block *notifier, unsigned long event, void *ptr) { struct net_device *real_dev, *netdev = netdev_notifier_info_to_dev(ptr); - struct bnxt_re_work *re_work; struct bnxt_re_dev *rdev; - int rc = 0; - bool sch_work = false; - bool release = true; real_dev = rdma_vlan_dev_real_dev(netdev); if (!real_dev) real_dev = netdev; - rdev = bnxt_re_from_netdev(real_dev); - if (!rdev && event != NETDEV_REGISTER) - return NOTIFY_OK; - if (real_dev != netdev) goto exit; - switch (event) { - case NETDEV_REGISTER: - if (rdev) - break; - rc = bnxt_re_add_device(&rdev, real_dev, - BNXT_QPLIB_WQE_MODE_STATIC); - if (!rc) - sch_work = true; - release = false; - break; + rdev = bnxt_re_from_netdev(real_dev); + if (!rdev) + return NOTIFY_DONE; - case NETDEV_UNREGISTER: - ib_unregister_device_queued(&rdev->ibdev); - break; + switch (event) { + case NETDEV_UP: + case NETDEV_DOWN: + case NETDEV_CHANGE: + bnxt_re_dispatch_event(&rdev->ibdev, NULL, 1, + netif_carrier_ok(real_dev) ? + IB_EVENT_PORT_ACTIVE : + IB_EVENT_PORT_ERR); + break; default: - sch_work = true; break; } - if (sch_work) { - /* Allocate for the deferred task */ - re_work = kzalloc(sizeof(*re_work), GFP_KERNEL); - if (re_work) { - get_device(&rdev->ibdev.dev); - re_work->rdev = rdev; - re_work->event = event; - re_work->vlan_dev = (real_dev == netdev ? - NULL : netdev); - INIT_WORK(&re_work->work, bnxt_re_task); - queue_work(bnxt_re_wq, &re_work->work); - } - } - + ib_device_put(&rdev->ibdev); exit: - if (rdev && release) - ib_device_put(&rdev->ibdev); return NOTIFY_DONE; } -static struct notifier_block bnxt_re_netdev_notifier = { - .notifier_call = bnxt_re_netdev_event -}; +#define BNXT_ADEV_NAME "bnxt_en" -static int __init bnxt_re_mod_init(void) +static void bnxt_re_remove(struct auxiliary_device *adev) { - int rc = 0; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); - pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version); + if (!rdev) + return; - bnxt_re_wq = create_singlethread_workqueue("bnxt_re"); - if (!bnxt_re_wq) - return -ENOMEM; + mutex_lock(&bnxt_re_mutex); + if (rdev->nb.notifier_call) { + unregister_netdevice_notifier(&rdev->nb); + rdev->nb.notifier_call = NULL; + } else { + /* If notifier is null, we should have already done a + * clean up before coming here. + */ + goto skip_remove; + } + + ib_unregister_device(&rdev->ibdev); + ib_dealloc_device(&rdev->ibdev); + bnxt_re_dev_uninit(rdev); +skip_remove: + mutex_unlock(&bnxt_re_mutex); +} + +static int bnxt_re_probe(struct auxiliary_device *adev, + const struct auxiliary_device_id *id) +{ + struct bnxt_re_dev *rdev; + int rc; - INIT_LIST_HEAD(&bnxt_re_dev_list); + mutex_lock(&bnxt_re_mutex); + rc = bnxt_re_add_device(adev, BNXT_QPLIB_WQE_MODE_STATIC); + if (rc) { + mutex_unlock(&bnxt_re_mutex); + return rc; + } + + rdev = auxiliary_get_drvdata(adev); - rc = register_netdevice_notifier(&bnxt_re_netdev_notifier); + rdev->nb.notifier_call = bnxt_re_netdev_event; + rc = register_netdevice_notifier(&rdev->nb); if (rc) { + rdev->nb.notifier_call = NULL; pr_err("%s: Cannot register to netdevice_notifier", ROCE_DRV_MODULE_NAME); - goto err_netdev; + goto err; } + + mutex_unlock(&bnxt_re_mutex); return 0; -err_netdev: - destroy_workqueue(bnxt_re_wq); +err: + mutex_unlock(&bnxt_re_mutex); + bnxt_re_remove(adev); return rc; } -static void __exit bnxt_re_mod_exit(void) +static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state) { - struct bnxt_re_dev *rdev; + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); - unregister_netdevice_notifier(&bnxt_re_netdev_notifier); - if (bnxt_re_wq) - destroy_workqueue(bnxt_re_wq); - list_for_each_entry(rdev, &bnxt_re_dev_list, list) { - /* VF device removal should be called before the removal - * of PF device. Queue VFs unregister first, so that VFs - * shall be removed before the PF during the call of - * ib_unregister_driver. - */ - if (rdev->is_virtfn) - ib_unregister_device(&rdev->ibdev); + if (!rdev) + return 0; + + mutex_lock(&bnxt_re_mutex); + /* L2 driver may invoke this callback during device error/crash or device + * reset. Current RoCE driver doesn't recover the device in case of + * error. Handle the error by dispatching fatal events to all qps + * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as + * L2 driver want to modify the MSIx table. + */ + + ibdev_info(&rdev->ibdev, "Handle device suspend call"); + /* Check the current device state from bnxt_en_dev and move the + * device to detached state if FW_FATAL_COND is set. + * This prevents more commands to HW during clean-up, + * in case the device is already in error. + */ + if (test_bit(BNXT_STATE_FW_FATAL_COND, &rdev->en_dev->en_state)) + set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); + + bnxt_re_dev_stop(rdev); + bnxt_re_stop_irq(rdev); + /* Move the device states to detached and avoid sending any more + * commands to HW + */ + set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags); + set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags); + mutex_unlock(&bnxt_re_mutex); + + return 0; +} + +static int bnxt_re_resume(struct auxiliary_device *adev) +{ + struct bnxt_re_dev *rdev = auxiliary_get_drvdata(adev); + + if (!rdev) + return 0; + + mutex_lock(&bnxt_re_mutex); + /* L2 driver may invoke this callback during device recovery, resume. + * reset. Current RoCE driver doesn't recover the device in case of + * error. Handle the error by dispatching fatal events to all qps + * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as + * L2 driver want to modify the MSIx table. + */ + + ibdev_info(&rdev->ibdev, "Handle device resume call"); + mutex_unlock(&bnxt_re_mutex); + + return 0; +} + +static const struct auxiliary_device_id bnxt_re_id_table[] = { + { .name = BNXT_ADEV_NAME ".rdma", }, + {}, +}; + +MODULE_DEVICE_TABLE(auxiliary, bnxt_re_id_table); + +static struct auxiliary_driver bnxt_re_driver = { + .name = "rdma", + .probe = bnxt_re_probe, + .remove = bnxt_re_remove, + .shutdown = bnxt_re_shutdown, + .suspend = bnxt_re_suspend, + .resume = bnxt_re_resume, + .id_table = bnxt_re_id_table, +}; + +static int __init bnxt_re_mod_init(void) +{ + int rc = 0; + + pr_info("%s: %s", ROCE_DRV_MODULE_NAME, version); + rc = auxiliary_driver_register(&bnxt_re_driver); + if (rc) { + pr_err("%s: Failed to register auxiliary driver\n", + ROCE_DRV_MODULE_NAME); + return rc; } - ib_unregister_driver(RDMA_DRIVER_BNXT_RE); + return 0; +} + +static void __exit bnxt_re_mod_exit(void) +{ + auxiliary_driver_unregister(&bnxt_re_driver); } module_init(bnxt_re_mod_init); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index c669ef6e47e7..dc32e4518a28 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3012,26 +3012,63 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev) } } -static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num) +static void mlx5_netdev_notifier_register(struct mlx5_roce *roce, + struct net_device *netdev) { int err; - dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event; - err = register_netdevice_notifier(&dev->port[port_num].roce.nb); - if (err) { - dev->port[port_num].roce.nb.notifier_call = NULL; - return err; - } + if (roce->tracking_netdev) + return; + roce->tracking_netdev = netdev; + roce->nb.notifier_call = mlx5_netdev_event; + err = register_netdevice_notifier_dev_net(netdev, &roce->nb, &roce->nn); + WARN_ON(err); +} - return 0; +static void mlx5_netdev_notifier_unregister(struct mlx5_roce *roce) +{ + if (!roce->tracking_netdev) + return; + unregister_netdevice_notifier_dev_net(roce->tracking_netdev, &roce->nb, + &roce->nn); + roce->tracking_netdev = NULL; } -static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num) +static int mlx5e_mdev_notifier_event(struct notifier_block *nb, + unsigned long event, void *data) { - if (dev->port[port_num].roce.nb.notifier_call) { - unregister_netdevice_notifier(&dev->port[port_num].roce.nb); - dev->port[port_num].roce.nb.notifier_call = NULL; + struct mlx5_roce *roce = container_of(nb, struct mlx5_roce, mdev_nb); + struct net_device *netdev = data; + + switch (event) { + case MLX5_DRIVER_EVENT_UPLINK_NETDEV: + if (netdev) + mlx5_netdev_notifier_register(roce, netdev); + else + mlx5_netdev_notifier_unregister(roce); + break; + default: + return NOTIFY_DONE; } + + return NOTIFY_OK; +} + +static void mlx5_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num) +{ + struct mlx5_roce *roce = &dev->port[port_num].roce; + + roce->mdev_nb.notifier_call = mlx5e_mdev_notifier_event; + mlx5_blocking_notifier_register(dev->mdev, &roce->mdev_nb); + mlx5_core_uplink_netdev_event_replay(dev->mdev); +} + +static void mlx5_mdev_netdev_untrack(struct mlx5_ib_dev *dev, u32 port_num) +{ + struct mlx5_roce *roce = &dev->port[port_num].roce; + + mlx5_blocking_notifier_unregister(dev->mdev, &roce->mdev_nb); + mlx5_netdev_notifier_unregister(roce); } static int mlx5_enable_eth(struct mlx5_ib_dev *dev) @@ -3138,7 +3175,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev, if (mpi->mdev_events.notifier_call) mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events); mpi->mdev_events.notifier_call = NULL; - mlx5_remove_netdev_notifier(ibdev, port_num); + mlx5_mdev_netdev_untrack(ibdev, port_num); spin_lock(&port->mp.mpi_lock); comps = mpi->mdev_refcnt; @@ -3196,12 +3233,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev, if (err) goto unbind; - err = mlx5_add_netdev_notifier(ibdev, port_num); - if (err) { - mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n", - port_num + 1); - goto unbind; - } + mlx5_mdev_netdev_track(ibdev, port_num); mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port; mlx5_notifier_register(mpi->mdev, &mpi->mdev_events); @@ -3909,9 +3941,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) port_num = mlx5_core_native_port_num(dev->mdev) - 1; /* Register only for native ports */ - err = mlx5_add_netdev_notifier(dev, port_num); - if (err) - return err; + mlx5_mdev_netdev_track(dev, port_num); err = mlx5_enable_eth(dev); if (err) @@ -3920,7 +3950,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev) return 0; cleanup: - mlx5_remove_netdev_notifier(dev, port_num); + mlx5_mdev_netdev_untrack(dev, port_num); return err; } @@ -3938,7 +3968,7 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev) mlx5_disable_eth(dev); port_num = mlx5_core_native_port_num(dev->mdev) - 1; - mlx5_remove_netdev_notifier(dev, port_num); + mlx5_mdev_netdev_untrack(dev, port_num); } } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 8b91babdd4c0..7394e7f36ba7 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -832,6 +832,9 @@ struct mlx5_roce { rwlock_t netdev_lock; struct net_device *netdev; struct notifier_block nb; + struct netdev_net_notifier nn; + struct notifier_block mdev_nb; + struct net_device *tracking_netdev; atomic_t tx_port_affinity; enum ib_port_state last_port_state; struct mlx5_ib_dev *dev; diff --git a/drivers/net/bonding/bond_debugfs.c b/drivers/net/bonding/bond_debugfs.c index 4f9b4a18c74c..594094526648 100644 --- a/drivers/net/bonding/bond_debugfs.c +++ b/drivers/net/bonding/bond_debugfs.c @@ -76,7 +76,7 @@ void bond_debug_reregister(struct bonding *bond) d = debugfs_rename(bonding_debug_root, bond->debug_dir, bonding_debug_root, bond->dev->name); - if (d) { + if (!IS_ERR(d)) { bond->debug_dir = d; } else { netdev_warn(bond->dev, "failed to reregister, so just unregister old one\n"); diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 7ae80763c960..0b93900b1dfa 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -6,25 +6,81 @@ #include <linux/can/dev.h> +void can_sjw_set_default(struct can_bittiming *bt) +{ + if (bt->sjw) + return; + + /* If user space provides no sjw, use sane default of phase_seg2 / 2 */ + bt->sjw = max(1U, min(bt->phase_seg1, bt->phase_seg2 / 2)); +} + +int can_sjw_check(const struct net_device *dev, const struct can_bittiming *bt, + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) +{ + if (bt->sjw > btc->sjw_max) { + NL_SET_ERR_MSG_FMT(extack, "sjw: %u greater than max sjw: %u", + bt->sjw, btc->sjw_max); + return -EINVAL; + } + + if (bt->sjw > bt->phase_seg1) { + NL_SET_ERR_MSG_FMT(extack, + "sjw: %u greater than phase-seg1: %u", + bt->sjw, bt->phase_seg1); + return -EINVAL; + } + + if (bt->sjw > bt->phase_seg2) { + NL_SET_ERR_MSG_FMT(extack, + "sjw: %u greater than phase-seg2: %u", + bt->sjw, bt->phase_seg2); + return -EINVAL; + } + + return 0; +} + /* Checks the validity of the specified bit-timing parameters prop_seg, * phase_seg1, phase_seg2 and sjw and tries to determine the bitrate * prescaler value brp. You can find more information in the header * file linux/can/netlink.h. */ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, + struct netlink_ext_ack *extack) { + const unsigned int tseg1 = bt->prop_seg + bt->phase_seg1; const struct can_priv *priv = netdev_priv(dev); - unsigned int tseg1, alltseg; u64 brp64; + int err; - tseg1 = bt->prop_seg + bt->phase_seg1; - if (!bt->sjw) - bt->sjw = 1; - if (bt->sjw > btc->sjw_max || - tseg1 < btc->tseg1_min || tseg1 > btc->tseg1_max || - bt->phase_seg2 < btc->tseg2_min || bt->phase_seg2 > btc->tseg2_max) - return -ERANGE; + if (tseg1 < btc->tseg1_min) { + NL_SET_ERR_MSG_FMT(extack, "prop-seg + phase-seg1: %u less than tseg1-min: %u", + tseg1, btc->tseg1_min); + return -EINVAL; + } + if (tseg1 > btc->tseg1_max) { + NL_SET_ERR_MSG_FMT(extack, "prop-seg + phase-seg1: %u greater than tseg1-max: %u", + tseg1, btc->tseg1_max); + return -EINVAL; + } + if (bt->phase_seg2 < btc->tseg2_min) { + NL_SET_ERR_MSG_FMT(extack, "phase-seg2: %u less than tseg2-min: %u", + bt->phase_seg2, btc->tseg2_min); + return -EINVAL; + } + if (bt->phase_seg2 > btc->tseg2_max) { + NL_SET_ERR_MSG_FMT(extack, "phase-seg2: %u greater than tseg2-max: %u", + bt->phase_seg2, btc->tseg2_max); + return -EINVAL; + } + + can_sjw_set_default(bt); + + err = can_sjw_check(dev, bt, btc, extack); + if (err) + return err; brp64 = (u64)priv->clock.freq * (u64)bt->tq; if (btc->brp_inc > 1) @@ -35,12 +91,21 @@ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittimin brp64 *= btc->brp_inc; bt->brp = (u32)brp64; - if (bt->brp < btc->brp_min || bt->brp > btc->brp_max) + if (bt->brp < btc->brp_min) { + NL_SET_ERR_MSG_FMT(extack, "resulting brp: %u less than brp-min: %u", + bt->brp, btc->brp_min); + return -EINVAL; + } + if (bt->brp > btc->brp_max) { + NL_SET_ERR_MSG_FMT(extack, "resulting brp: %u greater than brp-max: %u", + bt->brp, btc->brp_max); return -EINVAL; + } - alltseg = bt->prop_seg + bt->phase_seg1 + bt->phase_seg2 + 1; - bt->bitrate = priv->clock.freq / (bt->brp * alltseg); - bt->sample_point = ((tseg1 + 1) * 1000) / alltseg; + bt->bitrate = priv->clock.freq / (bt->brp * can_bit_time(bt)); + bt->sample_point = ((CAN_SYNC_SEG + tseg1) * 1000) / can_bit_time(bt); + bt->tq = DIV_U64_ROUND_CLOSEST(mul_u32_u32(bt->brp, NSEC_PER_SEC), + priv->clock.freq); return 0; } @@ -49,7 +114,8 @@ static int can_fixup_bittiming(const struct net_device *dev, struct can_bittimin static int can_validate_bitrate(const struct net_device *dev, const struct can_bittiming *bt, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt) + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack) { unsigned int i; @@ -58,30 +124,30 @@ can_validate_bitrate(const struct net_device *dev, const struct can_bittiming *b return 0; } + NL_SET_ERR_MSG_FMT(extack, "bitrate %u bps not supported", + bt->brp); + return -EINVAL; } int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt) + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack) { - int err; - /* Depending on the given can_bittiming parameter structure the CAN * timing parameters are calculated based on the provided bitrate OR * alternatively the CAN timing parameters (tq, prop_seg, etc.) are * provided directly which are then checked and fixed up. */ if (!bt->tq && bt->bitrate && btc) - err = can_calc_bittiming(dev, bt, btc); - else if (bt->tq && !bt->bitrate && btc) - err = can_fixup_bittiming(dev, bt, btc); - else if (!bt->tq && bt->bitrate && bitrate_const) - err = can_validate_bitrate(dev, bt, bitrate_const, - bitrate_const_cnt); - else - err = -EINVAL; - - return err; + return can_calc_bittiming(dev, bt, btc, extack); + if (bt->tq && !bt->bitrate && btc) + return can_fixup_bittiming(dev, bt, btc, extack); + if (!bt->tq && bt->bitrate && bitrate_const) + return can_validate_bitrate(dev, bt, bitrate_const, + bitrate_const_cnt, extack); + + return -EINVAL; } diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c index d3caa040614d..3809c148fb88 100644 --- a/drivers/net/can/dev/calc_bittiming.c +++ b/drivers/net/can/dev/calc_bittiming.c @@ -63,7 +63,7 @@ can_update_sample_point(const struct can_bittiming_const *btc, } int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) { struct can_priv *priv = netdev_priv(dev); unsigned int bitrate; /* current bitrate */ @@ -76,6 +76,7 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, unsigned int best_brp = 0; /* current best value for brp */ unsigned int brp, tsegall, tseg, tseg1 = 0, tseg2 = 0; u64 v64; + int err; /* Use CiA recommended sample points */ if (bt->sample_point) { @@ -133,13 +134,14 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, do_div(v64, bt->bitrate); bitrate_error = (u32)v64; if (bitrate_error > CAN_CALC_MAX_ERROR) { - netdev_err(dev, - "bitrate error %d.%d%% too high\n", - bitrate_error / 10, bitrate_error % 10); - return -EDOM; + NL_SET_ERR_MSG_FMT(extack, + "bitrate error: %u.%u%% too high", + bitrate_error / 10, bitrate_error % 10); + return -EINVAL; } - netdev_warn(dev, "bitrate error %d.%d%%\n", - bitrate_error / 10, bitrate_error % 10); + NL_SET_ERR_MSG_FMT(extack, + "bitrate error: %u.%u%%", + bitrate_error / 10, bitrate_error % 10); } /* real sample point */ @@ -154,23 +156,17 @@ int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, bt->phase_seg1 = tseg1 - bt->prop_seg; bt->phase_seg2 = tseg2; - /* check for sjw user settings */ - if (!bt->sjw || !btc->sjw_max) { - bt->sjw = 1; - } else { - /* bt->sjw is at least 1 -> sanitize upper bound to sjw_max */ - if (bt->sjw > btc->sjw_max) - bt->sjw = btc->sjw_max; - /* bt->sjw must not be higher than tseg2 */ - if (tseg2 < bt->sjw) - bt->sjw = tseg2; - } + can_sjw_set_default(bt); + + err = can_sjw_check(dev, bt, btc, extack); + if (err) + return err; bt->brp = best_brp; /* real bitrate */ bt->bitrate = priv->clock.freq / - (bt->brp * (CAN_SYNC_SEG + tseg1 + tseg2)); + (bt->brp * can_bit_time(bt)); return 0; } diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index c1956b1e9faf..7f9334a8af50 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -498,6 +498,18 @@ static int can_get_termination(struct net_device *ndev) return 0; } +static bool +can_bittiming_const_valid(const struct can_bittiming_const *btc) +{ + if (!btc) + return true; + + if (!btc->sjw_max) + return false; + + return true; +} + /* Register the CAN network device */ int register_candev(struct net_device *dev) { @@ -518,6 +530,15 @@ int register_candev(struct net_device *dev) if (!priv->data_bitrate_const != !priv->data_bitrate_const_cnt) return -EINVAL; + /* We only support either fixed bit rates or bit timing const. */ + if ((priv->bitrate_const || priv->data_bitrate_const) && + (priv->bittiming_const || priv->data_bittiming_const)) + return -EINVAL; + + if (!can_bittiming_const_valid(priv->bittiming_const) || + !can_bittiming_const_valid(priv->data_bittiming_const)) + return -EINVAL; + if (!priv->termination_const) { err = can_get_termination(dev); if (err) diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 8efa22d9f214..036d85ef07f5 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -36,10 +36,24 @@ static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { [IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 }, }; +static int can_validate_bittiming(const struct can_bittiming *bt, + struct netlink_ext_ack *extack) +{ + /* sample point is in one-tenth of a percent */ + if (bt->sample_point >= 1000) { + NL_SET_ERR_MSG(extack, "sample point must be between 0 and 100%"); + + return -EINVAL; + } + + return 0; +} + static int can_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { bool is_can_fd = false; + int err; /* Make sure that valid CAN FD configurations always consist of * - nominal/arbitration bittiming @@ -51,6 +65,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], if (!data) return 0; + if (data[IFLA_CAN_BITTIMING]) { + struct can_bittiming bt; + + memcpy(&bt, nla_data(data[IFLA_CAN_BITTIMING]), sizeof(bt)); + err = can_validate_bittiming(&bt, extack); + if (err) + return err; + } + if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK; @@ -71,7 +94,6 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], */ if (data[IFLA_CAN_TDC]) { struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; - int err; err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, data[IFLA_CAN_TDC], @@ -102,6 +124,15 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return -EOPNOTSUPP; } + if (data[IFLA_CAN_DATA_BITTIMING]) { + struct can_bittiming bt; + + memcpy(&bt, nla_data(data[IFLA_CAN_DATA_BITTIMING]), sizeof(bt)); + err = can_validate_bittiming(&bt, extack); + if (err) + return err; + } + return 0; } @@ -184,13 +215,15 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], err = can_get_bittiming(dev, &bt, priv->bittiming_const, priv->bitrate_const, - priv->bitrate_const_cnt); + priv->bitrate_const_cnt, + extack); if (err) return err; if (priv->bitrate_max && bt.bitrate > priv->bitrate_max) { - netdev_err(dev, "arbitration bitrate surpasses transceiver capabilities of %d bps\n", - priv->bitrate_max); + NL_SET_ERR_MSG_FMT(extack, + "arbitration bitrate %u bps surpasses transceiver capabilities of %u bps", + bt.bitrate, priv->bitrate_max); return -EINVAL; } @@ -288,13 +321,15 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], err = can_get_bittiming(dev, &dbt, priv->data_bittiming_const, priv->data_bitrate_const, - priv->data_bitrate_const_cnt); + priv->data_bitrate_const_cnt, + extack); if (err) return err; if (priv->bitrate_max && dbt.bitrate > priv->bitrate_max) { - netdev_err(dev, "canfd data bitrate surpasses transceiver capabilities of %d bps\n", - priv->bitrate_max); + NL_SET_ERR_MSG_FMT(extack, + "CANFD data bitrate %u bps surpasses transceiver capabilities of %u bps", + dbt.bitrate, priv->bitrate_max); return -EINVAL; } diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index f6fa7157b99b..ef4e1b9a9e1e 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -21,23 +21,23 @@ * wherever it is modified to a readable name. */ -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/interrupt.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/can/dev.h> +#include <linux/clk.h> #include <linux/errno.h> #include <linux/ethtool.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/netdevice.h> -#include <linux/platform_device.h> -#include <linux/can/dev.h> -#include <linux/clk.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/bitmap.h> -#include <linux/bitops.h> -#include <linux/iopoll.h> +#include <linux/platform_device.h> #include <linux/reset.h> +#include <linux/types.h> #define RCANFD_DRV_NAME "rcar_canfd" @@ -82,8 +82,8 @@ #define RCANFD_GERFL_DEF BIT(0) #define RCANFD_GERFL_ERR(gpriv, x) \ - ((x) & (reg_v3u(gpriv, RCANFD_GERFL_EEF0_7, \ - RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \ + ((x) & (reg_gen4(gpriv, RCANFD_GERFL_EEF0_7, \ + RCANFD_GERFL_EEF(0) | RCANFD_GERFL_EEF(1)) | \ RCANFD_GERFL_MES | \ ((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))) @@ -91,16 +91,16 @@ /* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */ #define RCANFD_GAFLCFG_SETRNC(gpriv, n, x) \ - (((x) & reg_v3u(gpriv, 0x1ff, 0xff)) << \ - (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) + (((x) & reg_gen4(gpriv, 0x1ff, 0xff)) << \ + (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) #define RCANFD_GAFLCFG_GETRNC(gpriv, n, x) \ - (((x) >> (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) & \ - reg_v3u(gpriv, 0x1ff, 0xff)) + (((x) >> (reg_gen4(gpriv, 16, 24) - ((n) & 1) * reg_gen4(gpriv, 16, 8))) & \ + reg_gen4(gpriv, 0x1ff, 0xff)) /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */ #define RCANFD_GAFLECTR_AFLDAE BIT(8) -#define RCANFD_GAFLECTR_AFLPN(gpriv, x) ((x) & reg_v3u(gpriv, 0x7f, 0x1f)) +#define RCANFD_GAFLECTR_AFLPN(gpriv, x) ((x) & reg_gen4(gpriv, 0x7f, 0x1f)) /* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */ #define RCANFD_GAFLID_GAFLLB BIT(29) @@ -118,13 +118,13 @@ /* RSCFDnCFDCmNCFG - CAN FD only */ #define RCANFD_NCFG_NTSEG2(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 25, 24)) + (((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 25, 24)) #define RCANFD_NCFG_NTSEG1(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0xff, 0x7f)) << reg_v3u(gpriv, 17, 16)) + (((x) & reg_gen4(gpriv, 0xff, 0x7f)) << reg_gen4(gpriv, 17, 16)) #define RCANFD_NCFG_NSJW(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 10, 11)) + (((x) & reg_gen4(gpriv, 0x7f, 0x1f)) << reg_gen4(gpriv, 10, 11)) #define RCANFD_NCFG_NBRP(x) (((x) & 0x3ff) << 0) @@ -186,19 +186,19 @@ #define RCANFD_CERFL_ERR(x) ((x) & (0x7fff)) /* above bits 14:0 */ /* RSCFDnCFDCmDCFG */ -#define RCANFD_DCFG_DSJW(x) (((x) & 0x7) << 24) +#define RCANFD_DCFG_DSJW(gpriv, x) (((x) & reg_gen4(gpriv, 0xf, 0x7)) << 24) #define RCANFD_DCFG_DTSEG2(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x0f, 0x7)) << reg_v3u(gpriv, 16, 20)) + (((x) & reg_gen4(gpriv, 0x0f, 0x7)) << reg_gen4(gpriv, 16, 20)) #define RCANFD_DCFG_DTSEG1(gpriv, x) \ - (((x) & reg_v3u(gpriv, 0x1f, 0xf)) << reg_v3u(gpriv, 8, 16)) + (((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 8, 16)) #define RCANFD_DCFG_DBRP(x) (((x) & 0xff) << 0) /* RSCFDnCFDCmFDCFG */ -#define RCANFD_FDCFG_CLOE BIT(30) -#define RCANFD_FDCFG_FDOE BIT(28) +#define RCANFD_GEN4_FDCFG_CLOE BIT(30) +#define RCANFD_GEN4_FDCFG_FDOE BIT(28) #define RCANFD_FDCFG_TDCE BIT(9) #define RCANFD_FDCFG_TDCOC BIT(8) #define RCANFD_FDCFG_TDCO(x) (((x) & 0x7f) >> 16) @@ -233,10 +233,11 @@ /* Common FIFO bits */ /* RSCFDnCFDCFCCk */ -#define RCANFD_CFCC_CFTML(gpriv, x) (((x) & 0xf) << reg_v3u(gpriv, 16, 20)) -#define RCANFD_CFCC_CFM(gpriv, x) (((x) & 0x3) << reg_v3u(gpriv, 8, 16)) +#define RCANFD_CFCC_CFTML(gpriv, x) \ + (((x) & reg_gen4(gpriv, 0x1f, 0xf)) << reg_gen4(gpriv, 16, 20)) +#define RCANFD_CFCC_CFM(gpriv, x) (((x) & 0x3) << reg_gen4(gpriv, 8, 16)) #define RCANFD_CFCC_CFIM BIT(12) -#define RCANFD_CFCC_CFDC(gpriv, x) (((x) & 0x7) << reg_v3u(gpriv, 21, 8)) +#define RCANFD_CFCC_CFDC(gpriv, x) (((x) & 0x7) << reg_gen4(gpriv, 21, 8)) #define RCANFD_CFCC_CFPLS(x) (((x) & 0x7) << 4) #define RCANFD_CFCC_CFTXIE BIT(2) #define RCANFD_CFCC_CFE BIT(0) @@ -304,7 +305,7 @@ #define RCANFD_RMND(y) (0x00a8 + (0x04 * (y))) /* RSCFDnCFDRFCCx / RSCFDnRFCCx */ -#define RCANFD_RFCC(gpriv, x) (reg_v3u(gpriv, 0x00c0, 0x00b8) + (0x04 * (x))) +#define RCANFD_RFCC(gpriv, x) (reg_gen4(gpriv, 0x00c0, 0x00b8) + (0x04 * (x))) /* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */ #define RCANFD_RFSTS(gpriv, x) (RCANFD_RFCC(gpriv, x) + 0x20) /* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */ @@ -314,13 +315,13 @@ /* RSCFDnCFDCFCCx / RSCFDnCFCCx */ #define RCANFD_CFCC(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */ #define RCANFD_CFSTS(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */ #define RCANFD_CFPCTR(gpriv, ch, idx) \ - (reg_v3u(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx))) + (reg_gen4(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDFESTS / RSCFDnFESTS */ #define RCANFD_FESTS (0x0238) @@ -428,16 +429,15 @@ /* RSCFDnRPGACCr */ #define RCANFD_C_RPGACC(r) (0x1900 + (0x04 * (r))) -/* R-Car V3U Classical and CAN FD mode specific register map */ -#define RCANFD_V3U_CFDCFG (0x1314) -#define RCANFD_V3U_DCFG(m) (0x1400 + (0x20 * (m))) +/* R-Car Gen4 Classical and CAN FD mode specific register map */ +#define RCANFD_GEN4_FDCFG(m) (0x1404 + (0x20 * (m))) -#define RCANFD_V3U_GAFL_OFFSET (0x1800) +#define RCANFD_GEN4_GAFL_OFFSET (0x1800) /* CAN FD mode specific register map */ /* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */ -#define RCANFD_F_DCFG(m) (0x0500 + (0x20 * (m))) +#define RCANFD_F_DCFG(gpriv, m) (reg_gen4(gpriv, 0x1400, 0x0500) + (0x20 * (m))) #define RCANFD_F_CFDCFG(m) (0x0504 + (0x20 * (m))) #define RCANFD_F_CFDCTR(m) (0x0508 + (0x20 * (m))) #define RCANFD_F_CFDSTS(m) (0x050c + (0x20 * (m))) @@ -453,7 +453,7 @@ #define RCANFD_F_RMDF(q, b) (0x200c + (0x04 * (b)) + (0x20 * (q))) /* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */ -#define RCANFD_F_RFOFFSET(gpriv) reg_v3u(gpriv, 0x6000, 0x3000) +#define RCANFD_F_RFOFFSET(gpriv) reg_gen4(gpriv, 0x6000, 0x3000) #define RCANFD_F_RFID(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + (0x80 * (x))) #define RCANFD_F_RFPTR(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x04 + (0x80 * (x))) #define RCANFD_F_RFFDSTS(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x08 + (0x80 * (x))) @@ -461,7 +461,7 @@ (RCANFD_F_RFOFFSET(gpriv) + 0x0c + (0x80 * (x)) + (0x04 * (df))) /* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */ -#define RCANFD_F_CFOFFSET(gpriv) reg_v3u(gpriv, 0x6400, 0x3400) +#define RCANFD_F_CFOFFSET(gpriv) reg_gen4(gpriv, 0x6400, 0x3400) #define RCANFD_F_CFID(gpriv, ch, idx) \ (RCANFD_F_CFOFFSET(gpriv) + (0x180 * (ch)) + (0x80 * (idx))) @@ -597,28 +597,28 @@ static const struct rcar_canfd_hw_info rcar_gen3_hw_info = { .shared_global_irqs = 1, }; +static const struct rcar_canfd_hw_info rcar_gen4_hw_info = { + .max_channels = 8, + .postdiv = 2, + .shared_global_irqs = 1, +}; + static const struct rcar_canfd_hw_info rzg2l_hw_info = { .max_channels = 2, .postdiv = 1, .multi_channel_irqs = 1, }; -static const struct rcar_canfd_hw_info r8a779a0_hw_info = { - .max_channels = 8, - .postdiv = 2, - .shared_global_irqs = 1, -}; - /* Helper functions */ -static inline bool is_v3u(struct rcar_canfd_global *gpriv) +static inline bool is_gen4(struct rcar_canfd_global *gpriv) { - return gpriv->info == &r8a779a0_hw_info; + return gpriv->info == &rcar_gen4_hw_info; } -static inline u32 reg_v3u(struct rcar_canfd_global *gpriv, - u32 v3u, u32 not_v3u) +static inline u32 reg_gen4(struct rcar_canfd_global *gpriv, + u32 gen4, u32 not_gen4) { - return is_v3u(gpriv) ? v3u : not_v3u; + return is_gen4(gpriv) ? gen4 : not_gen4; } static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg) @@ -688,13 +688,14 @@ static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev) static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv) { - if (is_v3u(gpriv)) { - if (gpriv->fdmode) - rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, - RCANFD_FDCFG_FDOE); - else - rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, - RCANFD_FDCFG_CLOE); + if (is_gen4(gpriv)) { + u32 ch, val = gpriv->fdmode ? RCANFD_GEN4_FDCFG_FDOE + : RCANFD_GEN4_FDCFG_CLOE; + + for_each_set_bit(ch, &gpriv->channels_mask, + gpriv->info->max_channels) + rcar_canfd_set_bit(gpriv->base, RCANFD_GEN4_FDCFG(ch), + val); } else { if (gpriv->fdmode) rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, @@ -814,8 +815,8 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, /* Write number of rules for channel */ rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(ch), RCANFD_GAFLCFG_SETRNC(gpriv, ch, num_rules)); - if (is_v3u(gpriv)) - offset = RCANFD_V3U_GAFL_OFFSET; + if (is_gen4(gpriv)) + offset = RCANFD_GEN4_GAFL_OFFSET; else if (gpriv->fdmode) offset = RCANFD_F_GAFL_OFFSET; else @@ -1343,17 +1344,14 @@ static void rcar_canfd_set_bittiming(struct net_device *dev) tseg2 = dbt->phase_seg2 - 1; cfg = (RCANFD_DCFG_DTSEG1(gpriv, tseg1) | RCANFD_DCFG_DBRP(brp) | - RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2)); + RCANFD_DCFG_DSJW(gpriv, sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2)); - if (is_v3u(gpriv)) - rcar_canfd_write(priv->base, RCANFD_V3U_DCFG(ch), cfg); - else - rcar_canfd_write(priv->base, RCANFD_F_DCFG(ch), cfg); + rcar_canfd_write(priv->base, RCANFD_F_DCFG(gpriv, ch), cfg); netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n", brp, sjw, tseg1, tseg2); } else { /* Classical CAN only mode */ - if (is_v3u(gpriv)) { + if (is_gen4(gpriv)) { cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) | RCANFD_NCFG_NBRP(brp) | RCANFD_NCFG_NSJW(gpriv, sjw) | @@ -1510,7 +1508,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len)); - if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) { rcar_canfd_write(priv->base, RCANFD_F_CFID(gpriv, ch, RCANFD_CFFIFO_IDX), id); rcar_canfd_write(priv->base, @@ -1569,7 +1567,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) u32 ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; - if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_gen4(gpriv)) { id = rcar_canfd_read(priv->base, RCANFD_F_RFID(gpriv, ridx)); dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(gpriv, ridx)); @@ -1620,7 +1618,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc)); if (id & RCANFD_RFID_RFRTR) cf->can_id |= CAN_RTR_FLAG; - else if (is_v3u(gpriv)) + else if (is_gen4(gpriv)) rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0)); else rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0)); @@ -1717,13 +1715,14 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, { const struct rcar_canfd_hw_info *info = gpriv->info; struct platform_device *pdev = gpriv->pdev; + struct device *dev = &pdev->dev; struct rcar_canfd_channel *priv; struct net_device *ndev; int err = -ENODEV; ndev = alloc_candev(sizeof(*priv), RCANFD_FIFO_DEPTH); if (!ndev) { - dev_err(&pdev->dev, "alloc_candev() failed\n"); + dev_err(dev, "alloc_candev() failed\n"); return -ENOMEM; } priv = netdev_priv(ndev); @@ -1736,7 +1735,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->channel = ch; priv->gpriv = gpriv; priv->can.clock.freq = fcan_freq; - dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq); + dev_info(dev, "can_clk rate is %u\n", priv->can.clock.freq); if (info->multi_channel_irqs) { char *irq_name; @@ -1755,31 +1754,31 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, goto fail; } - irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "canfd.ch%d_err", ch); + irq_name = devm_kasprintf(dev, GFP_KERNEL, "canfd.ch%d_err", + ch); if (!irq_name) { err = -ENOMEM; goto fail; } - err = devm_request_irq(&pdev->dev, err_irq, + err = devm_request_irq(dev, err_irq, rcar_canfd_channel_err_interrupt, 0, irq_name, priv); if (err) { - dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq CH Err(%d) failed, error %d\n", err_irq, err); goto fail; } - irq_name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "canfd.ch%d_trx", ch); + irq_name = devm_kasprintf(dev, GFP_KERNEL, "canfd.ch%d_trx", + ch); if (!irq_name) { err = -ENOMEM; goto fail; } - err = devm_request_irq(&pdev->dev, tx_irq, + err = devm_request_irq(dev, tx_irq, rcar_canfd_channel_tx_interrupt, 0, irq_name, priv); if (err) { - dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n", + dev_err(dev, "devm_request_irq Tx (%d) failed, error %d\n", tx_irq, err); goto fail; } @@ -1803,7 +1802,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, priv->can.do_set_mode = rcar_canfd_do_set_mode; priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter; - SET_NETDEV_DEV(ndev, &pdev->dev); + SET_NETDEV_DEV(ndev, dev); netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll, RCANFD_NAPI_WEIGHT); @@ -1811,11 +1810,10 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, gpriv->ch[priv->channel] = priv; err = register_candev(ndev); if (err) { - dev_err(&pdev->dev, - "register_candev() failed, error %d\n", err); + dev_err(dev, "register_candev() failed, error %d\n", err); goto fail_candev; } - dev_info(&pdev->dev, "device registered (channel %u)\n", priv->channel); + dev_info(dev, "device registered (channel %u)\n", priv->channel); return 0; fail_candev: @@ -1839,6 +1837,7 @@ static void rcar_canfd_channel_remove(struct rcar_canfd_global *gpriv, u32 ch) static int rcar_canfd_probe(struct platform_device *pdev) { const struct rcar_canfd_hw_info *info; + struct device *dev = &pdev->dev; void __iomem *addr; u32 sts, ch, fcan_freq; struct rcar_canfd_global *gpriv; @@ -1850,14 +1849,14 @@ static int rcar_canfd_probe(struct platform_device *pdev) char name[9] = "channelX"; int i; - info = of_device_get_match_data(&pdev->dev); + info = of_device_get_match_data(dev); - if (of_property_read_bool(pdev->dev.of_node, "renesas,no-can-fd")) + if (of_property_read_bool(dev->of_node, "renesas,no-can-fd")) fdmode = false; /* Classical CAN only mode */ for (i = 0; i < info->max_channels; ++i) { name[7] = '0' + i; - of_child = of_get_child_by_name(pdev->dev.of_node, name); + of_child = of_get_child_by_name(dev->of_node, name); if (of_child && of_device_is_available(of_child)) channels_mask |= BIT(i); of_node_put(of_child); @@ -1890,7 +1889,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) } /* Global controller context */ - gpriv = devm_kzalloc(&pdev->dev, sizeof(*gpriv), GFP_KERNEL); + gpriv = devm_kzalloc(dev, sizeof(*gpriv), GFP_KERNEL); if (!gpriv) return -ENOMEM; @@ -1899,32 +1898,30 @@ static int rcar_canfd_probe(struct platform_device *pdev) gpriv->fdmode = fdmode; gpriv->info = info; - gpriv->rstc1 = devm_reset_control_get_optional_exclusive(&pdev->dev, - "rstp_n"); + gpriv->rstc1 = devm_reset_control_get_optional_exclusive(dev, "rstp_n"); if (IS_ERR(gpriv->rstc1)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc1), + return dev_err_probe(dev, PTR_ERR(gpriv->rstc1), "failed to get rstp_n\n"); - gpriv->rstc2 = devm_reset_control_get_optional_exclusive(&pdev->dev, - "rstc_n"); + gpriv->rstc2 = devm_reset_control_get_optional_exclusive(dev, "rstc_n"); if (IS_ERR(gpriv->rstc2)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->rstc2), + return dev_err_probe(dev, PTR_ERR(gpriv->rstc2), "failed to get rstc_n\n"); /* Peripheral clock */ - gpriv->clkp = devm_clk_get(&pdev->dev, "fck"); + gpriv->clkp = devm_clk_get(dev, "fck"); if (IS_ERR(gpriv->clkp)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->clkp), + return dev_err_probe(dev, PTR_ERR(gpriv->clkp), "cannot get peripheral clock\n"); /* fCAN clock: Pick External clock. If not available fallback to * CANFD clock */ - gpriv->can_clk = devm_clk_get(&pdev->dev, "can_clk"); + gpriv->can_clk = devm_clk_get(dev, "can_clk"); if (IS_ERR(gpriv->can_clk) || (clk_get_rate(gpriv->can_clk) == 0)) { - gpriv->can_clk = devm_clk_get(&pdev->dev, "canfd"); + gpriv->can_clk = devm_clk_get(dev, "canfd"); if (IS_ERR(gpriv->can_clk)) - return dev_err_probe(&pdev->dev, PTR_ERR(gpriv->can_clk), + return dev_err_probe(dev, PTR_ERR(gpriv->can_clk), "cannot get canfd clock\n"); gpriv->fcan = RCANFD_CANFDCLK; @@ -1947,39 +1944,38 @@ static int rcar_canfd_probe(struct platform_device *pdev) /* Request IRQ that's common for both channels */ if (info->shared_global_irqs) { - err = devm_request_irq(&pdev->dev, ch_irq, + err = devm_request_irq(dev, ch_irq, rcar_canfd_channel_interrupt, 0, "canfd.ch_int", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", ch_irq, err); goto fail_dev; } - err = devm_request_irq(&pdev->dev, g_irq, - rcar_canfd_global_interrupt, 0, - "canfd.g_int", gpriv); + err = devm_request_irq(dev, g_irq, rcar_canfd_global_interrupt, + 0, "canfd.g_int", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_irq, err); goto fail_dev; } } else { - err = devm_request_irq(&pdev->dev, g_recc_irq, + err = devm_request_irq(dev, g_recc_irq, rcar_canfd_global_receive_fifo_interrupt, 0, "canfd.g_recc", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_recc_irq, err); goto fail_dev; } - err = devm_request_irq(&pdev->dev, g_err_irq, + err = devm_request_irq(dev, g_err_irq, rcar_canfd_global_err_interrupt, 0, "canfd.g_err", gpriv); if (err) { - dev_err(&pdev->dev, "devm_request_irq(%d) failed, error %d\n", + dev_err(dev, "devm_request_irq(%d) failed, error %d\n", g_err_irq, err); goto fail_dev; } @@ -1997,14 +1993,14 @@ static int rcar_canfd_probe(struct platform_device *pdev) /* Enable peripheral clock for register access */ err = clk_prepare_enable(gpriv->clkp); if (err) { - dev_err(&pdev->dev, - "failed to enable peripheral clock, error %d\n", err); + dev_err(dev, "failed to enable peripheral clock, error %d\n", + err); goto fail_reset; } err = rcar_canfd_reset_controller(gpriv); if (err) { - dev_err(&pdev->dev, "reset controller failed\n"); + dev_err(dev, "reset controller failed\n"); goto fail_clk; } @@ -2034,7 +2030,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) err = readl_poll_timeout((gpriv->base + RCANFD_GSTS), sts, !(sts & RCANFD_GSTS_GNOPM), 2, 500000); if (err) { - dev_err(&pdev->dev, "global operational mode failed\n"); + dev_err(dev, "global operational mode failed\n"); goto fail_mode; } @@ -2045,7 +2041,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, gpriv); - dev_info(&pdev->dev, "global operational state (clk %d, fdmode %d)\n", + dev_info(dev, "global operational state (clk %d, fdmode %d)\n", gpriv->fcan, gpriv->fdmode); return 0; @@ -2099,9 +2095,10 @@ static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend, rcar_canfd_resume); static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = { + { .compatible = "renesas,r8a779a0-canfd", .data = &rcar_gen4_hw_info }, { .compatible = "renesas,rcar-gen3-canfd", .data = &rcar_gen3_hw_info }, + { .compatible = "renesas,rcar-gen4-canfd", .data = &rcar_gen4_hw_info }, { .compatible = "renesas,rzg2l-canfd", .data = &rzg2l_hw_info }, - { .compatible = "renesas,r8a779a0-canfd", .data = &r8a779a0_hw_info }, { } }; diff --git a/drivers/net/can/sja1000/ems_pci.c b/drivers/net/can/sja1000/ems_pci.c index 4ab91759a5c6..c56e27223e5f 100644 --- a/drivers/net/can/sja1000/ems_pci.c +++ b/drivers/net/can/sja1000/ems_pci.c @@ -3,6 +3,7 @@ * Copyright (C) 2007 Wolfgang Grandegger <wg@grandegger.com> * Copyright (C) 2008 Markus Plessing <plessing@ems-wuensche.com> * Copyright (C) 2008 Sebastian Haas <haas@ems-wuensche.com> + * Copyright (C) 2023 EMS Dr. Thomas Wuensche */ #include <linux/kernel.h> @@ -19,12 +20,14 @@ #define DRV_NAME "ems_pci" -MODULE_AUTHOR("Sebastian Haas <haas@ems-wuenche.com>"); +MODULE_AUTHOR("Sebastian Haas <support@ems-wuensche.com>"); +MODULE_AUTHOR("Gerhard Uttenthaler <uttenthaler@ems-wuensche.com>"); MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-PCI/PCIe/104P CAN cards"); MODULE_LICENSE("GPL v2"); #define EMS_PCI_V1_MAX_CHAN 2 #define EMS_PCI_V2_MAX_CHAN 4 +#define EMS_PCI_V3_MAX_CHAN 4 #define EMS_PCI_MAX_CHAN EMS_PCI_V2_MAX_CHAN struct ems_pci_card { @@ -40,8 +43,7 @@ struct ems_pci_card { #define EMS_PCI_CAN_CLOCK (16000000 / 2) -/* - * Register definitions and descriptions are from LinCAN 0.3.3. +/* Register definitions and descriptions are from LinCAN 0.3.3. * * PSB4610 PITA-2 bridge control registers */ @@ -52,8 +54,7 @@ struct ems_pci_card { #define PITA2_MISC 0x1c /* Miscellaneous Register */ #define PITA2_MISC_CONFIG 0x04000000 /* Multiplexed parallel interface */ -/* - * Register definitions for the PLX 9030 +/* Register definitions for the PLX 9030 */ #define PLX_ICSR 0x4c /* Interrupt Control/Status register */ #define PLX_ICSR_LINTI1_ENA 0x0001 /* LINTi1 Enable */ @@ -62,8 +63,16 @@ struct ems_pci_card { #define PLX_ICSR_ENA_CLR (PLX_ICSR_LINTI1_ENA | PLX_ICSR_PCIINT_ENA | \ PLX_ICSR_LINTI1_CLR) -/* - * The board configuration is probably following: +/* Register definitions for the ASIX99100 + */ +#define ASIX_LINTSR 0x28 /* Interrupt Control/Status register */ +#define ASIX_LINTSR_INT0AC BIT(0) /* Writing 1 enables or clears interrupt */ + +#define ASIX_LIEMR 0x24 /* Local Interrupt Enable / Miscellaneous Register */ +#define ASIX_LIEMR_L0EINTEN BIT(16) /* Local INT0 input assertion enable */ +#define ASIX_LIEMR_LRST BIT(14) /* Local Reset assert */ + +/* The board configuration is probably following: * RX1 is connected to ground. * TX1 is not connected. * CLKO is not connected. @@ -72,23 +81,40 @@ struct ems_pci_card { */ #define EMS_PCI_OCR (OCR_TX0_PUSHPULL | OCR_TX1_PUSHPULL) -/* - * In the CDR register, you should set CBP to 1. +/* In the CDR register, you should set CBP to 1. * You will probably also want to set the clock divider value to 7 * (meaning direct oscillator output) because the second SJA1000 chip * is driven by the first one CLKOUT output. */ #define EMS_PCI_CDR (CDR_CBP | CDR_CLKOUT_MASK) -#define EMS_PCI_V1_BASE_BAR 1 -#define EMS_PCI_V1_CONF_SIZE 4096 /* size of PITA control area */ -#define EMS_PCI_V2_BASE_BAR 2 -#define EMS_PCI_V2_CONF_SIZE 128 /* size of PLX control area */ -#define EMS_PCI_CAN_BASE_OFFSET 0x400 /* offset where the controllers starts */ -#define EMS_PCI_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ +#define EMS_PCI_V1_BASE_BAR 1 +#define EMS_PCI_V1_CONF_BAR 0 +#define EMS_PCI_V1_CONF_SIZE 4096 /* size of PITA control area */ +#define EMS_PCI_V1_CAN_BASE_OFFSET 0x400 /* offset where the controllers start */ +#define EMS_PCI_V1_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ + +#define EMS_PCI_V2_BASE_BAR 2 +#define EMS_PCI_V2_CONF_BAR 0 +#define EMS_PCI_V2_CONF_SIZE 128 /* size of PLX control area */ +#define EMS_PCI_V2_CAN_BASE_OFFSET 0x400 /* offset where the controllers start */ +#define EMS_PCI_V2_CAN_CTRL_SIZE 0x200 /* memory size for each controller */ + +#define EMS_PCI_V3_BASE_BAR 0 +#define EMS_PCI_V3_CONF_BAR 5 +#define EMS_PCI_V3_CONF_SIZE 128 /* size of ASIX control area */ +#define EMS_PCI_V3_CAN_BASE_OFFSET 0x00 /* offset where the controllers starts */ +#define EMS_PCI_V3_CAN_CTRL_SIZE 0x100 /* memory size for each controller */ #define EMS_PCI_BASE_SIZE 4096 /* size of controller area */ +#ifndef PCI_VENDOR_ID_ASIX +#define PCI_VENDOR_ID_ASIX 0x125b +#define PCI_DEVICE_ID_ASIX_9110 0x9110 +#define PCI_SUBVENDOR_ID_ASIX 0xa000 +#endif +#define PCI_SUBDEVICE_ID_EMS 0x4010 + static const struct pci_device_id ems_pci_tbl[] = { /* CPC-PCI v1 */ {PCI_VENDOR_ID_SIEMENS, 0x2104, PCI_ANY_ID, PCI_ANY_ID,}, @@ -96,12 +122,13 @@ static const struct pci_device_id ems_pci_tbl[] = { {PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_PLX, 0x4000}, /* CPC-104P v2 */ {PCI_VENDOR_ID_PLX, PCI_DEVICE_ID_PLX_9030, PCI_VENDOR_ID_PLX, 0x4002}, + /* CPC-PCIe v3 */ + {PCI_VENDOR_ID_ASIX, PCI_DEVICE_ID_ASIX_9110, PCI_SUBVENDOR_ID_ASIX, PCI_SUBDEVICE_ID_EMS}, {0,} }; MODULE_DEVICE_TABLE(pci, ems_pci_tbl); -/* - * Helper to read internal registers from card logic (not CAN) +/* Helper to read internal registers from card logic (not CAN) */ static u8 ems_pci_v1_readb(struct ems_pci_card *card, unsigned int port) { @@ -146,8 +173,25 @@ static void ems_pci_v2_post_irq(const struct sja1000_priv *priv) writel(PLX_ICSR_ENA_CLR, card->conf_addr + PLX_ICSR); } -/* - * Check if a CAN controller is present at the specified location +static u8 ems_pci_v3_read_reg(const struct sja1000_priv *priv, int port) +{ + return readb(priv->reg_base + port); +} + +static void ems_pci_v3_write_reg(const struct sja1000_priv *priv, + int port, u8 val) +{ + writeb(val, priv->reg_base + port); +} + +static void ems_pci_v3_post_irq(const struct sja1000_priv *priv) +{ + struct ems_pci_card *card = (struct ems_pci_card *)priv->priv; + + writel(ASIX_LINTSR_INT0AC, card->conf_addr + ASIX_LINTSR); +} + +/* Check if a CAN controller is present at the specified location * by trying to set 'em into the PeliCAN mode */ static inline int ems_pci_check_chan(const struct sja1000_priv *priv) @@ -185,10 +229,10 @@ static void ems_pci_del_card(struct pci_dev *pdev) free_sja1000dev(dev); } - if (card->base_addr != NULL) + if (card->base_addr) pci_iounmap(card->pci_dev, card->base_addr); - if (card->conf_addr != NULL) + if (card->conf_addr) pci_iounmap(card->pci_dev, card->conf_addr); kfree(card); @@ -202,8 +246,7 @@ static void ems_pci_card_reset(struct ems_pci_card *card) writeb(0, card->base_addr); } -/* - * Probe PCI device for EMS CAN signature and register each available +/* Probe PCI device for EMS CAN signature and register each available * CAN channel to SJA1000 Socket-CAN subsystem. */ static int ems_pci_add_card(struct pci_dev *pdev, @@ -212,7 +255,7 @@ static int ems_pci_add_card(struct pci_dev *pdev, struct sja1000_priv *priv; struct net_device *dev; struct ems_pci_card *card; - int max_chan, conf_size, base_bar; + int max_chan, conf_size, base_bar, conf_bar; int err, i; /* Enabling PCI device */ @@ -222,8 +265,8 @@ static int ems_pci_add_card(struct pci_dev *pdev, } /* Allocating card structures to hold addresses, ... */ - card = kzalloc(sizeof(struct ems_pci_card), GFP_KERNEL); - if (card == NULL) { + card = kzalloc(sizeof(*card), GFP_KERNEL); + if (!card) { pci_disable_device(pdev); return -ENOMEM; } @@ -234,27 +277,35 @@ static int ems_pci_add_card(struct pci_dev *pdev, card->channels = 0; - if (pdev->vendor == PCI_VENDOR_ID_PLX) { + if (pdev->vendor == PCI_VENDOR_ID_ASIX) { + card->version = 3; /* CPC-PCI v3 */ + max_chan = EMS_PCI_V3_MAX_CHAN; + base_bar = EMS_PCI_V3_BASE_BAR; + conf_bar = EMS_PCI_V3_CONF_BAR; + conf_size = EMS_PCI_V3_CONF_SIZE; + } else if (pdev->vendor == PCI_VENDOR_ID_PLX) { card->version = 2; /* CPC-PCI v2 */ max_chan = EMS_PCI_V2_MAX_CHAN; base_bar = EMS_PCI_V2_BASE_BAR; + conf_bar = EMS_PCI_V2_CONF_BAR; conf_size = EMS_PCI_V2_CONF_SIZE; } else { card->version = 1; /* CPC-PCI v1 */ max_chan = EMS_PCI_V1_MAX_CHAN; base_bar = EMS_PCI_V1_BASE_BAR; + conf_bar = EMS_PCI_V1_CONF_BAR; conf_size = EMS_PCI_V1_CONF_SIZE; } /* Remap configuration space and controller memory area */ - card->conf_addr = pci_iomap(pdev, 0, conf_size); - if (card->conf_addr == NULL) { + card->conf_addr = pci_iomap(pdev, conf_bar, conf_size); + if (!card->conf_addr) { err = -ENOMEM; goto failure_cleanup; } card->base_addr = pci_iomap(pdev, base_bar, EMS_PCI_BASE_SIZE); - if (card->base_addr == NULL) { + if (!card->base_addr) { err = -ENOMEM; goto failure_cleanup; } @@ -276,12 +327,20 @@ static int ems_pci_add_card(struct pci_dev *pdev, } } + if (card->version == 3) { + /* ASIX chip asserts local reset to CAN controllers + * after bootup until it is deasserted + */ + writel(readl(card->conf_addr + ASIX_LIEMR) & ~ASIX_LIEMR_LRST, + card->conf_addr + ASIX_LIEMR); + } + ems_pci_card_reset(card); /* Detect available channels */ for (i = 0; i < max_chan; i++) { dev = alloc_sja1000dev(0); - if (dev == NULL) { + if (!dev) { err = -ENOMEM; goto failure_cleanup; } @@ -292,16 +351,25 @@ static int ems_pci_add_card(struct pci_dev *pdev, priv->irq_flags = IRQF_SHARED; dev->irq = pdev->irq; - priv->reg_base = card->base_addr + EMS_PCI_CAN_BASE_OFFSET - + (i * EMS_PCI_CAN_CTRL_SIZE); + if (card->version == 1) { priv->read_reg = ems_pci_v1_read_reg; priv->write_reg = ems_pci_v1_write_reg; priv->post_irq = ems_pci_v1_post_irq; - } else { + priv->reg_base = card->base_addr + EMS_PCI_V1_CAN_BASE_OFFSET + + (i * EMS_PCI_V1_CAN_CTRL_SIZE); + } else if (card->version == 2) { priv->read_reg = ems_pci_v2_read_reg; priv->write_reg = ems_pci_v2_write_reg; priv->post_irq = ems_pci_v2_post_irq; + priv->reg_base = card->base_addr + EMS_PCI_V2_CAN_BASE_OFFSET + + (i * EMS_PCI_V2_CAN_CTRL_SIZE); + } else { + priv->read_reg = ems_pci_v3_read_reg; + priv->write_reg = ems_pci_v3_write_reg; + priv->post_irq = ems_pci_v3_post_irq; + priv->reg_base = card->base_addr + EMS_PCI_V3_CAN_BASE_OFFSET + + (i * EMS_PCI_V3_CAN_CTRL_SIZE); } /* Check if channel is present */ @@ -313,20 +381,28 @@ static int ems_pci_add_card(struct pci_dev *pdev, SET_NETDEV_DEV(dev, &pdev->dev); dev->dev_id = i; - if (card->version == 1) + if (card->version == 1) { /* reset int flag of pita */ writel(PITA2_ICR_INT0_EN | PITA2_ICR_INT0, card->conf_addr + PITA2_ICR); - else + } else if (card->version == 2) { /* enable IRQ in PLX 9030 */ writel(PLX_ICSR_ENA_CLR, card->conf_addr + PLX_ICSR); + } else { + /* Enable IRQ in AX99100 */ + writel(ASIX_LINTSR_INT0AC, card->conf_addr + ASIX_LINTSR); + /* Enable local INT0 input enable */ + writel(readl(card->conf_addr + ASIX_LIEMR) | ASIX_LIEMR_L0EINTEN, + card->conf_addr + ASIX_LIEMR); + } /* Register SJA1000 device */ err = register_sja1000dev(dev); if (err) { - dev_err(&pdev->dev, "Registering device failed " - "(err=%d)\n", err); + dev_err(&pdev->dev, + "Registering device failed: %pe\n", + ERR_PTR(err)); free_sja1000dev(dev); goto failure_cleanup; } @@ -334,7 +410,7 @@ static int ems_pci_add_card(struct pci_dev *pdev, card->channels++; dev_info(&pdev->dev, "Channel #%d at 0x%p, irq %d\n", - i + 1, priv->reg_base, dev->irq); + i + 1, priv->reg_base, dev->irq); } else { free_sja1000dev(dev); } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c index bf3f0f150199..bfe4caa0c99d 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c @@ -30,11 +30,23 @@ mcp251xfd_cmd_prepare_write_reg(const struct mcp251xfd_priv *priv, last_byte = mcp251xfd_last_byte_set(mask); len = last_byte - first_byte + 1; - data = mcp251xfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte); + data = mcp251xfd_spi_cmd_write(priv, write_reg_buf, reg + first_byte, len); val_le32 = cpu_to_le32(val >> BITS_PER_BYTE * first_byte); memcpy(data, &val_le32, len); - if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) { + if (!(priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG)) { + len += sizeof(write_reg_buf->nocrc.cmd); + } else if (len == 1) { + u16 crc; + + /* CRC */ + len += sizeof(write_reg_buf->safe.cmd); + crc = mcp251xfd_crc16_compute(&write_reg_buf->safe, len); + put_unaligned_be16(crc, (void *)write_reg_buf + len); + + /* Total length */ + len += sizeof(write_reg_buf->safe.crc); + } else { u16 crc; mcp251xfd_spi_cmd_crc_set_len_in_reg(&write_reg_buf->crc.cmd, @@ -46,8 +58,6 @@ mcp251xfd_cmd_prepare_write_reg(const struct mcp251xfd_priv *priv, /* Total length */ len += sizeof(write_reg_buf->crc.crc); - } else { - len += sizeof(write_reg_buf->nocrc.cmd); } return len; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 2b0309fedfac..7024ff0cc2c0 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -504,6 +504,11 @@ union mcp251xfd_write_reg_buf { u8 data[4]; __be16 crc; } crc; + struct __packed { + struct mcp251xfd_buf_cmd cmd; + u8 data[1]; + __be16 crc; + } safe; } ____cacheline_aligned; struct mcp251xfd_tx_obj { @@ -759,6 +764,13 @@ mcp251xfd_spi_cmd_write_crc_set_addr(struct mcp251xfd_buf_cmd_crc *cmd, } static inline void +mcp251xfd_spi_cmd_write_safe_set_addr(struct mcp251xfd_buf_cmd *cmd, + u16 addr) +{ + cmd->cmd = cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE_CRC_SAFE | addr); +} + +static inline void mcp251xfd_spi_cmd_write_crc(struct mcp251xfd_buf_cmd_crc *cmd, u16 addr, u16 len) { @@ -769,14 +781,20 @@ mcp251xfd_spi_cmd_write_crc(struct mcp251xfd_buf_cmd_crc *cmd, static inline u8 * mcp251xfd_spi_cmd_write(const struct mcp251xfd_priv *priv, union mcp251xfd_write_reg_buf *write_reg_buf, - u16 addr) + u16 addr, u8 len) { u8 *data; if (priv->devtype_data.quirks & MCP251XFD_QUIRK_CRC_REG) { - mcp251xfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd, - addr); - data = write_reg_buf->crc.data; + if (len == 1) { + mcp251xfd_spi_cmd_write_safe_set_addr(&write_reg_buf->safe.cmd, + addr); + data = write_reg_buf->safe.data; + } else { + mcp251xfd_spi_cmd_write_crc_set_addr(&write_reg_buf->crc.cmd, + addr); + data = write_reg_buf->crc.data; + } } else { mcp251xfd_spi_cmd_write_nocrc(&write_reg_buf->nocrc.cmd, addr); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 687dd542f7f6..b211b6e283a2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -9,10 +9,11 @@ * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ #include <asm/unaligned.h> + +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -381,23 +382,42 @@ static int pcan_usb_get_serial(struct peak_usb_device *dev, u32 *serial_number) } /* - * read device id from device + * read can channel id from device */ -static int pcan_usb_get_device_id(struct peak_usb_device *dev, u32 *device_id) +static int pcan_usb_get_can_channel_id(struct peak_usb_device *dev, u32 *can_ch_id) { u8 args[PCAN_USB_CMD_ARGS_LEN]; int err; err = pcan_usb_wait_rsp(dev, PCAN_USB_CMD_DEVID, PCAN_USB_GET, args); if (err) - netdev_err(dev->netdev, "getting device id failure: %d\n", err); + netdev_err(dev->netdev, "getting can channel id failure: %d\n", err); else - *device_id = args[0]; + *can_ch_id = args[0]; return err; } +/* set a new CAN channel id in the flash memory of the device */ +static int pcan_usb_set_can_channel_id(struct peak_usb_device *dev, u32 can_ch_id) +{ + u8 args[PCAN_USB_CMD_ARGS_LEN]; + + /* this kind of device supports 8-bit values only */ + if (can_ch_id > U8_MAX) + return -EINVAL; + + /* during the flash process the device disconnects during ~1.25 s.: + * prohibit access when interface is UP + */ + if (dev->netdev->flags & IFF_UP) + return -EBUSY; + + args[0] = can_ch_id; + return pcan_usb_send_cmd(dev, PCAN_USB_CMD_DEVID, PCAN_USB_SET, args); +} + /* * update current time ref with received timestamp */ @@ -963,9 +983,18 @@ static int pcan_usb_set_phys_id(struct net_device *netdev, return err; } +/* This device only handles 8-bit CAN channel id. */ +static int pcan_usb_get_eeprom_len(struct net_device *netdev) +{ + return sizeof(u8); +} + static const struct ethtool_ops pcan_usb_ethtool_ops = { .set_phys_id = pcan_usb_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = pcan_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* @@ -1017,7 +1046,8 @@ const struct peak_usb_adapter pcan_usb = { .dev_init = pcan_usb_init, .dev_set_bus = pcan_usb_write_mode, .dev_set_bittiming = pcan_usb_set_bittiming, - .dev_get_device_id = pcan_usb_get_device_id, + .dev_get_can_channel_id = pcan_usb_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_set_can_channel_id, .dev_decode_buf = pcan_usb_decode_buf, .dev_encode_msg = pcan_usb_encode_msg, .dev_start = pcan_usb_start, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 1d996d3320fe..d881e1d30183 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -8,13 +8,15 @@ * * Many thanks to Klaus Hitschler <klaus.hitschler@gmx.de> */ +#include <linux/device.h> +#include <linux/ethtool.h> #include <linux/init.h> -#include <linux/signal.h> -#include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/signal.h> +#include <linux/slab.h> +#include <linux/sysfs.h> #include <linux/usb.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -53,6 +55,26 @@ static const struct usb_device_id peak_usb_table[] = { MODULE_DEVICE_TABLE(usb, peak_usb_table); +static ssize_t can_channel_id_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + struct peak_usb_device *peak_dev = netdev_priv(netdev); + + return sysfs_emit(buf, "%08X\n", peak_dev->can_channel_id); +} +static DEVICE_ATTR_RO(can_channel_id); + +/* mutable to avoid cast in attribute_group */ +static struct attribute *peak_usb_sysfs_attrs[] = { + &dev_attr_can_channel_id.attr, + NULL, +}; + +static const struct attribute_group peak_usb_sysfs_group = { + .name = "peak_usb", + .attrs = peak_usb_sysfs_attrs, +}; + /* * dump memory */ @@ -808,6 +830,86 @@ static const struct net_device_ops peak_usb_netdev_ops = { .ndo_change_mtu = can_change_mtu, }; +/* CAN-USB devices generally handle 32-bit CAN channel IDs. + * In case one doesn't, then it have to overload this function. + */ +int peak_usb_get_eeprom_len(struct net_device *netdev) +{ + return sizeof(u32); +} + +/* Every CAN-USB device exports the dev_get_can_channel_id() operation. It is used + * here to fill the data buffer with the user defined CAN channel ID. + */ +int peak_usb_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + u32 ch_id; + __le32 ch_id_le; + int err; + + err = dev->adapter->dev_get_can_channel_id(dev, &ch_id); + if (err) + return err; + + /* ethtool operates on individual bytes. The byte order of the CAN + * channel id in memory depends on the kernel architecture. We + * convert the CAN channel id back to the native byte order of the PEAK + * device itself to ensure that the order is consistent for all + * host architectures. + */ + ch_id_le = cpu_to_le32(ch_id); + memcpy(data, (u8 *)&ch_id_le + eeprom->offset, eeprom->len); + + /* update cached value */ + dev->can_channel_id = ch_id; + return err; +} + +/* Every CAN-USB device exports the dev_get_can_channel_id()/dev_set_can_channel_id() + * operations. They are used here to set the new user defined CAN channel ID. + */ +int peak_usb_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct peak_usb_device *dev = netdev_priv(netdev); + u32 ch_id; + __le32 ch_id_le; + int err; + + /* first, read the current user defined CAN channel ID */ + err = dev->adapter->dev_get_can_channel_id(dev, &ch_id); + if (err) { + netdev_err(netdev, "Failed to init CAN channel id (err %d)\n", err); + return err; + } + + /* do update the value with user given bytes. + * ethtool operates on individual bytes. The byte order of the CAN + * channel ID in memory depends on the kernel architecture. We + * convert the CAN channel ID back to the native byte order of the PEAK + * device itself to ensure that the order is consistent for all + * host architectures. + */ + ch_id_le = cpu_to_le32(ch_id); + memcpy((u8 *)&ch_id_le + eeprom->offset, data, eeprom->len); + ch_id = le32_to_cpu(ch_id_le); + + /* flash the new value now */ + err = dev->adapter->dev_set_can_channel_id(dev, ch_id); + if (err) { + netdev_err(netdev, "Failed to write new CAN channel id (err %d)\n", + err); + return err; + } + + /* update cached value with the new one */ + dev->can_channel_id = ch_id; + + return 0; +} + int pcan_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { info->so_timestamping = @@ -881,6 +983,9 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, /* add ethtool support */ netdev->ethtool_ops = peak_usb_adapter->ethtool_ops; + /* register peak_usb sysfs files */ + netdev->sysfs_groups[0] = &peak_usb_sysfs_group; + init_usb_anchor(&dev->rx_submitted); init_usb_anchor(&dev->tx_submitted); @@ -921,12 +1026,11 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, goto adap_dev_free; } - /* get device number early */ - if (dev->adapter->dev_get_device_id) - dev->adapter->dev_get_device_id(dev, &dev->device_number); + /* get CAN channel id early */ + dev->adapter->dev_get_can_channel_id(dev, &dev->can_channel_id); - netdev_info(netdev, "attached to %s channel %u (device %u)\n", - peak_usb_adapter->name, ctrl_idx, dev->device_number); + netdev_info(netdev, "attached to %s channel %u (device 0x%08X)\n", + peak_usb_adapter->name, ctrl_idx, dev->can_channel_id); return 0; @@ -964,7 +1068,7 @@ static void peak_usb_disconnect(struct usb_interface *intf) dev->state &= ~PCAN_USB_STATE_CONNECTED; strscpy(name, netdev->name, IFNAMSIZ); - unregister_netdev(netdev); + unregister_candev(netdev); kfree(dev->cmd_buf); dev->next_siblings = NULL; diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index f6bdd8b3f290..980e315186cf 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -60,7 +60,8 @@ struct peak_usb_adapter { int (*dev_set_data_bittiming)(struct peak_usb_device *dev, struct can_bittiming *bt); int (*dev_set_bus)(struct peak_usb_device *dev, u8 onoff); - int (*dev_get_device_id)(struct peak_usb_device *dev, u32 *device_id); + int (*dev_get_can_channel_id)(struct peak_usb_device *dev, u32 *can_ch_id); + int (*dev_set_can_channel_id)(struct peak_usb_device *dev, u32 can_ch_id); int (*dev_decode_buf)(struct peak_usb_device *dev, struct urb *urb); int (*dev_encode_msg)(struct peak_usb_device *dev, struct sk_buff *skb, u8 *obuf, size_t *size); @@ -122,7 +123,8 @@ struct peak_usb_device { u8 *cmd_buf; struct usb_anchor rx_submitted; - u32 device_number; + /* equivalent to the device ID in the Windows API */ + u32 can_channel_id; u8 device_rev; u8 ep_msg_in; @@ -147,4 +149,10 @@ void peak_usb_async_complete(struct urb *urb); void peak_usb_restart_complete(struct peak_usb_device *dev); int pcan_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info); +/* common 32-bit CAN channel ID ethtool management */ +int peak_usb_get_eeprom_len(struct net_device *netdev); +int peak_usb_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data); +int peak_usb_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *data); #endif diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c index 2ea1500df393..4d85b29a17b7 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c @@ -4,10 +4,10 @@ * * Copyright (C) 2013-2014 Stephane Grosjean <s.grosjean@peak-system.com> */ +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -147,6 +147,15 @@ struct __packed pcan_ufd_ovr_msg { u8 unused[3]; }; +#define PCAN_UFD_CMD_DEVID_SET 0x81 + +struct __packed pcan_ufd_device_id { + __le16 opcode_channel; + + u16 unused; + __le32 device_id; +}; + static inline int pufd_omsg_get_channel(struct pcan_ufd_ovr_msg *om) { return om->channel & 0xf; @@ -234,6 +243,15 @@ static int pcan_usb_fd_send_cmd(struct peak_usb_device *dev, void *cmd_tail) return err; } +static int pcan_usb_fd_read_fwinfo(struct peak_usb_device *dev, + struct pcan_ufd_fw_info *fw_info) +{ + return pcan_usb_pro_send_req(dev, PCAN_USBPRO_REQ_INFO, + PCAN_USBPRO_INFO_FW, + fw_info, + sizeof(*fw_info)); +} + /* build the commands list in the given buffer, to enter operational mode */ static int pcan_usb_fd_build_restart_cmd(struct peak_usb_device *dev, u8 *buf) { @@ -434,6 +452,34 @@ static int pcan_usb_fd_set_bittiming_fast(struct peak_usb_device *dev, return pcan_usb_fd_send_cmd(dev, ++cmd); } +/* read user CAN channel id from device */ +static int pcan_usb_fd_get_can_channel_id(struct peak_usb_device *dev, + u32 *can_ch_id) +{ + int err; + struct pcan_usb_fd_if *usb_if = pcan_usb_fd_dev_if(dev); + + err = pcan_usb_fd_read_fwinfo(dev, &usb_if->fw_info); + if (err) + return err; + + *can_ch_id = le32_to_cpu(usb_if->fw_info.dev_id[dev->ctrl_idx]); + return err; +} + +/* set a new CAN channel id in the flash memory of the device */ +static int pcan_usb_fd_set_can_channel_id(struct peak_usb_device *dev, u32 can_ch_id) +{ + struct pcan_ufd_device_id *cmd = pcan_usb_fd_cmd_buffer(dev); + + cmd->opcode_channel = pucan_cmd_opcode_channel(dev->ctrl_idx, + PCAN_UFD_CMD_DEVID_SET); + cmd->device_id = cpu_to_le32(can_ch_id); + + /* send the command */ + return pcan_usb_fd_send_cmd(dev, ++cmd); +} + /* handle restart but in asynchronously way * (uses PCAN-USB Pro code to complete asynchronous request) */ @@ -907,10 +953,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) fw_info = &pdev->usb_if->fw_info; - err = pcan_usb_pro_send_req(dev, PCAN_USBPRO_REQ_INFO, - PCAN_USBPRO_INFO_FW, - fw_info, - sizeof(*fw_info)); + err = pcan_usb_fd_read_fwinfo(dev, fw_info); if (err) { dev_err(dev->netdev->dev.parent, "unable to read %s firmware info (err %d)\n", @@ -972,7 +1015,7 @@ static int pcan_usb_fd_init(struct peak_usb_device *dev) } pdev->usb_if->dev[dev->ctrl_idx] = dev; - dev->device_number = + dev->can_channel_id = le32_to_cpu(pdev->usb_if->fw_info.dev_id[dev->ctrl_idx]); /* if vendor rsp is of type 2, then it contains EP numbers to @@ -1081,6 +1124,9 @@ static int pcan_usb_fd_set_phys_id(struct net_device *netdev, static const struct ethtool_ops pcan_usb_fd_ethtool_ops = { .set_phys_id = pcan_usb_fd_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = peak_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* describes the PCAN-USB FD adapter */ @@ -1148,6 +1194,8 @@ const struct peak_usb_adapter pcan_usb_fd = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1222,6 +1270,8 @@ const struct peak_usb_adapter pcan_usb_chip = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1296,6 +1346,8 @@ const struct peak_usb_adapter pcan_usb_pro_fd = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, @@ -1370,6 +1422,8 @@ const struct peak_usb_adapter pcan_usb_x6 = { .dev_set_bus = pcan_usb_fd_set_bus, .dev_set_bittiming = pcan_usb_fd_set_bittiming_slow, .dev_set_data_bittiming = pcan_usb_fd_set_bittiming_fast, + .dev_get_can_channel_id = pcan_usb_fd_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_fd_set_can_channel_id, .dev_decode_buf = pcan_usb_fd_decode_buf, .dev_start = pcan_usb_fd_start, .dev_stop = pcan_usb_fd_stop, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c index 5d8f6a40bb2c..f736196383ac 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c @@ -6,10 +6,10 @@ * Copyright (C) 2003-2011 PEAK System-Technik GmbH * Copyright (C) 2011-2012 Stephane Grosjean <s.grosjean@peak-system.com> */ +#include <linux/ethtool.h> +#include <linux/module.h> #include <linux/netdevice.h> #include <linux/usb.h> -#include <linux/module.h> -#include <linux/ethtool.h> #include <linux/can.h> #include <linux/can/dev.h> @@ -76,6 +76,7 @@ static u16 pcan_usb_pro_sizeof_rec[256] = { [PCAN_USBPRO_SETFILTR] = sizeof(struct pcan_usb_pro_filter), [PCAN_USBPRO_SETTS] = sizeof(struct pcan_usb_pro_setts), [PCAN_USBPRO_GETDEVID] = sizeof(struct pcan_usb_pro_devid), + [PCAN_USBPRO_SETDEVID] = sizeof(struct pcan_usb_pro_devid), [PCAN_USBPRO_SETLED] = sizeof(struct pcan_usb_pro_setled), [PCAN_USBPRO_RXMSG8] = sizeof(struct pcan_usb_pro_rxmsg), [PCAN_USBPRO_RXMSG4] = sizeof(struct pcan_usb_pro_rxmsg) - 4, @@ -149,6 +150,7 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, int id, ...) case PCAN_USBPRO_SETBTR: case PCAN_USBPRO_GETDEVID: + case PCAN_USBPRO_SETDEVID: *pc++ = va_arg(ap, int); pc += 2; *(__le32 *)pc = cpu_to_le32(va_arg(ap, u32)); @@ -419,8 +421,8 @@ static int pcan_usb_pro_set_led(struct peak_usb_device *dev, u8 mode, return pcan_usb_pro_send_cmd(dev, &um); } -static int pcan_usb_pro_get_device_id(struct peak_usb_device *dev, - u32 *device_id) +static int pcan_usb_pro_get_can_channel_id(struct peak_usb_device *dev, + u32 *can_ch_id) { struct pcan_usb_pro_devid *pdn; struct pcan_usb_pro_msg um; @@ -439,11 +441,23 @@ static int pcan_usb_pro_get_device_id(struct peak_usb_device *dev, return err; pdn = (struct pcan_usb_pro_devid *)pc; - *device_id = le32_to_cpu(pdn->dev_num); + *can_ch_id = le32_to_cpu(pdn->dev_num); return err; } +static int pcan_usb_pro_set_can_channel_id(struct peak_usb_device *dev, + u32 can_ch_id) +{ + struct pcan_usb_pro_msg um; + + pcan_msg_init_empty(&um, dev->cmd_buf, PCAN_USB_MAX_CMD_LEN); + pcan_msg_add_rec(&um, PCAN_USBPRO_SETDEVID, dev->ctrl_idx, + can_ch_id); + + return pcan_usb_pro_send_cmd(dev, &um); +} + static int pcan_usb_pro_set_bittiming(struct peak_usb_device *dev, struct can_bittiming *bt) { @@ -1023,6 +1037,9 @@ static int pcan_usb_pro_set_phys_id(struct net_device *netdev, static const struct ethtool_ops pcan_usb_pro_ethtool_ops = { .set_phys_id = pcan_usb_pro_set_phys_id, .get_ts_info = pcan_get_ts_info, + .get_eeprom_len = peak_usb_get_eeprom_len, + .get_eeprom = peak_usb_get_eeprom, + .set_eeprom = peak_usb_set_eeprom, }; /* @@ -1076,7 +1093,8 @@ const struct peak_usb_adapter pcan_usb_pro = { .dev_free = pcan_usb_pro_free, .dev_set_bus = pcan_usb_pro_set_bus, .dev_set_bittiming = pcan_usb_pro_set_bittiming, - .dev_get_device_id = pcan_usb_pro_get_device_id, + .dev_get_can_channel_id = pcan_usb_pro_get_can_channel_id, + .dev_set_can_channel_id = pcan_usb_pro_set_can_channel_id, .dev_decode_buf = pcan_usb_pro_decode_buf, .dev_encode_msg = pcan_usb_pro_encode_msg, .dev_start = pcan_usb_pro_start, diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h index a34e0fc021c9..28e740af905d 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.h @@ -62,6 +62,7 @@ struct __packed pcan_usb_pro_fwinfo { #define PCAN_USBPRO_SETBTR 0x02 #define PCAN_USBPRO_SETBUSACT 0x04 #define PCAN_USBPRO_SETSILENT 0x05 +#define PCAN_USBPRO_SETDEVID 0x06 #define PCAN_USBPRO_SETFILTR 0x0a #define PCAN_USBPRO_SETTS 0x10 #define PCAN_USBPRO_GETDEVID 0x12 diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 616b21c90d05..3a15015bc409 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1302,14 +1302,26 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) if (!priv->ports[port].pvid) mt7530_rmw(priv, MT7530_PVC_P(port), ACC_FRM_MASK, MT7530_VLAN_ACC_TAGGED); - } - /* Set the port as a user port which is to be able to recognize VID - * from incoming packets before fetching entry within the VLAN table. - */ - mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK | PVC_EG_TAG_MASK, - VLAN_ATTR(MT7530_VLAN_USER) | - PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + /* Set the port as a user port which is to be able to recognize + * VID from incoming packets before fetching entry within the + * VLAN table. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), + VLAN_ATTR_MASK | PVC_EG_TAG_MASK, + VLAN_ATTR(MT7530_VLAN_USER) | + PVC_EG_TAG(MT7530_VLAN_EG_DISABLED)); + } else { + /* Also set CPU ports to the "user" VLAN port attribute, to + * allow VLAN classification, but keep the EG_TAG attribute as + * "consistent" (i.o.w. don't change its value) for packets + * received by the switch from the CPU, so that tagged packets + * are forwarded to user ports as tagged, and untagged as + * untagged. + */ + mt7530_rmw(priv, MT7530_PVC_P(port), VLAN_ATTR_MASK, + VLAN_ATTR(MT7530_VLAN_USER)); + } } static void diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 640725524d0c..eff0a7dfcd21 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -12,6 +12,7 @@ config NET_DSA_MSCC_OCELOT_EXT tristate "Ocelot External Ethernet switch support" depends on NET_DSA && SPI depends on NET_VENDOR_MICROSEMI + depends on PTP_1588_CLOCK_OPTIONAL select MDIO_MSCC_MIIM select MFD_OCELOT_CORE select MSCC_OCELOT_SWITCH_LIB diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index e8ad5ea31aff..d3999db7c6a2 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -597,7 +597,9 @@ static int ena_xdp_set(struct net_device *netdev, struct netdev_bpf *bpf) if (rc) return rc; } + xdp_features_set_redirect_target(netdev, false); } else if (old_bpf_prog) { + xdp_features_clear_redirect_target(netdev); rc = ena_destroy_and_free_all_xdp_queues(adapter); if (rc) return rc; @@ -4103,6 +4105,8 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter, /* Set offload features */ ena_set_dev_offloads(feat, netdev); + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + adapter->max_mtu = feat->dev_attr.max_mtu; netdev->max_mtu = adapter->max_mtu; netdev->min_mtu = ENA_MIN_MTU; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 7d88caa4e623..16e7fb2c0dae 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -390,7 +390,8 @@ static DEFINE_MUTEX(xgbe_phy_comm_lock); static enum xgbe_an_mode xgbe_phy_an_mode(struct xgbe_prv_data *pdata); static void xgbe_phy_rrc(struct xgbe_prv_data *pdata); static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata, - unsigned int cmd, unsigned int sub_cmd); + enum xgbe_mb_cmd cmd, + enum xgbe_mb_subcmd sub_cmd); static int xgbe_phy_i2c_xfer(struct xgbe_prv_data *pdata, struct xgbe_i2c_op *i2c_op) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index 77609dc0a08d..0b2a52199914 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -21,6 +21,7 @@ #include <linux/ip.h> #include <linux/udp.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <linux/filter.h> MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 06508eebb585..d6d6d5d37ff3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -384,6 +384,11 @@ void aq_nic_ndev_init(struct aq_nic_s *self) self->ndev->mtu = aq_nic_cfg->mtu - ETH_HLEN; self->ndev->max_mtu = aq_hw_caps->mtu - ETH_FCS_LEN - ETH_HLEN; + self->ndev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG; } void aq_nic_set_tx_ring(struct aq_nic_s *self, unsigned int idx, diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f4ca0c6c0f51..948586bf1b5b 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -213,6 +213,7 @@ config BNXT select NET_DEVLINK select PAGE_POOL select DIMLIB + select AUXILIARY_BUS help This driver supports Broadcom NetXtreme-C/E 10/25/40/50 gigabit Ethernet cards. To compile this driver as a module, choose M here: diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 240a7e8a7652..ab5dfb3a4081 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2414,7 +2414,6 @@ static int bnxt_async_event_process(struct bnxt *bp, } bnxt_queue_sp_work(bp); async_event_process_exit: - bnxt_ulp_async_events(bp, cmpl); return 0; } @@ -5538,7 +5537,7 @@ vnic_mru: #endif if ((bp->flags & BNXT_FLAG_STRIP_VLAN) || def_vlan) req->flags |= cpu_to_le32(VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE); - if (!vnic_id && bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) + if (!vnic_id && bnxt_ulp_registered(bp->edev)) req->flags |= cpu_to_le32(bnxt_get_roce_vnic_mode(bp)); return hwrm_req_send(bp, req); @@ -13181,6 +13180,8 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + bnxt_rdma_aux_device_uninit(bp); + bnxt_ptp_clear(bp); pci_disable_pcie_error_reporting(pdev); unregister_netdev(dev); @@ -13686,6 +13687,9 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netif_set_tso_max_size(dev, GSO_MAX_SIZE); + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG; + #ifdef CONFIG_BNXT_SRIOV init_waitqueue_head(&bp->sriov_cfg_wait); #endif @@ -13776,11 +13780,13 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bnxt_dl_fw_reporters_create(bp); + bnxt_rdma_aux_device_init(bp); + bnxt_print_device_info(bp); pci_save_state(pdev); - return 0; + return 0; init_err_cleanup: bnxt_dl_unregister(bp); init_err_dl: @@ -13824,7 +13830,6 @@ static void bnxt_shutdown(struct pci_dev *pdev) if (netif_running(dev)) dev_close(dev); - bnxt_ulp_shutdown(bp); bnxt_clear_int_mode(bp); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5163ef4a49ea..dcb09fbe4007 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -24,6 +24,7 @@ #include <linux/interrupt.h> #include <linux/rhashtable.h> #include <linux/crash_dump.h> +#include <linux/auxiliary_bus.h> #include <net/devlink.h> #include <net/dst_metadata.h> #include <net/xdp.h> @@ -1631,6 +1632,12 @@ struct bnxt_fw_health { #define BNXT_FW_IF_RETRY 10 #define BNXT_FW_SLOT_RESET_RETRY 4 +struct bnxt_aux_priv { + struct auxiliary_device aux_dev; + struct bnxt_en_dev *edev; + int id; +}; + enum board_idx { BCM57301, BCM57302, @@ -1852,6 +1859,7 @@ struct bnxt { #define BNXT_CHIP_P4_PLUS(bp) \ (BNXT_CHIP_P4(bp) || BNXT_CHIP_P5(bp)) + struct bnxt_aux_priv *aux_priv; struct bnxt_en_dev *edev; struct bnxt_napi **bnapi; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index a4cba7cb2783..3ed3a2b3b3a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -749,7 +749,6 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset) *num_vfs = rc; } - bnxt_ulp_sriov_cfg(bp, *num_vfs); return 0; } @@ -823,10 +822,8 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) goto err_out2; rc = pci_enable_sriov(bp->pdev, *num_vfs); - if (rc) { - bnxt_ulp_sriov_cfg(bp, 0); + if (rc) goto err_out2; - } return 0; @@ -872,8 +869,6 @@ void bnxt_sriov_disable(struct bnxt *bp) rtnl_lock(); bnxt_restore_pf_fw_resources(bp); rtnl_unlock(); - - bnxt_ulp_sriov_cfg(bp, 0); } int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 2e54bf4fc7a7..d4cc9c371e7b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -19,89 +19,26 @@ #include <linux/irq.h> #include <asm/byteorder.h> #include <linux/bitmap.h> +#include <linux/auxiliary_bus.h> #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" #include "bnxt_ulp.h" -static int bnxt_register_dev(struct bnxt_en_dev *edev, unsigned int ulp_id, - struct bnxt_ulp_ops *ulp_ops, void *handle) -{ - struct net_device *dev = edev->net; - struct bnxt *bp = netdev_priv(dev); - struct bnxt_ulp *ulp; - - ASSERT_RTNL(); - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; - if (rcu_access_pointer(ulp->ulp_ops)) { - netdev_err(bp->dev, "ulp id %d already registered\n", ulp_id); - return -EBUSY; - } - if (ulp_id == BNXT_ROCE_ULP) { - unsigned int max_stat_ctxs; - - max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp); - if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS || - bp->cp_nr_rings == max_stat_ctxs) - return -ENOMEM; - } - - atomic_set(&ulp->ref_count, 0); - ulp->handle = handle; - rcu_assign_pointer(ulp->ulp_ops, ulp_ops); - - if (ulp_id == BNXT_ROCE_ULP) { - if (test_bit(BNXT_STATE_OPEN, &bp->state)) - bnxt_hwrm_vnic_cfg(bp, 0); - } - - return 0; -} - -static int bnxt_unregister_dev(struct bnxt_en_dev *edev, unsigned int ulp_id) -{ - struct net_device *dev = edev->net; - struct bnxt *bp = netdev_priv(dev); - struct bnxt_ulp *ulp; - int i = 0; - - ASSERT_RTNL(); - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; - if (!rcu_access_pointer(ulp->ulp_ops)) { - netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id); - return -EINVAL; - } - if (ulp_id == BNXT_ROCE_ULP && ulp->msix_requested) - edev->en_ops->bnxt_free_msix(edev, ulp_id); - - if (ulp->max_async_event_id) - bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true); - - RCU_INIT_POINTER(ulp->ulp_ops, NULL); - synchronize_rcu(); - ulp->max_async_event_id = 0; - ulp->async_events_bmap = NULL; - while (atomic_read(&ulp->ref_count) != 0 && i < 10) { - msleep(100); - i++; - } - return 0; -} +static DEFINE_IDA(bnxt_aux_dev_ids); static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent) { struct bnxt_en_dev *edev = bp->edev; int num_msix, idx, i; - num_msix = edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested; - idx = edev->ulp_tbl[BNXT_ROCE_ULP].msix_base; + if (!edev->ulp_tbl->msix_requested) { + netdev_warn(bp->dev, "Requested MSI-X vectors insufficient\n"); + return; + } + num_msix = edev->ulp_tbl->msix_requested; + idx = edev->ulp_tbl->msix_base; for (i = 0; i < num_msix; i++) { ent[i].vector = bp->irq_tbl[idx + i].vector; ent[i].ring_idx = idx + i; @@ -115,125 +52,95 @@ static void bnxt_fill_msix_vecs(struct bnxt *bp, struct bnxt_msix_entry *ent) } } -static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id, - struct bnxt_msix_entry *ent, int num_msix) +int bnxt_register_dev(struct bnxt_en_dev *edev, + struct bnxt_ulp_ops *ulp_ops, + void *handle) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); - struct bnxt_hw_resc *hw_resc; - int max_idx, max_cp_rings; - int avail_msix, idx; - int total_vecs; - int rc = 0; - - ASSERT_RTNL(); - if (ulp_id != BNXT_ROCE_ULP) - return -EINVAL; - - if (!(bp->flags & BNXT_FLAG_USING_MSIX)) - return -ENODEV; + unsigned int max_stat_ctxs; + struct bnxt_ulp *ulp; - if (edev->ulp_tbl[ulp_id].msix_requested) - return -EAGAIN; + max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp); + if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS || + bp->cp_nr_rings == max_stat_ctxs) + return -ENOMEM; - max_cp_rings = bnxt_get_max_func_cp_rings(bp); - avail_msix = bnxt_get_avail_msix(bp, num_msix); - if (!avail_msix) + ulp = edev->ulp_tbl; + if (!ulp) return -ENOMEM; - if (avail_msix > num_msix) - avail_msix = num_msix; - - if (BNXT_NEW_RM(bp)) { - idx = bp->cp_nr_rings; - } else { - max_idx = min_t(int, bp->total_irqs, max_cp_rings); - idx = max_idx - avail_msix; - } - edev->ulp_tbl[ulp_id].msix_base = idx; - edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - hw_resc = &bp->hw_resc; - total_vecs = idx + avail_msix; - if (bp->total_irqs < total_vecs || - (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) { - if (netif_running(dev)) { - bnxt_close_nic(bp, true, false); - rc = bnxt_open_nic(bp, true, false); - } else { - rc = bnxt_reserve_rings(bp, true); - } - } - if (rc) { - edev->ulp_tbl[ulp_id].msix_requested = 0; - return -EAGAIN; - } - if (BNXT_NEW_RM(bp)) { - int resv_msix; + ulp->handle = handle; + rcu_assign_pointer(ulp->ulp_ops, ulp_ops); + + if (test_bit(BNXT_STATE_OPEN, &bp->state)) + bnxt_hwrm_vnic_cfg(bp, 0); - resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings; - avail_msix = min_t(int, resv_msix, avail_msix); - edev->ulp_tbl[ulp_id].msix_requested = avail_msix; - } - bnxt_fill_msix_vecs(bp, ent); + bnxt_fill_msix_vecs(bp, bp->edev->msix_entries); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; - return avail_msix; + return 0; } +EXPORT_SYMBOL(bnxt_register_dev); -static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, unsigned int ulp_id) +void bnxt_unregister_dev(struct bnxt_en_dev *edev) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); + struct bnxt_ulp *ulp; + int i = 0; - ASSERT_RTNL(); - if (ulp_id != BNXT_ROCE_ULP) - return -EINVAL; + ulp = edev->ulp_tbl; + if (ulp->msix_requested) + edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; - if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) - return 0; + if (ulp->max_async_event_id) + bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, true); - edev->ulp_tbl[ulp_id].msix_requested = 0; - edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; - if (netif_running(dev) && !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED)) { - bnxt_close_nic(bp, true, false); - bnxt_open_nic(bp, true, false); + RCU_INIT_POINTER(ulp->ulp_ops, NULL); + synchronize_rcu(); + ulp->max_async_event_id = 0; + ulp->async_events_bmap = NULL; + while (atomic_read(&ulp->ref_count) != 0 && i < 10) { + msleep(100); + i++; } - return 0; + return; } +EXPORT_SYMBOL(bnxt_unregister_dev); int bnxt_get_ulp_msix_num(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_en_dev *edev = bp->edev; + u32 roce_msix = BNXT_VF(bp) ? + BNXT_MAX_VF_ROCE_MSIX : BNXT_MAX_ROCE_MSIX; - return edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested; - } - return 0; + return ((bp->flags & BNXT_FLAG_ROCE_CAP) ? + min_t(u32, roce_msix, num_online_cpus()) : 0); } int bnxt_get_ulp_msix_base(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { + if (bnxt_ulp_registered(bp->edev)) { struct bnxt_en_dev *edev = bp->edev; - if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested) - return edev->ulp_tbl[BNXT_ROCE_ULP].msix_base; + if (edev->ulp_tbl->msix_requested) + return edev->ulp_tbl->msix_base; } return 0; } int bnxt_get_ulp_stat_ctxs(struct bnxt *bp) { - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { + if (bnxt_ulp_registered(bp->edev)) { struct bnxt_en_dev *edev = bp->edev; - if (edev->ulp_tbl[BNXT_ROCE_ULP].msix_requested) + if (edev->ulp_tbl->msix_requested) return BNXT_MIN_ROCE_STAT_CTXS; } return 0; } -static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, +int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg) { struct net_device *dev = edev->net; @@ -243,7 +150,7 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, u32 resp_len; int rc; - if (ulp_id != BNXT_ROCE_ULP && bp->fw_reset_state) + if (bp->fw_reset_state) return -EBUSY; rc = hwrm_req_init(bp, req, 0 /* don't care */); @@ -267,42 +174,36 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, unsigned int ulp_id, hwrm_req_drop(bp, req); return rc; } - -static void bnxt_ulp_get(struct bnxt_ulp *ulp) -{ - atomic_inc(&ulp->ref_count); -} - -static void bnxt_ulp_put(struct bnxt_ulp *ulp) -{ - atomic_dec(&ulp->ref_count); -} +EXPORT_SYMBOL(bnxt_send_msg); void bnxt_ulp_stop(struct bnxt *bp) { + struct bnxt_aux_priv *aux_priv = bp->aux_priv; struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; if (!edev) return; edev->flags |= BNXT_EN_FLAG_ULP_STOPPED; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; + if (aux_priv) { + struct auxiliary_device *adev; - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_stop) - continue; - ops->ulp_stop(ulp->handle); + adev = &aux_priv->aux_dev; + if (adev->dev.driver) { + struct auxiliary_driver *adrv; + pm_message_t pm = {}; + + adrv = to_auxiliary_drv(adev->dev.driver); + edev->en_state = bp->state; + adrv->suspend(adev, pm); + } } } void bnxt_ulp_start(struct bnxt *bp, int err) { + struct bnxt_aux_priv *aux_priv = bp->aux_priv; struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; if (!edev) return; @@ -312,58 +213,19 @@ void bnxt_ulp_start(struct bnxt *bp, int err) if (err) return; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_start) - continue; - ops->ulp_start(ulp->handle); - } -} - -void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs) -{ - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; + if (aux_priv) { + struct auxiliary_device *adev; - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; + adev = &aux_priv->aux_dev; + if (adev->dev.driver) { + struct auxiliary_driver *adrv; - rcu_read_lock(); - ops = rcu_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_sriov_config) { - rcu_read_unlock(); - continue; + adrv = to_auxiliary_drv(adev->dev.driver); + edev->en_state = bp->state; + adrv->resume(adev); } - bnxt_ulp_get(ulp); - rcu_read_unlock(); - ops->ulp_sriov_config(ulp->handle, num_vfs); - bnxt_ulp_put(ulp); } -} -void bnxt_ulp_shutdown(struct bnxt *bp) -{ - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; - - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rtnl_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_shutdown) - continue; - ops->ulp_shutdown(ulp->handle); - } } void bnxt_ulp_irq_stop(struct bnxt *bp) @@ -374,8 +236,8 @@ void bnxt_ulp_irq_stop(struct bnxt *bp) if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return; - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[BNXT_ROCE_ULP]; + if (bnxt_ulp_registered(bp->edev)) { + struct bnxt_ulp *ulp = edev->ulp_tbl; if (!ulp->msix_requested) return; @@ -395,8 +257,8 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) if (!edev || !(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return; - if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP)) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[BNXT_ROCE_ULP]; + if (bnxt_ulp_registered(bp->edev)) { + struct bnxt_ulp *ulp = edev->ulp_tbl; struct bnxt_msix_entry *ent = NULL; if (!ulp->msix_requested) @@ -418,46 +280,15 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err) } } -void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl) -{ - u16 event_id = le16_to_cpu(cmpl->event_id); - struct bnxt_en_dev *edev = bp->edev; - struct bnxt_ulp_ops *ops; - int i; - - if (!edev) - return; - - rcu_read_lock(); - for (i = 0; i < BNXT_MAX_ULP; i++) { - struct bnxt_ulp *ulp = &edev->ulp_tbl[i]; - - ops = rcu_dereference(ulp->ulp_ops); - if (!ops || !ops->ulp_async_notifier) - continue; - if (!ulp->async_events_bmap || - event_id > ulp->max_async_event_id) - continue; - - /* Read max_async_event_id first before testing the bitmap. */ - smp_rmb(); - if (test_bit(event_id, ulp->async_events_bmap)) - ops->ulp_async_notifier(ulp->handle, cmpl); - } - rcu_read_unlock(); -} - -static int bnxt_register_async_events(struct bnxt_en_dev *edev, unsigned int ulp_id, - unsigned long *events_bmap, u16 max_id) +int bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, + u16 max_id) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); struct bnxt_ulp *ulp; - if (ulp_id >= BNXT_MAX_ULP) - return -EINVAL; - - ulp = &edev->ulp_tbl[ulp_id]; + ulp = edev->ulp_tbl; ulp->async_events_bmap = events_bmap; /* Make sure bnxt_ulp_async_events() sees this order */ smp_wmb(); @@ -465,38 +296,121 @@ static int bnxt_register_async_events(struct bnxt_en_dev *edev, unsigned int ulp bnxt_hwrm_func_drv_rgtr(bp, events_bmap, max_id + 1, true); return 0; } +EXPORT_SYMBOL(bnxt_register_async_events); -static const struct bnxt_en_ops bnxt_en_ops_tbl = { - .bnxt_register_device = bnxt_register_dev, - .bnxt_unregister_device = bnxt_unregister_dev, - .bnxt_request_msix = bnxt_req_msix_vecs, - .bnxt_free_msix = bnxt_free_msix_vecs, - .bnxt_send_fw_msg = bnxt_send_msg, - .bnxt_register_fw_async_events = bnxt_register_async_events, -}; +void bnxt_rdma_aux_device_uninit(struct bnxt *bp) +{ + struct bnxt_aux_priv *aux_priv; + struct auxiliary_device *adev; + + /* Skip if no auxiliary device init was done. */ + if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + return; + + aux_priv = bp->aux_priv; + adev = &aux_priv->aux_dev; + auxiliary_device_delete(adev); + auxiliary_device_uninit(adev); +} -struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev) +static void bnxt_aux_dev_release(struct device *dev) { - struct bnxt *bp = netdev_priv(dev); - struct bnxt_en_dev *edev; + struct bnxt_aux_priv *aux_priv = + container_of(dev, struct bnxt_aux_priv, aux_dev.dev); + + ida_free(&bnxt_aux_dev_ids, aux_priv->id); + kfree(aux_priv->edev->ulp_tbl); + kfree(aux_priv->edev); + kfree(aux_priv); +} + +static void bnxt_set_edev_info(struct bnxt_en_dev *edev, struct bnxt *bp) +{ + edev->net = bp->dev; + edev->pdev = bp->pdev; + edev->l2_db_size = bp->db_size; + edev->l2_db_size_nc = bp->db_size; - edev = bp->edev; - if (!edev) { - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return ERR_PTR(-ENOMEM); - edev->en_ops = &bnxt_en_ops_tbl; - edev->net = dev; - edev->pdev = bp->pdev; - edev->l2_db_size = bp->db_size; - edev->l2_db_size_nc = bp->db_size; - bp->edev = edev; - } - edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP; if (bp->flags & BNXT_FLAG_ROCEV1_CAP) edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP; if (bp->flags & BNXT_FLAG_ROCEV2_CAP) edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP; - return bp->edev; + if (bp->flags & BNXT_FLAG_VF) + edev->flags |= BNXT_EN_FLAG_VF; + + edev->chip_num = bp->chip_num; + edev->hw_ring_stats_size = bp->hw_ring_stats_size; + edev->pf_port_id = bp->pf.port_id; + edev->en_state = bp->state; + + edev->ulp_tbl->msix_requested = bnxt_get_ulp_msix_num(bp); +} + +void bnxt_rdma_aux_device_init(struct bnxt *bp) +{ + struct auxiliary_device *aux_dev; + struct bnxt_aux_priv *aux_priv; + struct bnxt_en_dev *edev; + struct bnxt_ulp *ulp; + int rc; + + if (!(bp->flags & BNXT_FLAG_ROCE_CAP)) + return; + + bp->aux_priv = kzalloc(sizeof(*bp->aux_priv), GFP_KERNEL); + if (!bp->aux_priv) + goto exit; + + bp->aux_priv->id = ida_alloc(&bnxt_aux_dev_ids, GFP_KERNEL); + if (bp->aux_priv->id < 0) { + netdev_warn(bp->dev, + "ida alloc failed for ROCE auxiliary device\n"); + kfree(bp->aux_priv); + goto exit; + } + + aux_priv = bp->aux_priv; + aux_dev = &aux_priv->aux_dev; + aux_dev->id = aux_priv->id; + aux_dev->name = "rdma"; + aux_dev->dev.parent = &bp->pdev->dev; + aux_dev->dev.release = bnxt_aux_dev_release; + + rc = auxiliary_device_init(aux_dev); + if (rc) { + ida_free(&bnxt_aux_dev_ids, bp->aux_priv->id); + kfree(bp->aux_priv); + goto exit; + } + + /* From this point, all cleanup will happen via the .release callback & + * any error unwinding will need to include a call to + * auxiliary_device_uninit. + */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + goto aux_dev_uninit; + + ulp = kzalloc(sizeof(*ulp), GFP_KERNEL); + if (!ulp) + goto aux_dev_uninit; + + edev->ulp_tbl = ulp; + aux_priv->edev = edev; + bp->edev = edev; + bnxt_set_edev_info(edev, bp); + + rc = auxiliary_device_add(aux_dev); + if (rc) { + netdev_warn(bp->dev, + "Failed to add auxiliary device for ROCE\n"); + goto aux_dev_uninit; + } + + return; + +aux_dev_uninit: + auxiliary_device_uninit(aux_dev); +exit: + bp->flags &= ~BNXT_FLAG_ROCE_CAP; } -EXPORT_SYMBOL(bnxt_ulp_probe); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index 42b50abc3e91..80cbc4b6130a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -15,6 +15,8 @@ #define BNXT_MIN_ROCE_CP_RINGS 2 #define BNXT_MIN_ROCE_STAT_CTXS 1 +#define BNXT_MAX_ROCE_MSIX 9 +#define BNXT_MAX_VF_ROCE_MSIX 2 struct hwrm_async_event_cmpl; struct bnxt; @@ -26,12 +28,6 @@ struct bnxt_msix_entry { }; struct bnxt_ulp_ops { - /* async_notifier() cannot sleep (in BH context) */ - void (*ulp_async_notifier)(void *, struct hwrm_async_event_cmpl *); - void (*ulp_stop)(void *); - void (*ulp_start)(void *); - void (*ulp_sriov_config)(void *, int); - void (*ulp_shutdown)(void *); void (*ulp_irq_stop)(void *); void (*ulp_irq_restart)(void *, struct bnxt_msix_entry *); }; @@ -57,6 +53,7 @@ struct bnxt_ulp { struct bnxt_en_dev { struct net_device *net; struct pci_dev *pdev; + struct bnxt_msix_entry msix_entries[BNXT_MAX_ROCE_MSIX]; u32 flags; #define BNXT_EN_FLAG_ROCEV1_CAP 0x1 #define BNXT_EN_FLAG_ROCEV2_CAP 0x2 @@ -64,8 +61,10 @@ struct bnxt_en_dev { BNXT_EN_FLAG_ROCEV2_CAP) #define BNXT_EN_FLAG_MSIX_REQUESTED 0x4 #define BNXT_EN_FLAG_ULP_STOPPED 0x8 - const struct bnxt_en_ops *en_ops; - struct bnxt_ulp ulp_tbl[BNXT_MAX_ULP]; + #define BNXT_EN_FLAG_VF 0x10 +#define BNXT_EN_VF(edev) ((edev)->flags & BNXT_EN_FLAG_VF) + + struct bnxt_ulp *ulp_tbl; int l2_db_size; /* Doorbell BAR size in * bytes mapped by L2 * driver. @@ -74,24 +73,19 @@ struct bnxt_en_dev { * bytes mapped as non- * cacheable. */ + u16 chip_num; + u16 hw_ring_stats_size; + u16 pf_port_id; + unsigned long en_state; /* Could be checked in + * RoCE driver suspend + * mode only. Will be + * updated in resume. + */ }; -struct bnxt_en_ops { - int (*bnxt_register_device)(struct bnxt_en_dev *, unsigned int, - struct bnxt_ulp_ops *, void *); - int (*bnxt_unregister_device)(struct bnxt_en_dev *, unsigned int); - int (*bnxt_request_msix)(struct bnxt_en_dev *, unsigned int, - struct bnxt_msix_entry *, int); - int (*bnxt_free_msix)(struct bnxt_en_dev *, unsigned int); - int (*bnxt_send_fw_msg)(struct bnxt_en_dev *, unsigned int, - struct bnxt_fw_msg *); - int (*bnxt_register_fw_async_events)(struct bnxt_en_dev *, unsigned int, - unsigned long *, u16); -}; - -static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id) +static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev) { - if (edev && rcu_access_pointer(edev->ulp_tbl[ulp_id].ulp_ops)) + if (edev && edev->ulp_tbl) return true; return false; } @@ -102,10 +96,15 @@ int bnxt_get_ulp_stat_ctxs(struct bnxt *bp); void bnxt_ulp_stop(struct bnxt *bp); void bnxt_ulp_start(struct bnxt *bp, int err); void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs); -void bnxt_ulp_shutdown(struct bnxt *bp); void bnxt_ulp_irq_stop(struct bnxt *bp); void bnxt_ulp_irq_restart(struct bnxt *bp, int err); void bnxt_ulp_async_events(struct bnxt *bp, struct hwrm_async_event_cmpl *cmpl); -struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev); - +void bnxt_rdma_aux_device_uninit(struct bnxt *bp); +void bnxt_rdma_aux_device_init(struct bnxt *bp); +int bnxt_register_dev(struct bnxt_en_dev *edev, struct bnxt_ulp_ops *ulp_ops, + void *handle); +void bnxt_unregister_dev(struct bnxt_en_dev *edev); +int bnxt_send_msg(struct bnxt_en_dev *edev, struct bnxt_fw_msg *fw_msg); +int bnxt_register_async_events(struct bnxt_en_dev *edev, + unsigned long *events_bmap, u16 max_id); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 36d5202c0aee..5843c93b1711 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -422,9 +422,11 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog) if (prog) { bnxt_set_rx_skb_mode(bp, true); + xdp_features_set_redirect_target(dev, true); } else { int rx, tx; + xdp_features_clear_redirect_target(dev); bnxt_set_rx_skb_mode(bp, false); bnxt_get_max_rings(bp, &rx, &tx, true); if (rx > 1) { diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 41964fd02452..6e141a8bbf43 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4684,25 +4684,26 @@ static int init_reset_optional(struct platform_device *pdev) if (ret) return dev_err_probe(&pdev->dev, ret, "failed to init SGMII PHY\n"); - } - ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); - if (!ret) { - u32 pm_info[2]; + ret = zynqmp_pm_is_function_supported(PM_IOCTL, IOCTL_SET_GEM_CONFIG); + if (!ret) { + u32 pm_info[2]; + + ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", + pm_info, ARRAY_SIZE(pm_info)); + if (ret) { + dev_err(&pdev->dev, "Failed to read power management information\n"); + goto err_out_phy_exit; + } + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); + if (ret) + goto err_out_phy_exit; - ret = of_property_read_u32_array(pdev->dev.of_node, "power-domains", - pm_info, ARRAY_SIZE(pm_info)); - if (ret) { - dev_err(&pdev->dev, "Failed to read power management information\n"); - goto err_out_phy_exit; + ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); + if (ret) + goto err_out_phy_exit; } - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_FIXED, 0); - if (ret) - goto err_out_phy_exit; - ret = zynqmp_pm_set_gem_config(pm_info[1], GEM_CONFIG_SGMII_MODE, 1); - if (ret) - goto err_out_phy_exit; } /* Fully reset controller at hardware level if mapped in device tree */ diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index f2f95493ec89..8b25313c7f6b 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -2218,6 +2218,8 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &nicvf_netdev_ops; netdev->watchdog_timeo = NICVF_TX_TIMEOUT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC; + /* MTU range: 64 - 9200 */ netdev->min_mtu = NIC_HW_MIN_FRS; netdev->max_mtu = NIC_HW_MAX_FRS; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h index be96f1dc0372..d4a862a9fd7d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_mqprio.h @@ -4,7 +4,7 @@ #ifndef __CXGB4_TC_MQPRIO_H__ #define __CXGB4_TC_MQPRIO_H__ -#include <net/pkt_cls.h> +#include <net/pkt_sched.h> #define CXGB4_EOSW_TXQ_DEFAULT_DESC_NUM 128 diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index c3cf427a9409..6982aaa928b5 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1926,6 +1926,10 @@ static int tsnep_probe(struct platform_device *pdev) netdev->features = NETIF_F_SG; netdev->hw_features = netdev->features | NETIF_F_LOOPBACK; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG; + /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/engleder/tsnep_tc.c b/drivers/net/ethernet/engleder/tsnep_tc.c index c4c6e1357317..d083e6684f12 100644 --- a/drivers/net/ethernet/engleder/tsnep_tc.c +++ b/drivers/net/ethernet/engleder/tsnep_tc.c @@ -403,12 +403,33 @@ static int tsnep_taprio(struct tsnep_adapter *adapter, return 0; } +static int tsnep_tc_query_caps(struct tsnep_adapter *adapter, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!adapter->gate_control) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + int tsnep_tc_setup(struct net_device *netdev, enum tc_setup_type type, void *type_data) { struct tsnep_adapter *adapter = netdev_priv(netdev); switch (type) { + case TC_QUERY_CAPS: + return tsnep_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_TAPRIO: return tsnep_taprio(adapter, type_data); default: diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 027fff9f7db0..9318a2554056 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -244,6 +244,10 @@ static int dpaa_netdev_init(struct net_device *net_dev, net_dev->features |= net_dev->hw_features; net_dev->vlan_features = net_dev->features; + net_dev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + if (is_valid_ether_addr(mac_addr)) { memcpy(net_dev->perm_addr, mac_addr, net_dev->addr_len); eth_hw_addr_set(net_dev, mac_addr); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 2e79d18fc3c7..746ccfde7255 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4596,6 +4596,10 @@ static int dpaa2_eth_netdev_init(struct net_device *net_dev) NETIF_F_LLTX | NETIF_F_HW_TC | NETIF_F_TSO; net_dev->gso_max_segs = DPAA2_ETH_ENQUEUE_MAX_FDS; net_dev->hw_features = net_dev->features; + net_dev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY | + NETDEV_XDP_ACT_NDO_XMIT; if (priv->dpni_attrs.vlan_filter_entries) net_dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 159ae740ba3c..2fc712b24d12 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -28,11 +28,9 @@ EXPORT_SYMBOL_GPL(enetc_port_mac_wr); static int enetc_num_stack_tx_queues(struct enetc_ndev_priv *priv) { int num_tx_rings = priv->num_tx_rings; - int i; - for (i = 0; i < priv->num_rx_rings; i++) - if (priv->rx_ring[i]->xdp.prog) - return num_tx_rings - num_possible_cpus(); + if (priv->xdp_prog) + return num_tx_rings - num_possible_cpus(); return num_tx_rings; } @@ -2456,7 +2454,6 @@ int enetc_open(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_bdr_resource *tx_res, *rx_res; - int num_stack_tx_queues; bool extended; int err; @@ -2482,16 +2479,6 @@ int enetc_open(struct net_device *ndev) goto err_alloc_rx; } - num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - - err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(ndev, priv->num_rx_rings); - if (err) - goto err_set_queues; - enetc_tx_onestep_tstamp_init(priv); enetc_assign_tx_resources(priv, tx_res); enetc_assign_rx_resources(priv, rx_res); @@ -2500,8 +2487,6 @@ int enetc_open(struct net_device *ndev) return 0; -err_set_queues: - enetc_free_rx_resources(rx_res, priv->num_rx_rings); err_alloc_rx: enetc_free_tx_resources(tx_res, priv->num_tx_rings); err_alloc_tx: @@ -2576,8 +2561,11 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, * without reconfiguration. */ if (!netif_running(priv->ndev)) { - if (cb) - cb(priv, ctx); + if (cb) { + err = cb(priv, ctx); + if (err) + return err; + } return 0; } @@ -2598,8 +2586,11 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, enetc_free_rxtx_rings(priv); /* Interface is down, run optional callback now */ - if (cb) - cb(priv, ctx); + if (cb) { + err = cb(priv, ctx); + if (err) + goto out_restart; + } enetc_assign_tx_resources(priv, tx_res); enetc_assign_rx_resources(priv, rx_res); @@ -2608,76 +2599,123 @@ static int enetc_reconfigure(struct enetc_ndev_priv *priv, bool extended, return 0; +out_restart: + enetc_setup_bdrs(priv, extended); + enetc_start(priv->ndev); + enetc_free_rx_resources(rx_res, priv->num_rx_rings); out_free_tx_res: enetc_free_tx_resources(tx_res, priv->num_tx_rings); out: return err; } -int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +static void enetc_debug_tx_ring_prios(struct enetc_ndev_priv *priv) +{ + int i; + + for (i = 0; i < priv->num_tx_rings; i++) + netdev_dbg(priv->ndev, "TX ring %d prio %d\n", i, + priv->tx_ring[i]->prio); +} + +static void enetc_reset_tc_mqprio(struct net_device *ndev) { struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct tc_mqprio_qopt *mqprio = type_data; struct enetc_hw *hw = &priv->si->hw; struct enetc_bdr *tx_ring; int num_stack_tx_queues; - u8 num_tc; int i; num_stack_tx_queues = enetc_num_stack_tx_queues(priv); - mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; - num_tc = mqprio->num_tc; - if (!num_tc) { - netdev_reset_tc(ndev); - netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + netdev_reset_tc(ndev); + netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + priv->min_num_stack_tx_queues = num_possible_cpus(); - /* Reset all ring priorities to 0 */ - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = 0; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + /* Reset all ring priorities to 0 */ + for (i = 0; i < priv->num_tx_rings; i++) { + tx_ring = priv->tx_ring[i]; + tx_ring->prio = 0; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } + + enetc_debug_tx_ring_prios(priv); +} + +int enetc_setup_tc_mqprio(struct net_device *ndev, void *type_data) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct tc_mqprio_qopt *mqprio = type_data; + struct enetc_hw *hw = &priv->si->hw; + int num_stack_tx_queues = 0; + u8 num_tc = mqprio->num_tc; + struct enetc_bdr *tx_ring; + int offset, count; + int err, tc, q; + if (!num_tc) { + enetc_reset_tc_mqprio(ndev); return 0; } - /* Check if we have enough BD rings available to accommodate all TCs */ - if (num_tc > num_stack_tx_queues) { - netdev_err(ndev, "Max %d traffic classes supported\n", - priv->num_tx_rings); - return -EINVAL; - } + err = netdev_set_num_tc(ndev, num_tc); + if (err) + return err; - /* For the moment, we use only one BD ring per TC. - * - * Configure num_tc BD rings with increasing priorities. - */ - for (i = 0; i < num_tc; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = i; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + for (tc = 0; tc < num_tc; tc++) { + offset = mqprio->offset[tc]; + count = mqprio->count[tc]; + num_stack_tx_queues += count; + + err = netdev_set_tc_queue(ndev, tc, count, offset); + if (err) + goto err_reset_tc; + + for (q = offset; q < offset + count; q++) { + tx_ring = priv->tx_ring[q]; + /* The prio_tc_map is skb_tx_hash()'s way of selecting + * between TX queues based on skb->priority. As such, + * there's nothing to offload based on it. + * Make the mqprio "traffic class" be the priority of + * this ring group, and leave the Tx IPV to traffic + * class mapping as its default mapping value of 1:1. + */ + tx_ring->prio = tc; + enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); + } } - /* Reset the number of netdev queues based on the TC count */ - netif_set_real_num_tx_queues(ndev, num_tc); + err = netif_set_real_num_tx_queues(ndev, num_stack_tx_queues); + if (err) + goto err_reset_tc; - netdev_set_num_tc(ndev, num_tc); + priv->min_num_stack_tx_queues = num_stack_tx_queues; - /* Each TC is associated with one netdev queue */ - for (i = 0; i < num_tc; i++) - netdev_set_tc_queue(ndev, i, 1, i); + enetc_debug_tx_ring_prios(priv); return 0; + +err_reset_tc: + enetc_reset_tc_mqprio(ndev); + return err; } EXPORT_SYMBOL_GPL(enetc_setup_tc_mqprio); static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) { struct bpf_prog *old_prog, *prog = ctx; - int i; + int num_stack_tx_queues; + int err, i; old_prog = xchg(&priv->xdp_prog, prog); + + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) { + xchg(&priv->xdp_prog, old_prog); + return err; + } + if (old_prog) bpf_prog_put(old_prog); @@ -2698,9 +2736,20 @@ static int enetc_reconfigure_xdp_cb(struct enetc_ndev_priv *priv, void *ctx) static int enetc_setup_xdp_prog(struct net_device *ndev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { + int num_xdp_tx_queues = prog ? num_possible_cpus() : 0; struct enetc_ndev_priv *priv = netdev_priv(ndev); bool extended; + if (priv->min_num_stack_tx_queues + num_xdp_tx_queues > + priv->num_tx_rings) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Reserving %d XDP TXQs does not leave a minimum of %d TXQs for network stack (total %d available)", + num_xdp_tx_queues, + priv->min_num_stack_tx_queues, + priv->num_tx_rings); + return -EBUSY; + } + extended = !!(priv->active_offloads & ENETC_F_RX_TSTAMP); /* The buffer layout is changing, so we need to drain the old @@ -2898,6 +2947,7 @@ EXPORT_SYMBOL_GPL(enetc_ioctl); int enetc_alloc_msix(struct enetc_ndev_priv *priv) { struct pci_dev *pdev = priv->si->pdev; + int num_stack_tx_queues; int first_xdp_tx_ring; int i, n, err, nvec; int v_tx_rings; @@ -2974,6 +3024,17 @@ int enetc_alloc_msix(struct enetc_ndev_priv *priv) } } + num_stack_tx_queues = enetc_num_stack_tx_queues(priv); + + err = netif_set_real_num_tx_queues(priv->ndev, num_stack_tx_queues); + if (err) + goto fail; + + err = netif_set_real_num_rx_queues(priv->ndev, priv->num_rx_rings); + if (err) + goto fail; + + priv->min_num_stack_tx_queues = num_possible_cpus(); first_xdp_tx_ring = priv->num_tx_rings - num_possible_cpus(); priv->xdp_tx_ring = &priv->tx_ring[first_xdp_tx_ring]; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index 1fe8dfd6b6d4..8010f31cd10d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -314,7 +314,6 @@ struct psfp_cap { }; #define ENETC_F_TX_TSTAMP_MASK 0xff -/* TODO: more hardware offloads */ enum enetc_active_offloads { /* 8 bits reserved for TX timestamp types (hwtstamp_tx_types) */ ENETC_F_TX_TSTAMP = BIT(0), @@ -323,6 +322,7 @@ enum enetc_active_offloads { ENETC_F_RX_TSTAMP = BIT(8), ENETC_F_QBV = BIT(9), ENETC_F_QCI = BIT(10), + ENETC_F_QBU = BIT(11), }; enum enetc_flags_bit { @@ -369,6 +369,9 @@ struct enetc_ndev_priv { struct psfp_cap psfp_cap; + /* Minimum number of TX queues required by the network stack */ + unsigned int min_num_stack_tx_queues; + struct phylink *phylink; int ic_mode; u32 tx_ictt; @@ -379,6 +382,11 @@ struct enetc_ndev_priv { struct work_struct tx_onestep_tstamp; struct sk_buff_head tx_skbs; + + /* Serialize access to MAC Merge state between ethtool requests + * and link state updates + */ + struct mutex mm_lock; }; /* Messaging */ @@ -424,6 +432,7 @@ int enetc_xdp_xmit(struct net_device *ndev, int num_frames, /* ethtool */ void enetc_set_ethtool_ops(struct net_device *ndev); +void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link); /* control buffer descriptor ring (CBDR) */ int enetc_setup_cbdr(struct device *dev, struct enetc_hw *hw, int bd_count, diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 05e2bad609c6..bca68edfbe9c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2017-2019 NXP */ +#include <linux/ethtool_netlink.h> #include <linux/net_tstamp.h> #include <linux/module.h> #include "enetc.h" @@ -299,14 +300,32 @@ static void enetc_get_ethtool_stats(struct net_device *ndev, data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg); } +static void enetc_pause_stats(struct enetc_hw *hw, int mac, + struct ethtool_pause_stats *pause_stats) +{ + pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(mac)); + pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(mac)); +} + static void enetc_get_pause_stats(struct net_device *ndev, struct ethtool_pause_stats *pause_stats) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - pause_stats->tx_pause_frames = enetc_port_rd(hw, ENETC_PM_TXPF(0)); - pause_stats->rx_pause_frames = enetc_port_rd(hw, ENETC_PM_RXPF(0)); + switch (pause_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_pause_stats(hw, 0, pause_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_pause_stats(hw, 1, pause_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_pause_stats(ndev, pause_stats); + break; + } } static void enetc_mac_stats(struct enetc_hw *hw, int mac, @@ -383,8 +402,20 @@ static void enetc_get_eth_mac_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_mac_stats(hw, 0, mac_stats); + switch (mac_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_mac_stats(hw, 0, mac_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mac_stats(hw, 1, mac_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_mac_stats(ndev, mac_stats); + break; + } } static void enetc_get_eth_ctrl_stats(struct net_device *ndev, @@ -392,8 +423,20 @@ static void enetc_get_eth_ctrl_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_ctrl_stats(hw, 0, ctrl_stats); + switch (ctrl_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_ctrl_stats(hw, 0, ctrl_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_ctrl_stats(hw, 1, ctrl_stats); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_ctrl_stats(ndev, ctrl_stats); + break; + } } static void enetc_get_rmon_stats(struct net_device *ndev, @@ -402,8 +445,20 @@ static void enetc_get_rmon_stats(struct net_device *ndev, { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; - enetc_rmon_stats(hw, 0, rmon_stats, ranges); + switch (rmon_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_rmon_stats(hw, 0, rmon_stats, ranges); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + if (si->hw_features & ENETC_SI_F_QBU) + enetc_rmon_stats(hw, 1, rmon_stats, ranges); + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_rmon_stats(ndev, rmon_stats); + break; + } } #define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \ @@ -863,6 +918,166 @@ static int enetc_set_link_ksettings(struct net_device *dev, return phylink_ethtool_ksettings_set(priv->phylink, cmd); } +static void enetc_get_mm_stats(struct net_device *ndev, + struct ethtool_mm_stats *s) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return; + + s->MACMergeFrameAssErrorCount = enetc_port_rd(hw, ENETC_MMFAECR); + s->MACMergeFrameSmdErrorCount = enetc_port_rd(hw, ENETC_MMFSECR); + s->MACMergeFrameAssOkCount = enetc_port_rd(hw, ENETC_MMFAOCR); + s->MACMergeFragCountRx = enetc_port_rd(hw, ENETC_MMFCRXR); + s->MACMergeFragCountTx = enetc_port_rd(hw, ENETC_MMFCTXR); + s->MACMergeHoldCount = enetc_port_rd(hw, ENETC_MMHCR); +} + +static int enetc_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_si *si = priv->si; + struct enetc_hw *hw = &si->hw; + u32 lafs, rafs, val; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return -EOPNOTSUPP; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_PFPMR); + state->pmac_enabled = !!(val & ENETC_PFPMR_PMACE); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + switch (ENETC_MMCSR_GET_VSTS(val)) { + case 0: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_DISABLED; + break; + case 2: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_VERIFYING; + break; + case 3: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_SUCCEEDED; + break; + case 4: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_FAILED; + break; + case 5: + default: + state->verify_status = ETHTOOL_MM_VERIFY_STATUS_UNKNOWN; + break; + } + + rafs = ENETC_MMCSR_GET_RAFS(val); + state->tx_min_frag_size = ethtool_mm_frag_size_add_to_min(rafs); + lafs = ENETC_MMCSR_GET_LAFS(val); + state->rx_min_frag_size = ethtool_mm_frag_size_add_to_min(lafs); + state->tx_enabled = !!(val & ENETC_MMCSR_LPE); /* mirror of MMCSR_ME */ + state->tx_active = !!(val & ENETC_MMCSR_LPA); + state->verify_enabled = !(val & ENETC_MMCSR_VDIS); + state->verify_time = ENETC_MMCSR_GET_VT(val); + /* A verifyTime of 128 ms would exceed the 7 bit width + * of the ENETC_MMCSR_VT field + */ + state->max_verify_time = 127; + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + struct enetc_hw *hw = &priv->si->hw; + struct enetc_si *si = priv->si; + u32 val, add_frag_size; + int err; + + if (!(si->hw_features & ENETC_SI_F_QBU)) + return -EOPNOTSUPP; + + err = ethtool_mm_frag_size_min_to_add(cfg->tx_min_frag_size, + &add_frag_size, extack); + if (err) + return err; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_PFPMR); + if (cfg->pmac_enabled) + val |= ENETC_PFPMR_PMACE; + else + val &= ~ENETC_PFPMR_PMACE; + enetc_port_wr(hw, ENETC_PFPMR, val); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + if (cfg->verify_enabled) + val &= ~ENETC_MMCSR_VDIS; + else + val |= ENETC_MMCSR_VDIS; + + if (cfg->tx_enabled) + priv->active_offloads |= ENETC_F_QBU; + else + priv->active_offloads &= ~ENETC_F_QBU; + + /* If link is up, enable MAC Merge right away */ + if (!!(priv->active_offloads & ENETC_F_QBU) && + !(val & ENETC_MMCSR_LINK_FAIL)) + val |= ENETC_MMCSR_ME; + + val &= ~ENETC_MMCSR_VT_MASK; + val |= ENETC_MMCSR_VT(cfg->verify_time); + + val &= ~ENETC_MMCSR_RAFS_MASK; + val |= ENETC_MMCSR_RAFS(add_frag_size); + + enetc_port_wr(hw, ENETC_MMCSR, val); + + mutex_unlock(&priv->mm_lock); + + return 0; +} + +/* When the link is lost, the verification state machine goes to the FAILED + * state and doesn't restart on its own after a new link up event. + * According to 802.3 Figure 99-8 - Verify state diagram, the LINK_FAIL bit + * should have been sufficient to re-trigger verification, but for ENETC it + * doesn't. As a workaround, we need to toggle the Merge Enable bit to + * re-trigger verification when link comes up. + */ +void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link) +{ + struct enetc_hw *hw = &priv->si->hw; + u32 val; + + mutex_lock(&priv->mm_lock); + + val = enetc_port_rd(hw, ENETC_MMCSR); + + if (link) { + val &= ~ENETC_MMCSR_LINK_FAIL; + if (priv->active_offloads & ENETC_F_QBU) + val |= ENETC_MMCSR_ME; + } else { + val |= ENETC_MMCSR_LINK_FAIL; + if (priv->active_offloads & ENETC_F_QBU) + val &= ~ENETC_MMCSR_ME; + } + + enetc_port_wr(hw, ENETC_MMCSR, val); + + mutex_unlock(&priv->mm_lock); +} +EXPORT_SYMBOL_GPL(enetc_mm_link_state_update); + static const struct ethtool_ops enetc_pf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | @@ -893,6 +1108,9 @@ static const struct ethtool_ops enetc_pf_ethtool_ops = { .set_wol = enetc_set_wol, .get_pauseparam = enetc_get_pauseparam, .set_pauseparam = enetc_set_pauseparam, + .get_mm = enetc_get_mm, + .set_mm = enetc_set_mm, + .get_mm_stats = enetc_get_mm_stats, }; static const struct ethtool_ops enetc_vf_ethtool_ops = { diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 041df7d0ae81..de2e0ee8cdcb 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -222,7 +222,30 @@ enum enetc_bdr_type {TX, RX}; #define ENETC_PSIVHFR0(n) (0x1e00 + (n) * 8) /* n = SI index */ #define ENETC_PSIVHFR1(n) (0x1e04 + (n) * 8) /* n = SI index */ #define ENETC_MMCSR 0x1f00 -#define ENETC_MMCSR_ME BIT(16) +#define ENETC_MMCSR_LINK_FAIL BIT(31) +#define ENETC_MMCSR_VT_MASK GENMASK(29, 23) /* Verify Time */ +#define ENETC_MMCSR_VT(x) (((x) << 23) & ENETC_MMCSR_VT_MASK) +#define ENETC_MMCSR_GET_VT(x) (((x) & ENETC_MMCSR_VT_MASK) >> 23) +#define ENETC_MMCSR_TXSTS_MASK GENMASK(22, 21) /* Merge Status */ +#define ENETC_MMCSR_GET_TXSTS(x) (((x) & ENETC_MMCSR_TXSTS_MASK) >> 21) +#define ENETC_MMCSR_VSTS_MASK GENMASK(20, 18) /* Verify Status */ +#define ENETC_MMCSR_GET_VSTS(x) (((x) & ENETC_MMCSR_VSTS_MASK) >> 18) +#define ENETC_MMCSR_VDIS BIT(17) /* Verify Disabled */ +#define ENETC_MMCSR_ME BIT(16) /* Merge Enabled */ +#define ENETC_MMCSR_RAFS_MASK GENMASK(9, 8) /* Remote Additional Fragment Size */ +#define ENETC_MMCSR_RAFS(x) (((x) << 8) & ENETC_MMCSR_RAFS_MASK) +#define ENETC_MMCSR_GET_RAFS(x) (((x) & ENETC_MMCSR_RAFS_MASK) >> 8) +#define ENETC_MMCSR_LAFS_MASK GENMASK(4, 3) /* Local Additional Fragment Size */ +#define ENETC_MMCSR_GET_LAFS(x) (((x) & ENETC_MMCSR_LAFS_MASK) >> 3) +#define ENETC_MMCSR_LPA BIT(2) /* Local Preemption Active */ +#define ENETC_MMCSR_LPE BIT(1) /* Local Preemption Enabled */ +#define ENETC_MMCSR_LPS BIT(0) /* Local Preemption Supported */ +#define ENETC_MMFAECR 0x1f08 +#define ENETC_MMFSECR 0x1f0c +#define ENETC_MMFAOCR 0x1f10 +#define ENETC_MMFCRXR 0x1f14 +#define ENETC_MMFCTXR 0x1f18 +#define ENETC_MMHCR 0x1f1c #define ENETC_PTCMSDUR(n) (0x2020 + (n) * 4) /* n = TC index [0..7] */ #define ENETC_PMAC_OFFSET 0x1000 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 7facc7d5261e..7cd22d370caa 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -807,6 +807,9 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features |= NETIF_F_RXHASH; ndev->priv_flags |= IFF_UNICAST_FLT; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG; if (si->hw_features & ENETC_SI_F_PSFP && !enetc_psfp_enable(priv)) { priv->active_offloads |= ENETC_F_QCI; @@ -1083,6 +1086,9 @@ static void enetc_pl_mac_link_up(struct phylink_config *config, enetc_port_mac_wr(si, ENETC_PM0_CMD_CFG, cmd_cfg); enetc_mac_enable(si, true); + + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mm_link_state_update(priv, true); } static void enetc_pl_mac_link_down(struct phylink_config *config, @@ -1090,8 +1096,15 @@ static void enetc_pl_mac_link_down(struct phylink_config *config, phy_interface_t interface) { struct enetc_pf *pf = phylink_to_enetc_pf(config); + struct enetc_si *si = pf->si; + struct enetc_ndev_priv *priv; - enetc_mac_enable(pf->si, false); + priv = netdev_priv(si->ndev); + + if (si->hw_features & ENETC_SI_F_QBU) + enetc_mm_link_state_update(priv, false); + + enetc_mac_enable(si, false); } static const struct phylink_mac_ops enetc_mac_phylink_ops = { @@ -1284,6 +1297,8 @@ static int enetc_pf_probe(struct pci_dev *pdev, priv = netdev_priv(ndev); + mutex_init(&priv->mm_lock); + enetc_init_si_rings_params(priv); err = enetc_alloc_si_resources(priv); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_qos.c b/drivers/net/ethernet/freescale/enetc/enetc_qos.c index fcebb54224c0..130ebf6853e6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_qos.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_qos.c @@ -136,29 +136,21 @@ int enetc_setup_tc_taprio(struct net_device *ndev, void *type_data) { struct tc_taprio_qopt_offload *taprio = type_data; struct enetc_ndev_priv *priv = netdev_priv(ndev); - struct enetc_hw *hw = &priv->si->hw; - struct enetc_bdr *tx_ring; - int err; - int i; + int err, i; /* TSD and Qbv are mutually exclusive in hardware */ for (i = 0; i < priv->num_tx_rings; i++) if (priv->tx_ring[i]->tsd_enable) return -EBUSY; - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = taprio->enable ? i : 0; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + err = enetc_setup_tc_mqprio(ndev, &taprio->mqprio); + if (err) + return err; err = enetc_setup_taprio(ndev, taprio); if (err) { - for (i = 0; i < priv->num_tx_rings; i++) { - tx_ring = priv->tx_ring[i]; - tx_ring->prio = taprio->enable ? 0 : i; - enetc_set_bdr_prio(hw, tx_ring->index, tx_ring->prio); - } + taprio->mqprio.qopt.num_tc = 0; + enetc_setup_tc_mqprio(ndev, &taprio->mqprio); } return err; @@ -1611,6 +1603,13 @@ int enetc_qos_query_caps(struct net_device *ndev, void *type_data) struct enetc_si *si = priv->si; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c index b4cce30e526a..df86770731ad 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_main.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c @@ -1160,6 +1160,11 @@ static int fun_xdp_setup(struct net_device *dev, struct netdev_bpf *xdp) WRITE_ONCE(rxqs[i]->xdp_prog, prog); } + if (prog) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); + dev->max_mtu = prog ? XDP_MAX_MTU : FUN_MAX_MTU; old_prog = xchg(&fp->xdp_prog, prog); if (old_prog) @@ -1765,6 +1770,7 @@ static int fun_create_netdev(struct fun_ethdev *ed, unsigned int portid) netdev->vlan_features = netdev->features & VLAN_FEAT; netdev->mpls_features = netdev->vlan_features; netdev->hw_enc_features = netdev->hw_features; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = FUN_MAX_MTU; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 5b40f9c53196..07111c241e0e 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -327,7 +327,6 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) static int gve_alloc_notify_blocks(struct gve_priv *priv) { int num_vecs_requested = priv->num_ntfy_blks + 1; - char *name = priv->dev->name; unsigned int active_cpus; int vecs_enabled; int i, j; @@ -371,8 +370,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) active_cpus = min_t(int, priv->num_ntfy_blks / 2, num_online_cpus()); /* Setup Management Vector - the last vector */ - snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "%s-mgmnt", - name); + snprintf(priv->mgmt_msix_name, sizeof(priv->mgmt_msix_name), "gve-mgmnt@pci:%s", + pci_name(priv->pdev)); err = request_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, gve_mgmnt_intr, 0, priv->mgmt_msix_name, priv); if (err) { @@ -401,8 +400,8 @@ static int gve_alloc_notify_blocks(struct gve_priv *priv) struct gve_notify_block *block = &priv->ntfy_blocks[i]; int msix_idx = i; - snprintf(block->name, sizeof(block->name), "%s-ntfy-block.%d", - name, i); + snprintf(block->name, sizeof(block->name), "gve-ntfy-blk%d@pci:%s", + i, pci_name(priv->pdev)); block->priv = priv; err = request_irq(priv->msix_vectors[msix_idx].vector, gve_is_gqi(priv) ? gve_intr : gve_intr_dqo, diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 17137de9338c..40f4306449eb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -32,6 +32,7 @@ #include <linux/pkt_sched.h> #include <linux/types.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #define HNAE3_MOD_VERSION "1.0" diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index b4c4fb873568..25be7f8ac7cd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -20,6 +20,7 @@ #include <net/gro.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tcp.h> #include <net/vxlan.h> #include <net/geneve.h> diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 60e351665c70..60ce4d15d82a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -33,6 +33,7 @@ #include <linux/net_tstamp.h> #include <linux/ptp_clock_kernel.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> #include <net/udp_tunnel.h> @@ -176,7 +177,7 @@ enum i40e_interrupt_policy { struct i40e_lump_tracking { u16 num_entries; - u16 list[0]; + u16 list[]; #define I40E_PILE_VALID_BIT 0x8000 #define I40E_IWARP_IRQ_PILE_ID (I40E_PILE_VALID_BIT - 2) }; @@ -1287,9 +1288,9 @@ void i40e_ptp_stop(struct i40e_pf *pf); int i40e_ptp_alloc_pins(struct i40e_pf *pf); int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset); int i40e_is_vsi_uplink_mode_veb(struct i40e_vsi *vsi); -i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf); -i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf); -i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf); +int i40e_get_partition_bw_setting(struct i40e_pf *pf); +int i40e_set_partition_bw_setting(struct i40e_pf *pf); +int i40e_commit_partition_bw_setting(struct i40e_pf *pf); void i40e_print_link_message(struct i40e_vsi *vsi, bool isup); void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 42439f725aa4..86fac8f959bb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -47,9 +47,9 @@ static void i40e_adminq_init_regs(struct i40e_hw *hw) * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) +static int i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) { - i40e_status ret_code; + int ret_code; ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, i40e_mem_atq_ring, @@ -74,9 +74,9 @@ static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) +static int i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) { - i40e_status ret_code; + int ret_code; ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, i40e_mem_arq_ring, @@ -115,11 +115,11 @@ static void i40e_free_adminq_arq(struct i40e_hw *hw) * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) +static int i40e_alloc_arq_bufs(struct i40e_hw *hw) { - i40e_status ret_code; struct i40e_aq_desc *desc; struct i40e_dma_mem *bi; + int ret_code; int i; /* We'll be allocating the buffer info memory first, then we can @@ -182,10 +182,10 @@ unwind_alloc_arq_bufs: * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw) +static int i40e_alloc_asq_bufs(struct i40e_hw *hw) { - i40e_status ret_code; struct i40e_dma_mem *bi; + int ret_code; int i; /* No mapped memory needed yet, just the buffer info structures */ @@ -266,9 +266,9 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw) * * Configure base address and length registers for the transmit queue **/ -static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) +static int i40e_config_asq_regs(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -295,9 +295,9 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) * * Configure base address and length registers for the receive (event queue) **/ -static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) +static int i40e_config_arq_regs(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -334,9 +334,9 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_asq(struct i40e_hw *hw) +static int i40e_init_asq(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; if (hw->aq.asq.count > 0) { /* queue already initialized */ @@ -393,9 +393,9 @@ init_adminq_exit: * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_arq(struct i40e_hw *hw) +static int i40e_init_arq(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; if (hw->aq.arq.count > 0) { /* queue already initialized */ @@ -445,9 +445,9 @@ init_adminq_exit: * * The main shutdown routine for the Admin Send Queue **/ -static i40e_status i40e_shutdown_asq(struct i40e_hw *hw) +static int i40e_shutdown_asq(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; mutex_lock(&hw->aq.asq_mutex); @@ -479,9 +479,9 @@ shutdown_asq_out: * * The main shutdown routine for the Admin Receive Queue **/ -static i40e_status i40e_shutdown_arq(struct i40e_hw *hw) +static int i40e_shutdown_arq(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; mutex_lock(&hw->aq.arq_mutex); @@ -582,12 +582,12 @@ static void i40e_set_hw_flags(struct i40e_hw *hw) * - hw->aq.arq_buf_size * - hw->aq.asq_buf_size **/ -i40e_status i40e_init_adminq(struct i40e_hw *hw) +int i40e_init_adminq(struct i40e_hw *hw) { u16 cfg_ptr, oem_hi, oem_lo; u16 eetrack_lo, eetrack_hi; - i40e_status ret_code; int retry = 0; + int ret_code; /* verify input for valid configuration */ if ((hw->aq.num_arq_entries == 0) || @@ -780,7 +780,7 @@ static bool i40e_asq_done(struct i40e_hw *hw) * This is the main send command driver routine for the Admin Queue send * queue. It runs the queue, cleans the queue, etc **/ -static i40e_status +static int i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ @@ -788,12 +788,12 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details, bool is_atomic_context) { - i40e_status status = 0; struct i40e_dma_mem *dma_buff = NULL; struct i40e_asq_cmd_details *details; struct i40e_aq_desc *desc_on_ring; bool cmd_completed = false; u16 retval = 0; + int status = 0; u32 val = 0; if (hw->aq.asq.count == 0) { @@ -984,7 +984,7 @@ asq_send_command_error: * Acquires the lock and calls the main send command execution * routine. **/ -i40e_status +int i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ @@ -992,7 +992,7 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details, bool is_atomic_context) { - i40e_status status; + int status; mutex_lock(&hw->aq.asq_mutex); status = i40e_asq_send_command_atomic_exec(hw, desc, buff, buff_size, @@ -1003,7 +1003,7 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw, return status; } -i40e_status +int i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details) @@ -1026,7 +1026,7 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, * routine. Returns the last Admin Queue status in aq_status * to avoid race conditions in access to hw->aq.asq_last_status. **/ -i40e_status +int i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ @@ -1035,7 +1035,7 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, bool is_atomic_context, enum i40e_admin_queue_err *aq_status) { - i40e_status status; + int status; mutex_lock(&hw->aq.asq_mutex); status = i40e_asq_send_command_atomic_exec(hw, desc, buff, @@ -1048,7 +1048,7 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, return status; } -i40e_status +int i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, @@ -1084,14 +1084,14 @@ void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, * the contents through e. It can also return how many events are * left to process through 'pending' **/ -i40e_status i40e_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *pending) +int i40e_clean_arq_element(struct i40e_hw *hw, + struct i40e_arq_event_info *e, + u16 *pending) { - i40e_status ret_code = 0; u16 ntc = hw->aq.arq.next_to_clean; struct i40e_aq_desc *desc; struct i40e_dma_mem *bi; + int ret_code = 0; u16 desc_idx; u16 datalen; u16 flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e_alloc.h b/drivers/net/ethernet/intel/i40e/i40e_alloc.h index cb8689222c8b..a6c9a9e343d1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_alloc.h @@ -20,16 +20,16 @@ enum i40e_memory_type { }; /* prototype for functions used for dynamic memory allocation */ -i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - enum i40e_memory_type type, - u64 size, u32 alignment); -i40e_status i40e_free_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem); -i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem, - u32 size); -i40e_status i40e_free_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem); +int i40e_allocate_dma_mem(struct i40e_hw *hw, + struct i40e_dma_mem *mem, + enum i40e_memory_type type, + u64 size, u32 alignment); +int i40e_free_dma_mem(struct i40e_hw *hw, + struct i40e_dma_mem *mem); +int i40e_allocate_virt_mem(struct i40e_hw *hw, + struct i40e_virt_mem *mem, + u32 size); +int i40e_free_virt_mem(struct i40e_hw *hw, + struct i40e_virt_mem *mem); #endif /* _I40E_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 6ea43ef40540..639c5a1ca853 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -541,7 +541,7 @@ static int i40e_client_virtchnl_send(struct i40e_info *ldev, { struct i40e_pf *pf = ldev->pf; struct i40e_hw *hw = &pf->hw; - i40e_status err; + int err; err = i40e_aq_send_msg_to_vf(hw, vf_id, VIRTCHNL_OP_RDMA, 0, msg, len, NULL); @@ -674,7 +674,7 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_vsi_context ctxt; bool update = true; - i40e_status err; + int err; /* TODO: for now do not allow setting VF's VSI setting */ if (is_vf) @@ -686,8 +686,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, ctxt.flags = I40E_AQ_VSI_TYPE_PF; if (err) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + "couldn't get PF vsi config, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -ENOENT; @@ -714,8 +714,8 @@ static int i40e_client_update_vsi_ctxt(struct i40e_info *ldev, err = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (err) { dev_info(&pf->pdev->dev, - "update VSI ctxt for PE failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + "update VSI ctxt for PE failed, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 8f764ff5c990..ed88e38d488b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -14,9 +14,9 @@ * This function sets the mac type of the adapter based on the * vendor ID and device ID stored in the hw structure. **/ -i40e_status i40e_set_mac_type(struct i40e_hw *hw) +int i40e_set_mac_type(struct i40e_hw *hw) { - i40e_status status = 0; + int status = 0; if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { switch (hw->device_id) { @@ -125,154 +125,6 @@ const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) } /** - * i40e_stat_str - convert status err code to a string - * @hw: pointer to the HW structure - * @stat_err: the status error code to convert - **/ -const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err) -{ - switch (stat_err) { - case 0: - return "OK"; - case I40E_ERR_NVM: - return "I40E_ERR_NVM"; - case I40E_ERR_NVM_CHECKSUM: - return "I40E_ERR_NVM_CHECKSUM"; - case I40E_ERR_PHY: - return "I40E_ERR_PHY"; - case I40E_ERR_CONFIG: - return "I40E_ERR_CONFIG"; - case I40E_ERR_PARAM: - return "I40E_ERR_PARAM"; - case I40E_ERR_MAC_TYPE: - return "I40E_ERR_MAC_TYPE"; - case I40E_ERR_UNKNOWN_PHY: - return "I40E_ERR_UNKNOWN_PHY"; - case I40E_ERR_LINK_SETUP: - return "I40E_ERR_LINK_SETUP"; - case I40E_ERR_ADAPTER_STOPPED: - return "I40E_ERR_ADAPTER_STOPPED"; - case I40E_ERR_INVALID_MAC_ADDR: - return "I40E_ERR_INVALID_MAC_ADDR"; - case I40E_ERR_DEVICE_NOT_SUPPORTED: - return "I40E_ERR_DEVICE_NOT_SUPPORTED"; - case I40E_ERR_PRIMARY_REQUESTS_PENDING: - return "I40E_ERR_PRIMARY_REQUESTS_PENDING"; - case I40E_ERR_INVALID_LINK_SETTINGS: - return "I40E_ERR_INVALID_LINK_SETTINGS"; - case I40E_ERR_AUTONEG_NOT_COMPLETE: - return "I40E_ERR_AUTONEG_NOT_COMPLETE"; - case I40E_ERR_RESET_FAILED: - return "I40E_ERR_RESET_FAILED"; - case I40E_ERR_SWFW_SYNC: - return "I40E_ERR_SWFW_SYNC"; - case I40E_ERR_NO_AVAILABLE_VSI: - return "I40E_ERR_NO_AVAILABLE_VSI"; - case I40E_ERR_NO_MEMORY: - return "I40E_ERR_NO_MEMORY"; - case I40E_ERR_BAD_PTR: - return "I40E_ERR_BAD_PTR"; - case I40E_ERR_RING_FULL: - return "I40E_ERR_RING_FULL"; - case I40E_ERR_INVALID_PD_ID: - return "I40E_ERR_INVALID_PD_ID"; - case I40E_ERR_INVALID_QP_ID: - return "I40E_ERR_INVALID_QP_ID"; - case I40E_ERR_INVALID_CQ_ID: - return "I40E_ERR_INVALID_CQ_ID"; - case I40E_ERR_INVALID_CEQ_ID: - return "I40E_ERR_INVALID_CEQ_ID"; - case I40E_ERR_INVALID_AEQ_ID: - return "I40E_ERR_INVALID_AEQ_ID"; - case I40E_ERR_INVALID_SIZE: - return "I40E_ERR_INVALID_SIZE"; - case I40E_ERR_INVALID_ARP_INDEX: - return "I40E_ERR_INVALID_ARP_INDEX"; - case I40E_ERR_INVALID_FPM_FUNC_ID: - return "I40E_ERR_INVALID_FPM_FUNC_ID"; - case I40E_ERR_QP_INVALID_MSG_SIZE: - return "I40E_ERR_QP_INVALID_MSG_SIZE"; - case I40E_ERR_QP_TOOMANY_WRS_POSTED: - return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; - case I40E_ERR_INVALID_FRAG_COUNT: - return "I40E_ERR_INVALID_FRAG_COUNT"; - case I40E_ERR_QUEUE_EMPTY: - return "I40E_ERR_QUEUE_EMPTY"; - case I40E_ERR_INVALID_ALIGNMENT: - return "I40E_ERR_INVALID_ALIGNMENT"; - case I40E_ERR_FLUSHED_QUEUE: - return "I40E_ERR_FLUSHED_QUEUE"; - case I40E_ERR_INVALID_PUSH_PAGE_INDEX: - return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; - case I40E_ERR_INVALID_IMM_DATA_SIZE: - return "I40E_ERR_INVALID_IMM_DATA_SIZE"; - case I40E_ERR_TIMEOUT: - return "I40E_ERR_TIMEOUT"; - case I40E_ERR_OPCODE_MISMATCH: - return "I40E_ERR_OPCODE_MISMATCH"; - case I40E_ERR_CQP_COMPL_ERROR: - return "I40E_ERR_CQP_COMPL_ERROR"; - case I40E_ERR_INVALID_VF_ID: - return "I40E_ERR_INVALID_VF_ID"; - case I40E_ERR_INVALID_HMCFN_ID: - return "I40E_ERR_INVALID_HMCFN_ID"; - case I40E_ERR_BACKING_PAGE_ERROR: - return "I40E_ERR_BACKING_PAGE_ERROR"; - case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: - return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; - case I40E_ERR_INVALID_PBLE_INDEX: - return "I40E_ERR_INVALID_PBLE_INDEX"; - case I40E_ERR_INVALID_SD_INDEX: - return "I40E_ERR_INVALID_SD_INDEX"; - case I40E_ERR_INVALID_PAGE_DESC_INDEX: - return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; - case I40E_ERR_INVALID_SD_TYPE: - return "I40E_ERR_INVALID_SD_TYPE"; - case I40E_ERR_MEMCPY_FAILED: - return "I40E_ERR_MEMCPY_FAILED"; - case I40E_ERR_INVALID_HMC_OBJ_INDEX: - return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; - case I40E_ERR_INVALID_HMC_OBJ_COUNT: - return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; - case I40E_ERR_INVALID_SRQ_ARM_LIMIT: - return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; - case I40E_ERR_SRQ_ENABLED: - return "I40E_ERR_SRQ_ENABLED"; - case I40E_ERR_ADMIN_QUEUE_ERROR: - return "I40E_ERR_ADMIN_QUEUE_ERROR"; - case I40E_ERR_ADMIN_QUEUE_TIMEOUT: - return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; - case I40E_ERR_BUF_TOO_SHORT: - return "I40E_ERR_BUF_TOO_SHORT"; - case I40E_ERR_ADMIN_QUEUE_FULL: - return "I40E_ERR_ADMIN_QUEUE_FULL"; - case I40E_ERR_ADMIN_QUEUE_NO_WORK: - return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; - case I40E_ERR_BAD_IWARP_CQE: - return "I40E_ERR_BAD_IWARP_CQE"; - case I40E_ERR_NVM_BLANK_MODE: - return "I40E_ERR_NVM_BLANK_MODE"; - case I40E_ERR_NOT_IMPLEMENTED: - return "I40E_ERR_NOT_IMPLEMENTED"; - case I40E_ERR_PE_DOORBELL_NOT_ENABLED: - return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; - case I40E_ERR_DIAG_TEST_FAILED: - return "I40E_ERR_DIAG_TEST_FAILED"; - case I40E_ERR_NOT_READY: - return "I40E_ERR_NOT_READY"; - case I40E_NOT_SUPPORTED: - return "I40E_NOT_SUPPORTED"; - case I40E_ERR_FIRMWARE_API_VERSION: - return "I40E_ERR_FIRMWARE_API_VERSION"; - case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: - return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; - } - - snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); - return hw->err_str; -} - -/** * i40e_debug_aq * @hw: debug mask related to admin queue * @mask: debug mask @@ -355,13 +207,13 @@ bool i40e_check_asq_alive(struct i40e_hw *hw) * Tell the Firmware that we're shutting down the AdminQ and whether * or not the driver is unloading as well. **/ -i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, - bool unloading) +int i40e_aq_queue_shutdown(struct i40e_hw *hw, + bool unloading) { struct i40e_aq_desc desc; struct i40e_aqc_queue_shutdown *cmd = (struct i40e_aqc_queue_shutdown *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_queue_shutdown); @@ -384,15 +236,15 @@ i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, * * Internal function to get or set RSS look up table **/ -static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw, - u16 vsi_id, bool pf_lut, - u8 *lut, u16 lut_size, - bool set) +static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw, + u16 vsi_id, bool pf_lut, + u8 *lut, u16 lut_size, + bool set) { - i40e_status status; struct i40e_aq_desc desc; struct i40e_aqc_get_set_rss_lut *cmd_resp = (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; + int status; if (set) i40e_fill_default_direct_cmd_desc(&desc, @@ -437,8 +289,8 @@ static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw, * * get the RSS lookup table, PF or VSI type **/ -i40e_status i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) +int i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) { return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, false); @@ -454,8 +306,8 @@ i40e_status i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id, * * set the RSS lookup table, PF or VSI type **/ -i40e_status i40e_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) +int i40e_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) { return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); } @@ -469,16 +321,16 @@ i40e_status i40e_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id, * * get the RSS key per VSI **/ -static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key, - bool set) +static int i40e_aq_get_set_rss_key(struct i40e_hw *hw, + u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key, + bool set) { - i40e_status status; struct i40e_aq_desc desc; struct i40e_aqc_get_set_rss_key *cmd_resp = (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); + int status; if (set) i40e_fill_default_direct_cmd_desc(&desc, @@ -509,9 +361,9 @@ static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw, * @key: pointer to key info struct * **/ -i40e_status i40e_aq_get_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) +int i40e_aq_get_rss_key(struct i40e_hw *hw, + u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) { return i40e_aq_get_set_rss_key(hw, vsi_id, key, false); } @@ -524,9 +376,9 @@ i40e_status i40e_aq_get_rss_key(struct i40e_hw *hw, * * set the RSS key per VSI **/ -i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) +int i40e_aq_set_rss_key(struct i40e_hw *hw, + u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) { return i40e_aq_get_set_rss_key(hw, vsi_id, key, true); } @@ -796,10 +648,10 @@ struct i40e_rx_ptype_decoded i40e_ptype_lookup[BIT(8)] = { * hw_addr, back, device_id, vendor_id, subsystem_device_id, * subsystem_vendor_id, and revision_id **/ -i40e_status i40e_init_shared_code(struct i40e_hw *hw) +int i40e_init_shared_code(struct i40e_hw *hw) { - i40e_status status = 0; u32 port, ari, func_rid; + int status = 0; i40e_set_mac_type(hw); @@ -836,15 +688,16 @@ i40e_status i40e_init_shared_code(struct i40e_hw *hw) * @addrs: the requestor's mac addr store * @cmd_details: pointer to command details structure or NULL **/ -static i40e_status i40e_aq_mac_address_read(struct i40e_hw *hw, - u16 *flags, - struct i40e_aqc_mac_address_read_data *addrs, - struct i40e_asq_cmd_details *cmd_details) +static int +i40e_aq_mac_address_read(struct i40e_hw *hw, + u16 *flags, + struct i40e_aqc_mac_address_read_data *addrs, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_mac_address_read *cmd_data = (struct i40e_aqc_mac_address_read *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_mac_address_read); desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF); @@ -863,14 +716,14 @@ static i40e_status i40e_aq_mac_address_read(struct i40e_hw *hw, * @mac_addr: address to write * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw, - u16 flags, u8 *mac_addr, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_mac_address_write(struct i40e_hw *hw, + u16 flags, u8 *mac_addr, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_mac_address_write *cmd_data = (struct i40e_aqc_mac_address_write *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_mac_address_write); @@ -893,11 +746,11 @@ i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw, * * Reads the adapter's MAC address from register **/ -i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr) +int i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr) { struct i40e_aqc_mac_address_read_data addrs; - i40e_status status; u16 flags = 0; + int status; status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL); @@ -914,11 +767,11 @@ i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr) * * Reads the adapter's Port MAC address **/ -i40e_status i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr) +int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr) { struct i40e_aqc_mac_address_read_data addrs; - i40e_status status; u16 flags = 0; + int status; status = i40e_aq_mac_address_read(hw, &flags, &addrs, NULL); if (status) @@ -972,13 +825,13 @@ void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable) * * Reads the part number string from the EEPROM. **/ -i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, - u32 pba_num_size) +int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, + u32 pba_num_size) { - i40e_status status = 0; u16 pba_word = 0; u16 pba_size = 0; u16 pba_ptr = 0; + int status = 0; u16 i = 0; status = i40e_read_nvm_word(hw, I40E_SR_PBA_FLAGS, &pba_word); @@ -1087,8 +940,8 @@ static enum i40e_media_type i40e_get_media_type(struct i40e_hw *hw) * @hw: pointer to the hardware structure * @retry_limit: how many times to retry before failure **/ -static i40e_status i40e_poll_globr(struct i40e_hw *hw, - u32 retry_limit) +static int i40e_poll_globr(struct i40e_hw *hw, + u32 retry_limit) { u32 cnt, reg = 0; @@ -1114,7 +967,7 @@ static i40e_status i40e_poll_globr(struct i40e_hw *hw, * Assuming someone else has triggered a global reset, * assure the global reset is complete and then reset the PF **/ -i40e_status i40e_pf_reset(struct i40e_hw *hw) +int i40e_pf_reset(struct i40e_hw *hw) { u32 cnt = 0; u32 cnt1 = 0; @@ -1453,15 +1306,16 @@ void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink) * * Returns the various PHY abilities supported on the Port. **/ -i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, - bool qualified_modules, bool report_init, - struct i40e_aq_get_phy_abilities_resp *abilities, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_get_phy_capabilities(struct i40e_hw *hw, + bool qualified_modules, bool report_init, + struct i40e_aq_get_phy_abilities_resp *abilities, + struct i40e_asq_cmd_details *cmd_details) { - struct i40e_aq_desc desc; - i40e_status status; u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp); u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0; + struct i40e_aq_desc desc; + int status; if (!abilities) return I40E_ERR_PARAM; @@ -1532,14 +1386,14 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, * of the PHY Config parameters. This status will be indicated by the * command response. **/ -enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, - struct i40e_aq_set_phy_config *config, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_phy_config(struct i40e_hw *hw, + struct i40e_aq_set_phy_config *config, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aq_set_phy_config *cmd = (struct i40e_aq_set_phy_config *)&desc.params.raw; - enum i40e_status_code status; + int status; if (!config) return I40E_ERR_PARAM; @@ -1554,7 +1408,7 @@ enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, return status; } -static noinline_for_stack enum i40e_status_code +static noinline_for_stack int i40e_set_fc_status(struct i40e_hw *hw, struct i40e_aq_get_phy_abilities_resp *abilities, bool atomic_restart) @@ -1612,11 +1466,11 @@ i40e_set_fc_status(struct i40e_hw *hw, * * Set the requested flow control mode using set_phy_config. **/ -enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, - bool atomic_restart) +int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, + bool atomic_restart) { struct i40e_aq_get_phy_abilities_resp abilities; - enum i40e_status_code status; + int status; *aq_failures = 0x0; @@ -1655,13 +1509,13 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, * * Tell the firmware that the driver is taking over from PXE **/ -i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_clear_pxe_mode(struct i40e_hw *hw, + struct i40e_asq_cmd_details *cmd_details) { - i40e_status status; struct i40e_aq_desc desc; struct i40e_aqc_clear_pxe *cmd = (struct i40e_aqc_clear_pxe *)&desc.params.raw; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_clear_pxe_mode); @@ -1683,14 +1537,14 @@ i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw, * * Sets up the link and restarts the Auto-Negotiation over the link. **/ -i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw, - bool enable_link, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_link_restart_an(struct i40e_hw *hw, + bool enable_link, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_link_restart_an *cmd = (struct i40e_aqc_set_link_restart_an *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_link_restart_an); @@ -1715,17 +1569,17 @@ i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw, * * Returns the link status of the adapter. **/ -i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, - bool enable_lse, struct i40e_link_status *link, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_link_info(struct i40e_hw *hw, + bool enable_lse, struct i40e_link_status *link, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_get_link_status *resp = (struct i40e_aqc_get_link_status *)&desc.params.raw; struct i40e_link_status *hw_link_info = &hw->phy.link_info; - i40e_status status; bool tx_pause, rx_pause; u16 command_flags; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_link_status); @@ -1811,14 +1665,14 @@ aq_get_link_info_exit: * * Set link interrupt mask. **/ -i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw, - u16 mask, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, + u16 mask, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_phy_int_mask *cmd = (struct i40e_aqc_set_phy_int_mask *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_phy_int_mask); @@ -1838,8 +1692,8 @@ i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw, * * Enable/disable loopback on a given port */ -i40e_status i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_lb_mode *cmd = @@ -1864,13 +1718,13 @@ i40e_status i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk, * * Reset the external PHY. **/ -i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_phy_debug *cmd = (struct i40e_aqc_set_phy_debug *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_phy_debug); @@ -1905,9 +1759,9 @@ static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj, * * Add a VSI context to the hardware. **/ -i40e_status i40e_aq_add_vsi(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_add_vsi(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_get_update_vsi *cmd = @@ -1915,7 +1769,7 @@ i40e_status i40e_aq_add_vsi(struct i40e_hw *hw, struct i40e_aqc_add_get_update_vsi_completion *resp = (struct i40e_aqc_add_get_update_vsi_completion *) &desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_vsi); @@ -1949,15 +1803,15 @@ aq_add_vsi_exit: * @seid: vsi number * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, - u16 seid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_default_vsi(struct i40e_hw *hw, + u16 seid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *) &desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -1977,15 +1831,15 @@ i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, * @seid: vsi number * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_clear_default_vsi(struct i40e_hw *hw, - u16 seid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_clear_default_vsi(struct i40e_hw *hw, + u16 seid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *) &desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2007,16 +1861,16 @@ i40e_status i40e_aq_clear_default_vsi(struct i40e_hw *hw, * @cmd_details: pointer to command details structure or NULL * @rx_only_promisc: flag to decide if egress traffic gets mirrored in promisc **/ -i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, - u16 seid, bool set, - struct i40e_asq_cmd_details *cmd_details, - bool rx_only_promisc) +int i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, + u16 seid, bool set, + struct i40e_asq_cmd_details *cmd_details, + bool rx_only_promisc) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - i40e_status status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2047,14 +1901,15 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, * @set: set multicast promiscuous enable/disable * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, - u16 seid, bool set, struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, + u16 seid, bool set, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - i40e_status status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2080,16 +1935,16 @@ i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, * @vid: The VLAN tag filter - capture any multicast packet with this VLAN tag * @cmd_details: pointer to command details structure or NULL **/ -enum i40e_status_code i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, - u16 vid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, + u16 vid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - enum i40e_status_code status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2116,16 +1971,16 @@ enum i40e_status_code i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw, * @vid: The VLAN tag filter - capture any unicast packet with this VLAN tag * @cmd_details: pointer to command details structure or NULL **/ -enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, - u16 vid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, + u16 vid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - enum i40e_status_code status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2158,15 +2013,15 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, * @vid: The VLAN tag filter - capture any broadcast packet with this VLAN tag * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, u16 vid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, u16 vid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - i40e_status status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2193,14 +2048,14 @@ i40e_status i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, * * Set or clear the broadcast promiscuous flag (filter) for a given VSI. **/ -i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, - u16 seid, bool set_filter, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, + u16 seid, bool set_filter, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2226,15 +2081,15 @@ i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, * @enable: set MAC L2 layer unicast promiscuous enable/disable for a given VLAN * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, + u16 seid, bool enable, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_vsi_promiscuous_modes *cmd = (struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw; - i40e_status status; u16 flags = 0; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); @@ -2256,9 +2111,9 @@ i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, * @vsi_ctx: pointer to a vsi context struct * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_vsi_params(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_get_update_vsi *cmd = @@ -2266,7 +2121,7 @@ i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw, struct i40e_aqc_add_get_update_vsi_completion *resp = (struct i40e_aqc_add_get_update_vsi_completion *) &desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_vsi_parameters); @@ -2298,9 +2153,9 @@ aq_get_vsi_params_exit: * * Update a VSI context. **/ -i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_update_vsi_params(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_get_update_vsi *cmd = @@ -2308,7 +2163,7 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, struct i40e_aqc_add_get_update_vsi_completion *resp = (struct i40e_aqc_add_get_update_vsi_completion *) &desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_update_vsi_parameters); @@ -2336,15 +2191,15 @@ i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, * * Fill the buf with switch configuration returned from AdminQ command **/ -i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw, - struct i40e_aqc_get_switch_config_resp *buf, - u16 buf_size, u16 *start_seid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_switch_config(struct i40e_hw *hw, + struct i40e_aqc_get_switch_config_resp *buf, + u16 buf_size, u16 *start_seid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_switch_seid *scfg = (struct i40e_aqc_switch_seid *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_switch_config); @@ -2370,15 +2225,15 @@ i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw, * * Set switch configuration bits **/ -enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, - u16 flags, - u16 valid_flags, u8 mode, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_switch_config(struct i40e_hw *hw, + u16 flags, + u16 valid_flags, u8 mode, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_switch_config *scfg = (struct i40e_aqc_set_switch_config *)&desc.params.raw; - enum i40e_status_code status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_switch_config); @@ -2407,16 +2262,16 @@ enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, * * Get the firmware version from the admin queue commands **/ -i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw, - u16 *fw_major_version, u16 *fw_minor_version, - u32 *fw_build, - u16 *api_major_version, u16 *api_minor_version, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_firmware_version(struct i40e_hw *hw, + u16 *fw_major_version, u16 *fw_minor_version, + u32 *fw_build, + u16 *api_major_version, u16 *api_minor_version, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_get_version *resp = (struct i40e_aqc_get_version *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_version); @@ -2446,14 +2301,14 @@ i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw, * * Send the driver version to the firmware **/ -i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw, +int i40e_aq_send_driver_version(struct i40e_hw *hw, struct i40e_driver_version *dv, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_driver_version *cmd = (struct i40e_aqc_driver_version *)&desc.params.raw; - i40e_status status; + int status; u16 len; if (dv == NULL) @@ -2488,9 +2343,9 @@ i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw, * * Side effect: LinkStatusEvent reporting becomes enabled **/ -i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) +int i40e_get_link_status(struct i40e_hw *hw, bool *link_up) { - i40e_status status = 0; + int status = 0; if (hw->phy.get_link_info) { status = i40e_update_link_info(hw); @@ -2509,10 +2364,10 @@ i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) * i40e_update_link_info - update status of the HW network link * @hw: pointer to the hw struct **/ -noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw) +noinline_for_stack int i40e_update_link_info(struct i40e_hw *hw) { struct i40e_aq_get_phy_abilities_resp abilities; - i40e_status status = 0; + int status = 0; status = i40e_aq_get_link_info(hw, true, NULL, NULL); if (status) @@ -2559,19 +2414,19 @@ noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw) * This asks the FW to add a VEB between the uplink and downlink * elements. If the uplink SEID is 0, this will be a floating VEB. **/ -i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, - u16 downlink_seid, u8 enabled_tc, - bool default_port, u16 *veb_seid, - bool enable_stats, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, + u16 downlink_seid, u8 enabled_tc, + bool default_port, u16 *veb_seid, + bool enable_stats, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_veb *cmd = (struct i40e_aqc_add_veb *)&desc.params.raw; struct i40e_aqc_add_veb_completion *resp = (struct i40e_aqc_add_veb_completion *)&desc.params.raw; - i40e_status status; u16 veb_flags = 0; + int status; /* SEIDs need to either both be set or both be 0 for floating VEB */ if (!!uplink_seid != !!downlink_seid) @@ -2617,17 +2472,17 @@ i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, * This retrieves the parameters for a particular VEB, specified by * uplink_seid, and returns them to the caller. **/ -i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw, - u16 veb_seid, u16 *switch_id, - bool *floating, u16 *statistic_index, - u16 *vebs_used, u16 *vebs_free, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_veb_parameters(struct i40e_hw *hw, + u16 veb_seid, u16 *switch_id, + bool *floating, u16 *statistic_index, + u16 *vebs_used, u16 *vebs_free, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_get_veb_parameters_completion *cmd_resp = (struct i40e_aqc_get_veb_parameters_completion *) &desc.params.raw; - i40e_status status; + int status; if (veb_seid == 0) return I40E_ERR_PARAM; @@ -2711,7 +2566,7 @@ i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list, * * Add MAC/VLAN addresses to the HW filtering **/ -i40e_status +int i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details) @@ -2743,7 +2598,7 @@ i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid, * It also calls _v2 versions of asq_send_command functions to * get the aq_status on the stack. **/ -i40e_status +int i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, @@ -2771,15 +2626,16 @@ i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, * * Remove MAC/VLAN addresses from the HW filtering **/ -i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, - struct i40e_aqc_remove_macvlan_element_data *mv_list, - u16 count, struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_macvlan *cmd = (struct i40e_aqc_macvlan *)&desc.params.raw; - i40e_status status; u16 buf_size; + int status; if (count == 0 || !mv_list || !hw) return I40E_ERR_PARAM; @@ -2818,7 +2674,7 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, * It also calls _v2 versions of asq_send_command functions to * get the aq_status on the stack. **/ -i40e_status +int i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, @@ -2866,19 +2722,19 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for * VEBs/VEPA elements only **/ -static i40e_status i40e_mirrorrule_op(struct i40e_hw *hw, - u16 opcode, u16 sw_seid, u16 rule_type, u16 id, - u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) +static int i40e_mirrorrule_op(struct i40e_hw *hw, + u16 opcode, u16 sw_seid, u16 rule_type, u16 id, + u16 count, __le16 *mr_list, + struct i40e_asq_cmd_details *cmd_details, + u16 *rule_id, u16 *rules_used, u16 *rules_free) { struct i40e_aq_desc desc; struct i40e_aqc_add_delete_mirror_rule *cmd = (struct i40e_aqc_add_delete_mirror_rule *)&desc.params.raw; struct i40e_aqc_add_delete_mirror_rule_completion *resp = (struct i40e_aqc_add_delete_mirror_rule_completion *)&desc.params.raw; - i40e_status status; u16 buf_size; + int status; buf_size = count * sizeof(*mr_list); @@ -2926,10 +2782,11 @@ static i40e_status i40e_mirrorrule_op(struct i40e_hw *hw, * * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only **/ -i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free) +int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, + u16 rule_type, u16 dest_vsi, u16 count, + __le16 *mr_list, + struct i40e_asq_cmd_details *cmd_details, + u16 *rule_id, u16 *rules_used, u16 *rules_free) { if (!(rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS || rule_type == I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS)) { @@ -2957,10 +2814,11 @@ i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, * * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only **/ -i40e_status i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free) +int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, + u16 rule_type, u16 rule_id, u16 count, + __le16 *mr_list, + struct i40e_asq_cmd_details *cmd_details, + u16 *rules_used, u16 *rules_free) { /* Rule ID has to be valid except rule_type: INGRESS VLAN mirroring */ if (rule_type == I40E_AQC_MIRROR_RULE_TYPE_VLAN) { @@ -2989,14 +2847,14 @@ i40e_status i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, * * send msg to vf **/ -i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, - u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, + u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_pf_vf_message *cmd = (struct i40e_aqc_pf_vf_message *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_vf); cmd->id = cpu_to_le32(vfid); @@ -3024,14 +2882,14 @@ i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, * * Read the register using the admin queue commands **/ -i40e_status i40e_aq_debug_read_register(struct i40e_hw *hw, +int i40e_aq_debug_read_register(struct i40e_hw *hw, u32 reg_addr, u64 *reg_val, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_debug_reg_read_write *cmd_resp = (struct i40e_aqc_debug_reg_read_write *)&desc.params.raw; - i40e_status status; + int status; if (reg_val == NULL) return I40E_ERR_PARAM; @@ -3059,14 +2917,14 @@ i40e_status i40e_aq_debug_read_register(struct i40e_hw *hw, * * Write to a register using the admin queue commands **/ -i40e_status i40e_aq_debug_write_register(struct i40e_hw *hw, - u32 reg_addr, u64 reg_val, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_debug_write_register(struct i40e_hw *hw, + u32 reg_addr, u64 reg_val, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_debug_reg_read_write *cmd = (struct i40e_aqc_debug_reg_read_write *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_write_reg); @@ -3090,16 +2948,16 @@ i40e_status i40e_aq_debug_write_register(struct i40e_hw *hw, * * requests common resource using the admin queue commands **/ -i40e_status i40e_aq_request_resource(struct i40e_hw *hw, - enum i40e_aq_resources_ids resource, - enum i40e_aq_resource_access_type access, - u8 sdp_number, u64 *timeout, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_request_resource(struct i40e_hw *hw, + enum i40e_aq_resources_ids resource, + enum i40e_aq_resource_access_type access, + u8 sdp_number, u64 *timeout, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_request_resource *cmd_resp = (struct i40e_aqc_request_resource *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_request_resource); @@ -3129,15 +2987,15 @@ i40e_status i40e_aq_request_resource(struct i40e_hw *hw, * * release common resource using the admin queue commands **/ -i40e_status i40e_aq_release_resource(struct i40e_hw *hw, - enum i40e_aq_resources_ids resource, - u8 sdp_number, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_release_resource(struct i40e_hw *hw, + enum i40e_aq_resources_ids resource, + u8 sdp_number, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_request_resource *cmd = (struct i40e_aqc_request_resource *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_release_resource); @@ -3161,15 +3019,15 @@ i40e_status i40e_aq_release_resource(struct i40e_hw *hw, * * Read the NVM using the admin queue commands **/ -i40e_status i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, void *data, - bool last_command, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, void *data, + bool last_command, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_nvm_update *cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; - i40e_status status; + int status; /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { @@ -3207,14 +3065,14 @@ i40e_aq_read_nvm_exit: * * Erase the NVM sector using the admin queue commands **/ -i40e_status i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, bool last_command, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, bool last_command, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_nvm_update *cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; - i40e_status status; + int status; /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { @@ -3255,8 +3113,8 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, u32 number, logical_id, phys_id; struct i40e_hw_capabilities *p; u16 id, ocp_cfg_word0; - i40e_status status; u8 major_rev; + int status; u32 i = 0; cap = (struct i40e_aqc_list_capabilities_element_resp *) buff; @@ -3497,14 +3355,14 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff, * * Get the device capabilities descriptions from the firmware **/ -i40e_status i40e_aq_discover_capabilities(struct i40e_hw *hw, - void *buff, u16 buff_size, u16 *data_size, - enum i40e_admin_queue_opc list_type_opc, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_discover_capabilities(struct i40e_hw *hw, + void *buff, u16 buff_size, u16 *data_size, + enum i40e_admin_queue_opc list_type_opc, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aqc_list_capabilites *cmd; struct i40e_aq_desc desc; - i40e_status status = 0; + int status = 0; cmd = (struct i40e_aqc_list_capabilites *)&desc.params.raw; @@ -3546,15 +3404,15 @@ exit: * * Update the NVM using the admin queue commands **/ -i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, void *data, - bool last_command, u8 preservation_flags, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, void *data, + bool last_command, u8 preservation_flags, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_nvm_update *cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; - i40e_status status; + int status; /* In offset the highest byte must be zeroed. */ if (offset & 0xFF000000) { @@ -3599,13 +3457,13 @@ i40e_aq_update_nvm_exit: * * Rearrange NVM structure, available only for transition FW **/ -i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_rearrange_nvm(struct i40e_hw *hw, + u8 rearrange_nvm, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aqc_nvm_update *cmd; - i40e_status status; struct i40e_aq_desc desc; + int status; cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw; @@ -3639,17 +3497,17 @@ i40e_aq_rearrange_nvm_exit: * * Requests the complete LLDP MIB (entire packet). **/ -i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, - u8 mib_type, void *buff, u16 buff_size, - u16 *local_len, u16 *remote_len, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, + u8 mib_type, void *buff, u16 buff_size, + u16 *local_len, u16 *remote_len, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_lldp_get_mib *cmd = (struct i40e_aqc_lldp_get_mib *)&desc.params.raw; struct i40e_aqc_lldp_get_mib *resp = (struct i40e_aqc_lldp_get_mib *)&desc.params.raw; - i40e_status status; + int status; if (buff_size == 0 || !buff) return I40E_ERR_PARAM; @@ -3689,14 +3547,14 @@ i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, * * Set the LLDP MIB. **/ -enum i40e_status_code +int i40e_aq_set_lldp_mib(struct i40e_hw *hw, u8 mib_type, void *buff, u16 buff_size, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aqc_lldp_set_local_mib *cmd; - enum i40e_status_code status; struct i40e_aq_desc desc; + int status; cmd = (struct i40e_aqc_lldp_set_local_mib *)&desc.params.raw; if (buff_size == 0 || !buff) @@ -3728,14 +3586,14 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw, * Enable or Disable posting of an event on ARQ when LLDP MIB * associated with the interface changes **/ -i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, - bool enable_update, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, + bool enable_update, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_lldp_update_mib *cmd = (struct i40e_aqc_lldp_update_mib *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_update_mib); @@ -3757,14 +3615,14 @@ i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, * Restore LLDP Agent factory settings if @restore set to True. In other case * only returns factory setting in AQ response. **/ -enum i40e_status_code +int i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_lldp_restore *cmd = (struct i40e_aqc_lldp_restore *)&desc.params.raw; - i40e_status status; + int status; if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT)) { i40e_debug(hw, I40E_DEBUG_ALL, @@ -3794,14 +3652,14 @@ i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, * * Stop or Shutdown the embedded LLDP Agent **/ -i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, - bool persist, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, + bool persist, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_lldp_stop *cmd = (struct i40e_aqc_lldp_stop *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_stop); @@ -3829,13 +3687,13 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, * * Start the embedded LLDP Agent on all ports. **/ -i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_start_lldp(struct i40e_hw *hw, bool persist, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_lldp_start *cmd = (struct i40e_aqc_lldp_start *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start); @@ -3861,14 +3719,14 @@ i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist, * @dcb_enable: True if DCB configuration needs to be applied * **/ -enum i40e_status_code +int i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_set_dcb_parameters *cmd = (struct i40e_aqc_set_dcb_parameters *)&desc.params.raw; - i40e_status status; + int status; if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) return I40E_ERR_DEVICE_NOT_SUPPORTED; @@ -3894,12 +3752,12 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable, * * Get CEE DCBX mode operational configuration from firmware **/ -i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, - void *buff, u16 buff_size, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, + void *buff, u16 buff_size, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; - i40e_status status; + int status; if (buff_size == 0 || !buff) return I40E_ERR_PARAM; @@ -3925,17 +3783,17 @@ i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, * and this function will call cpu_to_le16 to convert from Host byte order to * Little Endian order. **/ -i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw, - u16 udp_port, u8 protocol_index, - u8 *filter_index, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_add_udp_tunnel(struct i40e_hw *hw, + u16 udp_port, u8 protocol_index, + u8 *filter_index, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_udp_tunnel *cmd = (struct i40e_aqc_add_udp_tunnel *)&desc.params.raw; struct i40e_aqc_del_udp_tunnel_completion *resp = (struct i40e_aqc_del_udp_tunnel_completion *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_udp_tunnel); @@ -3956,13 +3814,13 @@ i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw, * @index: filter index * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_remove_udp_tunnel *cmd = (struct i40e_aqc_remove_udp_tunnel *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_del_udp_tunnel); @@ -3981,13 +3839,13 @@ i40e_status i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index, * * This deletes a switch element from the switch. **/ -i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_switch_seid *cmd = (struct i40e_aqc_switch_seid *)&desc.params.raw; - i40e_status status; + int status; if (seid == 0) return I40E_ERR_PARAM; @@ -4011,11 +3869,11 @@ i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, * recomputed and modified. The retval field in the descriptor * will be set to 0 when RPB is modified. **/ -i40e_status i40e_aq_dcb_updated(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_dcb_updated(struct i40e_hw *hw, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_dcb_updated); @@ -4035,15 +3893,15 @@ i40e_status i40e_aq_dcb_updated(struct i40e_hw *hw, * * Generic command handler for Tx scheduler AQ commands **/ -static i40e_status i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid, +static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid, void *buff, u16 buff_size, - enum i40e_admin_queue_opc opcode, + enum i40e_admin_queue_opc opcode, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_tx_sched_ind *cmd = (struct i40e_aqc_tx_sched_ind *)&desc.params.raw; - i40e_status status; + int status; bool cmd_param_flag = false; switch (opcode) { @@ -4093,14 +3951,14 @@ static i40e_status i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid, * @max_credit: Max BW limit credits * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, +int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, u16 seid, u16 credit, u8 max_credit, struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_configure_vsi_bw_limit *cmd = (struct i40e_aqc_configure_vsi_bw_limit *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_configure_vsi_bw_limit); @@ -4121,10 +3979,10 @@ i40e_status i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, * @bw_data: Buffer holding enabled TCs, relative TC BW limit/credits * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_configure_vsi_tc_bw_data *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_configure_vsi_tc_bw_data *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_configure_vsi_tc_bw, @@ -4139,11 +3997,12 @@ i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, * @opcode: Tx scheduler AQ command opcode * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_configure_switching_comp_ets_data *ets_data, - enum i40e_admin_queue_opc opcode, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_configure_switching_comp_ets_data *ets_data, + enum i40e_admin_queue_opc opcode, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)ets_data, sizeof(*ets_data), opcode, cmd_details); @@ -4156,7 +4015,8 @@ i40e_status i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, * @bw_data: Buffer holding enabled TCs, relative/absolute TC BW limit/credits * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_config_switch_comp_bw_config(struct i40e_hw *hw, +int +i40e_aq_config_switch_comp_bw_config(struct i40e_hw *hw, u16 seid, struct i40e_aqc_configure_switching_comp_bw_config_data *bw_data, struct i40e_asq_cmd_details *cmd_details) @@ -4173,10 +4033,11 @@ i40e_status i40e_aq_config_switch_comp_bw_config(struct i40e_hw *hw, * @bw_data: Buffer to hold VSI BW configuration * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_query_vsi_bw_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_vsi_bw_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_query_vsi_bw_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_vsi_bw_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_query_vsi_bw_config, @@ -4190,10 +4051,11 @@ i40e_status i40e_aq_query_vsi_bw_config(struct i40e_hw *hw, * @bw_data: Buffer to hold VSI BW configuration per TC * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_query_vsi_ets_sla_config, @@ -4207,10 +4069,11 @@ i40e_status i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw, * @bw_data: Buffer to hold switching component's per TC BW config * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_query_switching_comp_ets_config, @@ -4224,10 +4087,11 @@ i40e_status i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw, * @bw_data: Buffer to hold current ETS configuration for the Physical Port * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_query_port_ets_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_port_ets_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_query_port_ets_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_port_ets_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_query_port_ets_config, @@ -4241,10 +4105,11 @@ i40e_status i40e_aq_query_port_ets_config(struct i40e_hw *hw, * @bw_data: Buffer to hold switching component's BW configuration * @cmd_details: pointer to command details structure or NULL **/ -i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details) { return i40e_aq_tx_sched_cmd(hw, seid, (void *)bw_data, sizeof(*bw_data), i40e_aqc_opc_query_switching_comp_bw_config, @@ -4263,8 +4128,9 @@ i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, * Returns 0 if the values passed are valid and within * range else returns an error. **/ -static i40e_status i40e_validate_filter_settings(struct i40e_hw *hw, - struct i40e_filter_control_settings *settings) +static int +i40e_validate_filter_settings(struct i40e_hw *hw, + struct i40e_filter_control_settings *settings) { u32 fcoe_cntx_size, fcoe_filt_size; u32 fcoe_fmax; @@ -4350,11 +4216,11 @@ static i40e_status i40e_validate_filter_settings(struct i40e_hw *hw, * for a single PF. It is expected that these settings are programmed * at the driver initialization time. **/ -i40e_status i40e_set_filter_control(struct i40e_hw *hw, - struct i40e_filter_control_settings *settings) +int i40e_set_filter_control(struct i40e_hw *hw, + struct i40e_filter_control_settings *settings) { - i40e_status ret = 0; u32 hash_lut_size = 0; + int ret = 0; u32 val; if (!settings) @@ -4424,11 +4290,11 @@ i40e_status i40e_set_filter_control(struct i40e_hw *hw, * In return it will update the total number of perfect filter count in * the stats member. **/ -i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, - u8 *mac_addr, u16 ethtype, u16 flags, - u16 vsi_seid, u16 queue, bool is_add, - struct i40e_control_filter_stats *stats, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, + u8 *mac_addr, u16 ethtype, u16 flags, + u16 vsi_seid, u16 queue, bool is_add, + struct i40e_control_filter_stats *stats, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_add_remove_control_packet_filter *cmd = @@ -4437,7 +4303,7 @@ i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, struct i40e_aqc_add_remove_control_packet_filter_completion *resp = (struct i40e_aqc_add_remove_control_packet_filter_completion *) &desc.params.raw; - i40e_status status; + int status; if (vsi_seid == 0) return I40E_ERR_PARAM; @@ -4483,7 +4349,7 @@ void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP | I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX; u16 ethtype = I40E_FLOW_CONTROL_ETHTYPE; - i40e_status status; + int status; status = i40e_aq_add_rem_control_packet_filter(hw, NULL, ethtype, flag, seid, 0, true, NULL, @@ -4505,14 +4371,14 @@ void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, * is not passed then only register at 'reg_addr0' is read. * **/ -static i40e_status i40e_aq_alternate_read(struct i40e_hw *hw, - u32 reg_addr0, u32 *reg_val0, - u32 reg_addr1, u32 *reg_val1) +static int i40e_aq_alternate_read(struct i40e_hw *hw, + u32 reg_addr0, u32 *reg_val0, + u32 reg_addr1, u32 *reg_val1) { struct i40e_aq_desc desc; struct i40e_aqc_alternate_write *cmd_resp = (struct i40e_aqc_alternate_write *)&desc.params.raw; - i40e_status status; + int status; if (!reg_val0) return I40E_ERR_PARAM; @@ -4541,12 +4407,12 @@ static i40e_status i40e_aq_alternate_read(struct i40e_hw *hw, * * Suspend port's Tx traffic **/ -i40e_status i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aqc_tx_sched_ind *cmd; struct i40e_aq_desc desc; - i40e_status status; + int status; cmd = (struct i40e_aqc_tx_sched_ind *)&desc.params.raw; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_suspend_port_tx); @@ -4563,11 +4429,11 @@ i40e_status i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid, * * Resume port's Tx traffic **/ -i40e_status i40e_aq_resume_port_tx(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_resume_port_tx(struct i40e_hw *hw, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_resume_port_tx); @@ -4637,18 +4503,18 @@ void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status) * Dump internal FW/HW data for debug purposes. * **/ -i40e_status i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, - u8 table_id, u32 start_index, u16 buff_size, - void *buff, u16 *ret_buff_size, - u8 *ret_next_table, u32 *ret_next_index, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, + u8 table_id, u32 start_index, u16 buff_size, + void *buff, u16 *ret_buff_size, + u8 *ret_next_table, u32 *ret_next_index, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_debug_dump_internals *cmd = (struct i40e_aqc_debug_dump_internals *)&desc.params.raw; struct i40e_aqc_debug_dump_internals *resp = (struct i40e_aqc_debug_dump_internals *)&desc.params.raw; - i40e_status status; + int status; if (buff_size == 0 || !buff) return I40E_ERR_PARAM; @@ -4689,12 +4555,12 @@ i40e_status i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, * * Read bw from the alternate ram for the given pf **/ -i40e_status i40e_read_bw_from_alt_ram(struct i40e_hw *hw, - u32 *max_bw, u32 *min_bw, - bool *min_valid, bool *max_valid) +int i40e_read_bw_from_alt_ram(struct i40e_hw *hw, + u32 *max_bw, u32 *min_bw, + bool *min_valid, bool *max_valid) { - i40e_status status; u32 max_bw_addr, min_bw_addr; + int status; /* Calculate the address of the min/max bw registers */ max_bw_addr = I40E_ALT_STRUCT_FIRST_PF_OFFSET + @@ -4729,13 +4595,14 @@ i40e_status i40e_read_bw_from_alt_ram(struct i40e_hw *hw, * * Configure partitions guaranteed/max bw **/ -i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, - struct i40e_aqc_configure_partition_bw_data *bw_data, - struct i40e_asq_cmd_details *cmd_details) +int +i40e_aq_configure_partition_bw(struct i40e_hw *hw, + struct i40e_aqc_configure_partition_bw_data *bw_data, + struct i40e_asq_cmd_details *cmd_details) { - i40e_status status; - struct i40e_aq_desc desc; u16 bwd_size = sizeof(*bw_data); + struct i40e_aq_desc desc; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_configure_partition_bw); @@ -4764,11 +4631,11 @@ i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, * * Reads specified PHY register value **/ -i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, - u16 reg, u8 phy_addr, u16 *value) +int i40e_read_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 *value) { - i40e_status status = I40E_ERR_TIMEOUT; u8 port_num = (u8)hw->func_caps.mdio_port_num; + int status = I40E_ERR_TIMEOUT; u32 command = 0; u16 retry = 1000; @@ -4809,11 +4676,11 @@ i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, * * Writes specified PHY register value **/ -i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, - u16 reg, u8 phy_addr, u16 value) +int i40e_write_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 value) { - i40e_status status = I40E_ERR_TIMEOUT; u8 port_num = (u8)hw->func_caps.mdio_port_num; + int status = I40E_ERR_TIMEOUT; u32 command = 0; u16 retry = 1000; @@ -4850,13 +4717,13 @@ i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, * * Reads specified PHY register value **/ -i40e_status i40e_read_phy_register_clause45(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 *value) +int i40e_read_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value) { - i40e_status status = I40E_ERR_TIMEOUT; + u8 port_num = hw->func_caps.mdio_port_num; + int status = I40E_ERR_TIMEOUT; u32 command = 0; u16 retry = 1000; - u8 port_num = hw->func_caps.mdio_port_num; command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) | (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | @@ -4924,13 +4791,13 @@ phy_read_end: * * Writes value to specified PHY register **/ -i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 value) +int i40e_write_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value) { - i40e_status status = I40E_ERR_TIMEOUT; - u32 command = 0; - u16 retry = 1000; u8 port_num = hw->func_caps.mdio_port_num; + int status = I40E_ERR_TIMEOUT; + u16 retry = 1000; + u32 command = 0; command = (reg << I40E_GLGEN_MSCA_MDIADD_SHIFT) | (page << I40E_GLGEN_MSCA_DEVADD_SHIFT) | @@ -4991,10 +4858,10 @@ phy_write_end: * * Writes value to specified PHY register **/ -i40e_status i40e_write_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 value) +int i40e_write_phy_register(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value) { - i40e_status status; + int status; switch (hw->device_id) { case I40E_DEV_ID_1G_BASE_T_X722: @@ -5030,10 +4897,10 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, * * Reads specified PHY register value **/ -i40e_status i40e_read_phy_register(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 *value) +int i40e_read_phy_register(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value) { - i40e_status status; + int status; switch (hw->device_id) { case I40E_DEV_ID_1G_BASE_T_X722: @@ -5082,17 +4949,17 @@ u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num) * * Blinks PHY link LED **/ -i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval) +int i40e_blink_phy_link_led(struct i40e_hw *hw, + u32 time, u32 interval) { - i40e_status status = 0; - u32 i; - u16 led_ctl; - u16 gpio_led_port; - u16 led_reg; u16 led_addr = I40E_PHY_LED_PROV_REG_1; + u16 gpio_led_port; u8 phy_addr = 0; + int status = 0; + u16 led_ctl; u8 port_num; + u16 led_reg; + u32 i; i = rd32(hw, I40E_PFGEN_PORTNUM); port_num = (u8)(i & I40E_PFGEN_PORTNUM_PORT_NUM_MASK); @@ -5154,12 +5021,12 @@ phy_blinking_end: * @led_addr: LED register address * @reg_val: read register value **/ -static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr, - u32 *reg_val) +static int i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr, + u32 *reg_val) { - enum i40e_status_code status; u8 phy_addr = 0; u8 port_num; + int status; u32 i; *reg_val = 0; @@ -5188,12 +5055,12 @@ static enum i40e_status_code i40e_led_get_reg(struct i40e_hw *hw, u16 led_addr, * @led_addr: LED register address * @reg_val: register value to write **/ -static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr, - u32 reg_val) +static int i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr, + u32 reg_val) { - enum i40e_status_code status; u8 phy_addr = 0; u8 port_num; + int status; u32 i; if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { @@ -5223,17 +5090,17 @@ static enum i40e_status_code i40e_led_set_reg(struct i40e_hw *hw, u16 led_addr, * @val: original value of register to use * **/ -i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, - u16 *val) +int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, + u16 *val) { - i40e_status status = 0; u16 gpio_led_port; u8 phy_addr = 0; - u16 reg_val; + u32 reg_val_aq; + int status = 0; u16 temp_addr; + u16 reg_val; u8 port_num; u32 i; - u32 reg_val_aq; if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) { status = @@ -5278,12 +5145,12 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, * Set led's on or off when controlled by the PHY * **/ -i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on, - u16 led_addr, u32 mode) +int i40e_led_set_phy(struct i40e_hw *hw, bool on, + u16 led_addr, u32 mode) { - i40e_status status = 0; u32 led_ctl = 0; u32 led_reg = 0; + int status = 0; status = i40e_led_get_reg(hw, led_addr, &led_reg); if (status) @@ -5327,14 +5194,14 @@ restore_config: * Use the firmware to read the Rx control register, * especially useful if the Rx unit is under heavy pressure **/ -i40e_status i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp = (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; + int status; if (!reg_val) return I40E_ERR_PARAM; @@ -5358,8 +5225,8 @@ i40e_status i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, **/ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) { - i40e_status status = 0; bool use_register; + int status = 0; int retry = 5; u32 val = 0; @@ -5393,14 +5260,14 @@ do_retry: * Use the firmware to write to an Rx control register, * especially useful if the Rx unit is under heavy pressure **/ -i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_rx_ctl_reg_read_write *cmd = (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_write); @@ -5420,8 +5287,8 @@ i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, **/ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) { - i40e_status status = 0; bool use_register; + int status = 0; int retry = 5; use_register = (((hw->aq.api_maj_ver == 1) && @@ -5483,16 +5350,16 @@ static void i40e_mdio_if_number_selection(struct i40e_hw *hw, bool set_mdio, * NOTE: In common cases MDIO I/F number should not be changed, thats why you * may use simple wrapper i40e_aq_set_phy_register. **/ -enum i40e_status_code i40e_aq_set_phy_register_ext(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, bool page_change, - bool set_mdio, u8 mdio_num, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_set_phy_register_ext(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, bool page_change, + bool set_mdio, u8 mdio_num, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_phy_register_access *cmd = (struct i40e_aqc_phy_register_access *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_phy_register); @@ -5528,16 +5395,16 @@ enum i40e_status_code i40e_aq_set_phy_register_ext(struct i40e_hw *hw, * NOTE: In common cases MDIO I/F number should not be changed, thats why you * may use simple wrapper i40e_aq_get_phy_register. **/ -enum i40e_status_code i40e_aq_get_phy_register_ext(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, bool page_change, - bool set_mdio, u8 mdio_num, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_phy_register_ext(struct i40e_hw *hw, + u8 phy_select, u8 dev_addr, bool page_change, + bool set_mdio, u8 mdio_num, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_phy_register_access *cmd = (struct i40e_aqc_phy_register_access *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_phy_register); @@ -5568,18 +5435,17 @@ enum i40e_status_code i40e_aq_get_phy_register_ext(struct i40e_hw *hw, * @error_info: returns error information * @cmd_details: pointer to command details structure or NULL **/ -enum -i40e_status_code i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_write_personalization_profile *cmd = (struct i40e_aqc_write_personalization_profile *) &desc.params.raw; struct i40e_aqc_write_ddp_resp *resp; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_write_personalization_profile); @@ -5612,15 +5478,14 @@ i40e_status_code i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, * @flags: AdminQ command flags * @cmd_details: pointer to command details structure or NULL **/ -enum -i40e_status_code i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details *cmd_details) +int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details *cmd_details) { struct i40e_aq_desc desc; struct i40e_aqc_get_applied_profiles *cmd = (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; - i40e_status status; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_personalization_profile_list); @@ -5719,14 +5584,13 @@ i40e_find_section_in_profile(u32 section_type, * @hw: pointer to the hw struct * @aq: command buffer containing all data to execute AQ **/ -static enum -i40e_status_code i40e_ddp_exec_aq_section(struct i40e_hw *hw, - struct i40e_profile_aq_section *aq) +static int i40e_ddp_exec_aq_section(struct i40e_hw *hw, + struct i40e_profile_aq_section *aq) { - i40e_status status; struct i40e_aq_desc desc; u8 *msg = NULL; u16 msglen; + int status; i40e_fill_default_direct_cmd_desc(&desc, aq->opcode); desc.flags |= cpu_to_le16(aq->flags); @@ -5766,14 +5630,14 @@ i40e_status_code i40e_ddp_exec_aq_section(struct i40e_hw *hw, * * Validates supported devices and profile's sections. */ -static enum i40e_status_code +static int i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, u32 track_id, bool rollback) { struct i40e_profile_section_header *sec = NULL; - i40e_status status = 0; struct i40e_section_table *sec_tbl; u32 vendor_dev_id; + int status = 0; u32 dev_cnt; u32 sec_off; u32 i; @@ -5831,16 +5695,16 @@ i40e_validate_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, * * Handles the download of a complete package. */ -enum i40e_status_code +int i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, u32 track_id) { - i40e_status status = 0; - struct i40e_section_table *sec_tbl; struct i40e_profile_section_header *sec = NULL; struct i40e_profile_aq_section *ddp_aq; - u32 section_size = 0; + struct i40e_section_table *sec_tbl; u32 offset = 0, info = 0; + u32 section_size = 0; + int status = 0; u32 sec_off; u32 i; @@ -5894,15 +5758,15 @@ i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, * * Rolls back previously loaded package. */ -enum i40e_status_code +int i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, u32 track_id) { struct i40e_profile_section_header *sec = NULL; - i40e_status status = 0; struct i40e_section_table *sec_tbl; u32 offset = 0, info = 0; u32 section_size = 0; + int status = 0; u32 sec_off; int i; @@ -5946,15 +5810,15 @@ i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, * * Register a profile to the list of loaded profiles. */ -enum i40e_status_code +int i40e_add_pinfo_to_list(struct i40e_hw *hw, struct i40e_profile_segment *profile, u8 *profile_info_sec, u32 track_id) { - i40e_status status = 0; struct i40e_profile_section_header *sec = NULL; struct i40e_profile_info *pinfo; u32 offset = 0, info = 0; + int status = 0; sec = (struct i40e_profile_section_header *)profile_info_sec; sec->tbl_size = 1; @@ -5988,7 +5852,7 @@ i40e_add_pinfo_to_list(struct i40e_hw *hw, * of the function. * **/ -enum i40e_status_code +int i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_data *filters, u8 filter_count) @@ -5996,8 +5860,8 @@ i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid, struct i40e_aq_desc desc; struct i40e_aqc_add_remove_cloud_filters *cmd = (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; - enum i40e_status_code status; u16 buff_len; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_cloud_filters); @@ -6025,7 +5889,7 @@ i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid, * function. * **/ -enum i40e_status_code +int i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_bb *filters, u8 filter_count) @@ -6033,8 +5897,8 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aq_desc desc; struct i40e_aqc_add_remove_cloud_filters *cmd = (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; - i40e_status status; u16 buff_len; + int status; int i; i40e_fill_default_direct_cmd_desc(&desc, @@ -6082,7 +5946,7 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, * of the function. * **/ -enum i40e_status_code +int i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_data *filters, u8 filter_count) @@ -6090,8 +5954,8 @@ i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid, struct i40e_aq_desc desc; struct i40e_aqc_add_remove_cloud_filters *cmd = (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; - enum i40e_status_code status; u16 buff_len; + int status; i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_cloud_filters); @@ -6119,7 +5983,7 @@ i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid, * function. * **/ -enum i40e_status_code +int i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_bb *filters, u8 filter_count) @@ -6127,8 +5991,8 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aq_desc desc; struct i40e_aqc_add_remove_cloud_filters *cmd = (struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw; - i40e_status status; u16 buff_len; + int status; int i; i40e_fill_default_direct_cmd_desc(&desc, diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 673f341f4c0c..90638b67f8dc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -12,7 +12,7 @@ * * Get the DCBX status from the Firmware **/ -i40e_status i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status) +int i40e_get_dcbx_status(struct i40e_hw *hw, u16 *status) { u32 reg; @@ -497,15 +497,15 @@ static void i40e_parse_org_tlv(struct i40e_lldp_org_tlv *tlv, * * Parse DCB configuration from the LLDPDU **/ -i40e_status i40e_lldp_to_dcb_config(u8 *lldpmib, - struct i40e_dcbx_config *dcbcfg) +int i40e_lldp_to_dcb_config(u8 *lldpmib, + struct i40e_dcbx_config *dcbcfg) { - i40e_status ret = 0; struct i40e_lldp_org_tlv *tlv; - u16 type; - u16 length; u16 typelength; u16 offset = 0; + int ret = 0; + u16 length; + u16 type; if (!lldpmib || !dcbcfg) return I40E_ERR_PARAM; @@ -551,12 +551,12 @@ i40e_status i40e_lldp_to_dcb_config(u8 *lldpmib, * * Query DCB configuration from the Firmware **/ -i40e_status i40e_aq_get_dcb_config(struct i40e_hw *hw, u8 mib_type, - u8 bridgetype, - struct i40e_dcbx_config *dcbcfg) +int i40e_aq_get_dcb_config(struct i40e_hw *hw, u8 mib_type, + u8 bridgetype, + struct i40e_dcbx_config *dcbcfg) { - i40e_status ret = 0; struct i40e_virt_mem mem; + int ret = 0; u8 *lldpmib; /* Allocate the LLDPDU */ @@ -767,9 +767,9 @@ static void i40e_cee_to_dcb_config( * * Get IEEE mode DCB configuration from the Firmware **/ -static i40e_status i40e_get_ieee_dcb_config(struct i40e_hw *hw) +static int i40e_get_ieee_dcb_config(struct i40e_hw *hw) { - i40e_status ret = 0; + int ret = 0; /* IEEE mode */ hw->local_dcbx_config.dcbx_mode = I40E_DCBX_MODE_IEEE; @@ -797,11 +797,11 @@ out: * * Get DCB configuration from the Firmware **/ -i40e_status i40e_get_dcb_config(struct i40e_hw *hw) +int i40e_get_dcb_config(struct i40e_hw *hw) { - i40e_status ret = 0; - struct i40e_aqc_get_cee_dcb_cfg_resp cee_cfg; struct i40e_aqc_get_cee_dcb_cfg_v1_resp cee_v1_cfg; + struct i40e_aqc_get_cee_dcb_cfg_resp cee_cfg; + int ret = 0; /* If Firmware version < v4.33 on X710/XL710, IEEE only */ if ((hw->mac.type == I40E_MAC_XL710) && @@ -867,11 +867,11 @@ out: * * Update DCB configuration from the Firmware **/ -i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) +int i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) { - i40e_status ret = 0; struct i40e_lldp_variables lldp_cfg; u8 adminstatus = 0; + int ret = 0; if (!hw->func_caps.dcb) return I40E_NOT_SUPPORTED; @@ -940,13 +940,13 @@ i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) * Get status of FW Link Layer Discovery Protocol (LLDP) Agent. * Status of agent is reported via @lldp_status parameter. **/ -enum i40e_status_code +int i40e_get_fw_lldp_status(struct i40e_hw *hw, enum i40e_get_fw_lldp_status_resp *lldp_status) { struct i40e_virt_mem mem; - i40e_status ret; u8 *lldpmib; + int ret; if (!lldp_status) return I40E_ERR_PARAM; @@ -1238,13 +1238,13 @@ static void i40e_add_dcb_tlv(struct i40e_lldp_org_tlv *tlv, * * Set DCB configuration to the Firmware **/ -i40e_status i40e_set_dcb_config(struct i40e_hw *hw) +int i40e_set_dcb_config(struct i40e_hw *hw) { struct i40e_dcbx_config *dcbcfg; struct i40e_virt_mem mem; u8 mib_type, *lldpmib; - i40e_status ret; u16 miblen; + int ret; /* update the hw local config */ dcbcfg = &hw->local_dcbx_config; @@ -1274,8 +1274,8 @@ i40e_status i40e_set_dcb_config(struct i40e_hw *hw) * * send DCB configuration to FW **/ -i40e_status i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, - struct i40e_dcbx_config *dcbcfg) +int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, + struct i40e_dcbx_config *dcbcfg) { u16 length, offset = 0, tlvid, typelength; struct i40e_lldp_org_tlv *tlv; @@ -1888,13 +1888,13 @@ void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, * * Reads the LLDP configuration data from NVM using passed addresses **/ -static i40e_status _i40e_read_lldp_cfg(struct i40e_hw *hw, - struct i40e_lldp_variables *lldp_cfg, - u8 module, u32 word_offset) +static int _i40e_read_lldp_cfg(struct i40e_hw *hw, + struct i40e_lldp_variables *lldp_cfg, + u8 module, u32 word_offset) { u32 address, offset = (2 * word_offset); - i40e_status ret; __le16 raw_mem; + int ret; u16 mem; ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); @@ -1950,10 +1950,10 @@ err_lldp_cfg: * * Reads the LLDP configuration data from NVM **/ -i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw, - struct i40e_lldp_variables *lldp_cfg) +int i40e_read_lldp_cfg(struct i40e_hw *hw, + struct i40e_lldp_variables *lldp_cfg) { - i40e_status ret = 0; + int ret = 0; u32 mem; if (!lldp_cfg) diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h index 2370ceecb061..6b60dc9b7736 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h @@ -264,20 +264,20 @@ void i40e_dcb_hw_calculate_pool_sizes(struct i40e_hw *hw, void i40e_dcb_hw_rx_pb_config(struct i40e_hw *hw, struct i40e_rx_pb_config *old_pb_cfg, struct i40e_rx_pb_config *new_pb_cfg); -i40e_status i40e_get_dcbx_status(struct i40e_hw *hw, - u16 *status); -i40e_status i40e_lldp_to_dcb_config(u8 *lldpmib, - struct i40e_dcbx_config *dcbcfg); -i40e_status i40e_aq_get_dcb_config(struct i40e_hw *hw, u8 mib_type, - u8 bridgetype, - struct i40e_dcbx_config *dcbcfg); -i40e_status i40e_get_dcb_config(struct i40e_hw *hw); -i40e_status i40e_init_dcb(struct i40e_hw *hw, - bool enable_mib_change); -enum i40e_status_code +int i40e_get_dcbx_status(struct i40e_hw *hw, + u16 *status); +int i40e_lldp_to_dcb_config(u8 *lldpmib, + struct i40e_dcbx_config *dcbcfg); +int i40e_aq_get_dcb_config(struct i40e_hw *hw, u8 mib_type, + u8 bridgetype, + struct i40e_dcbx_config *dcbcfg); +int i40e_get_dcb_config(struct i40e_hw *hw); +int i40e_init_dcb(struct i40e_hw *hw, + bool enable_mib_change); +int i40e_get_fw_lldp_status(struct i40e_hw *hw, enum i40e_get_fw_lldp_status_resp *lldp_status); -i40e_status i40e_set_dcb_config(struct i40e_hw *hw); -i40e_status i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, - struct i40e_dcbx_config *dcbcfg); +int i40e_set_dcb_config(struct i40e_hw *hw); +int i40e_dcb_config_to_lldp(u8 *lldpmib, u16 *miblen, + struct i40e_dcbx_config *dcbcfg); #endif /* _I40E_DCB_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index e32c61909b31..195421d863ab 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -135,8 +135,8 @@ static int i40e_dcbnl_ieee_setets(struct net_device *netdev, ret = i40e_hw_dcb_config(pf, &pf->tmp_cfg); if (ret) { dev_info(&pf->pdev->dev, - "Failed setting DCB ETS configuration err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed setting DCB ETS configuration err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } @@ -174,8 +174,8 @@ static int i40e_dcbnl_ieee_setpfc(struct net_device *netdev, ret = i40e_hw_dcb_config(pf, &pf->tmp_cfg); if (ret) { dev_info(&pf->pdev->dev, - "Failed setting DCB PFC configuration err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed setting DCB PFC configuration err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } @@ -225,8 +225,8 @@ static int i40e_dcbnl_ieee_setapp(struct net_device *netdev, ret = i40e_hw_dcb_config(pf, &pf->tmp_cfg); if (ret) { dev_info(&pf->pdev->dev, - "Failed setting DCB configuration err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed setting DCB configuration err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } @@ -290,8 +290,8 @@ static int i40e_dcbnl_ieee_delapp(struct net_device *netdev, ret = i40e_hw_dcb_config(pf, &pf->tmp_cfg); if (ret) { dev_info(&pf->pdev->dev, - "Failed setting DCB configuration err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed setting DCB configuration err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index e1069ae658ad..7e8183762fd9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -36,7 +36,7 @@ static int i40e_ddp_does_profile_exist(struct i40e_hw *hw, { struct i40e_ddp_profile_list *profile_list; u8 buff[I40E_PROFILE_LIST_SIZE]; - i40e_status status; + int status; int i; status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0, @@ -91,7 +91,7 @@ static int i40e_ddp_does_profile_overlap(struct i40e_hw *hw, { struct i40e_ddp_profile_list *profile_list; u8 buff[I40E_PROFILE_LIST_SIZE]; - i40e_status status; + int status; int i; status = i40e_aq_get_ddp_list(hw, buff, I40E_PROFILE_LIST_SIZE, 0, @@ -117,14 +117,14 @@ static int i40e_ddp_does_profile_overlap(struct i40e_hw *hw, * * Register a profile to the list of loaded profiles. */ -static enum i40e_status_code +static int i40e_add_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile, u8 *profile_info_sec, u32 track_id) { struct i40e_profile_section_header *sec; struct i40e_profile_info *pinfo; - i40e_status status; u32 offset = 0, info = 0; + int status; sec = (struct i40e_profile_section_header *)profile_info_sec; sec->tbl_size = 1; @@ -157,14 +157,14 @@ i40e_add_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile, * * Removes DDP profile from the NIC. **/ -static enum i40e_status_code +static int i40e_del_pinfo(struct i40e_hw *hw, struct i40e_profile_segment *profile, u8 *profile_info_sec, u32 track_id) { struct i40e_profile_section_header *sec; struct i40e_profile_info *pinfo; - i40e_status status; u32 offset = 0, info = 0; + int status; sec = (struct i40e_profile_section_header *)profile_info_sec; sec->tbl_size = 1; @@ -270,12 +270,12 @@ int i40e_ddp_load(struct net_device *netdev, const u8 *data, size_t size, struct i40e_profile_segment *profile_hdr; struct i40e_profile_info pinfo; struct i40e_package_header *pkg_hdr; - i40e_status status; struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; u32 track_id; int istatus; + int status; pkg_hdr = (struct i40e_package_header *)data; if (!i40e_ddp_is_pkg_hdr_valid(netdev, pkg_hdr, size)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index c9dcd6d92c83..9954493cd448 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -918,9 +918,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "deleting relay %d\n", veb_seid); i40e_veb_release(pf->veb[i]); } else if (strncmp(cmd_buf, "add pvid", 8) == 0) { - i40e_status ret; - u16 vid; unsigned int v; + int ret; + u16 vid; cnt = sscanf(&cmd_buf[8], "%i %u", &vsi_seid, &v); if (cnt != 2) { @@ -1284,7 +1284,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, } } else if (strncmp(cmd_buf, "send aq_cmd", 11) == 0) { struct i40e_aq_desc *desc; - i40e_status ret; + int ret; desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL); if (!desc) @@ -1330,9 +1330,9 @@ static ssize_t i40e_dbg_command_write(struct file *filp, desc = NULL; } else if (strncmp(cmd_buf, "send indirect aq_cmd", 20) == 0) { struct i40e_aq_desc *desc; - i40e_status ret; u16 buffer_len; u8 *buff; + int ret; desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL); if (!desc) diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index ef4d3762bf37..5b3519c6e362 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -10,8 +10,8 @@ * @reg: reg to be tested * @mask: bits to be touched **/ -static i40e_status i40e_diag_reg_pattern_test(struct i40e_hw *hw, - u32 reg, u32 mask) +static int i40e_diag_reg_pattern_test(struct i40e_hw *hw, + u32 reg, u32 mask) { static const u32 patterns[] = { 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF @@ -74,9 +74,9 @@ struct i40e_diag_reg_test_info i40e_reg_list[] = { * * Perform registers diagnostic test **/ -i40e_status i40e_diag_reg_test(struct i40e_hw *hw) +int i40e_diag_reg_test(struct i40e_hw *hw) { - i40e_status ret_code = 0; + int ret_code = 0; u32 reg, mask; u32 i, j; @@ -114,9 +114,9 @@ i40e_status i40e_diag_reg_test(struct i40e_hw *hw) * * Perform EEPROM diagnostic test **/ -i40e_status i40e_diag_eeprom_test(struct i40e_hw *hw) +int i40e_diag_eeprom_test(struct i40e_hw *hw) { - i40e_status ret_code; + int ret_code; u16 reg_val; /* read NVM control word and if NVM valid, validate EEPROM checksum*/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index c3340f320a18..e641035c7297 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -22,7 +22,7 @@ struct i40e_diag_reg_test_info { extern struct i40e_diag_reg_test_info i40e_reg_list[]; -i40e_status i40e_diag_reg_test(struct i40e_hw *hw); -i40e_status i40e_diag_eeprom_test(struct i40e_hw *hw); +int i40e_diag_reg_test(struct i40e_hw *hw); +int i40e_diag_eeprom_test(struct i40e_hw *hw); #endif /* _I40E_DIAG_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 887a735fe2a7..4934ff58332c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1226,8 +1226,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, struct i40e_vsi *vsi = np->vsi; struct i40e_hw *hw = &pf->hw; bool autoneg_changed = false; - i40e_status status = 0; int timeout = 50; + int status = 0; int err = 0; __u32 speed; u8 autoneg; @@ -1455,8 +1455,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, status = i40e_aq_set_phy_config(hw, &config, NULL); if (status) { netdev_info(netdev, - "Set phy config failed, err %s aq_err %s\n", - i40e_stat_str(hw, status), + "Set phy config failed, err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; goto done; @@ -1465,8 +1465,8 @@ static int i40e_set_link_ksettings(struct net_device *netdev, status = i40e_update_link_info(hw); if (status) netdev_dbg(netdev, - "Updating link info failed with err %s aq_err %s\n", - i40e_stat_str(hw, status), + "Updating link info failed with err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); } else { @@ -1485,7 +1485,7 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg) struct i40e_aq_get_phy_abilities_resp abilities; struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; - i40e_status status = 0; + int status = 0; u32 flags = 0; int err = 0; @@ -1517,8 +1517,8 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg) status = i40e_aq_set_phy_config(hw, &config, NULL); if (status) { netdev_info(netdev, - "Set phy config failed, err %s aq_err %s\n", - i40e_stat_str(hw, status), + "Set phy config failed, err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; goto done; @@ -1531,8 +1531,8 @@ static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg) * (e.g. no physical connection etc.) */ netdev_dbg(netdev, - "Updating link info failed with err %s aq_err %s\n", - i40e_stat_str(hw, status), + "Updating link info failed with err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); } @@ -1547,7 +1547,7 @@ static int i40e_get_fec_param(struct net_device *netdev, struct i40e_aq_get_phy_abilities_resp abilities; struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; - i40e_status status = 0; + int status = 0; int err = 0; u8 fec_cfg; @@ -1634,12 +1634,12 @@ static int i40e_nway_reset(struct net_device *netdev) struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; bool link_up = hw->phy.link_info.link_info & I40E_AQ_LINK_UP; - i40e_status ret = 0; + int ret = 0; ret = i40e_aq_set_link_restart_an(hw, link_up, NULL); if (ret) { - netdev_info(netdev, "link restart failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + netdev_info(netdev, "link restart failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return -EIO; } @@ -1699,9 +1699,9 @@ static int i40e_set_pauseparam(struct net_device *netdev, struct i40e_link_status *hw_link_info = &hw->phy.link_info; struct i40e_dcbx_config *dcbx_cfg = &hw->local_dcbx_config; bool link_up = hw_link_info->link_info & I40E_AQ_LINK_UP; - i40e_status status; u8 aq_failures; int err = 0; + int status; u32 is_an; /* Changing the port's flow control is not supported if this isn't the @@ -1755,20 +1755,20 @@ static int i40e_set_pauseparam(struct net_device *netdev, status = i40e_set_fc(hw, &aq_failures, link_up); if (aq_failures & I40E_SET_FC_AQ_FAIL_GET) { - netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %s aq_err %s\n", - i40e_stat_str(hw, status), + netdev_info(netdev, "Set fc failed on the get_phy_capabilities call with err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; } if (aq_failures & I40E_SET_FC_AQ_FAIL_SET) { - netdev_info(netdev, "Set fc failed on the set_phy_config call with err %s aq_err %s\n", - i40e_stat_str(hw, status), + netdev_info(netdev, "Set fc failed on the set_phy_config call with err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; } if (aq_failures & I40E_SET_FC_AQ_FAIL_UPDATE) { - netdev_info(netdev, "Set fc failed on the get_link_info call with err %s aq_err %s\n", - i40e_stat_str(hw, status), + netdev_info(netdev, "Set fc failed on the get_link_info call with err %pe aq_err %s\n", + ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); err = -EAGAIN; } @@ -2583,8 +2583,8 @@ static u64 i40e_link_test(struct net_device *netdev, u64 *data) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; - i40e_status status; bool link_up = false; + int status; netif_info(pf, hw, netdev, "link test\n"); status = i40e_get_link_status(&pf->hw, &link_up); @@ -2807,11 +2807,11 @@ static int i40e_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) { struct i40e_netdev_priv *np = netdev_priv(netdev); - i40e_status ret = 0; struct i40e_pf *pf = np->vsi->back; struct i40e_hw *hw = &pf->hw; int blink_freq = 2; u16 temp_status; + int ret = 0; switch (state) { case ETHTOOL_ID_ACTIVE: @@ -5247,7 +5247,7 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; u32 reset_needed = 0; - i40e_status status; + int status; u32 i, j; orig_flags = READ_ONCE(pf->flags); @@ -5362,8 +5362,8 @@ flags_complete: 0, NULL); if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) { dev_info(&pf->pdev->dev, - "couldn't set switch config bits, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't set switch config bits, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* not a fatal problem, just keep going */ @@ -5435,9 +5435,8 @@ flags_complete: return -EBUSY; default: dev_warn(&pf->pdev->dev, - "Starting FW LLDP agent failed: error: %s, %s\n", - i40e_stat_str(&pf->hw, - status), + "Starting FW LLDP agent failed: error: %pe, %s\n", + ERR_PTR(status), i40e_aq_str(&pf->hw, adq_err)); return -EINVAL; @@ -5477,8 +5476,8 @@ static int i40e_get_module_info(struct net_device *netdev, u32 sff8472_comp = 0; u32 sff8472_swap = 0; u32 sff8636_rev = 0; - i40e_status status; u32 type = 0; + int status; /* Check if firmware supports reading module EEPROM. */ if (!(hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE)) { @@ -5582,8 +5581,8 @@ static int i40e_get_module_eeprom(struct net_device *netdev, struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; bool is_sfp = false; - i40e_status status; u32 value = 0; + int status; int i; if (!ee || !ee->len || !data) @@ -5624,10 +5623,10 @@ static int i40e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp phy_cfg; - enum i40e_status_code status = 0; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; + int status = 0; /* Get initial PHY capabilities */ status = i40e_aq_get_phy_capabilities(hw, false, true, &phy_cfg, NULL); @@ -5689,11 +5688,11 @@ static int i40e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_aq_get_phy_abilities_resp abilities; - enum i40e_status_code status = I40E_SUCCESS; struct i40e_aq_set_phy_config config; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; + int status = I40E_SUCCESS; __le16 eee_capability; /* Deny parameters we don't support */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 163ee8c6311c..46f7950a0049 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -17,17 +17,17 @@ * @type: what type of segment descriptor we're manipulating * @direct_mode_sz: size to alloc in direct mode **/ -i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 sd_index, - enum i40e_sd_entry_type type, - u64 direct_mode_sz) +int i40e_add_sd_table_entry(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 sd_index, + enum i40e_sd_entry_type type, + u64 direct_mode_sz) { enum i40e_memory_type mem_type __attribute__((unused)); struct i40e_hmc_sd_entry *sd_entry; bool dma_mem_alloc_done = false; + int ret_code = I40E_SUCCESS; struct i40e_dma_mem mem; - i40e_status ret_code = I40E_SUCCESS; u64 alloc_len; if (NULL == hmc_info->sd_table.sd_entry) { @@ -106,19 +106,19 @@ exit: * aligned on 4K boundary and zeroed memory. * 2. It should be 4K in size. **/ -i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 pd_index, - struct i40e_dma_mem *rsrc_pg) +int i40e_add_pd_table_entry(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 pd_index, + struct i40e_dma_mem *rsrc_pg) { - i40e_status ret_code = 0; struct i40e_hmc_pd_table *pd_table; struct i40e_hmc_pd_entry *pd_entry; struct i40e_dma_mem mem; struct i40e_dma_mem *page = &mem; u32 sd_idx, rel_pd_idx; - u64 *pd_addr; + int ret_code = 0; u64 page_desc; + u64 *pd_addr; if (pd_index / I40E_HMC_PD_CNT_IN_SD >= hmc_info->sd_table.sd_cnt) { ret_code = I40E_ERR_INVALID_PAGE_DESC_INDEX; @@ -185,15 +185,15 @@ exit: * 1. Caller can deallocate the memory used by backing storage after this * function returns. **/ -i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx) +int i40e_remove_pd_bp(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx) { - i40e_status ret_code = 0; struct i40e_hmc_pd_entry *pd_entry; struct i40e_hmc_pd_table *pd_table; struct i40e_hmc_sd_entry *sd_entry; u32 sd_idx, rel_pd_idx; + int ret_code = 0; u64 *pd_addr; /* calculate index */ @@ -241,11 +241,11 @@ exit: * @hmc_info: pointer to the HMC configuration information structure * @idx: the page index **/ -i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, - u32 idx) +int i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, + u32 idx) { - i40e_status ret_code = 0; struct i40e_hmc_sd_entry *sd_entry; + int ret_code = 0; /* get the entry and decrease its ref counter */ sd_entry = &hmc_info->sd_table.sd_entry[idx]; @@ -269,9 +269,9 @@ exit: * @idx: the page index * @is_pf: used to distinguish between VF and PF **/ -i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf) +int i40e_remove_sd_bp_new(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx, bool is_pf) { struct i40e_hmc_sd_entry *sd_entry; @@ -290,11 +290,11 @@ i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw, * @hmc_info: pointer to the HMC configuration information structure * @idx: segment descriptor index to find the relevant page descriptor **/ -i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, - u32 idx) +int i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, + u32 idx) { - i40e_status ret_code = 0; struct i40e_hmc_sd_entry *sd_entry; + int ret_code = 0; sd_entry = &hmc_info->sd_table.sd_entry[idx]; @@ -318,9 +318,9 @@ exit: * @idx: segment descriptor index to find the relevant page descriptor * @is_pf: used to distinguish between VF and PF **/ -i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf) +int i40e_remove_pd_page_new(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx, bool is_pf) { struct i40e_hmc_sd_entry *sd_entry; diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h index 3113792afaff..9960da07a573 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h @@ -187,28 +187,28 @@ struct i40e_hmc_info { /* add one more to the limit to correct our range */ \ *(pd_limit) += 1; \ } -i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 sd_index, - enum i40e_sd_entry_type type, - u64 direct_mode_sz); - -i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 pd_index, - struct i40e_dma_mem *rsrc_pg); -i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); -i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); + +int i40e_add_sd_table_entry(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 sd_index, + enum i40e_sd_entry_type type, + u64 direct_mode_sz); +int i40e_add_pd_table_entry(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 pd_index, + struct i40e_dma_mem *rsrc_pg); +int i40e_remove_pd_bp(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx); +int i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, + u32 idx); +int i40e_remove_sd_bp_new(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx, bool is_pf); +int i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, + u32 idx); +int i40e_remove_pd_page_new(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx, bool is_pf); #endif /* _I40E_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index d6e92ecddfbd..40c101f286d1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -74,12 +74,12 @@ static u64 i40e_calculate_l2fpm_size(u32 txq_num, u32 rxq_num, * Assumptions: * - HMC Resource Profile has been selected before calling this function. **/ -i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, - u32 rxq_num, u32 fcoe_cntx_num, - u32 fcoe_filt_num) +int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, + u32 rxq_num, u32 fcoe_cntx_num, + u32 fcoe_filt_num) { struct i40e_hmc_obj_info *obj, *full_obj; - i40e_status ret_code = 0; + int ret_code = 0; u64 l2fpm_size; u32 size_exp; @@ -229,11 +229,11 @@ init_lan_hmc_out: * 1. caller can deallocate the memory used by pd after this function * returns. **/ -static i40e_status i40e_remove_pd_page(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx) +static int i40e_remove_pd_page(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx) { - i40e_status ret_code = 0; + int ret_code = 0; if (!i40e_prep_remove_pd_page(hmc_info, idx)) ret_code = i40e_remove_pd_page_new(hw, hmc_info, idx, true); @@ -256,11 +256,11 @@ static i40e_status i40e_remove_pd_page(struct i40e_hw *hw, * 1. caller can deallocate the memory used by backing storage after this * function returns. **/ -static i40e_status i40e_remove_sd_bp(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx) +static int i40e_remove_sd_bp(struct i40e_hw *hw, + struct i40e_hmc_info *hmc_info, + u32 idx) { - i40e_status ret_code = 0; + int ret_code = 0; if (!i40e_prep_remove_sd_bp(hmc_info, idx)) ret_code = i40e_remove_sd_bp_new(hw, hmc_info, idx, true); @@ -276,15 +276,15 @@ static i40e_status i40e_remove_sd_bp(struct i40e_hw *hw, * This will allocate memory for PDs and backing pages and populate * the sd and pd entries. **/ -static i40e_status i40e_create_lan_hmc_object(struct i40e_hw *hw, - struct i40e_hmc_lan_create_obj_info *info) +static int i40e_create_lan_hmc_object(struct i40e_hw *hw, + struct i40e_hmc_lan_create_obj_info *info) { - i40e_status ret_code = 0; struct i40e_hmc_sd_entry *sd_entry; u32 pd_idx1 = 0, pd_lmt1 = 0; u32 pd_idx = 0, pd_lmt = 0; bool pd_error = false; u32 sd_idx, sd_lmt; + int ret_code = 0; u64 sd_size; u32 i, j; @@ -435,13 +435,13 @@ exit: * - This function will be called after i40e_init_lan_hmc() and before * any LAN/FCoE HMC objects can be created. **/ -i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw, - enum i40e_hmc_model model) +int i40e_configure_lan_hmc(struct i40e_hw *hw, + enum i40e_hmc_model model) { struct i40e_hmc_lan_create_obj_info info; - i40e_status ret_code = 0; u8 hmc_fn_id = hw->hmc.hmc_fn_id; struct i40e_hmc_obj_info *obj; + int ret_code = 0; /* Initialize part of the create object info struct */ info.hmc_info = &hw->hmc; @@ -520,13 +520,13 @@ configure_lan_hmc_out: * caller should deallocate memory allocated previously for * book-keeping information about PDs and backing storage. **/ -static i40e_status i40e_delete_lan_hmc_object(struct i40e_hw *hw, - struct i40e_hmc_lan_delete_obj_info *info) +static int i40e_delete_lan_hmc_object(struct i40e_hw *hw, + struct i40e_hmc_lan_delete_obj_info *info) { - i40e_status ret_code = 0; struct i40e_hmc_pd_table *pd_table; u32 pd_idx, pd_lmt, rel_pd_idx; u32 sd_idx, sd_lmt; + int ret_code = 0; u32 i, j; if (NULL == info) { @@ -632,10 +632,10 @@ exit: * This must be called by drivers as they are shutting down and being * removed from the OS. **/ -i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw) +int i40e_shutdown_lan_hmc(struct i40e_hw *hw) { struct i40e_hmc_lan_delete_obj_info info; - i40e_status ret_code; + int ret_code; info.hmc_info = &hw->hmc; info.rsrc_type = I40E_HMC_LAN_FULL; @@ -915,9 +915,9 @@ static void i40e_write_qword(u8 *hmc_bits, * @context_bytes: pointer to the context bit array (DMA memory) * @hmc_type: the type of HMC resource **/ -static i40e_status i40e_clear_hmc_context(struct i40e_hw *hw, - u8 *context_bytes, - enum i40e_hmc_lan_rsrc_type hmc_type) +static int i40e_clear_hmc_context(struct i40e_hw *hw, + u8 *context_bytes, + enum i40e_hmc_lan_rsrc_type hmc_type) { /* clean the bit array */ memset(context_bytes, 0, (u32)hw->hmc.hmc_obj[hmc_type].size); @@ -931,9 +931,9 @@ static i40e_status i40e_clear_hmc_context(struct i40e_hw *hw, * @ce_info: a description of the struct to be filled * @dest: the struct to be filled **/ -static i40e_status i40e_set_hmc_context(u8 *context_bytes, - struct i40e_context_ele *ce_info, - u8 *dest) +static int i40e_set_hmc_context(u8 *context_bytes, + struct i40e_context_ele *ce_info, + u8 *dest) { int f; @@ -973,18 +973,18 @@ static i40e_status i40e_set_hmc_context(u8 *context_bytes, * base pointer. This function is used for LAN Queue contexts. **/ static -i40e_status i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base, - enum i40e_hmc_lan_rsrc_type rsrc_type, - u32 obj_idx) +int i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base, + enum i40e_hmc_lan_rsrc_type rsrc_type, + u32 obj_idx) { struct i40e_hmc_info *hmc_info = &hw->hmc; u32 obj_offset_in_sd, obj_offset_in_pd; struct i40e_hmc_sd_entry *sd_entry; struct i40e_hmc_pd_entry *pd_entry; u32 pd_idx, pd_lmt, rel_pd_idx; - i40e_status ret_code = 0; u64 obj_offset_in_fpm; u32 sd_idx, sd_lmt; + int ret_code = 0; if (NULL == hmc_info) { ret_code = I40E_ERR_BAD_PTR; @@ -1042,11 +1042,11 @@ exit: * @hw: the hardware struct * @queue: the queue we care about **/ -i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue) +int i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, + u16 queue) { - i40e_status err; u8 *context_bytes; + int err; err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_TX, queue); @@ -1062,12 +1062,12 @@ i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, * @queue: the queue we care about * @s: the struct to be filled **/ -i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_txq *s) +int i40e_set_lan_tx_queue_context(struct i40e_hw *hw, + u16 queue, + struct i40e_hmc_obj_txq *s) { - i40e_status err; u8 *context_bytes; + int err; err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_TX, queue); @@ -1083,11 +1083,11 @@ i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, * @hw: the hardware struct * @queue: the queue we care about **/ -i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue) +int i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, + u16 queue) { - i40e_status err; u8 *context_bytes; + int err; err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_RX, queue); @@ -1103,12 +1103,12 @@ i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, * @queue: the queue we care about * @s: the struct to be filled **/ -i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_rxq *s) +int i40e_set_lan_rx_queue_context(struct i40e_hw *hw, + u16 queue, + struct i40e_hmc_obj_rxq *s) { - i40e_status err; u8 *context_bytes; + int err; err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_RX, queue); diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h index c46a2c449e60..9f960404c2b3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h @@ -137,22 +137,22 @@ struct i40e_hmc_lan_delete_obj_info { u32 count; }; -i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, - u32 rxq_num, u32 fcoe_cntx_num, - u32 fcoe_filt_num); -i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw, - enum i40e_hmc_model model); -i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw); - -i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_txq *s); -i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_rxq *s); +int i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, + u32 rxq_num, u32 fcoe_cntx_num, + u32 fcoe_filt_num); +int i40e_configure_lan_hmc(struct i40e_hw *hw, + enum i40e_hmc_model model); +int i40e_shutdown_lan_hmc(struct i40e_hw *hw); + +int i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, + u16 queue); +int i40e_set_lan_tx_queue_context(struct i40e_hw *hw, + u16 queue, + struct i40e_hmc_obj_txq *s); +int i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, + u16 queue); +int i40e_set_lan_rx_queue_context(struct i40e_hw *hw, + u16 queue, + struct i40e_hmc_obj_rxq *s); #endif /* _I40E_LAN_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 43693f902c27..3667ad6493d6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1817,13 +1817,13 @@ static int i40e_set_mac(struct net_device *netdev, void *p) spin_unlock_bh(&vsi->mac_filter_hash_lock); if (vsi->type == I40E_VSI_MAIN) { - i40e_status ret; + int ret; ret = i40e_aq_mac_address_write(hw, I40E_AQC_WRITE_TYPE_LAA_WOL, addr->sa_data, NULL); if (ret) - netdev_info(netdev, "Ignoring error from firmware on LAA update, status %s, AQ ret %s\n", - i40e_stat_str(hw, ret), + netdev_info(netdev, "Ignoring error from firmware on LAA update, status %pe, AQ ret %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } @@ -1854,8 +1854,8 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, ret = i40e_aq_set_rss_key(hw, vsi->id, seed_dw); if (ret) { dev_info(&pf->pdev->dev, - "Cannot set RSS key, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Cannot set RSS key, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return ret; } @@ -1866,8 +1866,8 @@ static int i40e_config_rss_aq(struct i40e_vsi *vsi, const u8 *seed, ret = i40e_aq_set_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { dev_info(&pf->pdev->dev, - "Cannot set RSS lut, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Cannot set RSS lut, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return ret; } @@ -2349,7 +2349,7 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, { struct i40e_hw *hw = &vsi->back->hw; enum i40e_admin_queue_err aq_status; - i40e_status aq_ret; + int aq_ret; aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL, &aq_status); @@ -2358,8 +2358,8 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name, if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) { *retval = -EIO; dev_info(&vsi->back->pdev->dev, - "ignoring delete macvlan error on %s, err %s, aq_err %s\n", - vsi_name, i40e_stat_str(hw, aq_ret), + "ignoring delete macvlan error on %s, err %pe, aq_err %s\n", + vsi_name, ERR_PTR(aq_ret), i40e_aq_str(hw, aq_status)); } } @@ -2423,13 +2423,13 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, * * Returns status indicating success or failure; **/ -static i40e_status +static int i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_mac_filter *f) { bool enable = f->state == I40E_FILTER_NEW; struct i40e_hw *hw = &vsi->back->hw; - i40e_status aq_ret; + int aq_ret; if (f->vlan == I40E_VLAN_ANY) { aq_ret = i40e_aq_set_vsi_broadcast(hw, @@ -2468,7 +2468,7 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc) { struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; - i40e_status aq_ret; + int aq_ret; if (vsi->type == I40E_VSI_MAIN && pf->lan_veb != I40E_NO_VEB && @@ -2488,8 +2488,8 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc) NULL); if (aq_ret) { dev_info(&pf->pdev->dev, - "Set default VSI failed, err %s, aq_err %s\n", - i40e_stat_str(hw, aq_ret), + "Set default VSI failed, err %pe, aq_err %s\n", + ERR_PTR(aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } } else { @@ -2500,8 +2500,8 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc) true); if (aq_ret) { dev_info(&pf->pdev->dev, - "set unicast promisc failed, err %s, aq_err %s\n", - i40e_stat_str(hw, aq_ret), + "set unicast promisc failed, err %pe, aq_err %s\n", + ERR_PTR(aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } aq_ret = i40e_aq_set_vsi_multicast_promiscuous( @@ -2510,8 +2510,8 @@ static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc) promisc, NULL); if (aq_ret) { dev_info(&pf->pdev->dev, - "set multicast promisc failed, err %s, aq_err %s\n", - i40e_stat_str(hw, aq_ret), + "set multicast promisc failed, err %pe, aq_err %s\n", + ERR_PTR(aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } } @@ -2541,12 +2541,12 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) unsigned int vlan_filters = 0; char vsi_name[16] = "PF"; int filter_list_len = 0; - i40e_status aq_ret = 0; u32 changed_flags = 0; struct hlist_node *h; struct i40e_pf *pf; int num_add = 0; int num_del = 0; + int aq_ret = 0; int retval = 0; u16 cmd_flags; int list_size; @@ -2814,9 +2814,9 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) retval = i40e_aq_rc_to_posix(aq_ret, hw->aq.asq_last_status); dev_info(&pf->pdev->dev, - "set multi promisc failed on %s, err %s aq_err %s\n", + "set multi promisc failed on %s, err %pe aq_err %s\n", vsi_name, - i40e_stat_str(hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } else { dev_info(&pf->pdev->dev, "%s allmulti mode.\n", @@ -2834,10 +2834,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) retval = i40e_aq_rc_to_posix(aq_ret, hw->aq.asq_last_status); dev_info(&pf->pdev->dev, - "Setting promiscuous %s failed on %s, err %s aq_err %s\n", + "Setting promiscuous %s failed on %s, err %pe aq_err %s\n", cur_promisc ? "on" : "off", vsi_name, - i40e_stat_str(hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } } @@ -2965,7 +2965,7 @@ int i40e_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) void i40e_vlan_stripping_enable(struct i40e_vsi *vsi) { struct i40e_vsi_context ctxt; - i40e_status ret; + int ret; /* Don't modify stripping options if a port VLAN is active */ if (vsi->info.pvid) @@ -2985,8 +2985,8 @@ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi) ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, - "update vlan stripping failed, err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), + "update vlan stripping failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&vsi->back->hw, vsi->back->hw.aq.asq_last_status)); } @@ -2999,7 +2999,7 @@ void i40e_vlan_stripping_enable(struct i40e_vsi *vsi) void i40e_vlan_stripping_disable(struct i40e_vsi *vsi) { struct i40e_vsi_context ctxt; - i40e_status ret; + int ret; /* Don't modify stripping options if a port VLAN is active */ if (vsi->info.pvid) @@ -3020,8 +3020,8 @@ void i40e_vlan_stripping_disable(struct i40e_vsi *vsi) ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, - "update vlan stripping failed, err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), + "update vlan stripping failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&vsi->back->hw, vsi->back->hw.aq.asq_last_status)); } @@ -3252,7 +3252,7 @@ static void i40e_restore_vlan(struct i40e_vsi *vsi) int i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid) { struct i40e_vsi_context ctxt; - i40e_status ret; + int ret; vsi->info.valid_sections = cpu_to_le16(I40E_AQ_VSI_PROP_VLAN_VALID); vsi->info.pvid = cpu_to_le16(vid); @@ -3265,8 +3265,8 @@ int i40e_vsi_add_pvid(struct i40e_vsi *vsi, u16 vid) ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, - "add pvid failed, err %s aq_err %s\n", - i40e_stat_str(&vsi->back->hw, ret), + "add pvid failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&vsi->back->hw, vsi->back->hw.aq.asq_last_status)); return -ENOENT; @@ -3429,8 +3429,8 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) u16 pf_q = vsi->base_queue + ring->queue_index; struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_txq tx_ctx; - i40e_status err = 0; u32 qtx_ctl = 0; + int err = 0; if (ring_is_xdp(ring)) ring->xsk_pool = i40e_xsk_pool(ring); @@ -3554,7 +3554,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) u16 pf_q = vsi->base_queue + ring->queue_index; struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; - i40e_status err = 0; + int err = 0; bool ok; int ret; @@ -5525,16 +5525,16 @@ static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi) struct i40e_aqc_query_vsi_bw_config_resp bw_config = {0}; struct i40e_pf *pf = vsi->back; struct i40e_hw *hw = &pf->hw; - i40e_status ret; u32 tc_bw_max; + int ret; int i; /* Get the VSI level BW configuration */ ret = i40e_aq_query_vsi_bw_config(hw, vsi->seid, &bw_config, NULL); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi bw config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get PF vsi bw config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } @@ -5544,8 +5544,8 @@ static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi) NULL); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi ets bw config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get PF vsi ets bw config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EINVAL; } @@ -5586,7 +5586,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, { struct i40e_aqc_configure_vsi_tc_bw_data bw_data; struct i40e_pf *pf = vsi->back; - i40e_status ret; + int ret; int i; /* There is no need to reset BW when mqprio mode is on. */ @@ -5734,8 +5734,8 @@ int i40e_update_adq_vsi_queues(struct i40e_vsi *vsi, int vsi_offset) ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { - dev_info(&pf->pdev->dev, "Update vsi config failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + dev_info(&pf->pdev->dev, "Update vsi config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return ret; } @@ -5790,8 +5790,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) &bw_config, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Failed querying vsi bw info, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Failed querying vsi bw info, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); goto out; } @@ -5857,8 +5857,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Update vsi tc config failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Update vsi tc config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); goto out; } @@ -5870,8 +5870,8 @@ static int i40e_vsi_config_tc(struct i40e_vsi *vsi, u8 enabled_tc) ret = i40e_vsi_get_bw_info(vsi); if (ret) { dev_info(&pf->pdev->dev, - "Failed updating vsi bw info, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Failed updating vsi bw info, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); goto out; } @@ -5962,8 +5962,8 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate) I40E_MAX_BW_INACTIVE_ACCUM, NULL); if (ret) dev_err(&pf->pdev->dev, - "Failed set tx rate (%llu Mbps) for vsi->seid %u, err %s aq_err %s\n", - max_tx_rate, seid, i40e_stat_str(&pf->hw, ret), + "Failed set tx rate (%llu Mbps) for vsi->seid %u, err %pe aq_err %s\n", + max_tx_rate, seid, ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return ret; } @@ -6038,8 +6038,8 @@ static void i40e_remove_queue_channels(struct i40e_vsi *vsi) last_aq_status = pf->hw.aq.asq_last_status; if (ret) dev_info(&pf->pdev->dev, - "Failed to delete cloud filter, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed to delete cloud filter, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, last_aq_status)); kfree(cfilter); } @@ -6173,8 +6173,8 @@ static int i40e_vsi_reconfig_rss(struct i40e_vsi *vsi, u16 rss_size) ret = i40e_config_rss(vsi, seed, lut, vsi->rss_table_size); if (ret) { dev_info(&pf->pdev->dev, - "Cannot set RSS lut, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Cannot set RSS lut, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); kfree(lut); return ret; @@ -6272,8 +6272,8 @@ static int i40e_add_channel(struct i40e_pf *pf, u16 uplink_seid, ret = i40e_aq_add_vsi(hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "add new vsi failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "add new vsi failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -ENOENT; @@ -6304,7 +6304,7 @@ static int i40e_channel_config_bw(struct i40e_vsi *vsi, struct i40e_channel *ch, u8 *bw_share) { struct i40e_aqc_configure_vsi_tc_bw_data bw_data; - i40e_status ret; + int ret; int i; memset(&bw_data, 0, sizeof(bw_data)); @@ -6340,9 +6340,9 @@ static int i40e_channel_config_tx_ring(struct i40e_pf *pf, struct i40e_vsi *vsi, struct i40e_channel *ch) { - i40e_status ret; - int i; u8 bw_share[I40E_MAX_TRAFFIC_CLASS] = {0}; + int ret; + int i; /* Enable ETS TCs with equal BW Share for now across all VSIs */ for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { @@ -6518,8 +6518,8 @@ static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi) mode, NULL); if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH) dev_err(&pf->pdev->dev, - "couldn't set switch config bits, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "couldn't set switch config bits, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); @@ -6719,8 +6719,8 @@ int i40e_veb_config_tc(struct i40e_veb *veb, u8 enabled_tc) &bw_data, NULL); if (ret) { dev_info(&pf->pdev->dev, - "VEB bw config failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "VEB bw config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto out; } @@ -6729,8 +6729,8 @@ int i40e_veb_config_tc(struct i40e_veb *veb, u8 enabled_tc) ret = i40e_veb_get_bw_info(veb); if (ret) { dev_info(&pf->pdev->dev, - "Failed getting veb bw config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed getting veb bw config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -6813,8 +6813,8 @@ static int i40e_resume_port_tx(struct i40e_pf *pf) ret = i40e_aq_resume_port_tx(hw, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Resume Port Tx failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Resume Port Tx failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Schedule PF reset to recover */ set_bit(__I40E_PF_RESET_REQUESTED, pf->state); @@ -6838,8 +6838,8 @@ static int i40e_suspend_port_tx(struct i40e_pf *pf) ret = i40e_aq_suspend_port_tx(hw, pf->mac_seid, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Suspend Port Tx failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Suspend Port Tx failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Schedule PF reset to recover */ set_bit(__I40E_PF_RESET_REQUESTED, pf->state); @@ -6878,8 +6878,8 @@ static int i40e_hw_set_dcb_config(struct i40e_pf *pf, ret = i40e_set_dcb_config(&pf->hw); if (ret) { dev_info(&pf->pdev->dev, - "Set DCB Config failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Set DCB Config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto out; } @@ -6995,8 +6995,8 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg) i40e_aqc_opc_modify_switching_comp_ets, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Modify Port ETS failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Modify Port ETS failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto out; } @@ -7033,8 +7033,8 @@ int i40e_hw_dcb_config(struct i40e_pf *pf, struct i40e_dcbx_config *new_cfg) ret = i40e_aq_dcb_updated(&pf->hw, NULL); if (ret) { dev_info(&pf->pdev->dev, - "DCB Updated failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "DCB Updated failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto out; } @@ -7117,8 +7117,8 @@ int i40e_dcb_sw_default_config(struct i40e_pf *pf) i40e_aqc_opc_enable_switching_comp_ets, NULL); if (err) { dev_info(&pf->pdev->dev, - "Enable Port ETS failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + "Enable Port ETS failed, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); err = -ENOENT; goto out; @@ -7197,8 +7197,8 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) pf->flags |= I40E_FLAG_DISABLE_FW_LLDP; } else { dev_info(&pf->pdev->dev, - "Query for DCB configuration failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + "Query for DCB configuration failed, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -7416,15 +7416,15 @@ static void i40e_vsi_reinit_locked(struct i40e_vsi *vsi) * @pf: board private structure * @is_up: whether the link state should be forced up or down **/ -static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) +static int i40e_force_link_state(struct i40e_pf *pf, bool is_up) { struct i40e_aq_get_phy_abilities_resp abilities; struct i40e_aq_set_phy_config config = {0}; bool non_zero_phy_type = is_up; struct i40e_hw *hw = &pf->hw; - i40e_status err; u64 mask; u8 speed; + int err; /* Card might've been put in an unstable state by other drivers * and applications, which causes incorrect speed values being @@ -7436,8 +7436,8 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) NULL); if (err) { dev_err(&pf->pdev->dev, - "failed to get phy cap., ret = %s last_status = %s\n", - i40e_stat_str(hw, err), + "failed to get phy cap., ret = %pe last_status = %s\n", + ERR_PTR(err), i40e_aq_str(hw, hw->aq.asq_last_status)); return err; } @@ -7448,8 +7448,8 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) NULL); if (err) { dev_err(&pf->pdev->dev, - "failed to get phy cap., ret = %s last_status = %s\n", - i40e_stat_str(hw, err), + "failed to get phy cap., ret = %pe last_status = %s\n", + ERR_PTR(err), i40e_aq_str(hw, hw->aq.asq_last_status)); return err; } @@ -7493,8 +7493,8 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) if (err) { dev_err(&pf->pdev->dev, - "set phy config ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, err), + "set phy config ret = %pe last_status = %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return err; } @@ -7657,11 +7657,11 @@ static void i40e_vsi_set_default_tc_config(struct i40e_vsi *vsi) * This function deletes a mac filter on the channel VSI which serves as the * macvlan. Returns 0 on success. **/ -static i40e_status i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid, - const u8 *macaddr, int *aq_err) +static int i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid, + const u8 *macaddr, int *aq_err) { struct i40e_aqc_remove_macvlan_element_data element; - i40e_status status; + int status; memset(&element, 0, sizeof(element)); ether_addr_copy(element.mac_addr, macaddr); @@ -7683,12 +7683,12 @@ static i40e_status i40e_del_macvlan_filter(struct i40e_hw *hw, u16 seid, * This function adds a mac filter on the channel VSI which serves as the * macvlan. Returns 0 on success. **/ -static i40e_status i40e_add_macvlan_filter(struct i40e_hw *hw, u16 seid, - const u8 *macaddr, int *aq_err) +static int i40e_add_macvlan_filter(struct i40e_hw *hw, u16 seid, + const u8 *macaddr, int *aq_err) { struct i40e_aqc_add_macvlan_element_data element; - i40e_status status; u16 cmd_flags = 0; + int status; ether_addr_copy(element.mac_addr, macaddr); element.vlan_tag = 0; @@ -7834,8 +7834,8 @@ static int i40e_fwd_ring_up(struct i40e_vsi *vsi, struct net_device *vdev, rx_ring->netdev = NULL; } dev_info(&pf->pdev->dev, - "Error adding mac filter on macvlan err %s, aq_err %s\n", - i40e_stat_str(hw, ret), + "Error adding mac filter on macvlan err %pe, aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, aq_err)); netdev_err(vdev, "L2fwd offload disabled to L2 filter error\n"); } @@ -7907,8 +7907,8 @@ static int i40e_setup_macvlans(struct i40e_vsi *vsi, u16 macvlan_cnt, u16 qcnt, ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "Update vsi tc config failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + "Update vsi tc config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return ret; } @@ -8123,8 +8123,8 @@ static void i40e_fwd_del(struct net_device *netdev, void *vdev) ch->fwd = NULL; } else { dev_info(&pf->pdev->dev, - "Error deleting mac filter on macvlan err %s, aq_err %s\n", - i40e_stat_str(hw, ret), + "Error deleting mac filter on macvlan err %pe, aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, aq_err)); } break; @@ -8875,8 +8875,8 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi, kfree(filter); if (err) { dev_err(&pf->pdev->dev, - "Failed to delete cloud filter, err %s\n", - i40e_stat_str(&pf->hw, err)); + "Failed to delete cloud filter, err %pe\n", + ERR_PTR(err)); return i40e_aq_rc_to_posix(err, pf->hw.aq.asq_last_status); } @@ -9438,8 +9438,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf, pf->flags &= ~I40E_FLAG_DCB_CAPABLE; } else { dev_info(&pf->pdev->dev, - "Failed querying DCB configuration data from firmware, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed querying DCB configuration data from firmware, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -9887,8 +9887,8 @@ static void i40e_link_event(struct i40e_pf *pf) { struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; u8 new_link_speed, old_link_speed; - i40e_status status; bool new_link, old_link; + int status; #ifdef CONFIG_I40E_DCB int err; #endif /* CONFIG_I40E_DCB */ @@ -10099,9 +10099,9 @@ static void i40e_clean_adminq_subtask(struct i40e_pf *pf) struct i40e_arq_event_info event; struct i40e_hw *hw = &pf->hw; u16 pending, i = 0; - i40e_status ret; u16 opcode; u32 oldval; + int ret; u32 val; /* Do not run clean AQ when PF reset fails */ @@ -10265,8 +10265,8 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf) ret = i40e_aq_get_vsi_params(&pf->hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get PF vsi config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return; } @@ -10277,8 +10277,8 @@ static void i40e_enable_pf_switch_lb(struct i40e_pf *pf) ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "update vsi switch failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "update vsi switch failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } } @@ -10301,8 +10301,8 @@ static void i40e_disable_pf_switch_lb(struct i40e_pf *pf) ret = i40e_aq_get_vsi_params(&pf->hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get PF vsi config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return; } @@ -10313,8 +10313,8 @@ static void i40e_disable_pf_switch_lb(struct i40e_pf *pf) ret = i40e_aq_update_vsi_params(&vsi->back->hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "update vsi switch failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "update vsi switch failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } } @@ -10458,8 +10458,8 @@ static int i40e_get_capabilities(struct i40e_pf *pf, buf_len = data_size; } else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) { dev_info(&pf->pdev->dev, - "capability discovery failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + "capability discovery failed, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -ENODEV; @@ -10580,7 +10580,7 @@ static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid) struct i40e_cloud_filter *cfilter; struct i40e_pf *pf = vsi->back; struct hlist_node *node; - i40e_status ret; + int ret; /* Add cloud filters back if they exist */ hlist_for_each_entry_safe(cfilter, node, &pf->cloud_filter_list, @@ -10596,8 +10596,8 @@ static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid) if (ret) { dev_dbg(&pf->pdev->dev, - "Failed to rebuild cloud filter, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Failed to rebuild cloud filter, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return ret; @@ -10615,7 +10615,7 @@ static int i40e_rebuild_cloud_filters(struct i40e_vsi *vsi, u16 seid) static int i40e_rebuild_channels(struct i40e_vsi *vsi) { struct i40e_channel *ch, *ch_tmp; - i40e_status ret; + int ret; if (list_empty(&vsi->ch_list)) return 0; @@ -10691,7 +10691,7 @@ static void i40e_clean_xps_state(struct i40e_vsi *vsi) static void i40e_prep_for_reset(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - i40e_status ret = 0; + int ret = 0; u32 v; clear_bit(__I40E_RESET_INTR_RECEIVED, pf->state); @@ -10796,7 +10796,7 @@ static void i40e_get_oem_version(struct i40e_hw *hw) static int i40e_reset(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - i40e_status ret; + int ret; ret = i40e_pf_reset(hw); if (ret) { @@ -10821,7 +10821,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) const bool is_recovery_mode_reported = i40e_check_recovery_mode(pf); struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi]; struct i40e_hw *hw = &pf->hw; - i40e_status ret; + int ret; u32 val; int v; @@ -10837,8 +10837,8 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) /* rebuild the basics for the AdminQ, HMC, and initial HW switch */ ret = i40e_init_adminq(&pf->hw); if (ret) { - dev_info(&pf->pdev->dev, "Rebuild AdminQ failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + dev_info(&pf->pdev->dev, "Rebuild AdminQ failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto clear_recovery; } @@ -10949,8 +10949,8 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) I40E_AQ_EVENT_MEDIA_NA | I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL); if (ret) - dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + dev_info(&pf->pdev->dev, "set phy mask fail, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Rebuild the VSIs and VEBs that existed before reset. @@ -11053,8 +11053,8 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) msleep(75); ret = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (ret) - dev_info(&pf->pdev->dev, "link restart failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + dev_info(&pf->pdev->dev, "link restart failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -11082,9 +11082,9 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) ret = i40e_set_promiscuous(pf, pf->cur_promisc); if (ret) dev_warn(&pf->pdev->dev, - "Failed to restore promiscuous setting: %s, err %s aq_err %s\n", + "Failed to restore promiscuous setting: %s, err %pe aq_err %s\n", pf->cur_promisc ? "on" : "off", - i40e_stat_str(&pf->hw, ret), + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); i40e_reset_all_vfs(pf, true); @@ -12218,8 +12218,8 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, (struct i40e_aqc_get_set_rss_key_data *)seed); if (ret) { dev_info(&pf->pdev->dev, - "Cannot get RSS key, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Cannot get RSS key, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return ret; @@ -12232,8 +12232,8 @@ static int i40e_get_rss_aq(struct i40e_vsi *vsi, const u8 *seed, ret = i40e_aq_get_rss_lut(hw, vsi->id, pf_lut, lut, lut_size); if (ret) { dev_info(&pf->pdev->dev, - "Cannot get RSS lut, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Cannot get RSS lut, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return ret; @@ -12508,11 +12508,11 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count) * i40e_get_partition_bw_setting - Retrieve BW settings for this PF partition * @pf: board private structure **/ -i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf) +int i40e_get_partition_bw_setting(struct i40e_pf *pf) { - i40e_status status; bool min_valid, max_valid; u32 max_bw, min_bw; + int status; status = i40e_read_bw_from_alt_ram(&pf->hw, &max_bw, &min_bw, &min_valid, &max_valid); @@ -12531,10 +12531,10 @@ i40e_status i40e_get_partition_bw_setting(struct i40e_pf *pf) * i40e_set_partition_bw_setting - Set BW settings for this PF partition * @pf: board private structure **/ -i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf) +int i40e_set_partition_bw_setting(struct i40e_pf *pf) { struct i40e_aqc_configure_partition_bw_data bw_data; - i40e_status status; + int status; memset(&bw_data, 0, sizeof(bw_data)); @@ -12553,12 +12553,12 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf) * i40e_commit_partition_bw_setting - Commit BW settings for this PF partition * @pf: board private structure **/ -i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) +int i40e_commit_partition_bw_setting(struct i40e_pf *pf) { /* Commit temporary BW setting to permanent NVM image */ enum i40e_admin_queue_err last_aq_status; - i40e_status ret; u16 nvm_word; + int ret; if (pf->hw.partition_id != 1) { dev_info(&pf->pdev->dev, @@ -12573,8 +12573,8 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) last_aq_status = pf->hw.aq.asq_last_status; if (ret) { dev_info(&pf->pdev->dev, - "Cannot acquire NVM for read access, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Cannot acquire NVM for read access, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, last_aq_status)); goto bw_commit_out; } @@ -12590,8 +12590,8 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) last_aq_status = pf->hw.aq.asq_last_status; i40e_release_nvm(&pf->hw); if (ret) { - dev_info(&pf->pdev->dev, "NVM read error, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + dev_info(&pf->pdev->dev, "NVM read error, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, last_aq_status)); goto bw_commit_out; } @@ -12604,8 +12604,8 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) last_aq_status = pf->hw.aq.asq_last_status; if (ret) { dev_info(&pf->pdev->dev, - "Cannot acquire NVM for write access, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "Cannot acquire NVM for write access, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, last_aq_status)); goto bw_commit_out; } @@ -12624,8 +12624,8 @@ i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf) i40e_release_nvm(&pf->hw); if (ret) dev_info(&pf->pdev->dev, - "BW settings NOT SAVED, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "BW settings NOT SAVED, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, last_aq_status)); bw_commit_out: @@ -12646,7 +12646,7 @@ static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf) #define I40E_LINK_BEHAVIOR_WORD_LENGTH 0x1 #define I40E_LINK_BEHAVIOR_OS_FORCED_ENABLED BIT(0) #define I40E_LINK_BEHAVIOR_PORT_BIT_LENGTH 4 - i40e_status read_status = I40E_SUCCESS; + int read_status = I40E_SUCCESS; u16 sr_emp_sr_settings_ptr = 0; u16 features_enable = 0; u16 link_behavior = 0; @@ -12679,8 +12679,8 @@ static bool i40e_is_total_port_shutdown_enabled(struct i40e_pf *pf) err_nvm: dev_warn(&pf->pdev->dev, - "total-port-shutdown feature is off due to read nvm error: %s\n", - i40e_stat_str(&pf->hw, read_status)); + "total-port-shutdown feature is off due to read nvm error: %pe\n", + ERR_PTR(read_status)); return ret; } @@ -13025,7 +13025,7 @@ static int i40e_udp_tunnel_set_port(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_hw *hw = &np->vsi->back->hw; u8 type, filter_index; - i40e_status ret; + int ret; type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? I40E_AQC_TUNNEL_TYPE_VXLAN : I40E_AQC_TUNNEL_TYPE_NGE; @@ -13033,8 +13033,8 @@ static int i40e_udp_tunnel_set_port(struct net_device *netdev, ret = i40e_aq_add_udp_tunnel(hw, ntohs(ti->port), type, &filter_index, NULL); if (ret) { - netdev_info(netdev, "add UDP port failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + netdev_info(netdev, "add UDP port failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return -EIO; } @@ -13049,12 +13049,12 @@ static int i40e_udp_tunnel_unset_port(struct net_device *netdev, { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_hw *hw = &np->vsi->back->hw; - i40e_status ret; + int ret; ret = i40e_aq_del_udp_tunnel(hw, ti->hw_priv, NULL); if (ret) { - netdev_info(netdev, "delete UDP port failed, err %s aq_err %s\n", - i40e_stat_str(hw, ret), + netdev_info(netdev, "delete UDP port failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(hw, hw->aq.asq_last_status)); return -EIO; } @@ -13339,9 +13339,11 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, old_prog = xchg(&vsi->xdp_prog, prog); if (need_reset) { - if (!prog) + if (!prog) { + xdp_features_clear_redirect_target(vsi->netdev); /* Wait until ndo_xsk_wakeup completes. */ synchronize_rcu(); + } i40e_reset_and_rebuild(pf, true, true); } @@ -13362,11 +13364,13 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, /* Kick start the NAPI context if there is an AF_XDP socket open * on that queue id. This so that receiving will start. */ - if (need_reset && prog) + if (need_reset && prog) { for (i = 0; i < vsi->num_queue_pairs; i++) if (vsi->xdp_rings[i]->xsk_pool) (void)i40e_xsk_wakeup(vsi->netdev, i, XDP_WAKEUP_RX); + xdp_features_set_redirect_target(vsi->netdev, true); + } return 0; } @@ -13783,6 +13787,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->hw_enc_features |= NETIF_F_TSO_MANGLEID; netdev->features &= ~NETIF_F_HW_TC; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; if (vsi->type == I40E_VSI_MAIN) { SET_NETDEV_DEV(netdev, &pf->pdev->dev); @@ -13941,8 +13947,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) ctxt.flags = I40E_AQ_VSI_TYPE_PF; if (ret) { dev_info(&pf->pdev->dev, - "couldn't get PF vsi config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get PF vsi config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -ENOENT; @@ -13971,8 +13977,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "update vsi failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "update vsi failed, err %d aq_err %s\n", + ret, i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); ret = -ENOENT; @@ -13991,8 +13997,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) ret = i40e_aq_update_vsi_params(hw, &ctxt, NULL); if (ret) { dev_info(&pf->pdev->dev, - "update vsi failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "update vsi failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); ret = -ENOENT; @@ -14014,9 +14020,9 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) * message and continue */ dev_info(&pf->pdev->dev, - "failed to configure TCs for main VSI tc_map 0x%08x, err %s aq_err %s\n", + "failed to configure TCs for main VSI tc_map 0x%08x, err %pe aq_err %s\n", enabled_tc, - i40e_stat_str(&pf->hw, ret), + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -14110,8 +14116,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) ret = i40e_aq_add_vsi(hw, &ctxt, NULL); if (ret) { dev_info(&vsi->back->pdev->dev, - "add vsi failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "add vsi failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); ret = -ENOENT; @@ -14142,8 +14148,8 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) ret = i40e_vsi_get_bw_info(vsi); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get vsi bw info, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get vsi bw info, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* VSI is already added so not tearing that up */ ret = 0; @@ -14589,8 +14595,8 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb) &bw_data, NULL); if (ret) { dev_info(&pf->pdev->dev, - "query veb bw config failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "query veb bw config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, hw->aq.asq_last_status)); goto out; } @@ -14599,8 +14605,8 @@ static int i40e_veb_get_bw_info(struct i40e_veb *veb) &ets_data, NULL); if (ret) { dev_info(&pf->pdev->dev, - "query veb bw ets config failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "query veb bw ets config failed, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, hw->aq.asq_last_status)); goto out; } @@ -14796,8 +14802,8 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi) /* get a VEB from the hardware */ if (ret) { dev_info(&pf->pdev->dev, - "couldn't add VEB, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't add VEB, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EPERM; } @@ -14807,16 +14813,16 @@ static int i40e_add_veb(struct i40e_veb *veb, struct i40e_vsi *vsi) &veb->stats_idx, NULL, NULL, NULL); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get VEB statistics idx, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get VEB statistics idx, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return -EPERM; } ret = i40e_veb_get_bw_info(veb); if (ret) { dev_info(&pf->pdev->dev, - "couldn't get VEB bw info, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't get VEB bw info, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); i40e_aq_delete_element(&pf->hw, veb->seid, NULL); return -ENOENT; @@ -15026,8 +15032,8 @@ int i40e_fetch_switch_configuration(struct i40e_pf *pf, bool printconfig) &next_seid, NULL); if (ret) { dev_info(&pf->pdev->dev, - "get switch config failed err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "get switch config failed err %d aq_err %s\n", + ret, i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); kfree(aq_buf); @@ -15072,8 +15078,8 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui ret = i40e_fetch_switch_configuration(pf, false); if (ret) { dev_info(&pf->pdev->dev, - "couldn't fetch switch config, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't fetch switch config, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); return ret; } @@ -15099,8 +15105,8 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui NULL); if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) { dev_info(&pf->pdev->dev, - "couldn't set switch config bits, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, ret), + "couldn't set switch config bits, err %pe aq_err %s\n", + ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* not a fatal problem, just keep going */ @@ -15437,13 +15443,12 @@ static bool i40e_check_recovery_mode(struct i40e_pf *pf) * * Return 0 on success, negative on failure. **/ -static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf) +static int i40e_pf_loop_reset(struct i40e_pf *pf) { /* wait max 10 seconds for PF reset to succeed */ const unsigned long time_end = jiffies + 10 * HZ; - struct i40e_hw *hw = &pf->hw; - i40e_status ret; + int ret; ret = i40e_pf_reset(hw); while (ret != I40E_SUCCESS && time_before(jiffies, time_end)) { @@ -15489,9 +15494,9 @@ static bool i40e_check_fw_empr(struct i40e_pf *pf) * Return 0 if NIC is healthy or negative value when there are issues * with resets **/ -static i40e_status i40e_handle_resets(struct i40e_pf *pf) +static int i40e_handle_resets(struct i40e_pf *pf) { - const i40e_status pfr = i40e_pf_loop_reset(pf); + const int pfr = i40e_pf_loop_reset(pf); const bool is_empr = i40e_check_fw_empr(pf); if (is_empr || pfr != I40E_SUCCESS) @@ -15628,13 +15633,15 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct i40e_aq_get_phy_abilities_resp abilities; #ifdef CONFIG_I40E_DCB enum i40e_get_fw_lldp_status_resp lldp_status; - i40e_status status; #endif /* CONFIG_I40E_DCB */ struct i40e_pf *pf; struct i40e_hw *hw; static u16 pfs_found; u16 wol_nvm_bits; u16 link_status; +#ifdef CONFIG_I40E_DCB + int status; +#endif /* CONFIG_I40E_DCB */ int err; u32 val; u32 i; @@ -16002,8 +16009,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) I40E_AQ_EVENT_MEDIA_NA | I40E_AQ_EVENT_MODULE_QUAL_FAIL), NULL); if (err) - dev_info(&pf->pdev->dev, "set phy mask fail, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + dev_info(&pf->pdev->dev, "set phy mask fail, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* Reconfigure hardware for allowing smaller MSS in the case @@ -16021,8 +16028,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) msleep(75); err = i40e_aq_set_link_restart_an(&pf->hw, true, NULL); if (err) - dev_info(&pf->pdev->dev, "link restart failed, err %s aq_err %s\n", - i40e_stat_str(&pf->hw, err), + dev_info(&pf->pdev->dev, "link restart failed, err %pe aq_err %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); } @@ -16154,8 +16161,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* get the requested speeds from the fw */ err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); if (err) - dev_dbg(&pf->pdev->dev, "get requested speeds ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, err), + dev_dbg(&pf->pdev->dev, "get requested speeds ret = %pe last_status = %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); pf->hw.phy.link_info.requested_speeds = abilities.link_speed; @@ -16165,8 +16172,8 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* get the supported phy types from the fw */ err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL); if (err) - dev_dbg(&pf->pdev->dev, "get supported phy types ret = %s last_status = %s\n", - i40e_stat_str(&pf->hw, err), + dev_dbg(&pf->pdev->dev, "get supported phy types ret = %pe last_status = %s\n", + ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); /* make sure the MFS hasn't been set lower than the default */ @@ -16236,7 +16243,7 @@ static void i40e_remove(struct pci_dev *pdev) { struct i40e_pf *pf = pci_get_drvdata(pdev); struct i40e_hw *hw = &pf->hw; - i40e_status ret_code; + int ret_code; int i; i40e_dbg_pf_exit(pf); @@ -16483,9 +16490,9 @@ static void i40e_pci_error_resume(struct pci_dev *pdev) static void i40e_enable_mc_magic_wake(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - i40e_status ret; u8 mac_addr[6]; u16 flags = 0; + int ret; /* Get current MAC address in case it's an LAA */ if (pf->vsi[pf->lan_vsi] && pf->vsi[pf->lan_vsi]->netdev) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 3a38bf8bcde7..9da0c87f0328 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -13,10 +13,10 @@ * in this file) as an equivalent of the FLASH part mapped into the SR. * We are accessing FLASH always thru the Shadow RAM. **/ -i40e_status i40e_init_nvm(struct i40e_hw *hw) +int i40e_init_nvm(struct i40e_hw *hw) { struct i40e_nvm_info *nvm = &hw->nvm; - i40e_status ret_code = 0; + int ret_code = 0; u32 fla, gens; u8 sr_size; @@ -52,12 +52,12 @@ i40e_status i40e_init_nvm(struct i40e_hw *hw) * This function will request NVM ownership for reading * via the proper Admin Command. **/ -i40e_status i40e_acquire_nvm(struct i40e_hw *hw, - enum i40e_aq_resource_access_type access) +int i40e_acquire_nvm(struct i40e_hw *hw, + enum i40e_aq_resource_access_type access) { - i40e_status ret_code = 0; u64 gtime, timeout; u64 time_left = 0; + int ret_code = 0; if (hw->nvm.blank_nvm_mode) goto i40e_i40e_acquire_nvm_exit; @@ -111,7 +111,7 @@ i40e_i40e_acquire_nvm_exit: **/ void i40e_release_nvm(struct i40e_hw *hw) { - i40e_status ret_code = I40E_SUCCESS; + int ret_code = I40E_SUCCESS; u32 total_delay = 0; if (hw->nvm.blank_nvm_mode) @@ -138,9 +138,9 @@ void i40e_release_nvm(struct i40e_hw *hw) * * Polls the SRCTL Shadow RAM register done bit. **/ -static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) +static int i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) { - i40e_status ret_code = I40E_ERR_TIMEOUT; + int ret_code = I40E_ERR_TIMEOUT; u32 srctl, wait_cnt; /* Poll the I40E_GLNVM_SRCTL until the done bit is set */ @@ -165,10 +165,10 @@ static i40e_status i40e_poll_sr_srctl_done_bit(struct i40e_hw *hw) * * Reads one 16 bit word from the Shadow RAM using the GLNVM_SRCTL register. **/ -static i40e_status i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset, - u16 *data) +static int i40e_read_nvm_word_srctl(struct i40e_hw *hw, u16 offset, + u16 *data) { - i40e_status ret_code = I40E_ERR_TIMEOUT; + int ret_code = I40E_ERR_TIMEOUT; u32 sr_reg; if (offset >= hw->nvm.sr_size) { @@ -216,13 +216,13 @@ read_nvm_exit: * * Writes a 16 bit words buffer to the Shadow RAM using the admin command. **/ -static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, - u8 module_pointer, u32 offset, - u16 words, void *data, - bool last_command) +static int i40e_read_nvm_aq(struct i40e_hw *hw, + u8 module_pointer, u32 offset, + u16 words, void *data, + bool last_command) { - i40e_status ret_code = I40E_ERR_NVM; struct i40e_asq_cmd_details cmd_details; + int ret_code = I40E_ERR_NVM; memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; @@ -264,10 +264,10 @@ static i40e_status i40e_read_nvm_aq(struct i40e_hw *hw, * * Reads one 16 bit word from the Shadow RAM using the AdminQ **/ -static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, - u16 *data) +static int i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, + u16 *data) { - i40e_status ret_code = I40E_ERR_TIMEOUT; + int ret_code = I40E_ERR_TIMEOUT; ret_code = i40e_read_nvm_aq(hw, 0x0, offset, 1, data, true); *data = le16_to_cpu(*(__le16 *)data); @@ -286,8 +286,8 @@ static i40e_status i40e_read_nvm_word_aq(struct i40e_hw *hw, u16 offset, * Do not use this function except in cases where the nvm lock is already * taken via i40e_acquire_nvm(). **/ -static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, - u16 offset, u16 *data) +static int __i40e_read_nvm_word(struct i40e_hw *hw, + u16 offset, u16 *data) { if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) return i40e_read_nvm_word_aq(hw, offset, data); @@ -303,10 +303,10 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw, * * Reads one 16 bit word from the Shadow RAM. **/ -i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, - u16 *data) +int i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, + u16 *data) { - i40e_status ret_code = 0; + int ret_code = 0; if (hw->flags & I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK) ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); @@ -330,17 +330,17 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, * @words_data_size: Words to read from NVM * @data_ptr: Pointer to memory location where resulting buffer will be stored **/ -enum i40e_status_code i40e_read_nvm_module_data(struct i40e_hw *hw, - u8 module_ptr, - u16 module_offset, - u16 data_offset, - u16 words_data_size, - u16 *data_ptr) +int i40e_read_nvm_module_data(struct i40e_hw *hw, + u8 module_ptr, + u16 module_offset, + u16 data_offset, + u16 words_data_size, + u16 *data_ptr) { - i40e_status status; u16 specific_ptr = 0; u16 ptr_value = 0; u32 offset = 0; + int status; if (module_ptr != 0) { status = i40e_read_nvm_word(hw, module_ptr, &ptr_value); @@ -406,10 +406,10 @@ enum i40e_status_code i40e_read_nvm_module_data(struct i40e_hw *hw, * method. The buffer read is preceded by the NVM ownership take * and followed by the release. **/ -static i40e_status i40e_read_nvm_buffer_srctl(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data) +static int i40e_read_nvm_buffer_srctl(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data) { - i40e_status ret_code = 0; + int ret_code = 0; u16 index, word; /* Loop thru the selected region */ @@ -437,13 +437,13 @@ static i40e_status i40e_read_nvm_buffer_srctl(struct i40e_hw *hw, u16 offset, * method. The buffer read is preceded by the NVM ownership take * and followed by the release. **/ -static i40e_status i40e_read_nvm_buffer_aq(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data) +static int i40e_read_nvm_buffer_aq(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data) { - i40e_status ret_code; - u16 read_size; bool last_cmd = false; u16 words_read = 0; + u16 read_size; + int ret_code; u16 i = 0; do { @@ -493,9 +493,9 @@ read_nvm_buffer_aq_exit: * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd() * method. **/ -static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, - u16 offset, u16 *words, - u16 *data) +static int __i40e_read_nvm_buffer(struct i40e_hw *hw, + u16 offset, u16 *words, + u16 *data) { if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) return i40e_read_nvm_buffer_aq(hw, offset, words, data); @@ -514,10 +514,10 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, * method. The buffer read is preceded by the NVM ownership take * and followed by the release. **/ -i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data) +int i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data) { - i40e_status ret_code = 0; + int ret_code = 0; if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); @@ -544,12 +544,12 @@ i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, * * Writes a 16 bit words buffer to the Shadow RAM using the admin command. **/ -static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 words, void *data, - bool last_command) +static int i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 words, void *data, + bool last_command) { - i40e_status ret_code = I40E_ERR_NVM; struct i40e_asq_cmd_details cmd_details; + int ret_code = I40E_ERR_NVM; memset(&cmd_details, 0, sizeof(cmd_details)); cmd_details.wb_desc = &hw->nvm_wb_desc; @@ -594,14 +594,14 @@ static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, * is customer specific and unknown. Therefore, this function skips all maximum * possible size of VPD (1kB). **/ -static i40e_status i40e_calc_nvm_checksum(struct i40e_hw *hw, - u16 *checksum) +static int i40e_calc_nvm_checksum(struct i40e_hw *hw, + u16 *checksum) { - i40e_status ret_code; struct i40e_virt_mem vmem; u16 pcie_alt_module = 0; u16 checksum_local = 0; u16 vpd_module = 0; + int ret_code; u16 *data; u16 i = 0; @@ -675,11 +675,11 @@ i40e_calc_nvm_checksum_exit: * on ARQ completion event reception by caller. * This function will commit SR to NVM. **/ -i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw) +int i40e_update_nvm_checksum(struct i40e_hw *hw) { - i40e_status ret_code; - u16 checksum; __le16 le_sum; + int ret_code; + u16 checksum; ret_code = i40e_calc_nvm_checksum(hw, &checksum); if (!ret_code) { @@ -699,12 +699,12 @@ i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw) * Performs checksum calculation and validates the NVM SW checksum. If the * caller does not need checksum, the value can be NULL. **/ -i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, - u16 *checksum) +int i40e_validate_nvm_checksum(struct i40e_hw *hw, + u16 *checksum) { - i40e_status ret_code = 0; - u16 checksum_sr = 0; u16 checksum_local = 0; + u16 checksum_sr = 0; + int ret_code = 0; /* We must acquire the NVM lock in order to correctly synchronize the * NVM accesses across multiple PFs. Without doing so it is possible @@ -733,36 +733,36 @@ i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, return ret_code; } -static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); +static int i40e_nvmupd_state_init(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_state_reading(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_state_writing(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *errno); static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, int *perrno); -static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno); -static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); -static i40e_status i40e_nvmupd_get_aq_event(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno); +static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + int *perrno); +static int i40e_nvmupd_nvm_write(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_nvm_read(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); static inline u8 i40e_nvmupd_get_module(u32 val) { return (u8)(val & I40E_NVM_MOD_PNT_MASK); @@ -807,12 +807,12 @@ static const char * const i40e_nvm_update_state_str[] = { * * Dispatches command depending on what update state is current **/ -i40e_status i40e_nvmupd_command(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +int i40e_nvmupd_command(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - i40e_status status; enum i40e_nvmupd_cmd upd_cmd; + int status; /* assume success */ *perrno = 0; @@ -923,12 +923,12 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, * Process legitimate commands of the Init state and conditionally set next * state. Reject all other commands. **/ -static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_state_init(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; + int status = 0; upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); @@ -1062,12 +1062,12 @@ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, * NVM ownership is already held. Process legitimate commands and set any * change in state; reject all other commands. **/ -static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_state_reading(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; + int status = 0; upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); @@ -1104,13 +1104,13 @@ static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, * NVM ownership is already held. Process legitimate commands and set any * change in state; reject all other commands **/ -static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_state_writing(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; bool retry_attempt = false; + int status = 0; upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); @@ -1187,8 +1187,8 @@ retry: */ if (status && (hw->aq.asq_last_status == I40E_AQ_RC_EBUSY) && !retry_attempt) { - i40e_status old_status = status; u32 old_asq_status = hw->aq.asq_last_status; + int old_status = status; u32 gtime; gtime = rd32(hw, I40E_GLVFGEN_TIMER); @@ -1370,17 +1370,17 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, * * cmd structure contains identifiers and data buffer **/ -static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_exec_aq(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { struct i40e_asq_cmd_details cmd_details; - i40e_status status; struct i40e_aq_desc *aq_desc; u32 buff_size = 0; u8 *buff = NULL; u32 aq_desc_len; u32 aq_data_len; + int status; i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); if (cmd->offset == 0xffff) @@ -1429,8 +1429,8 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, buff_size, &cmd_details); if (status) { i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_exec_aq err %s aq_err %s\n", - i40e_stat_str(hw, status), + "%s err %pe aq_err %s\n", + __func__, ERR_PTR(status), i40e_aq_str(hw, hw->aq.asq_last_status)); *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); return status; @@ -1454,9 +1454,9 @@ static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, * * cmd structure contains identifiers and data buffer **/ -static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { u32 aq_total_len; u32 aq_desc_len; @@ -1523,9 +1523,9 @@ static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, * * cmd structure contains identifiers and data buffer **/ -static i40e_status i40e_nvmupd_get_aq_event(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { u32 aq_total_len; u32 aq_desc_len; @@ -1557,13 +1557,13 @@ static i40e_status i40e_nvmupd_get_aq_event(struct i40e_hw *hw, * * cmd structure contains identifiers and data buffer **/ -static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_nvm_read(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { struct i40e_asq_cmd_details cmd_details; - i40e_status status; u8 module, transaction; + int status; bool last; transaction = i40e_nvmupd_get_transaction(cmd->config); @@ -1596,13 +1596,13 @@ static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, * * module, offset, data_size and data are in cmd structure **/ -static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - int *perrno) +static int i40e_nvmupd_nvm_erase(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + int *perrno) { - i40e_status status = 0; struct i40e_asq_cmd_details cmd_details; u8 module, transaction; + int status = 0; bool last; transaction = i40e_nvmupd_get_transaction(cmd->config); @@ -1636,14 +1636,14 @@ static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, * * module, offset, data_size and data are in cmd structure **/ -static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *perrno) +static int i40e_nvmupd_nvm_write(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) { - i40e_status status = 0; struct i40e_asq_cmd_details cmd_details; u8 module, transaction; u8 preservation_flags; + int status = 0; bool last; transaction = i40e_nvmupd_get_transaction(cmd->config); diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h index 2f6815b2f8df..2bd4de03dafa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h @@ -56,5 +56,4 @@ do { \ (h)->bus.func, ##__VA_ARGS__); \ } while (0) -typedef enum i40e_status_code i40e_status; #endif /* _I40E_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 9a71121420c3..fe845987d99a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -16,29 +16,29 @@ */ /* adminq functions */ -i40e_status i40e_init_adminq(struct i40e_hw *hw); +int i40e_init_adminq(struct i40e_hw *hw); void i40e_shutdown_adminq(struct i40e_hw *hw); void i40e_adminq_init_ring_data(struct i40e_hw *hw); -i40e_status i40e_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *events_pending); -i40e_status +int i40e_clean_arq_element(struct i40e_hw *hw, + struct i40e_arq_event_info *e, + u16 *events_pending); +int i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details); -i40e_status +int i40e_asq_send_command_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, enum i40e_admin_queue_err *aq_status); -i40e_status +int i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ u16 buff_size, struct i40e_asq_cmd_details *cmd_details, bool is_atomic_context); -i40e_status +int i40e_asq_send_command_atomic_v2(struct i40e_hw *hw, struct i40e_aq_desc *desc, void *buff, /* can be NULL */ @@ -53,327 +53,332 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void i40e_idle_aq(struct i40e_hw *hw); bool i40e_check_asq_alive(struct i40e_hw *hw); -i40e_status i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); +int i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); -const char *i40e_stat_str(struct i40e_hw *hw, i40e_status stat_err); -i40e_status i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40e_aq_set_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40e_aq_get_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); -i40e_status i40e_aq_set_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); +int i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +int i40e_aq_set_rss_lut(struct i40e_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +int i40e_aq_get_rss_key(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); +int i40e_aq_set_rss_key(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); u32 i40e_led_get(struct i40e_hw *hw); void i40e_led_set(struct i40e_hw *hw, u32 mode, bool blink); -i40e_status i40e_led_set_phy(struct i40e_hw *hw, bool on, - u16 led_addr, u32 mode); -i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, - u16 *val); -i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); +int i40e_led_set_phy(struct i40e_hw *hw, bool on, + u16 led_addr, u32 mode); +int i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, + u16 *val); +int i40e_blink_phy_link_led(struct i40e_hw *hw, + u32 time, u32 interval); /* admin send queue commands */ -i40e_status i40e_aq_get_firmware_version(struct i40e_hw *hw, - u16 *fw_major_version, u16 *fw_minor_version, - u32 *fw_build, - u16 *api_major_version, u16 *api_minor_version, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_debug_write_register(struct i40e_hw *hw, - u32 reg_addr, u64 reg_val, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_debug_read_register(struct i40e_hw *hw, +int i40e_aq_get_firmware_version(struct i40e_hw *hw, + u16 *fw_major_version, u16 *fw_minor_version, + u32 *fw_build, + u16 *api_major_version, u16 *api_minor_version, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_debug_write_register(struct i40e_hw *hw, + u32 reg_addr, u64 reg_val, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_debug_read_register(struct i40e_hw *hw, u32 reg_addr, u64 *reg_val, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_clear_default_vsi(struct i40e_hw *hw, u16 vsi_id, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_aq_get_phy_capabilities(struct i40e_hw *hw, - bool qualified_modules, bool report_init, - struct i40e_aq_get_phy_abilities_resp *abilities, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, - struct i40e_aq_set_phy_config *config, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, - bool atomic_reset); -i40e_status i40e_aq_set_mac_loopback(struct i40e_hw *hw, - bool ena_lpbk, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_clear_pxe_mode(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_link_restart_an(struct i40e_hw *hw, - bool enable_link, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_link_info(struct i40e_hw *hw, - bool enable_lse, struct i40e_link_status *link, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_local_advt_reg(struct i40e_hw *hw, - u64 advt_reg, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_send_driver_version(struct i40e_hw *hw, +int i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_default_vsi(struct i40e_hw *hw, u16 vsi_id, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_clear_default_vsi(struct i40e_hw *hw, u16 vsi_id, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_phy_capabilities(struct i40e_hw *hw, + bool qualified_modules, bool report_init, + struct i40e_aq_get_phy_abilities_resp *abilities, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_phy_config(struct i40e_hw *hw, + struct i40e_aq_set_phy_config *config, + struct i40e_asq_cmd_details *cmd_details); +int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, + bool atomic_reset); +int i40e_aq_set_mac_loopback(struct i40e_hw *hw, + bool ena_lpbk, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_clear_pxe_mode(struct i40e_hw *hw, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_link_restart_an(struct i40e_hw *hw, + bool enable_link, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_link_info(struct i40e_hw *hw, + bool enable_lse, struct i40e_link_status *link, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_local_advt_reg(struct i40e_hw *hw, + u64 advt_reg, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_send_driver_version(struct i40e_hw *hw, struct i40e_driver_version *dv, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_add_vsi(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, - u16 vsi_id, bool set_filter, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, - u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details, - bool rx_only_promisc); -i40e_status i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, - u16 vsi_id, bool set, struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, - u16 vid, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, - u16 vid, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, - u16 seid, bool enable, u16 vid, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, - u16 seid, bool enable, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_vsi_params(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_update_vsi_params(struct i40e_hw *hw, - struct i40e_vsi_context *vsi_ctx, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, - u16 downlink_seid, u8 enabled_tc, - bool default_port, u16 *pveb_seid, - bool enable_stats, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_veb_parameters(struct i40e_hw *hw, - u16 veb_seid, u16 *switch_id, bool *floating, - u16 *statistic_index, u16 *vebs_used, - u16 *vebs_free, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id, +int i40e_aq_add_vsi(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw, + u16 vsi_id, bool set_filter, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, u16 vsi_id, bool set, + struct i40e_asq_cmd_details *cmd_details, + bool rx_only_promisc); +int i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw, u16 vsi_id, bool set, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, + u16 vid, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, + u16 vid, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw, + u16 seid, bool enable, u16 vid, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_vsi_vlan_promisc(struct i40e_hw *hw, + u16 seid, bool enable, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_vsi_params(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_update_vsi_params(struct i40e_hw *hw, + struct i40e_vsi_context *vsi_ctx, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid, + u16 downlink_seid, u8 enabled_tc, + bool default_port, u16 *pveb_seid, + bool enable_stats, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_veb_parameters(struct i40e_hw *hw, + u16 veb_seid, u16 *switch_id, bool *floating, + u16 *statistic_index, u16 *vebs_used, + u16 *vebs_free, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_add_macvlan(struct i40e_hw *hw, u16 vsi_id, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details); -i40e_status +int i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_add_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, enum i40e_admin_queue_err *aq_status); -i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id, - struct i40e_aqc_remove_macvlan_element_data *mv_list, - u16 count, struct i40e_asq_cmd_details *cmd_details); -i40e_status +int i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id, + struct i40e_aqc_remove_macvlan_element_data *mv_list, + u16 count, struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid, struct i40e_aqc_remove_macvlan_element_data *mv_list, u16 count, struct i40e_asq_cmd_details *cmd_details, enum i40e_admin_queue_err *aq_status); -i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rule_id, u16 *rules_used, u16 *rules_free); -i40e_status i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, - u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list, - struct i40e_asq_cmd_details *cmd_details, - u16 *rules_used, u16 *rules_free); +int i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, + u16 rule_type, u16 dest_vsi, u16 count, __le16 *mr_list, + struct i40e_asq_cmd_details *cmd_details, + u16 *rule_id, u16 *rules_used, u16 *rules_free); +int i40e_aq_delete_mirrorrule(struct i40e_hw *hw, u16 sw_seid, + u16 rule_type, u16 rule_id, u16 count, __le16 *mr_list, + struct i40e_asq_cmd_details *cmd_details, + u16 *rules_used, u16 *rules_free); -i40e_status i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, - u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_switch_config(struct i40e_hw *hw, - struct i40e_aqc_get_switch_config_resp *buf, - u16 buf_size, u16 *start_seid, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code i40e_aq_set_switch_config(struct i40e_hw *hw, - u16 flags, - u16 valid_flags, u8 mode, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_request_resource(struct i40e_hw *hw, - enum i40e_aq_resources_ids resource, - enum i40e_aq_resource_access_type access, - u8 sdp_number, u64 *timeout, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_release_resource(struct i40e_hw *hw, - enum i40e_aq_resources_ids resource, - u8 sdp_number, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, void *data, - bool last_command, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, bool last_command, +int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid, + u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_switch_config(struct i40e_hw *hw, + struct i40e_aqc_get_switch_config_resp *buf, + u16 buf_size, u16 *start_seid, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_discover_capabilities(struct i40e_hw *hw, - void *buff, u16 buff_size, u16 *data_size, - enum i40e_admin_queue_opc list_type_opc, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, - u32 offset, u16 length, void *data, - bool last_command, u8 preservation_flags, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw, - u8 rearrange_nvm, +int i40e_aq_set_switch_config(struct i40e_hw *hw, + u16 flags, + u16 valid_flags, u8 mode, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_request_resource(struct i40e_hw *hw, + enum i40e_aq_resources_ids resource, + enum i40e_aq_resource_access_type access, + u8 sdp_number, u64 *timeout, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_release_resource(struct i40e_hw *hw, + enum i40e_aq_resources_ids resource, + u8 sdp_number, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, void *data, + bool last_command, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, bool last_command, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_discover_capabilities(struct i40e_hw *hw, + void *buff, u16 buff_size, u16 *data_size, + enum i40e_admin_queue_opc list_type_opc, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, - u8 mib_type, void *buff, u16 buff_size, - u16 *local_len, u16 *remote_len, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code +int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer, + u32 offset, u16 length, void *data, + bool last_command, u8 preservation_flags, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_rearrange_nvm(struct i40e_hw *hw, + u8 rearrange_nvm, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type, + u8 mib_type, void *buff, u16 buff_size, + u16 *local_len, u16 *remote_len, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_lldp_mib(struct i40e_hw *hw, u8 mib_type, void *buff, u16 buff_size, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, - bool enable_update, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code +int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw, + bool enable_update, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_restore_lldp(struct i40e_hw *hw, u8 *setting, bool restore, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, - bool persist, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_set_dcb_parameters(struct i40e_hw *hw, - bool dcb_enable, - struct i40e_asq_cmd_details - *cmd_details); -i40e_status i40e_aq_start_lldp(struct i40e_hw *hw, bool persist, +int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, + bool persist, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_dcb_parameters(struct i40e_hw *hw, + bool dcb_enable, + struct i40e_asq_cmd_details + *cmd_details); +int i40e_aq_start_lldp(struct i40e_hw *hw, bool persist, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, + void *buff, u16 buff_size, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, - void *buff, u16 buff_size, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_add_udp_tunnel(struct i40e_hw *hw, - u16 udp_port, u8 protocol_index, - u8 *filter_index, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_mac_address_write(struct i40e_hw *hw, - u16 flags, u8 *mac_addr, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, +int i40e_aq_add_udp_tunnel(struct i40e_hw *hw, + u16 udp_port, u8 protocol_index, + u8 *filter_index, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_mac_address_write(struct i40e_hw *hw, + u16 flags, u8 *mac_addr, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw, u16 seid, u16 credit, u8 max_credit, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_dcb_updated(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_config_switch_comp_bw_limit(struct i40e_hw *hw, - u16 seid, u16 credit, u8 max_bw, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, u16 seid, - struct i40e_aqc_configure_vsi_tc_bw_data *bw_data, +int i40e_aq_dcb_updated(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_configure_switching_comp_ets_data *ets_data, - enum i40e_admin_queue_opc opcode, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_config_switch_comp_bw_config(struct i40e_hw *hw, +int i40e_aq_config_switch_comp_bw_limit(struct i40e_hw *hw, + u16 seid, u16 credit, u8 max_bw, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, u16 seid, + struct i40e_aqc_configure_vsi_tc_bw_data *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int +i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_configure_switching_comp_ets_data *ets_data, + enum i40e_admin_queue_opc opcode, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_config_switch_comp_bw_config(struct i40e_hw *hw, u16 seid, struct i40e_aqc_configure_switching_comp_bw_config_data *bw_data, struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_query_vsi_bw_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_vsi_bw_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_query_port_ets_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_port_ets_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_resume_port_tx(struct i40e_hw *hw, - struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code +int i40e_aq_query_vsi_bw_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_vsi_bw_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int +i40e_aq_query_vsi_ets_sla_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_vsi_ets_sla_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int +i40e_aq_query_switch_comp_ets_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_switching_comp_ets_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int +i40e_aq_query_port_ets_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_port_ets_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int +i40e_aq_query_switch_comp_bw_config(struct i40e_hw *hw, + u16 seid, + struct i40e_aqc_query_switching_comp_bw_config_resp *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_resume_port_tx(struct i40e_hw *hw, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_bb *filters, u8 filter_count); -enum i40e_status_code +int i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 vsi, struct i40e_aqc_cloud_filters_element_data *filters, u8 filter_count); -enum i40e_status_code +int i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 vsi, struct i40e_aqc_cloud_filters_element_data *filters, u8 filter_count); -enum i40e_status_code +int i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid, struct i40e_aqc_cloud_filters_element_bb *filters, u8 filter_count); -i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw, - struct i40e_lldp_variables *lldp_cfg); -enum i40e_status_code +int i40e_read_lldp_cfg(struct i40e_hw *hw, + struct i40e_lldp_variables *lldp_cfg); +int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid, struct i40e_asq_cmd_details *cmd_details); /* i40e_common */ -i40e_status i40e_init_shared_code(struct i40e_hw *hw); -i40e_status i40e_pf_reset(struct i40e_hw *hw); +int i40e_init_shared_code(struct i40e_hw *hw); +int i40e_pf_reset(struct i40e_hw *hw); void i40e_clear_hw(struct i40e_hw *hw); void i40e_clear_pxe_mode(struct i40e_hw *hw); -i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up); -i40e_status i40e_update_link_info(struct i40e_hw *hw); -i40e_status i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr); -i40e_status i40e_read_bw_from_alt_ram(struct i40e_hw *hw, - u32 *max_bw, u32 *min_bw, bool *min_valid, - bool *max_valid); -i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, - struct i40e_aqc_configure_partition_bw_data *bw_data, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr); -i40e_status i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, - u32 pba_num_size); -i40e_status i40e_validate_mac_addr(u8 *mac_addr); +int i40e_get_link_status(struct i40e_hw *hw, bool *link_up); +int i40e_update_link_info(struct i40e_hw *hw); +int i40e_get_mac_addr(struct i40e_hw *hw, u8 *mac_addr); +int i40e_read_bw_from_alt_ram(struct i40e_hw *hw, + u32 *max_bw, u32 *min_bw, bool *min_valid, + bool *max_valid); +int +i40e_aq_configure_partition_bw(struct i40e_hw *hw, + struct i40e_aqc_configure_partition_bw_data *bw_data, + struct i40e_asq_cmd_details *cmd_details); +int i40e_get_port_mac_addr(struct i40e_hw *hw, u8 *mac_addr); +int i40e_read_pba_string(struct i40e_hw *hw, u8 *pba_num, + u32 pba_num_size); +int i40e_validate_mac_addr(u8 *mac_addr); void i40e_pre_tx_queue_cfg(struct i40e_hw *hw, u32 queue, bool enable); /* prototype for functions used for NVM access */ -i40e_status i40e_init_nvm(struct i40e_hw *hw); -i40e_status i40e_acquire_nvm(struct i40e_hw *hw, - enum i40e_aq_resource_access_type access); +int i40e_init_nvm(struct i40e_hw *hw); +int i40e_acquire_nvm(struct i40e_hw *hw, + enum i40e_aq_resource_access_type access); void i40e_release_nvm(struct i40e_hw *hw); -i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, - u16 *data); -enum i40e_status_code i40e_read_nvm_module_data(struct i40e_hw *hw, - u8 module_ptr, - u16 module_offset, - u16 data_offset, - u16 words_data_size, - u16 *data_ptr); -i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, - u16 *words, u16 *data); -i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw); -i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, - u16 *checksum); -i40e_status i40e_nvmupd_command(struct i40e_hw *hw, - struct i40e_nvm_access *cmd, - u8 *bytes, int *); +int i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, + u16 *data); +int i40e_read_nvm_module_data(struct i40e_hw *hw, + u8 module_ptr, + u16 module_offset, + u16 data_offset, + u16 words_data_size, + u16 *data_ptr); +int i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data); +int i40e_update_nvm_checksum(struct i40e_hw *hw); +int i40e_validate_nvm_checksum(struct i40e_hw *hw, + u16 *checksum); +int i40e_nvmupd_command(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *errno); void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, struct i40e_aq_desc *desc); void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw); void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status); -i40e_status i40e_set_mac_type(struct i40e_hw *hw); +int i40e_set_mac_type(struct i40e_hw *hw); extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; @@ -422,41 +427,41 @@ i40e_virtchnl_link_speed(enum i40e_aq_link_speed link_speed) /* i40e_common for VF drivers*/ void i40e_vf_parse_hw_config(struct i40e_hw *hw, struct virtchnl_vf_resource *msg); -i40e_status i40e_vf_reset(struct i40e_hw *hw); -i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_set_filter_control(struct i40e_hw *hw, - struct i40e_filter_control_settings *settings); -i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, - u8 *mac_addr, u16 ethtype, u16 flags, - u16 vsi_seid, u16 queue, bool is_add, - struct i40e_control_filter_stats *stats, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, - u8 table_id, u32 start_index, u16 buff_size, - void *buff, u16 *ret_buff_size, - u8 *ret_next_table, u32 *ret_next_index, - struct i40e_asq_cmd_details *cmd_details); +int i40e_vf_reset(struct i40e_hw *hw); +int i40e_aq_send_msg_to_pf(struct i40e_hw *hw, + enum virtchnl_ops v_opcode, + int v_retval, + u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details); +int i40e_set_filter_control(struct i40e_hw *hw, + struct i40e_filter_control_settings *settings); +int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, + u8 *mac_addr, u16 ethtype, u16 flags, + u16 vsi_seid, u16 queue, bool is_add, + struct i40e_control_filter_stats *stats, + struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id, + u8 table_id, u32 start_index, u16 buff_size, + void *buff, u16 *ret_buff_size, + u8 *ret_next_table, u32 *ret_next_index, + struct i40e_asq_cmd_details *cmd_details); void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, u16 vsi_seid); -i40e_status i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw, + u32 reg_addr, u32 *reg_val, + struct i40e_asq_cmd_details *cmd_details); u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr); -i40e_status i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_rx_ctl_write_register(struct i40e_hw *hw, + u32 reg_addr, u32 reg_val, + struct i40e_asq_cmd_details *cmd_details); void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); -enum i40e_status_code +int i40e_aq_set_phy_register_ext(struct i40e_hw *hw, u8 phy_select, u8 dev_addr, bool page_change, bool set_mdio, u8 mdio_num, u32 reg_addr, u32 reg_val, struct i40e_asq_cmd_details *cmd_details); -enum i40e_status_code +int i40e_aq_get_phy_register_ext(struct i40e_hw *hw, u8 phy_select, u8 dev_addr, bool page_change, bool set_mdio, u8 mdio_num, @@ -469,43 +474,43 @@ i40e_aq_get_phy_register_ext(struct i40e_hw *hw, #define i40e_aq_get_phy_register(hw, ps, da, pc, ra, rv, cd) \ i40e_aq_get_phy_register_ext(hw, ps, da, pc, false, 0, ra, rv, cd) -i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, - u16 reg, u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, - u16 reg, u8 phy_addr, u16 value); -i40e_status i40e_read_phy_register_clause45(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register_clause45(struct i40e_hw *hw, - u8 page, u16 reg, u8 phy_addr, u16 value); -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 value); +int i40e_read_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 *value); +int i40e_write_phy_register_clause22(struct i40e_hw *hw, + u16 reg, u8 phy_addr, u16 value); +int i40e_read_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 *value); +int i40e_write_phy_register_clause45(struct i40e_hw *hw, + u8 page, u16 reg, u8 phy_addr, u16 value); +int i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 *value); +int i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, + u8 phy_addr, u16 value); u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); -i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); -i40e_status i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details * - cmd_details); -i40e_status i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details * - cmd_details); +int i40e_blink_phy_link_led(struct i40e_hw *hw, + u32 time, u32 interval); +int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, + u16 buff_size, u32 track_id, + u32 *error_offset, u32 *error_info, + struct i40e_asq_cmd_details * + cmd_details); +int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff, + u16 buff_size, u8 flags, + struct i40e_asq_cmd_details * + cmd_details); struct i40e_generic_seg_header * i40e_find_segment_in_package(u32 segment_type, struct i40e_package_header *pkg_header); struct i40e_profile_section_header * i40e_find_section_in_profile(u32 section_type, struct i40e_profile_segment *profile); -enum i40e_status_code +int i40e_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); -enum i40e_status_code +int i40e_rollback_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, u32 track_id); -enum i40e_status_code +int i40e_add_pinfo_to_list(struct i40e_hw *hw, struct i40e_profile_segment *profile, u8 *profile_info_sec, u32 track_id); diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h index db3714a65dc7..4d2782e76038 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_status.h +++ b/drivers/net/ethernet/intel/i40e/i40e_status.h @@ -9,65 +9,30 @@ enum i40e_status_code { I40E_SUCCESS = 0, I40E_ERR_NVM = -1, I40E_ERR_NVM_CHECKSUM = -2, - I40E_ERR_PHY = -3, I40E_ERR_CONFIG = -4, I40E_ERR_PARAM = -5, - I40E_ERR_MAC_TYPE = -6, I40E_ERR_UNKNOWN_PHY = -7, - I40E_ERR_LINK_SETUP = -8, - I40E_ERR_ADAPTER_STOPPED = -9, I40E_ERR_INVALID_MAC_ADDR = -10, I40E_ERR_DEVICE_NOT_SUPPORTED = -11, - I40E_ERR_PRIMARY_REQUESTS_PENDING = -12, - I40E_ERR_INVALID_LINK_SETTINGS = -13, - I40E_ERR_AUTONEG_NOT_COMPLETE = -14, I40E_ERR_RESET_FAILED = -15, - I40E_ERR_SWFW_SYNC = -16, I40E_ERR_NO_AVAILABLE_VSI = -17, I40E_ERR_NO_MEMORY = -18, I40E_ERR_BAD_PTR = -19, - I40E_ERR_RING_FULL = -20, - I40E_ERR_INVALID_PD_ID = -21, - I40E_ERR_INVALID_QP_ID = -22, - I40E_ERR_INVALID_CQ_ID = -23, - I40E_ERR_INVALID_CEQ_ID = -24, - I40E_ERR_INVALID_AEQ_ID = -25, I40E_ERR_INVALID_SIZE = -26, - I40E_ERR_INVALID_ARP_INDEX = -27, - I40E_ERR_INVALID_FPM_FUNC_ID = -28, - I40E_ERR_QP_INVALID_MSG_SIZE = -29, - I40E_ERR_QP_TOOMANY_WRS_POSTED = -30, - I40E_ERR_INVALID_FRAG_COUNT = -31, I40E_ERR_QUEUE_EMPTY = -32, - I40E_ERR_INVALID_ALIGNMENT = -33, - I40E_ERR_FLUSHED_QUEUE = -34, - I40E_ERR_INVALID_PUSH_PAGE_INDEX = -35, - I40E_ERR_INVALID_IMM_DATA_SIZE = -36, I40E_ERR_TIMEOUT = -37, - I40E_ERR_OPCODE_MISMATCH = -38, - I40E_ERR_CQP_COMPL_ERROR = -39, - I40E_ERR_INVALID_VF_ID = -40, - I40E_ERR_INVALID_HMCFN_ID = -41, - I40E_ERR_BACKING_PAGE_ERROR = -42, - I40E_ERR_NO_PBLCHUNKS_AVAILABLE = -43, - I40E_ERR_INVALID_PBLE_INDEX = -44, I40E_ERR_INVALID_SD_INDEX = -45, I40E_ERR_INVALID_PAGE_DESC_INDEX = -46, I40E_ERR_INVALID_SD_TYPE = -47, - I40E_ERR_MEMCPY_FAILED = -48, I40E_ERR_INVALID_HMC_OBJ_INDEX = -49, I40E_ERR_INVALID_HMC_OBJ_COUNT = -50, - I40E_ERR_INVALID_SRQ_ARM_LIMIT = -51, - I40E_ERR_SRQ_ENABLED = -52, I40E_ERR_ADMIN_QUEUE_ERROR = -53, I40E_ERR_ADMIN_QUEUE_TIMEOUT = -54, I40E_ERR_BUF_TOO_SHORT = -55, I40E_ERR_ADMIN_QUEUE_FULL = -56, I40E_ERR_ADMIN_QUEUE_NO_WORK = -57, - I40E_ERR_BAD_IWARP_CQE = -58, I40E_ERR_NVM_BLANK_MODE = -59, I40E_ERR_NOT_IMPLEMENTED = -60, - I40E_ERR_PE_DOORBELL_NOT_ENABLED = -61, I40E_ERR_DIAG_TEST_FAILED = -62, I40E_ERR_NOT_READY = -63, I40E_NOT_SUPPORTED = -64, diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8fa0f0c12fde..8a4587585acd 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -17,7 +17,7 @@ **/ static void i40e_vc_vf_broadcast(struct i40e_pf *pf, enum virtchnl_ops v_opcode, - i40e_status v_retval, u8 *msg, + int v_retval, u8 *msg, u16 msglen) { struct i40e_hw *hw = &pf->hw; @@ -1247,13 +1247,13 @@ err: * @vl: List of VLANs - apply filter for given VLANs * @num_vlans: Number of elements in @vl **/ -static i40e_status +static int i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, bool unicast_enable, s16 *vl, u16 num_vlans) { - i40e_status aq_ret, aq_tmp = 0; struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; + int aq_ret, aq_tmp = 0; int i; /* No VLAN to set promisc on, set on VSI */ @@ -1265,9 +1265,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, int aq_err = pf->hw.aq.asq_last_status; dev_err(&pf->pdev->dev, - "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n", + "VF %d failed to set multicast promiscuous mode err %pe aq_err %s\n", vf->vf_id, - i40e_stat_str(&pf->hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, aq_err)); return aq_ret; @@ -1281,9 +1281,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, int aq_err = pf->hw.aq.asq_last_status; dev_err(&pf->pdev->dev, - "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n", + "VF %d failed to set unicast promiscuous mode err %pe aq_err %s\n", vf->vf_id, - i40e_stat_str(&pf->hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, aq_err)); } @@ -1298,9 +1298,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, int aq_err = pf->hw.aq.asq_last_status; dev_err(&pf->pdev->dev, - "VF %d failed to set multicast promiscuous mode err %s aq_err %s\n", + "VF %d failed to set multicast promiscuous mode err %pe aq_err %s\n", vf->vf_id, - i40e_stat_str(&pf->hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, aq_err)); if (!aq_tmp) @@ -1314,9 +1314,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, int aq_err = pf->hw.aq.asq_last_status; dev_err(&pf->pdev->dev, - "VF %d failed to set unicast promiscuous mode err %s aq_err %s\n", + "VF %d failed to set unicast promiscuous mode err %pe aq_err %s\n", vf->vf_id, - i40e_stat_str(&pf->hw, aq_ret), + ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, aq_err)); if (!aq_tmp) @@ -1340,13 +1340,13 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, * Called from the VF to configure the promiscuous mode of * VF vsis and from the VF reset path to reset promiscuous mode. **/ -static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, - u16 vsi_id, - bool allmulti, - bool alluni) +static int i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, + u16 vsi_id, + bool allmulti, + bool alluni) { - i40e_status aq_ret = I40E_SUCCESS; struct i40e_pf *pf = vf->pf; + int aq_ret = I40E_SUCCESS; struct i40e_vsi *vsi; u16 num_vlans; s16 *vl; @@ -1956,7 +1956,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, struct i40e_pf *pf; struct i40e_hw *hw; int abs_vf_id; - i40e_status aq_ret; + int aq_ret; /* validate the request */ if (!vf || vf->vf_id >= vf->pf->num_alloc_vfs) @@ -1988,7 +1988,7 @@ static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, **/ static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf, enum virtchnl_ops opcode, - i40e_status retval) + int retval) { return i40e_vc_send_msg_to_vf(vf, opcode, retval, NULL, 0); } @@ -2092,9 +2092,9 @@ static int i40e_vc_get_vf_resources_msg(struct i40e_vf *vf, u8 *msg) { struct virtchnl_vf_resource *vfres = NULL; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; struct i40e_vsi *vsi; int num_vsis = 1; + int aq_ret = 0; size_t len = 0; int ret; @@ -2222,9 +2222,9 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_promisc_info *info = (struct virtchnl_promisc_info *)msg; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; bool allmulti = false; bool alluni = false; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -2309,10 +2309,10 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_queue_pair_info *qpi; u16 vsi_id, vsi_queue_id = 0; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; int i, j = 0, idx = 0; struct i40e_vsi *vsi; u16 num_qps_all = 0; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -2459,8 +2459,8 @@ static int i40e_vc_config_irq_map_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_irq_map_info *irqmap_info = (struct virtchnl_irq_map_info *)msg; struct virtchnl_vector_map *map; + int aq_ret = 0; u16 vsi_id; - i40e_status aq_ret = 0; int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { @@ -2575,7 +2575,7 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; + int aq_ret = 0; int i; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { @@ -2633,7 +2633,7 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct virtchnl_queue_select *vqs = (struct virtchnl_queue_select *)msg; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -2784,7 +2784,7 @@ static int i40e_vc_get_stats_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_queue_select *)msg; struct i40e_pf *pf = vf->pf; struct i40e_eth_stats stats; - i40e_status aq_ret = 0; + int aq_ret = 0; struct i40e_vsi *vsi; memset(&stats, 0, sizeof(struct i40e_eth_stats)); @@ -2927,7 +2927,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_ether_addr_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status ret = 0; + int ret = 0; int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || @@ -2999,7 +2999,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) bool was_unimac_deleted = false; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status ret = 0; + int ret = 0; int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || @@ -3072,7 +3072,7 @@ static int i40e_vc_add_vlan_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_vlan_filter_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status aq_ret = 0; + int aq_ret = 0; int i; if ((vf->num_vlan >= I40E_VC_MAX_VLAN_PER_VF) && @@ -3143,7 +3143,7 @@ static int i40e_vc_remove_vlan_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_vlan_filter_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status aq_ret = 0; + int aq_ret = 0; int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || @@ -3199,7 +3199,7 @@ static int i40e_vc_rdma_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) { struct i40e_pf *pf = vf->pf; int abs_vf_id = vf->vf_id + pf->hw.func_caps.vf_base_id; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) { @@ -3228,7 +3228,7 @@ static int i40e_vc_rdma_qvmap_msg(struct i40e_vf *vf, u8 *msg, bool config) { struct virtchnl_rdma_qvlist_info *qvlist_info = (struct virtchnl_rdma_qvlist_info *)msg; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) || !test_bit(I40E_VF_STATE_RDMAENA, &vf->vf_states)) { @@ -3264,7 +3264,7 @@ static int i40e_vc_config_rss_key(struct i40e_vf *vf, u8 *msg) (struct virtchnl_rss_key *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || !i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) || @@ -3294,7 +3294,7 @@ static int i40e_vc_config_rss_lut(struct i40e_vf *vf, u8 *msg) (struct virtchnl_rss_lut *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status aq_ret = 0; + int aq_ret = 0; u16 i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) || @@ -3329,7 +3329,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg) { struct virtchnl_rss_hena *vrh = NULL; struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; + int aq_ret = 0; int len = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { @@ -3366,7 +3366,7 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg) (struct virtchnl_rss_hena *)msg; struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -3390,8 +3390,8 @@ err: **/ static int i40e_vc_enable_vlan_stripping(struct i40e_vf *vf, u8 *msg) { - i40e_status aq_ret = 0; struct i40e_vsi *vsi; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -3416,8 +3416,8 @@ err: **/ static int i40e_vc_disable_vlan_stripping(struct i40e_vf *vf, u8 *msg) { - i40e_status aq_ret = 0; struct i40e_vsi *vsi; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; @@ -3616,8 +3616,8 @@ static void i40e_del_all_cloud_filters(struct i40e_vf *vf) ret = i40e_add_del_cloud_filter(vsi, cfilter, false); if (ret) dev_err(&pf->pdev->dev, - "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", - vf->vf_id, i40e_stat_str(&pf->hw, ret), + "VF %d: Failed to delete cloud filter, err %pe aq_err %s\n", + vf->vf_id, ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); @@ -3643,7 +3643,7 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; struct hlist_node *node; - i40e_status aq_ret = 0; + int aq_ret = 0; int i, ret; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { @@ -3719,8 +3719,8 @@ static int i40e_vc_del_cloud_filter(struct i40e_vf *vf, u8 *msg) ret = i40e_add_del_cloud_filter(vsi, &cfilter, false); if (ret) { dev_err(&pf->pdev->dev, - "VF %d: Failed to delete cloud filter, err %s aq_err %s\n", - vf->vf_id, i40e_stat_str(&pf->hw, ret), + "VF %d: Failed to delete cloud filter, err %pe aq_err %s\n", + vf->vf_id, ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto err; } @@ -3774,7 +3774,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) struct i40e_cloud_filter *cfilter = NULL; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - i40e_status aq_ret = 0; + int aq_ret = 0; int i, ret; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { @@ -3853,8 +3853,8 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) ret = i40e_add_del_cloud_filter(vsi, cfilter, true); if (ret) { dev_err(&pf->pdev->dev, - "VF %d: Failed to add cloud filter, err %s aq_err %s\n", - vf->vf_id, i40e_stat_str(&pf->hw, ret), + "VF %d: Failed to add cloud filter, err %pe aq_err %s\n", + vf->vf_id, ERR_PTR(ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto err_free; } @@ -3883,7 +3883,7 @@ static int i40e_vc_add_qch_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; struct i40e_link_status *ls = &pf->hw.phy.link_info; int i, adq_request_qps = 0; - i40e_status aq_ret = 0; + int aq_ret = 0; u64 speed = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { @@ -3995,7 +3995,7 @@ err: static int i40e_vc_del_qch_msg(struct i40e_vf *vf, u8 *msg) { struct i40e_pf *pf = vf->pf; - i40e_status aq_ret = 0; + int aq_ret = 0; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = I40E_ERR_PARAM; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 23bc000e77b8..232bc61d9eee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -30,6 +30,7 @@ #include <linux/jiffies.h> #include <net/ip6_checksum.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/udp.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 3d26ff4122e0..7bd50e49312c 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -41,6 +41,7 @@ #include <linux/dim.h> #include <linux/gnss.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_gact.h> #include <net/ip.h> @@ -353,7 +354,6 @@ struct ice_vsi { struct ice_vf *vf; /* VF associated with this VSI */ - u16 ethtype; /* Ethernet protocol for pause frame */ u16 num_gfltr; u16 num_bfltr; @@ -889,7 +889,7 @@ ice_fetch_u64_stats_per_ring(struct u64_stats_sync *syncp, int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); int ice_down_up(struct ice_vsi *vsi); -int ice_vsi_cfg(struct ice_vsi *vsi); +int ice_vsi_cfg_lan(struct ice_vsi *vsi); struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi); int ice_vsi_determine_xdp_res(struct ice_vsi *vsi); int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog); @@ -907,6 +907,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); +void ice_deinit_rdma(struct ice_pf *pf); const char *ice_aq_str(enum ice_aq_err aq_err); bool ice_is_wol_supported(struct ice_hw *hw); void ice_fdir_del_all_fltrs(struct ice_vsi *vsi); @@ -931,6 +932,8 @@ int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +int ice_load(struct ice_pf *pf); +void ice_unload(struct ice_pf *pf); /** * ice_set_rdma_cap - enable RDMA support diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 554095b25f44..1911d644dfa8 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -355,9 +355,6 @@ static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) { if (ice_ring_uses_build_skb(rx_ring)) return ICE_SKB_PAD; - else if (ice_is_xdp_ena_vsi(rx_ring->vsi)) - return XDP_PACKET_HEADROOM; - return 0; } @@ -495,7 +492,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); - u16 num_bufs = ICE_DESC_UNUSED(ring); + u32 num_bufs = ICE_RX_DESC_UNUSED(ring); int err; ring->rx_buf_len = ring->vsi->rx_buf_len; @@ -503,8 +500,10 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (ring->vsi->type == ICE_VSI_PF) { if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ - xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, ring->q_vector->napi.napi_id); + __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->vsi->rx_buf_len); ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { @@ -524,9 +523,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } else { if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ - xdp_rxq_info_reg(&ring->xdp_rxq, - ring->netdev, - ring->q_index, ring->q_vector->napi.napi_id); + __xdp_rxq_info_reg(&ring->xdp_rxq, + ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->vsi->rx_buf_len); err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, @@ -536,6 +537,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } } + xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq); + ring->xdp.data = NULL; err = ice_setup_rx_ctx(ring); if (err) { dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index f5842ff42bc7..1b79bb0a4fcd 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1088,8 +1088,10 @@ int ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_cqinit; - hw->port_info = devm_kzalloc(ice_hw_to_dev(hw), - sizeof(*hw->port_info), GFP_KERNEL); + if (!hw->port_info) + hw->port_info = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*hw->port_info), + GFP_KERNEL); if (!hw->port_info) { status = -ENOMEM; goto err_unroll_cqinit; @@ -1217,11 +1219,6 @@ void ice_deinit_hw(struct ice_hw *hw) ice_free_hw_tbls(hw); mutex_destroy(&hw->tnl_lock); - if (hw->port_info) { - devm_kfree(ice_hw_to_dev(hw), hw->port_info); - hw->port_info = NULL; - } - /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); ice_destroy_all_ctrlq(hw); @@ -5537,7 +5534,7 @@ bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw) * returned by the firmware is a 16 bit * value, but is indexed * by [fls(speed) - 1] */ -static const u32 ice_aq_to_link_speed[15] = { +static const u32 ice_aq_to_link_speed[] = { SPEED_10, /* BIT(0) */ SPEED_100, SPEED_1000, @@ -5549,10 +5546,6 @@ static const u32 ice_aq_to_link_speed[15] = { SPEED_40000, SPEED_50000, SPEED_100000, /* BIT(10) */ - 0, - 0, - 0, - 0 /* BIT(14) */ }; /** @@ -5563,5 +5556,8 @@ static const u32 ice_aq_to_link_speed[15] = { */ u32 ice_get_link_speed(u16 index) { + if (index >= ARRAY_SIZE(ice_aq_to_link_speed)) + return 0; + return ice_aq_to_link_speed[index]; } diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 88497363fc4c..63acb7b96053 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -371,10 +371,7 @@ out_free_ctx: /** * ice_devlink_reload_empr_start - Start EMP reset to activate new firmware - * @devlink: pointer to the devlink instance to reload - * @netns_change: if true, the network namespace is changing - * @action: the action to perform. Must be DEVLINK_RELOAD_ACTION_FW_ACTIVATE - * @limit: limits on what reload should do, such as not resetting + * @pf: pointer to the pf instance * @extack: netlink extended ACK structure * * Allow user to activate new Embedded Management Processor firmware by @@ -387,12 +384,9 @@ out_free_ctx: * any source. */ static int -ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, - enum devlink_reload_action action, - enum devlink_reload_limit limit, +ice_devlink_reload_empr_start(struct ice_pf *pf, struct netlink_ext_ack *extack) { - struct ice_pf *pf = devlink_priv(devlink); struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; u8 pending; @@ -431,11 +425,51 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, } /** + * ice_devlink_reload_down - prepare for reload + * @devlink: pointer to the devlink instance to reload + * @netns_change: if true, the network namespace is changing + * @action: the action to perform + * @limit: limits on what reload should do, such as not resetting + * @extack: netlink extended ACK structure + */ +static int +ice_devlink_reload_down(struct devlink *devlink, bool netns_change, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: + if (ice_is_eswitch_mode_switchdev(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Go to legacy mode before doing reinit\n"); + return -EOPNOTSUPP; + } + if (ice_is_adq_active(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Turn off ADQ before doing reinit\n"); + return -EOPNOTSUPP; + } + if (ice_has_vfs(pf)) { + NL_SET_ERR_MSG_MOD(extack, + "Remove all VFs before doing reinit\n"); + return -EOPNOTSUPP; + } + ice_unload(pf); + return 0; + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: + return ice_devlink_reload_empr_start(pf, extack); + default: + WARN_ON(1); + return -EOPNOTSUPP; + } +} + +/** * ice_devlink_reload_empr_finish - Wait for EMP reset to finish - * @devlink: pointer to the devlink instance reloading - * @action: the action requested - * @limit: limits imposed by userspace, such as not resetting - * @actions_performed: on return, indicate what actions actually performed + * @pf: pointer to the pf instance * @extack: netlink extended ACK structure * * Wait for driver to finish rebuilding after EMP reset is completed. This @@ -443,17 +477,11 @@ ice_devlink_reload_empr_start(struct devlink *devlink, bool netns_change, * for the driver's rebuild to complete. */ static int -ice_devlink_reload_empr_finish(struct devlink *devlink, - enum devlink_reload_action action, - enum devlink_reload_limit limit, - u32 *actions_performed, +ice_devlink_reload_empr_finish(struct ice_pf *pf, struct netlink_ext_ack *extack) { - struct ice_pf *pf = devlink_priv(devlink); int err; - *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); - err = ice_wait_for_reset(pf, 60 * HZ); if (err) { NL_SET_ERR_MSG_MOD(extack, "Device still resetting after 1 minute"); @@ -1192,12 +1220,43 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, return status; } +/** + * ice_devlink_reload_up - do reload up after reinit + * @devlink: pointer to the devlink instance reloading + * @action: the action requested + * @limit: limits imposed by userspace, such as not resetting + * @actions_performed: on return, indicate what actions actually performed + * @extack: netlink extended ACK structure + */ +static int +ice_devlink_reload_up(struct devlink *devlink, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + switch (action) { + case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT); + return ice_load(pf); + case DEVLINK_RELOAD_ACTION_FW_ACTIVATE: + *actions_performed = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE); + return ice_devlink_reload_empr_finish(pf, extack); + default: + WARN_ON(1); + return -EOPNOTSUPP; + } +} + static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, - .reload_actions = BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), + .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | + BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), /* The ice driver currently does not support driver reinit */ - .reload_down = ice_devlink_reload_empr_start, - .reload_up = ice_devlink_reload_empr_finish, + .reload_down = ice_devlink_reload_down, + .reload_up = ice_devlink_reload_up, .port_split = ice_devlink_port_split, .port_unsplit = ice_devlink_port_unsplit, .eswitch_mode_get = ice_eswitch_mode_get, diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index f9f15acae90a..f6dd3f8fd936 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -71,17 +71,17 @@ void ice_eswitch_replay_vf_mac_rule(struct ice_vf *vf) if (!ice_is_switchdev_running(vf->pf)) return; - if (is_valid_ether_addr(vf->hw_lan_addr.addr)) { + if (is_valid_ether_addr(vf->hw_lan_addr)) { err = ice_eswitch_add_vf_mac_rule(vf->pf, vf, - vf->hw_lan_addr.addr); + vf->hw_lan_addr); if (err) { dev_err(ice_pf_to_dev(vf->pf), "Failed to add MAC %pM for VF %d\n, error %d\n", - vf->hw_lan_addr.addr, vf->vf_id, err); + vf->hw_lan_addr, vf->vf_id, err); return; } vf->num_mac++; - ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); } } @@ -237,7 +237,7 @@ ice_eswitch_release_reprs(struct ice_pf *pf, struct ice_vsi *ctrl_vsi) ice_vsi_update_security(vsi, ice_vsi_ctx_set_antispoof); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); netif_napi_del(&vf->repr->q_vector->napi); @@ -265,14 +265,14 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) GFP_KERNEL); if (!vf->repr->dst) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); goto err; } if (ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof)) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; @@ -281,7 +281,7 @@ static int ice_eswitch_setup_reprs(struct ice_pf *pf) if (ice_vsi_add_vlan_zero(vsi)) { ice_fltr_add_mac_and_broadcast(vsi, - vf->hw_lan_addr.addr, + vf->hw_lan_addr, ICE_FWD_TO_VSI); metadata_dst_free(vf->repr->dst); vf->repr->dst = NULL; @@ -338,7 +338,7 @@ void ice_eswitch_update_repr(struct ice_vsi *vsi) ret = ice_vsi_update_security(vsi, ice_vsi_ctx_clear_antispoof); if (ret) { - ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr.addr, ICE_FWD_TO_VSI); + ice_fltr_add_mac_and_broadcast(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); dev_err(ice_pf_to_dev(pf), "Failed to update VF %d port representor", vsi->vf->vf_id); } @@ -425,7 +425,13 @@ static void ice_eswitch_release_env(struct ice_pf *pf) static struct ice_vsi * ice_eswitch_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_SWITCHDEV_CTRL, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_SWITCHDEV_CTRL; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index baaeb7564b4b..b360bd8f1599 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -656,7 +656,7 @@ static int ice_lbtest_prepare_rings(struct ice_vsi *vsi) if (status) goto err_setup_rx_ring; - status = ice_vsi_cfg(vsi); + status = ice_vsi_cfg_lan(vsi); if (status) goto err_setup_rx_ring; @@ -3046,8 +3046,6 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, /* clone ring and setup updated count */ xdp_rings[i] = *vsi->xdp_rings[i]; xdp_rings[i].count = new_tx_cnt; - xdp_rings[i].next_dd = ICE_RING_QUARTER(&xdp_rings[i]) - 1; - xdp_rings[i].next_rs = ICE_RING_QUARTER(&xdp_rings[i]) - 1; xdp_rings[i].desc = NULL; xdp_rings[i].tx_buf = NULL; err = ice_setup_tx_ring(&xdp_rings[i]); @@ -3092,7 +3090,7 @@ process_rx: /* allocate Rx buffers */ err = ice_alloc_rx_bufs(&rx_rings[i], - ICE_DESC_UNUSED(&rx_rings[i])); + ICE_RX_DESC_UNUSED(&rx_rings[i])); rx_unwind: if (err) { while (i) { diff --git a/drivers/net/ethernet/intel/ice/ice_fltr.c b/drivers/net/ethernet/intel/ice/ice_fltr.c index 40e678cfb507..aff7a141c30d 100644 --- a/drivers/net/ethernet/intel/ice/ice_fltr.c +++ b/drivers/net/ethernet/intel/ice/ice_fltr.c @@ -208,6 +208,11 @@ static int ice_fltr_remove_eth_list(struct ice_vsi *vsi, struct list_head *list) void ice_fltr_remove_all(struct ice_vsi *vsi) { ice_remove_vsi_fltr(&vsi->back->hw, vsi->idx); + /* sync netdev filters if exist */ + if (vsi->netdev) { + __dev_uc_unsync(vsi->netdev, NULL); + __dev_mc_unsync(vsi->netdev, NULL); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 895c32bcc8b5..e6bc2285071e 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -6,6 +6,8 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" +static DEFINE_XARRAY_ALLOC1(ice_aux_id); + /** * ice_get_auxiliary_drv - retrieve iidc_auxiliary_drv struct * @pf: pointer to PF struct @@ -246,6 +248,17 @@ static int ice_reserve_rdma_qvector(struct ice_pf *pf) } /** + * ice_free_rdma_qvector - free vector resources reserved for RDMA driver + * @pf: board private structure to initialize + */ +static void ice_free_rdma_qvector(struct ice_pf *pf) +{ + pf->num_avail_sw_msix -= pf->num_rdma_msix; + ice_free_res(pf->irq_tracker, pf->rdma_base_vector, + ICE_RES_RDMA_VEC_ID); +} + +/** * ice_adev_release - function to be mapped to AUX dev's release op * @dev: pointer to device to free */ @@ -331,12 +344,48 @@ int ice_init_rdma(struct ice_pf *pf) struct device *dev = &pf->pdev->dev; int ret; + if (!ice_is_rdma_ena(pf)) { + dev_warn(dev, "RDMA is not supported on this device\n"); + return 0; + } + + ret = xa_alloc(&ice_aux_id, &pf->aux_idx, NULL, XA_LIMIT(1, INT_MAX), + GFP_KERNEL); + if (ret) { + dev_err(dev, "Failed to allocate device ID for AUX driver\n"); + return -ENOMEM; + } + /* Reserve vector resources */ ret = ice_reserve_rdma_qvector(pf); if (ret < 0) { dev_err(dev, "failed to reserve vectors for RDMA\n"); - return ret; + goto err_reserve_rdma_qvector; } pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; - return ice_plug_aux_dev(pf); + ret = ice_plug_aux_dev(pf); + if (ret) + goto err_plug_aux_dev; + return 0; + +err_plug_aux_dev: + ice_free_rdma_qvector(pf); +err_reserve_rdma_qvector: + pf->adev = NULL; + xa_erase(&ice_aux_id, pf->aux_idx); + return ret; +} + +/** + * ice_deinit_rdma - deinitialize RDMA on PF + * @pf: ptr to ice_pf + */ +void ice_deinit_rdma(struct ice_pf *pf) +{ + if (!ice_is_rdma_ena(pf)) + return; + + ice_unplug_aux_dev(pf); + ice_free_rdma_qvector(pf); + xa_erase(&ice_aux_id, pf->aux_idx); } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 301c1efe08b4..37fe639712e6 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -166,14 +166,14 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured - * @vf: the VF associated with this VSI, if any * * Return 0 on success and a negative value on error */ -static void ice_vsi_set_num_qs(struct ice_vsi *vsi, struct ice_vf *vf) +static void ice_vsi_set_num_qs(struct ice_vsi *vsi) { enum ice_vsi_type vsi_type = vsi->type; struct ice_pf *pf = vsi->back; + struct ice_vf *vf = vsi->vf; if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) return; @@ -282,10 +282,10 @@ static int ice_get_free_slot(void *array, int size, int curr) } /** - * ice_vsi_delete - delete a VSI from the switch + * ice_vsi_delete_from_hw - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -void ice_vsi_delete(struct ice_vsi *vsi) +static void ice_vsi_delete_from_hw(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; @@ -348,47 +348,144 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) } /** - * ice_vsi_clear - clean up and deallocate the provided VSI + * ice_vsi_free_stats - Free the ring statistics structures + * @vsi: VSI pointer + */ +static void ice_vsi_free_stats(struct ice_vsi *vsi) +{ + struct ice_vsi_stats *vsi_stat; + struct ice_pf *pf = vsi->back; + int i; + + if (vsi->type == ICE_VSI_CHNL) + return; + if (!pf->vsi_stats) + return; + + vsi_stat = pf->vsi_stats[vsi->idx]; + if (!vsi_stat) + return; + + ice_for_each_alloc_txq(vsi, i) { + if (vsi_stat->tx_ring_stats[i]) { + kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); + } + } + + ice_for_each_alloc_rxq(vsi, i) { + if (vsi_stat->rx_ring_stats[i]) { + kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); + WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); + } + } + + kfree(vsi_stat->tx_ring_stats); + kfree(vsi_stat->rx_ring_stats); + kfree(vsi_stat); + pf->vsi_stats[vsi->idx] = NULL; +} + +/** + * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI + * @vsi: VSI which is having stats allocated + */ +static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) +{ + struct ice_ring_stats **tx_ring_stats; + struct ice_ring_stats **rx_ring_stats; + struct ice_vsi_stats *vsi_stats; + struct ice_pf *pf = vsi->back; + u16 i; + + vsi_stats = pf->vsi_stats[vsi->idx]; + tx_ring_stats = vsi_stats->tx_ring_stats; + rx_ring_stats = vsi_stats->rx_ring_stats; + + /* Allocate Tx ring stats */ + ice_for_each_alloc_txq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_tx_ring *ring; + + ring = vsi->tx_rings[i]; + ring_stats = tx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(tx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + /* Allocate Rx ring stats */ + ice_for_each_alloc_rxq(vsi, i) { + struct ice_ring_stats *ring_stats; + struct ice_rx_ring *ring; + + ring = vsi->rx_rings[i]; + ring_stats = rx_ring_stats[i]; + + if (!ring_stats) { + ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); + if (!ring_stats) + goto err_out; + + WRITE_ONCE(rx_ring_stats[i], ring_stats); + } + + ring->ring_stats = ring_stats; + } + + return 0; + +err_out: + ice_vsi_free_stats(vsi); + return -ENOMEM; +} + +/** + * ice_vsi_free - clean up and deallocate the provided VSI * @vsi: pointer to VSI being cleared * * This deallocates the VSI's queue resources, removes it from the PF's * VSI array if necessary, and deallocates the VSI - * - * Returns 0 on success, negative on failure */ -int ice_vsi_clear(struct ice_vsi *vsi) +static void ice_vsi_free(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; - if (!vsi) - return 0; - - if (!vsi->back) - return -EINVAL; + if (!vsi || !vsi->back) + return; pf = vsi->back; dev = ice_pf_to_dev(pf); if (!pf->vsi[vsi->idx] || pf->vsi[vsi->idx] != vsi) { dev_dbg(dev, "vsi does not exist at pf->vsi[%d]\n", vsi->idx); - return -EINVAL; + return; } mutex_lock(&pf->sw_mutex); /* updates the PF for this cleared VSI */ pf->vsi[vsi->idx] = NULL; - if (vsi->idx < pf->next_vsi && vsi->type != ICE_VSI_CTRL) - pf->next_vsi = vsi->idx; - if (vsi->idx < pf->next_vsi && vsi->type == ICE_VSI_CTRL && vsi->vf) - pf->next_vsi = vsi->idx; + pf->next_vsi = vsi->idx; + ice_vsi_free_stats(vsi); ice_vsi_free_arrays(vsi); mutex_unlock(&pf->sw_mutex); devm_kfree(dev, vsi); +} - return 0; +void ice_vsi_delete(struct ice_vsi *vsi) +{ + ice_vsi_delete_from_hw(vsi); + ice_vsi_free(vsi); } /** @@ -461,6 +558,10 @@ static int ice_vsi_alloc_stat_arrays(struct ice_vsi *vsi) if (!pf->vsi_stats) return -ENOENT; + if (pf->vsi_stats[vsi->idx]) + /* realloc will happen in rebuild path */ + return 0; + vsi_stat = kzalloc(sizeof(*vsi_stat), GFP_KERNEL); if (!vsi_stat) return -ENOMEM; @@ -491,128 +592,92 @@ err_alloc_tx: } /** - * ice_vsi_alloc - Allocates the next available struct VSI in the PF - * @pf: board private structure - * @vsi_type: type of VSI + * ice_vsi_alloc_def - set default values for already allocated VSI + * @vsi: ptr to VSI * @ch: ptr to channel - * @vf: VF for ICE_VSI_VF and ICE_VSI_CTRL - * - * The VF pointer is used for ICE_VSI_VF and ICE_VSI_CTRL. For ICE_VSI_CTRL, - * it may be NULL in the case there is no association with a VF. For - * ICE_VSI_VF the VF pointer *must not* be NULL. - * - * returns a pointer to a VSI on success, NULL on failure. */ -static struct ice_vsi * -ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type vsi_type, - struct ice_channel *ch, struct ice_vf *vf) +static int +ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) { - struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi = NULL; - - if (WARN_ON(vsi_type == ICE_VSI_VF && !vf)) - return NULL; - - /* Need to protect the allocation of the VSIs at the PF level */ - mutex_lock(&pf->sw_mutex); - - /* If we have already allocated our maximum number of VSIs, - * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index - * is available to be populated - */ - if (pf->next_vsi == ICE_NO_VSI) { - dev_dbg(dev, "out of VSI slots!\n"); - goto unlock_pf; + if (vsi->type != ICE_VSI_CHNL) { + ice_vsi_set_num_qs(vsi); + if (ice_vsi_alloc_arrays(vsi)) + return -ENOMEM; } - vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); - if (!vsi) - goto unlock_pf; - - vsi->type = vsi_type; - vsi->back = pf; - set_bit(ICE_VSI_DOWN, vsi->state); - - if (vsi_type == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vf); - else if (vsi_type != ICE_VSI_CHNL) - ice_vsi_set_num_qs(vsi, NULL); - switch (vsi->type) { case ICE_VSI_SWITCHDEV_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup eswitch MSIX irq handler for VSI */ vsi->irq_handler = ice_eswitch_msix_clean_rings; break; case ICE_VSI_PF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings; break; case ICE_VSI_CTRL: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - /* Setup ctrl VSI MSIX irq handler */ vsi->irq_handler = ice_msix_clean_ctrl_vsi; - - /* For the PF control VSI this is NULL, for the VF control VSI - * this will be the first VF to allocate it. - */ - vsi->vf = vf; - break; - case ICE_VSI_VF: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; - vsi->vf = vf; break; case ICE_VSI_CHNL: if (!ch) - goto err_rings; + return -EINVAL; + vsi->num_rxq = ch->num_rxq; vsi->num_txq = ch->num_txq; vsi->next_base_q = ch->base_q; break; - case ICE_VSI_LB: - if (ice_vsi_alloc_arrays(vsi)) - goto err_rings; + case ICE_VSI_VF: break; default: - dev_warn(dev, "Unknown VSI type %d\n", vsi->type); - goto unlock_pf; + ice_vsi_free_arrays(vsi); + return -EINVAL; } - if (vsi->type == ICE_VSI_CTRL && !vf) { - /* Use the last VSI slot as the index for PF control VSI */ - vsi->idx = pf->num_alloc_vsi - 1; - pf->ctrl_vsi_idx = vsi->idx; - pf->vsi[vsi->idx] = vsi; - } else { - /* fill slot and make note of the index */ - vsi->idx = pf->next_vsi; - pf->vsi[pf->next_vsi] = vsi; + return 0; +} + +/** + * ice_vsi_alloc - Allocates the next available struct VSI in the PF + * @pf: board private structure + * + * Reserves a VSI index from the PF and allocates an empty VSI structure + * without a type. The VSI structure must later be initialized by calling + * ice_vsi_cfg(). + * + * returns a pointer to a VSI on success, NULL on failure. + */ +static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi = NULL; + + /* Need to protect the allocation of the VSIs at the PF level */ + mutex_lock(&pf->sw_mutex); - /* prepare pf->next_vsi for next use */ - pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, - pf->next_vsi); + /* If we have already allocated our maximum number of VSIs, + * pf->next_vsi will be ICE_NO_VSI. If not, pf->next_vsi index + * is available to be populated + */ + if (pf->next_vsi == ICE_NO_VSI) { + dev_dbg(dev, "out of VSI slots!\n"); + goto unlock_pf; } - if (vsi->type == ICE_VSI_CTRL && vf) - vf->ctrl_vsi_idx = vsi->idx; + vsi = devm_kzalloc(dev, sizeof(*vsi), GFP_KERNEL); + if (!vsi) + goto unlock_pf; - /* allocate memory for Tx/Rx ring stat pointers */ - if (ice_vsi_alloc_stat_arrays(vsi)) - goto err_rings; + vsi->back = pf; + set_bit(ICE_VSI_DOWN, vsi->state); - goto unlock_pf; + /* fill slot and make note of the index */ + vsi->idx = pf->next_vsi; + pf->vsi[pf->next_vsi] = vsi; + + /* prepare pf->next_vsi for next use */ + pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi, + pf->next_vsi); -err_rings: - devm_kfree(dev, vsi); - vsi = NULL; unlock_pf: mutex_unlock(&pf->sw_mutex); return vsi; @@ -1177,12 +1242,15 @@ ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) /** * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured - * @init_vsi: is this call creating a VSI + * @vsi_flags: VSI configuration flags + * + * Set ICE_FLAG_VSI_INIT to initialize a new VSI context, clear it to + * reconfigure an existing context. * * This initializes a VSI context depending on the VSI type to be added and * passes it down to the add_vsi aq command to create a new VSI. */ -static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) +static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags) { struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; @@ -1244,7 +1312,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) /* if updating VSI context, make sure to set valid_section: * to indicate which section of VSI context being updated */ - if (!init_vsi) + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) ctxt->info.valid_sections |= cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); } @@ -1257,7 +1325,8 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) if (ret) goto out; - if (!init_vsi) /* means VSI being updated */ + if (!(vsi_flags & ICE_VSI_FLAG_INIT)) + /* means VSI being updated */ /* must to indicate which section of VSI context are * being modified */ @@ -1272,7 +1341,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, bool init_vsi) cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); } - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL); if (ret) { dev_err(dev, "Add VSI failed, err %d\n", ret); @@ -1436,7 +1505,7 @@ static int ice_get_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) * ice_vsi_setup_vector_base - Set up the base vector for the given VSI * @vsi: ptr to the VSI * - * This should only be called after ice_vsi_alloc() which allocates the + * This should only be called after ice_vsi_alloc_def() which allocates the * corresponding SW VSI structure and initializes num_queue_pairs for the * newly allocated VSI. * @@ -1584,106 +1653,6 @@ err_out: } /** - * ice_vsi_free_stats - Free the ring statistics structures - * @vsi: VSI pointer - */ -static void ice_vsi_free_stats(struct ice_vsi *vsi) -{ - struct ice_vsi_stats *vsi_stat; - struct ice_pf *pf = vsi->back; - int i; - - if (vsi->type == ICE_VSI_CHNL) - return; - if (!pf->vsi_stats) - return; - - vsi_stat = pf->vsi_stats[vsi->idx]; - if (!vsi_stat) - return; - - ice_for_each_alloc_txq(vsi, i) { - if (vsi_stat->tx_ring_stats[i]) { - kfree_rcu(vsi_stat->tx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->tx_ring_stats[i], NULL); - } - } - - ice_for_each_alloc_rxq(vsi, i) { - if (vsi_stat->rx_ring_stats[i]) { - kfree_rcu(vsi_stat->rx_ring_stats[i], rcu); - WRITE_ONCE(vsi_stat->rx_ring_stats[i], NULL); - } - } - - kfree(vsi_stat->tx_ring_stats); - kfree(vsi_stat->rx_ring_stats); - kfree(vsi_stat); - pf->vsi_stats[vsi->idx] = NULL; -} - -/** - * ice_vsi_alloc_ring_stats - Allocates Tx and Rx ring stats for the VSI - * @vsi: VSI which is having stats allocated - */ -static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi) -{ - struct ice_ring_stats **tx_ring_stats; - struct ice_ring_stats **rx_ring_stats; - struct ice_vsi_stats *vsi_stats; - struct ice_pf *pf = vsi->back; - u16 i; - - vsi_stats = pf->vsi_stats[vsi->idx]; - tx_ring_stats = vsi_stats->tx_ring_stats; - rx_ring_stats = vsi_stats->rx_ring_stats; - - /* Allocate Tx ring stats */ - ice_for_each_alloc_txq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_tx_ring *ring; - - ring = vsi->tx_rings[i]; - ring_stats = tx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(tx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; - } - - /* Allocate Rx ring stats */ - ice_for_each_alloc_rxq(vsi, i) { - struct ice_ring_stats *ring_stats; - struct ice_rx_ring *ring; - - ring = vsi->rx_rings[i]; - ring_stats = rx_ring_stats[i]; - - if (!ring_stats) { - ring_stats = kzalloc(sizeof(*ring_stats), GFP_KERNEL); - if (!ring_stats) - goto err_out; - - WRITE_ONCE(rx_ring_stats[i], ring_stats); - } - - ring->ring_stats = ring_stats; - } - - return 0; - -err_out: - ice_vsi_free_stats(vsi); - return -ENOMEM; -} - -/** * ice_vsi_manage_rss_lut - disable/enable RSS * @vsi: the VSI being changed * @ena: boolean value indicating if this is an enable or disable request @@ -1992,8 +1961,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) { if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - vsi->rx_buf_len = ICE_RXBUF_2048; + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; + vsi->rx_buf_len = ICE_RXBUF_1664; #if (PAGE_SIZE < 8192) } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && (vsi->netdev->mtu <= ETH_DATA_LEN)) { @@ -2002,11 +1971,7 @@ void ice_vsi_cfg_frame_size(struct ice_vsi *vsi) #endif } else { vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; -#if (PAGE_SIZE < 8192) vsi->rx_buf_len = ICE_RXBUF_3072; -#else - vsi->rx_buf_len = ICE_RXBUF_2048; -#endif } } @@ -2645,54 +2610,97 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi) } /** - * ice_vsi_setup - Set up a VSI by a given type - * @pf: board private structure - * @pi: pointer to the port_info instance - * @vsi_type: VSI type - * @vf: pointer to VF to which this VSI connects. This field is used primarily - * for the ICE_VSI_VF type. Other VSI types should pass NULL. - * @ch: ptr to channel - * - * This allocates the sw VSI structure and its queue resources. + * ice_free_vf_ctrl_res - Free the VF control VSI resource + * @pf: pointer to PF structure + * @vsi: the VSI to free resources for * - * Returns pointer to the successfully allocated and configured VSI sw struct on - * success, NULL on failure. + * Check if the VF control VSI resource is still in use. If no VF is using it + * any more, release the VSI resource. Otherwise, leave it to be cleaned up + * once no other VF uses it. */ -struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, struct ice_vf *vf, - struct ice_channel *ch) +static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) +{ + struct ice_vf *vf; + unsigned int bkt; + + rcu_read_lock(); + ice_for_each_vf_rcu(pf, bkt, vf) { + if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + + /* No other VFs left that have control VSI. It is now safe to reclaim + * SW interrupts back to the common pool. + */ + ice_free_res(pf->irq_tracker, vsi->base_vector, + ICE_RES_VF_CTRL_VEC_ID); + pf->num_avail_sw_msix += vsi->num_q_vectors; +} + +static int ice_vsi_cfg_tc_lan(struct ice_pf *pf, struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = ice_pf_to_dev(pf); - struct ice_vsi *vsi; int ret, i; - if (vsi_type == ICE_VSI_CHNL) - vsi = ice_vsi_alloc(pf, vsi_type, ch, NULL); - else if (vsi_type == ICE_VSI_VF || vsi_type == ICE_VSI_CTRL) - vsi = ice_vsi_alloc(pf, vsi_type, NULL, vf); - else - vsi = ice_vsi_alloc(pf, vsi_type, NULL, NULL); + /* configure VSI nodes based on number of queues and TC's */ + ice_for_each_traffic_class(i) { + if (!(vsi->tc_cfg.ena_tc & BIT(i))) + continue; - if (!vsi) { - dev_err(dev, "could not allocate VSI\n"); - return NULL; + if (vsi->type == ICE_VSI_CHNL) { + if (!vsi->alloc_txq && vsi->num_txq) + max_txqs[i] = vsi->num_txq; + else + max_txqs[i] = pf->num_lan_tx; + } else { + max_txqs[i] = vsi->alloc_txq; + } + } + + dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); + ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, + max_txqs); + if (ret) { + dev_err(dev, "VSI %d failed lan queue config, error %d\n", + vsi->vsi_num, ret); + return ret; } - vsi->port_info = pi; + return 0; +} + +/** + * ice_vsi_cfg_def - configure default VSI based on the type + * @vsi: pointer to VSI + * @params: the parameters to configure this VSI with + */ +static int +ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +{ + struct device *dev = ice_pf_to_dev(vsi->back); + struct ice_pf *pf = vsi->back; + int ret; + vsi->vsw = pf->first_sw; - if (vsi->type == ICE_VSI_PF) - vsi->ethtype = ETH_P_PAUSE; + + ret = ice_vsi_alloc_def(vsi, params->ch); + if (ret) + return ret; + + /* allocate memory for Tx/Rx ring stat pointers */ + if (ice_vsi_alloc_stat_arrays(vsi)) + goto unroll_vsi_alloc; ice_alloc_fd_res(vsi); - if (vsi_type != ICE_VSI_CHNL) { - if (ice_vsi_get_qs(vsi)) { - dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", - vsi->idx); - goto unroll_vsi_alloc; - } + if (ice_vsi_get_qs(vsi)) { + dev_err(dev, "Failed to allocate queues. vsi->idx = %d\n", + vsi->idx); + goto unroll_vsi_alloc_stat; } /* set RSS capabilities */ @@ -2702,7 +2710,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, ice_vsi_set_tc_cfg(vsi); /* create the VSI */ - ret = ice_vsi_init(vsi, true); + ret = ice_vsi_init(vsi, params->flags); if (ret) goto unroll_get_qs; @@ -2733,6 +2741,14 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + if (ice_is_xdp_ena_vsi(vsi)) { + ret = ice_vsi_determine_xdp_res(vsi); + if (ret) + goto unroll_vector_base; + ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); + if (ret) + goto unroll_vector_base; + } /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ if (vsi->type != ICE_VSI_CTRL) @@ -2797,30 +2813,156 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, goto unroll_vsi_init; } - /* configure VSI nodes based on number of queues and TC's */ - ice_for_each_traffic_class(i) { - if (!(vsi->tc_cfg.ena_tc & BIT(i))) - continue; + return 0; - if (vsi->type == ICE_VSI_CHNL) { - if (!vsi->alloc_txq && vsi->num_txq) - max_txqs[i] = vsi->num_txq; - else - max_txqs[i] = pf->num_lan_tx; +unroll_vector_base: + /* reclaim SW interrupts back to the common pool */ + ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; +unroll_alloc_q_vector: + ice_vsi_free_q_vectors(vsi); +unroll_vsi_init: + ice_vsi_delete_from_hw(vsi); +unroll_get_qs: + ice_vsi_put_qs(vsi); +unroll_vsi_alloc_stat: + ice_vsi_free_stats(vsi); +unroll_vsi_alloc: + ice_vsi_free_arrays(vsi); + return ret; +} + +/** + * ice_vsi_cfg - configure a previously allocated VSI + * @vsi: pointer to VSI + * @params: parameters used to configure this VSI + */ +int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) +{ + struct ice_pf *pf = vsi->back; + int ret; + + if (WARN_ON(params->type == ICE_VSI_VF && !params->vf)) + return -EINVAL; + + vsi->type = params->type; + vsi->port_info = params->pi; + + /* For VSIs which don't have a connected VF, this will be NULL */ + vsi->vf = params->vf; + + ret = ice_vsi_cfg_def(vsi, params); + if (ret) + return ret; + + ret = ice_vsi_cfg_tc_lan(vsi->back, vsi); + if (ret) + ice_vsi_decfg(vsi); + + if (vsi->type == ICE_VSI_CTRL) { + if (vsi->vf) { + WARN_ON(vsi->vf->ctrl_vsi_idx != ICE_NO_VSI); + vsi->vf->ctrl_vsi_idx = vsi->idx; } else { - max_txqs[i] = vsi->alloc_txq; + WARN_ON(pf->ctrl_vsi_idx != ICE_NO_VSI); + pf->ctrl_vsi_idx = vsi->idx; } } - dev_dbg(dev, "vsi->tc_cfg.ena_tc = %d\n", vsi->tc_cfg.ena_tc); - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, - max_txqs); - if (ret) { - dev_err(dev, "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - goto unroll_clear_rings; + return ret; +} + +/** + * ice_vsi_decfg - remove all VSI configuration + * @vsi: pointer to VSI + */ +void ice_vsi_decfg(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + int err; + + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped + */ + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF && + !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + ice_cfg_sw_lldp(vsi, false, false); + + ice_fltr_remove_all(vsi); + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); + err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + if (err) + dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", + vsi->vsi_num, err); + + if (ice_is_xdp_ena_vsi(vsi)) + /* return value check can be skipped here, it always returns + * 0 if reset is in progress + */ + ice_destroy_xdp_rings(vsi); + + ice_vsi_clear_rings(vsi); + ice_vsi_free_q_vectors(vsi); + ice_vsi_put_qs(vsi); + ice_vsi_free_arrays(vsi); + + /* SR-IOV determines needed MSIX resources all at once instead of per + * VSI since when VFs are spawned we know how many VFs there are and how + * many interrupts each VF needs. SR-IOV MSIX resources are also + * cleared in the same manner. + */ + if (vsi->type == ICE_VSI_CTRL && vsi->vf) { + ice_free_vf_ctrl_res(pf, vsi); + } else if (vsi->type != ICE_VSI_VF) { + /* reclaim SW interrupts back to the common pool */ + ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); + pf->num_avail_sw_msix += vsi->num_q_vectors; + vsi->base_vector = 0; } + if (vsi->type == ICE_VSI_VF && + vsi->agg_node && vsi->agg_node->valid) + vsi->agg_node->num_vsis--; + if (vsi->agg_node) { + vsi->agg_node->valid = false; + vsi->agg_node->agg_id = 0; + } +} + +/** + * ice_vsi_setup - Set up a VSI by a given type + * @pf: board private structure + * @params: parameters to use when creating the VSI + * + * This allocates the sw VSI structure and its queue resources. + * + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. + */ +struct ice_vsi * +ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_vsi *vsi; + int ret; + + /* ice_vsi_setup can only initialize a new VSI, and we must have + * a port_info structure for it. + */ + if (WARN_ON(!(params->flags & ICE_VSI_FLAG_INIT)) || + WARN_ON(!params->pi)) + return NULL; + + vsi = ice_vsi_alloc(pf); + if (!vsi) { + dev_err(dev, "could not allocate VSI\n"); + return NULL; + } + + ret = ice_vsi_cfg(vsi, params); + if (ret) + goto err_vsi_cfg; + /* Add switch rule to drop all Tx Flow Control Frames, of look up * type ETHERTYPE from VSIs, and restrict malicious VF from sending * out PAUSE or PFC frames. If enabled, FW can still send FC frames. @@ -2830,34 +2972,21 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, * be dropped so that VFs cannot send LLDP packets to reconfig DCB * settings in the HW. */ - if (!ice_is_safe_mode(pf)) - if (vsi->type == ICE_VSI_PF) { - ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, true); - } + if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF) { + ice_fltr_add_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, + ICE_DROP_PACKET); + ice_cfg_sw_lldp(vsi, true, true); + } if (!vsi->agg_node) ice_set_agg_vsi(vsi); + return vsi; -unroll_clear_rings: - ice_vsi_clear_rings(vsi); -unroll_vector_base: - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; -unroll_alloc_q_vector: - ice_vsi_free_q_vectors(vsi); -unroll_vsi_init: - ice_vsi_free_stats(vsi); - ice_vsi_delete(vsi); -unroll_get_qs: - ice_vsi_put_qs(vsi); -unroll_vsi_alloc: - if (vsi_type == ICE_VSI_VF) +err_vsi_cfg: + if (params->type == ICE_VSI_VF) ice_enable_lag(pf->lag); - ice_vsi_clear(vsi); + ice_vsi_free(vsi); return NULL; } @@ -3121,37 +3250,6 @@ void ice_napi_del(struct ice_vsi *vsi) } /** - * ice_free_vf_ctrl_res - Free the VF control VSI resource - * @pf: pointer to PF structure - * @vsi: the VSI to free resources for - * - * Check if the VF control VSI resource is still in use. If no VF is using it - * any more, release the VSI resource. Otherwise, leave it to be cleaned up - * once no other VF uses it. - */ -static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) -{ - struct ice_vf *vf; - unsigned int bkt; - - rcu_read_lock(); - ice_for_each_vf_rcu(pf, bkt, vf) { - if (vf != vsi->vf && vf->ctrl_vsi_idx != ICE_NO_VSI) { - rcu_read_unlock(); - return; - } - } - rcu_read_unlock(); - - /* No other VFs left that have control VSI. It is now safe to reclaim - * SW interrupts back to the common pool. - */ - ice_free_res(pf->irq_tracker, vsi->base_vector, - ICE_RES_VF_CTRL_VEC_ID); - pf->num_avail_sw_msix += vsi->num_q_vectors; -} - -/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed * @@ -3160,7 +3258,6 @@ static void ice_free_vf_ctrl_res(struct ice_pf *pf, struct ice_vsi *vsi) int ice_vsi_release(struct ice_vsi *vsi) { struct ice_pf *pf; - int err; if (!vsi->back) return -ENODEV; @@ -3178,50 +3275,14 @@ int ice_vsi_release(struct ice_vsi *vsi) clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } + if (vsi->type == ICE_VSI_PF) + ice_devlink_destroy_pf_port(pf); + if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); - /* Disable VSI and free resources */ - if (vsi->type != ICE_VSI_LB) - ice_vsi_dis_irq(vsi); ice_vsi_close(vsi); - - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. - */ - if (vsi->type == ICE_VSI_CTRL && vsi->vf) { - ice_free_vf_ctrl_res(pf, vsi); - } else if (vsi->type != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - } - - if (!ice_is_safe_mode(pf)) { - if (vsi->type == ICE_VSI_PF) { - ice_fltr_remove_eth(vsi, ETH_P_PAUSE, ICE_FLTR_TX, - ICE_DROP_PACKET); - ice_cfg_sw_lldp(vsi, true, false); - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); - } - } - - if (ice_is_vsi_dflt_vsi(vsi)) - ice_clear_dflt_vsi(vsi); - ice_fltr_remove_all(vsi); - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); - if (err) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, err); - ice_vsi_delete(vsi); - ice_vsi_free_q_vectors(vsi); + ice_vsi_decfg(vsi); if (vsi->netdev) { if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { @@ -3235,19 +3296,12 @@ int ice_vsi_release(struct ice_vsi *vsi) } } - if (vsi->type == ICE_VSI_VF && - vsi->agg_node && vsi->agg_node->valid) - vsi->agg_node->num_vsis--; - ice_vsi_clear_rings(vsi); - ice_vsi_free_stats(vsi); - ice_vsi_put_qs(vsi); - /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. */ if (!ice_is_reset_in_progress(pf->state)) - ice_vsi_clear(vsi); + ice_vsi_delete(vsi); return 0; } @@ -3410,29 +3464,31 @@ ice_vsi_realloc_stat_arrays(struct ice_vsi *vsi, int prev_txq, int prev_rxq) /** * ice_vsi_rebuild - Rebuild VSI after reset * @vsi: VSI to be rebuild - * @init_vsi: is this an initialization or a reconfigure of the VSI + * @vsi_flags: flags used for VSI rebuild flow + * + * Set vsi_flags to ICE_VSI_FLAG_INIT to initialize a new VSI, or + * ICE_VSI_FLAG_NO_INIT to rebuild an existing VSI in hardware. * * Returns 0 on success and negative value on failure */ -int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) +int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags) { - u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct ice_vsi_cfg_params params = {}; struct ice_coalesce_stored *coalesce; - int ret, i, prev_txq, prev_rxq; + int ret, prev_txq, prev_rxq; int prev_num_q_vectors = 0; - enum ice_vsi_type vtype; struct ice_pf *pf; if (!vsi) return -EINVAL; + params = ice_vsi_to_params(vsi); + params.flags = vsi_flags; + pf = vsi->back; - vtype = vsi->type; - if (WARN_ON(vtype == ICE_VSI_VF && !vsi->vf)) + if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf)) return -EINVAL; - ice_vsi_init_vlan_ops(vsi); - coalesce = kcalloc(vsi->num_q_vectors, sizeof(struct ice_coalesce_stored), GFP_KERNEL); if (!coalesce) @@ -3443,188 +3499,33 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi) prev_txq = vsi->num_txq; prev_rxq = vsi->num_rxq; - ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); - ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); + ice_vsi_decfg(vsi); + ret = ice_vsi_cfg_def(vsi, ¶ms); if (ret) - dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n", - vsi->vsi_num, ret); - ice_vsi_free_q_vectors(vsi); - - /* SR-IOV determines needed MSIX resources all at once instead of per - * VSI since when VFs are spawned we know how many VFs there are and how - * many interrupts each VF needs. SR-IOV MSIX resources are also - * cleared in the same manner. - */ - if (vtype != ICE_VSI_VF) { - /* reclaim SW interrupts back to the common pool */ - ice_free_res(pf->irq_tracker, vsi->base_vector, vsi->idx); - pf->num_avail_sw_msix += vsi->num_q_vectors; - vsi->base_vector = 0; - } - - if (ice_is_xdp_ena_vsi(vsi)) - /* return value check can be skipped here, it always returns - * 0 if reset is in progress - */ - ice_destroy_xdp_rings(vsi); - ice_vsi_put_qs(vsi); - ice_vsi_clear_rings(vsi); - ice_vsi_free_arrays(vsi); - if (vtype == ICE_VSI_VF) - ice_vsi_set_num_qs(vsi, vsi->vf); - else - ice_vsi_set_num_qs(vsi, NULL); - - ret = ice_vsi_alloc_arrays(vsi); - if (ret < 0) - goto err_vsi; - - ice_vsi_get_qs(vsi); - - ice_alloc_fd_res(vsi); - ice_vsi_set_tc_cfg(vsi); - - /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_init(vsi, init_vsi); - if (ret < 0) - goto err_vsi; - - switch (vtype) { - case ICE_VSI_CTRL: - case ICE_VSI_SWITCHDEV_CTRL: - case ICE_VSI_PF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - ice_vsi_map_rings_to_vectors(vsi); - - vsi->stat_offsets_loaded = false; - if (ice_is_xdp_ena_vsi(vsi)) { - ret = ice_vsi_determine_xdp_res(vsi); - if (ret) - goto err_vectors; - ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog); - if (ret) - goto err_vectors; - } - /* ICE_VSI_CTRL does not need RSS so skip RSS processing */ - if (vtype != ICE_VSI_CTRL) - /* Do not exit if configuring RSS had an issue, at - * least receive traffic on first queue. Hence no - * need to capture return value - */ - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - ice_vsi_cfg_rss_lut_key(vsi); - - /* disable or enable CRC stripping */ - if (vsi->netdev) - ice_vsi_cfg_crc_strip(vsi, !!(vsi->netdev->features & - NETIF_F_RXFCS)); - - break; - case ICE_VSI_VF: - ret = ice_vsi_alloc_q_vectors(vsi); - if (ret) - goto err_rings; - - ret = ice_vsi_set_q_vectors_reg_idx(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_rings(vsi); - if (ret) - goto err_vectors; - - ret = ice_vsi_alloc_ring_stats(vsi); - if (ret) - goto err_vectors; - - vsi->stat_offsets_loaded = false; - break; - case ICE_VSI_CHNL: - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) { - ice_vsi_cfg_rss_lut_key(vsi); - ice_vsi_set_rss_flow_fld(vsi); - } - break; - default: - break; - } - - /* configure VSI nodes based on number of queues and TC's */ - for (i = 0; i < vsi->tc_cfg.numtc; i++) { - /* configure VSI nodes based on number of queues and TC's. - * ADQ creates VSIs for each TC/Channel but doesn't - * allocate queues instead it reconfigures the PF queues - * as per the TC command. So max_txqs should point to the - * PF Tx queues. - */ - if (vtype == ICE_VSI_CHNL) - max_txqs[i] = pf->num_lan_tx; - else - max_txqs[i] = vsi->alloc_txq; - - if (ice_is_xdp_ena_vsi(vsi)) - max_txqs[i] += vsi->num_xdp_txq; - } - - if (test_bit(ICE_FLAG_TC_MQPRIO, pf->flags)) - /* If MQPRIO is set, means channel code path, hence for main - * VSI's, use TC as 1 - */ - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, 1, max_txqs); - else - ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, - vsi->tc_cfg.ena_tc, max_txqs); + goto err_vsi_cfg; + ret = ice_vsi_cfg_tc_lan(pf, vsi); if (ret) { - dev_err(ice_pf_to_dev(pf), "VSI %d failed lan queue config, error %d\n", - vsi->vsi_num, ret); - if (init_vsi) { + if (vsi_flags & ICE_VSI_FLAG_INIT) { ret = -EIO; - goto err_vectors; + goto err_vsi_cfg_tc_lan; } else { + kfree(coalesce); return ice_schedule_reset(pf, ICE_RESET_PFR); } } if (ice_vsi_realloc_stat_arrays(vsi, prev_txq, prev_rxq)) - goto err_vectors; + goto err_vsi_cfg_tc_lan; ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors); kfree(coalesce); return 0; -err_vectors: - ice_vsi_free_q_vectors(vsi); -err_rings: - if (vsi->netdev) { - vsi->current_netdev_flags = 0; - unregister_netdev(vsi->netdev); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } -err_vsi: - ice_vsi_clear(vsi); - set_bit(ICE_RESET_FAILED, pf->state); +err_vsi_cfg_tc_lan: + ice_vsi_decfg(vsi); +err_vsi_cfg: kfree(coalesce); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index dcdf69a693e9..75221478f2dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -7,6 +7,47 @@ #include "ice.h" #include "ice_vlan.h" +/* Flags used for VSI configuration and rebuild */ +#define ICE_VSI_FLAG_INIT BIT(0) +#define ICE_VSI_FLAG_NO_INIT 0 + +/** + * struct ice_vsi_cfg_params - VSI configuration parameters + * @pi: pointer to the port_info instance for the VSI + * @ch: pointer to the channel structure for the VSI, may be NULL + * @vf: pointer to the VF associated with this VSI, may be NULL + * @type: the type of VSI to configure + * @flags: VSI flags used for rebuild and configuration + * + * Parameter structure used when configuring a new VSI. + */ +struct ice_vsi_cfg_params { + struct ice_port_info *pi; + struct ice_channel *ch; + struct ice_vf *vf; + enum ice_vsi_type type; + u32 flags; +}; + +/** + * ice_vsi_to_params - Get parameters for an existing VSI + * @vsi: the VSI to get parameters for + * + * Fill a parameter structure for reconfiguring a VSI with its current + * parameters, such as during a rebuild operation. + */ +static inline struct ice_vsi_cfg_params ice_vsi_to_params(struct ice_vsi *vsi) +{ + struct ice_vsi_cfg_params params = {}; + + params.pi = vsi->port_info; + params.ch = vsi->ch; + params.vf = vsi->vf; + params.type = vsi->type; + + return params; +} + const char *ice_vsi_type_str(enum ice_vsi_type vsi_type); bool ice_pf_state_is_nominal(struct ice_pf *pf); @@ -42,7 +83,6 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); int ice_set_link(struct ice_vsi *vsi, bool ena); void ice_vsi_delete(struct ice_vsi *vsi); -int ice_vsi_clear(struct ice_vsi *vsi); int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); @@ -51,9 +91,7 @@ int ice_vsi_cfg_rss_lut_key(struct ice_vsi *vsi); void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, - enum ice_vsi_type vsi_type, struct ice_vf *vf, - struct ice_channel *ch); +ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params); void ice_napi_del(struct ice_vsi *vsi); @@ -63,6 +101,7 @@ void ice_vsi_close(struct ice_vsi *vsi); int ice_ena_vsi(struct ice_vsi *vsi, bool locked); +void ice_vsi_decfg(struct ice_vsi *vsi); void ice_dis_vsi(struct ice_vsi *vsi, bool locked); int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); @@ -70,7 +109,8 @@ int ice_free_res(struct ice_res_tracker *res, u16 index, u16 id); int ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id); -int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi); +int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags); +int ice_vsi_cfg(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params); bool ice_is_reset_in_progress(unsigned long *state); int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 22b8ad058286..0712c1055aea 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -22,6 +22,7 @@ #include "ice_eswitch.h" #include "ice_tc_lib.h" #include "ice_vsi_vlan_ops.h" +#include <net/xdp_sock_drv.h> #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" static const char ice_driver_string[] = DRV_SUMMARY; @@ -44,7 +45,6 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all), hw debug_mask (0x8XXXX MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ -static DEFINE_IDA(ice_aux_ida); DEFINE_STATIC_KEY_FALSE(ice_xdp_locking_key); EXPORT_SYMBOL(ice_xdp_locking_key); @@ -538,7 +538,7 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type) /* Disable VFs until reset is completed */ mutex_lock(&pf->vfs.table_lock); ice_for_each_vf(pf, bkt, vf) - ice_set_vf_state_qs_dis(vf); + ice_set_vf_state_dis(vf); mutex_unlock(&pf->vfs.table_lock); if (ice_is_eswitch_mode_switchdev(pf)) { @@ -2570,8 +2570,6 @@ static int ice_xdp_alloc_setup_rings(struct ice_vsi *vsi) xdp_ring->netdev = NULL; xdp_ring->dev = dev; xdp_ring->count = vsi->num_tx_desc; - xdp_ring->next_dd = ICE_RING_QUARTER(xdp_ring) - 1; - xdp_ring->next_rs = ICE_RING_QUARTER(xdp_ring) - 1; WRITE_ONCE(vsi->xdp_rings[i], xdp_ring); if (ice_setup_tx_ring(xdp_ring)) goto free_xdp_rings; @@ -2863,6 +2861,18 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) } /** + * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @vsi: Pointer to VSI structure + */ +static int ice_max_xdp_frame_size(struct ice_vsi *vsi) +{ + if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) + return ICE_RXBUF_1664; + else + return ICE_RXBUF_3072; +} + +/** * ice_xdp_setup_prog - Add or remove XDP eBPF program * @vsi: VSI to setup XDP for * @prog: XDP program @@ -2872,13 +2882,16 @@ static int ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { - int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; + unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD; bool if_running = netif_running(vsi->netdev); int ret = 0, xdp_ring_err = 0; - if (frame_size > vsi->rx_buf_len) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large for loading XDP"); - return -EOPNOTSUPP; + if (prog && !prog->aux->xdp_has_frags) { + if (frame_size > ice_max_xdp_frame_size(vsi)) { + NL_SET_ERR_MSG_MOD(extack, + "MTU is too large for linear frames and XDP prog does not support frags"); + return -EOPNOTSUPP; + } } /* need to stop netdev while setting up the program for Rx rings */ @@ -2899,11 +2912,13 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed"); } + xdp_features_set_redirect_target(vsi->netdev, false); /* reallocate Rx queues that are used for zero-copy */ xdp_ring_err = ice_realloc_zc_buf(vsi, true); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { + xdp_features_clear_redirect_target(vsi->netdev); xdp_ring_err = ice_destroy_xdp_rings(vsi); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); @@ -3424,53 +3439,6 @@ static void ice_set_netdev_features(struct net_device *netdev) } /** - * ice_cfg_netdev - Allocate, configure and register a netdev - * @vsi: the VSI associated with the new netdev - * - * Returns 0 on success, negative value on failure - */ -static int ice_cfg_netdev(struct ice_vsi *vsi) -{ - struct ice_netdev_priv *np; - struct net_device *netdev; - u8 mac_addr[ETH_ALEN]; - - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); - if (!netdev) - return -ENOMEM; - - set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - vsi->netdev = netdev; - np = netdev_priv(netdev); - np->vsi = vsi; - - ice_set_netdev_features(netdev); - - ice_set_ops(netdev); - - if (vsi->type == ICE_VSI_PF) { - SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); - ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); - eth_hw_addr_set(netdev, mac_addr); - ether_addr_copy(netdev->perm_addr, mac_addr); - } - - netdev->priv_flags |= IFF_UNICAST_FLT; - - /* Setup netdev TC information */ - ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); - - /* setup watchdog timeout value to be 5 second */ - netdev->watchdog_timeo = 5 * HZ; - - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = ICE_MAX_MTU; - - return 0; -} - -/** * ice_fill_rss_lut - Fill the RSS lookup table with default values * @lut: Lookup table * @rss_table_size: Lookup table size @@ -3495,14 +3463,27 @@ void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size) static struct ice_vsi * ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_PF, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_PF; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } static struct ice_vsi * ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, struct ice_channel *ch) { - return ice_vsi_setup(pf, pi, ICE_VSI_CHNL, NULL, ch); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CHNL; + params.pi = pi; + params.ch = ch; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3516,7 +3497,13 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, static struct ice_vsi * ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_CTRL, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_CTRL; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3530,7 +3517,13 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) struct ice_vsi * ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) { - return ice_vsi_setup(pf, pi, ICE_VSI_LB, NULL, NULL); + struct ice_vsi_cfg_params params = {}; + + params.type = ICE_VSI_LB; + params.pi = pi; + params.flags = ICE_VSI_FLAG_INIT; + + return ice_vsi_setup(pf, ¶ms); } /** @@ -3690,20 +3683,6 @@ static void ice_tc_indir_block_unregister(struct ice_vsi *vsi) } /** - * ice_tc_indir_block_remove - clean indirect TC block notifications - * @pf: PF structure - */ -static void ice_tc_indir_block_remove(struct ice_pf *pf) -{ - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - - if (!pf_vsi) - return; - - ice_tc_indir_block_unregister(pf_vsi); -} - -/** * ice_tc_indir_block_register - Register TC indirect block notifications * @vsi: VSI struct which has the netdev * @@ -3723,76 +3702,6 @@ static int ice_tc_indir_block_register(struct ice_vsi *vsi) } /** - * ice_setup_pf_sw - Setup the HW switch on startup or after reset - * @pf: board private structure - * - * Returns 0 on success, negative value on failure - */ -static int ice_setup_pf_sw(struct ice_pf *pf) -{ - struct device *dev = ice_pf_to_dev(pf); - bool dvm = ice_is_dvm_ena(&pf->hw); - struct ice_vsi *vsi; - int status; - - if (ice_is_reset_in_progress(pf->state)) - return -EBUSY; - - status = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); - if (status) - return -EIO; - - vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); - if (!vsi) - return -ENOMEM; - - /* init channel list */ - INIT_LIST_HEAD(&vsi->ch_list); - - status = ice_cfg_netdev(vsi); - if (status) - goto unroll_vsi_setup; - /* netdev has to be configured before setting frame size */ - ice_vsi_cfg_frame_size(vsi); - - /* init indirect block notifications */ - status = ice_tc_indir_block_register(vsi); - if (status) { - dev_err(dev, "Failed to register netdev notifier\n"); - goto unroll_cfg_netdev; - } - - /* Setup DCB netlink interface */ - ice_dcbnl_setup(vsi); - - /* registering the NAPI handler requires both the queues and - * netdev to be created, which are done in ice_pf_vsi_setup() - * and ice_cfg_netdev() respectively - */ - ice_napi_add(vsi); - - status = ice_init_mac_fltr(pf); - if (status) - goto unroll_napi_add; - - return 0; - -unroll_napi_add: - ice_tc_indir_block_unregister(vsi); -unroll_cfg_netdev: - ice_napi_del(vsi); - if (vsi->netdev) { - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - free_netdev(vsi->netdev); - vsi->netdev = NULL; - } - -unroll_vsi_setup: - ice_vsi_release(vsi); - return status; -} - -/** * ice_get_avail_q_count - Get count of queues in use * @pf_qmap: bitmap to get queue use count from * @lock: pointer to a mutex that protects access to pf_qmap @@ -4221,13 +4130,13 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) /* set for the next time the netdev is started */ if (!netif_running(vsi->netdev)) { - ice_vsi_rebuild(vsi, false); + ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n"); goto done; } ice_vsi_close(vsi); - ice_vsi_rebuild(vsi, false); + ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); done: @@ -4490,6 +4399,23 @@ err_vsi_open: return err; } +static void ice_deinit_fdir(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_ctrl_vsi(pf); + + if (!vsi) + return; + + ice_vsi_manage_fdir(vsi, false); + ice_vsi_release(vsi); + if (pf->ctrl_vsi_idx != ICE_NO_VSI) { + pf->vsi[pf->ctrl_vsi_idx] = NULL; + pf->ctrl_vsi_idx = ICE_NO_VSI; + } + + mutex_destroy(&(&pf->hw)->fdir_fltr_lock); +} + /** * ice_get_opt_fw_name - return optional firmware file name or NULL * @pf: pointer to the PF instance @@ -4590,115 +4516,173 @@ static void ice_print_wake_reason(struct ice_pf *pf) /** * ice_register_netdev - register netdev - * @pf: pointer to the PF struct + * @vsi: pointer to the VSI struct */ -static int ice_register_netdev(struct ice_pf *pf) +static int ice_register_netdev(struct ice_vsi *vsi) { - struct ice_vsi *vsi; - int err = 0; + int err; - vsi = ice_get_main_vsi(pf); if (!vsi || !vsi->netdev) return -EIO; err = register_netdev(vsi->netdev); if (err) - goto err_register_netdev; + return err; set_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); netif_carrier_off(vsi->netdev); netif_tx_stop_all_queues(vsi->netdev); return 0; -err_register_netdev: - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - return err; +} + +static void ice_unregister_netdev(struct ice_vsi *vsi) +{ + if (!vsi || !vsi->netdev) + return; + + unregister_netdev(vsi->netdev); + clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); } /** - * ice_probe - Device initialization routine - * @pdev: PCI device information struct - * @ent: entry in ice_pci_tbl + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev * - * Returns 0 on success, negative on failure + * Returns 0 on success, negative value on failure */ -static int -ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +static int ice_cfg_netdev(struct ice_vsi *vsi) { - struct device *dev = &pdev->dev; - struct ice_vsi *vsi; - struct ice_pf *pf; - struct ice_hw *hw; - int i, err; + struct ice_netdev_priv *np; + struct net_device *netdev; + u8 mac_addr[ETH_ALEN]; - if (pdev->is_virtfn) { - dev_err(dev, "can't probe a virtual function\n"); - return -EINVAL; + netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, + vsi->alloc_rxq); + if (!netdev) + return -ENOMEM; + + set_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + vsi->netdev = netdev; + np = netdev_priv(netdev); + np->vsi = vsi; + + ice_set_netdev_features(netdev); + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; + ice_set_ops(netdev); + + if (vsi->type == ICE_VSI_PF) { + SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); + ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); + eth_hw_addr_set(netdev, mac_addr); } - /* this driver uses devres, see - * Documentation/driver-api/driver-model/devres.rst - */ - err = pcim_enable_device(pdev); + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* Setup netdev TC information */ + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); + + netdev->max_mtu = ICE_MAX_MTU; + + return 0; +} + +static void ice_decfg_netdev(struct ice_vsi *vsi) +{ + clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); + free_netdev(vsi->netdev); + vsi->netdev = NULL; +} + +static int ice_start_eth(struct ice_vsi *vsi) +{ + int err; + + err = ice_init_mac_fltr(vsi->back); if (err) return err; - err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); - if (err) { - dev_err(dev, "BAR0 I/O map error %d\n", err); - return err; - } + rtnl_lock(); + err = ice_vsi_open(vsi); + rtnl_unlock(); - pf = ice_allocate_pf(dev); - if (!pf) - return -ENOMEM; + return err; +} - /* initialize Auxiliary index to invalid value */ - pf->aux_idx = -1; +static int ice_init_eth(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + int err; - /* set up for high or low DMA */ - err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); - if (err) { - dev_err(dev, "DMA configuration failed: 0x%x\n", err); + if (!vsi) + return -EINVAL; + + /* init channel list */ + INIT_LIST_HEAD(&vsi->ch_list); + + err = ice_cfg_netdev(vsi); + if (err) return err; - } + /* Setup DCB netlink interface */ + ice_dcbnl_setup(vsi); - pci_set_master(pdev); + err = ice_init_mac_fltr(pf); + if (err) + goto err_init_mac_fltr; - pf->pdev = pdev; - pci_set_drvdata(pdev, pf); - set_bit(ICE_DOWN, pf->state); - /* Disable service task until DOWN bit is cleared */ - set_bit(ICE_SERVICE_DIS, pf->state); + err = ice_devlink_create_pf_port(pf); + if (err) + goto err_devlink_create_pf_port; - hw = &pf->hw; - hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; - pci_save_state(pdev); + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); - hw->back = pf; - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_device_id = pdev->subsystem_device; - hw->bus.device = PCI_SLOT(pdev->devfn); - hw->bus.func = PCI_FUNC(pdev->devfn); - ice_set_ctrlq_len(hw); + err = ice_register_netdev(vsi); + if (err) + goto err_register_netdev; - pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + err = ice_tc_indir_block_register(vsi); + if (err) + goto err_tc_indir_block_register; -#ifndef CONFIG_DYNAMIC_DEBUG - if (debug < -1) - hw->debug_mask = debug; -#endif + ice_napi_add(vsi); + + return 0; + +err_tc_indir_block_register: + ice_unregister_netdev(vsi); +err_register_netdev: + ice_devlink_destroy_pf_port(pf); +err_devlink_create_pf_port: +err_init_mac_fltr: + ice_decfg_netdev(vsi); + return err; +} + +static void ice_deinit_eth(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); + + if (!vsi) + return; + + ice_vsi_close(vsi); + ice_unregister_netdev(vsi); + ice_devlink_destroy_pf_port(pf); + ice_tc_indir_block_unregister(vsi); + ice_decfg_netdev(vsi); +} + +static int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err; err = ice_init_hw(hw); if (err) { dev_err(dev, "ice_init_hw failed: %d\n", err); - err = -EIO; - goto err_exit_unroll; + return err; } ice_init_feature_support(pf); @@ -4721,62 +4705,31 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); - goto err_init_pf_unroll; + goto err_init_pf; } - ice_devlink_init_regions(pf); - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; pf->hw.udp_tunnel_nic.flags = UDP_TUNNEL_NIC_INFO_MAY_SLEEP; pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - i = 0; if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = + pf->hw.udp_tunnel_nic.tables[0].n_entries = pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = + pf->hw.udp_tunnel_nic.tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; - i++; } if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[i].n_entries = + pf->hw.udp_tunnel_nic.tables[1].n_entries = pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[i].tunnel_types = + pf->hw.udp_tunnel_nic.tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; - i++; - } - - pf->num_alloc_vsi = hw->func_caps.guar_num_vsi; - if (!pf->num_alloc_vsi) { - err = -EIO; - goto err_init_pf_unroll; - } - if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { - dev_warn(&pf->pdev->dev, - "limiting the VSI count due to UDP tunnel limitation %d > %d\n", - pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); - pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; - } - - pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), - GFP_KERNEL); - if (!pf->vsi) { - err = -ENOMEM; - goto err_init_pf_unroll; - } - - pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, - sizeof(*pf->vsi_stats), GFP_KERNEL); - if (!pf->vsi_stats) { - err = -ENOMEM; - goto err_init_vsi_unroll; } err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); err = -EIO; - goto err_init_vsi_stats_unroll; + goto err_init_interrupt_scheme; } /* In case of MSIX we are going to setup the misc vector right here @@ -4787,49 +4740,94 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_init_interrupt_unroll; + goto err_req_irq_msix_misc; } - /* create switch struct for the switch element created by FW on boot */ - pf->first_sw = devm_kzalloc(dev, sizeof(*pf->first_sw), GFP_KERNEL); - if (!pf->first_sw) { - err = -ENOMEM; - goto err_msix_misc_unroll; - } + return 0; - if (hw->evb_veb) - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; - else - pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; +err_req_irq_msix_misc: + ice_clear_interrupt_scheme(pf); +err_init_interrupt_scheme: + ice_deinit_pf(pf); +err_init_pf: + ice_deinit_hw(hw); + return err; +} - pf->first_sw->pf = pf; +static void ice_deinit_dev(struct ice_pf *pf) +{ + ice_free_irq_msix_misc(pf); + ice_clear_interrupt_scheme(pf); + ice_deinit_pf(pf); + ice_deinit_hw(&pf->hw); +} - /* record the sw_id available for later use */ - pf->first_sw->sw_id = hw->port_info->sw_id; +static void ice_init_features(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); - err = ice_setup_pf_sw(pf); - if (err) { - dev_err(dev, "probe failed due to setup PF switch: %d\n", err); - goto err_alloc_sw_unroll; - } + if (ice_is_safe_mode(pf)) + return; - clear_bit(ICE_SERVICE_DIS, pf->state); + /* initialize DDP driven features */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_init(pf); - /* tell the firmware we are up */ - err = ice_send_version(pf); - if (err) { - dev_err(dev, "probe failed sending driver version %s. error: %d\n", - UTS_RELEASE, err); - goto err_send_version_unroll; + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_init(pf); + + /* Note: Flow director init failure is non-fatal to load */ + if (ice_init_fdir(pf)) + dev_err(dev, "could not initialize flow director\n"); + + /* Note: DCB init failure is non-fatal to load */ + if (ice_init_pf_dcb(pf, false)) { + clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); + clear_bit(ICE_FLAG_DCB_ENA, pf->flags); + } else { + ice_cfg_lldp_mib_change(&pf->hw, true); } - /* since everything is good, start the service timer */ - mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + if (ice_init_lag(pf)) + dev_warn(dev, "Failed to init link aggregation support\n"); +} + +static void ice_deinit_features(struct ice_pf *pf) +{ + ice_deinit_lag(pf); + if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) + ice_cfg_lldp_mib_change(&pf->hw, false); + ice_deinit_fdir(pf); + if (ice_is_feature_supported(pf, ICE_F_GNSS)) + ice_gnss_exit(pf); + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_release(pf); +} + +static void ice_init_wakeup(struct ice_pf *pf) +{ + /* Save wakeup reason register for later use */ + pf->wakeup_reason = rd32(&pf->hw, PFPM_WUS); + + /* check for a power management event */ + ice_print_wake_reason(pf); + + /* clear wake status, all bits */ + wr32(&pf->hw, PFPM_WUS, U32_MAX); + + /* Disable WoL at init, wait for user to enable */ + device_set_wakeup_enable(ice_pf_to_dev(pf), false); +} + +static int ice_init_link(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; err = ice_init_link_events(pf->hw.port_info); if (err) { dev_err(dev, "ice_init_link_events failed: %d\n", err); - goto err_send_version_unroll; + return err; } /* not a fatal error if this fails */ @@ -4865,122 +4863,350 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) set_bit(ICE_FLAG_NO_MEDIA, pf->flags); } - ice_verify_cacheline_size(pf); + return err; +} - /* Save wakeup reason register for later use */ - pf->wakeup_reason = rd32(hw, PFPM_WUS); +static int ice_init_pf_sw(struct ice_pf *pf) +{ + bool dvm = ice_is_dvm_ena(&pf->hw); + struct ice_vsi *vsi; + int err; - /* check for a power management event */ - ice_print_wake_reason(pf); + /* create switch struct for the switch element created by FW on boot */ + pf->first_sw = kzalloc(sizeof(*pf->first_sw), GFP_KERNEL); + if (!pf->first_sw) + return -ENOMEM; - /* clear wake status, all bits */ - wr32(hw, PFPM_WUS, U32_MAX); + if (pf->hw.evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; - /* Disable WoL at init, wait for user to enable */ - device_set_wakeup_enable(dev, false); + pf->first_sw->pf = pf; - if (ice_is_safe_mode(pf)) { - ice_set_safe_mode_vlan_cfg(pf); - goto probe_done; + /* record the sw_id available for later use */ + pf->first_sw->sw_id = pf->hw.port_info->sw_id; + + err = ice_aq_set_port_params(pf->hw.port_info, dvm, NULL); + if (err) + goto err_aq_set_port_params; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + err = -ENOMEM; + goto err_pf_vsi_setup; } - /* initialize DDP driven features */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_init(pf); + return 0; - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_init(pf); +err_pf_vsi_setup: +err_aq_set_port_params: + kfree(pf->first_sw); + return err; +} - /* Note: Flow director init failure is non-fatal to load */ - if (ice_init_fdir(pf)) - dev_err(dev, "could not initialize flow director\n"); +static void ice_deinit_pf_sw(struct ice_pf *pf) +{ + struct ice_vsi *vsi = ice_get_main_vsi(pf); - /* Note: DCB init failure is non-fatal to load */ - if (ice_init_pf_dcb(pf, false)) { - clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - clear_bit(ICE_FLAG_DCB_ENA, pf->flags); - } else { - ice_cfg_lldp_mib_change(&pf->hw, true); + if (!vsi) + return; + + ice_vsi_release(vsi); + kfree(pf->first_sw); +} + +static int ice_alloc_vsis(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + + pf->num_alloc_vsi = pf->hw.func_caps.guar_num_vsi; + if (!pf->num_alloc_vsi) + return -EIO; + + if (pf->num_alloc_vsi > UDP_TUNNEL_NIC_MAX_SHARING_DEVICES) { + dev_warn(dev, + "limiting the VSI count due to UDP tunnel limitation %d > %d\n", + pf->num_alloc_vsi, UDP_TUNNEL_NIC_MAX_SHARING_DEVICES); + pf->num_alloc_vsi = UDP_TUNNEL_NIC_MAX_SHARING_DEVICES; } - if (ice_init_lag(pf)) - dev_warn(dev, "Failed to init link aggregation support\n"); + pf->vsi = devm_kcalloc(dev, pf->num_alloc_vsi, sizeof(*pf->vsi), + GFP_KERNEL); + if (!pf->vsi) + return -ENOMEM; + + pf->vsi_stats = devm_kcalloc(dev, pf->num_alloc_vsi, + sizeof(*pf->vsi_stats), GFP_KERNEL); + if (!pf->vsi_stats) { + devm_kfree(dev, pf->vsi); + return -ENOMEM; + } - /* print PCI link speed and width */ - pcie_print_link_status(pf->pdev); + return 0; +} -probe_done: - err = ice_devlink_create_pf_port(pf); +static void ice_dealloc_vsis(struct ice_pf *pf) +{ + devm_kfree(ice_pf_to_dev(pf), pf->vsi_stats); + pf->vsi_stats = NULL; + + pf->num_alloc_vsi = 0; + devm_kfree(ice_pf_to_dev(pf), pf->vsi); + pf->vsi = NULL; +} + +static int ice_init_devlink(struct ice_pf *pf) +{ + int err; + + err = ice_devlink_register_params(pf); if (err) - goto err_create_pf_port; + return err; - vsi = ice_get_main_vsi(pf); - if (!vsi || !vsi->netdev) { - err = -EINVAL; - goto err_netdev_reg; - } + ice_devlink_init_regions(pf); + ice_devlink_register(pf); - SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); + return 0; +} + +static void ice_deinit_devlink(struct ice_pf *pf) +{ + ice_devlink_unregister(pf); + ice_devlink_destroy_regions(pf); + ice_devlink_unregister_params(pf); +} + +static int ice_init(struct ice_pf *pf) +{ + int err; + + err = ice_init_dev(pf); + if (err) + return err; - err = ice_register_netdev(pf); + err = ice_alloc_vsis(pf); if (err) - goto err_netdev_reg; + goto err_alloc_vsis; - err = ice_devlink_register_params(pf); + err = ice_init_pf_sw(pf); if (err) - goto err_netdev_reg; + goto err_init_pf_sw; + + ice_init_wakeup(pf); + + err = ice_init_link(pf); + if (err) + goto err_init_link; + + err = ice_send_version(pf); + if (err) + goto err_init_link; + + ice_verify_cacheline_size(pf); + + if (ice_is_safe_mode(pf)) + ice_set_safe_mode_vlan_cfg(pf); + else + /* print PCI link speed and width */ + pcie_print_link_status(pf->pdev); /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); - if (ice_is_rdma_ena(pf)) { - pf->aux_idx = ida_alloc(&ice_aux_ida, GFP_KERNEL); - if (pf->aux_idx < 0) { - dev_err(dev, "Failed to allocate device ID for AUX driver\n"); - err = -ENOMEM; - goto err_devlink_reg_param; - } + clear_bit(ICE_SERVICE_DIS, pf->state); - err = ice_init_rdma(pf); - if (err) { - dev_err(dev, "Failed to initialize RDMA: %d\n", err); - err = -EIO; - goto err_init_aux_unroll; - } - } else { - dev_warn(dev, "RDMA is not supported on this device\n"); - } + /* since everything is good, start the service timer */ + mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); - ice_devlink_register(pf); return 0; -err_init_aux_unroll: - pf->adev = NULL; - ida_free(&ice_aux_ida, pf->aux_idx); -err_devlink_reg_param: - ice_devlink_unregister_params(pf); -err_netdev_reg: - ice_devlink_destroy_pf_port(pf); -err_create_pf_port: -err_send_version_unroll: - ice_vsi_release_all(pf); -err_alloc_sw_unroll: +err_init_link: + ice_deinit_pf_sw(pf); +err_init_pf_sw: + ice_dealloc_vsis(pf); +err_alloc_vsis: + ice_deinit_dev(pf); + return err; +} + +static void ice_deinit(struct ice_pf *pf) +{ set_bit(ICE_SERVICE_DIS, pf->state); set_bit(ICE_DOWN, pf->state); - devm_kfree(dev, pf->first_sw); -err_msix_misc_unroll: - ice_free_irq_msix_misc(pf); -err_init_interrupt_unroll: - ice_clear_interrupt_scheme(pf); -err_init_vsi_stats_unroll: - devm_kfree(dev, pf->vsi_stats); - pf->vsi_stats = NULL; -err_init_vsi_unroll: - devm_kfree(dev, pf->vsi); -err_init_pf_unroll: - ice_deinit_pf(pf); - ice_devlink_destroy_regions(pf); - ice_deinit_hw(hw); -err_exit_unroll: + + ice_deinit_pf_sw(pf); + ice_dealloc_vsis(pf); + ice_deinit_dev(pf); +} + +/** + * ice_load - load pf by init hw and starting VSI + * @pf: pointer to the pf instance + */ +int ice_load(struct ice_pf *pf) +{ + struct ice_vsi_cfg_params params = {}; + struct ice_vsi *vsi; + int err; + + err = ice_reset(&pf->hw, ICE_RESET_PFR); + if (err) + return err; + + err = ice_init_dev(pf); + if (err) + return err; + + vsi = ice_get_main_vsi(pf); + + params = ice_vsi_to_params(vsi); + params.flags = ICE_VSI_FLAG_INIT; + + err = ice_vsi_cfg(vsi, ¶ms); + if (err) + goto err_vsi_cfg; + + err = ice_start_eth(ice_get_main_vsi(pf)); + if (err) + goto err_start_eth; + + err = ice_init_rdma(pf); + if (err) + goto err_init_rdma; + + ice_init_features(pf); + ice_service_task_restart(pf); + + clear_bit(ICE_DOWN, pf->state); + + return 0; + +err_init_rdma: + ice_vsi_close(ice_get_main_vsi(pf)); +err_start_eth: + ice_vsi_decfg(ice_get_main_vsi(pf)); +err_vsi_cfg: + ice_deinit_dev(pf); + return err; +} + +/** + * ice_unload - unload pf by stopping VSI and deinit hw + * @pf: pointer to the pf instance + */ +void ice_unload(struct ice_pf *pf) +{ + ice_deinit_features(pf); + ice_deinit_rdma(pf); + ice_vsi_close(ice_get_main_vsi(pf)); + ice_vsi_decfg(ice_get_main_vsi(pf)); + ice_deinit_dev(pf); +} + +/** + * ice_probe - Device initialization routine + * @pdev: PCI device information struct + * @ent: entry in ice_pci_tbl + * + * Returns 0 on success, negative on failure + */ +static int +ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) +{ + struct device *dev = &pdev->dev; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + + if (pdev->is_virtfn) { + dev_err(dev, "can't probe a virtual function\n"); + return -EINVAL; + } + + /* this driver uses devres, see + * Documentation/driver-api/driver-model/devres.rst + */ + err = pcim_enable_device(pdev); + if (err) + return err; + + err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), dev_driver_string(dev)); + if (err) { + dev_err(dev, "BAR0 I/O map error %d\n", err); + return err; + } + + pf = ice_allocate_pf(dev); + if (!pf) + return -ENOMEM; + + /* initialize Auxiliary index to invalid value */ + pf->aux_idx = -1; + + /* set up for high or low DMA */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (err) { + dev_err(dev, "DMA configuration failed: 0x%x\n", err); + return err; + } + + pci_set_master(pdev); + + pf->pdev = pdev; + pci_set_drvdata(pdev, pf); + set_bit(ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(ICE_SERVICE_DIS, pf->state); + + hw = &pf->hw; + hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; + pci_save_state(pdev); + + hw->back = pf; + hw->port_info = NULL; + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + pci_read_config_byte(pdev, PCI_REVISION_ID, &hw->revision_id); + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + hw->bus.device = PCI_SLOT(pdev->devfn); + hw->bus.func = PCI_FUNC(pdev->devfn); + ice_set_ctrlq_len(hw); + + pf->msg_enable = netif_msg_init(debug, ICE_DFLT_NETIF_M); + +#ifndef CONFIG_DYNAMIC_DEBUG + if (debug < -1) + hw->debug_mask = debug; +#endif + + err = ice_init(pf); + if (err) + goto err_init; + + err = ice_init_eth(pf); + if (err) + goto err_init_eth; + + err = ice_init_rdma(pf); + if (err) + goto err_init_rdma; + + err = ice_init_devlink(pf); + if (err) + goto err_init_devlink; + + ice_init_features(pf); + + return 0; + +err_init_devlink: + ice_deinit_rdma(pf); +err_init_rdma: + ice_deinit_eth(pf); +err_init_eth: + ice_deinit(pf); +err_init: pci_disable_device(pdev); return err; } @@ -5053,65 +5279,42 @@ static void ice_setup_mc_magic_wake(struct ice_pf *pf) static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - struct ice_hw *hw; int i; - hw = &pf->hw; - - ice_devlink_unregister(pf); for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { if (!ice_is_reset_in_progress(pf->state)) break; msleep(100); } - ice_tc_indir_block_remove(pf); - if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { set_bit(ICE_VF_RESETS_DISABLED, pf->state); ice_free_vfs(pf); } ice_service_task_stop(pf); - ice_aq_cancel_waiting_tasks(pf); - ice_unplug_aux_dev(pf); - if (pf->aux_idx >= 0) - ida_free(&ice_aux_ida, pf->aux_idx); - ice_devlink_unregister_params(pf); set_bit(ICE_DOWN, pf->state); - ice_deinit_lag(pf); - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) - ice_ptp_release(pf); - if (ice_is_feature_supported(pf, ICE_F_GNSS)) - ice_gnss_exit(pf); if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); - ice_setup_mc_magic_wake(pf); + ice_deinit_features(pf); + ice_deinit_devlink(pf); + ice_deinit_rdma(pf); + ice_deinit_eth(pf); + ice_deinit(pf); + ice_vsi_release_all(pf); - mutex_destroy(&hw->fdir_fltr_lock); - ice_devlink_destroy_pf_port(pf); + + ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - ice_free_irq_msix_misc(pf); - ice_for_each_vsi(pf, i) { - if (!pf->vsi[i]) - continue; - ice_vsi_free_q_vectors(pf->vsi[i]); - } - devm_kfree(&pdev->dev, pf->vsi_stats); - pf->vsi_stats = NULL; - ice_deinit_pf(pf); - ice_devlink_destroy_regions(pf); - ice_deinit_hw(hw); /* Issue a PFR as part of the prescribed driver unload flow. Do not * do it via ice_schedule_reset() since there is no need to rebuild * and the service task is already stopped. */ - ice_reset(hw, ICE_RESET_PFR); + ice_reset(&pf->hw, ICE_RESET_PFR); pci_wait_for_pending_transaction(pdev); - ice_clear_interrupt_scheme(pf); pci_disable_device(pdev); } @@ -5539,7 +5742,7 @@ static int __init ice_module_init(void) pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); - ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; @@ -6145,12 +6348,12 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) } /** - * ice_vsi_cfg - Setup the VSI + * ice_vsi_cfg_lan - Setup the VSI lan related config * @vsi: the VSI being configured * * Return 0 on success and negative value on error */ -int ice_vsi_cfg(struct ice_vsi *vsi) +int ice_vsi_cfg_lan(struct ice_vsi *vsi) { int err; @@ -6366,7 +6569,7 @@ int ice_up(struct ice_vsi *vsi) { int err; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (!err) err = ice_up_complete(vsi); @@ -6934,7 +7137,7 @@ int ice_vsi_open_ctrl(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -6988,7 +7191,7 @@ int ice_vsi_open(struct ice_vsi *vsi) if (err) goto err_setup_rx; - err = ice_vsi_cfg(vsi); + err = ice_vsi_cfg_lan(vsi); if (err) goto err_setup_rx; @@ -7073,7 +7276,7 @@ static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) continue; /* rebuild the VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "rebuild VSI failed, err %d, VSI index %d, type %s\n", err, vsi->idx, ice_vsi_type_str(type)); @@ -7329,18 +7532,6 @@ clear_recovery: } /** - * ice_max_xdp_frame_size - returns the maximum allowed frame size for XDP - * @vsi: Pointer to VSI structure - */ -static int ice_max_xdp_frame_size(struct ice_vsi *vsi) -{ - if (PAGE_SIZE >= 8192 || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - return ICE_RXBUF_2048 - XDP_PACKET_HEADROOM; - else - return ICE_RXBUF_3072; -} - -/** * ice_change_mtu - NDO callback to change the MTU * @netdev: network interface device structure * @new_mtu: new value for maximum frame size @@ -7352,6 +7543,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; + struct bpf_prog *prog; u8 count = 0; int err = 0; @@ -7360,7 +7552,8 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return 0; } - if (ice_is_xdp_ena_vsi(vsi)) { + prog = vsi->xdp_prog; + if (prog && !prog->aux->xdp_has_frags) { int frame_size = ice_max_xdp_frame_size(vsi); if (new_mtu + ICE_ETH_PKT_HDR_PAD > frame_size) { @@ -7368,6 +7561,12 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) frame_size - ICE_ETH_PKT_HDR_PAD); return -EINVAL; } + } else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) { + if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) { + netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n", + ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD); + return -EINVAL; + } } /* if a reset is in progress, wait for some time for it to complete */ @@ -8418,12 +8617,9 @@ static void ice_remove_q_channels(struct ice_vsi *vsi, bool rem_fltr) /* clear the VSI from scheduler tree */ ice_rm_vsi_lan_cfg(ch->ch_vsi->port_info, ch->ch_vsi->idx); - /* Delete VSI from FW */ + /* Delete VSI from FW, PF and HW VSI arrays */ ice_vsi_delete(ch->ch_vsi); - /* Delete VSI from PF and HW VSI arrays */ - ice_vsi_clear(ch->ch_vsi); - /* free the channel */ kfree(ch); } @@ -8482,7 +8678,7 @@ static int ice_rebuild_channels(struct ice_pf *pf) type = vsi->type; /* rebuild ADQ VSI */ - err = ice_vsi_rebuild(vsi, true); + err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT); if (err) { dev_err(dev, "VSI (type:%s) at index %d rebuild failed, err %d\n", ice_vsi_type_str(type), vsi->idx, err); @@ -8714,14 +8910,14 @@ config_tcf: cur_rxq = vsi->num_rxq; /* proceed with rebuild main VSI using correct number of queues */ - ret = ice_vsi_rebuild(vsi, false); + ret = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT); if (ret) { /* fallback to current number of queues */ dev_info(dev, "Rebuild failed with new queues, try with current number of queues\n"); vsi->req_txq = cur_txq; vsi->req_rxq = cur_rxq; clear_bit(ICE_RESET_FAILED, pf->state); - if (ice_vsi_rebuild(vsi, false)) { + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT)) { dev_err(dev, "Rebuild of main VSI failed again\n"); return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 3ba1408c56a9..96a64c25e2ef 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -41,21 +41,6 @@ static void ice_free_vf_entries(struct ice_pf *pf) } /** - * ice_vf_vsi_release - invalidate the VF's VSI after freeing it - * @vf: invalidate this VF's VSI after freeing it - */ -static void ice_vf_vsi_release(struct ice_vf *vf) -{ - struct ice_vsi *vsi = ice_get_vf_vsi(vf); - - if (WARN_ON(!vsi)) - return; - - ice_vsi_release(vsi); - ice_vf_invalidate_vsi(vf); -} - -/** * ice_free_vf_res - Free a VF's resources * @vf: pointer to the VF info */ @@ -248,11 +233,16 @@ void ice_free_vfs(struct ice_pf *pf) */ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) { - struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_vsi_cfg_params params = {}; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_VF, vf, NULL); + params.type = ICE_VSI_VF; + params.pi = ice_vf_get_port_info(vf); + params.vf = vf; + params.flags = ICE_VSI_FLAG_INIT; + + vsi = ice_vsi_setup(pf, ¶ms); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF VSI\n"); @@ -583,51 +573,19 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) */ static int ice_init_vf_vsi_res(struct ice_vf *vf) { - struct ice_vsi_vlan_ops *vlan_ops; struct ice_pf *pf = vf->pf; - u8 broadcast[ETH_ALEN]; struct ice_vsi *vsi; - struct device *dev; int err; vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); - dev = ice_pf_to_dev(pf); vsi = ice_vf_vsi_setup(vf); if (!vsi) return -ENOMEM; - err = ice_vsi_add_vlan_zero(vsi); - if (err) { - dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", - vf->vf_id); - goto release_vsi; - } - - vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); - err = vlan_ops->ena_rx_filtering(vsi); - if (err) { - dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", - vf->vf_id); - goto release_vsi; - } - - eth_broadcast_addr(broadcast); - err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); - if (err) { - dev_err(dev, "Failed to add broadcast MAC filter for VF %d, error %d\n", - vf->vf_id, err); - goto release_vsi; - } - - err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk); - if (err) { - dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", - vf->vf_id); + err = ice_vf_init_host_cfg(vf, vsi); + if (err) goto release_vsi; - } - - vf->num_mac = 1; return 0; @@ -697,6 +655,21 @@ static void ice_sriov_free_vf(struct ice_vf *vf) } /** + * ice_sriov_clear_reset_state - clears VF Reset status register + * @vf: the vf to configure + */ +static void ice_sriov_clear_reset_state(struct ice_vf *vf) +{ + struct ice_hw *hw = &vf->pf->hw; + + /* Clear the reset status register so that VF immediately sees that + * the device is resetting, even if hardware hasn't yet gotten around + * to clearing VFGEN_RSTAT for us. + */ + wr32(hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_INPROGRESS); +} + +/** * ice_sriov_clear_mbx_register - clears SRIOV VF's mailbox registers * @vf: the vf to configure */ @@ -799,23 +772,19 @@ static void ice_sriov_clear_reset_trigger(struct ice_vf *vf) } /** - * ice_sriov_vsi_rebuild - release and rebuild VF's VSI - * @vf: VF to release and setup the VSI for + * ice_sriov_create_vsi - Create a new VSI for a VF + * @vf: VF to create the VSI for * - * This is only called when a single VF is being reset (i.e. VFR, VFLR, host VF - * configuration change, etc.). + * This is called by ice_vf_recreate_vsi to create the new VSI after the old + * VSI has been released. */ -static int ice_sriov_vsi_rebuild(struct ice_vf *vf) +static int ice_sriov_create_vsi(struct ice_vf *vf) { - struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; - ice_vf_vsi_release(vf); - if (!ice_vf_vsi_setup(vf)) { - dev_err(ice_pf_to_dev(pf), - "Failed to release and setup the VF%u's VSI\n", - vf->vf_id); + vsi = ice_vf_vsi_setup(vf); + if (!vsi) return -ENOMEM; - } return 0; } @@ -826,8 +795,6 @@ static int ice_sriov_vsi_rebuild(struct ice_vf *vf) */ static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf) { - ice_vf_rebuild_host_cfg(vf); - ice_vf_set_initialized(vf); ice_ena_vf_mappings(vf); wr32(&vf->pf->hw, VFGEN_RSTAT(vf->vf_id), VIRTCHNL_VFR_VFACTIVE); } @@ -835,11 +802,13 @@ static void ice_sriov_post_vsi_rebuild(struct ice_vf *vf) static const struct ice_vf_ops ice_sriov_vf_ops = { .reset_type = ICE_VF_RESET, .free = ice_sriov_free_vf, + .clear_reset_state = ice_sriov_clear_reset_state, .clear_mbx_register = ice_sriov_clear_mbx_register, .trigger_reset_register = ice_sriov_trigger_reset_register, .poll_reset_status = ice_sriov_poll_reset_status, .clear_reset_trigger = ice_sriov_clear_reset_trigger, - .vsi_rebuild = ice_sriov_vsi_rebuild, + .irq_close = NULL, + .create_vsi = ice_sriov_create_vsi, .post_vsi_rebuild = ice_sriov_post_vsi_rebuild, }; @@ -879,21 +848,9 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) /* set sriov vf ops for VFs created during SRIOV flow */ vf->vf_ops = &ice_sriov_vf_ops; - vf->vf_sw_id = pf->first_sw; - /* assign default capabilities */ - vf->spoofchk = true; - vf->num_vf_qs = pf->vfs.num_qps_per; - ice_vc_set_default_allowlist(vf); - - /* ctrl_vsi_idx will be set to a valid value only when VF - * creates its first fdir rule. - */ - ice_vf_ctrl_invalidate_vsi(vf); - ice_vf_fdir_init(vf); - - ice_virtchnl_set_dflt_ops(vf); + ice_initialize_vf_entry(vf); - mutex_init(&vf->cfg_lock); + vf->vf_sw_id = pf->first_sw; hash_add_rcu(vfs->table, &vf->entry, vf_id); } @@ -1285,7 +1242,7 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) goto out_put_vf; ivi->vf = vf_id; - ether_addr_copy(ivi->mac, vf->hw_lan_addr.addr); + ether_addr_copy(ivi->mac, vf->hw_lan_addr); /* VF configuration for VLAN and applicable QoS */ ivi->vlan = ice_vf_get_port_vlan_id(vf); @@ -1333,8 +1290,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) return -EINVAL; /* nothing left to do, unicast MAC already set */ - if (ether_addr_equal(vf->dev_lan_addr.addr, mac) && - ether_addr_equal(vf->hw_lan_addr.addr, mac)) { + if (ether_addr_equal(vf->dev_lan_addr, mac) && + ether_addr_equal(vf->hw_lan_addr, mac)) { ret = 0; goto out_put_vf; } @@ -1348,8 +1305,8 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* VF is notified of its new MAC via the PF's response to the * VIRTCHNL_OP_GET_VF_RESOURCES message after the VF has been reset */ - ether_addr_copy(vf->dev_lan_addr.addr, mac); - ether_addr_copy(vf->hw_lan_addr.addr, mac); + ether_addr_copy(vf->dev_lan_addr, mac); + ether_addr_copy(vf->hw_lan_addr, mac); if (is_zero_ether_addr(mac)) { /* VF will send VIRTCHNL_OP_ADD_ETH_ADDR message with its MAC */ vf->pf_set_mac = false; @@ -1750,7 +1707,7 @@ void ice_print_vf_rx_mdd_event(struct ice_vf *vf) dev_info(dev, "%d Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pM. mdd-auto-reset-vfs=%s\n", vf->mdd_rx_events.count, pf->hw.pf_id, vf->vf_id, - vf->dev_lan_addr.addr, + vf->dev_lan_addr, test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags) ? "on" : "off"); } @@ -1794,7 +1751,7 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) dev_info(dev, "%d Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pM.\n", vf->mdd_tx_events.count, hw->pf_id, vf->vf_id, - vf->dev_lan_addr.addr); + vf->dev_lan_addr); } } mutex_unlock(&pf->vfs.table_lock); @@ -1884,7 +1841,7 @@ ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, if (pf_vsi) dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", - &vf->dev_lan_addr.addr[0], + &vf->dev_lan_addr[0], pf_vsi->netdev->dev_addr); } } diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 9b762f7972ce..61f844d22512 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -5420,7 +5420,7 @@ ice_add_adv_recipe(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, */ status = ice_add_special_words(rinfo, lkup_exts, ice_is_dvm_ena(hw)); if (status) - goto err_free_lkup_exts; + goto err_unroll; /* Group match words into recipes using preferred recipe grouping * criteria. diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 80706f7330f4..6b48cbc049c6 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -1688,7 +1688,7 @@ ice_tc_forward_to_queue(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr, struct ice_vsi *ch_vsi = NULL; u16 queue = act->rx_queue; - if (queue > vsi->num_rxq) { + if (queue >= vsi->num_rxq) { NL_SET_ERR_MSG_MOD(fltr->extack, "Unable to add filter because specified queue is invalid"); return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index ccf09c957a1c..466113c86e6f 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -113,12 +113,16 @@ static void ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) { if (tx_buf->skb) { - if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT) + if (tx_buf->tx_flags & ICE_TX_FLAGS_DUMMY_PKT) { devm_kfree(ring->dev, tx_buf->raw_buf); - else if (ice_ring_is_xdp(ring)) - page_frag_free(tx_buf->raw_buf); - else + } else if (ice_ring_is_xdp(ring)) { + if (ring->xsk_pool) + xsk_buff_free(tx_buf->xdp); + else + page_frag_free(tx_buf->raw_buf); + } else { dev_kfree_skb_any(tx_buf->skb); + } if (dma_unmap_len(tx_buf, len)) dma_unmap_single(ring->dev, dma_unmap_addr(tx_buf, dma), @@ -174,8 +178,6 @@ tx_skip_free: tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - tx_ring->next_dd = ICE_RING_QUARTER(tx_ring) - 1; - tx_ring->next_rs = ICE_RING_QUARTER(tx_ring) - 1; if (!tx_ring->netdev) return; @@ -382,6 +384,7 @@ err: */ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) { + struct xdp_buff *xdp = &rx_ring->xdp; struct device *dev = rx_ring->dev; u32 size; u16 i; @@ -390,16 +393,16 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) if (!rx_ring->rx_buf) return; - if (rx_ring->skb) { - dev_kfree_skb(rx_ring->skb); - rx_ring->skb = NULL; - } - if (rx_ring->xsk_pool) { ice_xsk_clean_rx_ring(rx_ring); goto rx_skip_free; } + if (xdp->data) { + xdp_return_buff(xdp); + xdp->data = NULL; + } + /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i]; @@ -437,6 +440,7 @@ rx_skip_free: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; + rx_ring->first_desc = 0; rx_ring->next_to_use = 0; } @@ -506,6 +510,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) rx_ring->next_to_use = 0; rx_ring->next_to_clean = 0; + rx_ring->first_desc = 0; if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); @@ -523,8 +528,16 @@ err: return -ENOMEM; } +/** + * ice_rx_frame_truesize + * @rx_ring: ptr to Rx ring + * @size: size + * + * calculate the truesize with taking into the account PAGE_SIZE of + * underlying arch + */ static unsigned int -ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused size) +ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size) { unsigned int truesize; @@ -545,34 +558,39 @@ ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, unsigned int __maybe_unused s * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action + * @rx_buf: Rx buffer to store the XDP action * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ -static int +static void ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring) + struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, + struct ice_rx_buf *rx_buf) { - int err; + unsigned int ret = ICE_XDP_PASS; u32 act; + if (!xdp_prog) + goto exit; + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: - return ICE_XDP_PASS; + break; case XDP_TX: if (static_branch_unlikely(&ice_xdp_locking_key)) spin_lock(&xdp_ring->tx_lock); - err = ice_xmit_xdp_ring(xdp->data, xdp->data_end - xdp->data, xdp_ring); + ret = __ice_xmit_xdp_ring(xdp, xdp_ring); if (static_branch_unlikely(&ice_xdp_locking_key)) spin_unlock(&xdp_ring->tx_lock); - if (err == ICE_XDP_CONSUMED) + if (ret == ICE_XDP_CONSUMED) goto out_failure; - return err; + break; case XDP_REDIRECT: - err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); - if (err) + if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog)) goto out_failure; - return ICE_XDP_REDIR; + ret = ICE_XDP_REDIR; + break; default: bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; @@ -581,8 +599,12 @@ out_failure: trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: - return ICE_XDP_CONSUMED; + ret = ICE_XDP_CONSUMED; } +exit: + rx_buf->act = ret; + if (unlikely(xdp_buff_has_frags(xdp))) + ice_set_rx_bufs_act(xdp, rx_ring, ret); } /** @@ -605,6 +627,7 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, unsigned int queue_index = smp_processor_id(); struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *xdp_ring; + struct ice_tx_buf *tx_buf; int nxmit = 0, i; if (test_bit(ICE_VSI_DOWN, vsi->state)) @@ -627,16 +650,18 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, xdp_ring = vsi->xdp_rings[queue_index]; } + tx_buf = &xdp_ring->tx_buf[xdp_ring->next_to_use]; for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; int err; - err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring); + err = ice_xmit_xdp_ring(xdpf, xdp_ring); if (err != ICE_XDP_TX) break; nxmit++; } + tx_buf->rs_idx = ice_set_rs_bit(xdp_ring); if (unlikely(flags & XDP_XMIT_FLUSH)) ice_xdp_ring_update_tail(xdp_ring); @@ -706,7 +731,7 @@ ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) * buffers. Then bump tail at most one time. Grouping like this lets us avoid * multiple tail writes per call. */ -bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, u16 cleaned_count) +bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; @@ -783,7 +808,6 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) /** * ice_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buf: buffer containing the page - * @rx_buf_pgcnt: rx_buf page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling ice_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is @@ -791,7 +815,7 @@ ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) * page freed */ static bool -ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) +ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) { unsigned int pagecnt_bias = rx_buf->pagecnt_bias; struct page *page = rx_buf->page; @@ -802,7 +826,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) + if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) return false; #else #define ICE_LAST_OFFSET \ @@ -824,33 +848,44 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf, int rx_buf_pgcnt) } /** - * ice_add_rx_frag - Add contents of Rx buffer to sk_buff as a frag + * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag * @rx_ring: Rx descriptor ring to transact packets on + * @xdp: xdp buff to place the data into * @rx_buf: buffer containing page to add - * @skb: sk_buff to place the data into * @size: packet length from rx_desc * - * This function will add the data contained in rx_buf->page to the skb. - * It will just attach the page as a frag to the skb. - * The function will then update the page offset. + * This function will add the data contained in rx_buf->page to the xdp buf. + * It will just attach the page as a frag. */ -static void -ice_add_rx_frag(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, - struct sk_buff *skb, unsigned int size) +static int +ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + struct ice_rx_buf *rx_buf, const unsigned int size) { -#if (PAGE_SIZE >= 8192) - unsigned int truesize = SKB_DATA_ALIGN(size + rx_ring->rx_offset); -#else - unsigned int truesize = ice_rx_pg_size(rx_ring) / 2; -#endif + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); if (!size) - return; - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page, - rx_buf->page_offset, size, truesize); + return 0; + + if (!xdp_buff_has_frags(xdp)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(xdp); + } + + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { + if (unlikely(xdp_buff_has_frags(xdp))) + ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, + rx_buf->page_offset, size); + sinfo->xdp_frags_size += size; - /* page is being used so we must update the page offset */ - ice_rx_buf_adjust_pg_offset(rx_buf, truesize); + if (page_is_pfmemalloc(rx_buf->page)) + xdp_buff_set_frag_pfmemalloc(xdp); + + return 0; } /** @@ -886,19 +921,18 @@ ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use * @rx_ring: Rx descriptor ring to transact packets on * @size: size of buffer to add to skb - * @rx_buf_pgcnt: rx_buf page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct ice_rx_buf * ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, - int *rx_buf_pgcnt) + const unsigned int ntc) { struct ice_rx_buf *rx_buf; - rx_buf = &rx_ring->rx_buf[rx_ring->next_to_clean]; - *rx_buf_pgcnt = + rx_buf = &rx_ring->rx_buf[ntc]; + rx_buf->pgcnt = #if (PAGE_SIZE < 8192) page_count(rx_buf->page); #else @@ -922,26 +956,25 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, /** * ice_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on - * @rx_buf: Rx buffer to pull data from * @xdp: xdp_buff pointing to the data * - * This function builds an skb around an existing Rx buffer, taking care - * to set up the skb correctly and avoid any memcpy overhead. + * This function builds an skb around an existing XDP buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. Driver has + * already combined frags (if any) to skb_shared_info. */ static struct sk_buff * -ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, - struct xdp_buff *xdp) +ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { u8 metasize = xdp->data - xdp->data_meta; -#if (PAGE_SIZE < 8192) - unsigned int truesize = ice_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(xdp->data_end - - xdp->data_hard_start); -#endif + struct skb_shared_info *sinfo = NULL; + unsigned int nr_frags; struct sk_buff *skb; + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } + /* Prefetch first cache line of first page. If xdp->data_meta * is unused, this points exactly as xdp->data, otherwise we * likely have a consumer accessing first few bytes of meta @@ -949,7 +982,7 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, */ net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ - skb = napi_build_skb(xdp->data_hard_start, truesize); + skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; @@ -964,8 +997,11 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, if (metasize) skb_metadata_set(skb, metasize); - /* buffer is used by skb, update page_offset */ - ice_rx_buf_adjust_pg_offset(rx_buf, truesize); + if (unlikely(xdp_buff_has_frags(xdp))) + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); return skb; } @@ -981,24 +1017,30 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, * skb correctly. */ static struct sk_buff * -ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, - struct xdp_buff *xdp) +ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) { - unsigned int metasize = xdp->data - xdp->data_meta; unsigned int size = xdp->data_end - xdp->data; + struct skb_shared_info *sinfo = NULL; + struct ice_rx_buf *rx_buf; + unsigned int nr_frags = 0; unsigned int headlen; struct sk_buff *skb; /* prefetch first cache line of first page */ - net_prefetch(xdp->data_meta); + net_prefetch(xdp->data); + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + } /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - ICE_RX_HDR_SIZE + metasize, + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; + rx_buf = &rx_ring->rx_buf[rx_ring->first_desc]; skb_record_rx_queue(skb, rx_ring->q_index); /* Determine available headroom for copy */ headlen = size; @@ -1006,32 +1048,42 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen + metasize), xdp->data_meta, - ALIGN(headlen + metasize, sizeof(long))); - - if (metasize) { - skb_metadata_set(skb, metasize); - __skb_pull(skb, metasize); - } + memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, + sizeof(long))); /* if we exhaust the linear part then add what is left as a frag */ size -= headlen; if (size) { -#if (PAGE_SIZE >= 8192) - unsigned int truesize = SKB_DATA_ALIGN(size); -#else - unsigned int truesize = ice_rx_pg_size(rx_ring) / 2; -#endif + /* besides adding here a partial frag, we are going to add + * frags from xdp_buff, make sure there is enough space for + * them + */ + if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) { + dev_kfree_skb(skb); + return NULL; + } skb_add_rx_frag(skb, 0, rx_buf->page, - rx_buf->page_offset + headlen, size, truesize); - /* buffer is used by skb, update page_offset */ - ice_rx_buf_adjust_pg_offset(rx_buf, truesize); + rx_buf->page_offset + headlen, size, + xdp->frame_sz); } else { - /* buffer is unused, reset bias back to rx_buf; data was copied - * onto skb's linear part so there's no need for adjusting - * page offset and we can reuse this buffer as-is + /* buffer is unused, change the act that should be taken later + * on; data was copied onto skb's linear part so there's no + * need for adjusting page offset and we can reuse this buffer + * as-is */ - rx_buf->pagecnt_bias++; + rx_buf->act = ICE_SKB_CONSUMED; + } + + if (unlikely(xdp_buff_has_frags(xdp))) { + struct skb_shared_info *skinfo = skb_shinfo(skb); + + memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0], + sizeof(skb_frag_t) * nr_frags); + + xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); } return skb; @@ -1041,26 +1093,17 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, * ice_put_rx_buf - Clean up used buffer and either recycle or free * @rx_ring: Rx descriptor ring to transact packets on * @rx_buf: Rx buffer to pull data from - * @rx_buf_pgcnt: Rx buffer page count pre xdp_do_redirect() * - * This function will update next_to_clean and then clean up the contents - * of the rx_buf. It will either recycle the buffer or unmap it and free - * the associated resources. + * This function will clean up the contents of the rx_buf. It will either + * recycle the buffer or unmap it and free the associated resources. */ static void -ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, - int rx_buf_pgcnt) +ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) { - u16 ntc = rx_ring->next_to_clean + 1; - - /* fetch, update, and store next to clean */ - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - if (!rx_buf) return; - if (ice_can_reuse_rx_page(rx_buf, rx_buf_pgcnt)) { + if (ice_can_reuse_rx_page(rx_buf)) { /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); } else { @@ -1076,27 +1119,6 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf, } /** - * ice_is_non_eop - process handling of non-EOP buffers - * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * - * If the buffer is an EOP buffer, this function exits returning false, - * otherwise return true indicating that this is in fact a non-EOP buffer. - */ -static bool -ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) -{ - /* if we are the last buffer then there is nothing else to do */ -#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) - if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF))) - return false; - - rx_ring->ring_stats->rx_stats.non_eop_descs++; - - return true; -} - -/** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: Rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1110,39 +1132,42 @@ ice_is_non_eop(struct ice_rx_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc) */ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) { - unsigned int total_rx_bytes = 0, total_rx_pkts = 0, frame_sz = 0; - u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); + unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; + struct xdp_buff *xdp = &rx_ring->xdp; struct ice_tx_ring *xdp_ring = NULL; - unsigned int xdp_res, xdp_xmit = 0; - struct sk_buff *skb = rx_ring->skb; struct bpf_prog *xdp_prog = NULL; - struct xdp_buff xdp; + u32 ntc = rx_ring->next_to_clean; + u32 cnt = rx_ring->count; + u32 cached_ntc = ntc; + u32 xdp_xmit = 0; + u32 cached_ntu; bool failure; + u32 first; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) - frame_sz = ice_rx_frame_truesize(rx_ring, 0); + xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0); #endif - xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); xdp_prog = READ_ONCE(rx_ring->xdp_prog); - if (xdp_prog) + if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; + cached_ntu = xdp_ring->next_to_use; + } /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; struct ice_rx_buf *rx_buf; - unsigned char *hard_start; + struct sk_buff *skb; unsigned int size; u16 stat_err_bits; - int rx_buf_pgcnt; u16 vlan_tag = 0; u16 rx_ptype; /* get the Rx desc from Rx ring based on 'next_to_clean' */ - rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = ICE_RX_DESC(rx_ring, ntc); /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr @@ -1166,8 +1191,8 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (rx_desc->wb.rxdid == FDIR_DESC_RXDID && ctrl_vsi->vf) ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc); - ice_put_rx_buf(rx_ring, NULL, 0); - cleaned_count++; + if (++ntc == cnt) + ntc = 0; continue; } @@ -1175,65 +1200,56 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) ICE_RX_FLX_DESC_PKT_LEN_M; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, size, &rx_buf_pgcnt); + rx_buf = ice_get_rx_buf(rx_ring, size, ntc); - if (!size) { - xdp.data = NULL; - xdp.data_end = NULL; - xdp.data_hard_start = NULL; - xdp.data_meta = NULL; - goto construct_skb; - } + if (!xdp->data) { + void *hard_start; - hard_start = page_address(rx_buf->page) + rx_buf->page_offset - - offset; - xdp_prepare_buff(&xdp, hard_start, offset, size, true); + hard_start = page_address(rx_buf->page) + rx_buf->page_offset - + offset; + xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); #if (PAGE_SIZE > 4096) - /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp.frame_sz = ice_rx_frame_truesize(rx_ring, size); + /* At larger PAGE_SIZE, frame_sz depend on len size */ + xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size); #endif + xdp_buff_clear_frags_flag(xdp); + } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { + break; + } + if (++ntc == cnt) + ntc = 0; - if (!xdp_prog) - goto construct_skb; + /* skip if it is NOP desc */ + if (ice_is_non_eop(rx_ring, rx_desc)) + continue; - xdp_res = ice_run_xdp(rx_ring, &xdp, xdp_prog, xdp_ring); - if (!xdp_res) + ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf); + if (rx_buf->act == ICE_XDP_PASS) goto construct_skb; - if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR)) { - xdp_xmit |= xdp_res; - ice_rx_buf_adjust_pg_offset(rx_buf, xdp.frame_sz); - } else { - rx_buf->pagecnt_bias++; - } - total_rx_bytes += size; + total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - cleaned_count++; - ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); + xdp->data = NULL; + rx_ring->first_desc = ntc; continue; construct_skb: - if (skb) { - ice_add_rx_frag(rx_ring, rx_buf, skb, size); - } else if (likely(xdp.data)) { - if (ice_ring_uses_build_skb(rx_ring)) - skb = ice_build_skb(rx_ring, rx_buf, &xdp); - else - skb = ice_construct_skb(rx_ring, rx_buf, &xdp); - } + if (likely(ice_ring_uses_build_skb(rx_ring))) + skb = ice_build_skb(rx_ring, xdp); + else + skb = ice_construct_skb(rx_ring, xdp); /* exit if we failed to retrieve a buffer */ if (!skb) { - rx_ring->ring_stats->rx_stats.alloc_buf_failed++; - if (rx_buf) - rx_buf->pagecnt_bias++; + rx_ring->ring_stats->rx_stats.alloc_page_failed++; + rx_buf->act = ICE_XDP_CONSUMED; + if (unlikely(xdp_buff_has_frags(xdp))) + ice_set_rx_bufs_act(xdp, rx_ring, + ICE_XDP_CONSUMED); + xdp->data = NULL; + rx_ring->first_desc = ntc; break; } - - ice_put_rx_buf(rx_ring, rx_buf, rx_buf_pgcnt); - cleaned_count++; - - /* skip if it is NOP desc */ - if (ice_is_non_eop(rx_ring, rx_desc)) - continue; + xdp->data = NULL; + rx_ring->first_desc = ntc; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1245,10 +1261,8 @@ construct_skb: vlan_tag = ice_get_vlan_tag_from_rx_desc(rx_desc); /* pad the skb if needed, to make a valid ethernet frame */ - if (eth_skb_pad(skb)) { - skb = NULL; + if (eth_skb_pad(skb)) continue; - } /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; @@ -1262,18 +1276,34 @@ construct_skb: ice_trace(clean_rx_irq_indicate, rx_ring, rx_desc, skb); /* send completed skb up the stack */ ice_receive_skb(rx_ring, skb, vlan_tag); - skb = NULL; /* update budget accounting */ total_rx_pkts++; } + first = rx_ring->first_desc; + while (cached_ntc != first) { + struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; + + if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + xdp_xmit |= buf->act; + } else if (buf->act & ICE_XDP_CONSUMED) { + buf->pagecnt_bias++; + } else if (buf->act == ICE_XDP_PASS) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + } + + ice_put_rx_buf(rx_ring, buf); + if (++cached_ntc >= cnt) + cached_ntc = 0; + } + rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ - failure = ice_alloc_rx_bufs(rx_ring, cleaned_count); + failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); - if (xdp_prog) - ice_finalize_xdp_rx(xdp_ring, xdp_xmit); - rx_ring->skb = skb; + if (xdp_xmit) + ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu); if (rx_ring->ring_stats) ice_update_rx_ring_stats(rx_ring, total_rx_pkts, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 4fd0e5d0a313..efa3d378f19e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -9,10 +9,12 @@ #define ICE_DFLT_IRQ_WORK 256 #define ICE_RXBUF_3072 3072 #define ICE_RXBUF_2048 2048 +#define ICE_RXBUF_1664 1664 #define ICE_RXBUF_1536 1536 #define ICE_MAX_CHAINED_RX_BUFS 5 #define ICE_MAX_BUF_TXD 8 #define ICE_MIN_TX_LEN 17 +#define ICE_MAX_FRAME_LEGACY_RX 8320 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to @@ -110,6 +112,10 @@ static inline int ice_skb_pad(void) (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) +#define ICE_RX_DESC_UNUSED(R) \ + ((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->first_desc - (R)->next_to_use - 1) + #define ICE_RING_QUARTER(R) ((R)->count >> 2) #define ICE_TX_FLAGS_TSO BIT(0) @@ -134,6 +140,7 @@ static inline int ice_skb_pad(void) #define ICE_XDP_TX BIT(1) #define ICE_XDP_REDIR BIT(2) #define ICE_XDP_EXIT BIT(3) +#define ICE_SKB_CONSUMED ICE_XDP_CONSUMED #define ICE_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) @@ -143,13 +150,20 @@ static inline int ice_skb_pad(void) #define ICE_TXD_LAST_DESC_CMD (ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS) struct ice_tx_buf { - struct ice_tx_desc *next_to_watch; + union { + struct ice_tx_desc *next_to_watch; + u32 rs_idx; + }; union { struct sk_buff *skb; void *raw_buf; /* used for XDP */ + struct xdp_buff *xdp; /* used for XDP_TX ZC */ }; unsigned int bytecount; - unsigned short gso_segs; + union { + unsigned int gso_segs; + unsigned int nr_frags; /* used for mbuf XDP */ + }; u32 tx_flags; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); @@ -170,7 +184,9 @@ struct ice_rx_buf { dma_addr_t dma; struct page *page; unsigned int page_offset; - u16 pagecnt_bias; + unsigned int pgcnt; + unsigned int act; + unsigned int pagecnt_bias; }; struct ice_q_stats { @@ -273,42 +289,44 @@ struct ice_rx_ring { struct ice_vsi *vsi; /* Backreference to associated VSI */ struct ice_q_vector *q_vector; /* Backreference to associated vector */ u8 __iomem *tail; + u16 q_index; /* Queue number of ring */ + + u16 count; /* Number of descriptors */ + u16 reg_idx; /* HW register index of the ring */ + u16 next_to_alloc; + /* CL2 - 2nd cacheline starts here */ union { struct ice_rx_buf *rx_buf; struct xdp_buff **xdp_buf; }; - /* CL2 - 2nd cacheline starts here */ - struct xdp_rxq_info xdp_rxq; + struct xdp_buff xdp; /* CL3 - 3rd cacheline starts here */ - u16 q_index; /* Queue number of ring */ - - u16 count; /* Number of descriptors */ - u16 reg_idx; /* HW register index of the ring */ + struct bpf_prog *xdp_prog; + u16 rx_offset; /* used in interrupt processing */ u16 next_to_use; u16 next_to_clean; - u16 next_to_alloc; - u16 rx_offset; - u16 rx_buf_len; + u16 first_desc; /* stats structs */ struct ice_ring_stats *ring_stats; struct rcu_head rcu; /* to avoid race on free */ - /* CL4 - 3rd cacheline starts here */ + /* CL4 - 4th cacheline starts here */ struct ice_channel *ch; - struct bpf_prog *xdp_prog; struct ice_tx_ring *xdp_ring; struct xsk_buff_pool *xsk_pool; - struct sk_buff *skb; dma_addr_t dma; /* physical address of ring */ u64 cached_phctime; + u16 rx_buf_len; u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; #define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) u8 flags; + /* CL5 - 5th cacheline starts here */ + struct xdp_rxq_info xdp_rxq; } ____cacheline_internodealigned_in_smp; struct ice_tx_ring { @@ -326,12 +344,11 @@ struct ice_tx_ring { struct xsk_buff_pool *xsk_pool; u16 next_to_use; u16 next_to_clean; - u16 next_rs; - u16 next_dd; u16 q_handle; /* Queue handle per TC */ u16 reg_idx; /* HW register index of the ring */ u16 count; /* Number of descriptors */ u16 q_index; /* Queue number of ring */ + u16 xdp_tx_active; /* stats structs */ struct ice_ring_stats *ring_stats; /* CL3 - 3rd cacheline starts here */ @@ -342,7 +359,6 @@ struct ice_tx_ring { spinlock_t tx_lock; u32 txq_teid; /* Added Tx queue TEID */ /* CL4 - 4th cacheline starts here */ - u16 xdp_tx_active; #define ICE_TX_FLAGS_RING_XDP BIT(0) #define ICE_TX_FLAGS_RING_VLAN_L2TAG1 BIT(1) #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) @@ -431,7 +447,7 @@ static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) union ice_32b_rx_flex_desc; -bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, u16 cleaned_count); +bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); u16 ice_select_queue(struct net_device *dev, struct sk_buff *skb, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 25f04266c668..9bbed3f14e42 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -221,128 +221,193 @@ ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) } /** + * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer + * @xdp_ring: XDP Tx ring + * @tx_buf: Tx buffer to clean + */ +static void +ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) +{ + dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + xdp_ring->xdp_tx_active--; + page_frag_free(tx_buf->raw_buf); + tx_buf->raw_buf = NULL; +} + +/** * ice_clean_xdp_irq - Reclaim resources after transmit completes on XDP ring * @xdp_ring: XDP ring to clean */ -static void ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) +static u32 ice_clean_xdp_irq(struct ice_tx_ring *xdp_ring) { - unsigned int total_bytes = 0, total_pkts = 0; - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); - u16 ntc = xdp_ring->next_to_clean; - struct ice_tx_desc *next_dd_desc; - u16 next_dd = xdp_ring->next_dd; - struct ice_tx_buf *tx_buf; - int i; + int total_bytes = 0, total_pkts = 0; + u32 ntc = xdp_ring->next_to_clean; + struct ice_tx_desc *tx_desc; + u32 cnt = xdp_ring->count; + u32 ready_frames = 0; + u32 frags; + u32 idx; + u32 ret; + + idx = xdp_ring->tx_buf[ntc].rs_idx; + tx_desc = ICE_TX_DESC(xdp_ring, idx); + if (tx_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)) { + if (idx >= ntc) + ready_frames = idx - ntc + 1; + else + ready_frames = idx + cnt - ntc + 1; + } - next_dd_desc = ICE_TX_DESC(xdp_ring, next_dd); - if (!(next_dd_desc->cmd_type_offset_bsz & - cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) - return; + if (!ready_frames) + return 0; + ret = ready_frames; - for (i = 0; i < tx_thresh; i++) { - tx_buf = &xdp_ring->tx_buf[ntc]; + while (ready_frames) { + struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc]; + /* bytecount holds size of head + frags */ total_bytes += tx_buf->bytecount; - /* normally tx_buf->gso_segs was taken but at this point - * it's always 1 for us - */ + frags = tx_buf->nr_frags; total_pkts++; + /* count head + frags */ + ready_frames -= frags + 1; - page_frag_free(tx_buf->raw_buf); - dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), - dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); - dma_unmap_len_set(tx_buf, len, 0); - tx_buf->raw_buf = NULL; - + if (xdp_ring->xsk_pool) + xsk_buff_free(tx_buf->xdp); + else + ice_clean_xdp_tx_buf(xdp_ring, tx_buf); ntc++; - if (ntc >= xdp_ring->count) + if (ntc == cnt) ntc = 0; + + for (int i = 0; i < frags; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; + + ice_clean_xdp_tx_buf(xdp_ring, tx_buf); + ntc++; + if (ntc == cnt) + ntc = 0; + } } - next_dd_desc->cmd_type_offset_bsz = 0; - xdp_ring->next_dd = xdp_ring->next_dd + tx_thresh; - if (xdp_ring->next_dd > xdp_ring->count) - xdp_ring->next_dd = tx_thresh - 1; + tx_desc->cmd_type_offset_bsz = 0; xdp_ring->next_to_clean = ntc; ice_update_tx_ring_stats(xdp_ring, total_pkts, total_bytes); + + return ret; } /** - * ice_xmit_xdp_ring - submit single packet to XDP ring for transmission - * @data: packet data pointer - * @size: packet data size + * __ice_xmit_xdp_ring - submit frame to XDP ring for transmission + * @xdp: XDP buffer to be placed onto Tx descriptors * @xdp_ring: XDP ring for transmission */ -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring) +int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) { - u16 tx_thresh = ICE_RING_QUARTER(xdp_ring); - u16 i = xdp_ring->next_to_use; + struct skb_shared_info *sinfo = NULL; + u32 size = xdp->data_end - xdp->data; + struct device *dev = xdp_ring->dev; + u32 ntu = xdp_ring->next_to_use; struct ice_tx_desc *tx_desc; + struct ice_tx_buf *tx_head; struct ice_tx_buf *tx_buf; - dma_addr_t dma; + u32 cnt = xdp_ring->count; + void *data = xdp->data; + u32 nr_frags = 0; + u32 free_space; + u32 frag = 0; + + free_space = ICE_DESC_UNUSED(xdp_ring); + + if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) + free_space += ice_clean_xdp_irq(xdp_ring); + + if (unlikely(xdp_buff_has_frags(xdp))) { + sinfo = xdp_get_shared_info_from_buff(xdp); + nr_frags = sinfo->nr_frags; + if (free_space < nr_frags + 1) { + xdp_ring->ring_stats->tx_stats.tx_busy++; + return ICE_XDP_CONSUMED; + } + } - if (ICE_DESC_UNUSED(xdp_ring) < tx_thresh) - ice_clean_xdp_irq(xdp_ring); + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_head = &xdp_ring->tx_buf[ntu]; + tx_buf = tx_head; - if (!unlikely(ICE_DESC_UNUSED(xdp_ring))) { - xdp_ring->ring_stats->tx_stats.tx_busy++; - return ICE_XDP_CONSUMED; - } + for (;;) { + dma_addr_t dma; - dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE); - if (dma_mapping_error(xdp_ring->dev, dma)) - return ICE_XDP_CONSUMED; + dma = dma_map_single(dev, data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) + goto dma_unmap; - tx_buf = &xdp_ring->tx_buf[i]; - tx_buf->bytecount = size; - tx_buf->gso_segs = 1; - tx_buf->raw_buf = data; + /* record length, and DMA address */ + dma_unmap_len_set(tx_buf, len, size); + dma_unmap_addr_set(tx_buf, dma, dma); - /* record length, and DMA address */ - dma_unmap_len_set(tx_buf, len, size); - dma_unmap_addr_set(tx_buf, dma, dma); + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); + tx_buf->raw_buf = data; - tx_desc = ICE_TX_DESC(xdp_ring, i); - tx_desc->buf_addr = cpu_to_le64(dma); - tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, 0, - size, 0); + ntu++; + if (ntu == cnt) + ntu = 0; - xdp_ring->xdp_tx_active++; - i++; - if (i == xdp_ring->count) { - i = 0; - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs = tx_thresh - 1; - } - xdp_ring->next_to_use = i; + if (frag == nr_frags) + break; - if (i > xdp_ring->next_rs) { - tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_rs); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); - xdp_ring->next_rs += tx_thresh; + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_buf = &xdp_ring->tx_buf[ntu]; + + data = skb_frag_address(&sinfo->frags[frag]); + size = skb_frag_size(&sinfo->frags[frag]); + frag++; } + /* store info about bytecount and frag count in first desc */ + tx_head->bytecount = xdp_get_buff_len(xdp); + tx_head->nr_frags = nr_frags; + + /* update last descriptor from a frame with EOP */ + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_EOP << ICE_TXD_QW1_CMD_S); + + xdp_ring->xdp_tx_active++; + xdp_ring->next_to_use = ntu; + return ICE_XDP_TX; + +dma_unmap: + for (;;) { + tx_buf = &xdp_ring->tx_buf[ntu]; + dma_unmap_page(dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buf, len, 0); + if (tx_buf == tx_head) + break; + + if (!ntu) + ntu += cnt; + ntu--; + } + return ICE_XDP_CONSUMED; } /** - * ice_xmit_xdp_buff - convert an XDP buffer to an XDP frame and send it - * @xdp: XDP buffer - * @xdp_ring: XDP Tx ring - * - * Returns negative on failure, 0 on success. + * ice_xmit_xdp_ring - submit frame to XDP ring for transmission + * @xdpf: XDP frame that will be converted to XDP buff + * @xdp_ring: XDP ring for transmission */ -int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) +int ice_xmit_xdp_ring(struct xdp_frame *xdpf, struct ice_tx_ring *xdp_ring) { - struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); - - if (unlikely(!xdpf)) - return ICE_XDP_CONSUMED; + struct xdp_buff xdp; - return ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring); + xdp_convert_frame_to_buff(xdpf, &xdp); + return __ice_xmit_xdp_ring(&xdp, xdp_ring); } /** @@ -354,14 +419,21 @@ int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring) * should be called when a batch of packets has been processed in the * napi loop. */ -void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res) +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, + u32 first_idx) { + struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[first_idx]; + if (xdp_res & ICE_XDP_REDIR) xdp_do_flush_map(); if (xdp_res & ICE_XDP_TX) { if (static_branch_unlikely(&ice_xdp_locking_key)) spin_lock(&xdp_ring->tx_lock); + /* store index of descriptor with RS bit set in the first + * ice_tx_buf of given NAPI batch + */ + tx_buf->rs_idx = ice_set_rs_bit(xdp_ring); ice_xdp_ring_update_tail(xdp_ring); if (static_branch_unlikely(&ice_xdp_locking_key)) spin_unlock(&xdp_ring->tx_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index c7d2954dc9ea..ea977f283c22 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -6,6 +6,36 @@ #include "ice.h" /** + * ice_set_rx_bufs_act - propagate Rx buffer action to frags + * @xdp: XDP buffer representing frame (linear and frags part) + * @rx_ring: Rx ring struct + * act: action to store onto Rx buffers related to XDP buffer parts + * + * Set action that should be taken before putting Rx buffer from first frag + * to one before last. Last one is handled by caller of this function as it + * is the EOP frag that is currently being processed. This function is + * supposed to be called only when XDP buffer contains frags. + */ +static inline void +ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring, + const unsigned int act) +{ + const struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + u32 first = rx_ring->first_desc; + u32 nr_frags = sinfo->nr_frags; + u32 cnt = rx_ring->count; + struct ice_rx_buf *buf; + + for (int i = 0; i < nr_frags; i++) { + buf = &rx_ring->rx_buf[first]; + buf->act = act; + + if (++first == cnt) + first = 0; + } +} + +/** * ice_test_staterr - tests bits in Rx descriptor status and error fields * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask @@ -21,6 +51,28 @@ ice_test_staterr(__le16 status_err_n, const u16 stat_err_bits) return !!(status_err_n & cpu_to_le16(stat_err_bits)); } +/** + * ice_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * + * If the buffer is an EOP buffer, this function exits returning false, + * otherwise return true indicating that this is in fact a non-EOP buffer. + */ +static inline bool +ice_is_non_eop(const struct ice_rx_ring *rx_ring, + const union ice_32b_rx_flex_desc *rx_desc) +{ + /* if we are the last buffer then there is nothing else to do */ +#define ICE_RXD_EOF BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S) + if (likely(ice_test_staterr(rx_desc->wb.status_error0, ICE_RXD_EOF))) + return false; + + rx_ring->ring_stats->rx_stats.non_eop_descs++; + + return true; +} + static inline __le64 ice_build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) { @@ -70,9 +122,28 @@ static inline void ice_xdp_ring_update_tail(struct ice_tx_ring *xdp_ring) writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } -void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res); +/** + * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU) + * @xdp_ring: XDP ring to produce the HW Tx descriptors on + * + * returns index of descriptor that had RS bit produced on + */ +static inline u32 ice_set_rs_bit(const struct ice_tx_ring *xdp_ring) +{ + u32 rs_idx = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1; + struct ice_tx_desc *tx_desc; + + tx_desc = ICE_TX_DESC(xdp_ring, rs_idx); + tx_desc->cmd_type_offset_bsz |= + cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); + + return rs_idx; +} + +void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, u32 first_idx); int ice_xmit_xdp_buff(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring); -int ice_xmit_xdp_ring(void *data, u16 size, struct ice_tx_ring *xdp_ring); +int ice_xmit_xdp_ring(struct xdp_frame *xdpf, struct ice_tx_ring *xdp_ring); +int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring); void ice_release_rx_desc(struct ice_rx_ring *rx_ring, u16 val); void ice_process_skb_fields(struct ice_rx_ring *rx_ring, diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 375eb6493f0f..0e57bd1b85fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -237,16 +237,49 @@ static void ice_vf_clear_counters(struct ice_vf *vf) */ static void ice_vf_pre_vsi_rebuild(struct ice_vf *vf) { + /* Close any IRQ mapping now */ + if (vf->vf_ops->irq_close) + vf->vf_ops->irq_close(vf); + ice_vf_clear_counters(vf); vf->vf_ops->clear_reset_trigger(vf); } /** + * ice_vf_recreate_vsi - Release and re-create the VF's VSI + * @vf: VF to recreate the VSI for + * + * This is only called when a single VF is being reset (i.e. VVF, VFLR, host + * VF configuration change, etc) + * + * It releases and then re-creates a new VSI. + */ +static int ice_vf_recreate_vsi(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + int err; + + ice_vf_vsi_release(vf); + + err = vf->vf_ops->create_vsi(vf); + if (err) { + dev_err(ice_pf_to_dev(pf), + "Failed to recreate the VF%u's VSI, error %d\n", + vf->vf_id, err); + return err; + } + + return 0; +} + +/** * ice_vf_rebuild_vsi - rebuild the VF's VSI * @vf: VF to rebuild the VSI for * * This is only called when all VF(s) are being reset (i.e. PCIe Reset on the * host, PFR, CORER, etc.). + * + * It reprograms the VSI configuration back into hardware. */ static int ice_vf_rebuild_vsi(struct ice_vf *vf) { @@ -256,7 +289,7 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) if (WARN_ON(!vsi)) return -EINVAL; - if (ice_vsi_rebuild(vsi, true)) { + if (ice_vsi_rebuild(vsi, ICE_VSI_FLAG_INIT)) { dev_err(ice_pf_to_dev(pf), "failed to rebuild VF %d VSI\n", vf->vf_id); return -EIO; @@ -271,6 +304,21 @@ static int ice_vf_rebuild_vsi(struct ice_vf *vf) } /** + * ice_vf_post_vsi_rebuild - Reset tasks that occur after VSI rebuild + * @vf: the VF being reset + * + * Perform reset tasks which must occur after the VSI has been re-created or + * rebuilt during a VF reset. + */ +static void ice_vf_post_vsi_rebuild(struct ice_vf *vf) +{ + ice_vf_rebuild_host_cfg(vf); + ice_vf_set_initialized(vf); + + vf->vf_ops->post_vsi_rebuild(vf); +} + +/** * ice_is_any_vf_in_unicast_promisc - check if any VF(s) * are in unicast promiscuous mode * @pf: PF structure for accessing VF(s) @@ -495,7 +543,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); - vf->vf_ops->post_vsi_rebuild(vf); + ice_vf_post_vsi_rebuild(vf); mutex_unlock(&vf->cfg_lock); } @@ -639,14 +687,14 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_vf_pre_vsi_rebuild(vf); - if (vf->vf_ops->vsi_rebuild(vf)) { + if (ice_vf_recreate_vsi(vf)) { dev_err(dev, "Failed to release and setup the VF%u's VSI\n", vf->vf_id); err = -EFAULT; goto out_unlock; } - vf->vf_ops->post_vsi_rebuild(vf); + ice_vf_post_vsi_rebuild(vf); vsi = ice_get_vf_vsi(vf); if (WARN_ON(!vsi)) { err = -EINVAL; @@ -673,7 +721,7 @@ out_unlock: * ice_set_vf_state_qs_dis - Set VF queues state to disabled * @vf: pointer to the VF structure */ -void ice_set_vf_state_qs_dis(struct ice_vf *vf) +static void ice_set_vf_state_qs_dis(struct ice_vf *vf) { /* Clear Rx/Tx enabled queues flag */ bitmap_zero(vf->txq_ena, ICE_MAX_RSS_QS_PER_VF); @@ -681,9 +729,45 @@ void ice_set_vf_state_qs_dis(struct ice_vf *vf) clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); } +/** + * ice_set_vf_state_dis - Set VF state to disabled + * @vf: pointer to the VF structure + */ +void ice_set_vf_state_dis(struct ice_vf *vf) +{ + ice_set_vf_state_qs_dis(vf); + vf->vf_ops->clear_reset_state(vf); +} + /* Private functions only accessed from other virtualization files */ /** + * ice_initialize_vf_entry - Initialize a VF entry + * @vf: pointer to the VF structure + */ +void ice_initialize_vf_entry(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vfs *vfs; + + vfs = &pf->vfs; + + /* assign default capabilities */ + vf->spoofchk = true; + vf->num_vf_qs = vfs->num_qps_per; + ice_vc_set_default_allowlist(vf); + ice_virtchnl_set_dflt_ops(vf); + + /* ctrl_vsi_idx will be set to a valid value only when iAVF + * creates its first fdir rule. + */ + ice_vf_ctrl_invalidate_vsi(vf); + ice_vf_fdir_init(vf); + + mutex_init(&vf->cfg_lock); +} + +/** * ice_dis_vf_qs - Disable the VF queues * @vf: pointer to the VF structure */ @@ -924,18 +1008,18 @@ static int ice_vf_rebuild_host_mac_cfg(struct ice_vf *vf) vf->num_mac++; - if (is_valid_ether_addr(vf->hw_lan_addr.addr)) { - status = ice_fltr_add_mac(vsi, vf->hw_lan_addr.addr, + if (is_valid_ether_addr(vf->hw_lan_addr)) { + status = ice_fltr_add_mac(vsi, vf->hw_lan_addr, ICE_FWD_TO_VSI); if (status) { dev_err(dev, "failed to add default unicast MAC filter %pM for VF %u, error %d\n", - &vf->hw_lan_addr.addr[0], vf->vf_id, + &vf->hw_lan_addr[0], vf->vf_id, status); return status; } vf->num_mac++; - ether_addr_copy(vf->dev_lan_addr.addr, vf->hw_lan_addr.addr); + ether_addr_copy(vf->dev_lan_addr, vf->hw_lan_addr); } return 0; @@ -1115,11 +1199,16 @@ void ice_vf_ctrl_vsi_release(struct ice_vf *vf) */ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) { - struct ice_port_info *pi = ice_vf_get_port_info(vf); + struct ice_vsi_cfg_params params = {}; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; - vsi = ice_vsi_setup(pf, pi, ICE_VSI_CTRL, vf, NULL); + params.type = ICE_VSI_CTRL; + params.pi = ice_vf_get_port_info(vf); + params.vf = vf; + params.flags = ICE_VSI_FLAG_INIT; + + vsi = ice_vsi_setup(pf, ¶ms); if (!vsi) { dev_err(ice_pf_to_dev(pf), "Failed to create VF control VSI\n"); ice_vf_ctrl_invalidate_vsi(vf); @@ -1129,6 +1218,60 @@ struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf) } /** + * ice_vf_init_host_cfg - Initialize host admin configuration + * @vf: VF to initialize + * @vsi: the VSI created at initialization + * + * Initialize the VF host configuration. Called during VF creation to setup + * VLAN 0, add the VF VSI broadcast filter, and setup spoof checking. It + * should only be called during VF creation. + */ +int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi) +{ + struct ice_vsi_vlan_ops *vlan_ops; + struct ice_pf *pf = vf->pf; + u8 broadcast[ETH_ALEN]; + struct device *dev; + int err; + + dev = ice_pf_to_dev(pf); + + err = ice_vsi_add_vlan_zero(vsi); + if (err) { + dev_warn(dev, "Failed to add VLAN 0 filter for VF %d\n", + vf->vf_id); + return err; + } + + vlan_ops = ice_get_compat_vsi_vlan_ops(vsi); + err = vlan_ops->ena_rx_filtering(vsi); + if (err) { + dev_warn(dev, "Failed to enable Rx VLAN filtering for VF %d\n", + vf->vf_id); + return err; + } + + eth_broadcast_addr(broadcast); + err = ice_fltr_add_mac(vsi, broadcast, ICE_FWD_TO_VSI); + if (err) { + dev_err(dev, "Failed to add broadcast MAC filter for VF %d, status %d\n", + vf->vf_id, err); + return err; + } + + vf->num_mac = 1; + + err = ice_vsi_apply_spoofchk(vsi, vf->spoofchk); + if (err) { + dev_warn(dev, "Failed to initialize spoofchk setting for VF %d\n", + vf->vf_id); + return err; + } + + return 0; +} + +/** * ice_vf_invalidate_vsi - invalidate vsi_idx/vsi_num to remove VSI access * @vf: VF to remove access to VSI for */ @@ -1139,6 +1282,24 @@ void ice_vf_invalidate_vsi(struct ice_vf *vf) } /** + * ice_vf_vsi_release - Release the VF VSI and invalidate indexes + * @vf: pointer to the VF structure + * + * Release the VF associated with this VSI and then invalidate the VSI + * indexes. + */ +void ice_vf_vsi_release(struct ice_vf *vf) +{ + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + + if (WARN_ON(!vsi)) + return; + + ice_vsi_release(vsi); + ice_vf_invalidate_vsi(vf); +} + +/** * ice_vf_set_initialized - VF is ready for VIRTCHNL communication * @vf: VF to set in initialized state * diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 52bd9a3816bf..ef30f05b5d02 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -56,11 +56,13 @@ struct ice_mdd_vf_events { struct ice_vf_ops { enum ice_disq_rst_src reset_type; void (*free)(struct ice_vf *vf); + void (*clear_reset_state)(struct ice_vf *vf); void (*clear_mbx_register)(struct ice_vf *vf); void (*trigger_reset_register)(struct ice_vf *vf, bool is_vflr); bool (*poll_reset_status)(struct ice_vf *vf); void (*clear_reset_trigger)(struct ice_vf *vf); - int (*vsi_rebuild)(struct ice_vf *vf); + void (*irq_close)(struct ice_vf *vf); + int (*create_vsi)(struct ice_vf *vf); void (*post_vsi_rebuild)(struct ice_vf *vf); }; @@ -96,8 +98,8 @@ struct ice_vf { struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ struct virtchnl_version_info vf_ver; u32 driver_caps; /* reported by VF driver */ - struct virtchnl_ether_addr dev_lan_addr; - struct virtchnl_ether_addr hw_lan_addr; + u8 dev_lan_addr[ETH_ALEN]; + u8 hw_lan_addr[ETH_ALEN]; struct ice_time_mac legacy_last_added_umac; DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF); DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); @@ -213,7 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); -void ice_set_vf_state_qs_dis(struct ice_vf *vf); +void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void ice_vf_get_promisc_masks(struct ice_vf *vf, struct ice_vsi *vsi, @@ -259,7 +261,7 @@ static inline int ice_check_vf_ready_for_cfg(struct ice_vf *vf) return -EOPNOTSUPP; } -static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) +static inline void ice_set_vf_state_dis(struct ice_vf *vf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h index 9c8ef2b01f0f..6f3293b793b5 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h @@ -23,6 +23,7 @@ #warning "Only include ice_vf_lib_private.h in CONFIG_PCI_IOV virtualization files" #endif +void ice_initialize_vf_entry(struct ice_vf *vf); void ice_dis_vf_qs(struct ice_vf *vf); int ice_check_vf_init(struct ice_vf *vf); enum virtchnl_status_code ice_err_to_virt_err(int err); @@ -35,7 +36,9 @@ void ice_vf_rebuild_host_cfg(struct ice_vf *vf); void ice_vf_ctrl_invalidate_vsi(struct ice_vf *vf); void ice_vf_ctrl_vsi_release(struct ice_vf *vf); struct ice_vsi *ice_vf_ctrl_vsi_setup(struct ice_vf *vf); +int ice_vf_init_host_cfg(struct ice_vf *vf, struct ice_vsi *vsi); void ice_vf_invalidate_vsi(struct ice_vf *vf); +void ice_vf_vsi_release(struct ice_vf *vf); void ice_vf_set_initialized(struct ice_vf *vf); #endif /* _ICE_VF_LIB_PRIVATE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index d4a4001b6e5d..f56fa94ff3d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -39,7 +39,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd); } -static const u32 ice_legacy_aq_to_vc_speed[15] = { +static const u32 ice_legacy_aq_to_vc_speed[] = { VIRTCHNL_LINK_SPEED_100MB, /* BIT(0) */ VIRTCHNL_LINK_SPEED_100MB, VIRTCHNL_LINK_SPEED_1GB, @@ -51,10 +51,6 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, VIRTCHNL_LINK_SPEED_40GB, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN, - VIRTCHNL_LINK_SPEED_UNKNOWN /* BIT(14) */ }; /** @@ -71,21 +67,20 @@ static const u32 ice_legacy_aq_to_vc_speed[15] = { */ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) { - u32 speed; + /* convert a BIT() value into an array index */ + u32 index = fls(link_speed) - 1; - if (adv_link_support) { - /* convert a BIT() value into an array index */ - speed = ice_get_link_speed(fls(link_speed) - 1); - } else { + if (adv_link_support) + return ice_get_link_speed(index); + else if (index < ARRAY_SIZE(ice_legacy_aq_to_vc_speed)) /* Virtchnl speeds are not defined for every speed supported in * the hardware. To maintain compatibility with older AVF * drivers, while reporting the speed the new speed values are * resolved to the closest known virtchnl speeds */ - speed = ice_legacy_aq_to_vc_speed[fls(link_speed) - 1]; - } + return ice_legacy_aq_to_vc_speed[index]; - return speed; + return VIRTCHNL_LINK_SPEED_UNKNOWN; } /* The mailbox overflow detection algorithm helps to check if there diff --git a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c index 5ecc0ee9a78e..b1ffb81893d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_vsi_vlan_ops.c @@ -44,13 +44,17 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) /* outer VLAN ops regardless of port VLAN config */ vlan_ops->add_vlan = ice_vsi_add_vlan; - vlan_ops->dis_rx_filtering = ice_vsi_dis_rx_vlan_filtering; vlan_ops->ena_tx_filtering = ice_vsi_ena_tx_vlan_filtering; vlan_ops->dis_tx_filtering = ice_vsi_dis_tx_vlan_filtering; if (ice_vf_is_port_vlan_ena(vf)) { /* setup outer VLAN ops */ vlan_ops->set_port_vlan = ice_vsi_set_outer_port_vlan; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; @@ -63,6 +67,9 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->ena_insertion = ice_vsi_ena_inner_insertion; vlan_ops->dis_insertion = ice_vsi_dis_inner_insertion; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; + if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else @@ -96,7 +103,14 @@ void ice_vf_vsi_init_vlan_ops(struct ice_vsi *vsi) vlan_ops->set_port_vlan = ice_vsi_set_inner_port_vlan; vlan_ops->ena_rx_filtering = ice_vsi_ena_rx_vlan_filtering; + /* all Rx traffic should be in the domain of the + * assigned port VLAN, so prevent disabling Rx VLAN + * filtering + */ + vlan_ops->dis_rx_filtering = noop_vlan; } else { + vlan_ops->dis_rx_filtering = + ice_vsi_dis_rx_vlan_filtering; if (!test_bit(ICE_FLAG_VF_VLAN_PRUNING, pf->flags)) vlan_ops->ena_rx_filtering = noop_vlan; else diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index dab3cd5d300e..e24e3f5017ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -507,7 +507,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->vsi_res[0].vsi_type = VIRTCHNL_VSI_SRIOV; vfres->vsi_res[0].num_queue_pairs = vsi->num_txq; ether_addr_copy(vfres->vsi_res[0].default_mac_addr, - vf->hw_lan_addr.addr); + vf->hw_lan_addr); /* match guest capabilities */ vf->driver_caps = vfres->vf_cap_flags; @@ -1802,10 +1802,10 @@ ice_vfhw_mac_add(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) * was correctly specified over VIRTCHNL */ if ((ice_is_vc_addr_legacy(vc_ether_addr) && - is_zero_ether_addr(vf->hw_lan_addr.addr)) || + is_zero_ether_addr(vf->hw_lan_addr)) || ice_is_vc_addr_primary(vc_ether_addr)) { - ether_addr_copy(vf->dev_lan_addr.addr, mac_addr); - ether_addr_copy(vf->hw_lan_addr.addr, mac_addr); + ether_addr_copy(vf->dev_lan_addr, mac_addr); + ether_addr_copy(vf->hw_lan_addr, mac_addr); } /* hardware and device MACs are already set, but its possible that the @@ -1836,7 +1836,7 @@ ice_vc_add_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, int ret; /* device MAC already added */ - if (ether_addr_equal(mac_addr, vf->dev_lan_addr.addr)) + if (ether_addr_equal(mac_addr, vf->dev_lan_addr)) return 0; if (is_unicast_ether_addr(mac_addr) && !ice_can_vf_change_mac(vf)) { @@ -1891,8 +1891,8 @@ ice_update_legacy_cached_mac(struct ice_vf *vf, ice_is_legacy_umac_expired(&vf->legacy_last_added_umac)) return; - ether_addr_copy(vf->dev_lan_addr.addr, vf->legacy_last_added_umac.addr); - ether_addr_copy(vf->hw_lan_addr.addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->dev_lan_addr, vf->legacy_last_added_umac.addr); + ether_addr_copy(vf->hw_lan_addr, vf->legacy_last_added_umac.addr); } /** @@ -1906,15 +1906,15 @@ ice_vfhw_mac_del(struct ice_vf *vf, struct virtchnl_ether_addr *vc_ether_addr) u8 *mac_addr = vc_ether_addr->addr; if (!is_valid_ether_addr(mac_addr) || - !ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + !ether_addr_equal(vf->dev_lan_addr, mac_addr)) return; /* allow the device MAC to be repopulated in the add flow and don't - * clear the hardware MAC (i.e. hw_lan_addr.addr) here as that is meant + * clear the hardware MAC (i.e. hw_lan_addr) here as that is meant * to be persistent on VM reboot and across driver unload/load, which * won't work if we clear the hardware MAC here */ - eth_zero_addr(vf->dev_lan_addr.addr); + eth_zero_addr(vf->dev_lan_addr); ice_update_legacy_cached_mac(vf, vc_ether_addr); } @@ -1934,7 +1934,7 @@ ice_vc_del_mac_addr(struct ice_vf *vf, struct ice_vsi *vsi, int status; if (!ice_can_vf_change_mac(vf) && - ether_addr_equal(vf->dev_lan_addr.addr, mac_addr)) + ether_addr_equal(vf->dev_lan_addr, mac_addr)) return 0; status = ice_fltr_remove_mac(vsi, mac_addr, ICE_FWD_TO_VSI); @@ -3733,7 +3733,7 @@ static int ice_vc_repr_add_mac(struct ice_vf *vf, u8 *msg) int result; if (!is_unicast_ether_addr(mac_addr) || - ether_addr_equal(mac_addr, vf->hw_lan_addr.addr)) + ether_addr_equal(mac_addr, vf->hw_lan_addr)) continue; if (vf->pf_set_mac) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index c6a58343d81d..e6ef6b303222 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -113,7 +113,7 @@ ice_vc_fdir_param_check(struct ice_vf *vf, u16 vsi_id) if (!ice_vc_isvalid_vsi_id(vf, vsi_id)) return -EINVAL; - if (!pf->vsi[vf->lan_vsi_idx]) + if (!ice_get_vf_vsi(vf)) return -EINVAL; return 0; @@ -494,7 +494,7 @@ ice_vc_fdir_rem_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, int tun) vf_prof = fdir->fdir_prof[flow]; - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) { dev_dbg(dev, "NULL vf %d vsi pointer\n", vf->vf_id); return; @@ -572,7 +572,7 @@ ice_vc_fdir_write_flow_prof(struct ice_vf *vf, enum ice_fltr_ptype flow, pf = vf->pf; dev = ice_pf_to_dev(pf); hw = &pf->hw; - vf_vsi = pf->vsi[vf->lan_vsi_idx]; + vf_vsi = ice_get_vf_vsi(vf); if (!vf_vsi) return -EINVAL; @@ -1205,7 +1205,7 @@ static int ice_vc_fdir_write_fltr(struct ice_vf *vf, pf = vf->pf; dev = ice_pf_to_dev(pf); hw = &pf->hw; - vsi = pf->vsi[vf->lan_vsi_idx]; + vsi = ice_get_vf_vsi(vf); if (!vsi) { dev_dbg(dev, "Invalid vsi for VF %d\n", vf->vf_id); return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 7105de6fb344..a25a68c69f22 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -598,6 +598,107 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) } /** + * ice_clean_xdp_irq_zc - AF_XDP ZC specific Tx cleaning routine + * @xdp_ring: XDP Tx ring + */ +static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) +{ + u16 ntc = xdp_ring->next_to_clean; + struct ice_tx_desc *tx_desc; + u16 cnt = xdp_ring->count; + struct ice_tx_buf *tx_buf; + u16 xsk_frames = 0; + u16 last_rs; + int i; + + last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1; + tx_desc = ICE_TX_DESC(xdp_ring, last_rs); + if (tx_desc->cmd_type_offset_bsz & + cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE)) { + if (last_rs >= ntc) + xsk_frames = last_rs - ntc + 1; + else + xsk_frames = last_rs + cnt - ntc + 1; + } + + if (!xsk_frames) + return; + + if (likely(!xdp_ring->xdp_tx_active)) + goto skip; + + ntc = xdp_ring->next_to_clean; + for (i = 0; i < xsk_frames; i++) { + tx_buf = &xdp_ring->tx_buf[ntc]; + + if (tx_buf->xdp) { + xsk_buff_free(tx_buf->xdp); + xdp_ring->xdp_tx_active--; + } else { + xsk_frames++; + } + + ntc++; + if (ntc == cnt) + ntc = 0; + } +skip: + tx_desc->cmd_type_offset_bsz = 0; + xdp_ring->next_to_clean += xsk_frames; + if (xdp_ring->next_to_clean >= cnt) + xdp_ring->next_to_clean -= cnt; + if (xsk_frames) + xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); +} + +/** + * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX + * @xdp: XDP buffer to xmit + * @xdp_ring: XDP ring to produce descriptor onto + * + * note that this function works directly on xdp_buff, no need to convert + * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning + * side will be able to xsk_buff_free() it. + * + * Returns ICE_XDP_TX for successfully produced desc, ICE_XDP_CONSUMED if there + * was not enough space on XDP ring + */ +static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp, + struct ice_tx_ring *xdp_ring) +{ + u32 size = xdp->data_end - xdp->data; + u32 ntu = xdp_ring->next_to_use; + struct ice_tx_desc *tx_desc; + struct ice_tx_buf *tx_buf; + dma_addr_t dma; + + if (ICE_DESC_UNUSED(xdp_ring) < ICE_RING_QUARTER(xdp_ring)) { + ice_clean_xdp_irq_zc(xdp_ring); + if (!ICE_DESC_UNUSED(xdp_ring)) { + xdp_ring->ring_stats->tx_stats.tx_busy++; + return ICE_XDP_CONSUMED; + } + } + + dma = xsk_buff_xdp_get_dma(xdp); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size); + + tx_buf = &xdp_ring->tx_buf[ntu]; + tx_buf->xdp = xdp; + tx_desc = ICE_TX_DESC(xdp_ring, ntu); + tx_desc->buf_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = ice_build_ctob(ICE_TX_DESC_CMD_EOP, + 0, size, 0); + xdp_ring->xdp_tx_active++; + + if (++ntu == xdp_ring->count) + ntu = 0; + xdp_ring->next_to_use = ntu; + + return ICE_XDP_TX; +} + +/** * ice_run_xdp_zc - Executes an XDP program in zero-copy path * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program @@ -630,7 +731,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, case XDP_PASS: break; case XDP_TX: - result = ice_xmit_xdp_buff(xdp, xdp_ring); + result = ice_xmit_xdp_tx_zc(xdp, xdp_ring); if (result == ICE_XDP_CONSUMED) goto out_failure; break; @@ -760,7 +861,7 @@ construct_skb: if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc); - ice_finalize_xdp_rx(xdp_ring, xdp_xmit); + ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0); ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes); if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { @@ -776,75 +877,6 @@ construct_skb: } /** - * ice_clean_xdp_tx_buf - Free and unmap XDP Tx buffer - * @xdp_ring: XDP Tx ring - * @tx_buf: Tx buffer to clean - */ -static void -ice_clean_xdp_tx_buf(struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf) -{ - page_frag_free(tx_buf->raw_buf); - xdp_ring->xdp_tx_active--; - dma_unmap_single(xdp_ring->dev, dma_unmap_addr(tx_buf, dma), - dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); - dma_unmap_len_set(tx_buf, len, 0); -} - -/** - * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ - * @xdp_ring: XDP Tx ring - */ -static void ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring) -{ - u16 ntc = xdp_ring->next_to_clean; - struct ice_tx_desc *tx_desc; - u16 cnt = xdp_ring->count; - struct ice_tx_buf *tx_buf; - u16 xsk_frames = 0; - u16 last_rs; - int i; - - last_rs = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : cnt - 1; - tx_desc = ICE_TX_DESC(xdp_ring, last_rs); - if ((tx_desc->cmd_type_offset_bsz & - cpu_to_le64(ICE_TX_DESC_DTYPE_DESC_DONE))) { - if (last_rs >= ntc) - xsk_frames = last_rs - ntc + 1; - else - xsk_frames = last_rs + cnt - ntc + 1; - } - - if (!xsk_frames) - return; - - if (likely(!xdp_ring->xdp_tx_active)) - goto skip; - - ntc = xdp_ring->next_to_clean; - for (i = 0; i < xsk_frames; i++) { - tx_buf = &xdp_ring->tx_buf[ntc]; - - if (tx_buf->raw_buf) { - ice_clean_xdp_tx_buf(xdp_ring, tx_buf); - tx_buf->raw_buf = NULL; - } else { - xsk_frames++; - } - - ntc++; - if (ntc >= xdp_ring->count) - ntc = 0; - } -skip: - tx_desc->cmd_type_offset_bsz = 0; - xdp_ring->next_to_clean += xsk_frames; - if (xdp_ring->next_to_clean >= cnt) - xdp_ring->next_to_clean -= cnt; - if (xsk_frames) - xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames); -} - -/** * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor * @xdp_ring: XDP ring to produce the HW Tx descriptor on * @desc: AF_XDP descriptor to pull the DMA address and length from @@ -918,20 +950,6 @@ static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *d } /** - * ice_set_rs_bit - set RS bit on last produced descriptor (one behind current NTU) - * @xdp_ring: XDP ring to produce the HW Tx descriptors on - */ -static void ice_set_rs_bit(struct ice_tx_ring *xdp_ring) -{ - u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1; - struct ice_tx_desc *tx_desc; - - tx_desc = ICE_TX_DESC(xdp_ring, ntu); - tx_desc->cmd_type_offset_bsz |= - cpu_to_le64(ICE_TX_DESC_CMD_RS << ICE_TXD_QW1_CMD_S); -} - -/** * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring * @xdp_ring: XDP ring to produce the HW Tx descriptors on * @@ -1065,8 +1083,8 @@ void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) while (ntc != ntu) { struct ice_tx_buf *tx_buf = &xdp_ring->tx_buf[ntc]; - if (tx_buf->raw_buf) - ice_clean_xdp_tx_buf(xdp_ring, tx_buf); + if (tx_buf->xdp) + xsk_buff_free(tx_buf->xdp); else xsk_frames++; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index c56b991fa610..087c950fea0b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2810,6 +2810,22 @@ static int igb_offload_txtime(struct igb_adapter *adapter, return 0; } +static int igb_tc_query_caps(struct igb_adapter *adapter, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + caps->broken_mqprio = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + static LIST_HEAD(igb_block_cb_list); static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, @@ -2818,6 +2834,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, struct igb_adapter *adapter = netdev_priv(dev); switch (type) { + case TC_QUERY_CAPS: + return igb_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_CBS: return igb_offload_cbs(adapter, type_data); case TC_SETUP_BLOCK: @@ -2871,8 +2889,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) bpf_prog_put(old_prog); /* bpf is just replaced, RXQ and MTU are already setup */ - if (!need_reset) + if (!need_reset) { return 0; + } else { + if (prog) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); + } if (running) igb_open(dev); @@ -3315,6 +3339,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 6ddcbc8b7b6a..2928a6c73692 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2942,7 +2942,9 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (tx_buffer->next_to_watch && time_after(jiffies, tx_buffer->time_stamp + (adapter->tx_timeout_factor * HZ)) && - !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF)) { + !(rd32(IGC_STATUS) & IGC_STATUS_TXOFF) && + (rd32(IGC_TDH(tx_ring->reg_idx)) != + readl(tx_ring->tail))) { /* detected Tx unit hang */ netdev_err(tx_ring->netdev, "Detected Tx Unit Hang\n" @@ -5069,6 +5071,24 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) } /** + * igc_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: queue number that timed out + **/ +static void igc_tx_timeout(struct net_device *netdev, + unsigned int __always_unused txqueue) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + + /* Do the reset outside of interrupt context */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + wr32(IGC_EICS, + (adapter->eims_enable_mask & ~adapter->eims_other)); +} + +/** * igc_get_stats64 - Get System Network Statistics * @netdev: network interface device structure * @stats: rtnl_link_stats64 pointer @@ -5495,7 +5515,7 @@ static void igc_watchdog_task(struct work_struct *work) case SPEED_100: case SPEED_1000: case SPEED_2500: - adapter->tx_timeout_factor = 7; + adapter->tx_timeout_factor = 1; break; } @@ -6205,12 +6225,35 @@ static int igc_tsn_enable_cbs(struct igc_adapter *adapter, return igc_tsn_offload_apply(adapter); } +static int igc_tc_query_caps(struct igc_adapter *adapter, + struct tc_query_caps_base *base) +{ + struct igc_hw *hw = &adapter->hw; + + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + caps->broken_mqprio = true; + + if (hw->mac.type == igc_i225) + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct igc_adapter *adapter = netdev_priv(dev); switch (type) { + case TC_QUERY_CAPS: + return igc_tc_query_caps(adapter, type_data); case TC_SETUP_QDISC_TAPRIO: return igc_tsn_enable_qbv_scheduling(adapter, type_data); @@ -6324,6 +6367,7 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_rx_mode = igc_set_rx_mode, .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, + .ndo_tx_timeout = igc_tx_timeout, .ndo_get_stats64 = igc_get_stats64, .ndo_fix_features = igc_fix_features, .ndo_set_features = igc_set_features, @@ -6531,6 +6575,9 @@ static int igc_probe(struct pci_dev *pdev, netdev->mpls_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= netdev->vlan_features; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index aeeb34e64610..e27af72aada8 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -29,6 +29,11 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, if (old_prog) bpf_prog_put(old_prog); + if (prog) + xdp_features_set_redirect_target(dev, true); + else + xdp_features_clear_redirect_target(dev); + if (if_running) igc_open(dev); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 992b7ae75233..a3aaf051f9f1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10301,6 +10301,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (err) return -EINVAL; + if (!prog) + xdp_features_clear_redirect_target(dev); } else { for (i = 0; i < adapter->num_rx_queues; i++) { WRITE_ONCE(adapter->rx_ring[i]->xdp_prog, @@ -10321,6 +10323,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (adapter->xdp_ring[i]->xsk_pool) (void)ixgbe_xsk_wakeup(adapter->netdev, i, XDP_WAKEUP_RX); + xdp_features_set_redirect_target(dev, true); } return 0; @@ -11016,6 +11019,9 @@ skip_sriov: netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index ea0a230c1153..a44e4bd56142 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4634,6 +4634,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_TX; netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC; /* MTU range: 68 - 1504 or 9710 */ netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f8925cac61e4..1cb4f59c0050 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -38,7 +38,7 @@ #include <net/ipv6.h> #include <net/tso.h> #include <net/page_pool.h> -#include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include <linux/bpf_trace.h> /* Registers */ @@ -5612,6 +5612,9 @@ static int mvneta_probe(struct platform_device *pdev) NETIF_F_TSO | NETIF_F_RXCSUM; dev->hw_features |= dev->features; dev->vlan_features |= dev->features; + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_set_tso_max_segs(dev, MVNETA_MAX_TSO_SEGS); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 4da45c5abba5..9b4ecbe4f36d 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6866,6 +6866,10 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->vlan_features |= features; netif_set_tso_max_segs(dev, MVPP2_MAX_TSO_SEGS); + + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + dev->priv_flags |= IFF_UNICAST_FLT; /* MTU range: 68 - 9704 */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index c1ea60bc2630..179433d0a54a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2512,10 +2512,13 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog) /* Network stack and XDP shared same rx queues. * Use separate tx queues for XDP and network stack. */ - if (pf->xdp_prog) + if (pf->xdp_prog) { pf->hw.xdp_queues = pf->hw.rx_queues; - else + xdp_features_set_redirect_target(dev, false); + } else { pf->hw.xdp_queues = 0; + xdp_features_clear_redirect_target(dev); + } pf->hw.tot_tx_queues += pf->hw.xdp_queues; @@ -2878,6 +2881,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2_netdev_ops; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(pf); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index f1cb1efc94cf..14be6ea51b88 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1621,8 +1621,8 @@ static struct page_pool *mtk_create_page_pool(struct mtk_eth *eth, if (IS_ERR(pp)) return pp; - err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, eth->rx_napi.napi_id, - id, PAGE_SIZE); + err = __xdp_rxq_info_reg(xdp_q, ð->dummy_dev, id, + eth->rx_napi.napi_id, PAGE_SIZE); if (err < 0) goto err_free_pp; @@ -1921,7 +1921,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, while (done < budget) { unsigned int pktlen, *rxdcsum; + bool has_hwaccel_tag = false; struct net_device *netdev; + u16 vlan_proto, vlan_tci; dma_addr_t dma_addr; u32 hash, reason; int mac = 0; @@ -2061,27 +2063,29 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { if (MTK_HAS_CAPS(eth->soc->caps, MTK_NETSYS_V2)) { - if (trxd.rxd3 & RX_DMA_VTAG_V2) - __vlan_hwaccel_put_tag(skb, - htons(RX_DMA_VPID(trxd.rxd4)), - RX_DMA_VID(trxd.rxd4)); + if (trxd.rxd3 & RX_DMA_VTAG_V2) { + vlan_proto = RX_DMA_VPID(trxd.rxd4); + vlan_tci = RX_DMA_VID(trxd.rxd4); + has_hwaccel_tag = true; + } } else if (trxd.rxd2 & RX_DMA_VTAG) { - __vlan_hwaccel_put_tag(skb, htons(RX_DMA_VPID(trxd.rxd3)), - RX_DMA_VID(trxd.rxd3)); + vlan_proto = RX_DMA_VPID(trxd.rxd3); + vlan_tci = RX_DMA_VID(trxd.rxd3); + has_hwaccel_tag = true; } } /* When using VLAN untagging in combination with DSA, the * hardware treats the MTK special tag as a VLAN and untags it. */ - if (skb_vlan_tag_present(skb) && netdev_uses_dsa(netdev)) { - unsigned int port = ntohs(skb->vlan_proto) & GENMASK(2, 0); + if (has_hwaccel_tag && netdev_uses_dsa(netdev)) { + unsigned int port = vlan_proto & GENMASK(2, 0); if (port < ARRAY_SIZE(eth->dsa_meta) && eth->dsa_meta[port]) skb_dst_set_noref(skb, ð->dsa_meta[port]->dst); - - __vlan_hwaccel_clear_tag(skb); + } else if (has_hwaccel_tag) { + __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan_tci); } skb_record_rx_queue(skb, 0); @@ -3177,7 +3181,7 @@ static void mtk_gdm_config(struct mtk_eth *eth, u32 config) val |= config; - if (!i && eth->netdev[0] && netdev_uses_dsa(eth->netdev[0])) + if (eth->netdev[i] && netdev_uses_dsa(eth->netdev[i])) val |= MTK_GDMA_SPECIAL_TAG; mtk_w32(eth, val, MTK_GDMA_FWD_CFG(i)); @@ -3243,8 +3247,7 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if ((mtk_uses_dsa(dev) && !eth->prog) && - !(mac->id == 1 && MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_TRGMII))) { + if (mtk_uses_dsa(dev) && !eth->prog) { for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { struct metadata_dst *md_dst = eth->dsa_meta[i]; @@ -3261,8 +3264,7 @@ static int mtk_open(struct net_device *dev) } } else { /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA, or the second MAC of the MT7621 and - * MT7623 SoCs is being used. + * one MAC does not use DSA. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; @@ -4449,6 +4451,12 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) register_netdevice_notifier(&mac->device_notifier); } + if (mtk_page_pool_enabled(eth)) + eth->netdev[id]->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG; + return 0; free_netdev: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index af4c4858f397..e11bc0ac880e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3416,6 +3416,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + /* MTU range: 68 - hw-specific max */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = priv->max_mtu; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 3e232a65a0c3..bb95b40d25eb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -245,8 +245,9 @@ void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) pages = dev->priv.dbg.pages_debugfs; debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); - debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages); - debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages); + debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.page_counters[MLX5_VF]); + debugfs_create_u32("fw_pages_sfs", 0400, pages, &dev->priv.page_counters[MLX5_SF]); + debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.page_counters[MLX5_HOST_PF]); debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 63fb7912b032..b742e04deec1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -268,9 +268,10 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink, struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_priv(devlink); + struct mlx5_devlink_trap_event_ctx trap_event_ctx; enum devlink_trap_action action_orig; struct mlx5_devlink_trap *dl_trap; - int err = 0; + int err; if (is_mdev_switchdev_mode(dev)) { NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode"); @@ -280,26 +281,25 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink, dl_trap = mlx5_find_trap_by_id(dev, trap->id); if (!dl_trap) { mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id); - err = -EINVAL; - goto out; + return -EINVAL; } - if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP) { - err = -EOPNOTSUPP; - goto out; - } + if (action != DEVLINK_TRAP_ACTION_DROP && action != DEVLINK_TRAP_ACTION_TRAP) + return -EOPNOTSUPP; if (action == dl_trap->trap.action) - goto out; + return 0; action_orig = dl_trap->trap.action; dl_trap->trap.action = action; + trap_event_ctx.trap = &dl_trap->trap; + trap_event_ctx.err = 0; err = mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_TYPE_TRAP, - &dl_trap->trap); - if (err) + &trap_event_ctx); + if (err == NOTIFY_BAD) dl_trap->trap.action = action_orig; -out: - return err; + + return trap_event_ctx.err; } static const struct devlink_ops mlx5_devlink_ops = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 1c1b62ee84bb..b561107e0df1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -24,6 +24,11 @@ struct mlx5_devlink_trap { struct list_head list; }; +struct mlx5_devlink_trap_event_ctx { + struct mlx5_trap_ctx *trap; + int err; +}; + struct mlx5_core_dev; void mlx5_devlink_trap_report(struct mlx5_core_dev *dev, int trap_id, struct sk_buff *skb, struct devlink_port *dl_port); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 21831386b26e..f40497823e65 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -64,6 +64,7 @@ static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer) MLX5_GET(mtrc_cap, out, num_string_trace); tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db); tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner); + tracer->str_db.loaded = false; for (i = 0; i < tracer->str_db.num_string_db; i++) { mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]); @@ -233,6 +234,8 @@ static int mlx5_fw_tracer_allocate_strings_db(struct mlx5_fw_tracer *tracer) int i; for (i = 0; i < num_string_db; i++) { + if (!string_db_size_out[i]) + continue; tracer->str_db.buffer[i] = kzalloc(string_db_size_out[i], GFP_KERNEL); if (!tracer->str_db.buffer[i]) goto free_strings_db; @@ -278,6 +281,8 @@ static void mlx5_tracer_read_strings_db(struct work_struct *work) } for (i = 0; i < num_string_db; i++) { + if (!tracer->str_db.size_out[i]) + continue; offset = 0; MLX5_SET(mtrc_stdb, in, string_db_index, i); num_of_reads = tracer->str_db.size_out[i] / @@ -384,6 +389,8 @@ static struct tracer_string_format *mlx5_tracer_get_string(struct mlx5_fw_tracer str_ptr = tracer_event->string_event.string_param; for (i = 0; i < tracer->str_db.num_string_db; i++) { + if (!tracer->str_db.size_out[i]) + continue; if (str_ptr > tracer->str_db.base_address_out[i] && str_ptr < tracer->str_db.base_address_out[i] + tracer->str_db.size_out[i]) { @@ -459,6 +466,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer, tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id); tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost); + tracer_event->out = trace; switch (tracer_event->event_id) { case TRACER_EVENT_TYPE_TIMESTAMP: @@ -581,6 +589,26 @@ void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, mlx5_tracer_clean_message(str_frmt); } +static int mlx5_tracer_handle_raw_string(struct mlx5_fw_tracer *tracer, + struct tracer_event *tracer_event) +{ + struct tracer_string_format *cur_string; + + cur_string = mlx5_tracer_message_insert(tracer, tracer_event); + if (!cur_string) + return -1; + + cur_string->event_id = tracer_event->event_id; + cur_string->timestamp = tracer_event->string_event.timestamp; + cur_string->lost = tracer_event->lost_event; + cur_string->string = "0x%08x%08x"; + cur_string->num_of_params = 2; + cur_string->params[0] = upper_32_bits(*tracer_event->out); + cur_string->params[1] = lower_32_bits(*tracer_event->out); + list_add_tail(&cur_string->list, &tracer->ready_strings_list); + return 0; +} + static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, struct tracer_event *tracer_event) { @@ -589,7 +617,7 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, if (tracer_event->string_event.tdsn == 0) { cur_string = mlx5_tracer_get_string(tracer, tracer_event); if (!cur_string) - return -1; + return mlx5_tracer_handle_raw_string(tracer, tracer_event); cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string); cur_string->last_param_num = 0; @@ -602,9 +630,9 @@ static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer, } else { cur_string = mlx5_tracer_message_get(tracer, tracer_event); if (!cur_string) { - pr_debug("%s Got string event for unknown string tdsm: %d\n", + pr_debug("%s Got string event for unknown string tmsn: %d\n", __func__, tracer_event->string_event.tmsn); - return -1; + return mlx5_tracer_handle_raw_string(tracer, tracer_event); } cur_string->last_param_num += 1; if (cur_string->last_param_num > TRACER_MAX_PARAMS) { @@ -756,6 +784,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) if (err) mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err); + tracer->buff.consumer_index = 0; return err; } @@ -820,7 +849,6 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { tracer->owner = false; - tracer->buff.consumer_index = 0; return; } @@ -930,6 +958,14 @@ unlock: return err; } +static void mlx5_fw_tracer_update_db(struct work_struct *work) +{ + struct mlx5_fw_tracer *tracer = + container_of(work, struct mlx5_fw_tracer, update_db_work); + + mlx5_fw_tracer_reload(tracer); +} + /* Create software resources (Buffers, etc ..) */ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) { @@ -957,6 +993,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev) INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change); INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db); INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces); + INIT_WORK(&tracer->update_db_work, mlx5_fw_tracer_update_db); + mutex_init(&tracer->state_lock); err = mlx5_query_mtrc_caps(tracer); @@ -1003,11 +1041,15 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) if (IS_ERR_OR_NULL(tracer)) return 0; - dev = tracer->dev; - if (!tracer->str_db.loaded) queue_work(tracer->work_queue, &tracer->read_fw_strings_work); + mutex_lock(&tracer->state_lock); + if (test_and_set_bit(MLX5_TRACER_STATE_UP, &tracer->state)) + goto unlock; + + dev = tracer->dev; + err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn); if (err) { mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err); @@ -1028,6 +1070,8 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) mlx5_core_warn(dev, "FWTracer: Failed to start tracer %d\n", err); goto err_notifier_unregister; } +unlock: + mutex_unlock(&tracer->state_lock); return 0; err_notifier_unregister: @@ -1037,6 +1081,7 @@ err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); err_cancel_work: cancel_work_sync(&tracer->read_fw_strings_work); + mutex_unlock(&tracer->state_lock); return err; } @@ -1046,17 +1091,27 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) if (IS_ERR_OR_NULL(tracer)) return; + mutex_lock(&tracer->state_lock); + if (!test_and_clear_bit(MLX5_TRACER_STATE_UP, &tracer->state)) + goto unlock; + mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n", tracer->owner); mlx5_eq_notifier_unregister(tracer->dev, &tracer->nb); cancel_work_sync(&tracer->ownership_change_work); cancel_work_sync(&tracer->handle_traces_work); + /* It is valid to get here from update_db_work. Hence, don't wait for + * update_db_work to finished. + */ + cancel_work(&tracer->update_db_work); if (tracer->owner) mlx5_fw_tracer_ownership_release(tracer); mlx5_core_destroy_mkey(tracer->dev, tracer->buff.mkey); mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn); +unlock: + mutex_unlock(&tracer->state_lock); } /* Free software resources (Buffers, etc ..) */ @@ -1073,6 +1128,7 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer) mlx5_fw_tracer_clean_saved_traces_array(tracer); mlx5_fw_tracer_free_strings_db(tracer); mlx5_fw_tracer_destroy_log_buf(tracer); + mutex_destroy(&tracer->state_lock); destroy_workqueue(tracer->work_queue); kvfree(tracer); } @@ -1082,6 +1138,8 @@ static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer) struct mlx5_core_dev *dev; int err; + if (test_and_set_bit(MLX5_TRACER_RECREATE_DB, &tracer->state)) + return 0; cancel_work_sync(&tracer->read_fw_strings_work); mlx5_fw_tracer_clean_ready_list(tracer); mlx5_fw_tracer_clean_print_hash(tracer); @@ -1092,17 +1150,18 @@ static int mlx5_fw_tracer_recreate_strings_db(struct mlx5_fw_tracer *tracer) err = mlx5_query_mtrc_caps(tracer); if (err) { mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err); - return err; + goto out; } err = mlx5_fw_tracer_allocate_strings_db(tracer); if (err) { mlx5_core_warn(dev, "FWTracer: Allocate strings DB failed %d\n", err); - return err; + goto out; } mlx5_fw_tracer_init_saved_traces_array(tracer); - - return 0; +out: + clear_bit(MLX5_TRACER_RECREATE_DB, &tracer->state); + return err; } int mlx5_fw_tracer_reload(struct mlx5_fw_tracer *tracer) @@ -1142,6 +1201,9 @@ static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE: queue_work(tracer->work_queue, &tracer->handle_traces_work); break; + case MLX5_TRACER_SUBTYPE_STRINGS_DB_UPDATE: + queue_work(tracer->work_queue, &tracer->update_db_work); + break; default: mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n", eqe->sub_type); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 4762b55b0b0e..5c548bb74f07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -63,6 +63,11 @@ struct mlx5_fw_trace_data { char msg[TRACE_STR_MSG]; }; +enum mlx5_fw_tracer_state { + MLX5_TRACER_STATE_UP = BIT(0), + MLX5_TRACER_RECREATE_DB = BIT(1), +}; + struct mlx5_fw_tracer { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -104,6 +109,9 @@ struct mlx5_fw_tracer { struct work_struct handle_traces_work; struct hlist_head hash[MESSAGE_HASH_SIZE]; struct list_head ready_strings_list; + struct work_struct update_db_work; + struct mutex state_lock; /* Synchronize update work with reload flows */ + unsigned long state; }; struct tracer_string_format { @@ -158,6 +166,7 @@ struct tracer_event { struct tracer_string_event string_event; struct tracer_timestamp_event timestamp_event; }; + u64 *out; }; struct mlx5_ifc_tracer_event_bits { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index b70e36025d92..9a3878f9e582 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -95,7 +95,7 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) mlx5_host_pf_cleanup(dev); - err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages); + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6f8723cc6874..125c7cb7d839 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -454,6 +454,7 @@ struct mlx5e_txqsq { struct mlx5_clock *clock; struct net_device *netdev; struct mlx5_core_dev *mdev; + struct mlx5e_channel *channel; struct mlx5e_priv *priv; /* control path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c index 57f4b1b50421..7ac1ad9c46de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c @@ -314,11 +314,11 @@ static int port_set_buffer(struct mlx5e_priv *priv, err = port_update_shared_buffer(priv->mdev, current_headroom_size, new_headroom_size); if (err) - return err; + goto out; err = port_update_pool_cfg(priv->mdev, port_buffer); if (err) - return err; + goto out; err = mlx5e_port_set_pbmc(mdev, in); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 8469e9c38670..9a1bc93b7dc6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -771,8 +771,8 @@ void mlx5e_ptp_activate_channel(struct mlx5e_ptp *c) if (test_bit(MLX5E_PTP_STATE_RX, c->state)) { mlx5e_ptp_rx_set_fs(c->priv); mlx5e_activate_rq(&c->rq); - mlx5e_trigger_napi_sched(&c->napi); } + mlx5e_trigger_napi_sched(&c->napi); } void mlx5e_ptp_deactivate_channel(struct mlx5e_ptp *c) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 8099a21e674c..ce85b48d327d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -438,10 +438,6 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, switch (event) { case SWITCHDEV_FDB_ADD_TO_BRIDGE: - /* only handle the event on native eswtich of representor */ - if (!mlx5_esw_bridge_is_local(dev, rep, esw)) - break; - fdb_info = container_of(info, struct switchdev_notifier_fdb_info, info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index b195dbbf6c90..41e356d9d785 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -81,6 +81,10 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) sq->stats->recover++; clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); mlx5e_activate_txqsq(sq); + if (sq->channel) + mlx5e_trigger_napi_icosq(sq->channel); + else + mlx5e_trigger_napi_sched(sq->cq.napi); return 0; out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index 78c427b38048..c095a12346de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -232,9 +232,9 @@ parse_mirred(struct mlx5e_tc_act_parse_state *parse_state, parse_state->ifindexes[if_count] = out_dev->ifindex; parse_state->if_count++; is_uplink_rep = mlx5e_eswitch_uplink_rep(out_dev); - err = mlx5_lag_do_mirred(priv->mdev, out_dev); - if (err) - return err; + + if (mlx5_lag_mpesw_do_mirred(priv->mdev, out_dev, extack)) + return -EOPNOTSUPP; out_dev = get_fdb_out_dev(uplink_dev, out_dev); if (!out_dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c index b86ac604d0c2..2e0d88b513aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c @@ -44,19 +44,17 @@ parse_tc_vlan_action(struct mlx5e_priv *priv, return -EOPNOTSUPP; } + if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, vlan_idx)) { + NL_SET_ERR_MSG_MOD(extack, "firmware vlan actions is not supported"); + return -EOPNOTSUPP; + } + switch (act->id) { case FLOW_ACTION_VLAN_POP: - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, "vlan pop action is not supported"); - return -EOPNOTSUPP; - } - + if (vlan_idx) *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2; - } else { + else *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; - } break; case FLOW_ACTION_VLAN_PUSH: attr->vlan_vid[vlan_idx] = act->vlan.vid; @@ -65,25 +63,10 @@ parse_tc_vlan_action(struct mlx5e_priv *priv, if (!attr->vlan_proto[vlan_idx]) attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q); - if (vlan_idx) { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, - MLX5_FS_VLAN_DEPTH)) { - NL_SET_ERR_MSG_MOD(extack, - "vlan push action is not supported for vlan depth > 1"); - return -EOPNOTSUPP; - } - + if (vlan_idx) *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; - } else { - if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && - (act->vlan.proto != htons(ETH_P_8021Q) || - act->vlan.prio)) { - NL_SET_ERR_MSG_MOD(extack, "vlan push action is not supported"); - return -EOPNOTSUPP; - } - + else *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; - } break; case FLOW_ACTION_VLAN_POP_ETH: parse_state->eth_pop = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index e84c3400ba1d..7b0d3de0ec6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -158,6 +158,11 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry, attrs->family = x->props.family; attrs->type = x->xso.type; attrs->reqid = x->props.reqid; + attrs->upspec.dport = ntohs(x->sel.dport); + attrs->upspec.dport_mask = ntohs(x->sel.dport_mask); + attrs->upspec.sport = ntohs(x->sel.sport); + attrs->upspec.sport_mask = ntohs(x->sel.sport_mask); + attrs->upspec.proto = x->sel.proto; mlx5e_ipsec_init_limits(sa_entry, attrs); } @@ -221,6 +226,13 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev, NL_SET_ERR_MSG_MOD(extack, "Cannot offload xfrm states with geniv other than seqiv"); return -EINVAL; } + + if (x->sel.proto != IPPROTO_IP && + (x->sel.proto != IPPROTO_UDP || x->xso.dir != XFRM_DEV_OFFLOAD_OUT)) { + NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction"); + return -EINVAL; + } + switch (x->xso.type) { case XFRM_DEV_OFFLOAD_CRYPTO: if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_CRYPTO)) { @@ -517,6 +529,12 @@ static int mlx5e_xfrm_validate_policy(struct xfrm_policy *x, return -EINVAL; } + if (x->selector.proto != IPPROTO_IP && + (x->selector.proto != IPPROTO_UDP || x->xdo.dir != XFRM_DEV_OFFLOAD_OUT)) { + NL_SET_ERR_MSG_MOD(extack, "Device does not support upper protocol other than UDP, and only Tx direction"); + return -EINVAL; + } + return 0; } @@ -537,6 +555,11 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry, attrs->action = x->action; attrs->type = XFRM_DEV_OFFLOAD_PACKET; attrs->reqid = x->xfrm_vec[0].reqid; + attrs->upspec.dport = ntohs(sel->dport); + attrs->upspec.dport_mask = ntohs(sel->dport_mask); + attrs->upspec.sport = ntohs(sel->sport); + attrs->upspec.sport_mask = ntohs(sel->sport_mask); + attrs->upspec.proto = sel->proto; } static int mlx5e_xfrm_add_policy(struct xfrm_policy *x, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 8bed9c361075..b387adca9c20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -52,6 +52,14 @@ struct aes_gcm_keymat { u32 aes_key[256 / 32]; }; +struct upspec { + u16 dport; + u16 dport_mask; + u16 sport; + u16 sport_mask; + u8 proto; +}; + struct mlx5_accel_esp_xfrm_attrs { u32 esn; u32 spi; @@ -68,6 +76,7 @@ struct mlx5_accel_esp_xfrm_attrs { __be32 a6[4]; } daddr; + struct upspec upspec; u8 dir : 2; u8 esn_overlap : 1; u8 esn_trigger : 1; @@ -181,6 +190,7 @@ struct mlx5_accel_pol_xfrm_attrs { __be32 a6[4]; } daddr; + struct upspec upspec; u8 family; u8 action; u8 type : 2; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c index 9f19f4b59a70..5da6fe68eea6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c @@ -467,6 +467,27 @@ static void setup_fte_reg_c0(struct mlx5_flow_spec *spec, u32 reqid) misc_parameters_2.metadata_reg_c_0, reqid); } +static void setup_fte_upper_proto_match(struct mlx5_flow_spec *spec, struct upspec *upspec) +{ + if (upspec->proto != IPPROTO_UDP) + return; + + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, spec->match_criteria, ip_protocol); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, ip_protocol, upspec->proto); + if (upspec->dport) { + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + upspec->dport_mask); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->dport); + } + + if (upspec->sport) { + MLX5_SET(fte_match_set_lyr_2_4, spec->match_criteria, udp_dport, + upspec->sport_mask); + MLX5_SET(fte_match_set_lyr_2_4, spec->match_value, udp_dport, upspec->sport); + } +} + static int setup_modify_header(struct mlx5_core_dev *mdev, u32 val, u8 dir, struct mlx5_flow_act *flow_act) { @@ -654,6 +675,7 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry) setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_no_frags(spec); + setup_fte_upper_proto_match(spec, &attrs->upspec); switch (attrs->type) { case XFRM_DEV_OFFLOAD_CRYPTO: @@ -728,6 +750,7 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry) setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6); setup_fte_no_frags(spec); + setup_fte_upper_proto_match(spec, &attrs->upspec); err = setup_modify_header(mdev, attrs->reqid, XFRM_DEV_OFFLOAD_OUT, &flow_act); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 57ac0f663fcd..7fb3835befbd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -92,7 +92,6 @@ static void mlx5e_ipsec_packet_setup(void *obj, u32 pdn, MLX5_SET(ipsec_aso, aso_ctx, remove_flow_pkt_cnt, lower_32_bits(attrs->hard_packet_limit)); MLX5_SET(ipsec_aso, aso_ctx, hard_lft_arm, 1); - MLX5_SET(ipsec_aso, aso_ctx, remove_flow_enable, 1); } if (attrs->soft_packet_limit != XFRM_INF) { @@ -329,8 +328,7 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) if (attrs->soft_packet_limit != XFRM_INF) if (!MLX5_GET(ipsec_aso, aso->ctx, soft_lft_arm) || - !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) || - !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable)) + !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm)) xfrm_state_check_expire(sa_entry->x); unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index e80b43b7aac9..60b3e08a1028 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -899,8 +899,6 @@ static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls, return; tls->debugfs.dfs_tx = debugfs_create_dir("tx", dfs_root); - if (!tls->debugfs.dfs_tx) - return; debugfs_create_size_t("pool_size", 0400, tls->debugfs.dfs_tx, &tls->tx_pool->size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 7298fe782e9e..05796f8b1d7c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -450,7 +450,7 @@ void mlx5e_enable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) void mlx5e_disable_cvlan_filter(struct mlx5e_flow_steering *fs, bool promisc) { - if (fs->vlan->cvlan_filter_disabled) + if (!fs->vlan || fs->vlan->cvlan_filter_disabled) return; fs->vlan->cvlan_filter_disabled = true; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0e87432ec6f1..ec81d935262f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -39,6 +39,7 @@ #include <linux/if_bridge.h> #include <linux/filter.h> #include <net/page_pool.h> +#include <net/pkt_sched.h> #include <net/xdp_sock_drv.h> #include "eswitch.h" #include "en.h" @@ -180,17 +181,21 @@ static void mlx5e_disable_async_events(struct mlx5e_priv *priv) static int blocking_event(struct notifier_block *nb, unsigned long event, void *data) { struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, blocking_events_nb); + struct mlx5_devlink_trap_event_ctx *trap_event_ctx = data; int err; switch (event) { case MLX5_DRIVER_EVENT_TYPE_TRAP: - err = mlx5e_handle_trap_event(priv, data); + err = mlx5e_handle_trap_event(priv, trap_event_ctx->trap); + if (err) { + trap_event_ctx->err = err; + return NOTIFY_BAD; + } break; default: - netdev_warn(priv->netdev, "Sync event: Unknown event %ld\n", event); - err = -EINVAL; + return NOTIFY_DONE; } - return err; + return NOTIFY_OK; } static void mlx5e_enable_blocking_events(struct mlx5e_priv *priv) @@ -592,7 +597,8 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param rq->ix = c->ix; rq->channel = c; rq->mdev = mdev; - rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + rq->hw_mtu = + MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN * !params->scatter_fcs_en; rq->xdpsq = &c->rq_xdpsq; rq->stats = &c->priv->channel_stats[c->ix]->rq; rq->ptp_cyc2time = mlx5_rq_ts_translator(mdev); @@ -1015,35 +1021,6 @@ int mlx5e_flush_rq(struct mlx5e_rq *rq, int curr_state) return mlx5e_rq_to_ready(rq, curr_state); } -static int mlx5e_modify_rq_scatter_fcs(struct mlx5e_rq *rq, bool enable) -{ - struct mlx5_core_dev *mdev = rq->mdev; - - void *in; - void *rqc; - int inlen; - int err; - - inlen = MLX5_ST_SZ_BYTES(modify_rq_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) - return -ENOMEM; - - rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); - - MLX5_SET(modify_rq_in, in, rq_state, MLX5_RQC_STATE_RDY); - MLX5_SET64(modify_rq_in, in, modify_bitmask, - MLX5_MODIFY_RQ_IN_MODIFY_BITMASK_SCATTER_FCS); - MLX5_SET(rqc, rqc, scatter_fcs, enable); - MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RDY); - - err = mlx5_core_modify_rq(mdev, rq->rqn, in); - - kvfree(in); - - return err; -} - static int mlx5e_modify_rq_vsd(struct mlx5e_rq *rq, bool vsd) { struct mlx5_core_dev *mdev = rq->mdev; @@ -1470,6 +1447,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->mkey_be = c->mkey_be; sq->netdev = c->netdev; sq->mdev = c->mdev; + sq->channel = c; sq->priv = c->priv; sq->ch_ix = c->ix; sq->txq_ix = txq_ix; @@ -2482,8 +2460,6 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_xsk(c); else mlx5e_activate_rq(&c->rq); - - mlx5e_trigger_napi_icosq(c); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -2575,13 +2551,19 @@ err_free: return err; } -static void mlx5e_activate_channels(struct mlx5e_channels *chs) +static void mlx5e_activate_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs) { int i; for (i = 0; i < chs->num; i++) mlx5e_activate_channel(chs->c[i]); + if (priv->htb) + mlx5e_qos_activate_queues(priv); + + for (i = 0; i < chs->num; i++) + mlx5e_trigger_napi_icosq(chs->c[i]); + if (chs->ptp) mlx5e_ptp_activate_channel(chs->ptp); } @@ -2888,9 +2870,7 @@ out: void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { mlx5e_build_txq_maps(priv); - mlx5e_activate_channels(&priv->channels); - if (priv->htb) - mlx5e_qos_activate_queues(priv); + mlx5e_activate_channels(priv, &priv->channels); mlx5e_xdp_tx_enable(priv); /* dev_watchdog() wants all TX queues to be started when the carrier is @@ -2998,32 +2978,37 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, mlx5e_fp_preactivate preactivate, void *context, bool reset) { - struct mlx5e_channels new_chs = {}; + struct mlx5e_channels *new_chs; int err; reset &= test_bit(MLX5E_STATE_OPENED, &priv->state); if (!reset) return mlx5e_switch_priv_params(priv, params, preactivate, context); - new_chs.params = *params; + new_chs = kzalloc(sizeof(*new_chs), GFP_KERNEL); + if (!new_chs) + return -ENOMEM; + new_chs->params = *params; - mlx5e_selq_prepare_params(&priv->selq, &new_chs.params); + mlx5e_selq_prepare_params(&priv->selq, &new_chs->params); - err = mlx5e_open_channels(priv, &new_chs); + err = mlx5e_open_channels(priv, new_chs); if (err) goto err_cancel_selq; - err = mlx5e_switch_priv_channels(priv, &new_chs, preactivate, context); + err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context); if (err) goto err_close; + kfree(new_chs); return 0; err_close: - mlx5e_close_channels(&new_chs); + mlx5e_close_channels(new_chs); err_cancel_selq: mlx5e_selq_cancel(&priv->selq); + kfree(new_chs); return err; } @@ -3315,20 +3300,6 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) mlx5e_destroy_tises(priv); } -static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) -{ - int err = 0; - int i; - - for (i = 0; i < chs->num; i++) { - err = mlx5e_modify_rq_scatter_fcs(&chs->c[i]->rq, enable); - if (err) - return err; - } - - return 0; -} - static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd) { int err; @@ -3904,41 +3875,27 @@ static int mlx5e_set_rx_port_ts(struct mlx5_core_dev *mdev, bool enable) return mlx5_set_ports_check(mdev, in, sizeof(in)); } +static int mlx5e_set_rx_port_ts_wrap(struct mlx5e_priv *priv, void *ctx) +{ + struct mlx5_core_dev *mdev = priv->mdev; + bool enable = *(bool *)ctx; + + return mlx5e_set_rx_port_ts(mdev, enable); +} + static int set_feature_rx_fcs(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_channels *chs = &priv->channels; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_params new_params; int err; mutex_lock(&priv->state_lock); - if (enable) { - err = mlx5e_set_rx_port_ts(mdev, false); - if (err) - goto out; - - chs->params.scatter_fcs_en = true; - err = mlx5e_modify_channels_scatter_fcs(chs, true); - if (err) { - chs->params.scatter_fcs_en = false; - mlx5e_set_rx_port_ts(mdev, true); - } - } else { - chs->params.scatter_fcs_en = false; - err = mlx5e_modify_channels_scatter_fcs(chs, false); - if (err) { - chs->params.scatter_fcs_en = true; - goto out; - } - err = mlx5e_set_rx_port_ts(mdev, true); - if (err) { - mlx5_core_warn(mdev, "Failed to set RX port timestamp %d\n", err); - err = 0; - } - } - -out: + new_params = chs->params; + new_params.scatter_fcs_en = enable; + err = mlx5e_safe_switch_params(priv, &new_params, mlx5e_set_rx_port_ts_wrap, + &new_params.scatter_fcs_en, true); mutex_unlock(&priv->state_lock); return err; } @@ -4075,6 +4032,10 @@ static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev if (netdev->features & NETIF_F_GRO_HW) netdev_warn(netdev, "Disabling HW_GRO, not supported in switchdev mode\n"); + features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + if (netdev->features & NETIF_F_HW_VLAN_CTAG_FILTER) + netdev_warn(netdev, "Disabling HW_VLAN CTAG FILTERING, not supported in switchdev mode\n"); + return features; } @@ -4780,6 +4741,13 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) if (old_prog) bpf_prog_put(old_prog); + if (reset) { + if (prog) + xdp_features_set_redirect_target(netdev, true); + else + xdp_features_clear_redirect_target(netdev); + } + if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset) goto unlock; @@ -5175,6 +5143,10 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->features |= NETIF_F_HIGHDMA; netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY | + NETDEV_XDP_ACT_RX_SG; + netdev->priv_flags |= IFF_UNICAST_FLT; netif_set_tso_max_size(netdev, GSO_MAX_SIZE); @@ -5975,7 +5947,7 @@ static int mlx5e_probe(struct auxiliary_device *adev, } mlx5e_dcbnl_init_app(priv); - mlx5_uplink_netdev_set(mdev, netdev); + mlx5_core_uplink_netdev_set(mdev, netdev); mlx5e_params_print_info(mdev, &priv->channels.params); return 0; @@ -5999,6 +5971,7 @@ static void mlx5e_remove(struct auxiliary_device *adev) struct mlx5e_priv *priv = mlx5e_dev->priv; pm_message_t state = {}; + mlx5_core_uplink_netdev_set(priv->mdev, NULL); mlx5e_dcbnl_delete_app(priv); unregister_netdev(priv->netdev); mlx5e_suspend(adev, state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 4e6f5caf8ab6..e2ec80ebde58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1124,8 +1124,6 @@ static void mlx5e_tc_debugfs_init(struct mlx5e_tc_table *tc, return; tc->dfs_root = debugfs_create_dir("tc", dfs_root); - if (!tc->dfs_root) - return; debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root, &tc->hairpin_params, &fops_hairpin_queues); @@ -1884,7 +1882,6 @@ post_process_attr(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *attr, struct netlink_ext_ack *extack) { - struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; bool vf_tun; int err = 0; @@ -1896,12 +1893,6 @@ post_process_attr(struct mlx5e_tc_flow *flow, if (err) goto err_out; - if (mlx5e_is_eswitch_flow(flow)) { - err = mlx5_eswitch_add_vlan_action(esw, attr); - if (err) - goto err_out; - } - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_tc_attach_mod_hdr(flow->priv, flow, attr); if (err) @@ -2105,8 +2096,6 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, if (mlx5_flow_has_geneve_opt(flow)) mlx5_geneve_tlv_option_del(priv->mdev->geneve); - mlx5_eswitch_del_vlan_action(esw, attr); - if (flow->decap_route) mlx5e_detach_decap_route(priv, flow); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 9b44557e7271..66ec7932f008 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -817,9 +817,12 @@ static void comp_irqs_release(struct mlx5_core_dev *dev) static int comp_irqs_request(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = dev->priv.eq_table; + const struct cpumask *prev = cpu_none_mask; + const struct cpumask *mask; int ncomp_eqs = table->num_comp_eqs; u16 *cpus; int ret; + int cpu; int i; ncomp_eqs = table->num_comp_eqs; @@ -838,8 +841,19 @@ static int comp_irqs_request(struct mlx5_core_dev *dev) ret = -ENOMEM; goto free_irqs; } - for (i = 0; i < ncomp_eqs; i++) - cpus[i] = cpumask_local_spread(i, dev->priv.numa_node); + + i = 0; + rcu_read_lock(); + for_each_numa_hop_mask(mask, dev->priv.numa_node) { + for_each_cpu_andnot(cpu, mask, prev) { + cpus[i] = cpu; + if (++i == ncomp_eqs) + goto spread_done; + } + prev = mask; + } +spread_done: + rcu_read_unlock(); ret = mlx5_irqs_request_vectors(dev, cpus, ncomp_eqs, table->comp_irqs); kfree(cpus); if (ret < 0) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index b176648d1343..3cdcb0e0b20f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1715,7 +1715,7 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 struct mlx5_esw_bridge *bridge; port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); - if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER) + if (!port) return; bridge = port->bridge; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 5b5a215a7dc5..fd03f076551b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -222,7 +222,6 @@ struct mlx5_eswitch_fdb { struct mlx5_flow_handle **send_to_vport_meta_rules; struct mlx5_flow_handle *miss_rule_uni; struct mlx5_flow_handle *miss_rule_multi; - int vlan_push_pop_refcount; struct mlx5_fs_chains *esw_chains_priv; struct { @@ -520,10 +519,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, struct netlink_ext_ack *extack); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type); -int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr); -int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr); int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u16 vport, u16 vlan, u8 qos, u8 set_flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 3a82e385544d..8fb09143e9e8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -579,16 +579,16 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (esw->mode != MLX5_ESWITCH_OFFLOADS) return ERR_PTR(-EOPNOTSUPP); + if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) + return ERR_PTR(-EOPNOTSUPP); + dest = kcalloc(MLX5_MAX_FLOW_FWD_VPORTS + 1, sizeof(*dest), GFP_KERNEL); if (!dest) return ERR_PTR(-ENOMEM); flow_act.action = attr->action; - /* if per flow vlan pop/push is emulated, don't set that into the firmware */ - if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH | - MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { flow_act.vlan[0].ethtype = ntohs(esw_attr->vlan_proto[0]); flow_act.vlan[0].vid = esw_attr->vlan_vid[0]; flow_act.vlan[0].prio = esw_attr->vlan_prio[0]; @@ -829,204 +829,6 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw, __mlx5_eswitch_del_rule(esw, rule, attr, true); } -static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) -{ - struct mlx5_eswitch_rep *rep; - unsigned long i; - int err = 0; - - esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); - mlx5_esw_for_each_host_func_vport(esw, i, rep, esw->esw_funcs.num_vfs) { - if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED) - continue; - - err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); - if (err) - goto out; - } - -out: - return err; -} - -static struct mlx5_eswitch_rep * -esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop) -{ - struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL; - - in_rep = attr->in_rep; - out_rep = attr->dests[0].rep; - - if (push) - vport = in_rep; - else if (pop) - vport = out_rep; - else - vport = in_rep; - - return vport; -} - -static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, - bool push, bool pop, bool fwd) -{ - struct mlx5_eswitch_rep *in_rep, *out_rep; - - if ((push || pop) && !fwd) - goto out_notsupp; - - in_rep = attr->in_rep; - out_rep = attr->dests[0].rep; - - if (push && in_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - if (pop && out_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - /* vport has vlan push configured, can't offload VF --> wire rules w.o it */ - if (!push && !pop && fwd) - if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK) - goto out_notsupp; - - /* protects against (1) setting rules with different vlans to push and - * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0) - */ - if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0])) - goto out_notsupp; - - return 0; - -out_notsupp: - return -EOPNOTSUPP; -} - -int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr) -{ - struct offloads_fdb *offloads = &esw->fdb_table.offloads; - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_eswitch_rep *vport = NULL; - bool push, pop, fwd; - int err = 0; - - /* nop if we're on the vlan push/pop non emulation mode */ - if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - return 0; - - push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); - pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - fwd = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && - !attr->dest_chain); - - mutex_lock(&esw->state_lock); - - err = esw_add_vlan_action_check(esw_attr, push, pop, fwd); - if (err) - goto unlock; - - attr->flags &= ~MLX5_ATTR_FLAG_VLAN_HANDLED; - - vport = esw_vlan_action_get_vport(esw_attr, push, pop); - - if (!push && !pop && fwd) { - /* tracks VF --> wire rules without vlan push action */ - if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { - vport->vlan_refcount++; - attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; - } - - goto unlock; - } - - if (!push && !pop) - goto unlock; - - if (!(offloads->vlan_push_pop_refcount)) { - /* it's the 1st vlan rule, apply global vlan pop policy */ - err = esw_set_global_vlan_pop(esw, SET_VLAN_STRIP); - if (err) - goto out; - } - offloads->vlan_push_pop_refcount++; - - if (push) { - if (vport->vlan_refcount) - goto skip_set_push; - - err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, esw_attr->vlan_vid[0], - 0, SET_VLAN_INSERT | SET_VLAN_STRIP); - if (err) - goto out; - vport->vlan = esw_attr->vlan_vid[0]; -skip_set_push: - vport->vlan_refcount++; - } -out: - if (!err) - attr->flags |= MLX5_ATTR_FLAG_VLAN_HANDLED; -unlock: - mutex_unlock(&esw->state_lock); - return err; -} - -int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, - struct mlx5_flow_attr *attr) -{ - struct offloads_fdb *offloads = &esw->fdb_table.offloads; - struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr; - struct mlx5_eswitch_rep *vport = NULL; - bool push, pop, fwd; - int err = 0; - - /* nop if we're on the vlan push/pop non emulation mode */ - if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1)) - return 0; - - if (!(attr->flags & MLX5_ATTR_FLAG_VLAN_HANDLED)) - return 0; - - push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH); - pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); - fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); - - mutex_lock(&esw->state_lock); - - vport = esw_vlan_action_get_vport(esw_attr, push, pop); - - if (!push && !pop && fwd) { - /* tracks VF --> wire rules without vlan push action */ - if (esw_attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) - vport->vlan_refcount--; - - goto out; - } - - if (push) { - vport->vlan_refcount--; - if (vport->vlan_refcount) - goto skip_unset_push; - - vport->vlan = 0; - err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, - 0, 0, SET_VLAN_STRIP); - if (err) - goto out; - } - -skip_unset_push: - offloads->vlan_push_pop_refcount--; - if (offloads->vlan_push_pop_refcount) - goto out; - - /* no more vlan rules, stop global vlan pop policy */ - err = esw_set_global_vlan_pop(esw, 0); - -out: - mutex_unlock(&esw->state_lock); - return err; -} - struct mlx5_flow_handle * mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, struct mlx5_eswitch *from_esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index 9459e56ee90a..718cf09c28ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -424,6 +424,7 @@ int mlx5_blocking_notifier_register(struct mlx5_core_dev *dev, struct notifier_b return blocking_notifier_chain_register(&events->sw_nh, nb); } +EXPORT_SYMBOL(mlx5_blocking_notifier_register); int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb) { @@ -431,6 +432,7 @@ int mlx5_blocking_notifier_unregister(struct mlx5_core_dev *dev, struct notifier return blocking_notifier_chain_unregister(&events->sw_nh, nb); } +EXPORT_SYMBOL(mlx5_blocking_notifier_unregister); int mlx5_blocking_notifier_call_chain(struct mlx5_core_dev *dev, unsigned int event, void *data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 32d4c967469c..374c17445e54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -272,8 +272,6 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, unsigned int size; int err; - if (ft_attr->max_fte != POOL_NEXT_SIZE) - size = roundup_pow_of_two(ft_attr->max_fte); size = mlx5_ft_pool_get_avail_sz(dev, ft->type, ft_attr->max_fte); if (!size) return -ENOSPC; @@ -412,11 +410,6 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_CMD_OP_CREATE_FLOW_GROUP); MLX5_SET(create_flow_group_in, in, table_type, ft->type); MLX5_SET(create_flow_group_in, in, table_id, ft->id); - if (ft->vport) { - MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); - MLX5_SET(create_flow_group_in, in, other_vport, 1); - } - MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); MLX5_SET(create_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index dd43a940499b..fad479df12e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1776,7 +1776,6 @@ static int build_match_list(struct match_list *match_head, { struct rhlist_head *tmp, *list; struct mlx5_flow_group *g; - int err = 0; rcu_read_lock(); INIT_LIST_HEAD(&match_head->list); @@ -1802,7 +1801,7 @@ static int build_match_list(struct match_list *match_head, list_add_tail(&curr_match->list, &match_head->list); } rcu_read_unlock(); - return err; + return 0; } static u64 matched_fgs_get_version(struct list_head *match_head) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 1da4da564e6d..63290da84010 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -371,6 +371,7 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev) mlx5_core_err(dev, "PCI link not ready (0x%04x) after %llu ms\n", reg16, mlx5_tout_ms(dev, PCI_TOGGLE)); err = -ETIMEDOUT; + goto restore; } do { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 879555ba847d..1e8bee906c31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -62,7 +62,7 @@ enum { }; enum { - MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_HEALTH_WORK, }; enum { @@ -675,7 +675,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) devlink = priv_to_devlink(dev); mutex_lock(&dev->intf_state_mutex); - if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { + if (test_bit(MLX5_DROP_HEALTH_WORK, &health->flags)) { mlx5_core_err(dev, "health works are not permitted at this stage\n"); mutex_unlock(&dev->intf_state_mutex); return; @@ -771,14 +771,8 @@ static unsigned long get_next_poll_jiffies(struct mlx5_core_dev *dev) void mlx5_trigger_health_work(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - spin_lock_irqsave(&health->wq_lock, flags); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) - queue_work(health->wq, &health->fatal_report_work); - else - mlx5_core_err(dev, "new health works are not permitted at this stage\n"); - spin_unlock_irqrestore(&health->wq_lock, flags); + queue_work(health->wq, &health->fatal_report_work); } #define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60) @@ -858,7 +852,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) timer_setup(&health->timer, poll_health, 0); health->fatal_error = MLX5_SENSOR_NO_ERR; - clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_HEALTH_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -869,13 +863,9 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - if (disable_health) { - spin_lock_irqsave(&health->wq_lock, flags); - set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); - spin_unlock_irqrestore(&health->wq_lock, flags); - } + if (disable_health) + set_bit(MLX5_DROP_HEALTH_WORK, &health->flags); del_timer_sync(&health->timer); } @@ -891,11 +881,8 @@ void mlx5_start_health_fw_log_up(struct mlx5_core_dev *dev) void mlx5_drain_health_wq(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; - unsigned long flags; - spin_lock_irqsave(&health->wq_lock, flags); - set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); - spin_unlock_irqrestore(&health->wq_lock, flags); + set_bit(MLX5_DROP_HEALTH_WORK, &health->flags); cancel_delayed_work_sync(&health->update_fw_log_ts_work); cancel_work_sync(&health->report_work); cancel_work_sync(&health->fatal_report_work); @@ -928,7 +915,6 @@ int mlx5_health_init(struct mlx5_core_dev *dev) kfree(name); if (!health->wq) goto out_err; - spin_lock_init(&health->wq_lock); INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work); INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work); INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index eff92dc0927c..779d92b762d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -172,6 +172,7 @@ enum mlx5_ptys_rate { MLX5_PTYS_RATE_EDR = 1 << 5, MLX5_PTYS_RATE_HDR = 1 << 6, MLX5_PTYS_RATE_NDR = 1 << 7, + MLX5_PTYS_RATE_XDR = 1 << 8, }; static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) @@ -185,20 +186,21 @@ static inline int mlx5_ptys_rate_enum_to_int(enum mlx5_ptys_rate rate) case MLX5_PTYS_RATE_EDR: return 25000; case MLX5_PTYS_RATE_HDR: return 50000; case MLX5_PTYS_RATE_NDR: return 100000; + case MLX5_PTYS_RATE_XDR: return 200000; default: return -1; } } -static int mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) +static u32 mlx5i_get_speed_settings(u16 ib_link_width_oper, u16 ib_proto_oper) { int rate, width; rate = mlx5_ptys_rate_enum_to_int(ib_proto_oper); if (rate < 0) - return -EINVAL; + return SPEED_UNKNOWN; width = mlx5_ptys_width_enum_to_int(ib_link_width_oper); if (width < 0) - return -EINVAL; + return SPEED_UNKNOWN; return rate * width; } @@ -221,16 +223,13 @@ static int mlx5i_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising); speed = mlx5i_get_speed_settings(ib_link_width_oper, ib_proto_oper); - if (speed < 0) - return -EINVAL; + link_ksettings->base.speed = speed; + link_ksettings->base.duplex = speed == SPEED_UNKNOWN ? DUPLEX_UNKNOWN : DUPLEX_FULL; - link_ksettings->base.duplex = DUPLEX_FULL; link_ksettings->base.port = PORT_OTHER; link_ksettings->base.autoneg = AUTONEG_DISABLE; - link_ksettings->base.speed = speed; - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c index b8feaf0f5c4c..f4b777d4e108 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/debugfs.c @@ -22,7 +22,7 @@ static int type_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; char *mode = NULL; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); if (__mlx5_lag_is_active(ldev)) mode = get_str_mode_type(ldev); @@ -41,7 +41,7 @@ static int port_sel_mode_show(struct seq_file *file, void *priv) int ret = 0; char *mode; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); if (__mlx5_lag_is_active(ldev)) mode = mlx5_get_str_port_sel_mode(ldev->mode, ldev->mode_flags); @@ -61,7 +61,7 @@ static int state_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; bool active; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); active = __mlx5_lag_is_active(ldev); mutex_unlock(&ldev->lock); @@ -77,7 +77,7 @@ static int flags_show(struct seq_file *file, void *priv) bool shared_fdb; bool lag_active; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); if (!lag_active) @@ -108,7 +108,7 @@ static int mapping_show(struct seq_file *file, void *priv) int num_ports; int i; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); lag_active = __mlx5_lag_is_active(ldev); if (lag_active) { @@ -142,7 +142,7 @@ static int members_show(struct seq_file *file, void *priv) struct mlx5_lag *ldev; int i; - ldev = dev->priv.lag; + ldev = mlx5_lag_dev(dev); mutex_lock(&ldev->lock); for (i = 0; i < ldev->ports; i++) { if (!ldev->pf[i].dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index ad32b80e8501..dbf218cac535 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1187,7 +1187,7 @@ static int __mlx5_lag_dev_add_mdev(struct mlx5_core_dev *dev) tmp_dev = mlx5_get_next_phys_dev_lag(dev); if (tmp_dev) - ldev = tmp_dev->priv.lag; + ldev = mlx5_lag_dev(tmp_dev); if (!ldev) { ldev = mlx5_lag_dev_alloc(dev); @@ -1386,8 +1386,7 @@ bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev) spin_lock_irqsave(&lag_lock, flags); ldev = mlx5_lag_dev(dev); - res = ldev && __mlx5_lag_is_sriov(ldev) && - test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); + res = ldev && test_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, &ldev->mode_flags); spin_unlock_irqrestore(&lag_lock, flags); return res; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h index f30ac2de639f..66013bef9939 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h @@ -50,19 +50,6 @@ struct lag_tracker { enum netdev_lag_hash hash_type; }; -enum mpesw_op { - MLX5_MPESW_OP_ENABLE, - MLX5_MPESW_OP_DISABLE, -}; - -struct mlx5_mpesw_work_st { - struct work_struct work; - struct mlx5_lag *lag; - enum mpesw_op op; - struct completion comp; - int result; -}; - /* LAG data of a ConnectX card. * It serves both its phys functions. */ @@ -124,8 +111,6 @@ int mlx5_activate_lag(struct mlx5_lag *ldev, int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev, struct net_device *ndev); bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev); -void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev); -int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev); char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags); void mlx5_infer_tx_enabled(struct lag_tracker *tracker, u8 num_ports, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index d9fcb9ed726f..d85a8dfc153d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -28,13 +28,9 @@ static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev) bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { - struct mlx5_lag *ldev; - bool res; - - ldev = mlx5_lag_dev(dev); - res = ldev && __mlx5_lag_is_multipath(ldev); + struct mlx5_lag *ldev = mlx5_lag_dev(dev); - return res; + return ldev && __mlx5_lag_is_multipath(ldev); } /** diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c index c17e8f1ec914..3799f89ed1a6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c @@ -58,7 +58,7 @@ static void mlx5_mpesw_work(struct work_struct *work) static int mlx5_lag_mpesw_queue_work(struct mlx5_core_dev *dev, enum mpesw_op op) { - struct mlx5_lag *ldev = dev->priv.lag; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); struct mlx5_mpesw_work_st *work; int err = 0; @@ -96,25 +96,27 @@ int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev) return mlx5_lag_mpesw_queue_work(dev, MLX5_MPESW_OP_ENABLE); } -int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev) +int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev, + struct net_device *out_dev, + struct netlink_ext_ack *extack) { - struct mlx5_lag *ldev = mdev->priv.lag; + struct mlx5_lag *ldev = mlx5_lag_dev(mdev); if (!netif_is_bond_master(out_dev) || !ldev) return 0; - if (ldev->mode == MLX5_LAG_MODE_MPESW) - return -EOPNOTSUPP; + if (ldev->mode != MLX5_LAG_MODE_MPESW) + return 0; - return 0; + NL_SET_ERR_MSG_MOD(extack, "can't forward to bond in mpesw mode"); + return -EOPNOTSUPP; } bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev) { - bool ret; + struct mlx5_lag *ldev = mlx5_lag_dev(dev); - ret = dev->priv.lag && dev->priv.lag->mode == MLX5_LAG_MODE_MPESW; - return ret; + return ldev && ldev->mode == MLX5_LAG_MODE_MPESW; } void mlx5_lag_mpesw_init(struct mlx5_lag *ldev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h index 88e8daffcf92..818f19b5a984 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.h @@ -12,8 +12,25 @@ struct lag_mpesw { atomic_t mpesw_rule_count; }; -int mlx5_lag_do_mirred(struct mlx5_core_dev *mdev, struct net_device *out_dev); +enum mpesw_op { + MLX5_MPESW_OP_ENABLE, + MLX5_MPESW_OP_DISABLE, +}; + +struct mlx5_mpesw_work_st { + struct work_struct work; + struct mlx5_lag *lag; + enum mpesw_op op; + struct completion comp; + int result; +}; + +int mlx5_lag_mpesw_do_mirred(struct mlx5_core_dev *mdev, + struct net_device *out_dev, + struct netlink_ext_ack *extack); bool mlx5_lag_mpesw_is_activated(struct mlx5_core_dev *dev); +void mlx5_lag_del_mpesw_rule(struct mlx5_core_dev *dev); +int mlx5_lag_add_mpesw_rule(struct mlx5_core_dev *dev); #if IS_ENABLED(CONFIG_MLX5_ESWITCH) void mlx5_lag_mpesw_init(struct mlx5_lag *ldev); void mlx5_lag_mpesw_cleanup(struct mlx5_lag *ldev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 75510a12ab02..4c9a40211059 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -362,7 +362,7 @@ static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta) return mlx5_ptp_adjtime(ptp, delta); } -static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) +static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm) { u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {}; @@ -370,7 +370,15 @@ static int mlx5_ptp_adjfreq_real_time(struct mlx5_core_dev *mdev, s32 freq) return 0; MLX5_SET(mtutc_reg, in, operation, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC); - MLX5_SET(mtutc_reg, in, freq_adjustment, freq); + + if (MLX5_CAP_MCAM_FEATURE(mdev, mtutc_freq_adj_units)) { + MLX5_SET(mtutc_reg, in, freq_adj_units, + MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM); + MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm); + } else { + MLX5_SET(mtutc_reg, in, freq_adj_units, MLX5_MTUTC_FREQ_ADJ_UNITS_PPB); + MLX5_SET(mtutc_reg, in, freq_adjustment, scaled_ppm_to_ppb(scaled_ppm)); + } return mlx5_set_mtutc(mdev, in, sizeof(in)); } @@ -385,7 +393,8 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) int err; mdev = container_of(clock, struct mlx5_core_dev, clock); - err = mlx5_ptp_adjfreq_real_time(mdev, scaled_ppm_to_ppb(scaled_ppm)); + + err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h index 55bd7c4c021e..ccf12f7db6f0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h @@ -84,11 +84,6 @@ static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) return devlink_net(priv_to_devlink(dev)); } -static inline void mlx5_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev) -{ - mdev->mlx5e_res.uplink_netdev = netdev; -} - static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev) { return mdev->mlx5e_res.uplink_netdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 9441588ac524..26e1057845fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -336,6 +336,24 @@ static u16 to_fw_pkey_sz(struct mlx5_core_dev *dev, u32 size) } } +void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *dev, struct net_device *netdev) +{ + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + dev->mlx5e_res.uplink_netdev = netdev; + mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + netdev); + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); +} + +void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *dev) +{ + mutex_lock(&dev->mlx5e_res.uplink_netdev_lock); + mlx5_blocking_notifier_call_chain(dev, MLX5_DRIVER_EVENT_UPLINK_NETDEV, + dev->mlx5e_res.uplink_netdev); + mutex_unlock(&dev->mlx5e_res.uplink_netdev_lock); +} +EXPORT_SYMBOL(mlx5_core_uplink_netdev_event_replay); + static int mlx5_core_get_caps_mode(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type, enum mlx5_cap_mode cap_mode) @@ -1609,6 +1627,7 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) lockdep_register_key(&dev->lock_key); mutex_init(&dev->intf_state_mutex); lockdep_set_class(&dev->intf_state_mutex, &dev->lock_key); + mutex_init(&dev->mlx5e_res.uplink_netdev_lock); mutex_init(&priv->bfregs.reg_head.lock); mutex_init(&priv->bfregs.wc_head.lock); @@ -1697,6 +1716,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mutex_destroy(&priv->alloc_mutex); mutex_destroy(&priv->bfregs.wc_head.lock); mutex_destroy(&priv->bfregs.reg_head.lock); + mutex_destroy(&dev->mlx5e_res.uplink_netdev_lock); mutex_destroy(&dev->intf_state_mutex); lockdep_unregister_key(&dev->lock_key); } @@ -2111,7 +2131,7 @@ static int __init mlx5_init(void) mlx5_core_verify_params(); mlx5_register_debugfs(); - err = pci_register_driver(&mlx5_core_driver); + err = mlx5e_init(); if (err) goto err_debug; @@ -2119,16 +2139,16 @@ static int __init mlx5_init(void) if (err) goto err_sf; - err = mlx5e_init(); + err = pci_register_driver(&mlx5_core_driver); if (err) - goto err_en; + goto err_pci; return 0; -err_en: +err_pci: mlx5_sf_driver_unregister(); err_sf: - pci_unregister_driver(&mlx5_core_driver); + mlx5e_cleanup(); err_debug: mlx5_unregister_debugfs(); return err; @@ -2136,9 +2156,9 @@ err_debug: static void __exit mlx5_cleanup(void) { - mlx5e_cleanup(); - mlx5_sf_driver_unregister(); pci_unregister_driver(&mlx5_core_driver); + mlx5_sf_driver_unregister(); + mlx5e_cleanup(); mlx5_unregister_debugfs(); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 60596357bfc7..64d4e7125e9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -74,6 +74,14 @@ static u32 get_function(u16 func_id, bool ec_function) return (u32)func_id | (ec_function << 16); } +static u16 func_id_to_type(struct mlx5_core_dev *dev, u16 func_id, bool ec_function) +{ + if (!func_id) + return mlx5_core_is_ecpf(dev) && !ec_function ? MLX5_HOST_PF : MLX5_PF; + + return func_id <= mlx5_core_max_vfs(dev) ? MLX5_VF : MLX5_SF; +} + static struct rb_root *page_root_per_function(struct mlx5_core_dev *dev, u32 function) { struct rb_root *root; @@ -211,7 +219,8 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr, u32 function) n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask)); if (n >= MLX5_NUM_4K_IN_PAGE) { - mlx5_core_warn(dev, "alloc 4k bug\n"); + mlx5_core_warn(dev, "alloc 4k bug: fw page = 0x%llx, n = %u, bitmask: %lu, max num of 4K pages: %d\n", + fp->addr, n, fp->bitmask, MLX5_NUM_4K_IN_PAGE); return -ENOENT; } clear_bit(n, &fp->bitmask); @@ -332,6 +341,7 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); int notify_fail = event; + u16 func_type; u64 addr; int err; u32 *in; @@ -383,11 +393,9 @@ retry: goto out_dropped; } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] += npages; dev->priv.fw_pages += npages; - if (func_id) - dev->priv.vfs_pages += npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages += npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", npages, ec_function, func_id, err); @@ -414,6 +422,7 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, struct rb_root *root; struct rb_node *p; int npages = 0; + u16 func_type; root = xa_load(&dev->priv.page_root_xa, function); if (WARN_ON_ONCE(!root)) @@ -428,11 +437,9 @@ static void release_all_pages(struct mlx5_core_dev *dev, u16 func_id, free_fwp(dev, fwp, fwp->free_count); } + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= npages; dev->priv.fw_pages -= npages; - if (func_id) - dev->priv.vfs_pages -= npages; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= npages; mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x\n", npages, ec_function, func_id); @@ -498,6 +505,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {}; int num_claimed; + u16 func_type; u32 *out; int err; int i; @@ -549,11 +557,9 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, if (nclaimed) *nclaimed = num_claimed; + func_type = func_id_to_type(dev, func_id, ec_function); + dev->priv.page_counters[func_type] -= num_claimed; dev->priv.fw_pages -= num_claimed; - if (func_id) - dev->priv.vfs_pages -= num_claimed; - else if (mlx5_core_is_ecpf(dev) && !ec_function) - dev->priv.host_pf_pages -= num_claimed; out_free: kvfree(out); @@ -706,12 +712,12 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.fw_pages, "FW pages counter is %d after reclaiming all pages\n", dev->priv.fw_pages); - WARN(dev->priv.vfs_pages, + WARN(dev->priv.page_counters[MLX5_VF], "VFs FW pages counter is %d after reclaiming all pages\n", - dev->priv.vfs_pages); - WARN(dev->priv.host_pf_pages, + dev->priv.page_counters[MLX5_VF]); + WARN(dev->priv.page_counters[MLX5_HOST_PF], "External host PF FW pages counter is %d after reclaiming all pages\n", - dev->priv.host_pf_pages); + dev->priv.page_counters[MLX5_HOST_PF]); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index c0e6c487c63c..3008e9ce2bbf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); - if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index b851141e03de..042ca0349124 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -1138,12 +1138,14 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, rule->flow_source)) return 0; + mlx5dr_domain_nic_lock(nic_dmn); + ret = mlx5dr_matcher_select_builders(matcher, nic_matcher, dr_rule_get_ipv(¶m->outer), dr_rule_get_ipv(¶m->inner)); if (ret) - return ret; + goto err_unlock; hw_ste_arr_is_opt = nic_matcher->num_of_builders <= DR_RULE_MAX_STES_OPTIMIZED; if (likely(hw_ste_arr_is_opt)) { @@ -1152,12 +1154,12 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, hw_ste_arr = kzalloc((nic_matcher->num_of_builders + DR_ACTION_MAX_STES) * DR_STE_SIZE, GFP_KERNEL); - if (!hw_ste_arr) - return -ENOMEM; + if (!hw_ste_arr) { + ret = -ENOMEM; + goto err_unlock; + } } - mlx5dr_domain_nic_lock(nic_dmn); - ret = mlx5dr_matcher_add_to_tbl_nic(dmn, nic_matcher); if (ret) goto free_hw_ste; @@ -1223,7 +1225,10 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - goto out; + if (unlikely(!hw_ste_arr_is_opt)) + kfree(hw_ste_arr); + + return 0; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,12 +1243,12 @@ remove_from_nic_tbl: mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher); free_hw_ste: - mlx5dr_domain_nic_unlock(nic_dmn); - -out: - if (unlikely(!hw_ste_arr_is_opt)) + if (!hw_ste_arr_is_opt) kfree(hw_ste_arr); +err_unlock: + mlx5dr_domain_nic_unlock(nic_dmn); + return ret; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 42422a106433..22db0bb15c45 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1750,29 +1750,12 @@ static const struct devlink_ops mlxsw_devlink_ops = { static int mlxsw_core_params_register(struct mlxsw_core *mlxsw_core) { - int err; - - err = mlxsw_core_fw_params_register(mlxsw_core); - if (err) - return err; - - if (mlxsw_core->driver->params_register) { - err = mlxsw_core->driver->params_register(mlxsw_core); - if (err) - goto err_params_register; - } - return 0; - -err_params_register: - mlxsw_core_fw_params_unregister(mlxsw_core); - return err; + return mlxsw_core_fw_params_register(mlxsw_core); } static void mlxsw_core_params_unregister(struct mlxsw_core *mlxsw_core) { mlxsw_core_fw_params_unregister(mlxsw_core); - if (mlxsw_core->driver->params_register) - mlxsw_core->driver->params_unregister(mlxsw_core); } struct mlxsw_core_health_event { @@ -2201,6 +2184,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_devlink_alloc; } devl_lock(devlink); + devl_register(devlink); } mlxsw_core = devlink_priv(devlink); @@ -2284,10 +2268,8 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_driver_init; } - if (!reload) { + if (!reload) devl_unlock(devlink); - devlink_register(devlink); - } return 0; err_driver_init: @@ -2319,6 +2301,7 @@ err_register_resources: err_bus_init: mlxsw_core_irq_event_handler_fini(mlxsw_core); if (!reload) { + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } @@ -2357,10 +2340,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (!reload) { - devlink_unregister(devlink); + if (!reload) devl_lock(devlink); - } if (devlink_is_reload_failed(devlink)) { if (!reload) @@ -2389,6 +2370,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, mlxsw_core->bus->fini(mlxsw_core->bus_priv); mlxsw_core_irq_event_handler_fini(mlxsw_core); if (!reload) { + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } @@ -2398,6 +2380,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, reload_fail_deinit: mlxsw_core_params_unregister(mlxsw_core); devl_resources_unregister(devlink); + devl_unregister(devlink); devl_unlock(devlink); devlink_free(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index a77cb0be7108..e5474d3e34db 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -421,8 +421,6 @@ struct mlxsw_driver { const struct mlxsw_config_profile *profile, u64 *p_single_size, u64 *p_double_size, u64 *p_linear_size); - int (*params_register)(struct mlxsw_core *mlxsw_core); - void (*params_unregister)(struct mlxsw_core *mlxsw_core); /* Notify a driver that a timestamped packet was transmitted. Driver * is responsible for freeing the passed-in SKB. diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index b0bdb9640ebf..a8f94b7544ee 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3861,62 +3861,6 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core, return 0; } -static int -mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - - ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp); - return 0; -} - -static int -mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id, - struct devlink_param_gset_ctx *ctx) -{ - struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); - - return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32); -} - -static const struct devlink_param mlxsw_sp2_devlink_params[] = { - DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, - "acl_region_rehash_interval", - DEVLINK_PARAM_TYPE_U32, - BIT(DEVLINK_PARAM_CMODE_RUNTIME), - mlxsw_sp_params_acl_region_rehash_intrvl_get, - mlxsw_sp_params_acl_region_rehash_intrvl_set, - NULL), -}; - -static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core) -{ - struct devlink *devlink = priv_to_devlink(mlxsw_core); - union devlink_param_value value; - int err; - - err = devl_params_register(devlink, mlxsw_sp2_devlink_params, - ARRAY_SIZE(mlxsw_sp2_devlink_params)); - if (err) - return err; - - value.vu32 = 0; - devl_param_driverinit_value_set(devlink, - MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, - value); - return 0; -} - -static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core) -{ - devl_params_unregister(priv_to_devlink(mlxsw_core), - mlxsw_sp2_devlink_params, - ARRAY_SIZE(mlxsw_sp2_devlink_params)); -} - static void mlxsw_sp_ptp_transmitted(struct mlxsw_core *mlxsw_core, struct sk_buff *skb, u16 local_port) { @@ -3994,8 +3938,6 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, @@ -4033,8 +3975,6 @@ static struct mlxsw_driver mlxsw_sp3_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, @@ -4070,8 +4010,6 @@ static struct mlxsw_driver mlxsw_sp4_driver = { .trap_policer_counter_get = mlxsw_sp_trap_policer_counter_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp2_params_register, - .params_unregister = mlxsw_sp2_params_unregister, .ptp_transmitted = mlxsw_sp_ptp_transmitted, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp4_config_profile, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index bbc73324451d..4c22f8004514 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -973,6 +973,7 @@ enum mlxsw_sp_acl_profile { }; struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl); +struct mlxsw_sp_acl_tcam *mlxsw_sp_acl_to_tcam(struct mlxsw_sp_acl *acl); int mlxsw_sp_acl_ruleset_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_flow_block *block, @@ -1096,8 +1097,6 @@ mlxsw_sp_acl_act_cookie_lookup(struct mlxsw_sp *mlxsw_sp, u32 cookie_index) int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); -u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); -int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val); struct mlxsw_sp_acl_mangle_action; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 6c5af018546f..0423ac262d89 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -40,6 +40,11 @@ struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl) return acl->afk; } +struct mlxsw_sp_acl_tcam *mlxsw_sp_acl_to_tcam(struct mlxsw_sp_acl *acl) +{ + return &acl->tcam; +} + struct mlxsw_sp_acl_ruleset_ht_key { struct mlxsw_sp_flow_block *block; u32 chain_index; @@ -1099,22 +1104,6 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) kfree(acl); } -u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp) -{ - struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - - return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp, - &acl->tcam); -} - -int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val) -{ - struct mlxsw_sp_acl *acl = mlxsw_sp->acl; - - return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp, - &acl->tcam, val); -} - struct mlxsw_sp_acl_rulei_ops mlxsw_sp1_acl_rulei_ops = { .act_mangle_field = mlxsw_sp1_acl_rulei_act_mangle_field, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 3b9ba8fa247a..d50786b0a6ce 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -9,6 +9,7 @@ #include <linux/rhashtable.h> #include <linux/netdevice.h> #include <linux/mutex.h> +#include <net/devlink.h> #include <trace/events/mlxsw.h> #include "reg.h" @@ -29,67 +30,6 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp) #define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */ #define MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS 100 /* number of entries */ -int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - u64 max_tcam_regions; - u64 max_regions; - u64 max_groups; - int err; - - mutex_init(&tcam->lock); - tcam->vregion_rehash_intrvl = - MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; - INIT_LIST_HEAD(&tcam->vregion_list); - - max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, - ACL_MAX_TCAM_REGIONS); - max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); - - /* Use 1:1 mapping between ACL region and TCAM region */ - if (max_tcam_regions < max_regions) - max_regions = max_tcam_regions; - - tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); - if (!tcam->used_regions) - return -ENOMEM; - tcam->max_regions = max_regions; - - max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); - tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); - if (!tcam->used_groups) { - err = -ENOMEM; - goto err_alloc_used_groups; - } - tcam->max_groups = max_groups; - tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, - ACL_MAX_GROUP_SIZE); - - err = ops->init(mlxsw_sp, tcam->priv, tcam); - if (err) - goto err_tcam_init; - - return 0; - -err_tcam_init: - bitmap_free(tcam->used_groups); -err_alloc_used_groups: - bitmap_free(tcam->used_regions); - return err; -} - -void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - - mutex_destroy(&tcam->lock); - ops->fini(mlxsw_sp, tcam->priv); - bitmap_free(tcam->used_groups); - bitmap_free(tcam->used_regions); -} - int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority) @@ -893,41 +833,6 @@ mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, kfree(vregion); } -u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - u32 vregion_rehash_intrvl; - - if (WARN_ON(!ops->region_rehash_hints_get)) - return 0; - vregion_rehash_intrvl = tcam->vregion_rehash_intrvl; - return vregion_rehash_intrvl; -} - -int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam, - u32 val) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_vregion *vregion; - - if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) - return -EINVAL; - if (WARN_ON(!ops->region_rehash_hints_get)) - return -EOPNOTSUPP; - tcam->vregion_rehash_intrvl = val; - mutex_lock(&tcam->lock); - list_for_each_entry(vregion, &tcam->vregion_list, tlist) { - if (val) - mlxsw_core_schedule_dw(&vregion->rehash.dw, 0); - else - cancel_delayed_work_sync(&vregion->rehash.dw); - } - mutex_unlock(&tcam->lock); - return 0; -} - static struct mlxsw_sp_acl_tcam_vregion * mlxsw_sp_acl_tcam_vregion_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_vgroup *vgroup, @@ -1542,6 +1447,153 @@ mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_tcam_vregion_rehash_end(mlxsw_sp, vregion, ctx); } +static int +mlxsw_sp_acl_tcam_region_rehash_intrvl_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp_acl_tcam *tcam; + struct mlxsw_sp *mlxsw_sp; + + mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); + ctx->val.vu32 = tcam->vregion_rehash_intrvl; + + return 0; +} + +static int +mlxsw_sp_acl_tcam_region_rehash_intrvl_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp_acl_tcam_vregion *vregion; + struct mlxsw_sp_acl_tcam *tcam; + struct mlxsw_sp *mlxsw_sp; + u32 val = ctx->val.vu32; + + if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) + return -EINVAL; + + mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + tcam = mlxsw_sp_acl_to_tcam(mlxsw_sp->acl); + tcam->vregion_rehash_intrvl = val; + mutex_lock(&tcam->lock); + list_for_each_entry(vregion, &tcam->vregion_list, tlist) { + if (val) + mlxsw_core_schedule_dw(&vregion->rehash.dw, 0); + else + cancel_delayed_work_sync(&vregion->rehash.dw); + } + mutex_unlock(&tcam->lock); + return 0; +} + +static const struct devlink_param mlxsw_sp_acl_tcam_rehash_params[] = { + DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + "acl_region_rehash_interval", + DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlxsw_sp_acl_tcam_region_rehash_intrvl_get, + mlxsw_sp_acl_tcam_region_rehash_intrvl_set, + NULL), +}; + +static int mlxsw_sp_acl_tcam_rehash_params_register(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + if (!mlxsw_sp->acl_tcam_ops->region_rehash_hints_get) + return 0; + + return devl_params_register(devlink, mlxsw_sp_acl_tcam_rehash_params, + ARRAY_SIZE(mlxsw_sp_acl_tcam_rehash_params)); +} + +static void +mlxsw_sp_acl_tcam_rehash_params_unregister(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + if (!mlxsw_sp->acl_tcam_ops->region_rehash_hints_get) + return; + + devl_params_unregister(devlink, mlxsw_sp_acl_tcam_rehash_params, + ARRAY_SIZE(mlxsw_sp_acl_tcam_rehash_params)); +} + +int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + u64 max_tcam_regions; + u64 max_regions; + u64 max_groups; + int err; + + mutex_init(&tcam->lock); + tcam->vregion_rehash_intrvl = + MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; + INIT_LIST_HEAD(&tcam->vregion_list); + + err = mlxsw_sp_acl_tcam_rehash_params_register(mlxsw_sp); + if (err) + goto err_rehash_params_register; + + max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_TCAM_REGIONS); + max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); + + /* Use 1:1 mapping between ACL region and TCAM region */ + if (max_tcam_regions < max_regions) + max_regions = max_tcam_regions; + + tcam->used_regions = bitmap_zalloc(max_regions, GFP_KERNEL); + if (!tcam->used_regions) { + err = -ENOMEM; + goto err_alloc_used_regions; + } + tcam->max_regions = max_regions; + + max_groups = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_GROUPS); + tcam->used_groups = bitmap_zalloc(max_groups, GFP_KERNEL); + if (!tcam->used_groups) { + err = -ENOMEM; + goto err_alloc_used_groups; + } + tcam->max_groups = max_groups; + tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, + ACL_MAX_GROUP_SIZE); + + err = ops->init(mlxsw_sp, tcam->priv, tcam); + if (err) + goto err_tcam_init; + + return 0; + +err_tcam_init: + bitmap_free(tcam->used_groups); +err_alloc_used_groups: + bitmap_free(tcam->used_regions); +err_alloc_used_regions: + mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); +err_rehash_params_register: + mutex_destroy(&tcam->lock); + return err; +} + +void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + ops->fini(mlxsw_sp, tcam->priv); + bitmap_free(tcam->used_groups); + bitmap_free(tcam->used_regions); + mlxsw_sp_acl_tcam_rehash_params_unregister(mlxsw_sp); + mutex_destroy(&tcam->lock); +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC_32_47, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index edbbc89e7a71..462bf448497d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -29,11 +29,6 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); -u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam); -int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam *tcam, - u32 val); int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c index 80625ba0b354..cf0cc7562d04 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0+ #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "lan966x_main.h" diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c index 88c655d6318f..bd10a7189741 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_tc_flower.c @@ -3,53 +3,135 @@ #include "lan966x_main.h" #include "vcap_api.h" #include "vcap_api_client.h" +#include "vcap_tc.h" -struct lan966x_tc_flower_parse_usage { - struct flow_cls_offload *f; - struct flow_rule *frule; - struct vcap_rule *vrule; - unsigned int used_keys; - u16 l3_proto; -}; +static bool lan966x_tc_is_known_etype(u16 etype) +{ + switch (etype) { + case ETH_P_ALL: + case ETH_P_ARP: + case ETH_P_IP: + case ETH_P_IPV6: + return true; + } + + return false; +} -static int lan966x_tc_flower_handler_ethaddr_usage(struct lan966x_tc_flower_parse_usage *st) +static int +lan966x_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) { - enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; - enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; - struct flow_match_eth_addrs match; - struct vcap_u48_key smac, dmac; + struct flow_match_control match; int err = 0; - flow_rule_match_eth_addrs(st->frule, &match); - - if (!is_zero_ether_addr(match.mask->src)) { - vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); - vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + flow_rule_match_control(st->frule, &match); + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + if (match.key->flags & FLOW_DIS_IS_FRAGMENT) + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAGMENT, + VCAP_BIT_1); + else + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAGMENT, + VCAP_BIT_0); if (err) goto out; } - if (!is_zero_ether_addr(match.mask->dst)) { - vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); - vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (match.key->flags & FLOW_DIS_FIRST_FRAG) + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAG_OFS_GT0, + VCAP_BIT_0); + else + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_L3_FRAG_OFS_GT0, + VCAP_BIT_1); if (err) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); return err; out: - NL_SET_ERR_MSG_MOD(st->f->common.extack, "eth_addr parse error"); + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); return err; } static int -(*lan966x_tc_flower_handlers_usage[])(struct lan966x_tc_flower_parse_usage *st) = { - [FLOW_DISSECTOR_KEY_ETH_ADDRS] = lan966x_tc_flower_handler_ethaddr_usage, +lan966x_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_basic match; + int err = 0; + + flow_rule_match_basic(st->frule, &match); + if (match.mask->n_proto) { + st->l3_proto = be16_to_cpu(match.key->n_proto); + if (!lan966x_tc_is_known_etype(st->l3_proto)) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ETYPE, + st->l3_proto, ~0); + if (err) + goto out; + } else if (st->l3_proto == ETH_P_IP) { + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_IP4_IS, + VCAP_BIT_1); + if (err) + goto out; + } + } + if (match.mask->ip_proto) { + st->l4_proto = match.key->ip_proto; + + if (st->l4_proto == IPPROTO_TCP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_1); + if (err) + goto out; + } else if (st->l4_proto == IPPROTO_UDP) { + err = vcap_rule_add_key_bit(st->vrule, + VCAP_KF_TCP_IS, + VCAP_BIT_0); + if (err) + goto out; + } else { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP_PROTO, + st->l4_proto, ~0); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_proto parse error"); + return err; +} + +static int +lan966x_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st) +{ + return vcap_tc_flower_handler_vlan_usage(st, + VCAP_KF_8021Q_VID_CLS, + VCAP_KF_8021Q_PCP_CLS); +} + +static int +(*lan966x_tc_flower_handlers_usage[])(struct vcap_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = vcap_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = vcap_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = vcap_tc_flower_handler_ipv6_usage, + [FLOW_DISSECTOR_KEY_CONTROL] = lan966x_tc_flower_handler_control_usage, + [FLOW_DISSECTOR_KEY_PORTS] = vcap_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_BASIC] = lan966x_tc_flower_handler_basic_usage, + [FLOW_DISSECTOR_KEY_VLAN] = lan966x_tc_flower_handler_vlan_usage, + [FLOW_DISSECTOR_KEY_TCP] = vcap_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_ARP] = vcap_tc_flower_handler_arp_usage, + [FLOW_DISSECTOR_KEY_IP] = vcap_tc_flower_handler_ip_usage, }; static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, @@ -57,8 +139,8 @@ static int lan966x_tc_flower_use_dissectors(struct flow_cls_offload *f, struct vcap_rule *vrule, u16 *l3_proto) { - struct lan966x_tc_flower_parse_usage state = { - .f = f, + struct vcap_tc_flower_parse_usage state = { + .fco = f, .vrule = vrule, .l3_proto = ETH_P_ALL, }; @@ -234,6 +316,24 @@ static int lan966x_tc_flower_del(struct lan966x_port *port, return err; } +static int lan966x_tc_flower_stats(struct lan966x_port *port, + struct flow_cls_offload *f, + struct vcap_admin *admin) +{ + struct vcap_counter count = {}; + int err; + + err = vcap_get_rule_count_by_cookie(port->lan966x->vcap_ctrl, + &count, f->cookie); + if (err) + return err; + + flow_stats_update(&f->stats, 0x0, count.value, 0, 0, + FLOW_ACTION_HW_STATS_IMMEDIATE); + + return err; +} + int lan966x_tc_flower(struct lan966x_port *port, struct flow_cls_offload *f, bool ingress) @@ -252,6 +352,8 @@ int lan966x_tc_flower(struct lan966x_port *port, return lan966x_tc_flower_add(port, f, admin, ingress); case FLOW_CLS_DESTROY: return lan966x_tc_flower_del(port, f, admin); + case FLOW_CLS_STATS: + return lan966x_tc_flower_stats(port, f, admin); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/microchip/sparx5/Makefile b/drivers/net/ethernet/microchip/sparx5/Makefile index d0ed7090aa54..1cb1cc3f1a85 100644 --- a/drivers/net/ethernet/microchip/sparx5/Makefile +++ b/drivers/net/ethernet/microchip/sparx5/Makefile @@ -9,7 +9,8 @@ sparx5-switch-y := sparx5_main.o sparx5_packet.o \ sparx5_netdev.o sparx5_phylink.o sparx5_port.o sparx5_mactable.o sparx5_vlan.o \ sparx5_switchdev.o sparx5_calendar.o sparx5_ethtool.o sparx5_fdma.o \ sparx5_ptp.o sparx5_pgid.o sparx5_tc.o sparx5_qos.o \ - sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o sparx5_tc_matchall.o + sparx5_vcap_impl.o sparx5_vcap_ag_api.o sparx5_tc_flower.o \ + sparx5_tc_matchall.o sparx5_pool.o sparx5_sdlb.o sparx5_police.o sparx5_psfp.o sparx5-switch-$(CONFIG_SPARX5_DCB) += sparx5_dcb.o sparx5-switch-$(CONFIG_DEBUG_FS) += sparx5_vcap_debugfs.o diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 300fb7247bb3..c213a4414e65 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -205,6 +205,7 @@ static const struct sparx5_main_io_resource sparx5_main_iomap[] = { { TARGET_EACL, 0x112c0000, 2 }, /* 0x6112c0000 */ { TARGET_ANA_CL, 0x11400000, 2 }, /* 0x611400000 */ { TARGET_ANA_L3, 0x11480000, 2 }, /* 0x611480000 */ + { TARGET_ANA_AC_SDLB, 0x11500000, 2 }, /* 0x611500000 */ { TARGET_HSCH, 0x11580000, 2 }, /* 0x611580000 */ { TARGET_REW, 0x11600000, 2 }, /* 0x611600000 */ { TARGET_ANA_L2, 0x11800000, 2 }, /* 0x611800000 */ @@ -501,8 +502,8 @@ static int sparx5_init_coreclock(struct sparx5 *sparx5) clk_period = sparx5_clk_period(freq); - spx5_rmw(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(clk_period / 100), - HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, + spx5_rmw(HSCH_SYS_CLK_PER_100PS_SET(clk_period / 100), + HSCH_SYS_CLK_PER_100PS, sparx5, HSCH_SYS_CLK_PER); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 4a574cdcb584..72e7928912eb 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -396,6 +396,7 @@ int sparx5_ptp_txtstamp_request(struct sparx5_port *port, void sparx5_ptp_txtstamp_release(struct sparx5_port *port, struct sk_buff *skb); irqreturn_t sparx5_ptp_irq_handler(int irq, void *args); +int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); /* sparx5_vcap_impl.c */ int sparx5_vcap_init(struct sparx5 *sparx5); @@ -413,6 +414,129 @@ int sparx5_pgid_alloc_glag(struct sparx5 *spx5, u16 *idx); int sparx5_pgid_alloc_mcast(struct sparx5 *spx5, u16 *idx); int sparx5_pgid_free(struct sparx5 *spx5, u16 idx); +/* sparx5_pool.c */ +struct sparx5_pool_entry { + u16 ref_cnt; + u32 idx; /* tc index */ +}; + +u32 sparx5_pool_idx_to_id(u32 idx); +int sparx5_pool_put(struct sparx5_pool_entry *pool, int size, u32 id); +int sparx5_pool_get(struct sparx5_pool_entry *pool, int size, u32 *id); +int sparx5_pool_get_with_idx(struct sparx5_pool_entry *pool, int size, u32 idx, + u32 *id); + +/* sparx5_sdlb.c */ +#define SPX5_SDLB_PUP_TOKEN_DISABLE 0x1FFF +#define SPX5_SDLB_PUP_TOKEN_MAX (SPX5_SDLB_PUP_TOKEN_DISABLE - 1) +#define SPX5_SDLB_GROUP_RATE_MAX 25000000000ULL +#define SPX5_SDLB_2CYCLES_TYPE2_THRES_OFFSET 13 +#define SPX5_SDLB_CNT 4096 +#define SPX5_SDLB_GROUP_CNT 10 +#define SPX5_CLK_PER_100PS_DEFAULT 16 + +struct sparx5_sdlb_group { + u64 max_rate; + u32 min_burst; + u32 frame_size; + u32 pup_interval; + u32 nsets; +}; + +extern struct sparx5_sdlb_group sdlb_groups[SPX5_SDLB_GROUP_CNT]; +int sparx5_sdlb_pup_token_get(struct sparx5 *sparx5, u32 pup_interval, + u64 rate); + +int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5); +int sparx5_sdlb_group_get_by_rate(struct sparx5 *sparx5, u32 rate, u32 burst); +int sparx5_sdlb_group_get_by_index(struct sparx5 *sparx5, u32 idx, u32 *group); + +int sparx5_sdlb_group_add(struct sparx5 *sparx5, u32 group, u32 idx); +int sparx5_sdlb_group_del(struct sparx5 *sparx5, u32 group, u32 idx); + +void sparx5_sdlb_group_init(struct sparx5 *sparx5, u64 max_rate, u32 min_burst, + u32 frame_size, u32 idx); + +/* sparx5_police.c */ +enum { + /* More policer types will be added later */ + SPX5_POL_SERVICE +}; + +struct sparx5_policer { + u32 type; + u32 idx; + u64 rate; + u32 burst; + u32 group; + u8 event_mask; +}; + +int sparx5_policer_conf_set(struct sparx5 *sparx5, struct sparx5_policer *pol); + +/* sparx5_psfp.c */ +#define SPX5_PSFP_GCE_CNT 4 +#define SPX5_PSFP_SG_CNT 1024 +#define SPX5_PSFP_SG_MIN_CYCLE_TIME_NS (1 * NSEC_PER_USEC) +#define SPX5_PSFP_SG_MAX_CYCLE_TIME_NS ((1 * NSEC_PER_SEC) - 1) +#define SPX5_PSFP_SG_MAX_IPV (SPX5_PRIOS - 1) +#define SPX5_PSFP_SG_OPEN (SPX5_PSFP_SG_CNT - 1) +#define SPX5_PSFP_SG_CYCLE_TIME_DEFAULT 1000000 +#define SPX5_PSFP_SF_MAX_SDU 16383 + +struct sparx5_psfp_fm { + struct sparx5_policer pol; +}; + +struct sparx5_psfp_gce { + bool gate_state; /* StreamGateState */ + u32 interval; /* TimeInterval */ + u32 ipv; /* InternalPriorityValue */ + u32 maxoctets; /* IntervalOctetMax */ +}; + +struct sparx5_psfp_sg { + bool gate_state; /* PSFPAdminGateStates */ + bool gate_enabled; /* PSFPGateEnabled */ + u32 ipv; /* PSFPAdminIPV */ + struct timespec64 basetime; /* PSFPAdminBaseTime */ + u32 cycletime; /* PSFPAdminCycleTime */ + u32 cycletimeext; /* PSFPAdminCycleTimeExtension */ + u32 num_entries; /* PSFPAdminControlListLength */ + struct sparx5_psfp_gce gce[SPX5_PSFP_GCE_CNT]; +}; + +struct sparx5_psfp_sf { + bool sblock_osize_ena; + bool sblock_osize; + u32 max_sdu; + u32 sgid; /* Gate id */ + u32 fmid; /* Flow meter id */ +}; + +int sparx5_psfp_fm_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_fm *fm, u32 *id); +int sparx5_psfp_fm_del(struct sparx5 *sparx5, u32 id); + +int sparx5_psfp_sg_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_sg *sg, u32 *id); +int sparx5_psfp_sg_del(struct sparx5 *sparx5, u32 id); + +int sparx5_psfp_sf_add(struct sparx5 *sparx5, const struct sparx5_psfp_sf *sf, + u32 *id); +int sparx5_psfp_sf_del(struct sparx5 *sparx5, u32 id); + +u32 sparx5_psfp_isdx_get_sf(struct sparx5 *sparx5, u32 isdx); +u32 sparx5_psfp_isdx_get_fm(struct sparx5 *sparx5, u32 isdx); +u32 sparx5_psfp_sf_get_sg(struct sparx5 *sparx5, u32 sfid); +void sparx5_isdx_conf_set(struct sparx5 *sparx5, u32 isdx, u32 sfid, u32 fmid); + +void sparx5_psfp_init(struct sparx5 *sparx5); + +/* sparx5_qos.c */ +void sparx5_new_base_time(struct sparx5 *sparx5, const u32 cycle_time, + const ktime_t org_base_time, ktime_t *new_base_time); + /* Clock period in picoseconds */ static inline u32 sparx5_clk_period(enum sparx5_core_clockfreq cclock) { diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h index 4813433b435c..bd73742939d3 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main_regs.h @@ -19,6 +19,7 @@ enum sparx5_target { TARGET_ANA_AC = 1, TARGET_ANA_ACL = 2, TARGET_ANA_AC_POL = 4, + TARGET_ANA_AC_SDLB = 5, TARGET_ANA_CL = 6, TARGET_ANA_L2 = 7, TARGET_ANA_L3 = 8, @@ -130,6 +131,254 @@ enum sparx5_target { #define ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA_GET(x)\ FIELD_GET(ANA_AC_PGID_MISC_CFG_PGID_CPU_COPY_ENA, x) +/* ANA_AC:TSN_SF:TSN_SF */ +#define ANA_AC_TSN_SF \ + __REG(TARGET_ANA_AC, 0, 1, 839136, 0, 1, 4, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY BIT(9) +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY, x) +#define ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_TSN_STREAM_BLOCK_OVERSIZE_STICKY, x) + +#define ANA_AC_TSN_SF_PORT_NUM GENMASK(8, 0) +#define ANA_AC_TSN_SF_PORT_NUM_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_PORT_NUM, x) +#define ANA_AC_TSN_SF_PORT_NUM_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_PORT_NUM, x) + +/* ANA_AC:TSN_SF_CFG:TSN_SF_CFG */ +#define ANA_AC_TSN_SF_CFG(g) \ + __REG(TARGET_ANA_AC, 0, 1, 839680, g, 1024, 4, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_CFG_TSN_SGID GENMASK(25, 16) +#define ANA_AC_TSN_SF_CFG_TSN_SGID_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_CFG_TSN_SGID, x) +#define ANA_AC_TSN_SF_CFG_TSN_SGID_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_CFG_TSN_SGID, x) + +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU GENMASK(15, 2) +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_CFG_TSN_MAX_SDU, x) +#define ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_CFG_TSN_MAX_SDU, x) + +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA BIT(1) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_SET(x) \ + FIELD_PREP(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, x) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_GET(x) \ + FIELD_GET(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, x) + +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE BIT(0) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_SET(x) \ + FIELD_PREP(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE, x) +#define ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_GET(x) \ + FIELD_GET(ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE, x) + +/* ANA_AC:TSN_SF_STATUS:TSN_SF_STATUS */ +#define ANA_AC_TSN_SF_STATUS \ + __REG(TARGET_ANA_AC, 0, 1, 839072, 0, 1, 16, 0, 0, 1, 4) + +#define ANA_AC_TSN_SF_STATUS_FRM_LEN GENMASK(25, 12) +#define ANA_AC_TSN_SF_STATUS_FRM_LEN_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_FRM_LEN, x) +#define ANA_AC_TSN_SF_STATUS_FRM_LEN_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_FRM_LEN, x) + +#define ANA_AC_TSN_SF_STATUS_DLB_DROP BIT(11) +#define ANA_AC_TSN_SF_STATUS_DLB_DROP_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_DLB_DROP, x) +#define ANA_AC_TSN_SF_STATUS_DLB_DROP_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_DLB_DROP, x) + +#define ANA_AC_TSN_SF_STATUS_TSN_SFID GENMASK(10, 1) +#define ANA_AC_TSN_SF_STATUS_TSN_SFID_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_TSN_SFID, x) +#define ANA_AC_TSN_SF_STATUS_TSN_SFID_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_TSN_SFID, x) + +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD BIT(0) +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD_SET(x)\ + FIELD_PREP(ANA_AC_TSN_SF_STATUS_TSTAMP_VLD, x) +#define ANA_AC_TSN_SF_STATUS_TSTAMP_VLD_GET(x)\ + FIELD_GET(ANA_AC_TSN_SF_STATUS_TSTAMP_VLD, x) + +/* ANA_AC:SG_ACCESS:SG_ACCESS_CTRL */ +#define ANA_AC_SG_ACCESS_CTRL \ + __REG(TARGET_ANA_AC, 0, 1, 839140, 0, 1, 12, 0, 0, 1, 4) + +#define ANA_AC_SG_ACCESS_CTRL_SGID GENMASK(9, 0) +#define ANA_AC_SG_ACCESS_CTRL_SGID_SET(x)\ + FIELD_PREP(ANA_AC_SG_ACCESS_CTRL_SGID, x) +#define ANA_AC_SG_ACCESS_CTRL_SGID_GET(x)\ + FIELD_GET(ANA_AC_SG_ACCESS_CTRL_SGID, x) + +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE BIT(28) +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_SET(x)\ + FIELD_PREP(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE, x) +#define ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_GET(x)\ + FIELD_GET(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE, x) + +/* ANA_AC:SG_ACCESS:SG_CYCLETIME_UPDATE_PERIOD */ +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD \ + __REG(TARGET_ANA_AC, 0, 1, 839140, 0, 1, 12, 8, 0, 1, 4) + +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS GENMASK(15, 0) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS_SET(x)\ + FIELD_PREP(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS, x) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS_GET(x)\ + FIELD_GET(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_CLKS, x) + +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA BIT(31) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA, x) +#define ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA, x) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_1 */ +#define ANA_AC_SG_CONFIG_REG_1 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 48, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_2 */ +#define ANA_AC_SG_CONFIG_REG_2 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 52, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_3 */ +#define ANA_AC_SG_CONFIG_REG_3 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 56, 0, 1, 4) + +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB GENMASK(15, 0) +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB, x) +#define ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB, x) + +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH GENMASK(18, 16) +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH, x) +#define ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH, x) + +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE BIT(20) +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, x) +#define ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, x) + +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS GENMASK(24, 21) +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INIT_IPS, x) +#define ANA_AC_SG_CONFIG_REG_3_INIT_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INIT_IPS, x) + +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE, x) +#define ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE, x) + +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA BIT(26) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA, x) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INVALID_RX_ENA, x) + +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX BIT(27) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_INVALID_RX, x) +#define ANA_AC_SG_CONFIG_REG_3_INVALID_RX_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_INVALID_RX, x) + +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA BIT(28) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA, x) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_ENA, x) + +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED BIT(29) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_SET(x)\ + FIELD_PREP(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED, x) +#define ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED_GET(x)\ + FIELD_GET(ANA_AC_SG_CONFIG_REG_3_OCTETS_EXCEEDED, x) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_4 */ +#define ANA_AC_SG_CONFIG_REG_4 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 60, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_CONFIG_REG_5 */ +#define ANA_AC_SG_CONFIG_REG_5 \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 64, 0, 1, 4) + +/* ANA_AC:SG_CONFIG:SG_GCL_GS_CONFIG */ +#define ANA_AC_SG_GCL_GS_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 0, r, 4, 4) + +#define ANA_AC_SG_GCL_GS_CONFIG_IPS GENMASK(3, 0) +#define ANA_AC_SG_GCL_GS_CONFIG_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_GCL_GS_CONFIG_IPS, x) +#define ANA_AC_SG_GCL_GS_CONFIG_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_GCL_GS_CONFIG_IPS, x) + +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE BIT(4) +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE, x) +#define ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE, x) + +/* ANA_AC:SG_CONFIG:SG_GCL_TI_CONFIG */ +#define ANA_AC_SG_GCL_TI_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 16, r, 4, 4) + +/* ANA_AC:SG_CONFIG:SG_GCL_OCT_CONFIG */ +#define ANA_AC_SG_GCL_OCT_CONFIG(r) \ + __REG(TARGET_ANA_AC, 0, 1, 851584, 0, 1, 128, 32, r, 4, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_1 */ +#define ANA_AC_SG_STATUS_REG_1 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 0, 0, 1, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_2 */ +#define ANA_AC_SG_STATUS_REG_2 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 4, 0, 1, 4) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_3 */ +#define ANA_AC_SG_STATUS_REG_3 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 8, 0, 1, 4) + +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB GENMASK(15, 0) +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB, x) +#define ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_CFG_CHG_TIME_SEC_MSB, x) + +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE BIT(16) +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_GATE_STATE, x) +#define ANA_AC_SG_STATUS_REG_3_GATE_STATE_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_GATE_STATE, x) + +#define ANA_AC_SG_STATUS_REG_3_IPS GENMASK(23, 20) +#define ANA_AC_SG_STATUS_REG_3_IPS_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_IPS, x) +#define ANA_AC_SG_STATUS_REG_3_IPS_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_IPS, x) + +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING BIT(24) +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING, x) +#define ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_CONFIG_PENDING, x) + +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX GENMASK(27, 25) +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX_SET(x)\ + FIELD_PREP(ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX, x) +#define ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX_GET(x)\ + FIELD_GET(ANA_AC_SG_STATUS_REG_3_GCL_OCTET_INDEX, x) + +/* ANA_AC:SG_STATUS:SG_STATUS_REG_4 */ +#define ANA_AC_SG_STATUS_REG_4 \ + __REG(TARGET_ANA_AC, 0, 1, 839088, 0, 1, 16, 12, 0, 1, 4) + /* ANA_AC:STAT_GLOBAL_CFG_PORT:STAT_GLOBAL_EVENT_MASK */ #define ANA_AC_PORT_SGE_CFG(r) __REG(TARGET_ANA_AC, 0, 1, 851552, 0, 1, 20, 0, r, 4, 4) @@ -568,6 +817,232 @@ enum sparx5_target { #define ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA_GET(x)\ FIELD_GET(ANA_AC_POL_SLB_DLB_CTRL_DLB_ADD_ENA, x) +/* ANA_AC_SDLB:LBGRP_TBL:XLB_START */ +#define ANA_AC_SDLB_XLB_START(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 0, 0, 1, 4) + +#define ANA_AC_SDLB_XLB_START_LBSET_START GENMASK(12, 0) +#define ANA_AC_SDLB_XLB_START_LBSET_START_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_START_LBSET_START, x) +#define ANA_AC_SDLB_XLB_START_LBSET_START_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_START_LBSET_START, x) + +/* ANA_AC_SDLB:LBGRP_TBL:PUP_INTERVAL */ +#define ANA_AC_SDLB_PUP_INTERVAL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 4, 0, 1, 4) + +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL GENMASK(19, 0) +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL, x) +#define ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL, x) + +/* ANA_AC_SDLB:LBGRP_TBL:PUP_CTRL */ +#define ANA_AC_SDLB_PUP_CTRL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 8, 0, 1, 4) + +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT GENMASK(18, 0) +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT, x) +#define ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_CTRL_PUP_LB_DT, x) + +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA BIT(24) +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_CTRL_PUP_ENA, x) +#define ANA_AC_SDLB_PUP_CTRL_PUP_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_CTRL_PUP_ENA, x) + +/* ANA_AC_SDLB:LBGRP_TBL:LBGRP_MISC */ +#define ANA_AC_SDLB_LBGRP_MISC(g)\ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 12, 0, 1, 4) + +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT GENMASK(12, 8) +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT, x) +#define ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT, x) + +/* ANA_AC_SDLB:LBGRP_TBL:FRM_RATE_TOKENS */ +#define ANA_AC_SDLB_FRM_RATE_TOKENS(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 16, 0, 1, 4) + +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS GENMASK(12, 0) +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS, x) +#define ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS, x) + +/* ANA_AC_SDLB:LBGRP_TBL:LBGRP_STATE_TBL */ +#define ANA_AC_SDLB_LBGRP_STATE_TBL(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 295468, g, 10, 24, 20, 0, 1, 4) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING BIT(0) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_ONGOING, x) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK BIT(1) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_WAIT_ACK, x) + +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT GENMASK(28, 16) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT, x) +#define ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_LBGRP_STATE_TBL_PUP_LBSET_NEXT, x) + +/* ANA_AC_SDLB:LBSET_TBL:PUP_TOKENS */ +#define ANA_AC_SDLB_PUP_TOKENS(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 0, r, 2, 4) + +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS GENMASK(12, 0) +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS, x) +#define ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS, x) + +/* ANA_AC_SDLB:LBSET_TBL:THRES */ +#define ANA_AC_SDLB_THRES(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 8, r, 2, 4) + +#define ANA_AC_SDLB_THRES_THRES GENMASK(9, 0) +#define ANA_AC_SDLB_THRES_THRES_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_THRES_THRES, x) +#define ANA_AC_SDLB_THRES_THRES_GET(x)\ + FIELD_GET(ANA_AC_SDLB_THRES_THRES, x) + +#define ANA_AC_SDLB_THRES_THRES_HYS GENMASK(25, 16) +#define ANA_AC_SDLB_THRES_THRES_HYS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_THRES_THRES_HYS, x) +#define ANA_AC_SDLB_THRES_THRES_HYS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_THRES_THRES_HYS, x) + +/* ANA_AC_SDLB:LBSET_TBL:XLB_NEXT */ +#define ANA_AC_SDLB_XLB_NEXT(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 16, 0, 1, 4) + +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT GENMASK(12, 0) +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT, x) +#define ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT, x) + +#define ANA_AC_SDLB_XLB_NEXT_LBGRP GENMASK(27, 24) +#define ANA_AC_SDLB_XLB_NEXT_LBGRP_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_XLB_NEXT_LBGRP, x) +#define ANA_AC_SDLB_XLB_NEXT_LBGRP_GET(x)\ + FIELD_GET(ANA_AC_SDLB_XLB_NEXT_LBGRP, x) + +/* ANA_AC_SDLB:LBSET_TBL:INH_CTRL */ +#define ANA_AC_SDLB_INH_CTRL(g, r) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 20, r, 2, 4) + +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX GENMASK(12, 0) +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, x) +#define ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, x) + +#define ANA_AC_SDLB_INH_CTRL_INH_MODE GENMASK(21, 20) +#define ANA_AC_SDLB_INH_CTRL_INH_MODE_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_INH_MODE, x) +#define ANA_AC_SDLB_INH_CTRL_INH_MODE_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_INH_MODE, x) + +#define ANA_AC_SDLB_INH_CTRL_INH_LB BIT(24) +#define ANA_AC_SDLB_INH_CTRL_INH_LB_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_CTRL_INH_LB, x) +#define ANA_AC_SDLB_INH_CTRL_INH_LB_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_CTRL_INH_LB, x) + +/* ANA_AC_SDLB:LBSET_TBL:INH_LBSET_ADDR */ +#define ANA_AC_SDLB_INH_LBSET_ADDR(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 28, 0, 1, 4) + +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR GENMASK(12, 0) +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR, x) +#define ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR_GET(x)\ + FIELD_GET(ANA_AC_SDLB_INH_LBSET_ADDR_INH_LBSET_ADDR, x) + +/* ANA_AC_SDLB:LBSET_TBL:DLB_MISC */ +#define ANA_AC_SDLB_DLB_MISC(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 32, 0, 1, 4) + +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA BIT(0) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA, x) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_DLB_FRM_RATE_ENA, x) + +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA BIT(6) +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA, x) +#define ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_MARK_ALL_FRMS_RED_ENA, x) + +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ GENMASK(14, 8) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ, x) +#define ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_MISC_DLB_FRM_ADJ, x) + +/* ANA_AC_SDLB:LBSET_TBL:DLB_CFG */ +#define ANA_AC_SDLB_DLB_CFG(g) \ + __REG(TARGET_ANA_AC_SDLB, 0, 1, 0, g, 4616, 64, 36, 0, 1, 4) + +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA BIT(11) +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA, x) +#define ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DROP_ON_YELLOW_ENA, x) + +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL GENMASK(10, 9) +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL, x) +#define ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DP_BYPASS_LVL, x) + +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS BIT(8) +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS, x) +#define ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_HIER_DLB_DIS, x) + +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS BIT(7) +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS, x) +#define ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_ENCAP_DATA_DIS, x) + +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL GENMASK(6, 5) +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL, x) +#define ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_COLOR_AWARE_LVL, x) + +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL GENMASK(4, 3) +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL, x) +#define ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_CIR_INC_DP_VAL, x) + +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE BIT(2) +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_DLB_MODE, x) +#define ANA_AC_SDLB_DLB_CFG_DLB_MODE_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_DLB_MODE, x) + +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK GENMASK(1, 0) +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK_SET(x)\ + FIELD_PREP(ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK, x) +#define ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK_GET(x)\ + FIELD_GET(ANA_AC_SDLB_DLB_CFG_TRAFFIC_TYPE_MASK, x) + /* ANA_CL:PORT:FILTER_CTRL */ #define ANA_CL_FILTER_CTRL(g) __REG(TARGET_ANA_CL, 0, 1, 131072, g, 70, 512, 4, 0, 1, 4) @@ -956,6 +1431,82 @@ enum sparx5_target { #define ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL_GET(x)\ FIELD_GET(ANA_CL_QOS_MAP_CFG_DSCP_REWR_VAL, x) +/* ANA_L2:COMMON:FWD_CFG */ +#define ANA_L2_FWD_CFG \ + __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 0, 0, 1, 4) + +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL GENMASK(21, 20) +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL, x) +#define ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_MAC_TBL_SPLIT_SEL, x) + +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA BIT(18) +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA, x) +#define ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_PORT_DEFAULT_BDLB_ENA, x) + +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA BIT(17) +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA, x) +#define ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_QUEUE_DEFAULT_SDLB_ENA, x) + +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA BIT(16) +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, x) +#define ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, x) + +#define ANA_L2_FWD_CFG_CPU_DMAC_QU GENMASK(10, 8) +#define ANA_L2_FWD_CFG_CPU_DMAC_QU_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_CPU_DMAC_QU, x) +#define ANA_L2_FWD_CFG_CPU_DMAC_QU_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_CPU_DMAC_QU, x) + +#define ANA_L2_FWD_CFG_LOOPBACK_ENA BIT(7) +#define ANA_L2_FWD_CFG_LOOPBACK_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_LOOPBACK_ENA, x) +#define ANA_L2_FWD_CFG_LOOPBACK_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_LOOPBACK_ENA, x) + +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA BIT(6) +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA, x) +#define ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_CPU_DMAC_COPY_ENA, x) + +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL BIT(4) +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FILTER_MODE_SEL, x) +#define ANA_L2_FWD_CFG_FILTER_MODE_SEL_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FILTER_MODE_SEL, x) + +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA BIT(3) +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_MIRROR_ENA, x) + +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA BIT(2) +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_IGNORE_VLAN_ENA, x) + +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA BIT(1) +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA, x) +#define ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FLOOD_CPU_COPY_ENA, x) + +#define ANA_L2_FWD_CFG_FWD_ENA BIT(0) +#define ANA_L2_FWD_CFG_FWD_ENA_SET(x)\ + FIELD_PREP(ANA_L2_FWD_CFG_FWD_ENA, x) +#define ANA_L2_FWD_CFG_FWD_ENA_GET(x)\ + FIELD_GET(ANA_L2_FWD_CFG_FWD_ENA, x) + /* ANA_L2:COMMON:AUTO_LRN_CFG */ #define ANA_L2_AUTO_LRN_CFG __REG(TARGET_ANA_L2, 0, 1, 566024, 0, 1, 700, 24, 0, 1, 4) @@ -980,6 +1531,26 @@ enum sparx5_target { #define ANA_L2_OWN_UPSID_OWN_UPSID_GET(x)\ FIELD_GET(ANA_L2_OWN_UPSID_OWN_UPSID, x) +/* ANA_L2:ISDX:DLB_CFG */ +#define ANA_L2_DLB_CFG(g) \ + __REG(TARGET_ANA_L2, 0, 1, 0, g, 4096, 128, 56, 0, 1, 4) + +#define ANA_L2_DLB_CFG_DLB_IDX GENMASK(12, 0) +#define ANA_L2_DLB_CFG_DLB_IDX_SET(x)\ + FIELD_PREP(ANA_L2_DLB_CFG_DLB_IDX, x) +#define ANA_L2_DLB_CFG_DLB_IDX_GET(x)\ + FIELD_GET(ANA_L2_DLB_CFG_DLB_IDX, x) + +/* ANA_L2:ISDX:TSN_CFG */ +#define ANA_L2_TSN_CFG(g) \ + __REG(TARGET_ANA_L2, 0, 1, 0, g, 4096, 128, 100, 0, 1, 4) + +#define ANA_L2_TSN_CFG_TSN_SFID GENMASK(9, 0) +#define ANA_L2_TSN_CFG_TSN_SFID_SET(x)\ + FIELD_PREP(ANA_L2_TSN_CFG_TSN_SFID, x) +#define ANA_L2_TSN_CFG_TSN_SFID_GET(x)\ + FIELD_GET(ANA_L2_TSN_CFG_TSN_SFID, x) + /* ANA_L3:COMMON:VLAN_CTRL */ #define ANA_L3_VLAN_CTRL __REG(TARGET_ANA_L3, 0, 1, 493632, 0, 1, 184, 4, 0, 1, 4) @@ -3736,11 +4307,11 @@ enum sparx5_target { /* HSCH:HSCH_MISC:SYS_CLK_PER */ #define HSCH_SYS_CLK_PER __REG(TARGET_HSCH, 0, 1, 163104, 0, 1, 648, 640, 0, 1, 4) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS GENMASK(7, 0) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_SET(x)\ - FIELD_PREP(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) -#define HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS_GET(x)\ - FIELD_GET(HSCH_SYS_CLK_PER_SYS_CLK_PER_100PS, x) +#define HSCH_SYS_CLK_PER_100PS GENMASK(7, 0) +#define HSCH_SYS_CLK_PER_100PS_SET(x)\ + FIELD_PREP(HSCH_SYS_CLK_PER_100PS, x) +#define HSCH_SYS_CLK_PER_100PS_GET(x)\ + FIELD_GET(HSCH_SYS_CLK_PER_100PS, x) /* HSCH:HSCH_LEAK_LISTS:HSCH_TIMER_CFG */ #define HSCH_HSCH_TIMER_CFG(g, r) __REG(TARGET_HSCH, 0, 1, 161664, g, 4, 32, 0, r, 4, 4) diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_police.c b/drivers/net/ethernet/microchip/sparx5/sparx5_police.c new file mode 100644 index 000000000000..8ada5cee1342 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_police.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static int sparx5_policer_service_conf_set(struct sparx5 *sparx5, + struct sparx5_policer *pol) +{ + u32 idx, pup_tokens, max_pup_tokens, burst, thres; + struct sparx5_sdlb_group *g; + u64 rate; + + g = &sdlb_groups[pol->group]; + idx = pol->idx; + + rate = pol->rate * 1000; + burst = pol->burst; + + pup_tokens = sparx5_sdlb_pup_token_get(sparx5, g->pup_interval, rate); + max_pup_tokens = + sparx5_sdlb_pup_token_get(sparx5, g->pup_interval, g->max_rate); + + thres = DIV_ROUND_UP(burst, g->min_burst); + + spx5_wr(ANA_AC_SDLB_PUP_TOKENS_PUP_TOKENS_SET(pup_tokens), sparx5, + ANA_AC_SDLB_PUP_TOKENS(idx, 0)); + + spx5_rmw(ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX_SET(max_pup_tokens), + ANA_AC_SDLB_INH_CTRL_PUP_TOKENS_MAX, sparx5, + ANA_AC_SDLB_INH_CTRL(idx, 0)); + + spx5_rmw(ANA_AC_SDLB_THRES_THRES_SET(thres), ANA_AC_SDLB_THRES_THRES, + sparx5, ANA_AC_SDLB_THRES(idx, 0)); + + return 0; +} + +int sparx5_policer_conf_set(struct sparx5 *sparx5, struct sparx5_policer *pol) +{ + /* More policer types will be added later */ + switch (pol->type) { + case SPX5_POL_SERVICE: + return sparx5_policer_service_conf_set(sparx5, pol); + default: + break; + } + + return 0; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c b/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c new file mode 100644 index 000000000000..b4b280c6138b --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_pool.c @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +static u32 sparx5_pool_id_to_idx(u32 id) +{ + return --id; +} + +u32 sparx5_pool_idx_to_id(u32 idx) +{ + return ++idx; +} + +/* Release resource from pool. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_put(struct sparx5_pool_entry *pool, int size, u32 id) +{ + struct sparx5_pool_entry *e_itr; + + e_itr = (pool + sparx5_pool_id_to_idx(id)); + if (e_itr->ref_cnt == 0) + return -EINVAL; + + return --e_itr->ref_cnt; +} + +/* Get resource from pool. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_get(struct sparx5_pool_entry *pool, int size, u32 *id) +{ + struct sparx5_pool_entry *e_itr; + int i; + + for (i = 0, e_itr = pool; i < size; i++, e_itr++) { + if (e_itr->ref_cnt == 0) { + *id = sparx5_pool_idx_to_id(i); + return ++e_itr->ref_cnt; + } + } + + return -ENOSPC; +} + +/* Get resource from pool that matches index. + * Return reference count on success, otherwise return error. + */ +int sparx5_pool_get_with_idx(struct sparx5_pool_entry *pool, int size, u32 idx, + u32 *id) +{ + struct sparx5_pool_entry *e_itr; + int i, ret = -ENOSPC; + + for (i = 0, e_itr = pool; i < size; i++, e_itr++) { + /* Pool index of first free entry */ + if (e_itr->ref_cnt == 0 && ret == -ENOSPC) + ret = i; + /* Tc index already in use ? */ + if (e_itr->idx == idx && e_itr->ref_cnt > 0) { + ret = i; + break; + } + } + + /* Did we find a free entry? */ + if (ret >= 0) { + *id = sparx5_pool_idx_to_id(ret); + e_itr = (pool + ret); + e_itr->idx = idx; + return ++e_itr->ref_cnt; + } + + return ret; +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c new file mode 100644 index 000000000000..8dee1ab1fa75 --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_psfp.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +#define SPX5_PSFP_SF_CNT 1024 +#define SPX5_PSFP_SG_CONFIG_CHANGE_SLEEP 1000 +#define SPX5_PSFP_SG_CONFIG_CHANGE_TIMEO 100000 + +/* Pool of available service policers */ +static struct sparx5_pool_entry sparx5_psfp_fm_pool[SPX5_SDLB_CNT]; + +/* Pool of available stream gates */ +static struct sparx5_pool_entry sparx5_psfp_sg_pool[SPX5_PSFP_SG_CNT]; + +/* Pool of available stream filters */ +static struct sparx5_pool_entry sparx5_psfp_sf_pool[SPX5_PSFP_SF_CNT]; + +static int sparx5_psfp_sf_get(u32 *id) +{ + return sparx5_pool_get(sparx5_psfp_sf_pool, SPX5_PSFP_SF_CNT, id); +} + +static int sparx5_psfp_sf_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_sf_pool, SPX5_PSFP_SF_CNT, id); +} + +static int sparx5_psfp_sg_get(u32 idx, u32 *id) +{ + return sparx5_pool_get_with_idx(sparx5_psfp_sg_pool, SPX5_PSFP_SG_CNT, + idx, id); +} + +static int sparx5_psfp_sg_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_sg_pool, SPX5_PSFP_SG_CNT, id); +} + +static int sparx5_psfp_fm_get(u32 idx, u32 *id) +{ + return sparx5_pool_get_with_idx(sparx5_psfp_fm_pool, SPX5_SDLB_CNT, idx, + id); +} + +static int sparx5_psfp_fm_put(u32 id) +{ + return sparx5_pool_put(sparx5_psfp_fm_pool, SPX5_SDLB_CNT, id); +} + +u32 sparx5_psfp_isdx_get_sf(struct sparx5 *sparx5, u32 isdx) +{ + return ANA_L2_TSN_CFG_TSN_SFID_GET(spx5_rd(sparx5, + ANA_L2_TSN_CFG(isdx))); +} + +u32 sparx5_psfp_isdx_get_fm(struct sparx5 *sparx5, u32 isdx) +{ + return ANA_L2_DLB_CFG_DLB_IDX_GET(spx5_rd(sparx5, + ANA_L2_DLB_CFG(isdx))); +} + +u32 sparx5_psfp_sf_get_sg(struct sparx5 *sparx5, u32 sfid) +{ + return ANA_AC_TSN_SF_CFG_TSN_SGID_GET(spx5_rd(sparx5, + ANA_AC_TSN_SF_CFG(sfid))); +} + +void sparx5_isdx_conf_set(struct sparx5 *sparx5, u32 isdx, u32 sfid, u32 fmid) +{ + spx5_rmw(ANA_L2_TSN_CFG_TSN_SFID_SET(sfid), ANA_L2_TSN_CFG_TSN_SFID, + sparx5, ANA_L2_TSN_CFG(isdx)); + + spx5_rmw(ANA_L2_DLB_CFG_DLB_IDX_SET(fmid), ANA_L2_DLB_CFG_DLB_IDX, + sparx5, ANA_L2_DLB_CFG(isdx)); +} + +/* Internal priority value to internal priority selector */ +static u32 sparx5_psfp_ipv_to_ips(s32 ipv) +{ + return ipv > 0 ? (ipv | BIT(3)) : 0; +} + +static int sparx5_psfp_sgid_get_status(struct sparx5 *sparx5) +{ + return spx5_rd(sparx5, ANA_AC_SG_ACCESS_CTRL); +} + +static int sparx5_psfp_sgid_wait_for_completion(struct sparx5 *sparx5) +{ + u32 val; + + return readx_poll_timeout(sparx5_psfp_sgid_get_status, sparx5, val, + !ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_GET(val), + SPX5_PSFP_SG_CONFIG_CHANGE_SLEEP, + SPX5_PSFP_SG_CONFIG_CHANGE_TIMEO); +} + +static void sparx5_psfp_sg_config_change(struct sparx5 *sparx5, u32 id) +{ + spx5_wr(ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), sparx5, + ANA_AC_SG_ACCESS_CTRL); + + spx5_wr(ANA_AC_SG_ACCESS_CTRL_CONFIG_CHANGE_SET(1) | + ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), + sparx5, ANA_AC_SG_ACCESS_CTRL); + + if (sparx5_psfp_sgid_wait_for_completion(sparx5) < 0) + pr_debug("%s:%d timed out waiting for sgid completion", + __func__, __LINE__); +} + +static void sparx5_psfp_sf_set(struct sparx5 *sparx5, u32 id, + const struct sparx5_psfp_sf *sf) +{ + /* Configure stream gate*/ + spx5_rmw(ANA_AC_TSN_SF_CFG_TSN_SGID_SET(sf->sgid) | + ANA_AC_TSN_SF_CFG_TSN_MAX_SDU_SET(sf->max_sdu) | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE_SET(sf->sblock_osize) | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA_SET(sf->sblock_osize_ena), + ANA_AC_TSN_SF_CFG_TSN_SGID | ANA_AC_TSN_SF_CFG_TSN_MAX_SDU | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_STATE | + ANA_AC_TSN_SF_CFG_BLOCK_OVERSIZE_ENA, + sparx5, ANA_AC_TSN_SF_CFG(id)); +} + +static int sparx5_psfp_sg_set(struct sparx5 *sparx5, u32 id, + const struct sparx5_psfp_sg *sg) +{ + u32 ips, base_lsb, base_msb, accum_time_interval = 0; + const struct sparx5_psfp_gce *gce; + int i; + + ips = sparx5_psfp_ipv_to_ips(sg->ipv); + base_lsb = sg->basetime.tv_sec & 0xffffffff; + base_msb = sg->basetime.tv_sec >> 32; + + /* Set stream gate id */ + spx5_wr(ANA_AC_SG_ACCESS_CTRL_SGID_SET(id), sparx5, + ANA_AC_SG_ACCESS_CTRL); + + /* Write AdminPSFP values */ + spx5_wr(sg->basetime.tv_nsec, sparx5, ANA_AC_SG_CONFIG_REG_1); + spx5_wr(base_lsb, sparx5, ANA_AC_SG_CONFIG_REG_2); + + spx5_rmw(ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB_SET(base_msb) | + ANA_AC_SG_CONFIG_REG_3_INIT_IPS_SET(ips) | + ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH_SET(sg->num_entries) | + ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE_SET(sg->gate_state) | + ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE_SET(1), + ANA_AC_SG_CONFIG_REG_3_BASE_TIME_SEC_MSB | + ANA_AC_SG_CONFIG_REG_3_INIT_IPS | + ANA_AC_SG_CONFIG_REG_3_LIST_LENGTH | + ANA_AC_SG_CONFIG_REG_3_INIT_GATE_STATE | + ANA_AC_SG_CONFIG_REG_3_GATE_ENABLE, + sparx5, ANA_AC_SG_CONFIG_REG_3); + + spx5_wr(sg->cycletime, sparx5, ANA_AC_SG_CONFIG_REG_4); + spx5_wr(sg->cycletimeext, sparx5, ANA_AC_SG_CONFIG_REG_5); + + /* For each scheduling entry */ + for (i = 0; i < sg->num_entries; i++) { + gce = &sg->gce[i]; + ips = sparx5_psfp_ipv_to_ips(gce->ipv); + /* hardware needs TimeInterval to be cumulative */ + accum_time_interval += gce->interval; + /* Set gate state */ + spx5_wr(ANA_AC_SG_GCL_GS_CONFIG_IPS_SET(ips) | + ANA_AC_SG_GCL_GS_CONFIG_GATE_STATE_SET(gce->gate_state), + sparx5, ANA_AC_SG_GCL_GS_CONFIG(i)); + + /* Set time interval */ + spx5_wr(accum_time_interval, sparx5, + ANA_AC_SG_GCL_TI_CONFIG(i)); + + /* Set maximum octets */ + spx5_wr(gce->maxoctets, sparx5, ANA_AC_SG_GCL_OCT_CONFIG(i)); + } + + return 0; +} + +static int sparx5_sdlb_conf_set(struct sparx5 *sparx5, + struct sparx5_psfp_fm *fm) +{ + int (*sparx5_sdlb_group_action)(struct sparx5 *sparx5, u32 group, + u32 idx); + + if (!fm->pol.rate && !fm->pol.burst) + sparx5_sdlb_group_action = &sparx5_sdlb_group_del; + else + sparx5_sdlb_group_action = &sparx5_sdlb_group_add; + + sparx5_policer_conf_set(sparx5, &fm->pol); + + return sparx5_sdlb_group_action(sparx5, fm->pol.group, fm->pol.idx); +} + +int sparx5_psfp_sf_add(struct sparx5 *sparx5, const struct sparx5_psfp_sf *sf, + u32 *id) +{ + int ret; + + ret = sparx5_psfp_sf_get(id); + if (ret < 0) + return ret; + + sparx5_psfp_sf_set(sparx5, *id, sf); + + return 0; +} + +int sparx5_psfp_sf_del(struct sparx5 *sparx5, u32 id) +{ + const struct sparx5_psfp_sf sf = { 0 }; + + sparx5_psfp_sf_set(sparx5, id, &sf); + + return sparx5_psfp_sf_put(id); +} + +int sparx5_psfp_sg_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_sg *sg, u32 *id) +{ + ktime_t basetime; + int ret; + + ret = sparx5_psfp_sg_get(uidx, id); + if (ret < 0) + return ret; + /* Was already in use, no need to reconfigure */ + if (ret > 1) + return 0; + + /* Calculate basetime for this stream gate */ + sparx5_new_base_time(sparx5, sg->cycletime, 0, &basetime); + sg->basetime = ktime_to_timespec64(basetime); + + sparx5_psfp_sg_set(sparx5, *id, sg); + + /* Signal hardware to copy AdminPSFP values into OperPSFP values */ + sparx5_psfp_sg_config_change(sparx5, *id); + + return 0; +} + +int sparx5_psfp_sg_del(struct sparx5 *sparx5, u32 id) +{ + const struct sparx5_psfp_sg sg = { 0 }; + int ret; + + ret = sparx5_psfp_sg_put(id); + if (ret < 0) + return ret; + /* Stream gate still in use ? */ + if (ret > 0) + return 0; + + return sparx5_psfp_sg_set(sparx5, id, &sg); +} + +int sparx5_psfp_fm_add(struct sparx5 *sparx5, u32 uidx, + struct sparx5_psfp_fm *fm, u32 *id) +{ + struct sparx5_policer *pol = &fm->pol; + int ret; + + /* Get flow meter */ + ret = sparx5_psfp_fm_get(uidx, &fm->pol.idx); + if (ret < 0) + return ret; + /* Was already in use, no need to reconfigure */ + if (ret > 1) + return 0; + + ret = sparx5_sdlb_group_get_by_rate(sparx5, pol->rate, pol->burst); + if (ret < 0) + return ret; + + fm->pol.group = ret; + + ret = sparx5_sdlb_conf_set(sparx5, fm); + if (ret < 0) + return ret; + + *id = fm->pol.idx; + + return 0; +} + +int sparx5_psfp_fm_del(struct sparx5 *sparx5, u32 id) +{ + struct sparx5_psfp_fm fm = { .pol.idx = id, + .pol.type = SPX5_POL_SERVICE }; + int ret; + + /* Find the group that this lb belongs to */ + ret = sparx5_sdlb_group_get_by_index(sparx5, id, &fm.pol.group); + if (ret < 0) + return ret; + + ret = sparx5_psfp_fm_put(id); + if (ret < 0) + return ret; + /* Do not reset flow-meter if still in use. */ + if (ret > 0) + return 0; + + return sparx5_sdlb_conf_set(sparx5, &fm); +} + +void sparx5_psfp_init(struct sparx5 *sparx5) +{ + const struct sparx5_sdlb_group *group; + int i; + + for (i = 0; i < SPX5_SDLB_GROUP_CNT; i++) { + group = &sdlb_groups[i]; + sparx5_sdlb_group_init(sparx5, group->max_rate, + group->min_burst, group->frame_size, i); + } + + spx5_wr(ANA_AC_SG_CYCLETIME_UPDATE_PERIOD_SG_CT_UPDATE_ENA_SET(1), + sparx5, ANA_AC_SG_CYCLETIME_UPDATE_PERIOD); + + spx5_rmw(ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA_SET(1), + ANA_L2_FWD_CFG_ISDX_LOOKUP_ENA, sparx5, ANA_L2_FWD_CFG); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 0ed1ea7727c5..0edb98cef7e4 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -476,8 +476,7 @@ static int sparx5_ptp_settime64(struct ptp_clock_info *ptp, return 0; } -static int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, - struct timespec64 *ts) +int sparx5_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct sparx5_phc *phc = container_of(ptp, struct sparx5_phc, info); struct sparx5 *sparx5 = phc->sparx5; @@ -633,7 +632,7 @@ int sparx5_ptp_init(struct sparx5 *sparx5) /* Enable master counters */ spx5_wr(PTP_PTP_DOM_CFG_PTP_ENA_SET(0x7), sparx5, PTP_PTP_DOM_CFG); - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; @@ -649,7 +648,7 @@ void sparx5_ptp_deinit(struct sparx5 *sparx5) struct sparx5_port *port; int i; - for (i = 0; i < sparx5->port_count; i++) { + for (i = 0; i < SPX5_PORTS; i++) { port = sparx5->ports[i]; if (!port) continue; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c index 379e540e5e6a..5f34febaee6b 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.c @@ -9,6 +9,63 @@ #include "sparx5_main.h" #include "sparx5_qos.h" +/* Calculate new base_time based on cycle_time. + * + * The hardware requires a base_time that is always in the future. + * We define threshold_time as current_time + (2 * cycle_time). + * If base_time is below threshold_time this function recalculates it to be in + * the interval: + * threshold_time <= base_time < (threshold_time + cycle_time) + * + * A very simple algorithm could be like this: + * new_base_time = org_base_time + N * cycle_time + * using the lowest N so (new_base_time >= threshold_time + */ +void sparx5_new_base_time(struct sparx5 *sparx5, const u32 cycle_time, + const ktime_t org_base_time, ktime_t *new_base_time) +{ + ktime_t current_time, threshold_time, new_time; + struct timespec64 ts; + u64 nr_of_cycles_p2; + u64 nr_of_cycles; + u64 diff_time; + + new_time = org_base_time; + + sparx5_ptp_gettime64(&sparx5->phc[SPARX5_PHC_PORT].info, &ts); + current_time = timespec64_to_ktime(ts); + threshold_time = current_time + (2 * cycle_time); + diff_time = threshold_time - new_time; + nr_of_cycles = div_u64(diff_time, cycle_time); + nr_of_cycles_p2 = 1; /* Use 2^0 as start value */ + + if (new_time >= threshold_time) { + *new_base_time = new_time; + return; + } + + /* Calculate the smallest power of 2 (nr_of_cycles_p2) + * that is larger than nr_of_cycles. + */ + while (nr_of_cycles_p2 < nr_of_cycles) + nr_of_cycles_p2 <<= 1; /* Next (higher) power of 2 */ + + /* Add as big chunks (power of 2 * cycle_time) + * as possible for each power of 2 + */ + while (nr_of_cycles_p2) { + if (new_time < threshold_time) { + new_time += cycle_time * nr_of_cycles_p2; + while (new_time < threshold_time) + new_time += cycle_time * nr_of_cycles_p2; + new_time -= cycle_time * nr_of_cycles_p2; + } + nr_of_cycles_p2 >>= 1; /* Next (lower) power of 2 */ + } + new_time += cycle_time; + *new_base_time = new_time; +} + /* Max rates for leak groups */ static const u32 spx5_hsch_max_group_rate[SPX5_HSCH_LEAK_GRP_CNT] = { 1048568, /* 1.049 Gbps */ @@ -393,6 +450,8 @@ int sparx5_qos_init(struct sparx5 *sparx5) if (ret < 0) return ret; + sparx5_psfp_init(sparx5); + return 0; } diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c new file mode 100644 index 000000000000..f5267218caeb --- /dev/null +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_sdlb.c @@ -0,0 +1,335 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip Sparx5 Switch driver + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include "sparx5_main_regs.h" +#include "sparx5_main.h" + +struct sparx5_sdlb_group sdlb_groups[SPX5_SDLB_GROUP_CNT] = { + { SPX5_SDLB_GROUP_RATE_MAX, 8192 / 1, 64 }, /* 25 G */ + { 15000000000ULL, 8192 / 1, 64 }, /* 15 G */ + { 10000000000ULL, 8192 / 1, 64 }, /* 10 G */ + { 5000000000ULL, 8192 / 1, 64 }, /* 5 G */ + { 2500000000ULL, 8192 / 1, 64 }, /* 2.5 G */ + { 1000000000ULL, 8192 / 2, 64 }, /* 1 G */ + { 500000000ULL, 8192 / 2, 64 }, /* 500 M */ + { 100000000ULL, 8192 / 4, 64 }, /* 100 M */ + { 50000000ULL, 8192 / 4, 64 }, /* 50 M */ + { 5000000ULL, 8192 / 8, 64 } /* 5 M */ +}; + +int sparx5_sdlb_clk_hz_get(struct sparx5 *sparx5) +{ + u32 clk_per_100ps; + u64 clk_hz; + + clk_per_100ps = HSCH_SYS_CLK_PER_100PS_GET(spx5_rd(sparx5, + HSCH_SYS_CLK_PER)); + if (!clk_per_100ps) + clk_per_100ps = SPX5_CLK_PER_100PS_DEFAULT; + + clk_hz = (10 * 1000 * 1000) / clk_per_100ps; + return clk_hz *= 1000; +} + +static int sparx5_sdlb_pup_interval_get(struct sparx5 *sparx5, u32 max_token, + u64 max_rate) +{ + u64 clk_hz; + + clk_hz = sparx5_sdlb_clk_hz_get(sparx5); + + return div64_u64((8 * clk_hz * max_token), max_rate); +} + +int sparx5_sdlb_pup_token_get(struct sparx5 *sparx5, u32 pup_interval, u64 rate) +{ + u64 clk_hz; + + if (!rate) + return SPX5_SDLB_PUP_TOKEN_DISABLE; + + clk_hz = sparx5_sdlb_clk_hz_get(sparx5); + + return DIV64_U64_ROUND_UP((rate * pup_interval), (clk_hz * 8)); +} + +static void sparx5_sdlb_group_disable(struct sparx5 *sparx5, u32 group) +{ + spx5_rmw(ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(0), + ANA_AC_SDLB_PUP_CTRL_PUP_ENA, sparx5, + ANA_AC_SDLB_PUP_CTRL(group)); +} + +static void sparx5_sdlb_group_enable(struct sparx5 *sparx5, u32 group) +{ + spx5_rmw(ANA_AC_SDLB_PUP_CTRL_PUP_ENA_SET(1), + ANA_AC_SDLB_PUP_CTRL_PUP_ENA, sparx5, + ANA_AC_SDLB_PUP_CTRL(group)); +} + +static u32 sparx5_sdlb_group_get_first(struct sparx5 *sparx5, u32 group) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_XLB_START(group)); + + return ANA_AC_SDLB_XLB_START_LBSET_START_GET(val); +} + +static u32 sparx5_sdlb_group_get_next(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_XLB_NEXT(lb)); + + return ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_GET(val); +} + +static bool sparx5_sdlb_group_is_first(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + return lb == sparx5_sdlb_group_get_first(sparx5, group); +} + +static bool sparx5_sdlb_group_is_last(struct sparx5 *sparx5, u32 group, + u32 lb) +{ + return lb == sparx5_sdlb_group_get_next(sparx5, group, lb); +} + +static bool sparx5_sdlb_group_is_empty(struct sparx5 *sparx5, u32 group) +{ + u32 val; + + val = spx5_rd(sparx5, ANA_AC_SDLB_PUP_CTRL(group)); + + return ANA_AC_SDLB_PUP_CTRL_PUP_ENA_GET(val) == 0; +} + +static u32 sparx5_sdlb_group_get_last(struct sparx5 *sparx5, u32 group) +{ + u32 itr, next; + + itr = sparx5_sdlb_group_get_first(sparx5, group); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, group, itr); + if (itr == next) + return itr; + + itr = next; + } +} + +static bool sparx5_sdlb_group_is_singular(struct sparx5 *sparx5, u32 group) +{ + if (sparx5_sdlb_group_is_empty(sparx5, group)) + return false; + + return sparx5_sdlb_group_get_first(sparx5, group) == + sparx5_sdlb_group_get_last(sparx5, group); +} + +static int sparx5_sdlb_group_get_adjacent(struct sparx5 *sparx5, u32 group, + u32 idx, u32 *prev, u32 *next, + u32 *first) +{ + u32 itr; + + *first = sparx5_sdlb_group_get_first(sparx5, group); + *prev = *first; + *next = *first; + itr = *first; + + for (;;) { + *next = sparx5_sdlb_group_get_next(sparx5, group, itr); + + if (itr == idx) + return 0; /* Found it */ + + if (itr == *next) + return -EINVAL; /* Was not found */ + + *prev = itr; + itr = *next; + } +} + +static int sparx5_sdlb_group_get_count(struct sparx5 *sparx5, u32 group) +{ + u32 itr, next; + int count = 0; + + itr = sparx5_sdlb_group_get_first(sparx5, group); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, group, itr); + if (itr == next) + return count; + + itr = next; + count++; + } +} + +int sparx5_sdlb_group_get_by_rate(struct sparx5 *sparx5, u32 rate, u32 burst) +{ + const struct sparx5_sdlb_group *group; + u64 rate_bps; + int i, count; + + rate_bps = rate * 1000; + + for (i = SPX5_SDLB_GROUP_CNT - 1; i >= 0; i--) { + group = &sdlb_groups[i]; + + count = sparx5_sdlb_group_get_count(sparx5, i); + + /* Check that this group is not full. + * According to LB group configuration rules: the number of XLBs + * in a group must not exceed PUP_INTERVAL/4 - 1. + */ + if (count > ((group->pup_interval / 4) - 1)) + continue; + + if (rate_bps < group->max_rate) + return i; + } + + return -ENOSPC; +} + +int sparx5_sdlb_group_get_by_index(struct sparx5 *sparx5, u32 idx, u32 *group) +{ + u32 itr, next; + int i; + + for (i = 0; i < SPX5_SDLB_GROUP_CNT; i++) { + if (sparx5_sdlb_group_is_empty(sparx5, i)) + continue; + + itr = sparx5_sdlb_group_get_first(sparx5, i); + + for (;;) { + next = sparx5_sdlb_group_get_next(sparx5, i, itr); + + if (itr == idx) { + *group = i; + return 0; /* Found it */ + } + if (itr == next) + break; /* Was not found */ + + itr = next; + } + } + + return -EINVAL; +} + +static int sparx5_sdlb_group_link(struct sparx5 *sparx5, u32 group, u32 idx, + u32 first, u32 next, bool empty) +{ + /* Stop leaking */ + sparx5_sdlb_group_disable(sparx5, group); + + if (empty) + return 0; + + /* Link insertion lb to next lb */ + spx5_wr(ANA_AC_SDLB_XLB_NEXT_LBSET_NEXT_SET(next) | + ANA_AC_SDLB_XLB_NEXT_LBGRP_SET(group), + sparx5, ANA_AC_SDLB_XLB_NEXT(idx)); + + /* Set the first lb */ + spx5_wr(ANA_AC_SDLB_XLB_START_LBSET_START_SET(first), sparx5, + ANA_AC_SDLB_XLB_START(group)); + + /* Start leaking */ + sparx5_sdlb_group_enable(sparx5, group); + + return 0; +}; + +int sparx5_sdlb_group_add(struct sparx5 *sparx5, u32 group, u32 idx) +{ + u32 first, next; + + /* We always add to head of the list */ + first = idx; + + if (sparx5_sdlb_group_is_empty(sparx5, group)) + next = idx; + else + next = sparx5_sdlb_group_get_first(sparx5, group); + + return sparx5_sdlb_group_link(sparx5, group, idx, first, next, false); +} + +int sparx5_sdlb_group_del(struct sparx5 *sparx5, u32 group, u32 idx) +{ + u32 first, next, prev; + bool empty = false; + + if (sparx5_sdlb_group_get_adjacent(sparx5, group, idx, &prev, &next, + &first) < 0) { + pr_err("%s:%d Could not find idx: %d in group: %d", __func__, + __LINE__, idx, group); + return -EINVAL; + } + + if (sparx5_sdlb_group_is_singular(sparx5, group)) { + empty = true; + } else if (sparx5_sdlb_group_is_last(sparx5, group, idx)) { + /* idx is removed, prev is now last */ + idx = prev; + next = prev; + } else if (sparx5_sdlb_group_is_first(sparx5, group, idx)) { + /* idx is removed and points to itself, first is next */ + first = next; + next = idx; + } else { + /* Next is not touched */ + idx = prev; + } + + return sparx5_sdlb_group_link(sparx5, group, idx, first, next, empty); +} + +void sparx5_sdlb_group_init(struct sparx5 *sparx5, u64 max_rate, u32 min_burst, + u32 frame_size, u32 idx) +{ + u32 thres_shift, mask = 0x01, power = 0; + struct sparx5_sdlb_group *group; + u64 max_token; + + group = &sdlb_groups[idx]; + + /* Number of positions to right-shift LB's threshold value. */ + while ((min_burst & mask) == 0) { + power++; + mask <<= 1; + } + thres_shift = SPX5_SDLB_2CYCLES_TYPE2_THRES_OFFSET - power; + + max_token = (min_burst > SPX5_SDLB_PUP_TOKEN_MAX) ? + SPX5_SDLB_PUP_TOKEN_MAX : + min_burst; + group->pup_interval = + sparx5_sdlb_pup_interval_get(sparx5, max_token, max_rate); + + group->frame_size = frame_size; + + spx5_wr(ANA_AC_SDLB_PUP_INTERVAL_PUP_INTERVAL_SET(group->pup_interval), + sparx5, ANA_AC_SDLB_PUP_INTERVAL(idx)); + + spx5_wr(ANA_AC_SDLB_FRM_RATE_TOKENS_FRM_RATE_TOKENS_SET(frame_size), + sparx5, ANA_AC_SDLB_FRM_RATE_TOKENS(idx)); + + spx5_wr(ANA_AC_SDLB_LBGRP_MISC_THRES_SHIFT_SET(thres_shift), sparx5, + ANA_AC_SDLB_LBGRP_MISC(idx)); +} diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c index 205246b5af82..e80f3166db7d 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc.c @@ -5,6 +5,7 @@ */ #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "sparx5_tc.h" #include "sparx5_main.h" diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c index 217ff127e3c7..d73668dcc6b6 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_tc_flower.c @@ -4,11 +4,13 @@ * Copyright (c) 2022 Microchip Technology Inc. and its subsidiaries. */ +#include <net/tc_act/tc_gate.h> #include <net/tcp.h> #include "sparx5_tc.h" #include "vcap_api.h" #include "vcap_api_client.h" +#include "vcap_tc.h" #include "sparx5_main.h" #include "sparx5_vcap_impl.h" @@ -26,223 +28,8 @@ struct sparx5_multiple_rules { struct sparx5_wildcard_rule rule[SPX5_MAX_RULE_SIZE]; }; -struct sparx5_tc_flower_parse_usage { - struct flow_cls_offload *fco; - struct flow_rule *frule; - struct vcap_rule *vrule; - struct vcap_admin *admin; - u16 l3_proto; - u8 l4_proto; - unsigned int used_keys; -}; - -enum sparx5_is2_arp_opcode { - SPX5_IS2_ARP_REQUEST, - SPX5_IS2_ARP_REPLY, - SPX5_IS2_RARP_REQUEST, - SPX5_IS2_RARP_REPLY, -}; - -enum tc_arp_opcode { - TC_ARP_OP_RESERVED, - TC_ARP_OP_REQUEST, - TC_ARP_OP_REPLY, -}; - -static int sparx5_tc_flower_handler_ethaddr_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; - enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; - struct flow_match_eth_addrs match; - struct vcap_u48_key smac, dmac; - int err = 0; - - flow_rule_match_eth_addrs(st->frule, &match); - - if (!is_zero_ether_addr(match.mask->src)) { - vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); - vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); - if (err) - goto out; - } - - if (!is_zero_ether_addr(match.mask->dst)) { - vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); - vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); - err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "eth_addr parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_ipv4_usage(struct sparx5_tc_flower_parse_usage *st) -{ - int err = 0; - - if (st->l3_proto == ETH_P_IP) { - struct flow_match_ipv4_addrs mt; - - flow_rule_match_ipv4_addrs(st->frule, &mt); - if (mt.mask->src) { - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_IP4_SIP, - be32_to_cpu(mt.key->src), - be32_to_cpu(mt.mask->src)); - if (err) - goto out; - } - if (mt.mask->dst) { - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_IP4_DIP, - be32_to_cpu(mt.key->dst), - be32_to_cpu(mt.mask->dst)); - if (err) - goto out; - } - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_ipv6_usage(struct sparx5_tc_flower_parse_usage *st) -{ - int err = 0; - - if (st->l3_proto == ETH_P_IPV6) { - struct flow_match_ipv6_addrs mt; - struct vcap_u128_key sip; - struct vcap_u128_key dip; - - flow_rule_match_ipv6_addrs(st->frule, &mt); - /* Check if address masks are non-zero */ - if (!ipv6_addr_any(&mt.mask->src)) { - vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); - vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); - err = vcap_rule_add_key_u128(st->vrule, - VCAP_KF_L3_IP6_SIP, &sip); - if (err) - goto out; - } - if (!ipv6_addr_any(&mt.mask->dst)) { - vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); - vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); - err = vcap_rule_add_key_u128(st->vrule, - VCAP_KF_L3_IP6_DIP, &dip); - if (err) - goto out; - } - } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); - return err; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_control_usage(struct sparx5_tc_flower_parse_usage *st) -{ - struct flow_match_control mt; - u32 value, mask; - int err = 0; - - flow_rule_match_control(st->frule, &mt); - - if (mt.mask->flags) { - if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { - if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { - value = 1; /* initial fragment */ - mask = 0x3; - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - } else { - if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { - value = 3; /* follow up fragment */ - mask = 0x3; - } else { - value = 0; /* no fragment */ - mask = 0x3; - } - } - - err = vcap_rule_add_key_u32(st->vrule, - VCAP_KF_L3_FRAGMENT_TYPE, - value, mask); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_portnum_usage(struct sparx5_tc_flower_parse_usage *st) -{ - struct flow_match_ports mt; - u16 value, mask; - int err = 0; - - flow_rule_match_ports(st->frule, &mt); - - if (mt.mask->src) { - value = be16_to_cpu(mt.key->src); - mask = be16_to_cpu(mt.mask->src); - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, - mask); - if (err) - goto out; - } - - if (mt.mask->dst) { - value = be16_to_cpu(mt.key->dst); - mask = be16_to_cpu(mt.mask->dst); - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, - mask); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); - return err; -} - static int -sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_basic_usage(struct vcap_tc_flower_parse_usage *st) { struct flow_match_basic mt; int err = 0; @@ -273,7 +60,6 @@ sparx5_tc_flower_handler_basic_usage(struct sparx5_tc_flower_parse_usage *st) if (err) goto out; } - } } @@ -317,268 +103,92 @@ out: } static int -sparx5_tc_flower_handler_cvlan_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field vid_key = VCAP_KF_8021Q_VID0; - enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP0; - struct flow_match_vlan mt; - u16 tpid; - int err; - - if (st->admin->vtype != VCAP_TYPE_IS0) { - NL_SET_ERR_MSG_MOD(st->fco->common.extack, - "cvlan not supported in this VCAP"); - return -EINVAL; - } - - flow_rule_match_cvlan(st->frule, &mt); - - tpid = be16_to_cpu(mt.key->vlan_tpid); - - if (tpid == ETH_P_8021Q) { - vid_key = VCAP_KF_8021Q_VID1; - pcp_key = VCAP_KF_8021Q_PCP1; - } - - if (mt.mask->vlan_id) { - err = vcap_rule_add_key_u32(st->vrule, vid_key, - mt.key->vlan_id, - mt.mask->vlan_id); - if (err) - goto out; - } - - if (mt.mask->vlan_priority) { - err = vcap_rule_add_key_u32(st->vrule, pcp_key, - mt.key->vlan_priority, - mt.mask->vlan_priority); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); - - return 0; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "cvlan parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_vlan_usage(struct sparx5_tc_flower_parse_usage *st) -{ - enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; - enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; - struct flow_match_vlan mt; - int err; - - flow_rule_match_vlan(st->frule, &mt); - - if (st->admin->vtype == VCAP_TYPE_IS0) { - vid_key = VCAP_KF_8021Q_VID0; - pcp_key = VCAP_KF_8021Q_PCP0; - } - - if (mt.mask->vlan_id) { - err = vcap_rule_add_key_u32(st->vrule, vid_key, - mt.key->vlan_id, - mt.mask->vlan_id); - if (err) - goto out; - } - - if (mt.mask->vlan_priority) { - err = vcap_rule_add_key_u32(st->vrule, pcp_key, - mt.key->vlan_priority, - mt.mask->vlan_priority); - if (err) - goto out; - } - - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); - - return 0; -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); - return err; -} - -static int -sparx5_tc_flower_handler_tcp_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_control_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_tcp mt; - u16 tcp_flags_mask; - u16 tcp_flags_key; - enum vcap_bit val; + struct flow_match_control mt; + u32 value, mask; int err = 0; - flow_rule_match_tcp(st->frule, &mt); - tcp_flags_key = be16_to_cpu(mt.key->flags); - tcp_flags_mask = be16_to_cpu(mt.mask->flags); - - if (tcp_flags_mask & TCPHDR_FIN) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_FIN) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_SYN) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_SYN) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_RST) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_RST) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); - if (err) - goto out; - } - - if (tcp_flags_mask & TCPHDR_PSH) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_PSH) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); - if (err) - goto out; - } + flow_rule_match_control(st->frule, &mt); - if (tcp_flags_mask & TCPHDR_ACK) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_ACK) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); - if (err) - goto out; - } + if (mt.mask->flags) { + if (mt.mask->flags & FLOW_DIS_FIRST_FRAG) { + if (mt.key->flags & FLOW_DIS_FIRST_FRAG) { + value = 1; /* initial fragment */ + mask = 0x3; + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } + } else { + if (mt.mask->flags & FLOW_DIS_IS_FRAGMENT) { + value = 3; /* follow up fragment */ + mask = 0x3; + } else { + value = 0; /* no fragment */ + mask = 0x3; + } + } - if (tcp_flags_mask & TCPHDR_URG) { - val = VCAP_BIT_0; - if (tcp_flags_key & TCPHDR_URG) - val = VCAP_BIT_1; - err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_FRAGMENT_TYPE, + value, mask); if (err) goto out; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL); return err; out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_frag parse error"); return err; } static int -sparx5_tc_flower_handler_arp_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_arp mt; - u16 value, mask; - u32 ipval, ipmsk; - int err; - - flow_rule_match_arp(st->frule, &mt); - - if (mt.mask->op) { - mask = 0x3; - if (st->l3_proto == ETH_P_ARP) { - value = mt.key->op == TC_ARP_OP_REQUEST ? - SPX5_IS2_ARP_REQUEST : - SPX5_IS2_ARP_REPLY; - } else { /* RARP */ - value = mt.key->op == TC_ARP_OP_REQUEST ? - SPX5_IS2_RARP_REQUEST : - SPX5_IS2_RARP_REPLY; - } - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ARP_OPCODE, - value, mask); - if (err) - goto out; - } - - /* The IS2 ARP keyset does not support ARP hardware addresses */ - if (!is_zero_ether_addr(mt.mask->sha) || - !is_zero_ether_addr(mt.mask->tha)) { - err = -EINVAL; - goto out; - } - - if (mt.mask->sip) { - ipval = be32_to_cpu((__force __be32)mt.key->sip); - ipmsk = be32_to_cpu((__force __be32)mt.mask->sip); - - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_SIP, - ipval, ipmsk); - if (err) - goto out; - } - - if (mt.mask->tip) { - ipval = be32_to_cpu((__force __be32)mt.key->tip); - ipmsk = be32_to_cpu((__force __be32)mt.mask->tip); - - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_DIP, - ipval, ipmsk); - if (err) - goto out; + if (st->admin->vtype != VCAP_TYPE_IS0) { + NL_SET_ERR_MSG_MOD(st->fco->common.extack, + "cvlan not supported in this VCAP"); + return -EINVAL; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); - - return 0; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "arp parse error"); - return err; + return vcap_tc_flower_handler_cvlan_usage(st); } static int -sparx5_tc_flower_handler_ip_usage(struct sparx5_tc_flower_parse_usage *st) +sparx5_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st) { - struct flow_match_ip mt; - int err = 0; - - flow_rule_match_ip(st->frule, &mt); + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID_CLS; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP_CLS; - if (mt.mask->tos) { - err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, - mt.key->tos, - mt.mask->tos); - if (err) - goto out; + if (st->admin->vtype == VCAP_TYPE_IS0) { + vid_key = VCAP_KF_8021Q_VID0; + pcp_key = VCAP_KF_8021Q_PCP0; } - st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); - - return err; - -out: - NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); - return err; + return vcap_tc_flower_handler_vlan_usage(st, vid_key, pcp_key); } -static int (*sparx5_tc_flower_usage_handlers[])(struct sparx5_tc_flower_parse_usage *st) = { - [FLOW_DISSECTOR_KEY_ETH_ADDRS] = sparx5_tc_flower_handler_ethaddr_usage, - [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = sparx5_tc_flower_handler_ipv4_usage, - [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = sparx5_tc_flower_handler_ipv6_usage, +static int (*sparx5_tc_flower_usage_handlers[])(struct vcap_tc_flower_parse_usage *st) = { + [FLOW_DISSECTOR_KEY_ETH_ADDRS] = vcap_tc_flower_handler_ethaddr_usage, + [FLOW_DISSECTOR_KEY_IPV4_ADDRS] = vcap_tc_flower_handler_ipv4_usage, + [FLOW_DISSECTOR_KEY_IPV6_ADDRS] = vcap_tc_flower_handler_ipv6_usage, [FLOW_DISSECTOR_KEY_CONTROL] = sparx5_tc_flower_handler_control_usage, - [FLOW_DISSECTOR_KEY_PORTS] = sparx5_tc_flower_handler_portnum_usage, + [FLOW_DISSECTOR_KEY_PORTS] = vcap_tc_flower_handler_portnum_usage, [FLOW_DISSECTOR_KEY_BASIC] = sparx5_tc_flower_handler_basic_usage, [FLOW_DISSECTOR_KEY_CVLAN] = sparx5_tc_flower_handler_cvlan_usage, [FLOW_DISSECTOR_KEY_VLAN] = sparx5_tc_flower_handler_vlan_usage, - [FLOW_DISSECTOR_KEY_TCP] = sparx5_tc_flower_handler_tcp_usage, - [FLOW_DISSECTOR_KEY_ARP] = sparx5_tc_flower_handler_arp_usage, - [FLOW_DISSECTOR_KEY_IP] = sparx5_tc_flower_handler_ip_usage, + [FLOW_DISSECTOR_KEY_TCP] = vcap_tc_flower_handler_tcp_usage, + [FLOW_DISSECTOR_KEY_ARP] = vcap_tc_flower_handler_arp_usage, + [FLOW_DISSECTOR_KEY_IP] = vcap_tc_flower_handler_ip_usage, }; static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, @@ -586,7 +196,7 @@ static int sparx5_tc_use_dissectors(struct flow_cls_offload *fco, struct vcap_rule *vrule, u16 *l3_proto) { - struct sparx5_tc_flower_parse_usage state = { + struct vcap_tc_flower_parse_usage state = { .fco = fco, .vrule = vrule, .l3_proto = ETH_P_ALL, @@ -989,19 +599,156 @@ out: return err; } +static int sparx5_tc_flower_parse_act_gate(struct sparx5_psfp_sg *sg, + struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + int i; + + if (act->gate.prio < -1 || act->gate.prio > SPX5_PSFP_SG_MAX_IPV) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate priority"); + return -EINVAL; + } + + if (act->gate.cycletime < SPX5_PSFP_SG_MIN_CYCLE_TIME_NS || + act->gate.cycletime > SPX5_PSFP_SG_MAX_CYCLE_TIME_NS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate cycletime"); + return -EINVAL; + } + + if (act->gate.cycletimeext > SPX5_PSFP_SG_MAX_CYCLE_TIME_NS) { + NL_SET_ERR_MSG_MOD(extack, "Invalid gate cycletimeext"); + return -EINVAL; + } + + if (act->gate.num_entries >= SPX5_PSFP_GCE_CNT) { + NL_SET_ERR_MSG_MOD(extack, "Invalid number of gate entries"); + return -EINVAL; + } + + sg->gate_state = true; + sg->ipv = act->gate.prio; + sg->num_entries = act->gate.num_entries; + sg->cycletime = act->gate.cycletime; + sg->cycletimeext = act->gate.cycletimeext; + + for (i = 0; i < sg->num_entries; i++) { + sg->gce[i].gate_state = !!act->gate.entries[i].gate_state; + sg->gce[i].interval = act->gate.entries[i].interval; + sg->gce[i].ipv = act->gate.entries[i].ipv; + sg->gce[i].maxoctets = act->gate.entries[i].maxoctets; + } + + return 0; +} + +static int sparx5_tc_flower_parse_act_police(struct sparx5_policer *pol, + struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + pol->type = SPX5_POL_SERVICE; + pol->rate = div_u64(act->police.rate_bytes_ps, 1000) * 8; + pol->burst = act->police.burst; + pol->idx = act->hw_index; + + /* rate is now in kbit */ + if (pol->rate > DIV_ROUND_UP(SPX5_SDLB_GROUP_RATE_MAX, 1000)) { + NL_SET_ERR_MSG_MOD(extack, "Maximum rate exceeded"); + return -EINVAL; + } + + if (act->police.exceed.act_id != FLOW_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when exceed action is not drop"); + return -EOPNOTSUPP; + } + + if (act->police.notexceed.act_id != FLOW_ACTION_PIPE && + act->police.notexceed.act_id != FLOW_ACTION_ACCEPT) { + NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform action is not pipe or ok"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int sparx5_tc_flower_psfp_setup(struct sparx5 *sparx5, + struct vcap_rule *vrule, int sg_idx, + int pol_idx, struct sparx5_psfp_sg *sg, + struct sparx5_psfp_fm *fm, + struct sparx5_psfp_sf *sf) +{ + u32 psfp_sfid = 0, psfp_fmid = 0, psfp_sgid = 0; + int ret; + + /* Must always have a stream gate - max sdu (filter option) is evaluated + * after frames have passed the gate, so in case of only a policer, we + * allocate a stream gate that is always open. + */ + if (sg_idx < 0) { + sg_idx = sparx5_pool_idx_to_id(SPX5_PSFP_SG_OPEN); + sg->ipv = 0; /* Disabled */ + sg->cycletime = SPX5_PSFP_SG_CYCLE_TIME_DEFAULT; + sg->num_entries = 1; + sg->gate_state = 1; /* Open */ + sg->gate_enabled = 1; + sg->gce[0].gate_state = 1; + sg->gce[0].interval = SPX5_PSFP_SG_CYCLE_TIME_DEFAULT; + sg->gce[0].ipv = 0; + sg->gce[0].maxoctets = 0; /* Disabled */ + } + + ret = sparx5_psfp_sg_add(sparx5, sg_idx, sg, &psfp_sgid); + if (ret < 0) + return ret; + + if (pol_idx >= 0) { + /* Add new flow-meter */ + ret = sparx5_psfp_fm_add(sparx5, pol_idx, fm, &psfp_fmid); + if (ret < 0) + return ret; + } + + /* Map stream filter to stream gate */ + sf->sgid = psfp_sgid; + + /* Add new stream-filter and map it to a steam gate */ + ret = sparx5_psfp_sf_add(sparx5, sf, &psfp_sfid); + if (ret < 0) + return ret; + + /* Streams are classified by ISDX - map ISDX 1:1 to sfid for now. */ + sparx5_isdx_conf_set(sparx5, psfp_sfid, psfp_sfid, psfp_fmid); + + ret = vcap_rule_add_action_bit(vrule, VCAP_AF_ISDX_ADD_REPLACE_SEL, + VCAP_BIT_1); + if (ret) + return ret; + + ret = vcap_rule_add_action_u32(vrule, VCAP_AF_ISDX_VAL, psfp_sfid); + if (ret) + return ret; + + return 0; +} + static int sparx5_tc_flower_replace(struct net_device *ndev, struct flow_cls_offload *fco, struct vcap_admin *admin, bool ingress) { + struct sparx5_psfp_sf sf = { .max_sdu = SPX5_PSFP_SF_MAX_SDU }; + struct netlink_ext_ack *extack = fco->common.extack; + int err, idx, tc_sg_idx = -1, tc_pol_idx = -1; struct sparx5_port *port = netdev_priv(ndev); struct sparx5_multiple_rules multi = {}; + struct sparx5 *sparx5 = port->sparx5; + struct sparx5_psfp_sg sg = { 0 }; + struct sparx5_psfp_fm fm = { 0 }; struct flow_action_entry *act; struct vcap_control *vctrl; struct flow_rule *frule; struct vcap_rule *vrule; u16 l3_proto; - int err, idx; vctrl = port->sparx5->vcap_ctrl; @@ -1033,6 +780,26 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, frule = flow_cls_offload_flow_rule(fco); flow_action_for_each(idx, act, &frule->action) { switch (act->id) { + case FLOW_ACTION_GATE: { + err = sparx5_tc_flower_parse_act_gate(&sg, act, extack); + if (err < 0) + goto out; + + tc_sg_idx = act->hw_index; + + break; + } + case FLOW_ACTION_POLICE: { + err = sparx5_tc_flower_parse_act_police(&fm.pol, act, + extack); + if (err < 0) + goto out; + + tc_pol_idx = fm.pol.idx; + sf.max_sdu = act->police.mtu; + + break; + } case FLOW_ACTION_TRAP: if (admin->vtype != VCAP_TYPE_IS2 && admin->vtype != VCAP_TYPE_ES2) { @@ -1079,6 +846,14 @@ static int sparx5_tc_flower_replace(struct net_device *ndev, } } + /* Setup PSFP */ + if (tc_sg_idx >= 0 || tc_pol_idx >= 0) { + err = sparx5_tc_flower_psfp_setup(sparx5, vrule, tc_sg_idx, + tc_pol_idx, &sg, &fm, &sf); + if (err) + goto out; + } + err = sparx5_tc_select_protocol_keyset(ndev, vrule, admin, l3_proto, &multi); if (err) { @@ -1107,19 +882,86 @@ out: return err; } +static void sparx5_tc_free_psfp_resources(struct sparx5 *sparx5, + struct vcap_rule *vrule) +{ + struct vcap_client_actionfield *afield; + u32 isdx, sfid, sgid, fmid; + + /* Check if VCAP_AF_ISDX_VAL action is set for this rule - and if + * it is used for stream and/or flow-meter classification. + */ + afield = vcap_find_actionfield(vrule, VCAP_AF_ISDX_VAL); + if (!afield) + return; + + isdx = afield->data.u32.value; + sfid = sparx5_psfp_isdx_get_sf(sparx5, isdx); + + if (!sfid) + return; + + fmid = sparx5_psfp_isdx_get_fm(sparx5, isdx); + sgid = sparx5_psfp_sf_get_sg(sparx5, sfid); + + if (fmid && sparx5_psfp_fm_del(sparx5, fmid) < 0) + pr_err("%s:%d Could not delete invalid fmid: %d", __func__, + __LINE__, fmid); + + if (sgid && sparx5_psfp_sg_del(sparx5, sgid) < 0) + pr_err("%s:%d Could not delete invalid sgid: %d", __func__, + __LINE__, sgid); + + if (sparx5_psfp_sf_del(sparx5, sfid) < 0) + pr_err("%s:%d Could not delete invalid sfid: %d", __func__, + __LINE__, sfid); + + sparx5_isdx_conf_set(sparx5, isdx, 0, 0); +} + +static int sparx5_tc_free_rule_resources(struct net_device *ndev, + struct vcap_control *vctrl, + int rule_id) +{ + struct sparx5_port *port = netdev_priv(ndev); + struct sparx5 *sparx5 = port->sparx5; + struct vcap_rule *vrule; + int ret = 0; + + vrule = vcap_get_rule(vctrl, rule_id); + if (!vrule || IS_ERR(vrule)) + return -EINVAL; + + sparx5_tc_free_psfp_resources(sparx5, vrule); + + vcap_free_rule(vrule); + return ret; +} + static int sparx5_tc_flower_destroy(struct net_device *ndev, struct flow_cls_offload *fco, struct vcap_admin *admin) { struct sparx5_port *port = netdev_priv(ndev); + int err = -ENOENT, count = 0, rule_id; struct vcap_control *vctrl; - int err = -ENOENT, rule_id; vctrl = port->sparx5->vcap_ctrl; while (true) { rule_id = vcap_lookup_rule_by_cookie(vctrl, fco->cookie); if (rule_id <= 0) break; + if (count == 0) { + /* Resources are attached to the first rule of + * a set of rules. Only works if the rules are + * in the correct order. + */ + err = sparx5_tc_free_rule_resources(ndev, vctrl, + rule_id); + if (err) + pr_err("%s:%d: could not free resources %d\n", + __func__, __LINE__, rule_id); + } err = vcap_del_rule(vctrl, ndev, rule_id); if (err) { pr_err("%s:%d: could not delete rule %d\n", diff --git a/drivers/net/ethernet/microchip/vcap/Makefile b/drivers/net/ethernet/microchip/vcap/Makefile index 0adb8f5a8735..c86f20e6491f 100644 --- a/drivers/net/ethernet/microchip/vcap/Makefile +++ b/drivers/net/ethernet/microchip/vcap/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_VCAP) += vcap.o obj-$(CONFIG_VCAP_KUNIT_TEST) += vcap_model_kunit.o vcap-$(CONFIG_DEBUG_FS) += vcap_api_debugfs.o -vcap-y += vcap_api.o +vcap-y += vcap_api.o vcap_tc.o diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c index 660d7cd92fcc..6307d59f23da 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api.c +++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c @@ -2755,7 +2755,7 @@ int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, EXPORT_SYMBOL_GPL(vcap_rule_get_key_u32); /* Find a client action field in a rule */ -static struct vcap_client_actionfield * +struct vcap_client_actionfield * vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) { struct vcap_rule_internal *ri = (struct vcap_rule_internal *)rule; @@ -2766,6 +2766,7 @@ vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act) return caf; return NULL; } +EXPORT_SYMBOL_GPL(vcap_find_actionfield); /* Check if the actionfield is already in the rule */ static bool vcap_actionfield_unique(struct vcap_rule *rule, diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h index de29540fd190..417af9754bcc 100644 --- a/drivers/net/ethernet/microchip/vcap/vcap_api_client.h +++ b/drivers/net/ethernet/microchip/vcap/vcap_api_client.h @@ -268,4 +268,7 @@ int vcap_rule_mod_action_u32(struct vcap_rule *rule, /* Get a 32 bit key field value and mask from the rule */ int vcap_rule_get_key_u32(struct vcap_rule *rule, enum vcap_key_field key, u32 *value, u32 *mask); + +struct vcap_client_actionfield * +vcap_find_actionfield(struct vcap_rule *rule, enum vcap_action_field act); #endif /* __VCAP_API_CLIENT__ */ diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.c b/drivers/net/ethernet/microchip/vcap/vcap_tc.c new file mode 100644 index 000000000000..09a994a7cec2 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Microchip VCAP TC + * + * Copyright (c) 2023 Microchip Technology Inc. and its subsidiaries. + */ + +#include <net/flow_offload.h> +#include <net/ipv6.h> +#include <net/tcp.h> + +#include "vcap_api_client.h" +#include "vcap_tc.h" + +enum vcap_is2_arp_opcode { + VCAP_IS2_ARP_REQUEST, + VCAP_IS2_ARP_REPLY, + VCAP_IS2_RARP_REQUEST, + VCAP_IS2_RARP_REPLY, +}; + +enum vcap_arp_opcode { + VCAP_ARP_OP_RESERVED, + VCAP_ARP_OP_REQUEST, + VCAP_ARP_OP_REPLY, +}; + +int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st) +{ + enum vcap_key_field smac_key = VCAP_KF_L2_SMAC; + enum vcap_key_field dmac_key = VCAP_KF_L2_DMAC; + struct flow_match_eth_addrs match; + struct vcap_u48_key smac, dmac; + int err = 0; + + flow_rule_match_eth_addrs(st->frule, &match); + + if (!is_zero_ether_addr(match.mask->src)) { + vcap_netbytes_copy(smac.value, match.key->src, ETH_ALEN); + vcap_netbytes_copy(smac.mask, match.mask->src, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, smac_key, &smac); + if (err) + goto out; + } + + if (!is_zero_ether_addr(match.mask->dst)) { + vcap_netbytes_copy(dmac.value, match.key->dst, ETH_ALEN); + vcap_netbytes_copy(dmac.mask, match.mask->dst, ETH_ALEN); + err = vcap_rule_add_key_u48(st->vrule, dmac_key, &dmac); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "eth_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ethaddr_usage); + +int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IP) { + struct flow_match_ipv4_addrs mt; + + flow_rule_match_ipv4_addrs(st->frule, &mt); + if (mt.mask->src) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_SIP, + be32_to_cpu(mt.key->src), + be32_to_cpu(mt.mask->src)); + if (err) + goto out; + } + if (mt.mask->dst) { + err = vcap_rule_add_key_u32(st->vrule, + VCAP_KF_L3_IP4_DIP, + be32_to_cpu(mt.key->dst), + be32_to_cpu(mt.mask->dst)); + if (err) + goto out; + } + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv4_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ipv4_usage); + +int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st) +{ + int err = 0; + + if (st->l3_proto == ETH_P_IPV6) { + struct flow_match_ipv6_addrs mt; + struct vcap_u128_key sip; + struct vcap_u128_key dip; + + flow_rule_match_ipv6_addrs(st->frule, &mt); + /* Check if address masks are non-zero */ + if (!ipv6_addr_any(&mt.mask->src)) { + vcap_netbytes_copy(sip.value, mt.key->src.s6_addr, 16); + vcap_netbytes_copy(sip.mask, mt.mask->src.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_SIP, &sip); + if (err) + goto out; + } + if (!ipv6_addr_any(&mt.mask->dst)) { + vcap_netbytes_copy(dip.value, mt.key->dst.s6_addr, 16); + vcap_netbytes_copy(dip.mask, mt.mask->dst.s6_addr, 16); + err = vcap_rule_add_key_u128(st->vrule, + VCAP_KF_L3_IP6_DIP, &dip); + if (err) + goto out; + } + } + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + return err; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ipv6_addr parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ipv6_usage); + +int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_ports mt; + u16 value, mask; + int err = 0; + + flow_rule_match_ports(st->frule, &mt); + + if (mt.mask->src) { + value = be16_to_cpu(mt.key->src); + mask = be16_to_cpu(mt.mask->src); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_SPORT, value, + mask); + if (err) + goto out; + } + + if (mt.mask->dst) { + value = be16_to_cpu(mt.key->dst); + mask = be16_to_cpu(mt.mask->dst); + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L4_DPORT, value, + mask); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "port parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_portnum_usage); + +int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st) +{ + enum vcap_key_field vid_key = VCAP_KF_8021Q_VID0; + enum vcap_key_field pcp_key = VCAP_KF_8021Q_PCP0; + struct flow_match_vlan mt; + u16 tpid; + int err; + + flow_rule_match_cvlan(st->frule, &mt); + + tpid = be16_to_cpu(mt.key->vlan_tpid); + + if (tpid == ETH_P_8021Q) { + vid_key = VCAP_KF_8021Q_VID1; + pcp_key = VCAP_KF_8021Q_PCP1; + } + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_CVLAN); + + return 0; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "cvlan parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_cvlan_usage); + +int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st, + enum vcap_key_field vid_key, + enum vcap_key_field pcp_key) +{ + struct flow_match_vlan mt; + int err; + + flow_rule_match_vlan(st->frule, &mt); + + if (mt.mask->vlan_id) { + err = vcap_rule_add_key_u32(st->vrule, vid_key, + mt.key->vlan_id, + mt.mask->vlan_id); + if (err) + goto out; + } + + if (mt.mask->vlan_priority) { + err = vcap_rule_add_key_u32(st->vrule, pcp_key, + mt.key->vlan_priority, + mt.mask->vlan_priority); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); + + return 0; +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "vlan parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_vlan_usage); + +int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_tcp mt; + u16 tcp_flags_mask; + u16 tcp_flags_key; + enum vcap_bit val; + int err = 0; + + flow_rule_match_tcp(st->frule, &mt); + tcp_flags_key = be16_to_cpu(mt.key->flags); + tcp_flags_mask = be16_to_cpu(mt.mask->flags); + + if (tcp_flags_mask & TCPHDR_FIN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_FIN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_FIN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_SYN) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_SYN) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_SYN, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_RST) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_RST) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_RST, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_PSH) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_PSH) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_PSH, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_ACK) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_ACK) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_ACK, val); + if (err) + goto out; + } + + if (tcp_flags_mask & TCPHDR_URG) { + val = VCAP_BIT_0; + if (tcp_flags_key & TCPHDR_URG) + val = VCAP_BIT_1; + err = vcap_rule_add_key_bit(st->vrule, VCAP_KF_L4_URG, val); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_TCP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "tcp_flags parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_tcp_usage); + +int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_arp mt; + u16 value, mask; + u32 ipval, ipmsk; + int err; + + flow_rule_match_arp(st->frule, &mt); + + if (mt.mask->op) { + mask = 0x3; + if (st->l3_proto == ETH_P_ARP) { + value = mt.key->op == VCAP_ARP_OP_REQUEST ? + VCAP_IS2_ARP_REQUEST : + VCAP_IS2_ARP_REPLY; + } else { /* RARP */ + value = mt.key->op == VCAP_ARP_OP_REQUEST ? + VCAP_IS2_RARP_REQUEST : + VCAP_IS2_RARP_REPLY; + } + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_ARP_OPCODE, + value, mask); + if (err) + goto out; + } + + /* The IS2 ARP keyset does not support ARP hardware addresses */ + if (!is_zero_ether_addr(mt.mask->sha) || + !is_zero_ether_addr(mt.mask->tha)) { + err = -EINVAL; + goto out; + } + + if (mt.mask->sip) { + ipval = be32_to_cpu((__force __be32)mt.key->sip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->sip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_SIP, + ipval, ipmsk); + if (err) + goto out; + } + + if (mt.mask->tip) { + ipval = be32_to_cpu((__force __be32)mt.key->tip); + ipmsk = be32_to_cpu((__force __be32)mt.mask->tip); + + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_IP4_DIP, + ipval, ipmsk); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_ARP); + + return 0; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "arp parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_arp_usage); + +int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st) +{ + struct flow_match_ip mt; + int err = 0; + + flow_rule_match_ip(st->frule, &mt); + + if (mt.mask->tos) { + err = vcap_rule_add_key_u32(st->vrule, VCAP_KF_L3_TOS, + mt.key->tos, + mt.mask->tos); + if (err) + goto out; + } + + st->used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); + + return err; + +out: + NL_SET_ERR_MSG_MOD(st->fco->common.extack, "ip_tos parse error"); + return err; +} +EXPORT_SYMBOL_GPL(vcap_tc_flower_handler_ip_usage); diff --git a/drivers/net/ethernet/microchip/vcap/vcap_tc.h b/drivers/net/ethernet/microchip/vcap/vcap_tc.h new file mode 100644 index 000000000000..5c55ccbee175 --- /dev/null +++ b/drivers/net/ethernet/microchip/vcap/vcap_tc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Copyright (C) 2023 Microchip Technology Inc. and its subsidiaries. + * Microchip VCAP TC + */ + +#ifndef __VCAP_TC__ +#define __VCAP_TC__ + +struct vcap_tc_flower_parse_usage { + struct flow_cls_offload *fco; + struct flow_rule *frule; + struct vcap_rule *vrule; + struct vcap_admin *admin; + u16 l3_proto; + u8 l4_proto; + unsigned int used_keys; +}; + +int vcap_tc_flower_handler_ethaddr_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ipv4_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ipv6_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_portnum_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_cvlan_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_vlan_usage(struct vcap_tc_flower_parse_usage *st, + enum vcap_key_field vid_key, + enum vcap_key_field pcp_key); +int vcap_tc_flower_handler_tcp_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_arp_usage(struct vcap_tc_flower_parse_usage *st); +int vcap_tc_flower_handler_ip_usage(struct vcap_tc_flower_parse_usage *st); + +#endif /* __VCAP_TC__ */ diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index b144f2237748..f9b8f372ec8a 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1217,9 +1217,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) unsigned int max_queues_per_port = num_online_cpus(); struct gdma_context *gc = pci_get_drvdata(pdev); struct gdma_irq_context *gic; - unsigned int max_irqs; - u16 *cpus; - cpumask_var_t req_mask; + unsigned int max_irqs, cpu; int nvec, irq; int err, i = 0, j; @@ -1240,21 +1238,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) goto free_irq_vector; } - if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) { - err = -ENOMEM; - goto free_irq; - } - - cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL); - if (!cpus) { - err = -ENOMEM; - goto free_mask; - } - for (i = 0; i < nvec; i++) - cpus[i] = cpumask_local_spread(i, gc->numa_node); - for (i = 0; i < nvec; i++) { - cpumask_set_cpu(cpus[i], req_mask); gic = &gc->irq_contexts[i]; gic->handler = NULL; gic->arg = NULL; @@ -1269,17 +1253,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; - goto free_mask; + goto free_irq; } err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); if (err) - goto free_mask; - irq_set_affinity_and_hint(irq, req_mask); - cpumask_clear(req_mask); + goto free_irq; + + cpu = cpumask_local_spread(i, gc->numa_node); + irq_set_affinity_and_hint(irq, cpumask_of(cpu)); } - free_cpumask_var(req_mask); - kfree(cpus); err = mana_gd_alloc_res_map(nvec, &gc->msix_resource); if (err) @@ -1290,13 +1273,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) return 0; -free_mask: - free_cpumask_var(req_mask); - kfree(cpus); free_irq: for (j = i - 1; j >= 0; j--) { irq = pci_irq_vector(pdev, j); gic = &gc->irq_contexts[j]; + + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } @@ -1324,6 +1306,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) continue; gic = &gc->irq_contexts[i]; + + /* Need to clear the hint before free_irq */ + irq_update_affinity_hint(irq, NULL); free_irq(irq, gic); } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 2f6a048dee90..6120f2b6684f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -2160,6 +2160,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, ndev->hw_features |= NETIF_F_RXHASH; ndev->features = ndev->hw_features; ndev->vlan_features = 0; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; err = register_netdev(ndev); if (err) { diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig index 8dd8c7f425d2..81e605691bb8 100644 --- a/drivers/net/ethernet/mscc/Kconfig +++ b/drivers/net/ethernet/mscc/Kconfig @@ -13,6 +13,7 @@ if NET_VENDOR_MICROSEMI # Users should depend on NET_SWITCHDEV, HAS_IOMEM, BRIDGE config MSCC_OCELOT_SWITCH_LIB + depends on PTP_1588_CLOCK_OPTIONAL select NET_DEVLINK select REGMAP_MMIO select PACKING diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7c0897e779dc..ee052404eb55 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -605,6 +605,18 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, flow_rule_match_control(rule, &match); } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + filter->key_type = OCELOT_VCAP_KEY_ANY; + filter->vlan.vid.value = match.key->vlan_id; + filter->vlan.vid.mask = match.mask->vlan_id; + filter->vlan.pcp.value[0] = match.key->vlan_priority; + filter->vlan.pcp.mask[0] = match.mask->vlan_priority; + match_protocol = false; + } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct flow_match_eth_addrs match; @@ -737,18 +749,6 @@ ocelot_flower_parse_key(struct ocelot *ocelot, int port, bool ingress, match_protocol = false; } - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_match_vlan match; - - flow_rule_match_vlan(rule, &match); - filter->key_type = OCELOT_VCAP_KEY_ANY; - filter->vlan.vid.value = match.key->vlan_id; - filter->vlan.vid.mask = match.mask->vlan_id; - filter->vlan.pcp.value[0] = match.key->vlan_priority; - filter->vlan.pcp.mask[0] = match.mask->vlan_priority; - match_protocol = false; - } - finished_key_parsing: if (match_protocol && proto != ETH_P_ALL) { if (filter->block_id == VCAP_ES0) { diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.c b/drivers/net/ethernet/mscc/ocelot_ptp.c index 1a82f10c8853..2180ae94c744 100644 --- a/drivers/net/ethernet/mscc/ocelot_ptp.c +++ b/drivers/net/ethernet/mscc/ocelot_ptp.c @@ -335,8 +335,8 @@ static void ocelot_populate_ipv6_ptp_event_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_EV_PORT; trap->key.ipv6.dport.mask = 0xffff; } @@ -355,8 +355,8 @@ static void ocelot_populate_ipv6_ptp_general_trap_key(struct ocelot_vcap_filter *trap) { trap->key_type = OCELOT_VCAP_KEY_IPV6; - trap->key.ipv4.proto.value[0] = IPPROTO_UDP; - trap->key.ipv4.proto.mask[0] = 0xff; + trap->key.ipv6.proto.value[0] = IPPROTO_UDP; + trap->key.ipv6.proto.mask[0] = 0xff; trap->key.ipv6.dport.value = PTP_GEN_PORT; trap->key.ipv6.dport.mask = 0xffff; } diff --git a/drivers/net/ethernet/mscc/vsc7514_regs.c b/drivers/net/ethernet/mscc/vsc7514_regs.c index da0c0dcc8f81..ef6fd3f6be30 100644 --- a/drivers/net/ethernet/mscc/vsc7514_regs.c +++ b/drivers/net/ethernet/mscc/vsc7514_regs.c @@ -68,7 +68,7 @@ const struct reg_field vsc7514_regfields[REGFIELD_MAX] = { }; EXPORT_SYMBOL(vsc7514_regfields); -const u32 vsc7514_ana_regmap[] = { +static const u32 vsc7514_ana_regmap[] = { REG(ANA_ADVLEARN, 0x009000), REG(ANA_VLANMASK, 0x009004), REG(ANA_PORT_B_DOMAIN, 0x009008), @@ -148,9 +148,8 @@ const u32 vsc7514_ana_regmap[] = { REG(ANA_POL_HYST, 0x008bec), REG(ANA_POL_MISC_CFG, 0x008bf0), }; -EXPORT_SYMBOL(vsc7514_ana_regmap); -const u32 vsc7514_qs_regmap[] = { +static const u32 vsc7514_qs_regmap[] = { REG(QS_XTR_GRP_CFG, 0x000000), REG(QS_XTR_RD, 0x000008), REG(QS_XTR_FRM_PRUNING, 0x000010), @@ -164,9 +163,8 @@ const u32 vsc7514_qs_regmap[] = { REG(QS_INJ_ERR, 0x000040), REG(QS_INH_DBG, 0x000048), }; -EXPORT_SYMBOL(vsc7514_qs_regmap); -const u32 vsc7514_qsys_regmap[] = { +static const u32 vsc7514_qsys_regmap[] = { REG(QSYS_PORT_MODE, 0x011200), REG(QSYS_SWITCH_PORT_MODE, 0x011234), REG(QSYS_STAT_CNT_CFG, 0x011264), @@ -209,9 +207,8 @@ const u32 vsc7514_qsys_regmap[] = { REG(QSYS_SE_STATE, 0x00004c), REG(QSYS_HSCH_MISC_CFG, 0x011388), }; -EXPORT_SYMBOL(vsc7514_qsys_regmap); -const u32 vsc7514_rew_regmap[] = { +static const u32 vsc7514_rew_regmap[] = { REG(REW_PORT_VLAN_CFG, 0x000000), REG(REW_TAG_CFG, 0x000004), REG(REW_PORT_CFG, 0x000008), @@ -224,9 +221,8 @@ const u32 vsc7514_rew_regmap[] = { REG(REW_STAT_CFG, 0x000890), REG(REW_PPT, 0x000680), }; -EXPORT_SYMBOL(vsc7514_rew_regmap); -const u32 vsc7514_sys_regmap[] = { +static const u32 vsc7514_sys_regmap[] = { REG(SYS_COUNT_RX_OCTETS, 0x000000), REG(SYS_COUNT_RX_UNICAST, 0x000004), REG(SYS_COUNT_RX_MULTICAST, 0x000008), @@ -347,9 +343,8 @@ const u32 vsc7514_sys_regmap[] = { REG(SYS_PTP_NXT, 0x0006c0), REG(SYS_PTP_CFG, 0x0006c4), }; -EXPORT_SYMBOL(vsc7514_sys_regmap); -const u32 vsc7514_vcap_regmap[] = { +static const u32 vsc7514_vcap_regmap[] = { /* VCAP_CORE_CFG */ REG(VCAP_CORE_UPDATE_CTRL, 0x000000), REG(VCAP_CORE_MV_CFG, 0x000004), @@ -371,9 +366,8 @@ const u32 vsc7514_vcap_regmap[] = { REG(VCAP_CONST_CORE_CNT, 0x0003b8), REG(VCAP_CONST_IF_CNT, 0x0003bc), }; -EXPORT_SYMBOL(vsc7514_vcap_regmap); -const u32 vsc7514_ptp_regmap[] = { +static const u32 vsc7514_ptp_regmap[] = { REG(PTP_PIN_CFG, 0x000000), REG(PTP_PIN_TOD_SEC_MSB, 0x000004), REG(PTP_PIN_TOD_SEC_LSB, 0x000008), @@ -384,9 +378,8 @@ const u32 vsc7514_ptp_regmap[] = { REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), }; -EXPORT_SYMBOL(vsc7514_ptp_regmap); -const u32 vsc7514_dev_gmii_regmap[] = { +static const u32 vsc7514_dev_gmii_regmap[] = { REG(DEV_CLOCK_CFG, 0x0), REG(DEV_PORT_MISC, 0x4), REG(DEV_EVENTS, 0x8), @@ -427,7 +420,6 @@ const u32 vsc7514_dev_gmii_regmap[] = { REG(DEV_PCS_FX100_CFG, 0x94), REG(DEV_PCS_FX100_STATUS, 0x98), }; -EXPORT_SYMBOL(vsc7514_dev_gmii_regmap); const u32 *vsc7514_regmap[TARGET_MAX] = { [ANA] = vsc7514_ana_regmap, @@ -443,7 +435,7 @@ const u32 *vsc7514_regmap[TARGET_MAX] = { }; EXPORT_SYMBOL(vsc7514_regmap); -const struct vcap_field vsc7514_vcap_es0_keys[] = { +static const struct vcap_field vsc7514_vcap_es0_keys[] = { [VCAP_ES0_EGR_PORT] = { 0, 4 }, [VCAP_ES0_IGR_PORT] = { 4, 4 }, [VCAP_ES0_RSV] = { 8, 2 }, @@ -453,9 +445,8 @@ const struct vcap_field vsc7514_vcap_es0_keys[] = { [VCAP_ES0_DP] = { 24, 1 }, [VCAP_ES0_PCP] = { 25, 3 }, }; -EXPORT_SYMBOL(vsc7514_vcap_es0_keys); -const struct vcap_field vsc7514_vcap_es0_actions[] = { +static const struct vcap_field vsc7514_vcap_es0_actions[] = { [VCAP_ES0_ACT_PUSH_OUTER_TAG] = { 0, 2 }, [VCAP_ES0_ACT_PUSH_INNER_TAG] = { 2, 1 }, [VCAP_ES0_ACT_TAG_A_TPID_SEL] = { 3, 2 }, @@ -475,9 +466,8 @@ const struct vcap_field vsc7514_vcap_es0_actions[] = { [VCAP_ES0_ACT_RSV] = { 49, 24 }, [VCAP_ES0_ACT_HIT_STICKY] = { 73, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_es0_actions); -const struct vcap_field vsc7514_vcap_is1_keys[] = { +static const struct vcap_field vsc7514_vcap_is1_keys[] = { [VCAP_IS1_HK_TYPE] = { 0, 1 }, [VCAP_IS1_HK_LOOKUP] = { 1, 2 }, [VCAP_IS1_HK_IGR_PORT_MASK] = { 3, 12 }, @@ -527,9 +517,8 @@ const struct vcap_field vsc7514_vcap_is1_keys[] = { [VCAP_IS1_HK_IP4_L4_RNG] = { 148, 8 }, [VCAP_IS1_HK_IP4_IP_PAYLOAD_S1_5TUPLE] = { 156, 32 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is1_keys); -const struct vcap_field vsc7514_vcap_is1_actions[] = { +static const struct vcap_field vsc7514_vcap_is1_actions[] = { [VCAP_IS1_ACT_DSCP_ENA] = { 0, 1 }, [VCAP_IS1_ACT_DSCP_VAL] = { 1, 6 }, [VCAP_IS1_ACT_QOS_ENA] = { 7, 1 }, @@ -552,9 +541,8 @@ const struct vcap_field vsc7514_vcap_is1_actions[] = { [VCAP_IS1_ACT_CUSTOM_ACE_TYPE_ENA] = { 74, 4 }, [VCAP_IS1_ACT_HIT_STICKY] = { 78, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is1_actions); -const struct vcap_field vsc7514_vcap_is2_keys[] = { +static const struct vcap_field vsc7514_vcap_is2_keys[] = { /* Common: 46 bits */ [VCAP_IS2_TYPE] = { 0, 4 }, [VCAP_IS2_HK_FIRST] = { 4, 1 }, @@ -633,9 +621,8 @@ const struct vcap_field vsc7514_vcap_is2_keys[] = { [VCAP_IS2_HK_OAM_CCM_CNTS_EQ0] = { 186, 1 }, [VCAP_IS2_HK_OAM_IS_Y1731] = { 187, 1 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is2_keys); -const struct vcap_field vsc7514_vcap_is2_actions[] = { +static const struct vcap_field vsc7514_vcap_is2_actions[] = { [VCAP_IS2_ACT_HIT_ME_ONCE] = { 0, 1 }, [VCAP_IS2_ACT_CPU_COPY_ENA] = { 1, 1 }, [VCAP_IS2_ACT_CPU_QU_NUM] = { 2, 3 }, @@ -652,7 +639,6 @@ const struct vcap_field vsc7514_vcap_is2_actions[] = { [VCAP_IS2_ACT_ACL_ID] = { 43, 6 }, [VCAP_IS2_ACT_HIT_CNT] = { 49, 32 }, }; -EXPORT_SYMBOL(vsc7514_vcap_is2_actions); struct vcap_props vsc7514_vcap_props[] = { [VCAP_ES0] = { diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index c90d35f5ebca..808599b8066e 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -80,7 +80,7 @@ nfp-objs += \ abm/main.o endif -nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o +nfp-$(CONFIG_NFP_NET_IPSEC) += crypto/ipsec.o nfd3/ipsec.o nfdk/ipsec.o nfp-$(CONFIG_NFP_DEBUG) += nfp_net_debugfs.o diff --git a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c index b44263177981..b8bc89fc2540 100644 --- a/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c +++ b/drivers/net/ethernet/netronome/nfp/crypto/ipsec.c @@ -10,6 +10,7 @@ #include <linux/ktime.h> #include <net/xfrm.h> +#include "../nfpcore/nfp_dev.h" #include "../nfp_net_ctrl.h" #include "../nfp_net.h" #include "crypto.h" @@ -330,6 +331,10 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x, trunc_len = -1; break; case SADB_AALG_MD5HMAC: + if (nn->pdev->device == PCI_DEVICE_ID_NFP3800) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported authentication algorithm"); + return -EINVAL; + } set_md5hmac(cfg, &trunc_len); break; case SADB_AALG_SHA1HMAC: @@ -373,6 +378,10 @@ static int nfp_net_xfrm_add_state(struct xfrm_state *x, cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_NULL; break; case SADB_EALG_3DESCBC: + if (nn->pdev->device == PCI_DEVICE_ID_NFP3800) { + NL_SET_ERR_MSG_MOD(extack, "Unsupported encryption algorithm for offload"); + return -EINVAL; + } cfg->ctrl_word.cimode = NFP_IPSEC_CIMODE_CBC; cfg->ctrl_word.cipher = NFP_IPSEC_CIPHER_3DES; break; diff --git a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c index 861082c5dbff..59fb0583cc08 100644 --- a/drivers/net/ethernet/netronome/nfp/nfd3/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfd3/dp.c @@ -192,10 +192,10 @@ static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, return 0; md_bytes = sizeof(meta_id) + - !!md_dst * NFP_NET_META_PORTID_SIZE + - !!tls_handle * NFP_NET_META_CONN_HANDLE_SIZE + - vlan_insert * NFP_NET_META_VLAN_SIZE + - *ipsec * NFP_NET_META_IPSEC_FIELD_SIZE; /* IPsec has 12 bytes of metadata */ + (!!md_dst ? NFP_NET_META_PORTID_SIZE : 0) + + (!!tls_handle ? NFP_NET_META_CONN_HANDLE_SIZE : 0) + + (vlan_insert ? NFP_NET_META_VLAN_SIZE : 0) + + (*ipsec ? NFP_NET_META_IPSEC_FIELD_SIZE : 0); if (unlikely(skb_cow_head(skb, md_bytes))) return -ENOMEM; @@ -226,9 +226,6 @@ static int nfp_nfd3_prep_tx_meta(struct nfp_net_dp *dp, struct sk_buff *skb, meta_id |= NFP_NET_META_VLAN; } if (*ipsec) { - /* IPsec has three consecutive 4-bit IPsec metadata types, - * so in total IPsec has three 4 bytes of metadata. - */ data -= NFP_NET_META_IPSEC_SIZE; put_unaligned_be32(offload_info.seq_hi, data); data -= NFP_NET_META_IPSEC_SIZE; diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c index ccacb6ab6c39..d60c0e991a91 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/dp.c +++ b/drivers/net/ethernet/netronome/nfp/nfdk/dp.c @@ -6,6 +6,7 @@ #include <linux/overflow.h> #include <linux/sizes.h> #include <linux/bitfield.h> +#include <net/xfrm.h> #include "../nfp_app.h" #include "../nfp_net.h" @@ -172,25 +173,32 @@ close_block: static int nfp_nfdk_prep_tx_meta(struct nfp_net_dp *dp, struct nfp_app *app, - struct sk_buff *skb) + struct sk_buff *skb, bool *ipsec) { struct metadata_dst *md_dst = skb_metadata_dst(skb); + struct nfp_ipsec_offload offload_info; unsigned char *data; bool vlan_insert; u32 meta_id = 0; int md_bytes; +#ifdef CONFIG_NFP_NET_IPSEC + if (xfrm_offload(skb)) + *ipsec = nfp_net_ipsec_tx_prep(dp, skb, &offload_info); +#endif + if (unlikely(md_dst && md_dst->type != METADATA_HW_PORT_MUX)) md_dst = NULL; vlan_insert = skb_vlan_tag_present(skb) && (dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN_V2); - if (!(md_dst || vlan_insert)) + if (!(md_dst || vlan_insert || *ipsec)) return 0; md_bytes = sizeof(meta_id) + - !!md_dst * NFP_NET_META_PORTID_SIZE + - vlan_insert * NFP_NET_META_VLAN_SIZE; + (!!md_dst ? NFP_NET_META_PORTID_SIZE : 0) + + (vlan_insert ? NFP_NET_META_VLAN_SIZE : 0) + + (*ipsec ? NFP_NET_META_IPSEC_FIELD_SIZE : 0); if (unlikely(skb_cow_head(skb, md_bytes))) return -ENOMEM; @@ -212,6 +220,17 @@ nfp_nfdk_prep_tx_meta(struct nfp_net_dp *dp, struct nfp_app *app, meta_id |= NFP_NET_META_VLAN; } + if (*ipsec) { + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_hi, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.seq_low, data); + data -= NFP_NET_META_IPSEC_SIZE; + put_unaligned_be32(offload_info.handle - 1, data); + meta_id <<= NFP_NET_META_IPSEC_FIELD_SIZE; + meta_id |= NFP_NET_META_IPSEC << 8 | NFP_NET_META_IPSEC << 4 | NFP_NET_META_IPSEC; + } + meta_id = FIELD_PREP(NFDK_META_LEN, md_bytes) | FIELD_PREP(NFDK_META_FIELDS, meta_id); @@ -243,6 +262,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) struct nfp_net_dp *dp; int nr_frags, wr_idx; dma_addr_t dma_addr; + bool ipsec = false; u64 metadata; dp = &nn->dp; @@ -263,7 +283,7 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - metadata = nfp_nfdk_prep_tx_meta(dp, nn->app, skb); + metadata = nfp_nfdk_prep_tx_meta(dp, nn->app, skb, &ipsec); if (unlikely((int)metadata < 0)) goto err_flush; @@ -361,6 +381,9 @@ netdev_tx_t nfp_nfdk_tx(struct sk_buff *skb, struct net_device *netdev) (txd - 1)->dma_len_type = cpu_to_le16(dlen_type | NFDK_DESC_TX_EOP); + if (ipsec) + metadata = nfp_nfdk_ipsec_tx(metadata, skb); + if (!skb_is_gso(skb)) { real_len = skb->len; /* Metadata desc */ @@ -760,6 +783,15 @@ nfp_nfdk_parse_meta(struct net_device *netdev, struct nfp_meta_parsed *meta, return false; data += sizeof(struct nfp_net_tls_resync_req); break; +#ifdef CONFIG_NFP_NET_IPSEC + case NFP_NET_META_IPSEC: + /* Note: IPsec packet could have zero saidx, so need add 1 + * to indicate packet is IPsec packet within driver. + */ + meta->ipsec_saidx = get_unaligned_be32(data) + 1; + data += 4; + break; +#endif default: return true; } @@ -1186,6 +1218,13 @@ static int nfp_nfdk_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; } +#ifdef CONFIG_NFP_NET_IPSEC + if (meta.ipsec_saidx != 0 && unlikely(nfp_net_ipsec_rx(&meta, skb))) { + nfp_nfdk_rx_drop(dp, r_vec, rx_ring, NULL, skb); + continue; + } +#endif + if (meta_len_xdp) skb_metadata_set(skb, meta_len_xdp); diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c b/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c new file mode 100644 index 000000000000..58d8f59eb885 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/nfdk/ipsec.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2023 Corigine, Inc */ + +#include <net/xfrm.h> + +#include "../nfp_net.h" +#include "nfdk.h" + +u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb) +{ + struct xfrm_state *x = xfrm_input_state(skb); + + if (x->xso.dev && (x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)) + flags |= NFDK_DESC_TX_L3_CSUM | NFDK_DESC_TX_L4_CSUM; + + return flags; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h b/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h index 0ea51d9f2325..fe55980348e9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h +++ b/drivers/net/ethernet/netronome/nfp/nfdk/nfdk.h @@ -125,4 +125,12 @@ nfp_nfdk_ctrl_tx_one(struct nfp_net *nn, struct nfp_net_r_vector *r_vec, void nfp_nfdk_ctrl_poll(struct tasklet_struct *t); void nfp_nfdk_rx_ring_fill_freelist(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring); +#ifndef CONFIG_NFP_NET_IPSEC +static inline u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb) +{ + return flags; +} +#else +u64 nfp_nfdk_ipsec_tx(u64 flags, struct sk_buff *skb); +#endif #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 18fc9971f1c8..e4825d885560 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2529,10 +2529,15 @@ static void nfp_net_netdev_init(struct nfp_net *nn) netdev->features &= ~NETIF_F_HW_VLAN_STAG_RX; nn->dp.ctrl &= ~NFP_NET_CFG_CTRL_RXQINQ; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC; + if (nn->app && nn->app->type->id == NFP_APP_BPF_NIC) + netdev->xdp_features |= NETDEV_XDP_ACT_HW_OFFLOAD; + /* Finalise the netdev setup */ switch (nn->dp.ops->version) { case NFP_NFD_VER_NFD3: netdev->netdev_ops = &nfp_nfd3_netdev_ops; + netdev->xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; break; case NFP_NFD_VER_NFDK: netdev->netdev_ops = &nfp_nfdk_netdev_ops; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index e9d228d7a95d..918319f965b3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -293,35 +293,131 @@ nfp_net_set_fec_link_mode(struct nfp_eth_table_port *eth_port, } } -static const u16 nfp_eth_media_table[] = { - [NFP_MEDIA_1000BASE_CX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_1000BASE_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - [NFP_MEDIA_10GBASE_KX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - [NFP_MEDIA_10GBASE_CX4] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - [NFP_MEDIA_10GBASE_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, - [NFP_MEDIA_10GBASE_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - [NFP_MEDIA_10GBASE_ER] = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, - [NFP_MEDIA_25GBASE_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_KR_S] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - [NFP_MEDIA_25GBASE_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_CR_S] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - [NFP_MEDIA_25GBASE_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - [NFP_MEDIA_40GBASE_CR4] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, - [NFP_MEDIA_40GBASE_KR4] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, - [NFP_MEDIA_40GBASE_SR4] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, - [NFP_MEDIA_40GBASE_LR4] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, - [NFP_MEDIA_50GBASE_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, - [NFP_MEDIA_50GBASE_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, - [NFP_MEDIA_50GBASE_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, - [NFP_MEDIA_50GBASE_LR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_ER] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_50GBASE_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - [NFP_MEDIA_100GBASE_KR4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_SR4] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR4] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, - [NFP_MEDIA_100GBASE_KP4] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - [NFP_MEDIA_100GBASE_CR10] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, +static const struct nfp_eth_media_link_mode { + u16 ethtool_link_mode; + u16 speed; +} nfp_eth_media_table[NFP_MEDIA_LINK_MODES_NUMBER] = { + [NFP_MEDIA_1000BASE_CX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_1000BASE_KX] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + .speed = NFP_SPEED_1G, + }, + [NFP_MEDIA_10GBASE_KX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CX4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_10GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + .speed = NFP_SPEED_10G, + }, + [NFP_MEDIA_25GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_KR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_CR_S] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_25GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + .speed = NFP_SPEED_25G, + }, + [NFP_MEDIA_40GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_40GBASE_LR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + .speed = NFP_SPEED_40G, + }, + [NFP_MEDIA_50GBASE_KR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_SR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_CR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_LR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_ER] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_50GBASE_FR] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + .speed = NFP_SPEED_50G, + }, + [NFP_MEDIA_100GBASE_KR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_SR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_KP4] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, + [NFP_MEDIA_100GBASE_CR10] = { + .ethtool_link_mode = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + .speed = NFP_SPEED_100G, + }, +}; + +static const unsigned int nfp_eth_speed_map[NFP_SUP_SPEED_NUMBER] = { + [NFP_SPEED_1G] = SPEED_1000, + [NFP_SPEED_10G] = SPEED_10000, + [NFP_SPEED_25G] = SPEED_25000, + [NFP_SPEED_40G] = SPEED_40000, + [NFP_SPEED_50G] = SPEED_50000, + [NFP_SPEED_100G] = SPEED_100000, }; static void nfp_add_media_link_mode(struct nfp_port *port, @@ -334,8 +430,12 @@ static void nfp_add_media_link_mode(struct nfp_port *port, }; struct nfp_cpp *cpp = port->app->cpp; - if (nfp_eth_read_media(cpp, ðm)) + if (nfp_eth_read_media(cpp, ðm)) { + bitmap_fill(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); return; + } + + bitmap_zero(port->speed_bitmap, NFP_SUP_SPEED_NUMBER); for (u32 i = 0; i < 2; i++) { supported_modes[i] = le64_to_cpu(ethm.supported_modes[i]); @@ -344,20 +444,26 @@ static void nfp_add_media_link_mode(struct nfp_port *port, for (u32 i = 0; i < NFP_MEDIA_LINK_MODES_NUMBER; i++) { if (i < 64) { - if (supported_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[0] & BIT_ULL(i)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[0] & BIT_ULL(i)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } else { - if (supported_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + if (supported_modes[1] & BIT_ULL(i - 64)) { + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.supported); + __set_bit(nfp_eth_media_table[i].speed, + port->speed_bitmap); + } if (advertised_modes[1] & BIT_ULL(i - 64)) - __set_bit(nfp_eth_media_table[i], + __set_bit(nfp_eth_media_table[i].ethtool_link_mode, cmd->link_modes.advertising); } } @@ -468,6 +574,22 @@ nfp_net_set_link_ksettings(struct net_device *netdev, if (cmd->base.speed != SPEED_UNKNOWN) { u32 speed = cmd->base.speed / eth_port->lanes; + bool is_supported = false; + + for (u32 i = 0; i < NFP_SUP_SPEED_NUMBER; i++) { + if (cmd->base.speed == nfp_eth_speed_map[i] && + test_bit(i, port->speed_bitmap)) { + is_supported = true; + break; + } + } + + if (!is_supported) { + netdev_err(netdev, "Speed %u is not supported.\n", + cmd->base.speed); + err = -EINVAL; + goto err_bad_set; + } if (req_aneg) { netdev_err(netdev, "Speed changing is not allowed when working on autoneg mode.\n"); @@ -1908,12 +2030,12 @@ nfp_net_get_eeprom(struct net_device *netdev, struct nfp_app *app = nfp_app_from_netdev(netdev); u8 buf[NFP_EEPROM_LEN] = {}; - if (eeprom->len == 0) - return -EINVAL; - if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) return -EOPNOTSUPP; + if (eeprom->len == 0) + return -EINVAL; + eeprom->magic = app->pdev->vendor | (app->pdev->device << 16); memcpy(bytes, buf + eeprom->offset, eeprom->len); @@ -1927,15 +2049,15 @@ nfp_net_set_eeprom(struct net_device *netdev, struct nfp_app *app = nfp_app_from_netdev(netdev); u8 buf[NFP_EEPROM_LEN] = {}; + if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) + return -EOPNOTSUPP; + if (eeprom->len == 0) return -EINVAL; if (eeprom->magic != (app->pdev->vendor | app->pdev->device << 16)) return -EINVAL; - if (nfp_net_get_port_mac_by_hwinfo(netdev, buf)) - return -EOPNOTSUPP; - memcpy(buf + eeprom->offset, bytes, eeprom->len); if (nfp_net_set_port_mac_by_hwinfo(netdev, buf)) return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index f8cd157ca1d7..9c04f9f0e2c9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -38,6 +38,16 @@ enum nfp_port_flags { NFP_PORT_CHANGED = 0, }; +enum { + NFP_SPEED_1G, + NFP_SPEED_10G, + NFP_SPEED_25G, + NFP_SPEED_40G, + NFP_SPEED_50G, + NFP_SPEED_100G, + NFP_SUP_SPEED_NUMBER +}; + /** * struct nfp_port - structure representing NFP port * @netdev: backpointer to associated netdev @@ -52,6 +62,7 @@ enum nfp_port_flags { * @eth_forced: for %NFP_PORT_PHYS_PORT port is forced UP or DOWN, don't change * @eth_port: for %NFP_PORT_PHYS_PORT translated ETH Table port entry * @eth_stats: for %NFP_PORT_PHYS_PORT MAC stats if available + * @speed_bitmap: for %NFP_PORT_PHYS_PORT supported speed bitmap * @pf_id: for %NFP_PORT_PF_PORT, %NFP_PORT_VF_PORT ID of the PCI PF (0-3) * @vf_id: for %NFP_PORT_VF_PORT ID of the PCI VF within @pf_id * @pf_split: for %NFP_PORT_PF_PORT %true if PCI PF has more than one vNIC @@ -78,6 +89,7 @@ struct nfp_port { bool eth_forced; struct nfp_eth_table_port *eth_port; u8 __iomem *eth_stats; + DECLARE_BITMAP(speed_bitmap, NFP_SUP_SPEED_NUMBER); }; /* NFP_PORT_PF_PORT, NFP_PORT_VF_PORT */ struct { diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 626b9113e7c4..d911f4fd9af6 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -708,9 +708,16 @@ void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, q->lif->index, q->name, q->hw_type, q->hw_index, q->head_idx, ring_doorbell); - if (ring_doorbell) + if (ring_doorbell) { ionic_dbell_ring(lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_jiffies = jiffies; + + if (q_to_qcq(q)->napi_qcq) + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + } } static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h index 2a1d7b9c07e7..bce3ca38669b 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -25,6 +25,12 @@ #define IONIC_DEV_INFO_REG_COUNT 32 #define IONIC_DEV_CMD_REG_COUNT 32 +#define IONIC_NAPI_DEADLINE (HZ / 200) /* 5ms */ +#define IONIC_ADMIN_DOORBELL_DEADLINE (HZ / 2) /* 500ms */ +#define IONIC_TX_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MIN_DOORBELL_DEADLINE (HZ / 100) /* 10ms */ +#define IONIC_RX_MAX_DOORBELL_DEADLINE (HZ * 5) /* 5s */ + struct ionic_dev_bar { void __iomem *vaddr; phys_addr_t bus_addr; @@ -216,6 +222,8 @@ struct ionic_queue { struct ionic_lif *lif; struct ionic_desc_info *info; u64 dbval; + unsigned long dbell_deadline; + unsigned long dbell_jiffies; u16 head_idx; u16 tail_idx; unsigned int index; @@ -361,4 +369,8 @@ void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, int ionic_heartbeat_check(struct ionic *ionic); bool ionic_is_fw_running(struct ionic_dev *idev); +bool ionic_adminq_poke_doorbell(struct ionic_queue *q); +bool ionic_txq_poke_doorbell(struct ionic_queue *q); +bool ionic_rxq_poke_doorbell(struct ionic_queue *q); + #endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 4dd16c487f2b..63a78a9ac241 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -16,6 +16,7 @@ #include "ionic.h" #include "ionic_bus.h" +#include "ionic_dev.h" #include "ionic_lif.h" #include "ionic_txrx.h" #include "ionic_ethtool.h" @@ -200,6 +201,13 @@ void ionic_link_status_check_request(struct ionic_lif *lif, bool can_sleep) } } +static void ionic_napi_deadline(struct timer_list *timer) +{ + struct ionic_qcq *qcq = container_of(timer, struct ionic_qcq, napi_deadline); + + napi_schedule(&qcq->napi); +} + static irqreturn_t ionic_isr(int irq, void *data) { struct napi_struct *napi = data; @@ -269,6 +277,7 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) .oper = IONIC_Q_ENABLE, }, }; + int ret; idev = &lif->ionic->idev; dev = lif->ionic->dev; @@ -276,16 +285,24 @@ static int ionic_qcq_enable(struct ionic_qcq *qcq) dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", ctx.cmd.q_control.index, ctx.cmd.q_control.type); + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + + ret = ionic_adminq_post_wait(lif, &ctx); + if (ret) + return ret; + + if (qcq->napi.poll) + napi_enable(&qcq->napi); + if (qcq->flags & IONIC_QCQ_F_INTR) { irq_set_affinity_hint(qcq->intr.vector, &qcq->intr.affinity_mask); - napi_enable(&qcq->napi); - ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, IONIC_INTR_MASK_CLEAR); } - return ionic_adminq_post_wait(lif, &ctx); + return 0; } static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int fw_err) @@ -316,6 +333,7 @@ static int ionic_qcq_disable(struct ionic_lif *lif, struct ionic_qcq *qcq, int f synchronize_irq(qcq->intr.vector); irq_set_affinity_hint(qcq->intr.vector, NULL); napi_disable(&qcq->napi); + del_timer_sync(&qcq->napi_deadline); } /* If there was a previous fw communcation error, don't bother with @@ -451,6 +469,7 @@ static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, n_qcq->intr.vector = src_qcq->intr.vector; n_qcq->intr.index = src_qcq->intr.index; + n_qcq->napi_qcq = src_qcq->napi_qcq; } static int ionic_alloc_qcq_interrupt(struct ionic_lif *lif, struct ionic_qcq *qcq) @@ -564,13 +583,15 @@ static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, } if (flags & IONIC_QCQ_F_NOTIFYQ) { - int q_size, cq_size; + int q_size; - /* q & cq need to be contiguous in case of notifyq */ + /* q & cq need to be contiguous in NotifyQ, so alloc it all in q + * and don't alloc qc. We leave new->qc_size and new->qc_base + * as 0 to be sure we don't try to free it later. + */ q_size = ALIGN(num_descs * desc_size, PAGE_SIZE); - cq_size = ALIGN(num_descs * cq_desc_size, PAGE_SIZE); - - new->q_size = PAGE_SIZE + q_size + cq_size; + new->q_size = PAGE_SIZE + q_size + + ALIGN(num_descs * cq_desc_size, PAGE_SIZE); new->q_base = dma_alloc_coherent(dev, new->q_size, &new->q_base_pa, GFP_KERNEL); if (!new->q_base) { @@ -773,8 +794,14 @@ static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); - if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) + q->dbell_deadline = IONIC_TX_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) { netif_napi_add(lif->netdev, &qcq->napi, ionic_tx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + } qcq->flags |= IONIC_QCQ_F_INITED; @@ -828,11 +855,17 @@ static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + if (test_bit(IONIC_LIF_F_SPLIT_INTR, lif->state)) netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi); else netif_napi_add(lif->netdev, &qcq->napi, ionic_txrx_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + qcq->flags |= IONIC_QCQ_F_INITED; return 0; @@ -1150,6 +1183,7 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) struct ionic_dev *idev = &lif->ionic->idev; unsigned long irqflags; unsigned int flags = 0; + bool resched = false; int rx_work = 0; int tx_work = 0; int n_work = 0; @@ -1187,6 +1221,16 @@ static int ionic_adminq_napi(struct napi_struct *napi, int budget) ionic_intr_credits(idev->intr_ctrl, intr->index, credits, flags); } + if (!a_work && ionic_adminq_poke_doorbell(&lif->adminqcq->q)) + resched = true; + if (lif->hwstamp_rxq && !rx_work && ionic_rxq_poke_doorbell(&lif->hwstamp_rxq->q)) + resched = true; + if (lif->hwstamp_txq && !tx_work && ionic_txq_poke_doorbell(&lif->hwstamp_txq->q)) + resched = true; + if (resched) + mod_timer(&lif->adminqcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -3245,8 +3289,14 @@ static int ionic_lif_adminq_init(struct ionic_lif *lif) dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + q->dbell_deadline = IONIC_ADMIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi); + qcq->napi_qcq = qcq; + timer_setup(&qcq->napi_deadline, ionic_napi_deadline, 0); + napi_enable(&qcq->napi); if (qcq->flags & IONIC_QCQ_F_INTR) diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index a53984bf3544..734519895614 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -74,8 +74,10 @@ struct ionic_qcq { struct ionic_queue q; struct ionic_cq cq; struct ionic_intr_info intr; + struct timer_list napi_deadline; struct napi_struct napi; unsigned int flags; + struct ionic_qcq *napi_qcq; struct dentry *dentry; }; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index a13530ec4dd8..08c42b039d92 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -289,6 +289,35 @@ static void ionic_adminq_cb(struct ionic_queue *q, complete_all(&ctx->work); } +bool ionic_adminq_poke_doorbell(struct ionic_queue *q) +{ + struct ionic_lif *lif = q->lif; + unsigned long now, then, dif; + unsigned long irqflags; + + spin_lock_irqsave(&lif->adminq_lock, irqflags); + + if (q->tail_idx == q->head_idx) { + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + spin_unlock_irqrestore(&lif->adminq_lock, irqflags); + + return true; +} + int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) { struct ionic_desc_info *desc_info; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 0c3977416cd1..f761780f0162 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -22,6 +22,67 @@ static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, ionic_q_post(q, ring_dbell, cb_func, cb_arg); } +bool ionic_txq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + struct netdev_queue *netdev_txq; + struct net_device *netdev; + + netdev = q->lif->netdev; + netdev_txq = netdev_get_tx_queue(netdev, q->index); + + HARD_TX_LOCK(netdev, netdev_txq, smp_processor_id()); + + if (q->tail_idx == q->head_idx) { + HARD_TX_UNLOCK(netdev, netdev_txq); + return false; + } + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + } + + HARD_TX_UNLOCK(netdev, netdev_txq); + + return true; +} + +bool ionic_rxq_poke_doorbell(struct ionic_queue *q) +{ + unsigned long now, then, dif; + + /* no lock, called from rx napi or txrx napi, nothing else can fill */ + + if (q->tail_idx == q->head_idx) + return false; + + now = READ_ONCE(jiffies); + then = q->dbell_jiffies; + dif = now - then; + + if (dif > q->dbell_deadline) { + ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, + q->dbval | q->head_idx); + + q->dbell_jiffies = now; + + dif = 2 * q->dbell_deadline; + if (dif > IONIC_RX_MAX_DOORBELL_DEADLINE) + dif = IONIC_RX_MAX_DOORBELL_DEADLINE; + + q->dbell_deadline = dif; + } + + return true; +} + static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) { return netdev_get_tx_queue(q->lif->netdev, q->index); @@ -424,6 +485,12 @@ void ionic_rx_fill(struct ionic_queue *q) ionic_dbell_ring(q->lif->kern_dbpage, q->hw_type, q->dbval | q->head_idx); + + q->dbell_deadline = IONIC_RX_MIN_DOORBELL_DEADLINE; + q->dbell_jiffies = jiffies; + + mod_timer(&q_to_qcq(q)->napi_qcq->napi_deadline, + jiffies + IONIC_NAPI_DEADLINE); } void ionic_rx_empty(struct ionic_queue *q) @@ -511,6 +578,9 @@ int ionic_tx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_txq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } @@ -544,23 +614,29 @@ int ionic_rx_napi(struct napi_struct *napi, int budget) work_done, flags); } + if (!work_done && ionic_rxq_poke_doorbell(&qcq->q)) + mod_timer(&qcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return work_done; } int ionic_txrx_napi(struct napi_struct *napi, int budget) { - struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_qcq *rxqcq = napi_to_qcq(napi); struct ionic_cq *rxcq = napi_to_cq(napi); unsigned int qi = rxcq->bound_q->index; + struct ionic_qcq *txqcq; struct ionic_dev *idev; struct ionic_lif *lif; struct ionic_cq *txcq; + bool resched = false; u32 rx_work_done = 0; u32 tx_work_done = 0; u32 flags = 0; lif = rxcq->bound_q->lif; idev = &lif->ionic->idev; + txqcq = lif->txqcqs[qi]; txcq = &lif->txqcqs[qi]->cq; tx_work_done = ionic_cq_service(txcq, IONIC_TX_BUDGET_DEFAULT, @@ -572,7 +648,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) ionic_rx_fill(rxcq->bound_q); if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) { - ionic_dim_update(qcq, 0); + ionic_dim_update(rxqcq, 0); flags |= IONIC_INTR_CRED_UNMASK; rxcq->bound_intr->rearm_count++; } @@ -583,6 +659,13 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget) tx_work_done + rx_work_done, flags); } + if (!rx_work_done && ionic_rxq_poke_doorbell(&rxqcq->q)) + resched = true; + if (!tx_work_done && ionic_txq_poke_doorbell(&txqcq->q)) + resched = true; + if (resched) + mod_timer(&rxqcq->napi_deadline, jiffies + IONIC_NAPI_DEADLINE); + return rx_work_done; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 953f304b8588..b6d999927e86 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -892,6 +892,9 @@ static void qede_init_ndev(struct qede_dev *edev) ndev->hw_features = hw_features; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + /* MTU range: 46 - 9600 */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE; diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 50b61a0a7f53..853394e5bb8b 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -123,13 +123,6 @@ static void rswitch_fwd_init(struct rswitch_private *priv) iowrite32(GENMASK(RSWITCH_NUM_PORTS - 1, 0), priv->addr + FWPBFC(priv->gwca.index)); } -/* gPTP timer (gPTP) */ -static void rswitch_get_timestamp(struct rswitch_private *priv, - struct timespec64 *ts) -{ - priv->ptp_priv->info.gettime64(&priv->ptp_priv->info, ts); -} - /* Gateway CPU agent block (GWCA) */ static int rswitch_gwca_change_mode(struct rswitch_private *priv, enum rswitch_gwca_mode mode) @@ -240,7 +233,7 @@ static int rswitch_get_num_cur_queues(struct rswitch_gwca_queue *gq) static bool rswitch_is_queue_rxed(struct rswitch_gwca_queue *gq) { - struct rswitch_ext_ts_desc *desc = &gq->ts_ring[gq->dirty]; + struct rswitch_ext_ts_desc *desc = &gq->rx_ring[gq->dirty]; if ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) return true; @@ -280,36 +273,43 @@ static void rswitch_gwca_queue_free(struct net_device *ndev, { int i; - if (gq->gptp) { + if (!gq->dir_tx) { dma_free_coherent(ndev->dev.parent, sizeof(struct rswitch_ext_ts_desc) * - (gq->ring_size + 1), gq->ts_ring, gq->ring_dma); - gq->ts_ring = NULL; - } else { - dma_free_coherent(ndev->dev.parent, - sizeof(struct rswitch_ext_desc) * - (gq->ring_size + 1), gq->ring, gq->ring_dma); - gq->ring = NULL; - } + (gq->ring_size + 1), gq->rx_ring, gq->ring_dma); + gq->rx_ring = NULL; - if (!gq->dir_tx) { for (i = 0; i < gq->ring_size; i++) dev_kfree_skb(gq->skbs[i]); + } else { + dma_free_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_desc) * + (gq->ring_size + 1), gq->tx_ring, gq->ring_dma); + gq->tx_ring = NULL; } kfree(gq->skbs); gq->skbs = NULL; } +static void rswitch_gwca_ts_queue_free(struct rswitch_private *priv) +{ + struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; + + dma_free_coherent(&priv->pdev->dev, + sizeof(struct rswitch_ts_desc) * (gq->ring_size + 1), + gq->ts_ring, gq->ring_dma); + gq->ts_ring = NULL; +} + static int rswitch_gwca_queue_alloc(struct net_device *ndev, struct rswitch_private *priv, struct rswitch_gwca_queue *gq, - bool dir_tx, bool gptp, int ring_size) + bool dir_tx, int ring_size) { int i, bit; gq->dir_tx = dir_tx; - gq->gptp = gptp; gq->ring_size = ring_size; gq->ndev = ndev; @@ -317,18 +317,19 @@ static int rswitch_gwca_queue_alloc(struct net_device *ndev, if (!gq->skbs) return -ENOMEM; - if (!dir_tx) + if (!dir_tx) { rswitch_gwca_queue_alloc_skb(gq, 0, gq->ring_size); - if (gptp) - gq->ts_ring = dma_alloc_coherent(ndev->dev.parent, + gq->rx_ring = dma_alloc_coherent(ndev->dev.parent, sizeof(struct rswitch_ext_ts_desc) * (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); - else - gq->ring = dma_alloc_coherent(ndev->dev.parent, - sizeof(struct rswitch_ext_desc) * - (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); - if (!gq->ts_ring && !gq->ring) + } else { + gq->tx_ring = dma_alloc_coherent(ndev->dev.parent, + sizeof(struct rswitch_ext_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + } + + if (!gq->rx_ring && !gq->tx_ring) goto out; i = gq->index / 32; @@ -346,6 +347,17 @@ out: return -ENOMEM; } +static int rswitch_gwca_ts_queue_alloc(struct rswitch_private *priv) +{ + struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; + + gq->ring_size = TS_RING_SIZE; + gq->ts_ring = dma_alloc_coherent(&priv->pdev->dev, + sizeof(struct rswitch_ts_desc) * + (gq->ring_size + 1), &gq->ring_dma, GFP_KERNEL); + return !gq->ts_ring ? -ENOMEM : 0; +} + static void rswitch_desc_set_dptr(struct rswitch_desc *desc, dma_addr_t addr) { desc->dptrl = cpu_to_le32(lower_32_bits(addr)); @@ -361,14 +373,14 @@ static int rswitch_gwca_queue_format(struct net_device *ndev, struct rswitch_private *priv, struct rswitch_gwca_queue *gq) { - int tx_ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size; + int ring_size = sizeof(struct rswitch_ext_desc) * gq->ring_size; struct rswitch_ext_desc *desc; struct rswitch_desc *linkfix; dma_addr_t dma_addr; int i; - memset(gq->ring, 0, tx_ring_size); - for (i = 0, desc = gq->ring; i < gq->ring_size; i++, desc++) { + memset(gq->tx_ring, 0, ring_size); + for (i = 0, desc = gq->tx_ring; i < gq->ring_size; i++, desc++) { if (!gq->dir_tx) { dma_addr = dma_map_single(ndev->dev.parent, gq->skbs[i]->data, PKT_BUF_SZ, @@ -386,7 +398,7 @@ static int rswitch_gwca_queue_format(struct net_device *ndev, rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); desc->desc.die_dt = DT_LINKFIX; - linkfix = &priv->linkfix_table[gq->index]; + linkfix = &priv->gwca.linkfix_table[gq->index]; linkfix->die_dt = DT_LINKFIX; rswitch_desc_set_dptr(linkfix, gq->ring_dma); @@ -397,7 +409,7 @@ static int rswitch_gwca_queue_format(struct net_device *ndev, err: if (!gq->dir_tx) { - for (i--, desc = gq->ring; i >= 0; i--, desc++) { + for (i--, desc = gq->tx_ring; i >= 0; i--, desc++) { dma_addr = rswitch_desc_get_dptr(&desc->desc); dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE); @@ -407,9 +419,23 @@ err: return -ENOMEM; } -static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, - struct rswitch_gwca_queue *gq, - int start_index, int num) +static void rswitch_gwca_ts_queue_fill(struct rswitch_private *priv, + int start_index, int num) +{ + struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; + struct rswitch_ts_desc *desc; + int i, index; + + for (i = 0; i < num; i++) { + index = (i + start_index) % gq->ring_size; + desc = &gq->ts_ring[index]; + desc->desc.die_dt = DT_FEMPTY_ND | DIE; + } +} + +static int rswitch_gwca_queue_ext_ts_fill(struct net_device *ndev, + struct rswitch_gwca_queue *gq, + int start_index, int num) { struct rswitch_device *rdev = netdev_priv(ndev); struct rswitch_ext_ts_desc *desc; @@ -418,7 +444,7 @@ static int rswitch_gwca_queue_ts_fill(struct net_device *ndev, for (i = 0; i < num; i++) { index = (i + start_index) % gq->ring_size; - desc = &gq->ts_ring[index]; + desc = &gq->rx_ring[index]; if (!gq->dir_tx) { dma_addr = dma_map_single(ndev->dev.parent, gq->skbs[index]->data, PKT_BUF_SZ, @@ -442,7 +468,7 @@ err: if (!gq->dir_tx) { for (i--; i >= 0; i--) { index = (i + start_index) % gq->ring_size; - desc = &gq->ts_ring[index]; + desc = &gq->rx_ring[index]; dma_addr = rswitch_desc_get_dptr(&desc->desc); dma_unmap_single(ndev->dev.parent, dma_addr, PKT_BUF_SZ, DMA_FROM_DEVICE); @@ -452,25 +478,25 @@ err: return -ENOMEM; } -static int rswitch_gwca_queue_ts_format(struct net_device *ndev, - struct rswitch_private *priv, - struct rswitch_gwca_queue *gq) +static int rswitch_gwca_queue_ext_ts_format(struct net_device *ndev, + struct rswitch_private *priv, + struct rswitch_gwca_queue *gq) { - int tx_ts_ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size; + int ring_size = sizeof(struct rswitch_ext_ts_desc) * gq->ring_size; struct rswitch_ext_ts_desc *desc; struct rswitch_desc *linkfix; int err; - memset(gq->ts_ring, 0, tx_ts_ring_size); - err = rswitch_gwca_queue_ts_fill(ndev, gq, 0, gq->ring_size); + memset(gq->rx_ring, 0, ring_size); + err = rswitch_gwca_queue_ext_ts_fill(ndev, gq, 0, gq->ring_size); if (err < 0) return err; - desc = &gq->ts_ring[gq->ring_size]; /* Last */ + desc = &gq->rx_ring[gq->ring_size]; /* Last */ rswitch_desc_set_dptr(&desc->desc, gq->ring_dma); desc->desc.die_dt = DT_LINKFIX; - linkfix = &priv->linkfix_table[gq->index]; + linkfix = &priv->gwca.linkfix_table[gq->index]; linkfix->die_dt = DT_LINKFIX; rswitch_desc_set_dptr(linkfix, gq->ring_dma); @@ -480,28 +506,31 @@ static int rswitch_gwca_queue_ts_format(struct net_device *ndev, return 0; } -static int rswitch_gwca_desc_alloc(struct rswitch_private *priv) +static int rswitch_gwca_linkfix_alloc(struct rswitch_private *priv) { int i, num_queues = priv->gwca.num_queues; + struct rswitch_gwca *gwca = &priv->gwca; struct device *dev = &priv->pdev->dev; - priv->linkfix_table_size = sizeof(struct rswitch_desc) * num_queues; - priv->linkfix_table = dma_alloc_coherent(dev, priv->linkfix_table_size, - &priv->linkfix_table_dma, GFP_KERNEL); - if (!priv->linkfix_table) + gwca->linkfix_table_size = sizeof(struct rswitch_desc) * num_queues; + gwca->linkfix_table = dma_alloc_coherent(dev, gwca->linkfix_table_size, + &gwca->linkfix_table_dma, GFP_KERNEL); + if (!gwca->linkfix_table) return -ENOMEM; for (i = 0; i < num_queues; i++) - priv->linkfix_table[i].die_dt = DT_EOS; + gwca->linkfix_table[i].die_dt = DT_EOS; return 0; } -static void rswitch_gwca_desc_free(struct rswitch_private *priv) +static void rswitch_gwca_linkfix_free(struct rswitch_private *priv) { - if (priv->linkfix_table) - dma_free_coherent(&priv->pdev->dev, priv->linkfix_table_size, - priv->linkfix_table, priv->linkfix_table_dma); - priv->linkfix_table = NULL; + struct rswitch_gwca *gwca = &priv->gwca; + + if (gwca->linkfix_table) + dma_free_coherent(&priv->pdev->dev, gwca->linkfix_table_size, + gwca->linkfix_table, gwca->linkfix_table_dma); + gwca->linkfix_table = NULL; } static struct rswitch_gwca_queue *rswitch_gwca_get(struct rswitch_private *priv) @@ -536,8 +565,7 @@ static int rswitch_txdmac_alloc(struct net_device *ndev) if (!rdev->tx_queue) return -EBUSY; - err = rswitch_gwca_queue_alloc(ndev, priv, rdev->tx_queue, true, false, - TX_RING_SIZE); + err = rswitch_gwca_queue_alloc(ndev, priv, rdev->tx_queue, true, TX_RING_SIZE); if (err < 0) { rswitch_gwca_put(priv, rdev->tx_queue); return err; @@ -571,8 +599,7 @@ static int rswitch_rxdmac_alloc(struct net_device *ndev) if (!rdev->rx_queue) return -EBUSY; - err = rswitch_gwca_queue_alloc(ndev, priv, rdev->rx_queue, false, true, - RX_RING_SIZE); + err = rswitch_gwca_queue_alloc(ndev, priv, rdev->rx_queue, false, RX_RING_SIZE); if (err < 0) { rswitch_gwca_put(priv, rdev->rx_queue); return err; @@ -594,7 +621,7 @@ static int rswitch_rxdmac_init(struct rswitch_private *priv, int index) struct rswitch_device *rdev = priv->rdev[index]; struct net_device *ndev = rdev->ndev; - return rswitch_gwca_queue_ts_format(ndev, priv, rdev->rx_queue); + return rswitch_gwca_queue_ext_ts_format(ndev, priv, rdev->rx_queue); } static int rswitch_gwca_hw_init(struct rswitch_private *priv) @@ -617,8 +644,11 @@ static int rswitch_gwca_hw_init(struct rswitch_private *priv) iowrite32(GWVCC_VEM_SC_TAG, priv->addr + GWVCC); iowrite32(0, priv->addr + GWTTFC); - iowrite32(lower_32_bits(priv->linkfix_table_dma), priv->addr + GWDCBAC1); - iowrite32(upper_32_bits(priv->linkfix_table_dma), priv->addr + GWDCBAC0); + iowrite32(lower_32_bits(priv->gwca.linkfix_table_dma), priv->addr + GWDCBAC1); + iowrite32(upper_32_bits(priv->gwca.linkfix_table_dma), priv->addr + GWDCBAC0); + iowrite32(lower_32_bits(priv->gwca.ts_queue.ring_dma), priv->addr + GWTDCAC10); + iowrite32(upper_32_bits(priv->gwca.ts_queue.ring_dma), priv->addr + GWTDCAC00); + iowrite32(GWCA_TS_IRQ_BIT, priv->addr + GWTSDCC0); rswitch_gwca_set_rate_limit(priv, priv->gwca.speed); for (i = 0; i < RSWITCH_NUM_PORTS; i++) { @@ -675,7 +705,7 @@ static bool rswitch_rx(struct net_device *ndev, int *quota) boguscnt = min_t(int, gq->ring_size, *quota); limit = boguscnt; - desc = &gq->ts_ring[gq->cur]; + desc = &gq->rx_ring[gq->cur]; while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY) { if (--boguscnt < 0) break; @@ -703,14 +733,14 @@ static bool rswitch_rx(struct net_device *ndev, int *quota) rdev->ndev->stats.rx_bytes += pkt_len; gq->cur = rswitch_next_queue_index(gq, true, 1); - desc = &gq->ts_ring[gq->cur]; + desc = &gq->rx_ring[gq->cur]; } num = rswitch_get_num_cur_queues(gq); ret = rswitch_gwca_queue_alloc_skb(gq, gq->dirty, num); if (ret < 0) goto err; - ret = rswitch_gwca_queue_ts_fill(ndev, gq, gq->dirty, num); + ret = rswitch_gwca_queue_ext_ts_fill(ndev, gq, gq->dirty, num); if (ret < 0) goto err; gq->dirty = rswitch_next_queue_index(gq, false, num); @@ -737,7 +767,7 @@ static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only) for (; rswitch_get_num_cur_queues(gq) > 0; gq->dirty = rswitch_next_queue_index(gq, false, 1)) { - desc = &gq->ring[gq->dirty]; + desc = &gq->tx_ring[gq->dirty]; if (free_txed_only && (desc->desc.die_dt & DT_MASK) != DT_FEMPTY) break; @@ -745,15 +775,6 @@ static int rswitch_tx_free(struct net_device *ndev, bool free_txed_only) size = le16_to_cpu(desc->desc.info_ds) & TX_DS; skb = gq->skbs[gq->dirty]; if (skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { - struct skb_shared_hwtstamps shhwtstamps; - struct timespec64 ts; - - rswitch_get_timestamp(rdev->priv, &ts); - memset(&shhwtstamps, 0, sizeof(shhwtstamps)); - shhwtstamps.hwtstamp = timespec64_to_ktime(ts); - skb_tstamp_tx(skb, &shhwtstamps); - } dma_addr = rswitch_desc_get_dptr(&desc->desc); dma_unmap_single(ndev->dev.parent, dma_addr, size, DMA_TO_DEVICE); @@ -879,6 +900,73 @@ static int rswitch_gwca_request_irqs(struct rswitch_private *priv) return 0; } +static void rswitch_ts(struct rswitch_private *priv) +{ + struct rswitch_gwca_queue *gq = &priv->gwca.ts_queue; + struct rswitch_gwca_ts_info *ts_info, *ts_info2; + struct skb_shared_hwtstamps shhwtstamps; + struct rswitch_ts_desc *desc; + struct timespec64 ts; + u32 tag, port; + int num; + + desc = &gq->ts_ring[gq->cur]; + while ((desc->desc.die_dt & DT_MASK) != DT_FEMPTY_ND) { + dma_rmb(); + + port = TS_DESC_DPN(__le32_to_cpu(desc->desc.dptrl)); + tag = TS_DESC_TSUN(__le32_to_cpu(desc->desc.dptrl)); + + list_for_each_entry_safe(ts_info, ts_info2, &priv->gwca.ts_info_list, list) { + if (!(ts_info->port == port && ts_info->tag == tag)) + continue; + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + ts.tv_sec = __le32_to_cpu(desc->ts_sec); + ts.tv_nsec = __le32_to_cpu(desc->ts_nsec & cpu_to_le32(0x3fffffff)); + shhwtstamps.hwtstamp = timespec64_to_ktime(ts); + skb_tstamp_tx(ts_info->skb, &shhwtstamps); + dev_consume_skb_irq(ts_info->skb); + list_del(&ts_info->list); + kfree(ts_info); + break; + } + + gq->cur = rswitch_next_queue_index(gq, true, 1); + desc = &gq->ts_ring[gq->cur]; + } + + num = rswitch_get_num_cur_queues(gq); + rswitch_gwca_ts_queue_fill(priv, gq->dirty, num); + gq->dirty = rswitch_next_queue_index(gq, false, num); +} + +static irqreturn_t rswitch_gwca_ts_irq(int irq, void *dev_id) +{ + struct rswitch_private *priv = dev_id; + + if (ioread32(priv->addr + GWTSDIS) & GWCA_TS_IRQ_BIT) { + iowrite32(GWCA_TS_IRQ_BIT, priv->addr + GWTSDIS); + rswitch_ts(priv); + + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static int rswitch_gwca_ts_request_irqs(struct rswitch_private *priv) +{ + int irq; + + irq = platform_get_irq_byname(priv->pdev, GWCA_TS_IRQ_RESOURCE_NAME); + if (irq < 0) + return irq; + + return devm_request_irq(&priv->pdev->dev, irq, rswitch_gwca_ts_irq, + 0, GWCA_TS_IRQ_NAME, priv); +} + /* Ethernet TSN Agent block (ETHA) and Ethernet MAC IP block (RMAC) */ static int rswitch_etha_change_mode(struct rswitch_etha *etha, enum rswitch_etha_mode mode) @@ -1349,15 +1437,28 @@ static int rswitch_open(struct net_device *ndev) rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, true); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, true); + iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDIE); + return 0; }; static int rswitch_stop(struct net_device *ndev) { struct rswitch_device *rdev = netdev_priv(ndev); + struct rswitch_gwca_ts_info *ts_info, *ts_info2; netif_tx_stop_all_queues(ndev); + iowrite32(GWCA_TS_IRQ_BIT, rdev->priv->addr + GWTSDID); + + list_for_each_entry_safe(ts_info, ts_info2, &rdev->priv->gwca.ts_info_list, list) { + if (ts_info->port != rdev->port) + continue; + dev_kfree_skb_irq(ts_info->skb); + list_del(&ts_info->list); + kfree(ts_info); + } + rswitch_enadis_data_irq(rdev->priv, rdev->tx_queue->index, false); rswitch_enadis_data_irq(rdev->priv, rdev->rx_queue->index, false); @@ -1390,17 +1491,31 @@ static netdev_tx_t rswitch_start_xmit(struct sk_buff *skb, struct net_device *nd } gq->skbs[gq->cur] = skb; - desc = &gq->ring[gq->cur]; + desc = &gq->tx_ring[gq->cur]; rswitch_desc_set_dptr(&desc->desc, dma_addr); desc->desc.info_ds = cpu_to_le16(skb->len); desc->info1 = cpu_to_le64(INFO1_DV(BIT(rdev->etha->index)) | INFO1_FMT); if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { + struct rswitch_gwca_ts_info *ts_info; + + ts_info = kzalloc(sizeof(*ts_info), GFP_ATOMIC); + if (!ts_info) { + dma_unmap_single(ndev->dev.parent, dma_addr, skb->len, DMA_TO_DEVICE); + return -ENOMEM; + } + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; rdev->ts_tag++; desc->info1 |= cpu_to_le64(INFO1_TSUN(rdev->ts_tag) | INFO1_TXC); + + ts_info->skb = skb_get(skb); + ts_info->port = rdev->port; + ts_info->tag = rdev->ts_tag; + list_add_tail(&ts_info->list, &rdev->priv->gwca.ts_info_list); + + skb_tx_timestamp(skb); } - skb_tx_timestamp(skb); dma_wmb(); @@ -1650,10 +1765,17 @@ static int rswitch_init(struct rswitch_private *priv) if (err < 0) return err; - err = rswitch_gwca_desc_alloc(priv); + err = rswitch_gwca_linkfix_alloc(priv); if (err < 0) return -ENOMEM; + err = rswitch_gwca_ts_queue_alloc(priv); + if (err < 0) + goto err_ts_queue_alloc; + + rswitch_gwca_ts_queue_fill(priv, 0, TS_RING_SIZE); + INIT_LIST_HEAD(&priv->gwca.ts_info_list); + for (i = 0; i < RSWITCH_NUM_PORTS; i++) { err = rswitch_device_alloc(priv, i); if (err < 0) { @@ -1674,6 +1796,10 @@ static int rswitch_init(struct rswitch_private *priv) if (err < 0) goto err_gwca_request_irq; + err = rswitch_gwca_ts_request_irqs(priv); + if (err < 0) + goto err_gwca_ts_request_irq; + err = rswitch_gwca_hw_init(priv); if (err < 0) goto err_gwca_hw_init; @@ -1704,6 +1830,7 @@ err_ether_port_init_all: rswitch_gwca_hw_deinit(priv); err_gwca_hw_init: +err_gwca_ts_request_irq: err_gwca_request_irq: rcar_gen4_ptp_unregister(priv->ptp_priv); @@ -1712,7 +1839,10 @@ err_ptp_register: rswitch_device_free(priv, i); err_device_alloc: - rswitch_gwca_desc_free(priv); + rswitch_gwca_ts_queue_free(priv); + +err_ts_queue_alloc: + rswitch_gwca_linkfix_free(priv); return err; } @@ -1791,7 +1921,8 @@ static void rswitch_deinit(struct rswitch_private *priv) rswitch_device_free(priv, i); } - rswitch_gwca_desc_free(priv); + rswitch_gwca_ts_queue_free(priv); + rswitch_gwca_linkfix_free(priv); rswitch_clock_disable(priv); } diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 59830ab91a69..27d3d38c055f 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -27,6 +27,7 @@ #define TX_RING_SIZE 1024 #define RX_RING_SIZE 1024 +#define TS_RING_SIZE (TX_RING_SIZE * RSWITCH_NUM_PORTS) #define PKT_BUF_SZ 1584 #define RSWITCH_ALIGN 128 @@ -49,6 +50,10 @@ #define AGENT_INDEX_GWCA 3 #define GWRO RSWITCH_GWCA0_OFFSET +#define GWCA_TS_IRQ_RESOURCE_NAME "gwca0_rxts0" +#define GWCA_TS_IRQ_NAME "rswitch: gwca0_rxts0" +#define GWCA_TS_IRQ_BIT BIT(0) + #define FWRO 0 #define TPRO RSWITCH_TOP_OFFSET #define CARO RSWITCH_COMA_OFFSET @@ -831,7 +836,7 @@ enum DIE_DT { DT_FSINGLE = 0x80, DT_FSTART = 0x90, DT_FMID = 0xa0, - DT_FEND = 0xb8, + DT_FEND = 0xb0, /* Chain control */ DT_LEMPTY = 0xc0, @@ -843,7 +848,7 @@ enum DIE_DT { DT_FEMPTY = 0x40, DT_FEMPTY_IS = 0x10, DT_FEMPTY_IC = 0x20, - DT_FEMPTY_ND = 0x38, + DT_FEMPTY_ND = 0x30, DT_FEMPTY_START = 0x50, DT_FEMPTY_MID = 0x60, DT_FEMPTY_END = 0x70, @@ -865,6 +870,12 @@ enum DIE_DT { /* For reception */ #define INFO1_SPN(port) ((u64)(port) << 36ULL) +/* For timestamp descriptor in dptrl (Byte 4 to 7) */ +#define TS_DESC_TSUN(dptrl) ((dptrl) & GENMASK(7, 0)) +#define TS_DESC_SPN(dptrl) (((dptrl) & GENMASK(10, 8)) >> 8) +#define TS_DESC_DPN(dptrl) (((dptrl) & GENMASK(17, 16)) >> 16) +#define TS_DESC_TN(dptrl) ((dptrl) & BIT(24)) + struct rswitch_desc { __le16 info_ds; /* Descriptor size */ u8 die_dt; /* Descriptor interrupt enable and type */ @@ -911,27 +922,43 @@ struct rswitch_etha { * name, this driver calls "queue". */ struct rswitch_gwca_queue { - int index; - bool dir_tx; - bool gptp; union { - struct rswitch_ext_desc *ring; - struct rswitch_ext_ts_desc *ts_ring; + struct rswitch_ext_desc *tx_ring; + struct rswitch_ext_ts_desc *rx_ring; + struct rswitch_ts_desc *ts_ring; }; + + /* Common */ dma_addr_t ring_dma; int ring_size; int cur; int dirty; - struct sk_buff **skbs; + /* For [rt]_ring */ + int index; + bool dir_tx; + struct sk_buff **skbs; struct net_device *ndev; /* queue to ndev for irq */ }; +struct rswitch_gwca_ts_info { + struct sk_buff *skb; + struct list_head list; + + int port; + u8 tag; +}; + #define RSWITCH_NUM_IRQ_REGS (RSWITCH_MAX_NUM_QUEUES / BITS_PER_TYPE(u32)) struct rswitch_gwca { int index; + struct rswitch_desc *linkfix_table; + dma_addr_t linkfix_table_dma; + u32 linkfix_table_size; struct rswitch_gwca_queue *queues; int num_queues; + struct rswitch_gwca_queue ts_queue; + struct list_head ts_info_list; DECLARE_BITMAP(used, RSWITCH_MAX_NUM_QUEUES); u32 tx_irq_bits[RSWITCH_NUM_IRQ_REGS]; u32 rx_irq_bits[RSWITCH_NUM_IRQ_REGS]; @@ -969,9 +996,6 @@ struct rswitch_private { struct platform_device *pdev; void __iomem *addr; struct rcar_gen4_ptp_private *ptp_priv; - struct rswitch_desc *linkfix_table; - dma_addr_t linkfix_table_dma; - u32 linkfix_table_size; struct rswitch_device *rdev[RSWITCH_NUM_PORTS]; diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 3a86f1213a05..02c2adeb0a12 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1028,6 +1028,10 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; net_dev->features |= efx->fixed_features; + net_dev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + rc = efx_register_netdev(efx); if (!rc) return 0; diff --git a/drivers/net/ethernet/sfc/siena/efx.c b/drivers/net/ethernet/sfc/siena/efx.c index 60e5b7c8ccf9..ef52ec71d197 100644 --- a/drivers/net/ethernet/sfc/siena/efx.c +++ b/drivers/net/ethernet/sfc/siena/efx.c @@ -1007,6 +1007,10 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) net_dev->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; net_dev->features |= efx->fixed_features; + net_dev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + rc = efx_register_netdev(efx); if (!rc) return 0; diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 9b46579b5a10..2d7347b71c41 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -2104,6 +2104,9 @@ static int netsec_probe(struct platform_device *pdev) NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; ndev->hw_features = ndev->features; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + priv->rx_cksum_offload_flag = true; ret = netsec_register_mdio(priv, phy_addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 592b4067f9b8..16a7421715cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -567,6 +567,7 @@ struct tc_cbs_qopt_offload; struct flow_cls_offload; struct tc_taprio_qopt_offload; struct tc_etf_qopt_offload; +struct tc_query_caps_base; struct stmmac_tc_ops { int (*init)(struct stmmac_priv *priv); @@ -580,6 +581,8 @@ struct stmmac_tc_ops { struct tc_taprio_qopt_offload *qopt); int (*setup_etf)(struct stmmac_priv *priv, struct tc_etf_qopt_offload *qopt); + int (*query_caps)(struct stmmac_priv *priv, + struct tc_query_caps_base *base); }; #define stmmac_tc_init(__priv, __args...) \ @@ -594,6 +597,8 @@ struct stmmac_tc_ops { stmmac_do_callback(__priv, tc, setup_taprio, __args) #define stmmac_tc_setup_etf(__priv, __args...) \ stmmac_do_callback(__priv, tc, setup_etf, __args) +#define stmmac_tc_query_caps(__priv, __args...) \ + stmmac_do_callback(__priv, tc, query_caps, __args) struct stmmac_counters; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 1a5b8dab5e9b..868f59ec8439 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5992,6 +5992,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type, struct stmmac_priv *priv = netdev_priv(ndev); switch (type) { + case TC_QUERY_CAPS: + return stmmac_tc_query_caps(priv, priv, type_data); case TC_SETUP_BLOCK: return flow_block_cb_setup_simple(type_data, &stmmac_block_cb_list, @@ -7151,6 +7153,8 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; ret = stmmac_tc_init(priv, priv); if (!ret) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 2cfb18cef1d4..9d55226479b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -1107,6 +1107,25 @@ static int tc_setup_etf(struct stmmac_priv *priv, return 0; } +static int tc_query_caps(struct stmmac_priv *priv, + struct tc_query_caps_base *base) +{ + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!priv->dma_cap.estsel) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + const struct stmmac_tc_ops dwmac510_tc_ops = { .init = tc_init, .setup_cls_u32 = tc_setup_cls_u32, @@ -1114,4 +1133,5 @@ const struct stmmac_tc_ops dwmac510_tc_ops = { .setup_cls = tc_setup_cls, .setup_taprio = tc_setup_taprio, .setup_etf = tc_setup_etf, + .query_caps = tc_query_caps, }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index e162771893af..8dc2c3085dcf 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -585,6 +585,26 @@ static int am65_cpsw_setup_taprio(struct net_device *ndev, void *type_data) return am65_cpsw_set_taprio(ndev, type_data); } +static int am65_cpsw_tc_query_caps(struct net_device *ndev, void *type_data) +{ + struct tc_query_caps_base *base = type_data; + + switch (base->type) { + case TC_SETUP_QDISC_TAPRIO: { + struct tc_taprio_caps *caps = base->caps; + + if (!IS_ENABLED(CONFIG_TI_AM65_CPSW_TAS)) + return -EOPNOTSUPP; + + caps->gate_mask_per_txq = true; + + return 0; + } + default: + return -EOPNOTSUPP; + } +} + static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port, struct netlink_ext_ack *extack, struct flow_cls_offload *cls, @@ -765,6 +785,8 @@ int am65_cpsw_qos_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type, void *type_data) { switch (type) { + case TC_QUERY_CAPS: + return am65_cpsw_tc_query_caps(ndev, type_data); case TC_SETUP_QDISC_TAPRIO: return am65_cpsw_setup_taprio(ndev, type_data); case TC_SETUP_BLOCK: diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 13c9c2d6b79b..37f0b62ec5d6 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1458,6 +1458,8 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv) priv_sl2->emac_port = 1; cpsw->slaves[1].ndev = ndev; ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; @@ -1635,6 +1637,8 @@ static int cpsw_probe(struct platform_device *pdev) cpsw->slaves[0].ndev = ndev; ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 83596ec0c7cb..35128dd45ffc 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1405,6 +1405,10 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_NETNS_LOCAL | NETIF_F_HW_TC; + ndev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + ndev->netdev_ops = &cpsw_netdev_ops; ndev->ethtool_ops = &cpsw_ethtool_ops; SET_NETDEV_DEV(ndev, dev); diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 758295c898ac..e966dd47e2db 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -20,6 +20,7 @@ #include <linux/skbuff.h> #include <net/page_pool.h> #include <net/pkt_cls.h> +#include <net/pkt_sched.h> #include "cpsw.h" #include "cpts.h" diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig index 0922beac3ec0..c9d88673d306 100644 --- a/drivers/net/ethernet/wangxun/Kconfig +++ b/drivers/net/ethernet/wangxun/Kconfig @@ -18,6 +18,7 @@ if NET_VENDOR_WANGXUN config LIBWX tristate + select PAGE_POOL help Common library for Wangxun(R) Ethernet drivers. diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile index 1ed5e23af944..850d1615cd18 100644 --- a/drivers/net/ethernet/wangxun/libwx/Makefile +++ b/drivers/net/ethernet/wangxun/libwx/Makefile @@ -4,4 +4,4 @@ obj-$(CONFIG_LIBWX) += libwx.o -libwx-objs := wx_hw.o +libwx-objs := wx_hw.o wx_lib.o diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index 3d7ba0c0df38..7db57f934a91 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -8,13 +8,14 @@ #include <linux/pci.h> #include "wx_type.h" +#include "wx_lib.h" #include "wx_hw.h" static void wx_intr_disable(struct wx *wx, u64 qmask) { u32 mask; - mask = (qmask & 0xFFFFFFFF); + mask = (qmask & U32_MAX); if (mask) wr32(wx, WX_PX_IMS(0), mask); @@ -25,6 +26,45 @@ static void wx_intr_disable(struct wx *wx, u64 qmask) } } +void wx_intr_enable(struct wx *wx, u64 qmask) +{ + u32 mask; + + mask = (qmask & U32_MAX); + if (mask) + wr32(wx, WX_PX_IMC(0), mask); + if (wx->mac.type == wx_mac_sp) { + mask = (qmask >> 32); + if (mask) + wr32(wx, WX_PX_IMC(1), mask); + } +} +EXPORT_SYMBOL(wx_intr_enable); + +/** + * wx_irq_disable - Mask off interrupt generation on the NIC + * @wx: board private structure + **/ +void wx_irq_disable(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + wr32(wx, WX_PX_MISC_IEN, 0); + wx_intr_disable(wx, WX_INTR_ALL); + + if (pdev->msix_enabled) { + int vector; + + for (vector = 0; vector < wx->num_q_vectors; vector++) + synchronize_irq(wx->msix_entries[vector].vector); + + synchronize_irq(wx->msix_entries[vector].vector); + } else { + synchronize_irq(pdev->irq); + } +} +EXPORT_SYMBOL(wx_irq_disable); + /* cmd_addr is used for some special command: * 1. to be sector address, when implemented erase sector command * 2. to be flash address when implemented read, write flash address @@ -765,6 +805,37 @@ void wx_flush_sw_mac_table(struct wx *wx) } EXPORT_SYMBOL(wx_flush_sw_mac_table); +static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool) +{ + u32 i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) { + if (ether_addr_equal(addr, wx->mac_table[i].addr)) { + if (wx->mac_table[i].pools != (1ULL << pool)) { + memcpy(wx->mac_table[i].addr, addr, ETH_ALEN); + wx->mac_table[i].pools |= (1ULL << pool); + wx_sync_mac_table(wx); + return i; + } + } + } + + if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) + continue; + wx->mac_table[i].state |= (WX_MAC_STATE_MODIFIED | + WX_MAC_STATE_IN_USE); + memcpy(wx->mac_table[i].addr, addr, ETH_ALEN); + wx->mac_table[i].pools |= (1ULL << pool); + wx_sync_mac_table(wx); + return i; + } + return -ENOMEM; +} + static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool) { u32 i; @@ -789,6 +860,184 @@ static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool) return -ENOMEM; } +static int wx_available_rars(struct wx *wx) +{ + u32 i, count = 0; + + for (i = 0; i < wx->mac.num_rar_entries; i++) { + if (wx->mac_table[i].state == 0) + count++; + } + + return count; +} + +/** + * wx_write_uc_addr_list - write unicast addresses to RAR table + * @netdev: network interface device structure + * @pool: index for mac table + * + * Writes unicast address list to the RAR table. + * Returns: -ENOMEM on failure/insufficient address space + * 0 on no addresses written + * X on writing X addresses to the RAR table + **/ +static int wx_write_uc_addr_list(struct net_device *netdev, int pool) +{ + struct wx *wx = netdev_priv(netdev); + int count = 0; + + /* return ENOMEM indicating insufficient memory for addresses */ + if (netdev_uc_count(netdev) > wx_available_rars(wx)) + return -ENOMEM; + + if (!netdev_uc_empty(netdev)) { + struct netdev_hw_addr *ha; + + netdev_for_each_uc_addr(ha, netdev) { + wx_del_mac_filter(wx, ha->addr, pool); + wx_add_mac_filter(wx, ha->addr, pool); + count++; + } + } + return count; +} + +/** + * wx_mta_vector - Determines bit-vector in multicast table to set + * @wx: pointer to private structure + * @mc_addr: the multicast address + * + * Extracts the 12 bits, from a multicast address, to determine which + * bit-vector to set in the multicast table. The hardware uses 12 bits, from + * incoming rx multicast addresses, to determine the bit-vector to check in + * the MTA. Which of the 4 combination, of 12-bits, the hardware uses is set + * by the MO field of the MCSTCTRL. The MO field is set during initialization + * to mc_filter_type. + **/ +static u32 wx_mta_vector(struct wx *wx, u8 *mc_addr) +{ + u32 vector = 0; + + switch (wx->mac.mc_filter_type) { + case 0: /* use bits [47:36] of the address */ + vector = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4)); + break; + case 1: /* use bits [46:35] of the address */ + vector = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5)); + break; + case 2: /* use bits [45:34] of the address */ + vector = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6)); + break; + case 3: /* use bits [43:32] of the address */ + vector = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8)); + break; + default: /* Invalid mc_filter_type */ + wx_err(wx, "MC filter type param set incorrectly\n"); + break; + } + + /* vector can only be 12-bits or boundary will be exceeded */ + vector &= 0xFFF; + return vector; +} + +/** + * wx_set_mta - Set bit-vector in multicast table + * @wx: pointer to private structure + * @mc_addr: Multicast address + * + * Sets the bit-vector in the multicast table. + **/ +static void wx_set_mta(struct wx *wx, u8 *mc_addr) +{ + u32 vector, vector_bit, vector_reg; + + wx->addr_ctrl.mta_in_use++; + + vector = wx_mta_vector(wx, mc_addr); + wx_dbg(wx, " bit-vector = 0x%03X\n", vector); + + /* The MTA is a register array of 128 32-bit registers. It is treated + * like an array of 4096 bits. We want to set bit + * BitArray[vector_value]. So we figure out what register the bit is + * in, read it, OR in the new bit, then write back the new value. The + * register is determined by the upper 7 bits of the vector value and + * the bit within that register are determined by the lower 5 bits of + * the value. + */ + vector_reg = (vector >> 5) & 0x7F; + vector_bit = vector & 0x1F; + wx->mac.mta_shadow[vector_reg] |= (1 << vector_bit); +} + +/** + * wx_update_mc_addr_list - Updates MAC list of multicast addresses + * @wx: pointer to private structure + * @netdev: pointer to net device structure + * + * The given list replaces any existing list. Clears the MC addrs from receive + * address registers and the multicast table. Uses unused receive address + * registers for the first multicast addresses, and hashes the rest into the + * multicast table. + **/ +static void wx_update_mc_addr_list(struct wx *wx, struct net_device *netdev) +{ + struct netdev_hw_addr *ha; + u32 i, psrctl; + + /* Set the new number of MC addresses that we are being requested to + * use. + */ + wx->addr_ctrl.num_mc_addrs = netdev_mc_count(netdev); + wx->addr_ctrl.mta_in_use = 0; + + /* Clear mta_shadow */ + wx_dbg(wx, " Clearing MTA\n"); + memset(&wx->mac.mta_shadow, 0, sizeof(wx->mac.mta_shadow)); + + /* Update mta_shadow */ + netdev_for_each_mc_addr(ha, netdev) { + wx_dbg(wx, " Adding the multicast addresses:\n"); + wx_set_mta(wx, ha->addr); + } + + /* Enable mta */ + for (i = 0; i < wx->mac.mcft_size; i++) + wr32a(wx, WX_PSR_MC_TBL(0), i, + wx->mac.mta_shadow[i]); + + if (wx->addr_ctrl.mta_in_use > 0) { + psrctl = rd32(wx, WX_PSR_CTL); + psrctl &= ~(WX_PSR_CTL_MO | WX_PSR_CTL_MFE); + psrctl |= WX_PSR_CTL_MFE | + (wx->mac.mc_filter_type << WX_PSR_CTL_MO_SHIFT); + wr32(wx, WX_PSR_CTL, psrctl); + } + + wx_dbg(wx, "Update mc addr list Complete\n"); +} + +/** + * wx_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int wx_write_mc_addr_list(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + + if (!netif_running(netdev)) + return 0; + + wx_update_mc_addr_list(wx, netdev); + + return netdev_mc_count(netdev); +} + /** * wx_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -844,6 +1093,430 @@ void wx_disable_rx(struct wx *wx) } EXPORT_SYMBOL(wx_disable_rx); +static void wx_enable_rx(struct wx *wx) +{ + u32 psrctl; + + /* enable mac receiver */ + wr32m(wx, WX_MAC_RX_CFG, + WX_MAC_RX_CFG_RE, WX_MAC_RX_CFG_RE); + + wr32m(wx, WX_RDB_PB_CTL, + WX_RDB_PB_CTL_RXEN, WX_RDB_PB_CTL_RXEN); + + if (wx->mac.set_lben) { + psrctl = rd32(wx, WX_PSR_CTL); + psrctl |= WX_PSR_CTL_SW_EN; + wr32(wx, WX_PSR_CTL, psrctl); + wx->mac.set_lben = false; + } +} + +/** + * wx_set_rxpba - Initialize Rx packet buffer + * @wx: pointer to private structure + **/ +static void wx_set_rxpba(struct wx *wx) +{ + u32 rxpktsize, txpktsize, txpbthresh; + + rxpktsize = wx->mac.rx_pb_size << WX_RDB_PB_SZ_SHIFT; + wr32(wx, WX_RDB_PB_SZ(0), rxpktsize); + + /* Only support an equally distributed Tx packet buffer strategy. */ + txpktsize = wx->mac.tx_pb_size; + txpbthresh = (txpktsize / 1024) - WX_TXPKT_SIZE_MAX; + wr32(wx, WX_TDB_PB_SZ(0), txpktsize); + wr32(wx, WX_TDM_PB_THRE(0), txpbthresh); +} + +static void wx_configure_port(struct wx *wx) +{ + u32 value, i; + + value = WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ; + wr32m(wx, WX_CFG_PORT_CTL, + WX_CFG_PORT_CTL_D_VLAN | + WX_CFG_PORT_CTL_QINQ, + value); + + wr32(wx, WX_CFG_TAG_TPID(0), + ETH_P_8021Q | ETH_P_8021AD << 16); + wx->tpid[0] = ETH_P_8021Q; + wx->tpid[1] = ETH_P_8021AD; + for (i = 1; i < 4; i++) + wr32(wx, WX_CFG_TAG_TPID(i), + ETH_P_8021Q | ETH_P_8021Q << 16); + for (i = 2; i < 8; i++) + wx->tpid[i] = ETH_P_8021Q; +} + +/** + * wx_disable_sec_rx_path - Stops the receive data path + * @wx: pointer to private structure + * + * Stops the receive data path and waits for the HW to internally empty + * the Rx security block + **/ +static int wx_disable_sec_rx_path(struct wx *wx) +{ + u32 secrx; + + wr32m(wx, WX_RSC_CTL, + WX_RSC_CTL_RX_DIS, WX_RSC_CTL_RX_DIS); + + return read_poll_timeout(rd32, secrx, secrx & WX_RSC_ST_RSEC_RDY, + 1000, 40000, false, wx, WX_RSC_ST); +} + +/** + * wx_enable_sec_rx_path - Enables the receive data path + * @wx: pointer to private structure + * + * Enables the receive data path. + **/ +static void wx_enable_sec_rx_path(struct wx *wx) +{ + wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_RX_DIS, 0); + WX_WRITE_FLUSH(wx); +} + +void wx_set_rx_mode(struct net_device *netdev) +{ + struct wx *wx = netdev_priv(netdev); + u32 fctrl, vmolr, vlnctrl; + int count; + + /* Check for Promiscuous and All Multicast modes */ + fctrl = rd32(wx, WX_PSR_CTL); + fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE); + vmolr = rd32(wx, WX_PSR_VM_L2CTL(0)); + vmolr &= ~(WX_PSR_VM_L2CTL_UPE | + WX_PSR_VM_L2CTL_MPE | + WX_PSR_VM_L2CTL_ROPE | + WX_PSR_VM_L2CTL_ROMPE); + vlnctrl = rd32(wx, WX_PSR_VLAN_CTL); + vlnctrl &= ~(WX_PSR_VLAN_CTL_VFE | WX_PSR_VLAN_CTL_CFIEN); + + /* set all bits that we expect to always be set */ + fctrl |= WX_PSR_CTL_BAM | WX_PSR_CTL_MFE; + vmolr |= WX_PSR_VM_L2CTL_BAM | + WX_PSR_VM_L2CTL_AUPE | + WX_PSR_VM_L2CTL_VACC; + vlnctrl |= WX_PSR_VLAN_CTL_VFE; + + wx->addr_ctrl.user_set_promisc = false; + if (netdev->flags & IFF_PROMISC) { + wx->addr_ctrl.user_set_promisc = true; + fctrl |= WX_PSR_CTL_UPE | WX_PSR_CTL_MPE; + /* pf don't want packets routing to vf, so clear UPE */ + vmolr |= WX_PSR_VM_L2CTL_MPE; + vlnctrl &= ~WX_PSR_VLAN_CTL_VFE; + } + + if (netdev->flags & IFF_ALLMULTI) { + fctrl |= WX_PSR_CTL_MPE; + vmolr |= WX_PSR_VM_L2CTL_MPE; + } + + if (netdev->features & NETIF_F_RXALL) { + vmolr |= (WX_PSR_VM_L2CTL_UPE | WX_PSR_VM_L2CTL_MPE); + vlnctrl &= ~WX_PSR_VLAN_CTL_VFE; + /* receive bad packets */ + wr32m(wx, WX_RSC_CTL, + WX_RSC_CTL_SAVE_MAC_ERR, + WX_RSC_CTL_SAVE_MAC_ERR); + } else { + vmolr |= WX_PSR_VM_L2CTL_ROPE | WX_PSR_VM_L2CTL_ROMPE; + } + + /* Write addresses to available RAR registers, if there is not + * sufficient space to store all the addresses then enable + * unicast promiscuous mode + */ + count = wx_write_uc_addr_list(netdev, 0); + if (count < 0) { + vmolr &= ~WX_PSR_VM_L2CTL_ROPE; + vmolr |= WX_PSR_VM_L2CTL_UPE; + } + + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = wx_write_mc_addr_list(netdev); + if (count < 0) { + vmolr &= ~WX_PSR_VM_L2CTL_ROMPE; + vmolr |= WX_PSR_VM_L2CTL_MPE; + } + + wr32(wx, WX_PSR_VLAN_CTL, vlnctrl); + wr32(wx, WX_PSR_CTL, fctrl); + wr32(wx, WX_PSR_VM_L2CTL(0), vmolr); +} +EXPORT_SYMBOL(wx_set_rx_mode); + +static void wx_set_rx_buffer_len(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + u32 mhadd, max_frame; + + max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN); + + mhadd = rd32(wx, WX_PSR_MAX_SZ); + if (max_frame != mhadd) + wr32(wx, WX_PSR_MAX_SZ, max_frame); +} + +/* Disable the specified rx queue */ +void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring) +{ + u8 reg_idx = ring->reg_idx; + u32 rxdctl; + int ret; + + /* write value back with RRCFG.EN bit cleared */ + wr32m(wx, WX_PX_RR_CFG(reg_idx), + WX_PX_RR_CFG_RR_EN, 0); + + /* the hardware may take up to 100us to really disable the rx queue */ + ret = read_poll_timeout(rd32, rxdctl, !(rxdctl & WX_PX_RR_CFG_RR_EN), + 10, 100, true, wx, WX_PX_RR_CFG(reg_idx)); + + if (ret == -ETIMEDOUT) { + /* Just for information */ + wx_err(wx, + "RRCFG.EN on Rx queue %d not cleared within the polling period\n", + reg_idx); + } +} +EXPORT_SYMBOL(wx_disable_rx_queue); + +static void wx_enable_rx_queue(struct wx *wx, struct wx_ring *ring) +{ + u8 reg_idx = ring->reg_idx; + u32 rxdctl; + int ret; + + ret = read_poll_timeout(rd32, rxdctl, rxdctl & WX_PX_RR_CFG_RR_EN, + 1000, 10000, true, wx, WX_PX_RR_CFG(reg_idx)); + + if (ret == -ETIMEDOUT) { + /* Just for information */ + wx_err(wx, + "RRCFG.EN on Rx queue %d not set within the polling period\n", + reg_idx); + } +} + +static void wx_configure_srrctl(struct wx *wx, + struct wx_ring *rx_ring) +{ + u16 reg_idx = rx_ring->reg_idx; + u32 srrctl; + + srrctl = rd32(wx, WX_PX_RR_CFG(reg_idx)); + srrctl &= ~(WX_PX_RR_CFG_RR_HDR_SZ | + WX_PX_RR_CFG_RR_BUF_SZ | + WX_PX_RR_CFG_SPLIT_MODE); + /* configure header buffer length, needed for RSC */ + srrctl |= WX_RXBUFFER_256 << WX_PX_RR_CFG_BHDRSIZE_SHIFT; + + /* configure the packet buffer length */ + srrctl |= WX_RX_BUFSZ >> WX_PX_RR_CFG_BSIZEPKT_SHIFT; + + wr32(wx, WX_PX_RR_CFG(reg_idx), srrctl); +} + +static void wx_configure_tx_ring(struct wx *wx, + struct wx_ring *ring) +{ + u32 txdctl = WX_PX_TR_CFG_ENABLE; + u8 reg_idx = ring->reg_idx; + u64 tdba = ring->dma; + int ret; + + /* disable queue to avoid issues while updating state */ + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + WX_WRITE_FLUSH(wx); + + wr32(wx, WX_PX_TR_BAL(reg_idx), tdba & DMA_BIT_MASK(32)); + wr32(wx, WX_PX_TR_BAH(reg_idx), upper_32_bits(tdba)); + + /* reset head and tail pointers */ + wr32(wx, WX_PX_TR_RP(reg_idx), 0); + wr32(wx, WX_PX_TR_WP(reg_idx), 0); + ring->tail = wx->hw_addr + WX_PX_TR_WP(reg_idx); + + if (ring->count < WX_MAX_TXD) + txdctl |= ring->count / 128 << WX_PX_TR_CFG_TR_SIZE_SHIFT; + txdctl |= 0x20 << WX_PX_TR_CFG_WTHRESH_SHIFT; + + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct wx_tx_buffer) * ring->count); + + /* enable queue */ + wr32(wx, WX_PX_TR_CFG(reg_idx), txdctl); + + /* poll to verify queue is enabled */ + ret = read_poll_timeout(rd32, txdctl, txdctl & WX_PX_TR_CFG_ENABLE, + 1000, 10000, true, wx, WX_PX_TR_CFG(reg_idx)); + if (ret == -ETIMEDOUT) + wx_err(wx, "Could not enable Tx Queue %d\n", reg_idx); +} + +static void wx_configure_rx_ring(struct wx *wx, + struct wx_ring *ring) +{ + u16 reg_idx = ring->reg_idx; + union wx_rx_desc *rx_desc; + u64 rdba = ring->dma; + u32 rxdctl; + + /* disable queue to avoid issues while updating state */ + rxdctl = rd32(wx, WX_PX_RR_CFG(reg_idx)); + wx_disable_rx_queue(wx, ring); + + wr32(wx, WX_PX_RR_BAL(reg_idx), rdba & DMA_BIT_MASK(32)); + wr32(wx, WX_PX_RR_BAH(reg_idx), upper_32_bits(rdba)); + + if (ring->count == WX_MAX_RXD) + rxdctl |= 0 << WX_PX_RR_CFG_RR_SIZE_SHIFT; + else + rxdctl |= (ring->count / 128) << WX_PX_RR_CFG_RR_SIZE_SHIFT; + + rxdctl |= 0x1 << WX_PX_RR_CFG_RR_THER_SHIFT; + wr32(wx, WX_PX_RR_CFG(reg_idx), rxdctl); + + /* reset head and tail pointers */ + wr32(wx, WX_PX_RR_RP(reg_idx), 0); + wr32(wx, WX_PX_RR_WP(reg_idx), 0); + ring->tail = wx->hw_addr + WX_PX_RR_WP(reg_idx); + + wx_configure_srrctl(wx, ring); + + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct wx_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = WX_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + + /* enable receive descriptor ring */ + wr32m(wx, WX_PX_RR_CFG(reg_idx), + WX_PX_RR_CFG_RR_EN, WX_PX_RR_CFG_RR_EN); + + wx_enable_rx_queue(wx, ring); + wx_alloc_rx_buffers(ring, wx_desc_unused(ring)); +} + +/** + * wx_configure_tx - Configure Transmit Unit after Reset + * @wx: pointer to private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void wx_configure_tx(struct wx *wx) +{ + u32 i; + + /* TDM_CTL.TE must be before Tx queues are enabled */ + wr32m(wx, WX_TDM_CTL, + WX_TDM_CTL_TE, WX_TDM_CTL_TE); + + /* Setup the HW Tx Head and Tail descriptor pointers */ + for (i = 0; i < wx->num_tx_queues; i++) + wx_configure_tx_ring(wx, wx->tx_ring[i]); + + wr32m(wx, WX_TSC_BUF_AE, WX_TSC_BUF_AE_THR, 0x10); + + if (wx->mac.type == wx_mac_em) + wr32m(wx, WX_TSC_CTL, WX_TSC_CTL_TX_DIS | WX_TSC_CTL_TSEC_DIS, 0x1); + + /* enable mac transmitter */ + wr32m(wx, WX_MAC_TX_CFG, + WX_MAC_TX_CFG_TE, WX_MAC_TX_CFG_TE); +} + +/** + * wx_configure_rx - Configure Receive Unit after Reset + * @wx: pointer to private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void wx_configure_rx(struct wx *wx) +{ + u32 psrtype, i; + int ret; + + wx_disable_rx(wx); + + psrtype = WX_RDB_PL_CFG_L4HDR | + WX_RDB_PL_CFG_L3HDR | + WX_RDB_PL_CFG_L2HDR | + WX_RDB_PL_CFG_TUN_TUNHDR | + WX_RDB_PL_CFG_TUN_TUNHDR; + wr32(wx, WX_RDB_PL_CFG(0), psrtype); + + /* enable hw crc stripping */ + wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP); + + if (wx->mac.type == wx_mac_sp) { + u32 psrctl; + + /* RSC Setup */ + psrctl = rd32(wx, WX_PSR_CTL); + psrctl |= WX_PSR_CTL_RSC_ACK; /* Disable RSC for ACK packets */ + psrctl |= WX_PSR_CTL_RSC_DIS; + wr32(wx, WX_PSR_CTL, psrctl); + } + + /* set_rx_buffer_len must be called before ring initialization */ + wx_set_rx_buffer_len(wx); + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < wx->num_rx_queues; i++) + wx_configure_rx_ring(wx, wx->rx_ring[i]); + + /* Enable all receives, disable security engine prior to block traffic */ + ret = wx_disable_sec_rx_path(wx); + if (ret < 0) + wx_err(wx, "The register status is abnormal, please check device."); + + wx_enable_rx(wx); + wx_enable_sec_rx_path(wx); +} + +static void wx_configure_isb(struct wx *wx) +{ + /* set ISB Address */ + wr32(wx, WX_PX_ISB_ADDR_L, wx->isb_dma & DMA_BIT_MASK(32)); + if (IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)) + wr32(wx, WX_PX_ISB_ADDR_H, upper_32_bits(wx->isb_dma)); +} + +void wx_configure(struct wx *wx) +{ + wx_set_rxpba(wx); + wx_configure_port(wx); + + wx_set_rx_mode(wx->netdev); + + wx_enable_sec_rx_path(wx); + + wx_configure_tx(wx); + wx_configure_rx(wx); + wx_configure_isb(wx); +} +EXPORT_SYMBOL(wx_configure); + /** * wx_disable_pcie_master - Disable PCI-express master access * @wx: pointer to hardware structure diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h index 803983546f3a..44dfd6ea442a 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h @@ -4,6 +4,8 @@ #ifndef _WX_HW_H_ #define _WX_HW_H_ +void wx_intr_enable(struct wx *wx, u64 qmask); +void wx_irq_disable(struct wx *wx); int wx_check_flash_load(struct wx *wx, u32 check_bit); void wx_control_hw(struct wx *wx, bool drv); int wx_mng_present(struct wx *wx); @@ -20,6 +22,9 @@ void wx_mac_set_default_filter(struct wx *wx, u8 *addr); void wx_flush_sw_mac_table(struct wx *wx); int wx_set_mac(struct net_device *netdev, void *p); void wx_disable_rx(struct wx *wx); +void wx_set_rx_mode(struct net_device *netdev); +void wx_disable_rx_queue(struct wx *wx, struct wx_ring *ring); +void wx_configure(struct wx *wx); int wx_disable_pcie_master(struct wx *wx); int wx_stop_adapter(struct wx *wx); void wx_reset_misc(struct wx *wx); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c new file mode 100644 index 000000000000..eb89a274083e --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -0,0 +1,2004 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. */ + +#include <linux/etherdevice.h> +#include <net/page_pool.h> +#include <linux/iopoll.h> +#include <linux/pci.h> + +#include "wx_type.h" +#include "wx_lib.h" +#include "wx_hw.h" + +/* wx_test_staterr - tests bits in Rx descriptor status and error fields */ +static __le32 wx_test_staterr(union wx_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + +static bool wx_can_reuse_rx_page(struct wx_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote and pfmemalloc pages */ + if (!dev_page_is_reusable(page)) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) + return false; +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + +/** + * wx_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void wx_reuse_rx_page(struct wx_ring *rx_ring, + struct wx_rx_buffer *old_buff) +{ + u16 nta = rx_ring->next_to_alloc; + struct wx_rx_buffer *new_buff; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_buff->page = old_buff->page; + new_buff->page_dma = old_buff->page_dma; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; +} + +static void wx_dma_sync_frag(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer) +{ + struct sk_buff *skb = rx_buffer->skb; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + + dma_sync_single_range_for_cpu(rx_ring->dev, + WX_CB(skb)->dma, + skb_frag_off(frag), + skb_frag_size(frag), + DMA_FROM_DEVICE); + + /* If the page was released, just unmap it. */ + if (unlikely(WX_CB(skb)->page_released)) + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); +} + +static struct wx_rx_buffer *wx_get_rx_buffer(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff **skb, + int *rx_buffer_pgcnt) +{ + struct wx_rx_buffer *rx_buffer; + unsigned int size; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + size = le16_to_cpu(rx_desc->wb.upper.length); + +#if (PAGE_SIZE < 8192) + *rx_buffer_pgcnt = page_count(rx_buffer->page); +#else + *rx_buffer_pgcnt = 0; +#endif + + prefetchw(rx_buffer->page); + *skb = rx_buffer->skb; + + /* Delay unmapping of the first packet. It carries the header + * information, HW may still access the header after the writeback. + * Only unmap it when EOP is reached + */ + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP)) { + if (!*skb) + goto skip_sync; + } else { + if (*skb) + wx_dma_sync_frag(rx_ring, rx_buffer); + } + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); +skip_sync: + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void wx_put_rx_buffer(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer, + struct sk_buff *skb, + int rx_buffer_pgcnt) +{ + if (wx_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { + /* hand second half of page back to the ring */ + wx_reuse_rx_page(rx_ring, rx_buffer); + } else { + if (!IS_ERR(skb) && WX_CB(skb)->dma == rx_buffer->dma) + /* the page has been released from the ring */ + WX_CB(skb)->page_released = true; + else + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; + rx_buffer->skb = NULL; +} + +static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, + struct wx_rx_buffer *rx_buffer, + union wx_rx_desc *rx_desc) +{ + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) + unsigned int truesize = WX_RX_BUFSZ; +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); +#endif + struct sk_buff *skb = rx_buffer->skb; + + if (!skb) { + void *page_addr = page_address(rx_buffer->page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, WX_RXBUFFER_256); + if (unlikely(!skb)) + return NULL; + + /* we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); + + if (size <= WX_RXBUFFER_256) { + memcpy(__skb_put(skb, size), page_addr, + ALIGN(size, sizeof(long))); + rx_buffer->pagecnt_bias++; + + return skb; + } + + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_EOP)) + WX_CB(skb)->dma = rx_buffer->dma; + + skb_add_rx_frag(skb, 0, rx_buffer->page, + rx_buffer->page_offset, + size, truesize); + goto out; + + } else { + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); + } + +out: +#if (PAGE_SIZE < 8192) + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +static bool wx_alloc_mapped_page(struct wx_ring *rx_ring, + struct wx_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + page = page_pool_dev_alloc_pages(rx_ring->page_pool); + WARN_ON(!page); + dma = page_pool_get_dma_addr(page); + + bi->page_dma = dma; + bi->page = page; + bi->page_offset = 0; + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; + + return true; +} + +/** + * wx_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: ring to place buffers on + * @cleaned_count: number of buffers to replace + **/ +void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count) +{ + u16 i = rx_ring->next_to_use; + union wx_rx_desc *rx_desc; + struct wx_rx_buffer *bi; + + /* nothing to do */ + if (!cleaned_count) + return; + + rx_desc = WX_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + if (!wx_alloc_mapped_page(rx_ring, bi)) + break; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + WX_RX_BUFSZ, + DMA_FROM_DEVICE); + + rx_desc->read.pkt_addr = + cpu_to_le64(bi->page_dma + bi->page_offset); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = WX_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the status bits for the next_to_use descriptor */ + rx_desc->wb.upper.status_error = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, rx_ring->tail); + } +} + +u16 wx_desc_unused(struct wx_ring *ring) +{ + u16 ntc = ring->next_to_clean; + u16 ntu = ring->next_to_use; + + return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1; +} + +/** + * wx_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool wx_is_non_eop(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(WX_RX_DESC(rx_ring, ntc)); + + /* if we are the last buffer then there is nothing else to do */ + if (likely(wx_test_staterr(rx_desc, WX_RXD_STAT_EOP))) + return false; + + rx_ring->rx_buffer_info[ntc].skb = skb; + + return true; +} + +static void wx_pull_tail(struct sk_buff *skb) +{ + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + unsigned int pull_len; + unsigned char *va; + + /* it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); + + /* we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(skb->dev, va, WX_RXBUFFER_256); + + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + skb_frag_off_add(frag, pull_len); + skb->data_len -= pull_len; + skb->tail += pull_len; +} + +/** + * wx_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool wx_cleanup_headers(struct wx_ring *rx_ring, + union wx_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *netdev = rx_ring->netdev; + + /* verify that the packet does not have any known errors */ + if (!netdev || + unlikely(wx_test_staterr(rx_desc, WX_RXD_ERR_RXE) && + !(netdev->features & NETIF_F_RXALL))) { + dev_kfree_skb_any(skb); + return true; + } + + /* place header in linear portion of buffer */ + if (!skb_headlen(skb)) + wx_pull_tail(skb); + + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * wx_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * @q_vector: structure containing interrupt and ring information + * @rx_ring: rx descriptor ring to transact packets on + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the system. + * + * Returns amount of work completed. + **/ +static int wx_clean_rx_irq(struct wx_q_vector *q_vector, + struct wx_ring *rx_ring, + int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 cleaned_count = wx_desc_unused(rx_ring); + + do { + struct wx_rx_buffer *rx_buffer; + union wx_rx_desc *rx_desc; + struct sk_buff *skb; + int rx_buffer_pgcnt; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= WX_RX_BUFFER_WRITE) { + wx_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = WX_RX_DESC(rx_ring, rx_ring->next_to_clean); + if (!wx_test_staterr(rx_desc, WX_RXD_STAT_DD)) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + rx_buffer = wx_get_rx_buffer(rx_ring, rx_desc, &skb, &rx_buffer_pgcnt); + + /* retrieve a buffer from the ring */ + skb = wx_build_skb(rx_ring, rx_buffer, rx_desc); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_buffer->pagecnt_bias++; + break; + } + + wx_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); + cleaned_count++; + + /* place incomplete frames back on ring for completion */ + if (wx_is_non_eop(rx_ring, rx_desc, skb)) + continue; + + /* verify the packet layout is correct */ + if (wx_cleanup_headers(rx_ring, rx_desc, skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + skb_record_rx_queue(skb, rx_ring->queue_index); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); + napi_gro_receive(&q_vector->napi, skb); + + /* update budget accounting */ + total_rx_packets++; + } while (likely(total_rx_packets < budget)); + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return total_rx_packets; +} + +static struct netdev_queue *wx_txring_txq(const struct wx_ring *ring) +{ + return netdev_get_tx_queue(ring->netdev, ring->queue_index); +} + +/** + * wx_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: structure containing interrupt and ring information + * @tx_ring: tx ring to clean + * @napi_budget: Used to determine if we are in netpoll + **/ +static bool wx_clean_tx_irq(struct wx_q_vector *q_vector, + struct wx_ring *tx_ring, int napi_budget) +{ + unsigned int budget = q_vector->wx->tx_work_limit; + unsigned int total_bytes = 0, total_packets = 0; + unsigned int i = tx_ring->next_to_clean; + struct wx_tx_buffer *tx_buffer; + union wx_tx_desc *tx_desc; + + if (!netif_carrier_ok(tx_ring->netdev)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = WX_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + union wx_tx_desc *eop_desc = tx_buffer->next_to_watch; + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(WX_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + + /* free the skb */ + napi_consume_skb(tx_buffer->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + dma_unmap_len_set(tx_buffer, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + netdev_tx_completed_queue(wx_txring_txq(tx_ring), + total_packets, total_bytes); + +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) + if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && + (wx_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + + if (__netif_subqueue_stopped(tx_ring->netdev, + tx_ring->queue_index) && + netif_running(tx_ring->netdev)) + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + } + + return !!budget; +} + +/** + * wx_poll - NAPI polling RX/TX cleanup routine + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function will clean all queues associated with a q_vector. + **/ +static int wx_poll(struct napi_struct *napi, int budget) +{ + struct wx_q_vector *q_vector = container_of(napi, struct wx_q_vector, napi); + int per_ring_budget, work_done = 0; + struct wx *wx = q_vector->wx; + bool clean_complete = true; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->tx) { + if (!wx_clean_tx_irq(q_vector, ring, budget)) + clean_complete = false; + } + + /* Exit if we are called by netpoll */ + if (budget <= 0) + return budget; + + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling + */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget / q_vector->rx.count, 1); + else + per_ring_budget = budget; + + wx_for_each_ring(ring, q_vector->rx) { + int cleaned = wx_clean_rx_irq(q_vector, ring, per_ring_budget); + + work_done += cleaned; + if (cleaned >= per_ring_budget) + clean_complete = false; + } + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* all work done, exit the polling mode */ + if (likely(napi_complete_done(napi, work_done))) { + if (netif_running(wx->netdev)) + wx_intr_enable(wx, WX_INTR_Q(q_vector->v_idx)); + } + + return min(work_done, budget - 1); +} + +static int wx_maybe_stop_tx(struct wx_ring *tx_ring, u16 size) +{ + if (likely(wx_desc_unused(tx_ring) >= size)) + return 0; + + netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); + + /* For the next check */ + smp_mb(); + + /* We need to check again in a case another CPU has just + * made room available. + */ + if (likely(wx_desc_unused(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! - use start_queue because it doesn't call schedule */ + netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); + + return 0; +} + +static void wx_tx_map(struct wx_ring *tx_ring, + struct wx_tx_buffer *first) +{ + struct sk_buff *skb = first->skb; + struct wx_tx_buffer *tx_buffer; + u16 i = tx_ring->next_to_use; + unsigned int data_len, size; + union wx_tx_desc *tx_desc; + skb_frag_t *frag; + dma_addr_t dma; + u32 cmd_type; + + cmd_type = WX_TXD_DTYP_DATA | WX_TXD_IFCS; + tx_desc = WX_TX_DESC(tx_ring, i); + + tx_desc->read.olinfo_status = cpu_to_le32(skb->len << WX_TXD_PAYLEN_SHIFT); + + size = skb_headlen(skb); + data_len = skb->data_len; + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > WX_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cpu_to_le32(cmd_type ^ WX_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = WX_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + dma += WX_MAX_DATA_PER_TXD; + size -= WX_MAX_DATA_PER_TXD; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = WX_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + size = skb_frag_size(frag); + + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= size | WX_TXD_EOP | WX_TXD_RS; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + + netdev_tx_sent_queue(wx_txring_txq(tx_ring), first->bytecount); + + skb_tx_timestamp(skb); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + wx_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(wx_txring_txq(tx_ring)) || !netdev_xmit_more()) + writel(i, tx_ring->tail); + + return; +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_buffer_info map */ + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[i]; + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + if (tx_buffer == first) + break; + if (i == 0) + i += tx_ring->count; + i--; + } + + dev_kfree_skb_any(first->skb); + first->skb = NULL; + + tx_ring->next_to_use = i; +} + +static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb, + struct wx_ring *tx_ring) +{ + u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct wx_tx_buffer *first; + unsigned short f; + + /* need: 1 descriptor per page * PAGE_SIZE/WX_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/WX_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_frag_size(&skb_shinfo(skb)-> + frags[f])); + + if (wx_maybe_stop_tx(tx_ring, count + 3)) + return NETDEV_TX_BUSY; + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + wx_tx_map(tx_ring, first); + + return NETDEV_TX_OK; +} + +netdev_tx_t wx_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + unsigned int r_idx = skb->queue_mapping; + struct wx *wx = netdev_priv(netdev); + struct wx_ring *tx_ring; + + if (!netif_carrier_ok(netdev)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb_put_padto(skb, 17)) + return NETDEV_TX_OK; + + if (r_idx >= wx->num_tx_queues) + r_idx = r_idx % wx->num_tx_queues; + tx_ring = wx->tx_ring[r_idx]; + + return wx_xmit_frame_ring(skb, tx_ring); +} +EXPORT_SYMBOL(wx_xmit_frame); + +void wx_napi_enable_all(struct wx *wx) +{ + struct wx_q_vector *q_vector; + int q_idx; + + for (q_idx = 0; q_idx < wx->num_q_vectors; q_idx++) { + q_vector = wx->q_vector[q_idx]; + napi_enable(&q_vector->napi); + } +} +EXPORT_SYMBOL(wx_napi_enable_all); + +void wx_napi_disable_all(struct wx *wx) +{ + struct wx_q_vector *q_vector; + int q_idx; + + for (q_idx = 0; q_idx < wx->num_q_vectors; q_idx++) { + q_vector = wx->q_vector[q_idx]; + napi_disable(&q_vector->napi); + } +} +EXPORT_SYMBOL(wx_napi_disable_all); + +/** + * wx_set_rss_queues: Allocate queues for RSS + * @wx: board private structure to initialize + * + * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try + * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * + **/ +static void wx_set_rss_queues(struct wx *wx) +{ + wx->num_rx_queues = wx->mac.max_rx_queues; + wx->num_tx_queues = wx->mac.max_tx_queues; +} + +static void wx_set_num_queues(struct wx *wx) +{ + /* Start with base case */ + wx->num_rx_queues = 1; + wx->num_tx_queues = 1; + wx->queues_per_pool = 1; + + wx_set_rss_queues(wx); +} + +/** + * wx_acquire_msix_vectors - acquire MSI-X vectors + * @wx: board private structure + * + * Attempts to acquire a suitable range of MSI-X vector interrupts. Will + * return a negative error code if unable to acquire MSI-X vectors for any + * reason. + */ +static int wx_acquire_msix_vectors(struct wx *wx) +{ + struct irq_affinity affd = {0, }; + int nvecs, i; + + nvecs = min_t(int, num_online_cpus(), wx->mac.max_msix_vectors); + + wx->msix_entries = kcalloc(nvecs, + sizeof(struct msix_entry), + GFP_KERNEL); + if (!wx->msix_entries) + return -ENOMEM; + + nvecs = pci_alloc_irq_vectors_affinity(wx->pdev, nvecs, + nvecs, + PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, + &affd); + if (nvecs < 0) { + wx_err(wx, "Failed to allocate MSI-X interrupts. Err: %d\n", nvecs); + kfree(wx->msix_entries); + wx->msix_entries = NULL; + return nvecs; + } + + for (i = 0; i < nvecs; i++) { + wx->msix_entries[i].entry = i; + wx->msix_entries[i].vector = pci_irq_vector(wx->pdev, i); + } + + /* one for msix_other */ + nvecs -= 1; + wx->num_q_vectors = nvecs; + wx->num_rx_queues = nvecs; + wx->num_tx_queues = nvecs; + + return 0; +} + +/** + * wx_set_interrupt_capability - set MSI-X or MSI if supported + * @wx: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int wx_set_interrupt_capability(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + int nvecs, ret; + + /* We will try to get MSI-X interrupts first */ + ret = wx_acquire_msix_vectors(wx); + if (ret == 0 || (ret == -ENOMEM)) + return ret; + + wx->num_rx_queues = 1; + wx->num_tx_queues = 1; + wx->num_q_vectors = 1; + + /* minmum one for queue, one for misc*/ + nvecs = 1; + nvecs = pci_alloc_irq_vectors(pdev, nvecs, + nvecs, PCI_IRQ_MSI | PCI_IRQ_LEGACY); + if (nvecs == 1) { + if (pdev->msi_enabled) + wx_err(wx, "Fallback to MSI.\n"); + else + wx_err(wx, "Fallback to LEGACY.\n"); + } else { + wx_err(wx, "Failed to allocate MSI/LEGACY interrupts. Error: %d\n", nvecs); + return nvecs; + } + + pdev->irq = pci_irq_vector(pdev, 0); + + return 0; +} + +/** + * wx_cache_ring_rss - Descriptor ring to register mapping for RSS + * @wx: board private structure to initialize + * + * Cache the descriptor ring offsets for RSS, ATR, FCoE, and SR-IOV. + * + **/ +static void wx_cache_ring_rss(struct wx *wx) +{ + u16 i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx->rx_ring[i]->reg_idx = i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx->tx_ring[i]->reg_idx = i; +} + +static void wx_add_ring(struct wx_ring *ring, struct wx_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * wx_alloc_q_vector - Allocate memory for a single interrupt vector + * @wx: board private structure to initialize + * @v_count: q_vectors allocated on wx, used for ring interleaving + * @v_idx: index of vector in wx struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + **/ +static int wx_alloc_q_vector(struct wx *wx, + unsigned int v_count, unsigned int v_idx, + unsigned int txr_count, unsigned int txr_idx, + unsigned int rxr_count, unsigned int rxr_idx) +{ + struct wx_q_vector *q_vector; + int ring_count, default_itr; + struct wx_ring *ring; + + /* note this will allocate space for the ring structure as well! */ + ring_count = txr_count + rxr_count; + + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(wx->netdev, &q_vector->napi, + wx_poll); + + /* tie q_vector and wx together */ + wx->q_vector[v_idx] = q_vector; + q_vector->wx = wx; + q_vector->v_idx = v_idx; + if (cpu_online(v_idx)) + q_vector->numa_node = cpu_to_node(v_idx); + + /* initialize pointer to rings */ + ring = q_vector->ring; + + if (wx->mac.type == wx_mac_sp) + default_itr = WX_12K_ITR; + else + default_itr = WX_7K_ITR; + /* initialize ITR */ + if (txr_count && !rxr_count) + /* tx only vector */ + q_vector->itr = wx->tx_itr_setting ? + default_itr : wx->tx_itr_setting; + else + /* rx or rx/tx vector */ + q_vector->itr = wx->rx_itr_setting ? + default_itr : wx->rx_itr_setting; + + while (txr_count) { + /* assign generic ring traits */ + ring->dev = &wx->pdev->dev; + ring->netdev = wx->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + wx_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = wx->tx_ring_count; + + ring->queue_index = txr_idx; + + /* assign ring to wx */ + wx->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + while (rxr_count) { + /* assign generic ring traits */ + ring->dev = &wx->pdev->dev; + ring->netdev = wx->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + wx_add_ring(ring, &q_vector->rx); + + /* apply Rx specific ring traits */ + ring->count = wx->rx_ring_count; + ring->queue_index = rxr_idx; + + /* assign ring to wx */ + wx->rx_ring[rxr_idx] = ring; + + /* update count and index */ + rxr_count--; + rxr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + return 0; +} + +/** + * wx_free_q_vector - Free memory allocated for specific interrupt vector + * @wx: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void wx_free_q_vector(struct wx *wx, int v_idx) +{ + struct wx_q_vector *q_vector = wx->q_vector[v_idx]; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->tx) + wx->tx_ring[ring->queue_index] = NULL; + + wx_for_each_ring(ring, q_vector->rx) + wx->rx_ring[ring->queue_index] = NULL; + + wx->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); + kfree_rcu(q_vector, rcu); +} + +/** + * wx_alloc_q_vectors - Allocate memory for interrupt vectors + * @wx: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int wx_alloc_q_vectors(struct wx *wx) +{ + unsigned int rxr_idx = 0, txr_idx = 0, v_idx = 0; + unsigned int rxr_remaining = wx->num_rx_queues; + unsigned int txr_remaining = wx->num_tx_queues; + unsigned int q_vectors = wx->num_q_vectors; + int rqpv, tqpv; + int err; + + for (; v_idx < q_vectors; v_idx++) { + rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); + tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + err = wx_alloc_q_vector(wx, q_vectors, v_idx, + tqpv, txr_idx, + rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + rxr_idx++; + txr_idx++; + } + + return 0; + +err_out: + wx->num_tx_queues = 0; + wx->num_rx_queues = 0; + wx->num_q_vectors = 0; + + while (v_idx--) + wx_free_q_vector(wx, v_idx); + + return -ENOMEM; +} + +/** + * wx_free_q_vectors - Free memory allocated for interrupt vectors + * @wx: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void wx_free_q_vectors(struct wx *wx) +{ + int v_idx = wx->num_q_vectors; + + wx->num_tx_queues = 0; + wx->num_rx_queues = 0; + wx->num_q_vectors = 0; + + while (v_idx--) + wx_free_q_vector(wx, v_idx); +} + +void wx_reset_interrupt_capability(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + if (!pdev->msi_enabled && !pdev->msix_enabled) + return; + + pci_free_irq_vectors(wx->pdev); + if (pdev->msix_enabled) { + kfree(wx->msix_entries); + wx->msix_entries = NULL; + } +} +EXPORT_SYMBOL(wx_reset_interrupt_capability); + +/** + * wx_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @wx: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +void wx_clear_interrupt_scheme(struct wx *wx) +{ + wx_free_q_vectors(wx); + wx_reset_interrupt_capability(wx); +} +EXPORT_SYMBOL(wx_clear_interrupt_scheme); + +int wx_init_interrupt_scheme(struct wx *wx) +{ + int ret; + + /* Number of supported queues */ + wx_set_num_queues(wx); + + /* Set interrupt mode */ + ret = wx_set_interrupt_capability(wx); + if (ret) { + wx_err(wx, "Allocate irq vectors for failed.\n"); + return ret; + } + + /* Allocate memory for queues */ + ret = wx_alloc_q_vectors(wx); + if (ret) { + wx_err(wx, "Unable to allocate memory for queue vectors.\n"); + wx_reset_interrupt_capability(wx); + return ret; + } + + wx_cache_ring_rss(wx); + + return 0; +} +EXPORT_SYMBOL(wx_init_interrupt_scheme); + +irqreturn_t wx_msix_clean_rings(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector = data; + + /* EIAM disabled interrupts (on this vector) for us */ + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule_irqoff(&q_vector->napi); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL(wx_msix_clean_rings); + +void wx_free_irq(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + int vector; + + if (!(pdev->msix_enabled)) { + free_irq(pdev->irq, wx); + return; + } + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + /* free only the irqs that were actually requested */ + if (!q_vector->rx.ring && !q_vector->tx.ring) + continue; + + free_irq(entry->vector, q_vector); + } + + free_irq(wx->msix_entries[vector].vector, wx); +} +EXPORT_SYMBOL(wx_free_irq); + +/** + * wx_setup_isb_resources - allocate interrupt status resources + * @wx: board private structure + * + * Return 0 on success, negative on failure + **/ +int wx_setup_isb_resources(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + wx->isb_mem = dma_alloc_coherent(&pdev->dev, + sizeof(u32) * 4, + &wx->isb_dma, + GFP_KERNEL); + if (!wx->isb_mem) { + wx_err(wx, "Alloc isb_mem failed\n"); + return -ENOMEM; + } + + return 0; +} +EXPORT_SYMBOL(wx_setup_isb_resources); + +/** + * wx_free_isb_resources - allocate all queues Rx resources + * @wx: board private structure + * + * Return 0 on success, negative on failure + **/ +void wx_free_isb_resources(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + + dma_free_coherent(&pdev->dev, sizeof(u32) * 4, + wx->isb_mem, wx->isb_dma); + wx->isb_mem = NULL; +} +EXPORT_SYMBOL(wx_free_isb_resources); + +u32 wx_misc_isb(struct wx *wx, enum wx_isb_idx idx) +{ + u32 cur_tag = 0; + + cur_tag = wx->isb_mem[WX_ISB_HEADER]; + wx->isb_tag[idx] = cur_tag; + + return (__force u32)cpu_to_le32(wx->isb_mem[idx]); +} +EXPORT_SYMBOL(wx_misc_isb); + +/** + * wx_set_ivar - set the IVAR registers, mapping interrupt causes to vectors + * @wx: pointer to wx struct + * @direction: 0 for Rx, 1 for Tx, -1 for other causes + * @queue: queue to map the corresponding interrupt to + * @msix_vector: the vector to map to the corresponding queue + * + **/ +static void wx_set_ivar(struct wx *wx, s8 direction, + u16 queue, u16 msix_vector) +{ + u32 ivar, index; + + if (direction == -1) { + /* other causes */ + msix_vector |= WX_PX_IVAR_ALLOC_VAL; + index = 0; + ivar = rd32(wx, WX_PX_MISC_IVAR); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + wr32(wx, WX_PX_MISC_IVAR, ivar); + } else { + /* tx or rx causes */ + msix_vector |= WX_PX_IVAR_ALLOC_VAL; + index = ((16 * (queue & 1)) + (8 * direction)); + ivar = rd32(wx, WX_PX_IVAR(queue >> 1)); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + wr32(wx, WX_PX_IVAR(queue >> 1), ivar); + } +} + +/** + * wx_write_eitr - write EITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + * + * This function is made to be called by ethtool and by the driver + * when it needs to update EITR registers at runtime. Hardware + * specific quirks/differences are taken care of here. + */ +static void wx_write_eitr(struct wx_q_vector *q_vector) +{ + struct wx *wx = q_vector->wx; + int v_idx = q_vector->v_idx; + u32 itr_reg; + + if (wx->mac.type == wx_mac_sp) + itr_reg = q_vector->itr & WX_SP_MAX_EITR; + else + itr_reg = q_vector->itr & WX_EM_MAX_EITR; + + itr_reg |= WX_PX_ITR_CNT_WDIS; + + wr32(wx, WX_PX_ITR(v_idx), itr_reg); +} + +/** + * wx_configure_vectors - Configure vectors for hardware + * @wx: board private structure + * + * wx_configure_vectors sets up the hardware to properly generate MSI-X/MSI/LEGACY + * interrupts. + **/ +void wx_configure_vectors(struct wx *wx) +{ + struct pci_dev *pdev = wx->pdev; + u32 eitrsel = 0; + u16 v_idx; + + if (pdev->msix_enabled) { + /* Populate MSIX to EITR Select */ + wr32(wx, WX_PX_ITRSEL, eitrsel); + /* use EIAM to auto-mask when MSI-X interrupt is asserted + * this saves a register write for every interrupt + */ + wr32(wx, WX_PX_GPIE, WX_PX_GPIE_MODEL); + } else { + /* legacy interrupts, use EIAM to auto-mask when reading EICR, + * specifically only auto mask tx and rx interrupts. + */ + wr32(wx, WX_PX_GPIE, 0); + } + + /* Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (v_idx = 0; v_idx < wx->num_q_vectors; v_idx++) { + struct wx_q_vector *q_vector = wx->q_vector[v_idx]; + struct wx_ring *ring; + + wx_for_each_ring(ring, q_vector->rx) + wx_set_ivar(wx, 0, ring->reg_idx, v_idx); + + wx_for_each_ring(ring, q_vector->tx) + wx_set_ivar(wx, 1, ring->reg_idx, v_idx); + + wx_write_eitr(q_vector); + } + + wx_set_ivar(wx, -1, 0, v_idx); + if (pdev->msix_enabled) + wr32(wx, WX_PX_ITR(v_idx), 1950); +} +EXPORT_SYMBOL(wx_configure_vectors); + +/** + * wx_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void wx_clean_rx_ring(struct wx_ring *rx_ring) +{ + struct wx_rx_buffer *rx_buffer; + u16 i = rx_ring->next_to_clean; + + rx_buffer = &rx_ring->rx_buffer_info[i]; + + /* Free all the Rx ring sk_buffs */ + while (i != rx_ring->next_to_alloc) { + if (rx_buffer->skb) { + struct sk_buff *skb = rx_buffer->skb; + + if (WX_CB(skb)->page_released) + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + + dev_kfree_skb(skb); + } + + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + WX_RX_BUFSZ, + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + page_pool_put_full_page(rx_ring->page_pool, rx_buffer->page, false); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + + i++; + rx_buffer++; + if (i == rx_ring->count) { + i = 0; + rx_buffer = rx_ring->rx_buffer_info; + } + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * wx_clean_all_rx_rings - Free Rx Buffers for all queues + * @wx: board private structure + **/ +void wx_clean_all_rx_rings(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx_clean_rx_ring(wx->rx_ring[i]); +} +EXPORT_SYMBOL(wx_clean_all_rx_rings); + +/** + * wx_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +static void wx_free_rx_resources(struct wx_ring *rx_ring) +{ + wx_clean_rx_ring(rx_ring); + kvfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!rx_ring->desc) + return; + + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; + + if (rx_ring->page_pool) { + page_pool_destroy(rx_ring->page_pool); + rx_ring->page_pool = NULL; + } +} + +/** + * wx_free_all_rx_resources - Free Rx Resources for All Queues + * @wx: pointer to hardware structure + * + * Free all receive software resources + **/ +static void wx_free_all_rx_resources(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_rx_queues; i++) + wx_free_rx_resources(wx->rx_ring[i]); +} + +/** + * wx_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void wx_clean_tx_ring(struct wx_ring *tx_ring) +{ + struct wx_tx_buffer *tx_buffer; + u16 i = tx_ring->next_to_clean; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + + while (i != tx_ring->next_to_use) { + union wx_tx_desc *eop_desc, *tx_desc; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = WX_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = WX_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + netdev_tx_reset_queue(wx_txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * wx_clean_all_tx_rings - Free Tx Buffers for all queues + * @wx: board private structure + **/ +void wx_clean_all_tx_rings(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx_clean_tx_ring(wx->tx_ring[i]); +} +EXPORT_SYMBOL(wx_clean_all_tx_rings); + +/** + * wx_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +static void wx_free_tx_resources(struct wx_ring *tx_ring) +{ + wx_clean_tx_ring(tx_ring); + kvfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + tx_ring->desc = NULL; +} + +/** + * wx_free_all_tx_resources - Free Tx Resources for All Queues + * @wx: pointer to hardware structure + * + * Free all transmit software resources + **/ +static void wx_free_all_tx_resources(struct wx *wx) +{ + int i; + + for (i = 0; i < wx->num_tx_queues; i++) + wx_free_tx_resources(wx->tx_ring[i]); +} + +void wx_free_resources(struct wx *wx) +{ + wx_free_isb_resources(wx); + wx_free_all_rx_resources(wx); + wx_free_all_tx_resources(wx); +} +EXPORT_SYMBOL(wx_free_resources); + +static int wx_alloc_page_pool(struct wx_ring *rx_ring) +{ + int ret = 0; + + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = 0, + .pool_size = rx_ring->size, + .nid = dev_to_node(rx_ring->dev), + .dev = rx_ring->dev, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = PAGE_SIZE, + }; + + rx_ring->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rx_ring->page_pool)) { + ret = PTR_ERR(rx_ring->page_pool); + rx_ring->page_pool = NULL; + } + + return ret; +} + +/** + * wx_setup_rx_resources - allocate Rx resources (Descriptors) + * @rx_ring: rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +static int wx_setup_rx_resources(struct wx_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = NUMA_NO_NODE; + int size, ret; + + size = sizeof(struct wx_rx_buffer) * rx_ring->count; + + if (rx_ring->q_vector) + numa_node = rx_ring->q_vector->numa_node; + + rx_ring->rx_buffer_info = kvmalloc_node(size, GFP_KERNEL, numa_node); + if (!rx_ring->rx_buffer_info) + rx_ring->rx_buffer_info = kvmalloc(size, GFP_KERNEL); + if (!rx_ring->rx_buffer_info) + goto err; + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union wx_rx_desc); + rx_ring->size = ALIGN(rx_ring->size, 4096); + + set_dev_node(dev, numa_node); + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + if (!rx_ring->desc) { + set_dev_node(dev, orig_node); + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + } + + if (!rx_ring->desc) + goto err; + + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + ret = wx_alloc_page_pool(rx_ring); + if (ret < 0) { + dev_err(rx_ring->dev, "Page pool creation failed: %d\n", ret); + goto err; + } + + return 0; +err: + kvfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); + return -ENOMEM; +} + +/** + * wx_setup_all_rx_resources - allocate all queues Rx resources + * @wx: pointer to hardware structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_all_rx_resources(struct wx *wx) +{ + int i, err = 0; + + for (i = 0; i < wx->num_rx_queues; i++) { + err = wx_setup_rx_resources(wx->rx_ring[i]); + if (!err) + continue; + + wx_err(wx, "Allocation for Rx Queue %u failed\n", i); + goto err_setup_rx; + } + + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + wx_free_rx_resources(wx->rx_ring[i]); + return err; +} + +/** + * wx_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_tx_resources(struct wx_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = NUMA_NO_NODE; + int size; + + size = sizeof(struct wx_tx_buffer) * tx_ring->count; + + if (tx_ring->q_vector) + numa_node = tx_ring->q_vector->numa_node; + + tx_ring->tx_buffer_info = kvmalloc_node(size, GFP_KERNEL, numa_node); + if (!tx_ring->tx_buffer_info) + tx_ring->tx_buffer_info = kvmalloc(size, GFP_KERNEL); + if (!tx_ring->tx_buffer_info) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union wx_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + set_dev_node(dev, numa_node); + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + if (!tx_ring->desc) { + set_dev_node(dev, orig_node); + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + } + + if (!tx_ring->desc) + goto err; + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + + return 0; + +err: + kvfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); + return -ENOMEM; +} + +/** + * wx_setup_all_tx_resources - allocate all queues Tx resources + * @wx: pointer to private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int wx_setup_all_tx_resources(struct wx *wx) +{ + int i, err = 0; + + for (i = 0; i < wx->num_tx_queues; i++) { + err = wx_setup_tx_resources(wx->tx_ring[i]); + if (!err) + continue; + + wx_err(wx, "Allocation for Tx Queue %u failed\n", i); + goto err_setup_tx; + } + + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + wx_free_tx_resources(wx->tx_ring[i]); + return err; +} + +int wx_setup_resources(struct wx *wx) +{ + int err; + + /* allocate transmit descriptors */ + err = wx_setup_all_tx_resources(wx); + if (err) + return err; + + /* allocate receive descriptors */ + err = wx_setup_all_rx_resources(wx); + if (err) + goto err_free_tx; + + err = wx_setup_isb_resources(wx); + if (err) + goto err_free_rx; + + return 0; + +err_free_rx: + wx_free_all_rx_resources(wx); +err_free_tx: + wx_free_all_tx_resources(wx); + + return err; +} +EXPORT_SYMBOL(wx_setup_resources); + +/** + * wx_get_stats64 - Get System Network Statistics + * @netdev: network interface device structure + * @stats: storage space for 64bit statistics + */ +void wx_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct wx *wx = netdev_priv(netdev); + int i; + + rcu_read_lock(); + for (i = 0; i < wx->num_rx_queues; i++) { + struct wx_ring *ring = READ_ONCE(wx->rx_ring[i]); + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry(&ring->syncp, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + } + } + + for (i = 0; i < wx->num_tx_queues; i++) { + struct wx_ring *ring = READ_ONCE(wx->tx_ring[i]); + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry(&ring->syncp, + start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } + } + + rcu_read_unlock(); +} +EXPORT_SYMBOL(wx_get_stats64); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.h b/drivers/net/ethernet/wangxun/libwx/wx_lib.h new file mode 100644 index 000000000000..50ee41f1fa10 --- /dev/null +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * WangXun Gigabit PCI Express Linux driver + * Copyright (c) 2019 - 2022 Beijing WangXun Technology Co., Ltd. + */ + +#ifndef _WX_LIB_H_ +#define _WX_LIB_H_ + +void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count); +u16 wx_desc_unused(struct wx_ring *ring); +netdev_tx_t wx_xmit_frame(struct sk_buff *skb, + struct net_device *netdev); +void wx_napi_enable_all(struct wx *wx); +void wx_napi_disable_all(struct wx *wx); +void wx_reset_interrupt_capability(struct wx *wx); +void wx_clear_interrupt_scheme(struct wx *wx); +int wx_init_interrupt_scheme(struct wx *wx); +irqreturn_t wx_msix_clean_rings(int __always_unused irq, void *data); +void wx_free_irq(struct wx *wx); +int wx_setup_isb_resources(struct wx *wx); +void wx_free_isb_resources(struct wx *wx); +u32 wx_misc_isb(struct wx *wx, enum wx_isb_idx idx); +void wx_configure_vectors(struct wx *wx); +void wx_clean_all_rx_rings(struct wx *wx); +void wx_clean_all_tx_rings(struct wx *wx); +void wx_free_resources(struct wx *wx); +int wx_setup_resources(struct wx *wx); +void wx_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats); + +#endif /* _NGBE_LIB_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index c86a37914d43..eede93d4120d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -5,6 +5,7 @@ #define _WX_TYPE_H_ #include <linux/bitfield.h> +#include <linux/netdevice.h> /* Vendor ID */ #ifndef PCI_VENDOR_ID_WANGXUN @@ -65,21 +66,50 @@ /* port cfg Registers */ #define WX_CFG_PORT_CTL 0x14400 #define WX_CFG_PORT_CTL_DRV_LOAD BIT(3) +#define WX_CFG_PORT_CTL_QINQ BIT(2) +#define WX_CFG_PORT_CTL_D_VLAN BIT(0) /* double vlan*/ +#define WX_CFG_TAG_TPID(_i) (0x14430 + ((_i) * 4)) + +/* GPIO Registers */ +#define WX_GPIO_DR 0x14800 +#define WX_GPIO_DR_0 BIT(0) /* SDP0 Data Value */ +#define WX_GPIO_DR_1 BIT(1) /* SDP1 Data Value */ +#define WX_GPIO_DDR 0x14804 +#define WX_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ +#define WX_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ +#define WX_GPIO_CTL 0x14808 +#define WX_GPIO_INTEN 0x14830 +#define WX_GPIO_INTEN_0 BIT(0) +#define WX_GPIO_INTEN_1 BIT(1) +#define WX_GPIO_INTMASK 0x14834 +#define WX_GPIO_INTTYPE_LEVEL 0x14838 +#define WX_GPIO_POLARITY 0x1483C +#define WX_GPIO_EOI 0x1484C /*********************** Transmit DMA registers **************************/ /* transmit global control */ #define WX_TDM_CTL 0x18000 /* TDM CTL BIT */ #define WX_TDM_CTL_TE BIT(0) /* Transmit Enable */ +#define WX_TDM_PB_THRE(_i) (0x18020 + ((_i) * 4)) /***************************** RDB registers *********************************/ /* receive packet buffer */ #define WX_RDB_PB_CTL 0x19000 #define WX_RDB_PB_CTL_RXEN BIT(31) /* Enable Receiver */ #define WX_RDB_PB_CTL_DISABLED BIT(0) +#define WX_RDB_PB_SZ(_i) (0x19020 + ((_i) * 4)) +#define WX_RDB_PB_SZ_SHIFT 10 /* statistic */ #define WX_RDB_PFCMACDAL 0x19210 #define WX_RDB_PFCMACDAH 0x19214 +/* ring assignment */ +#define WX_RDB_PL_CFG(_i) (0x19300 + ((_i) * 4)) +#define WX_RDB_PL_CFG_L4HDR BIT(1) +#define WX_RDB_PL_CFG_L3HDR BIT(2) +#define WX_RDB_PL_CFG_L2HDR BIT(3) +#define WX_RDB_PL_CFG_TUN_TUNHDR BIT(4) +#define WX_RDB_PL_CFG_TUN_OUTL2HDR BIT(5) /******************************* PSR Registers *******************************/ /* psr control */ @@ -97,10 +127,24 @@ #define WX_PSR_CTL_MO_SHIFT 5 #define WX_PSR_CTL_MO (0x3 << WX_PSR_CTL_MO_SHIFT) #define WX_PSR_CTL_TPE BIT(4) +#define WX_PSR_MAX_SZ 0x15020 +#define WX_PSR_VLAN_CTL 0x15088 +#define WX_PSR_VLAN_CTL_CFIEN BIT(29) /* bit 29 */ +#define WX_PSR_VLAN_CTL_VFE BIT(30) /* bit 30 */ /* mcasst/ucast overflow tbl */ #define WX_PSR_MC_TBL(_i) (0x15200 + ((_i) * 4)) #define WX_PSR_UC_TBL(_i) (0x15400 + ((_i) * 4)) +/* VM L2 contorl */ +#define WX_PSR_VM_L2CTL(_i) (0x15600 + ((_i) * 4)) +#define WX_PSR_VM_L2CTL_UPE BIT(4) /* unicast promiscuous */ +#define WX_PSR_VM_L2CTL_VACC BIT(6) /* accept nomatched vlan */ +#define WX_PSR_VM_L2CTL_AUPE BIT(8) /* accept untagged packets */ +#define WX_PSR_VM_L2CTL_ROMPE BIT(9) /* accept packets in MTA tbl */ +#define WX_PSR_VM_L2CTL_ROPE BIT(10) /* accept packets in UC tbl */ +#define WX_PSR_VM_L2CTL_BAM BIT(11) /* accept broadcast packets */ +#define WX_PSR_VM_L2CTL_MPE BIT(12) /* multicast promiscuous */ + /* Management */ #define WX_PSR_MNG_FLEX_SEL 0x1582C #define WX_PSR_MNG_FLEX_DW_L(_i) (0x15A00 + ((_i) * 16)) @@ -122,6 +166,27 @@ #define WX_PSR_MAC_SWC_IDX 0x16210 #define WX_CLEAR_VMDQ_ALL 0xFFFFFFFFU +/********************************* RSEC **************************************/ +/* general rsec */ +#define WX_RSC_CTL 0x17000 +#define WX_RSC_CTL_SAVE_MAC_ERR BIT(6) +#define WX_RSC_CTL_CRC_STRIP BIT(2) +#define WX_RSC_CTL_RX_DIS BIT(1) +#define WX_RSC_ST 0x17004 +#define WX_RSC_ST_RSEC_RDY BIT(0) + +/****************************** TDB ******************************************/ +#define WX_TDB_PB_SZ(_i) (0x1CC00 + ((_i) * 4)) +#define WX_TXPKT_SIZE_MAX 0xA /* Max Tx Packet size */ + +/****************************** TSEC *****************************************/ +/* Security Control Registers */ +#define WX_TSC_CTL 0x1D000 +#define WX_TSC_CTL_TX_DIS BIT(1) +#define WX_TSC_CTL_TSEC_DIS BIT(0) +#define WX_TSC_BUF_AE 0x1D00C +#define WX_TSC_BUF_AE_THR GENMASK(9, 0) + /************************************** MNG ********************************/ #define WX_MNG_SWFW_SYNC 0x1E008 #define WX_MNG_SWFW_SYNC_SW_MB BIT(2) @@ -135,6 +200,7 @@ #define WX_MAC_TX_CFG 0x11000 #define WX_MAC_TX_CFG_TE BIT(0) #define WX_MAC_TX_CFG_SPEED_MASK GENMASK(30, 29) +#define WX_MAC_TX_CFG_SPEED_10G FIELD_PREP(WX_MAC_TX_CFG_SPEED_MASK, 0) #define WX_MAC_TX_CFG_SPEED_1G FIELD_PREP(WX_MAC_TX_CFG_SPEED_MASK, 3) #define WX_MAC_RX_CFG 0x11004 #define WX_MAC_RX_CFG_RE BIT(0) @@ -151,10 +217,34 @@ /* Interrupt Registers */ #define WX_BME_CTL 0x12020 #define WX_PX_MISC_IC 0x100 +#define WX_PX_MISC_ICS 0x104 +#define WX_PX_MISC_IEN 0x108 +#define WX_PX_INTA 0x110 +#define WX_PX_GPIE 0x118 +#define WX_PX_GPIE_MODEL BIT(0) +#define WX_PX_IC 0x120 #define WX_PX_IMS(_i) (0x140 + (_i) * 4) +#define WX_PX_IMC(_i) (0x150 + (_i) * 4) +#define WX_PX_ISB_ADDR_L 0x160 +#define WX_PX_ISB_ADDR_H 0x164 #define WX_PX_TRANSACTION_PENDING 0x168 +#define WX_PX_ITRSEL 0x180 +#define WX_PX_ITR(_i) (0x200 + (_i) * 4) +#define WX_PX_ITR_CNT_WDIS BIT(31) +#define WX_PX_MISC_IVAR 0x4FC +#define WX_PX_IVAR(_i) (0x500 + (_i) * 4) + +#define WX_PX_IVAR_ALLOC_VAL 0x80 /* Interrupt Allocation valid */ +#define WX_7K_ITR 595 +#define WX_12K_ITR 336 +#define WX_SP_MAX_EITR 0x00000FF8U +#define WX_EM_MAX_EITR 0x00007FFCU /* transmit DMA Registers */ +#define WX_PX_TR_BAL(_i) (0x03000 + ((_i) * 0x40)) +#define WX_PX_TR_BAH(_i) (0x03004 + ((_i) * 0x40)) +#define WX_PX_TR_WP(_i) (0x03008 + ((_i) * 0x40)) +#define WX_PX_TR_RP(_i) (0x0300C + ((_i) * 0x40)) #define WX_PX_TR_CFG(_i) (0x03010 + ((_i) * 0x40)) /* Transmit Config masks */ #define WX_PX_TR_CFG_ENABLE BIT(0) /* Ena specific Tx Queue */ @@ -164,8 +254,22 @@ #define WX_PX_TR_CFG_THRE_SHIFT 8 /* Receive DMA Registers */ +#define WX_PX_RR_BAL(_i) (0x01000 + ((_i) * 0x40)) +#define WX_PX_RR_BAH(_i) (0x01004 + ((_i) * 0x40)) +#define WX_PX_RR_WP(_i) (0x01008 + ((_i) * 0x40)) +#define WX_PX_RR_RP(_i) (0x0100C + ((_i) * 0x40)) #define WX_PX_RR_CFG(_i) (0x01010 + ((_i) * 0x40)) /* PX_RR_CFG bit definitions */ +#define WX_PX_RR_CFG_SPLIT_MODE BIT(26) +#define WX_PX_RR_CFG_RR_THER_SHIFT 16 +#define WX_PX_RR_CFG_RR_HDR_SZ GENMASK(15, 12) +#define WX_PX_RR_CFG_RR_BUF_SZ GENMASK(11, 8) +#define WX_PX_RR_CFG_BHDRSIZE_SHIFT 6 /* 64byte resolution (>> 6) + * + at bit 8 offset (<< 12) + * = (<< 6) + */ +#define WX_PX_RR_CFG_BSIZEPKT_SHIFT 2 /* so many KBs */ +#define WX_PX_RR_CFG_RR_SIZE_SHIFT 1 #define WX_PX_RR_CFG_RR_EN BIT(0) /* Number of 80 microseconds we wait for PCI Express master disable */ @@ -193,8 +297,46 @@ #define WX_MAC_STATE_MODIFIED 0x2 #define WX_MAC_STATE_IN_USE 0x4 +#define WX_MAX_RXD 8192 +#define WX_MAX_TXD 8192 + +/* Supported Rx Buffer Sizes */ +#define WX_RXBUFFER_256 256 /* Used for skb receive header */ +#define WX_RXBUFFER_2K 2048 +#define WX_MAX_RXBUFFER 16384 /* largest size for single descriptor */ + +#if MAX_SKB_FRAGS < 8 +#define WX_RX_BUFSZ ALIGN(WX_MAX_RXBUFFER / MAX_SKB_FRAGS, 1024) +#else +#define WX_RX_BUFSZ WX_RXBUFFER_2K +#endif + +#define WX_RX_BUFFER_WRITE 16 /* Must be power of 2 */ + +#define WX_MAX_DATA_PER_TXD BIT(14) +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), WX_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + +/* Ether Types */ +#define WX_ETH_P_CNM 0x22E7 + #define WX_CFG_PORT_ST 0x14404 +/******************* Receive Descriptor bit definitions **********************/ +#define WX_RXD_STAT_DD BIT(0) /* Done */ +#define WX_RXD_STAT_EOP BIT(1) /* End of Packet */ + +#define WX_RXD_ERR_RXE BIT(29) /* Any MAC Error */ + +/*********************** Transmit Descriptor Config Masks ****************/ +#define WX_TXD_STAT_DD BIT(0) /* Descriptor Done */ +#define WX_TXD_DTYP_DATA 0 /* Adv Data Descriptor */ +#define WX_TXD_PAYLEN_SHIFT 13 /* Desc PAYLEN shift */ +#define WX_TXD_EOP BIT(24) /* End of Packet */ +#define WX_TXD_IFCS BIT(25) /* Insert FCS */ +#define WX_TXD_RS BIT(27) /* Report Status */ + /* Host Interface Command Structures */ struct wx_hic_hdr { u8 cmd; @@ -270,9 +412,12 @@ struct wx_mac_info { bool set_lben; u8 addr[ETH_ALEN]; u8 perm_addr[ETH_ALEN]; + u32 mta_shadow[128]; s32 mc_filter_type; u32 mcft_size; u32 num_rar_entries; + u32 rx_pb_size; + u32 tx_pb_size; u32 max_tx_queues; u32 max_rx_queues; @@ -312,6 +457,161 @@ enum wx_reset_type { WX_GLOBAL_RESET }; +struct wx_cb { + dma_addr_t dma; + u16 append_cnt; /* number of skb's appended */ + bool page_released; + bool dma_released; +}; + +#define WX_CB(skb) ((struct wx_cb *)(skb)->cb) + +/* Transmit Descriptor */ +union wx_tx_desc { + struct { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; + } read; + struct { + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; + } wb; +}; + +/* Receive Descriptor */ +union wx_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + union { + __le32 data; + struct { + __le16 pkt_info; /* RSS, Pkt type */ + __le16 hdr_info; /* Splithdr, hdrlen */ + } hs_rss; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + struct { + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ + } csum_ip; + } hi_dword; + } lower; + struct { + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ + } upper; + } wb; /* writeback */ +}; + +#define WX_RX_DESC(R, i) \ + (&(((union wx_rx_desc *)((R)->desc))[i])) +#define WX_TX_DESC(R, i) \ + (&(((union wx_tx_desc *)((R)->desc))[i])) + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct wx_tx_buffer { + union wx_tx_desc *next_to_watch; + struct sk_buff *skb; + unsigned int bytecount; + unsigned short gso_segs; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); +}; + +struct wx_rx_buffer { + struct sk_buff *skb; + dma_addr_t dma; + dma_addr_t page_dma; + struct page *page; + unsigned int page_offset; + u16 pagecnt_bias; +}; + +struct wx_queue_stats { + u64 packets; + u64 bytes; +}; + +/* iterator for handling rings in ring container */ +#define wx_for_each_ring(posm, headm) \ + for (posm = (headm).ring; posm; posm = posm->next) + +struct wx_ring_container { + struct wx_ring *ring; /* pointer to linked list of rings */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +struct wx_ring { + struct wx_ring *next; /* pointer to next ring in q_vector */ + struct wx_q_vector *q_vector; /* backpointer to host q_vector */ + struct net_device *netdev; /* netdev ring belongs to */ + struct device *dev; /* device for DMA mapping */ + struct page_pool *page_pool; + void *desc; /* descriptor ring memory */ + union { + struct wx_tx_buffer *tx_buffer_info; + struct wx_rx_buffer *rx_buffer_info; + }; + u8 __iomem *tail; + dma_addr_t dma; /* phys. address of descriptor ring */ + unsigned int size; /* length in bytes */ + + u16 count; /* amount of descriptors */ + + u8 queue_index; /* needed for multiqueue queue management */ + u8 reg_idx; /* holds the special value that gets + * the hardware register offset + * associated with this ring, which is + * different for DCB and RSS modes + */ + u16 next_to_use; + u16 next_to_clean; + u16 next_to_alloc; + + struct wx_queue_stats stats; + struct u64_stats_sync syncp; +} ____cacheline_internodealigned_in_smp; + +struct wx_q_vector { + struct wx *wx; + int cpu; /* CPU for DCA */ + int numa_node; + u16 v_idx; /* index of q_vector within array, also used for + * finding the bit in EICR and friends that + * represents the vector for this ring + */ + u16 itr; /* Interrupt throttle rate written to EITR */ + struct wx_ring_container rx, tx; + struct napi_struct napi; + struct rcu_head rcu; /* to avoid race with update stats on free */ + + char name[IFNAMSIZ + 17]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct wx_ring ring[0] ____cacheline_internodealigned_in_smp; +}; + +enum wx_isb_idx { + WX_ISB_HEADER, + WX_ISB_MISC, + WX_ISB_VEC0, + WX_ISB_VEC1, + WX_ISB_MAX +}; + struct wx { u8 __iomem *hw_addr; struct pci_dev *pdev; @@ -331,6 +631,7 @@ struct wx { u16 oem_svid; u16 msg_enable; bool adapter_stopped; + u16 tpid[8]; char eeprom_id[32]; enum wx_reset_type reset_type; @@ -360,6 +661,18 @@ struct wx { u32 tx_ring_count; u32 rx_ring_count; + struct wx_ring *tx_ring[64] ____cacheline_aligned_in_smp; + struct wx_ring *rx_ring[64]; + struct wx_q_vector *q_vector[64]; + + unsigned int queues_per_pool; + struct msix_entry *msix_entries; + + /* misc interrupt status block */ + dma_addr_t isb_dma; + u32 *isb_mem; + u32 isb_tag[WX_ISB_MAX]; + #define WX_MAX_RETA_ENTRIES 128 u8 rss_indir_tbl[WX_MAX_RETA_ENTRIES]; @@ -371,6 +684,7 @@ struct wx { }; #define WX_INTR_ALL (~0ULL) +#define WX_INTR_Q(i) BIT(i) /* register operations */ #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index ed52f80b5475..f94d415daf3c 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -13,6 +13,7 @@ #include "../libwx/wx_type.h" #include "../libwx/wx_hw.h" +#include "../libwx/wx_lib.h" #include "ngbe_type.h" #include "ngbe_mdio.h" #include "ngbe_hw.h" @@ -112,6 +113,9 @@ static int ngbe_sw_init(struct wx *wx) wx->mac.num_rar_entries = NGBE_RAR_ENTRIES; wx->mac.max_rx_queues = NGBE_MAX_RX_QUEUES; wx->mac.max_tx_queues = NGBE_MAX_TX_QUEUES; + wx->mac.mcft_size = NGBE_MC_TBL_SIZE; + wx->mac.rx_pb_size = NGBE_RX_PB_SIZE; + wx->mac.tx_pb_size = NGBE_TDB_PB_SZ; /* PCI config space info */ err = wx_sw_init(wx); @@ -148,27 +152,211 @@ static int ngbe_sw_init(struct wx *wx) return 0; } +/** + * ngbe_irq_enable - Enable default interrupt generation settings + * @wx: board private structure + * @queues: enable all queues interrupts + **/ +static void ngbe_irq_enable(struct wx *wx, bool queues) +{ + u32 mask; + + /* enable misc interrupt */ + mask = NGBE_PX_MISC_IEN_MASK; + + wr32(wx, WX_GPIO_DDR, WX_GPIO_DDR_0); + wr32(wx, WX_GPIO_INTEN, WX_GPIO_INTEN_0 | WX_GPIO_INTEN_1); + wr32(wx, WX_GPIO_INTTYPE_LEVEL, 0x0); + wr32(wx, WX_GPIO_POLARITY, wx->gpio_ctrl ? 0 : 0x3); + + wr32(wx, WX_PX_MISC_IEN, mask); + + /* mask interrupt */ + if (queues) + wx_intr_enable(wx, NGBE_INTR_ALL); + else + wx_intr_enable(wx, NGBE_INTR_MISC(wx)); +} + +/** + * ngbe_intr - msi/legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t ngbe_intr(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector; + struct wx *wx = data; + struct pci_dev *pdev; + u32 eicr; + + q_vector = wx->q_vector[0]; + pdev = wx->pdev; + + eicr = wx_misc_isb(wx, WX_ISB_VEC0); + if (!eicr) { + /* shared interrupt alert! + * the interrupt that we masked before the EICR read. + */ + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, true); + return IRQ_NONE; /* Not our interrupt */ + } + wx->isb_mem[WX_ISB_VEC0] = 0; + if (!(pdev->msi_enabled)) + wr32(wx, WX_PX_INTA, 1); + + wx->isb_mem[WX_ISB_MISC] = 0; + /* would disable interrupts here but it is auto disabled */ + napi_schedule_irqoff(&q_vector->napi); + + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data) +{ + struct wx *wx = data; + + /* re-enable the original interrupt state, no lsc, no queues */ + if (netif_running(wx->netdev)) + ngbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +/** + * ngbe_request_msix_irqs - Initialize MSI-X interrupts + * @wx: board private structure + * + * ngbe_request_msix_irqs allocates MSI-X vectors and requests + * interrupts from the kernel. + **/ +static int ngbe_request_msix_irqs(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + int vector, err; + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-TxRx-%d", netdev->name, entry->entry); + else + /* skip this unused q_vector */ + continue; + + err = request_irq(entry->vector, wx_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", + q_vector->name, err); + goto free_queue_irqs; + } + } + + err = request_irq(wx->msix_entries[vector].vector, + ngbe_msix_other, 0, netdev->name, wx); + + if (err) { + wx_err(wx, "request_irq for msix_other failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(wx->msix_entries[vector].vector, + wx->q_vector[vector]); + } + wx_reset_interrupt_capability(wx); + return err; +} + +/** + * ngbe_request_irq - initialize interrupts + * @wx: board private structure + * + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int ngbe_request_irq(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + struct pci_dev *pdev = wx->pdev; + int err; + + if (pdev->msix_enabled) + err = ngbe_request_msix_irqs(wx); + else if (pdev->msi_enabled) + err = request_irq(pdev->irq, ngbe_intr, 0, + netdev->name, wx); + else + err = request_irq(pdev->irq, ngbe_intr, IRQF_SHARED, + netdev->name, wx); + + if (err) + wx_err(wx, "request_irq failed, Error %d\n", err); + + return err; +} + static void ngbe_disable_device(struct wx *wx) { struct net_device *netdev = wx->netdev; + u32 i; + /* disable all enabled rx queues */ + for (i = 0; i < wx->num_rx_queues; i++) + /* this call also flushes the previous write */ + wx_disable_rx_queue(wx, wx->rx_ring[i]); /* disable receives */ wx_disable_rx(wx); + wx_napi_disable_all(wx); + netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); if (wx->gpio_ctrl) ngbe_sfp_modules_txrx_powerctl(wx, false); + wx_irq_disable(wx); + /* disable transmits in the hardware now that interrupts are off */ + for (i = 0; i < wx->num_tx_queues; i++) { + u8 reg_idx = wx->tx_ring[i]->reg_idx; + + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + } } static void ngbe_down(struct wx *wx) { phy_stop(wx->phydev); ngbe_disable_device(wx); + wx_clean_all_tx_rings(wx); + wx_clean_all_rx_rings(wx); } static void ngbe_up(struct wx *wx) { + wx_configure_vectors(wx); + + /* make sure to complete pre-operations */ + smp_mb__before_atomic(); + wx_napi_enable_all(wx); + /* enable transmits */ + netif_tx_start_all_queues(wx->netdev); + + /* clear any pending interrupts, may auto mask */ + rd32(wx, WX_PX_IC); + rd32(wx, WX_PX_MISC_IC); + ngbe_irq_enable(wx, true); if (wx->gpio_ctrl) ngbe_sfp_modules_txrx_powerctl(wx, true); + phy_start(wx->phydev); } @@ -187,12 +375,39 @@ static int ngbe_open(struct net_device *netdev) int err; wx_control_hw(wx, true); - err = ngbe_phy_connect(wx); + + err = wx_setup_resources(wx); if (err) return err; + + wx_configure(wx); + + err = ngbe_request_irq(wx); + if (err) + goto err_free_resources; + + err = ngbe_phy_connect(wx); + if (err) + goto err_free_irq; + + err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues); + if (err) + goto err_dis_phy; + + err = netif_set_real_num_rx_queues(netdev, wx->num_rx_queues); + if (err) + goto err_dis_phy; + ngbe_up(wx); return 0; +err_dis_phy: + phy_disconnect(wx->phydev); +err_free_irq: + wx_free_irq(wx); +err_free_resources: + wx_free_resources(wx); + return err; } /** @@ -211,18 +426,14 @@ static int ngbe_close(struct net_device *netdev) struct wx *wx = netdev_priv(netdev); ngbe_down(wx); + wx_free_irq(wx); + wx_free_resources(wx); phy_disconnect(wx->phydev); wx_control_hw(wx, false); return 0; } -static netdev_tx_t ngbe_xmit_frame(struct sk_buff *skb, - struct net_device *netdev) -{ - return NETDEV_TX_OK; -} - static void ngbe_dev_shutdown(struct pci_dev *pdev, bool *enable_wake) { struct wx *wx = pci_get_drvdata(pdev); @@ -258,9 +469,11 @@ static void ngbe_shutdown(struct pci_dev *pdev) static const struct net_device_ops ngbe_netdev_ops = { .ndo_open = ngbe_open, .ndo_stop = ngbe_close, - .ndo_start_xmit = ngbe_xmit_frame, + .ndo_start_xmit = wx_xmit_frame, + .ndo_set_rx_mode = wx_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, + .ndo_get_stats64 = wx_get_stats64, }; /** @@ -336,6 +549,17 @@ static int ngbe_probe(struct pci_dev *pdev, netdev->netdev_ops = &ngbe_netdev_ops; netdev->features |= NETIF_F_HIGHDMA; + netdev->features = NETIF_F_SG; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | + NETIF_F_RXALL; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_SUPP_NOFCS; + + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = NGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); wx->bd_number = func_nums; /* setup the private structure */ @@ -411,10 +635,14 @@ static int ngbe_probe(struct pci_dev *pdev, eth_hw_addr_set(netdev, wx->mac.perm_addr); wx_mac_set_default_filter(wx, wx->mac.perm_addr); + err = wx_init_interrupt_scheme(wx); + if (err) + goto err_free_mac_table; + /* phy Interface Configuration */ err = ngbe_mdio_init(wx); if (err) - goto err_free_mac_table; + goto err_clear_interrupt_scheme; err = register_netdev(netdev); if (err) @@ -431,6 +659,8 @@ static int ngbe_probe(struct pci_dev *pdev, err_register: wx_control_hw(wx, false); +err_clear_interrupt_scheme: + wx_clear_interrupt_scheme(wx); err_free_mac_table: kfree(wx->mac_table); err_pci_release_regions: @@ -462,6 +692,7 @@ static void ngbe_remove(struct pci_dev *pdev) pci_select_bars(pdev, IORESOURCE_MEM)); kfree(wx->mac_table); + wx_clear_interrupt_scheme(wx); pci_disable_pcie_error_reporting(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h index fd71260f73de..a2351349785e 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h @@ -90,6 +90,20 @@ enum NGBE_MSCA_CMD_value { #define NGBE_GPIO_DDR_0 BIT(0) /* SDP0 IO direction */ #define NGBE_GPIO_DDR_1 BIT(1) /* SDP1 IO direction */ +/* Extended Interrupt Enable Set */ +#define NGBE_PX_MISC_IEN_DEV_RST BIT(10) +#define NGBE_PX_MISC_IEN_ETH_LK BIT(18) +#define NGBE_PX_MISC_IEN_INT_ERR BIT(20) +#define NGBE_PX_MISC_IEN_GPIO BIT(26) +#define NGBE_PX_MISC_IEN_MASK ( \ + NGBE_PX_MISC_IEN_DEV_RST | \ + NGBE_PX_MISC_IEN_ETH_LK | \ + NGBE_PX_MISC_IEN_INT_ERR | \ + NGBE_PX_MISC_IEN_GPIO) + +#define NGBE_INTR_ALL 0x1FF +#define NGBE_INTR_MISC(A) BIT((A)->num_q_vectors) + #define NGBE_PHY_CONFIG(reg_offset) (0x14000 + ((reg_offset) * 4)) #define NGBE_CFG_LAN_SPEED 0x14440 #define NGBE_CFG_PORT_ST 0x14404 @@ -120,6 +134,10 @@ enum NGBE_MSCA_CMD_value { #define NGBE_ETH_LENGTH_OF_ADDRESS 6 #define NGBE_MAX_MSIX_VECTORS 0x09 #define NGBE_RAR_ENTRIES 32 +#define NGBE_RX_PB_SIZE 42 +#define NGBE_MC_TBL_SIZE 128 +#define NGBE_TDB_PB_SZ (20 * 1024) /* 160KB Packet Buffer */ +#define NGBE_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ /* TX/RX descriptor defines */ #define NGBE_DEFAULT_TXD 512 /* default ring size */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index aa4d09df3b01..094df377726b 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -11,6 +11,7 @@ #include <net/ip.h> #include "../libwx/wx_type.h" +#include "../libwx/wx_lib.h" #include "../libwx/wx_hw.h" #include "txgbe_type.h" #include "txgbe_hw.h" @@ -72,9 +73,177 @@ static int txgbe_enumerate_functions(struct wx *wx) return physfns; } +/** + * txgbe_irq_enable - Enable default interrupt generation settings + * @wx: pointer to private structure + * @queues: enable irqs for queues + **/ +static void txgbe_irq_enable(struct wx *wx, bool queues) +{ + /* unmask interrupt */ + wx_intr_enable(wx, TXGBE_INTR_MISC(wx)); + if (queues) + wx_intr_enable(wx, TXGBE_INTR_QALL(wx)); +} + +/** + * txgbe_intr - msi/legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t txgbe_intr(int __always_unused irq, void *data) +{ + struct wx_q_vector *q_vector; + struct wx *wx = data; + struct pci_dev *pdev; + u32 eicr; + + q_vector = wx->q_vector[0]; + pdev = wx->pdev; + + eicr = wx_misc_isb(wx, WX_ISB_VEC0); + if (!eicr) { + /* shared interrupt alert! + * the interrupt that we masked before the ICR read. + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, true); + return IRQ_NONE; /* Not our interrupt */ + } + wx->isb_mem[WX_ISB_VEC0] = 0; + if (!(pdev->msi_enabled)) + wr32(wx, WX_PX_INTA, 1); + + wx->isb_mem[WX_ISB_MISC] = 0; + /* would disable interrupts here but it is auto disabled */ + napi_schedule_irqoff(&q_vector->napi); + + /* re-enable link(maybe) and non-queue interrupts, no flush. + * txgbe_poll will re-enable the queue interrupts + */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +static irqreturn_t txgbe_msix_other(int __always_unused irq, void *data) +{ + struct wx *wx = data; + + /* re-enable the original interrupt state */ + if (netif_running(wx->netdev)) + txgbe_irq_enable(wx, false); + + return IRQ_HANDLED; +} + +/** + * txgbe_request_msix_irqs - Initialize MSI-X interrupts + * @wx: board private structure + * + * Allocate MSI-X vectors and request interrupts from the kernel. + **/ +static int txgbe_request_msix_irqs(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + int vector, err; + + for (vector = 0; vector < wx->num_q_vectors; vector++) { + struct wx_q_vector *q_vector = wx->q_vector[vector]; + struct msix_entry *entry = &wx->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-TxRx-%d", netdev->name, entry->entry); + else + /* skip this unused q_vector */ + continue; + + err = request_irq(entry->vector, wx_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + wx_err(wx, "request_irq failed for MSIX interrupt %s Error: %d\n", + q_vector->name, err); + goto free_queue_irqs; + } + } + + err = request_irq(wx->msix_entries[vector].vector, + txgbe_msix_other, 0, netdev->name, wx); + if (err) { + wx_err(wx, "request_irq for msix_other failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(wx->msix_entries[vector].vector, + wx->q_vector[vector]); + } + wx_reset_interrupt_capability(wx); + return err; +} + +/** + * txgbe_request_irq - initialize interrupts + * @wx: board private structure + * + * Attempt to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int txgbe_request_irq(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + struct pci_dev *pdev = wx->pdev; + int err; + + if (pdev->msix_enabled) + err = txgbe_request_msix_irqs(wx); + else if (pdev->msi_enabled) + err = request_irq(wx->pdev->irq, &txgbe_intr, 0, + netdev->name, wx); + else + err = request_irq(wx->pdev->irq, &txgbe_intr, IRQF_SHARED, + netdev->name, wx); + + if (err) + wx_err(wx, "request_irq failed, Error %d\n", err); + + return err; +} + static void txgbe_up_complete(struct wx *wx) { + u32 reg; + wx_control_hw(wx, true); + wx_configure_vectors(wx); + + /* make sure to complete pre-operations */ + smp_mb__before_atomic(); + wx_napi_enable_all(wx); + + /* clear any pending interrupts, may auto mask */ + rd32(wx, WX_PX_IC); + rd32(wx, WX_PX_MISC_IC); + txgbe_irq_enable(wx, true); + + /* Configure MAC Rx and Tx when link is up */ + reg = rd32(wx, WX_MAC_RX_CFG); + wr32(wx, WX_MAC_RX_CFG, reg); + wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR); + reg = rd32(wx, WX_MAC_WDG_TIMEOUT); + wr32(wx, WX_MAC_WDG_TIMEOUT, reg); + reg = rd32(wx, WX_MAC_TX_CFG); + wr32(wx, WX_MAC_TX_CFG, (reg & ~WX_MAC_TX_CFG_SPEED_MASK) | WX_MAC_TX_CFG_SPEED_10G); + + /* enable transmits */ + netif_tx_start_all_queues(wx->netdev); + netif_carrier_on(wx->netdev); } static void txgbe_reset(struct wx *wx) @@ -96,14 +265,24 @@ static void txgbe_reset(struct wx *wx) static void txgbe_disable_device(struct wx *wx) { struct net_device *netdev = wx->netdev; + u32 i; wx_disable_pcie_master(wx); /* disable receives */ wx_disable_rx(wx); + /* disable all enabled rx queues */ + for (i = 0; i < wx->num_rx_queues; i++) + /* this call also flushes the previous write */ + wx_disable_rx_queue(wx, wx->rx_ring[i]); + + netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); netif_tx_disable(netdev); + wx_irq_disable(wx); + wx_napi_disable_all(wx); + if (wx->bus.func < 2) wr32m(wx, TXGBE_MIS_PRB_CTL, TXGBE_MIS_PRB_CTL_LAN_UP(wx->bus.func), 0); else @@ -116,6 +295,13 @@ static void txgbe_disable_device(struct wx *wx) wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0); } + /* disable transmits in the hardware now that interrupts are off */ + for (i = 0; i < wx->num_tx_queues; i++) { + u8 reg_idx = wx->tx_ring[i]->reg_idx; + + wr32(wx, WX_PX_TR_CFG(reg_idx), WX_PX_TR_CFG_SWFLSH); + } + /* Disable the Tx DMA engine */ wr32m(wx, WX_TDM_CTL, WX_TDM_CTL_TE, 0); } @@ -124,6 +310,9 @@ static void txgbe_down(struct wx *wx) { txgbe_disable_device(wx); txgbe_reset(wx); + + wx_clean_all_tx_rings(wx); + wx_clean_all_rx_rings(wx); } /** @@ -132,12 +321,15 @@ static void txgbe_down(struct wx *wx) **/ static int txgbe_sw_init(struct wx *wx) { + u16 msix_count = 0; int err; wx->mac.num_rar_entries = TXGBE_SP_RAR_ENTRIES; wx->mac.max_tx_queues = TXGBE_SP_MAX_TX_QUEUES; wx->mac.max_rx_queues = TXGBE_SP_MAX_RX_QUEUES; wx->mac.mcft_size = TXGBE_SP_MC_TBL_SIZE; + wx->mac.rx_pb_size = TXGBE_SP_RX_PB_SIZE; + wx->mac.tx_pb_size = TXGBE_SP_TDB_PB_SZ; /* PCI config space info */ err = wx_sw_init(wx); @@ -156,6 +348,25 @@ static int txgbe_sw_init(struct wx *wx) break; } + /* Set common capability flags and settings */ + wx->max_q_vectors = TXGBE_MAX_MSIX_VECTORS; + err = wx_get_pcie_msix_counts(wx, &msix_count, TXGBE_MAX_MSIX_VECTORS); + if (err) + wx_err(wx, "Do not support MSI-X\n"); + wx->mac.max_msix_vectors = msix_count; + + /* enable itr by default in dynamic mode */ + wx->rx_itr_setting = 1; + wx->tx_itr_setting = 1; + + /* set default ring sizes */ + wx->tx_ring_count = TXGBE_DEFAULT_TXD; + wx->rx_ring_count = TXGBE_DEFAULT_RXD; + + /* set default work limits */ + wx->tx_work_limit = TXGBE_DEFAULT_TX_WORK; + wx->rx_work_limit = TXGBE_DEFAULT_RX_WORK; + return 0; } @@ -171,10 +382,39 @@ static int txgbe_sw_init(struct wx *wx) static int txgbe_open(struct net_device *netdev) { struct wx *wx = netdev_priv(netdev); + int err; + + err = wx_setup_resources(wx); + if (err) + goto err_reset; + + wx_configure(wx); + + err = txgbe_request_irq(wx); + if (err) + goto err_free_isb; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, wx->num_tx_queues); + if (err) + goto err_free_irq; + + err = netif_set_real_num_rx_queues(netdev, wx->num_rx_queues); + if (err) + goto err_free_irq; txgbe_up_complete(wx); return 0; + +err_free_irq: + wx_free_irq(wx); +err_free_isb: + wx_free_isb_resources(wx); +err_reset: + txgbe_reset(wx); + + return err; } /** @@ -187,6 +427,7 @@ static int txgbe_open(struct net_device *netdev) static void txgbe_close_suspend(struct wx *wx) { txgbe_disable_device(wx); + wx_free_resources(wx); } /** @@ -205,6 +446,8 @@ static int txgbe_close(struct net_device *netdev) struct wx *wx = netdev_priv(netdev); txgbe_down(wx); + wx_free_irq(wx); + wx_free_resources(wx); wx_control_hw(wx, false); return 0; @@ -240,18 +483,14 @@ static void txgbe_shutdown(struct pci_dev *pdev) } } -static netdev_tx_t txgbe_xmit_frame(struct sk_buff *skb, - struct net_device *netdev) -{ - return NETDEV_TX_OK; -} - static const struct net_device_ops txgbe_netdev_ops = { .ndo_open = txgbe_open, .ndo_stop = txgbe_close, - .ndo_start_xmit = txgbe_xmit_frame, + .ndo_start_xmit = wx_xmit_frame, + .ndo_set_rx_mode = wx_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = wx_set_mac, + .ndo_get_stats64 = wx_get_stats64, }; /** @@ -354,6 +593,16 @@ static int txgbe_probe(struct pci_dev *pdev, } netdev->features |= NETIF_F_HIGHDMA; + netdev->features = NETIF_F_SG; + + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | NETIF_F_RXALL; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_SUPP_NOFCS; + + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = TXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); /* make sure the EEPROM is good */ err = txgbe_validate_eeprom_checksum(wx, NULL); @@ -367,6 +616,10 @@ static int txgbe_probe(struct pci_dev *pdev, eth_hw_addr_set(netdev, wx->mac.perm_addr); wx_mac_set_default_filter(wx, wx->mac.perm_addr); + err = wx_init_interrupt_scheme(wx); + if (err) + goto err_free_mac_table; + /* Save off EEPROM version number and Option Rom version which * together make a unique identify for the eeprom */ @@ -411,6 +664,8 @@ static int txgbe_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, wx); + netif_tx_stop_all_queues(netdev); + /* calculate the expected PCIe bandwidth required for optimal * performance. Note that some older parts will never have enough * bandwidth due to being older generation PCIe parts. We clamp these @@ -435,6 +690,7 @@ static int txgbe_probe(struct pci_dev *pdev, return 0; err_release_hw: + wx_clear_interrupt_scheme(wx); wx_control_hw(wx, false); err_free_mac_table: kfree(wx->mac_table); @@ -468,6 +724,7 @@ static void txgbe_remove(struct pci_dev *pdev) pci_select_bars(pdev, IORESOURCE_MEM)); kfree(wx->mac_table); + wx_clear_interrupt_scheme(wx); pci_disable_pcie_error_reporting(pdev); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index cbd705a9f4bd..563ea51deca6 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -67,6 +67,7 @@ #define TXGBE_PBANUM1_PTR 0x06 #define TXGBE_PBANUM_PTR_GUARD 0xFAFA +#define TXGBE_MAX_MSIX_VECTORS 64 #define TXGBE_MAX_FDIR_INDICES 63 #define TXGBE_MAX_RX_QUEUES (TXGBE_MAX_FDIR_INDICES + 1) @@ -76,6 +77,26 @@ #define TXGBE_SP_MAX_RX_QUEUES 128 #define TXGBE_SP_RAR_ENTRIES 128 #define TXGBE_SP_MC_TBL_SIZE 128 +#define TXGBE_SP_RX_PB_SIZE 512 +#define TXGBE_SP_TDB_PB_SZ (160 * 1024) /* 160KB Packet Buffer */ +#define TXGBE_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */ + +/* TX/RX descriptor defines */ +#define TXGBE_DEFAULT_TXD 512 +#define TXGBE_DEFAULT_TX_WORK 256 + +#if (PAGE_SIZE < 8192) +#define TXGBE_DEFAULT_RXD 512 +#define TXGBE_DEFAULT_RX_WORK 256 +#else +#define TXGBE_DEFAULT_RXD 256 +#define TXGBE_DEFAULT_RX_WORK 128 +#endif + +#define TXGBE_INTR_MISC(A) BIT((A)->num_q_vectors) +#define TXGBE_INTR_QALL(A) (TXGBE_INTR_MISC(A) - 1) + +#define TXGBE_MAX_EITR GENMASK(11, 3) extern char txgbe_driver_name[]; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index e02d1e3ef672..79f4e13620a4 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1034,7 +1034,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, packet->dma_range = kcalloc(page_count, sizeof(*packet->dma_range), - GFP_KERNEL); + GFP_ATOMIC); if (!packet->dma_range) return -ENOMEM; diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index f9b219e6cd58..a9b139bbdb2c 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2559,6 +2559,8 @@ static int netvsc_probe(struct hv_device *dev, netdev_lockdep_set_classes(net); + net->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + /* MTU range: 68 - 1500 or 65521 */ net->min_mtu = NETVSC_MTU_MIN; if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index bea2da1c4c51..2cb1710f6ac3 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -182,6 +182,41 @@ static bool gsi_channel_initialized(struct gsi_channel *channel) return !!channel->gsi; } +/* Encode the channel protocol for the CH_C_CNTXT_0 register */ +static u32 ch_c_cntxt_0_type_encode(enum ipa_version version, + enum gsi_channel_type type) +{ + u32 val; + + val = u32_encode_bits(type, CHTYPE_PROTOCOL_FMASK); + if (version < IPA_VERSION_4_5) + return val; + + type >>= hweight32(CHTYPE_PROTOCOL_FMASK); + + return val | u32_encode_bits(type, CHTYPE_PROTOCOL_MSB_FMASK); +} + +/* Encode a channel ring buffer length for the CH_C_CNTXT_1 register */ +static u32 ch_c_cntxt_1_length_encode(enum ipa_version version, u32 length) +{ + if (version < IPA_VERSION_4_9) + return u32_encode_bits(length, GENMASK(15, 0)); + + return u32_encode_bits(length, GENMASK(19, 0)); +} + +/* Encode the length of the event channel ring buffer for the + * EV_CH_E_CNTXT_1 register. + */ +static u32 ev_ch_e_cntxt_1_length_encode(enum ipa_version version, u32 length) +{ + if (version < IPA_VERSION_4_9) + return u32_encode_bits(length, GENMASK(15, 0)); + + return u32_encode_bits(length, GENMASK(19, 0)); +} + /* Update the GSI IRQ type register with the cached value */ static void gsi_irq_type_update(struct gsi *gsi, u32 val) { @@ -191,12 +226,12 @@ static void gsi_irq_type_update(struct gsi *gsi, u32 val) static void gsi_irq_type_enable(struct gsi *gsi, enum gsi_irq_type_id type_id) { - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(type_id)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | type_id); } static void gsi_irq_type_disable(struct gsi *gsi, enum gsi_irq_type_id type_id) { - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~BIT(type_id)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap & ~type_id); } /* Event ring commands are performed one at a time. Their completion @@ -292,19 +327,19 @@ static void gsi_irq_enable(struct gsi *gsi) /* Global interrupts include hardware error reports. Enable * that so we can at least report the error should it occur. */ - iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GLOB_EE)); + iowrite32(ERROR_INT, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | GSI_GLOB_EE); /* General GSI interrupts are reported to all EEs; if they occur * they are unrecoverable (without reset). A breakpoint interrupt * also exists, but we don't support that. We want to be notified * of errors so we can report them, even if they can't be handled. */ - val = BIT(BUS_ERROR); - val |= BIT(CMD_FIFO_OVRFLOW); - val |= BIT(MCS_STACK_OVRFLOW); + val = BUS_ERROR; + val |= CMD_FIFO_OVRFLOW; + val |= MCS_STACK_OVRFLOW; iowrite32(val, gsi->virt + GSI_CNTXT_GSI_IRQ_EN_OFFSET); - gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | BIT(GSI_GENERAL)); + gsi_irq_type_update(gsi, gsi->type_enabled_bitmap | GSI_GENERAL); } /* Disable all GSI interrupt types */ @@ -676,7 +711,7 @@ static void gsi_evt_ring_program(struct gsi *gsi, u32 evt_ring_id) iowrite32(val, gsi->virt + GSI_EV_CH_E_CNTXT_0_OFFSET(evt_ring_id)); size = ring->count * GSI_RING_ELEMENT_SIZE; - val = ev_r_length_encoded(gsi->version, size); + val = ev_ch_e_cntxt_1_length_encode(gsi->version, size); iowrite32(val, gsi->virt + GSI_EV_CH_E_CNTXT_1_OFFSET(evt_ring_id)); /* The context 2 and 3 registers store the low-order and @@ -765,14 +800,14 @@ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell) u32 val; /* We program all channels as GPI type/protocol */ - val = chtype_protocol_encoded(gsi->version, GSI_CHANNEL_TYPE_GPI); + val = ch_c_cntxt_0_type_encode(gsi->version, GSI_CHANNEL_TYPE_GPI); if (channel->toward_ipa) val |= CHTYPE_DIR_FMASK; val |= u32_encode_bits(channel->evt_ring_id, ERINDEX_FMASK); val |= u32_encode_bits(GSI_RING_ELEMENT_SIZE, ELEMENT_SIZE_FMASK); iowrite32(val, gsi->virt + GSI_CH_C_CNTXT_0_OFFSET(channel_id)); - val = r_length_encoded(gsi->version, size); + val = ch_c_cntxt_1_length_encode(gsi->version, size); iowrite32(val, gsi->virt + GSI_CH_C_CNTXT_1_OFFSET(channel_id)); /* The context 2 and 3 registers store the low-order and @@ -1195,15 +1230,15 @@ static void gsi_isr_glob_ee(struct gsi *gsi) val = ioread32(gsi->virt + GSI_CNTXT_GLOB_IRQ_STTS_OFFSET); - if (val & BIT(ERROR_INT)) + if (val & ERROR_INT) gsi_isr_glob_err(gsi); iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_CLR_OFFSET); - val &= ~BIT(ERROR_INT); + val &= ~ERROR_INT; - if (val & BIT(GP_INT1)) { - val ^= BIT(GP_INT1); + if (val & GP_INT1) { + val ^= GP_INT1; gsi_isr_gp_int1(gsi); } @@ -1264,19 +1299,19 @@ static irqreturn_t gsi_isr(int irq, void *dev_id) intr_mask ^= gsi_intr; switch (gsi_intr) { - case BIT(GSI_CH_CTRL): + case GSI_CH_CTRL: gsi_isr_chan_ctrl(gsi); break; - case BIT(GSI_EV_CTRL): + case GSI_EV_CTRL: gsi_isr_evt_ctrl(gsi); break; - case BIT(GSI_GLOB_EE): + case GSI_GLOB_EE: gsi_isr_glob_ee(gsi); break; - case BIT(GSI_IEOB): + case GSI_IEOB: gsi_isr_ieob(gsi); break; - case BIT(GSI_GENERAL): + case GSI_GENERAL: gsi_isr_general(gsi); break; default: @@ -1654,7 +1689,7 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, * channel), and only from this function. So we enable the GP_INT1 * IRQ type here, and disable it again after the command completes. */ - val = BIT(ERROR_INT) | BIT(GP_INT1); + val = ERROR_INT | GP_INT1; iowrite32(val, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); /* First zero the result code field */ @@ -1666,12 +1701,13 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK); val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK); val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK); - val |= u32_encode_bits(params, GENERIC_PARAMS_FMASK); + if (gsi->version >= IPA_VERSION_4_11) + val |= u32_encode_bits(params, GENERIC_PARAMS_FMASK); timeout = !gsi_command(gsi, GSI_GENERIC_CMD_OFFSET, val); /* Disable the GP_INT1 IRQ type again */ - iowrite32(BIT(ERROR_INT), gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); + iowrite32(ERROR_INT, gsi->virt + GSI_CNTXT_GLOB_IRQ_EN_OFFSET); if (!timeout) return gsi->result; diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index 3763359f208f..d171f65d4198 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -62,6 +62,18 @@ /* All other register offsets are relative to gsi->virt */ +#define GSI_CH_C_CNTXT_0_OFFSET(ch) \ + (0x0001c000 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) +#define CHTYPE_PROTOCOL_FMASK GENMASK(2, 0) +#define CHTYPE_DIR_FMASK GENMASK(3, 3) +#define EE_FMASK GENMASK(7, 4) +#define CHID_FMASK GENMASK(12, 8) +/* The next field is present for IPA v4.5 and above */ +#define CHTYPE_PROTOCOL_MSB_FMASK GENMASK(13, 13) +#define ERINDEX_FMASK GENMASK(18, 14) +#define CHSTATE_FMASK GENMASK(23, 20) +#define ELEMENT_SIZE_FMASK GENMASK(31, 24) + /** enum gsi_channel_type - CHTYPE_PROTOCOL field values in CH_C_CNTXT_0 */ enum gsi_channel_type { GSI_CHANNEL_TYPE_MHI = 0x0, @@ -76,46 +88,9 @@ enum gsi_channel_type { GSI_CHANNEL_TYPE_11AD = 0x9, }; -#define GSI_CH_C_CNTXT_0_OFFSET(ch) \ - (0x0001c000 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) -#define CHTYPE_PROTOCOL_FMASK GENMASK(2, 0) -#define CHTYPE_DIR_FMASK GENMASK(3, 3) -#define EE_FMASK GENMASK(7, 4) -#define CHID_FMASK GENMASK(12, 8) -/* The next field is present for IPA v4.5 and above */ -#define CHTYPE_PROTOCOL_MSB_FMASK GENMASK(13, 13) -#define ERINDEX_FMASK GENMASK(18, 14) -#define CHSTATE_FMASK GENMASK(23, 20) -#define ELEMENT_SIZE_FMASK GENMASK(31, 24) - -/* Encoded value for CH_C_CNTXT_0 register channel protocol fields */ -static inline u32 -chtype_protocol_encoded(enum ipa_version version, enum gsi_channel_type type) -{ - u32 val; - - val = u32_encode_bits(type, CHTYPE_PROTOCOL_FMASK); - if (version < IPA_VERSION_4_5) - return val; - - /* Encode upper bit(s) as well */ - type >>= hweight32(CHTYPE_PROTOCOL_FMASK); - val |= u32_encode_bits(type, CHTYPE_PROTOCOL_MSB_FMASK); - - return val; -} - #define GSI_CH_C_CNTXT_1_OFFSET(ch) \ (0x0001c004 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) -/* Encoded value for CH_C_CNTXT_1 register R_LENGTH field */ -static inline u32 r_length_encoded(enum ipa_version version, u32 length) -{ - if (version < IPA_VERSION_4_9) - return u32_encode_bits(length, GENMASK(15, 0)); - return u32_encode_bits(length, GENMASK(19, 0)); -} - #define GSI_CH_C_CNTXT_2_OFFSET(ch) \ (0x0001c008 + 0x4000 * GSI_EE_AP + 0x80 * (ch)) @@ -167,13 +142,6 @@ enum gsi_prefetch_mode { #define GSI_EV_CH_E_CNTXT_1_OFFSET(ev) \ (0x0001d004 + 0x4000 * GSI_EE_AP + 0x80 * (ev)) -/* Encoded value for EV_CH_C_CNTXT_1 register EV_R_LENGTH field */ -static inline u32 ev_r_length_encoded(enum ipa_version version, u32 length) -{ - if (version < IPA_VERSION_4_9) - return u32_encode_bits(length, GENMASK(15, 0)); - return u32_encode_bits(length, GENMASK(19, 0)); -} #define GSI_EV_CH_E_CNTXT_2_OFFSET(ev) \ (0x0001d008 + 0x4000 * GSI_EE_AP + 0x80 * (ev)) @@ -299,15 +267,25 @@ enum gsi_iram_size { #define GSI_CNTXT_TYPE_IRQ_MSK_OFFSET \ (0x0001f088 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the TYPE_IRQ and TYPE_IRQ_MSK registers */ +/** + * enum gsi_irq_type_id: GSI IRQ types + * @GSI_CH_CTRL: Channel allocation, deallocation, etc. + * @GSI_EV_CTRL: Event ring allocation, deallocation, etc. + * @GSI_GLOB_EE: Global/general event + * @GSI_IEOB: Transfer (TRE) completion + * @GSI_INTER_EE_CH_CTRL: Remote-issued stop/reset (unused) + * @GSI_INTER_EE_EV_CTRL: Remote-issued event reset (unused) + * @GSI_GENERAL: General hardware event (bus error, etc.) + */ enum gsi_irq_type_id { - GSI_CH_CTRL = 0x0, /* channel allocation, etc. */ - GSI_EV_CTRL = 0x1, /* event ring allocation, etc. */ - GSI_GLOB_EE = 0x2, /* global/general event */ - GSI_IEOB = 0x3, /* TRE completion */ - GSI_INTER_EE_CH_CTRL = 0x4, /* remote-issued stop/reset (unused) */ - GSI_INTER_EE_EV_CTRL = 0x5, /* remote-issued event reset (unused) */ - GSI_GENERAL = 0x6, /* general-purpose event */ + GSI_CH_CTRL = BIT(0), + GSI_EV_CTRL = BIT(1), + GSI_GLOB_EE = BIT(2), + GSI_IEOB = BIT(3), + GSI_INTER_EE_CH_CTRL = BIT(4), + GSI_INTER_EE_EV_CTRL = BIT(5), + GSI_GENERAL = BIT(6), + /* IRQ types 7-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_SRC_CH_IRQ_OFFSET \ @@ -343,12 +321,14 @@ enum gsi_irq_type_id { (0x0001f108 + 0x4000 * GSI_EE_AP) #define GSI_CNTXT_GLOB_IRQ_CLR_OFFSET \ (0x0001f110 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the GLOB_IRQ_* registers */ + +/** enum gsi_global_irq_id: Global GSI interrupt events */ enum gsi_global_irq_id { - ERROR_INT = 0x0, - GP_INT1 = 0x1, - GP_INT2 = 0x2, - GP_INT3 = 0x3, + ERROR_INT = BIT(0), + GP_INT1 = BIT(1), + GP_INT2 = BIT(2), + GP_INT3 = BIT(3), + /* Global IRQ types 4-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_GSI_IRQ_STTS_OFFSET \ @@ -357,12 +337,14 @@ enum gsi_global_irq_id { (0x0001f120 + 0x4000 * GSI_EE_AP) #define GSI_CNTXT_GSI_IRQ_CLR_OFFSET \ (0x0001f128 + 0x4000 * GSI_EE_AP) -/* Values here are bit positions in the (general) GSI_IRQ_* registers */ -enum gsi_general_id { - BREAK_POINT = 0x0, - BUS_ERROR = 0x1, - CMD_FIFO_OVRFLOW = 0x2, - MCS_STACK_OVRFLOW = 0x3, + +/** enum gsi_general_irq_id: GSI general IRQ conditions */ +enum gsi_general_irq_id { + BREAK_POINT = BIT(0), + BUS_ERROR = BIT(1), + CMD_FIFO_OVRFLOW = BIT(2), + MCS_STACK_OVRFLOW = BIT(3), + /* General IRQ types 4-31 (and their bit values) are reserved */ }; #define GSI_CNTXT_INTSET_OFFSET \ @@ -372,7 +354,6 @@ enum gsi_general_id { #define GSI_ERROR_LOG_OFFSET \ (0x0001f200 + 0x4000 * GSI_EE_AP) -/* Fields below are present for IPA v3.5.1 and above */ #define ERR_ARG3_FMASK GENMASK(3, 0) #define ERR_ARG2_FMASK GENMASK(7, 4) #define ERR_ARG1_FMASK GENMASK(11, 8) diff --git a/drivers/net/ipa/ipa.h b/drivers/net/ipa/ipa.h index 5372db58b5bd..f3355e040a9e 100644 --- a/drivers/net/ipa/ipa.h +++ b/drivers/net/ipa/ipa.h @@ -45,7 +45,6 @@ struct ipa_interrupt; * @interrupt: IPA Interrupt information * @uc_powered: true if power is active by proxy for microcontroller * @uc_loaded: true after microcontroller has reported it's ready - * @reg_addr: DMA address used for IPA register access * @reg_virt: Virtual address used for IPA register access * @regs: IPA register definitions * @mem_addr: DMA address of IPA-local memory space @@ -97,9 +96,8 @@ struct ipa { bool uc_powered; bool uc_loaded; - dma_addr_t reg_addr; void __iomem *reg_virt; - const struct ipa_regs *regs; + const struct regs *regs; dma_addr_t mem_addr; void *mem_virt; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 16169641ddeb..f1419fbd776c 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -287,7 +287,7 @@ static bool ipa_cmd_register_write_offset_valid(struct ipa *ipa, /* Check whether offsets passed to register_write are valid */ static bool ipa_cmd_register_write_valid(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; const char *name; u32 offset; @@ -300,7 +300,7 @@ static bool ipa_cmd_register_write_valid(struct ipa *ipa) else reg = ipa_reg(ipa, FILT_ROUT_CACHE_FLUSH); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); name = "filter/route hash flush"; if (!ipa_cmd_register_write_offset_valid(ipa, name, offset)) return false; @@ -314,7 +314,7 @@ static bool ipa_cmd_register_write_valid(struct ipa *ipa) * fits in the register write command field(s) that must hold it. */ reg = ipa_reg(ipa, ENDP_STATUS); - offset = ipa_reg_n_offset(reg, IPA_ENDPOINT_COUNT - 1); + offset = reg_n_offset(reg, IPA_ENDPOINT_COUNT - 1); name = "maximal endpoint status"; if (!ipa_cmd_register_write_offset_valid(ipa, name, offset)) return false; diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 798dfa4484d5..2ee80ed140b7 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -241,7 +241,7 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, if (!data->toward_ipa) { const struct ipa_endpoint_rx *rx_config; - const struct ipa_reg *reg; + const struct reg *reg; u32 buffer_size; u32 aggr_size; u32 limit; @@ -304,7 +304,7 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, rx_config->aggr_hard_limit); reg = ipa_reg(ipa, ENDP_INIT_AGGR); - limit = ipa_reg_field_max(reg, BYTE_LIMIT); + limit = reg_field_max(reg, BYTE_LIMIT); if (aggr_size > limit) { dev_err(dev, "aggregated size too large for RX endpoint %u (%u KB > %u KB)\n", data->endpoint_id, aggr_size, limit); @@ -447,7 +447,7 @@ static bool ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay) { struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 field_id; u32 offset; bool state; @@ -460,11 +460,11 @@ ipa_endpoint_init_ctrl(struct ipa_endpoint *endpoint, bool suspend_delay) WARN_ON(ipa->version >= IPA_VERSION_4_0); reg = ipa_reg(ipa, ENDP_INIT_CTRL); - offset = ipa_reg_n_offset(reg, endpoint->endpoint_id); + offset = reg_n_offset(reg, endpoint->endpoint_id); val = ioread32(ipa->reg_virt + offset); field_id = endpoint->toward_ipa ? ENDP_DELAY : ENDP_SUSPEND; - mask = ipa_reg_bit(reg, field_id); + mask = reg_bit(reg, field_id); state = !!(val & mask); @@ -493,13 +493,13 @@ static bool ipa_endpoint_aggr_active(struct ipa_endpoint *endpoint) u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, STATE_AGGR_ACTIVE); - val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + val = ioread32(ipa->reg_virt + reg_n_offset(reg, unit)); return !!(val & BIT(endpoint_id % 32)); } @@ -510,12 +510,12 @@ static void ipa_endpoint_force_close(struct ipa_endpoint *endpoint) u32 mask = BIT(endpoint_id % 32); struct ipa *ipa = endpoint->ipa; u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; WARN_ON(!test_bit(endpoint_id, ipa->available)); reg = ipa_reg(ipa, AGGR_FORCE_CLOSE); - iowrite32(mask, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + iowrite32(mask, ipa->reg_virt + reg_n_offset(reg, unit)); } /** @@ -613,7 +613,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) for_each_set_bit(endpoint_id, ipa->defined, ipa->endpoint_count) { struct ipa_endpoint *endpoint; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; /* We only reset modem TX endpoints */ @@ -622,7 +622,7 @@ int ipa_endpoint_modem_exception_reset_all(struct ipa *ipa) continue; reg = ipa_reg(ipa, ENDP_STATUS); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); /* Value written is 0, and all bits are updated. That * means status is disabled on the endpoint, and as a @@ -645,7 +645,7 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; enum ipa_cs_offload_en enabled; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_CFG); @@ -658,7 +658,7 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) /* Checksum header offset is in 4-byte units */ off = sizeof(struct rmnet_map_header) / sizeof(u32); - val |= ipa_reg_encode(reg, CS_METADATA_HDR_OFFSET, off); + val |= reg_encode(reg, CS_METADATA_HDR_OFFSET, off); enabled = version < IPA_VERSION_4_5 ? IPA_CS_OFFLOAD_UL @@ -671,26 +671,26 @@ static void ipa_endpoint_init_cfg(struct ipa_endpoint *endpoint) } else { enabled = IPA_CS_OFFLOAD_NONE; } - val |= ipa_reg_encode(reg, CS_OFFLOAD_EN, enabled); + val |= reg_encode(reg, CS_OFFLOAD_EN, enabled); /* CS_GEN_QMB_MASTER_SEL is 0 */ - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_nat(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (!endpoint->toward_ipa) return; reg = ipa_reg(ipa, ENDP_INIT_NAT); - val = ipa_reg_encode(reg, NAT_EN, IPA_NAT_TYPE_BYPASS); + val = reg_encode(reg, NAT_EN, IPA_NAT_TYPE_BYPASS); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static u32 @@ -716,13 +716,13 @@ ipa_qmap_header_size(enum ipa_version version, struct ipa_endpoint *endpoint) /* Encoded value for ENDP_INIT_HDR register HDR_LEN* field(s) */ static u32 ipa_header_size_encode(enum ipa_version version, - const struct ipa_reg *reg, u32 header_size) + const struct reg *reg, u32 header_size) { - u32 field_max = ipa_reg_field_max(reg, HDR_LEN); + u32 field_max = reg_field_max(reg, HDR_LEN); u32 val; /* We know field_max can be used as a mask (2^n - 1) */ - val = ipa_reg_encode(reg, HDR_LEN, header_size & field_max); + val = reg_encode(reg, HDR_LEN, header_size & field_max); if (version < IPA_VERSION_4_5) { WARN_ON(header_size > field_max); return val; @@ -730,21 +730,21 @@ static u32 ipa_header_size_encode(enum ipa_version version, /* IPA v4.5 adds a few more most-significant bits */ header_size >>= hweight32(field_max); - WARN_ON(header_size > ipa_reg_field_max(reg, HDR_LEN_MSB)); - val |= ipa_reg_encode(reg, HDR_LEN_MSB, header_size); + WARN_ON(header_size > reg_field_max(reg, HDR_LEN_MSB)); + val |= reg_encode(reg, HDR_LEN_MSB, header_size); return val; } /* Encoded value for ENDP_INIT_HDR register OFST_METADATA* field(s) */ static u32 ipa_metadata_offset_encode(enum ipa_version version, - const struct ipa_reg *reg, u32 offset) + const struct reg *reg, u32 offset) { - u32 field_max = ipa_reg_field_max(reg, HDR_OFST_METADATA); + u32 field_max = reg_field_max(reg, HDR_OFST_METADATA); u32 val; /* We know field_max can be used as a mask (2^n - 1) */ - val = ipa_reg_encode(reg, HDR_OFST_METADATA, offset); + val = reg_encode(reg, HDR_OFST_METADATA, offset); if (version < IPA_VERSION_4_5) { WARN_ON(offset > field_max); return val; @@ -752,8 +752,8 @@ static u32 ipa_metadata_offset_encode(enum ipa_version version, /* IPA v4.5 adds a few more most-significant bits */ offset >>= hweight32(field_max); - WARN_ON(offset > ipa_reg_field_max(reg, HDR_OFST_METADATA_MSB)); - val |= ipa_reg_encode(reg, HDR_OFST_METADATA_MSB, offset); + WARN_ON(offset > reg_field_max(reg, HDR_OFST_METADATA_MSB)); + val |= reg_encode(reg, HDR_OFST_METADATA_MSB, offset); return val; } @@ -783,7 +783,7 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_HDR); @@ -806,13 +806,13 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) off = offsetof(struct rmnet_map_header, pkt_len); /* Upper bits are stored in HDR_EXT with IPA v4.5 */ if (version >= IPA_VERSION_4_5) - off &= ipa_reg_field_max(reg, HDR_OFST_PKT_SIZE); + off &= reg_field_max(reg, HDR_OFST_PKT_SIZE); - val |= ipa_reg_bit(reg, HDR_OFST_PKT_SIZE_VALID); - val |= ipa_reg_encode(reg, HDR_OFST_PKT_SIZE, off); + val |= reg_bit(reg, HDR_OFST_PKT_SIZE_VALID); + val |= reg_encode(reg, HDR_OFST_PKT_SIZE, off); } /* For QMAP TX, metadata offset is 0 (modem assumes this) */ - val |= ipa_reg_bit(reg, HDR_OFST_METADATA_VALID); + val |= reg_bit(reg, HDR_OFST_METADATA_VALID); /* HDR_ADDITIONAL_CONST_LEN is 0; (RX only) */ /* HDR_A5_MUX is 0 */ @@ -820,7 +820,7 @@ static void ipa_endpoint_init_hdr(struct ipa_endpoint *endpoint) /* HDR_METADATA_REG_VALID is 0 (TX only, version < v4.5) */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) @@ -828,13 +828,13 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) u32 pad_align = endpoint->config.rx.pad_align; u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_HDR_EXT); if (endpoint->config.qmap) { /* We have a header, so we must specify its endianness */ - val |= ipa_reg_bit(reg, HDR_ENDIANNESS); /* big endian */ + val |= reg_bit(reg, HDR_ENDIANNESS); /* big endian */ /* A QMAP header contains a 6 bit pad field at offset 0. * The RMNet driver assumes this field is meaningful in @@ -844,16 +844,16 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) * (although 0) should be ignored. */ if (!endpoint->toward_ipa) { - val |= ipa_reg_bit(reg, HDR_TOTAL_LEN_OR_PAD_VALID); + val |= reg_bit(reg, HDR_TOTAL_LEN_OR_PAD_VALID); /* HDR_TOTAL_LEN_OR_PAD is 0 (pad, not total_len) */ - val |= ipa_reg_bit(reg, HDR_PAYLOAD_LEN_INC_PADDING); + val |= reg_bit(reg, HDR_PAYLOAD_LEN_INC_PADDING); /* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0 */ } } /* HDR_PAYLOAD_LEN_INC_PADDING is 0 */ if (!endpoint->toward_ipa) - val |= ipa_reg_encode(reg, HDR_PAD_TO_ALIGNMENT, pad_align); + val |= reg_encode(reg, HDR_PAD_TO_ALIGNMENT, pad_align); /* IPA v4.5 adds some most-significant bits to a few fields, * two of which are defined in the HDR (not HDR_EXT) register. @@ -861,25 +861,25 @@ static void ipa_endpoint_init_hdr_ext(struct ipa_endpoint *endpoint) if (ipa->version >= IPA_VERSION_4_5) { /* HDR_TOTAL_LEN_OR_PAD_OFFSET is 0, so MSB is 0 */ if (endpoint->config.qmap && !endpoint->toward_ipa) { - u32 mask = ipa_reg_field_max(reg, HDR_OFST_PKT_SIZE); + u32 mask = reg_field_max(reg, HDR_OFST_PKT_SIZE); u32 off; /* Field offset within header */ off = offsetof(struct rmnet_map_header, pkt_len); /* Low bits are in the ENDP_INIT_HDR register */ off >>= hweight32(mask); - val |= ipa_reg_encode(reg, HDR_OFST_PKT_SIZE_MSB, off); + val |= reg_encode(reg, HDR_OFST_PKT_SIZE_MSB, off); /* HDR_ADDITIONAL_CONST_LEN is 0 so MSB is 0 */ } } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; u32 offset; @@ -887,7 +887,7 @@ static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) return; /* Register not valid for TX endpoints */ reg = ipa_reg(ipa, ENDP_INIT_HDR_METADATA_MASK); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); /* Note that HDR_ENDIANNESS indicates big endian header fields */ if (endpoint->config.qmap) @@ -899,7 +899,7 @@ static void ipa_endpoint_init_hdr_metadata_mask(struct ipa_endpoint *endpoint) static void ipa_endpoint_init_mode(struct ipa_endpoint *endpoint) { struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -911,14 +911,14 @@ static void ipa_endpoint_init_mode(struct ipa_endpoint *endpoint) enum ipa_endpoint_name name = endpoint->config.dma_endpoint; u32 dma_endpoint_id = ipa->name_map[name]->endpoint_id; - val = ipa_reg_encode(reg, ENDP_MODE, IPA_DMA); - val |= ipa_reg_encode(reg, DEST_PIPE_INDEX, dma_endpoint_id); + val = reg_encode(reg, ENDP_MODE, IPA_DMA); + val |= reg_encode(reg, DEST_PIPE_INDEX, dma_endpoint_id); } else { - val = ipa_reg_encode(reg, ENDP_MODE, IPA_BASIC); + val = reg_encode(reg, ENDP_MODE, IPA_BASIC); } /* All other bits unspecified (and 0) */ - offset = ipa_reg_n_offset(reg, endpoint->endpoint_id); + offset = reg_n_offset(reg, endpoint->endpoint_id); iowrite32(val, ipa->reg_virt + offset); } @@ -963,7 +963,7 @@ out: } /* Encode the aggregation timer limit (microseconds) based on IPA version */ -static u32 aggr_time_limit_encode(struct ipa *ipa, const struct ipa_reg *reg, +static u32 aggr_time_limit_encode(struct ipa *ipa, const struct reg *reg, u32 microseconds) { u32 ticks; @@ -972,14 +972,14 @@ static u32 aggr_time_limit_encode(struct ipa *ipa, const struct ipa_reg *reg, if (!microseconds) return 0; /* Nothing to compute if time limit is 0 */ - max = ipa_reg_field_max(reg, TIME_LIMIT); + max = reg_field_max(reg, TIME_LIMIT); if (ipa->version >= IPA_VERSION_4_5) { u32 select; ticks = ipa_qtime_val(ipa, microseconds, max, &select); - return ipa_reg_encode(reg, AGGR_GRAN_SEL, select) | - ipa_reg_encode(reg, TIME_LIMIT, ticks); + return reg_encode(reg, AGGR_GRAN_SEL, select) | + reg_encode(reg, TIME_LIMIT, ticks); } /* We program aggregation granularity in ipa_hardware_config() */ @@ -987,14 +987,14 @@ static u32 aggr_time_limit_encode(struct ipa *ipa, const struct ipa_reg *reg, WARN(ticks > max, "aggr_time_limit too large (%u > %u usec)\n", microseconds, max * IPA_AGGR_GRANULARITY); - return ipa_reg_encode(reg, TIME_LIMIT, ticks); + return reg_encode(reg, TIME_LIMIT, ticks); } static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_INIT_AGGR); @@ -1005,13 +1005,13 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) u32 limit; rx_config = &endpoint->config.rx; - val |= ipa_reg_encode(reg, AGGR_EN, IPA_ENABLE_AGGR); - val |= ipa_reg_encode(reg, AGGR_TYPE, IPA_GENERIC); + val |= reg_encode(reg, AGGR_EN, IPA_ENABLE_AGGR); + val |= reg_encode(reg, AGGR_TYPE, IPA_GENERIC); buffer_size = rx_config->buffer_size; limit = ipa_aggr_size_kb(buffer_size - NET_SKB_PAD, rx_config->aggr_hard_limit); - val |= ipa_reg_encode(reg, BYTE_LIMIT, limit); + val |= reg_encode(reg, BYTE_LIMIT, limit); limit = rx_config->aggr_time_limit; val |= aggr_time_limit_encode(ipa, reg, limit); @@ -1019,20 +1019,20 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) /* AGGR_PKT_LIMIT is 0 (unlimited) */ if (rx_config->aggr_close_eof) - val |= ipa_reg_bit(reg, SW_EOF_ACTIVE); + val |= reg_bit(reg, SW_EOF_ACTIVE); } else { - val |= ipa_reg_encode(reg, AGGR_EN, IPA_ENABLE_DEAGGR); - val |= ipa_reg_encode(reg, AGGR_TYPE, IPA_QCMAP); + val |= reg_encode(reg, AGGR_EN, IPA_ENABLE_DEAGGR); + val |= reg_encode(reg, AGGR_TYPE, IPA_QCMAP); /* other fields ignored */ } /* AGGR_FORCE_CLOSE is 0 */ /* AGGR_GRAN_SEL is 0 for IPA v4.5 */ } else { - val |= ipa_reg_encode(reg, AGGR_EN, IPA_BYPASS_AGGR); + val |= reg_encode(reg, AGGR_EN, IPA_BYPASS_AGGR); /* other fields ignored */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } /* The head-of-line blocking timer is defined as a tick count. For @@ -1043,7 +1043,7 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) * Return the encoded value representing the timeout period provided * that should be written to the ENDP_INIT_HOL_BLOCK_TIMER register. */ -static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, +static u32 hol_block_timer_encode(struct ipa *ipa, const struct reg *reg, u32 microseconds) { u32 width; @@ -1057,14 +1057,14 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, return 0; /* Nothing to compute if timer period is 0 */ if (ipa->version >= IPA_VERSION_4_5) { - u32 max = ipa_reg_field_max(reg, TIMER_LIMIT); + u32 max = reg_field_max(reg, TIMER_LIMIT); u32 select; u32 ticks; ticks = ipa_qtime_val(ipa, microseconds, max, &select); - return ipa_reg_encode(reg, TIMER_GRAN_SEL, 1) | - ipa_reg_encode(reg, TIMER_LIMIT, ticks); + return reg_encode(reg, TIMER_GRAN_SEL, 1) | + reg_encode(reg, TIMER_LIMIT, ticks); } /* Use 64 bit arithmetic to avoid overflow */ @@ -1072,11 +1072,11 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, ticks = DIV_ROUND_CLOSEST(microseconds * rate, 128 * USEC_PER_SEC); /* We still need the result to fit into the field */ - WARN_ON(ticks > ipa_reg_field_max(reg, TIMER_BASE_VALUE)); + WARN_ON(ticks > reg_field_max(reg, TIMER_BASE_VALUE)); /* IPA v3.5.1 through v4.1 just record the tick count */ if (ipa->version < IPA_VERSION_4_2) - return ipa_reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks); + return reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks); /* For IPA v4.2, the tick count is represented by base and * scale fields within the 32-bit timer register, where: @@ -1087,7 +1087,7 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, * such that high bit is included. */ high = fls(ticks); /* 1..32 (or warning above) */ - width = hweight32(ipa_reg_fmask(reg, TIMER_BASE_VALUE)); + width = hweight32(reg_fmask(reg, TIMER_BASE_VALUE)); scale = high > width ? high - width : 0; if (scale) { /* If we're scaling, round up to get a closer result */ @@ -1097,8 +1097,8 @@ static u32 hol_block_timer_encode(struct ipa *ipa, const struct ipa_reg *reg, scale++; } - val = ipa_reg_encode(reg, TIMER_SCALE, scale); - val |= ipa_reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks >> scale); + val = reg_encode(reg, TIMER_SCALE, scale); + val |= reg_encode(reg, TIMER_BASE_VALUE, (u32)ticks >> scale); return val; } @@ -1109,14 +1109,14 @@ static void ipa_endpoint_init_hol_block_timer(struct ipa_endpoint *endpoint, { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* This should only be changed when HOL_BLOCK_EN is disabled */ reg = ipa_reg(ipa, ENDP_INIT_HOL_BLOCK_TIMER); val = hol_block_timer_encode(ipa, reg, microseconds); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void @@ -1124,13 +1124,13 @@ ipa_endpoint_init_hol_block_en(struct ipa_endpoint *endpoint, bool enable) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; reg = ipa_reg(ipa, ENDP_INIT_HOL_BLOCK_EN); - offset = ipa_reg_n_offset(reg, endpoint_id); - val = enable ? ipa_reg_bit(reg, HOL_BLOCK_EN) : 0; + offset = reg_n_offset(reg, endpoint_id); + val = enable ? reg_bit(reg, HOL_BLOCK_EN) : 0; iowrite32(val, ipa->reg_virt + offset); @@ -1171,7 +1171,7 @@ static void ipa_endpoint_init_deaggr(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; if (!endpoint->toward_ipa) @@ -1183,7 +1183,7 @@ static void ipa_endpoint_init_deaggr(struct ipa_endpoint *endpoint) /* PACKET_OFFSET_LOCATION is ignored (not valid) */ /* MAX_PACKET_LEN is 0 (not enforced) */ - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint) @@ -1191,20 +1191,20 @@ static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint) u32 resource_group = endpoint->config.resource_group; u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, ENDP_INIT_RSRC_GRP); - val = ipa_reg_encode(reg, ENDP_RSRC_GRP, resource_group); + val = reg_encode(reg, ENDP_RSRC_GRP, resource_group); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (!endpoint->toward_ipa) @@ -1213,14 +1213,14 @@ static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint) reg = ipa_reg(ipa, ENDP_INIT_SEQ); /* Low-order byte configures primary packet processing */ - val = ipa_reg_encode(reg, SEQ_TYPE, endpoint->config.tx.seq_type); + val = reg_encode(reg, SEQ_TYPE, endpoint->config.tx.seq_type); /* Second byte (if supported) configures replicated packet processing */ if (ipa->version < IPA_VERSION_4_5) - val |= ipa_reg_encode(reg, SEQ_REP_TYPE, - endpoint->config.tx.seq_rep_type); + val |= reg_encode(reg, SEQ_REP_TYPE, + endpoint->config.tx.seq_rep_type); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } /** @@ -1270,12 +1270,12 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 val = 0; reg = ipa_reg(ipa, ENDP_STATUS); if (endpoint->config.status_enable) { - val |= ipa_reg_bit(reg, STATUS_EN); + val |= reg_bit(reg, STATUS_EN); if (endpoint->toward_ipa) { enum ipa_endpoint_name name; u32 status_endpoint_id; @@ -1283,8 +1283,7 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) name = endpoint->config.tx.status_endpoint; status_endpoint_id = ipa->name_map[name]->endpoint_id; - val |= ipa_reg_encode(reg, STATUS_ENDP, - status_endpoint_id); + val |= reg_encode(reg, STATUS_ENDP, status_endpoint_id); } /* STATUS_LOCATION is 0, meaning IPA packet status * precedes the packet (not present for IPA v4.5+) @@ -1292,7 +1291,7 @@ static void ipa_endpoint_status(struct ipa_endpoint *endpoint) /* STATUS_PKT_SUPPRESS_FMASK is 0 (not present for v4.0+) */ } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, endpoint_id)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, endpoint_id)); } static int ipa_endpoint_replenish_one(struct ipa_endpoint *endpoint, @@ -1636,18 +1635,18 @@ void ipa_endpoint_trans_release(struct ipa_endpoint *endpoint, void ipa_endpoint_default_route_set(struct ipa *ipa, u32 endpoint_id) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, ROUTE); /* ROUTE_DIS is 0 */ - val = ipa_reg_encode(reg, ROUTE_DEF_PIPE, endpoint_id); - val |= ipa_reg_bit(reg, ROUTE_DEF_HDR_TABLE); + val = reg_encode(reg, ROUTE_DEF_PIPE, endpoint_id); + val |= reg_bit(reg, ROUTE_DEF_HDR_TABLE); /* ROUTE_DEF_HDR_OFST is 0 */ - val |= ipa_reg_encode(reg, ROUTE_FRAG_DEF_PIPE, endpoint_id); - val |= ipa_reg_bit(reg, ROUTE_DEF_RETAIN_HDR); + val |= reg_encode(reg, ROUTE_FRAG_DEF_PIPE, endpoint_id); + val |= reg_bit(reg, ROUTE_DEF_RETAIN_HDR); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } void ipa_endpoint_default_route_clear(struct ipa *ipa) @@ -1985,7 +1984,7 @@ void ipa_endpoint_deconfig(struct ipa *ipa) int ipa_endpoint_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_reg *reg; + const struct reg *reg; u32 endpoint_id; u32 hw_limit; u32 tx_count; @@ -2019,12 +2018,12 @@ int ipa_endpoint_config(struct ipa *ipa) * the highest one doesn't exceed the number supported by software. */ reg = ipa_reg(ipa, FLAVOR_0); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + val = ioread32(ipa->reg_virt + reg_offset(reg)); /* Our RX is an IPA producer; our TX is an IPA consumer. */ - tx_count = ipa_reg_decode(reg, MAX_CONS_PIPES, val); - rx_count = ipa_reg_decode(reg, MAX_PROD_PIPES, val); - rx_base = ipa_reg_decode(reg, PROD_LOWEST, val); + tx_count = reg_decode(reg, MAX_CONS_PIPES, val); + rx_count = reg_decode(reg, MAX_PROD_PIPES, val); + rx_base = reg_decode(reg, PROD_LOWEST, val); limit = rx_base + rx_count; if (limit > IPA_ENDPOINT_MAX) { diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index 9a1153e80a3a..4bc05948f772 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -47,12 +47,12 @@ struct ipa_interrupt { static void ipa_interrupt_process(struct ipa_interrupt *interrupt, u32 irq_id) { struct ipa *ipa = interrupt->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 mask = BIT(irq_id); u32 offset; reg = ipa_reg(ipa, IPA_IRQ_CLR); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); switch (irq_id) { case IPA_IRQ_UC_0: @@ -85,7 +85,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) struct ipa_interrupt *interrupt = dev_id; struct ipa *ipa = interrupt->ipa; u32 enabled = interrupt->enabled; - const struct ipa_reg *reg; + const struct reg *reg; struct device *dev; u32 pending; u32 offset; @@ -102,7 +102,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) * only the enabled ones. */ reg = ipa_reg(ipa, IPA_IRQ_STTS); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); pending = ioread32(ipa->reg_virt + offset); while ((mask = pending & enabled)) { do { @@ -120,8 +120,7 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) dev_dbg(dev, "clearing disabled IPA interrupts 0x%08x\n", pending); reg = ipa_reg(ipa, IPA_IRQ_CLR); - offset = ipa_reg_offset(reg); - iowrite32(pending, ipa->reg_virt + offset); + iowrite32(pending, ipa->reg_virt + reg_offset(reg)); } out_power_put: pm_runtime_mark_last_busy(dev); @@ -132,9 +131,9 @@ out_power_put: static void ipa_interrupt_enabled_update(struct ipa *ipa) { - const struct ipa_reg *reg = ipa_reg(ipa, IPA_IRQ_EN); + const struct reg *reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(ipa->interrupt->enabled, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(ipa->interrupt->enabled, ipa->reg_virt + reg_offset(reg)); } /* Enable an IPA interrupt type */ @@ -170,7 +169,7 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, struct ipa *ipa = interrupt->ipa; u32 mask = BIT(endpoint_id % 32); u32 unit = endpoint_id / 32; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -181,7 +180,7 @@ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, return; reg = ipa_reg(ipa, IRQ_SUSPEND_EN); - offset = ipa_reg_n_offset(reg, unit); + offset = reg_n_offset(reg, unit); val = ioread32(ipa->reg_virt + offset); if (enable) @@ -215,18 +214,18 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt) unit_count = roundup(ipa->endpoint_count, 32); for (unit = 0; unit < unit_count; unit++) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, IRQ_SUSPEND_INFO); - val = ioread32(ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + val = ioread32(ipa->reg_virt + reg_n_offset(reg, unit)); /* SUSPEND interrupt status isn't cleared on IPA version 3.0 */ if (ipa->version == IPA_VERSION_3_0) continue; reg = ipa_reg(ipa, IRQ_SUSPEND_CLR); - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, unit)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, unit)); } } @@ -241,7 +240,7 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; struct ipa_interrupt *interrupt; - const struct ipa_reg *reg; + const struct reg *reg; unsigned int irq; int ret; @@ -261,7 +260,7 @@ struct ipa_interrupt *ipa_interrupt_config(struct ipa *ipa) /* Start with all IPA interrupts disabled */ reg = ipa_reg(ipa, IPA_IRQ_EN); - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); ret = request_threaded_irq(irq, NULL, ipa_isr_thread, IRQF_ONESHOT, "ipa", interrupt); diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 60d7c558163f..6cb7bf96a626 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -203,7 +203,7 @@ static void ipa_teardown(struct ipa *ipa) static void ipa_hardware_config_bcr(struct ipa *ipa, const struct ipa_data *data) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* IPA v4.5+ has no backward compatibility register */ @@ -212,13 +212,13 @@ ipa_hardware_config_bcr(struct ipa *ipa, const struct ipa_data *data) reg = ipa_reg(ipa, IPA_BCR); val = data->backward_compat; - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } static void ipa_hardware_config_tx(struct ipa *ipa) { enum ipa_version version = ipa->version; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -227,11 +227,11 @@ static void ipa_hardware_config_tx(struct ipa *ipa) /* Disable PA mask to allow HOLB drop */ reg = ipa_reg(ipa, IPA_TX_CFG); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); val = ioread32(ipa->reg_virt + offset); - val &= ~ipa_reg_bit(reg, PA_MASK_EN); + val &= ~reg_bit(reg, PA_MASK_EN); iowrite32(val, ipa->reg_virt + offset); } @@ -239,7 +239,7 @@ static void ipa_hardware_config_tx(struct ipa *ipa) static void ipa_hardware_config_clkon(struct ipa *ipa) { enum ipa_version version = ipa->version; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (version >= IPA_VERSION_4_5) @@ -252,20 +252,20 @@ static void ipa_hardware_config_clkon(struct ipa *ipa) reg = ipa_reg(ipa, CLKON_CFG); if (version == IPA_VERSION_3_1) { /* Disable MISC clock gating */ - val = ipa_reg_bit(reg, CLKON_MISC); + val = reg_bit(reg, CLKON_MISC); } else { /* IPA v4.0+ */ /* Enable open global clocks in the CLKON configuration */ - val = ipa_reg_bit(reg, CLKON_GLOBAL); - val |= ipa_reg_bit(reg, GLOBAL_2X_CLK); + val = reg_bit(reg, CLKON_GLOBAL); + val |= reg_bit(reg, GLOBAL_2X_CLK); } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* Configure bus access behavior for IPA components */ static void ipa_hardware_config_comp(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; @@ -274,21 +274,22 @@ static void ipa_hardware_config_comp(struct ipa *ipa) return; reg = ipa_reg(ipa, COMP_CFG); - offset = ipa_reg_offset(reg); + offset = reg_offset(reg); + val = ioread32(ipa->reg_virt + offset); if (ipa->version == IPA_VERSION_4_0) { - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_CONS_EN); - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_PROD_EN); - val &= ~ipa_reg_bit(reg, IPA_QMB_SELECT_GLOBAL_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_CONS_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_PROD_EN); + val &= ~reg_bit(reg, IPA_QMB_SELECT_GLOBAL_EN); } else if (ipa->version < IPA_VERSION_4_5) { - val |= ipa_reg_bit(reg, GSI_MULTI_AXI_MASTERS_DIS); + val |= reg_bit(reg, GSI_MULTI_AXI_MASTERS_DIS); } else { /* For IPA v4.5 FULL_FLUSH_WAIT_RS_CLOSURE_EN is 0 */ } - val |= ipa_reg_bit(reg, GSI_MULTI_INORDER_RD_DIS); - val |= ipa_reg_bit(reg, GSI_MULTI_INORDER_WR_DIS); + val |= reg_bit(reg, GSI_MULTI_INORDER_RD_DIS); + val |= reg_bit(reg, GSI_MULTI_INORDER_WR_DIS); iowrite32(val, ipa->reg_virt + offset); } @@ -299,7 +300,7 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data) { const struct ipa_qsb_data *data0; const struct ipa_qsb_data *data1; - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* QMB 0 represents DDR; QMB 1 (if present) represents PCIe */ @@ -310,29 +311,27 @@ ipa_hardware_config_qsb(struct ipa *ipa, const struct ipa_data *data) /* Max outstanding write accesses for QSB masters */ reg = ipa_reg(ipa, QSB_MAX_WRITES); - val = ipa_reg_encode(reg, GEN_QMB_0_MAX_WRITES, data0->max_writes); + val = reg_encode(reg, GEN_QMB_0_MAX_WRITES, data0->max_writes); if (data->qsb_count > 1) - val |= ipa_reg_encode(reg, GEN_QMB_1_MAX_WRITES, - data1->max_writes); + val |= reg_encode(reg, GEN_QMB_1_MAX_WRITES, data1->max_writes); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Max outstanding read accesses for QSB masters */ reg = ipa_reg(ipa, QSB_MAX_READS); - val = ipa_reg_encode(reg, GEN_QMB_0_MAX_READS, data0->max_reads); + val = reg_encode(reg, GEN_QMB_0_MAX_READS, data0->max_reads); if (ipa->version >= IPA_VERSION_4_0) - val |= ipa_reg_encode(reg, GEN_QMB_0_MAX_READS_BEATS, - data0->max_reads_beats); + val |= reg_encode(reg, GEN_QMB_0_MAX_READS_BEATS, + data0->max_reads_beats); if (data->qsb_count > 1) { - val = ipa_reg_encode(reg, GEN_QMB_1_MAX_READS, - data1->max_reads); + val = reg_encode(reg, GEN_QMB_1_MAX_READS, data1->max_reads); if (ipa->version >= IPA_VERSION_4_0) - val |= ipa_reg_encode(reg, GEN_QMB_1_MAX_READS_BEATS, - data1->max_reads_beats); + val |= reg_encode(reg, GEN_QMB_1_MAX_READS_BEATS, + data1->max_reads_beats); } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* The internal inactivity timer clock is used for the aggregation timer */ @@ -368,46 +367,47 @@ static __always_inline u32 ipa_aggr_granularity_val(u32 usec) */ static void ipa_qtime_config(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; /* Timer clock divider must be disabled when we change the rate */ reg = ipa_reg(ipa, TIMERS_XO_CLK_DIV_CFG); - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); reg = ipa_reg(ipa, QTIME_TIMESTAMP_CFG); /* Set DPL time stamp resolution to use Qtime (instead of 1 msec) */ - val = ipa_reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT); - val |= ipa_reg_bit(reg, DPL_TIMESTAMP_SEL); + val = reg_encode(reg, DPL_TIMESTAMP_LSB, DPL_TIMESTAMP_SHIFT); + val |= reg_bit(reg, DPL_TIMESTAMP_SEL); /* Configure tag and NAT Qtime timestamp resolution as well */ - val = ipa_reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); - val = ipa_reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); + val = reg_encode(reg, TAG_TIMESTAMP_LSB, TAG_TIMESTAMP_SHIFT); + val = reg_encode(reg, NAT_TIMESTAMP_LSB, NAT_TIMESTAMP_SHIFT); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Set granularity of pulse generators used for other timers */ reg = ipa_reg(ipa, TIMERS_PULSE_GRAN_CFG); - val = ipa_reg_encode(reg, PULSE_GRAN_0, IPA_GRAN_100_US); - val |= ipa_reg_encode(reg, PULSE_GRAN_1, IPA_GRAN_1_MS); + val = reg_encode(reg, PULSE_GRAN_0, IPA_GRAN_100_US); + val |= reg_encode(reg, PULSE_GRAN_1, IPA_GRAN_1_MS); if (ipa->version >= IPA_VERSION_5_0) { - val |= ipa_reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_10_MS); - val |= ipa_reg_encode(reg, PULSE_GRAN_3, IPA_GRAN_10_MS); + val |= reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_10_MS); + val |= reg_encode(reg, PULSE_GRAN_3, IPA_GRAN_10_MS); } else { - val |= ipa_reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_1_MS); + val |= reg_encode(reg, PULSE_GRAN_2, IPA_GRAN_1_MS); } - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); /* Actual divider is 1 more than value supplied here */ reg = ipa_reg(ipa, TIMERS_XO_CLK_DIV_CFG); - offset = ipa_reg_offset(reg); - val = ipa_reg_encode(reg, DIV_VALUE, IPA_XO_CLOCK_DIVIDER - 1); + offset = reg_offset(reg); + + val = reg_encode(reg, DIV_VALUE, IPA_XO_CLOCK_DIVIDER - 1); iowrite32(val, ipa->reg_virt + offset); /* Divider value is set; re-enable the common timer clock divider */ - val |= ipa_reg_bit(reg, DIV_ENABLE); + val |= reg_bit(reg, DIV_ENABLE); iowrite32(val, ipa->reg_virt + offset); } @@ -416,13 +416,13 @@ static void ipa_qtime_config(struct ipa *ipa) static void ipa_hardware_config_counter(struct ipa *ipa) { u32 granularity = ipa_aggr_granularity_val(IPA_AGGR_GRANULARITY); - const struct ipa_reg *reg; + const struct reg *reg; u32 val; reg = ipa_reg(ipa, COUNTER_CFG); /* If defined, EOT_COAL_GRANULARITY is 0 */ - val = ipa_reg_encode(reg, AGGR_GRANULARITY, granularity); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + val = reg_encode(reg, AGGR_GRANULARITY, granularity); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } static void ipa_hardware_config_timing(struct ipa *ipa) @@ -435,7 +435,7 @@ static void ipa_hardware_config_timing(struct ipa *ipa) static void ipa_hardware_config_hashing(struct ipa *ipa) { - const struct ipa_reg *reg; + const struct reg *reg; /* Other than IPA v4.2, all versions enable "hashing". Starting * with IPA v5.0, the filter and router tables are implemented @@ -451,26 +451,26 @@ static void ipa_hardware_config_hashing(struct ipa *ipa) /* IPV6_ROUTER_HASH, IPV6_FILTER_HASH, IPV4_ROUTER_HASH, * IPV4_FILTER_HASH are all zero. */ - iowrite32(0, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(0, ipa->reg_virt + reg_offset(reg)); } static void ipa_idle_indication_cfg(struct ipa *ipa, u32 enter_idle_debounce_thresh, bool const_non_idle_enable) { - const struct ipa_reg *reg; + const struct reg *reg; u32 val; if (ipa->version < IPA_VERSION_3_5_1) return; reg = ipa_reg(ipa, IDLE_INDICATION_CFG); - val = ipa_reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH, - enter_idle_debounce_thresh); + val = reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH, + enter_idle_debounce_thresh); if (const_non_idle_enable) - val |= ipa_reg_bit(reg, CONST_NON_IDLE_ENABLE); + val |= reg_bit(reg, CONST_NON_IDLE_ENABLE); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /** diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index a07776e20cb0..85096d1efe5b 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -75,7 +75,7 @@ ipa_mem_zero_region_add(struct gsi_trans *trans, enum ipa_mem_id mem_id) int ipa_mem_setup(struct ipa *ipa) { dma_addr_t addr = ipa->zero_addr; - const struct ipa_reg *reg; + const struct reg *reg; const struct ipa_mem *mem; struct gsi_trans *trans; u32 offset; @@ -115,8 +115,8 @@ int ipa_mem_setup(struct ipa *ipa) offset = ipa->mem_offset + mem->offset; reg = ipa_reg(ipa, LOCAL_PKT_PROC_CNTXT); - val = ipa_reg_encode(reg, IPA_BASE_ADDR, offset); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + val = reg_encode(reg, IPA_BASE_ADDR, offset); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); return 0; } @@ -318,8 +318,8 @@ static bool ipa_mem_size_valid(struct ipa *ipa) int ipa_mem_config(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_reg *reg; const struct ipa_mem *mem; + const struct reg *reg; dma_addr_t addr; u32 mem_size; void *virt; @@ -328,13 +328,13 @@ int ipa_mem_config(struct ipa *ipa) /* Check the advertised location and size of the shared memory area */ reg = ipa_reg(ipa, SHARED_MEM_SIZE); - val = ioread32(ipa->reg_virt + ipa_reg_offset(reg)); + val = ioread32(ipa->reg_virt + reg_offset(reg)); /* The fields in the register are in 8 byte units */ - ipa->mem_offset = 8 * ipa_reg_decode(reg, MEM_BADDR, val); + ipa->mem_offset = 8 * reg_decode(reg, MEM_BADDR, val); /* Make sure the end is within the region's mapped space */ - mem_size = 8 * ipa_reg_decode(reg, MEM_SIZE, val); + mem_size = 8 * reg_decode(reg, MEM_SIZE, val); /* If the sizes don't match, issue a warning */ if (ipa->mem_offset + mem_size < ipa->mem_size) { diff --git a/drivers/net/ipa/ipa_reg.c b/drivers/net/ipa/ipa_reg.c index ddd529153e15..735fa6591609 100644 --- a/drivers/net/ipa/ipa_reg.c +++ b/drivers/net/ipa/ipa_reg.c @@ -9,73 +9,96 @@ #include "ipa.h" #include "ipa_reg.h" -/* Is this register valid and defined for the current IPA version? */ -static bool ipa_reg_valid(struct ipa *ipa, enum ipa_reg_id reg_id) +/* Is this register ID valid for the current IPA version? */ +static bool ipa_reg_id_valid(struct ipa *ipa, enum ipa_reg_id reg_id) { enum ipa_version version = ipa->version; - bool valid; - - /* Check for bogus (out of range) register IDs */ - if ((u32)reg_id >= ipa->regs->reg_count) - return false; switch (reg_id) { case IPA_BCR: case COUNTER_CFG: - valid = version < IPA_VERSION_4_5; - break; + return version < IPA_VERSION_4_5; case IPA_TX_CFG: case FLAVOR_0: case IDLE_INDICATION_CFG: - valid = version >= IPA_VERSION_3_5; - break; + return version >= IPA_VERSION_3_5; case QTIME_TIMESTAMP_CFG: case TIMERS_XO_CLK_DIV_CFG: case TIMERS_PULSE_GRAN_CFG: - valid = version >= IPA_VERSION_4_5; - break; + return version >= IPA_VERSION_4_5; case SRC_RSRC_GRP_45_RSRC_TYPE: case DST_RSRC_GRP_45_RSRC_TYPE: - valid = version <= IPA_VERSION_3_1 || - version == IPA_VERSION_4_5; - break; + return version <= IPA_VERSION_3_1 || + version == IPA_VERSION_4_5; case SRC_RSRC_GRP_67_RSRC_TYPE: case DST_RSRC_GRP_67_RSRC_TYPE: - valid = version <= IPA_VERSION_3_1; - break; + return version <= IPA_VERSION_3_1; case ENDP_FILTER_ROUTER_HSH_CFG: - valid = version != IPA_VERSION_4_2; - break; + return version != IPA_VERSION_4_2; case IRQ_SUSPEND_EN: case IRQ_SUSPEND_CLR: - valid = version >= IPA_VERSION_3_1; - break; + return version >= IPA_VERSION_3_1; + + case COMP_CFG: + case CLKON_CFG: + case ROUTE: + case SHARED_MEM_SIZE: + case QSB_MAX_WRITES: + case QSB_MAX_READS: + case FILT_ROUT_HASH_EN: + case FILT_ROUT_CACHE_CFG: + case FILT_ROUT_HASH_FLUSH: + case FILT_ROUT_CACHE_FLUSH: + case STATE_AGGR_ACTIVE: + case LOCAL_PKT_PROC_CNTXT: + case AGGR_FORCE_CLOSE: + case SRC_RSRC_GRP_01_RSRC_TYPE: + case SRC_RSRC_GRP_23_RSRC_TYPE: + case DST_RSRC_GRP_01_RSRC_TYPE: + case DST_RSRC_GRP_23_RSRC_TYPE: + case ENDP_INIT_CTRL: + case ENDP_INIT_CFG: + case ENDP_INIT_NAT: + case ENDP_INIT_HDR: + case ENDP_INIT_HDR_EXT: + case ENDP_INIT_HDR_METADATA_MASK: + case ENDP_INIT_MODE: + case ENDP_INIT_AGGR: + case ENDP_INIT_HOL_BLOCK_EN: + case ENDP_INIT_HOL_BLOCK_TIMER: + case ENDP_INIT_DEAGGR: + case ENDP_INIT_RSRC_GRP: + case ENDP_INIT_SEQ: + case ENDP_STATUS: + case ENDP_FILTER_CACHE_CFG: + case ENDP_ROUTER_CACHE_CFG: + case IPA_IRQ_STTS: + case IPA_IRQ_EN: + case IPA_IRQ_CLR: + case IPA_IRQ_UC: + case IRQ_SUSPEND_INFO: + return true; /* These should be defined for all versions */ default: - valid = true; /* Others should be defined for all versions */ - break; + return false; } - - /* To be valid, it must be defined */ - - return valid && ipa->regs->reg[reg_id]; } -const struct ipa_reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id) +const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id) { - if (WARN_ON(!ipa_reg_valid(ipa, reg_id))) + if (WARN(!ipa_reg_id_valid(ipa, reg_id), "invalid reg %u\n", reg_id)) return NULL; - return ipa->regs->reg[reg_id]; + return reg(ipa->regs, reg_id); } -static const struct ipa_regs *ipa_regs(enum ipa_version version) +static const struct regs *ipa_regs(enum ipa_version version) { switch (version) { case IPA_VERSION_3_1: @@ -100,7 +123,7 @@ static const struct ipa_regs *ipa_regs(enum ipa_version version) int ipa_reg_init(struct ipa *ipa) { struct device *dev = &ipa->pdev->dev; - const struct ipa_regs *regs; + const struct regs *regs; struct resource *res; regs = ipa_regs(ipa->version); @@ -123,7 +146,6 @@ int ipa_reg_init(struct ipa *ipa) dev_err(dev, "unable to remap \"ipa-reg\" memory\n"); return -ENOMEM; } - ipa->reg_addr = res->start; ipa->regs = regs; return 0; diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h index 82d43eca170e..28aa1351dd48 100644 --- a/drivers/net/ipa/ipa_reg.h +++ b/drivers/net/ipa/ipa_reg.h @@ -10,6 +10,7 @@ #include <linux/bug.h> #include "ipa_version.h" +#include "reg.h" struct ipa; @@ -35,7 +36,7 @@ struct ipa; * by register ID. Each entry in the array specifies the base offset and * (for parameterized registers) a non-zero stride value. Not all versions * of IPA define all registers. The offset for a register is returned by - * ipa_reg_offset() when the register's ipa_reg structure is supplied; + * reg_offset() when the register's ipa_reg structure is supplied; * zero is returned for an undefined register (this should never happen). * * Some registers encode multiple fields within them. Each field in @@ -44,9 +45,9 @@ struct ipa; * an array of field masks, indexed by field ID. Two functions are * used to access register fields; both take an ipa_reg structure as * argument. To encode a value to be represented in a register field, - * the value and field ID are passed to ipa_reg_encode(). To extract + * the value and field ID are passed to reg_encode(). To extract * a value encoded in a register field, the field ID is passed to - * ipa_reg_decode(). In addition, for single-bit fields, ipa_reg_bit() + * reg_decode(). In addition, for single-bit fields, reg_bit() * can be used to either encode the bit value, or to generate a mask * used to extract the bit value. */ @@ -110,56 +111,6 @@ enum ipa_reg_id { IPA_REG_ID_COUNT, /* Last; not an ID */ }; -/** - * struct ipa_reg - An IPA register descriptor - * @offset: Register offset relative to base of the "ipa-reg" memory - * @stride: Distance between two instances, if parameterized - * @fcount: Number of entries in the @fmask array - * @fmask: Array of mask values defining position and width of fields - * @name: Upper-case name of the IPA register - */ -struct ipa_reg { - u32 offset; - u32 stride; - u32 fcount; - const u32 *fmask; /* BIT(nr) or GENMASK(h, l) */ - const char *name; -}; - -/* Helper macro for defining "simple" (non-parameterized) registers */ -#define IPA_REG(__NAME, __reg_id, __offset) \ - IPA_REG_STRIDE(__NAME, __reg_id, __offset, 0) - -/* Helper macro for defining parameterized registers, specifying stride */ -#define IPA_REG_STRIDE(__NAME, __reg_id, __offset, __stride) \ - static const struct ipa_reg ipa_reg_ ## __reg_id = { \ - .name = #__NAME, \ - .offset = __offset, \ - .stride = __stride, \ - } - -#define IPA_REG_FIELDS(__NAME, __name, __offset) \ - IPA_REG_STRIDE_FIELDS(__NAME, __name, __offset, 0) - -#define IPA_REG_STRIDE_FIELDS(__NAME, __name, __offset, __stride) \ - static const struct ipa_reg ipa_reg_ ## __name = { \ - .name = #__NAME, \ - .offset = __offset, \ - .stride = __stride, \ - .fcount = ARRAY_SIZE(ipa_reg_ ## __name ## _fmask), \ - .fmask = ipa_reg_ ## __name ## _fmask, \ - } - -/** - * struct ipa_regs - Description of registers supported by hardware - * @reg_count: Number of registers in the @reg[] array - * @reg: Array of register descriptors - */ -struct ipa_regs { - u32 reg_count; - const struct ipa_reg **reg; -}; - /* COMP_CFG register */ enum ipa_reg_comp_cfg_field_id { COMP_CFG_ENABLE, /* Not IPA v4.0+ */ @@ -687,79 +638,15 @@ enum ipa_reg_ipa_irq_uc_field_id { UC_INTR, }; -extern const struct ipa_regs ipa_regs_v3_1; -extern const struct ipa_regs ipa_regs_v3_5_1; -extern const struct ipa_regs ipa_regs_v4_2; -extern const struct ipa_regs ipa_regs_v4_5; -extern const struct ipa_regs ipa_regs_v4_7; -extern const struct ipa_regs ipa_regs_v4_9; -extern const struct ipa_regs ipa_regs_v4_11; - -/* Return the field mask for a field in a register */ -static inline u32 ipa_reg_fmask(const struct ipa_reg *reg, u32 field_id) -{ - if (!reg || WARN_ON(field_id >= reg->fcount)) - return 0; - - return reg->fmask[field_id]; -} - -/* Return the mask for a single-bit field in a register */ -static inline u32 ipa_reg_bit(const struct ipa_reg *reg, u32 field_id) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - WARN_ON(!is_power_of_2(fmask)); - - return fmask; -} - -/* Encode a value into the given field of a register */ -static inline u32 -ipa_reg_encode(const struct ipa_reg *reg, u32 field_id, u32 val) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - if (!fmask) - return 0; - - val <<= __ffs(fmask); - if (WARN_ON(val & ~fmask)) - return 0; - - return val; -} - -/* Given a register value, decode (extract) the value in the given field */ -static inline u32 -ipa_reg_decode(const struct ipa_reg *reg, u32 field_id, u32 val) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - return fmask ? (val & fmask) >> __ffs(fmask) : 0; -} - -/* Return the maximum value representable by the given field; always 2^n - 1 */ -static inline u32 ipa_reg_field_max(const struct ipa_reg *reg, u32 field_id) -{ - u32 fmask = ipa_reg_fmask(reg, field_id); - - return fmask ? fmask >> __ffs(fmask) : 0; -} - -const struct ipa_reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id); - -/* Returns 0 for NULL reg; warning will have already been issued */ -static inline u32 ipa_reg_offset(const struct ipa_reg *reg) -{ - return reg ? reg->offset : 0; -} +extern const struct regs ipa_regs_v3_1; +extern const struct regs ipa_regs_v3_5_1; +extern const struct regs ipa_regs_v4_2; +extern const struct regs ipa_regs_v4_5; +extern const struct regs ipa_regs_v4_7; +extern const struct regs ipa_regs_v4_9; +extern const struct regs ipa_regs_v4_11; -/* Returns 0 for NULL reg; warning will have already been issued */ -static inline u32 ipa_reg_n_offset(const struct ipa_reg *reg, u32 n) -{ - return reg ? reg->offset + n * reg->stride : 0; -} +const struct reg *ipa_reg(struct ipa *ipa, enum ipa_reg_id reg_id); int ipa_reg_init(struct ipa *ipa); void ipa_reg_exit(struct ipa *ipa); diff --git a/drivers/net/ipa/ipa_resource.c b/drivers/net/ipa/ipa_resource.c index a257f0e5e361..82c88a744d10 100644 --- a/drivers/net/ipa/ipa_resource.c +++ b/drivers/net/ipa/ipa_resource.c @@ -70,20 +70,20 @@ static bool ipa_resource_limits_valid(struct ipa *ipa, static void ipa_resource_config_common(struct ipa *ipa, u32 resource_type, - const struct ipa_reg *reg, + const struct reg *reg, const struct ipa_resource_limits *xlimits, const struct ipa_resource_limits *ylimits) { u32 val; - val = ipa_reg_encode(reg, X_MIN_LIM, xlimits->min); - val |= ipa_reg_encode(reg, X_MAX_LIM, xlimits->max); + val = reg_encode(reg, X_MIN_LIM, xlimits->min); + val |= reg_encode(reg, X_MAX_LIM, xlimits->max); if (ylimits) { - val |= ipa_reg_encode(reg, Y_MIN_LIM, ylimits->min); - val |= ipa_reg_encode(reg, Y_MAX_LIM, ylimits->max); + val |= reg_encode(reg, Y_MIN_LIM, ylimits->min); + val |= reg_encode(reg, Y_MAX_LIM, ylimits->max); } - iowrite32(val, ipa->reg_virt + ipa_reg_n_offset(reg, resource_type)); + iowrite32(val, ipa->reg_virt + reg_n_offset(reg, resource_type)); } static void ipa_resource_config_src(struct ipa *ipa, u32 resource_type, @@ -92,7 +92,7 @@ static void ipa_resource_config_src(struct ipa *ipa, u32 resource_type, u32 group_count = data->rsrc_group_src_count; const struct ipa_resource_limits *ylimits; const struct ipa_resource *resource; - const struct ipa_reg *reg; + const struct reg *reg; resource = &data->resource_src[resource_type]; @@ -129,7 +129,7 @@ static void ipa_resource_config_dst(struct ipa *ipa, u32 resource_type, u32 group_count = data->rsrc_group_dst_count; const struct ipa_resource_limits *ylimits; const struct ipa_resource *resource; - const struct ipa_reg *reg; + const struct reg *reg; resource = &data->resource_dst[resource_type]; diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index b9d505191f88..f0529c31d0b6 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -345,9 +345,8 @@ void ipa_table_reset(struct ipa *ipa, bool modem) int ipa_table_hash_flush(struct ipa *ipa) { - const struct ipa_reg *reg; struct gsi_trans *trans; - u32 offset; + const struct reg *reg; u32 val; if (!ipa_table_hash_support(ipa)) @@ -361,22 +360,20 @@ int ipa_table_hash_flush(struct ipa *ipa) if (ipa->version < IPA_VERSION_5_0) { reg = ipa_reg(ipa, FILT_ROUT_HASH_FLUSH); - offset = ipa_reg_offset(reg); - val = ipa_reg_bit(reg, IPV6_ROUTER_HASH); - val |= ipa_reg_bit(reg, IPV6_FILTER_HASH); - val |= ipa_reg_bit(reg, IPV4_ROUTER_HASH); - val |= ipa_reg_bit(reg, IPV4_FILTER_HASH); + val = reg_bit(reg, IPV6_ROUTER_HASH); + val |= reg_bit(reg, IPV6_FILTER_HASH); + val |= reg_bit(reg, IPV4_ROUTER_HASH); + val |= reg_bit(reg, IPV4_FILTER_HASH); } else { reg = ipa_reg(ipa, FILT_ROUT_CACHE_FLUSH); - offset = ipa_reg_offset(reg); /* IPA v5.0+ uses a unified cache (both IPv4 and IPv6) */ - val = ipa_reg_bit(reg, ROUTER_CACHE); - val |= ipa_reg_bit(reg, FILTER_CACHE); + val = reg_bit(reg, ROUTER_CACHE); + val |= reg_bit(reg, FILTER_CACHE); } - ipa_cmd_register_write_add(trans, offset, val, val, false); + ipa_cmd_register_write_add(trans, reg_offset(reg), val, val, false); gsi_trans_commit_wait(trans); @@ -495,22 +492,22 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint) { u32 endpoint_id = endpoint->endpoint_id; struct ipa *ipa = endpoint->ipa; - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; if (ipa->version < IPA_VERSION_5_0) { reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); val = ioread32(endpoint->ipa->reg_virt + offset); /* Zero all filter-related fields, preserving the rest */ - val &= ~ipa_reg_fmask(reg, FILTER_HASH_MSK_ALL); + val &= ~reg_fmask(reg, FILTER_HASH_MSK_ALL); } else { /* IPA v5.0 separates filter and router cache configuration */ reg = ipa_reg(ipa, ENDP_FILTER_CACHE_CFG); - offset = ipa_reg_n_offset(reg, endpoint_id); + offset = reg_n_offset(reg, endpoint_id); /* Zero all filter-related fields */ val = 0; @@ -554,22 +551,22 @@ static bool ipa_route_id_modem(struct ipa *ipa, u32 route_id) */ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id) { - const struct ipa_reg *reg; + const struct reg *reg; u32 offset; u32 val; if (ipa->version < IPA_VERSION_5_0) { reg = ipa_reg(ipa, ENDP_FILTER_ROUTER_HSH_CFG); - offset = ipa_reg_n_offset(reg, route_id); + offset = reg_n_offset(reg, route_id); val = ioread32(ipa->reg_virt + offset); /* Zero all route-related fields, preserving the rest */ - val &= ~ipa_reg_fmask(reg, ROUTER_HASH_MSK_ALL); + val &= ~reg_fmask(reg, ROUTER_HASH_MSK_ALL); } else { /* IPA v5.0 separates filter and router cache configuration */ reg = ipa_reg(ipa, ENDP_ROUTER_CACHE_CFG); - offset = ipa_reg_n_offset(reg, route_id); + offset = reg_n_offset(reg, route_id); /* Zero all route-related fields */ val = 0; diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index cb8a76a75f21..7eaa0b4ebed9 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -231,7 +231,7 @@ void ipa_uc_power(struct ipa *ipa) static void send_uc_command(struct ipa *ipa, u32 command, u32 command_param) { struct ipa_uc_mem_area *shared = ipa_uc_shared(ipa); - const struct ipa_reg *reg; + const struct reg *reg; u32 val; /* Fill in the command data */ @@ -243,9 +243,9 @@ static void send_uc_command(struct ipa *ipa, u32 command, u32 command_param) /* Use an interrupt to tell the microcontroller the command is ready */ reg = ipa_reg(ipa, IPA_IRQ_UC); - val = ipa_reg_bit(reg, UC_INTR); + val = reg_bit(reg, UC_INTR); - iowrite32(val, ipa->reg_virt + ipa_reg_offset(reg)); + iowrite32(val, ipa->reg_virt + reg_offset(reg)); } /* Tell the microcontroller the AP is shutting down */ diff --git a/drivers/net/ipa/ipa_version.h b/drivers/net/ipa/ipa_version.h index d15821467743..06e75b8ece7e 100644 --- a/drivers/net/ipa/ipa_version.h +++ b/drivers/net/ipa/ipa_version.h @@ -9,7 +9,7 @@ /** * enum ipa_version * @IPA_VERSION_3_0: IPA version 3.0/GSI version 1.0 - * @IPA_VERSION_3_1: IPA version 3.1/GSI version 1.1 + * @IPA_VERSION_3_1: IPA version 3.1/GSI version 1.0 * @IPA_VERSION_3_5: IPA version 3.5/GSI version 1.2 * @IPA_VERSION_3_5_1: IPA version 3.5.1/GSI version 1.3 * @IPA_VERSION_4_0: IPA version 4.0/GSI version 2.0 @@ -20,6 +20,8 @@ * @IPA_VERSION_4_9: IPA version 4.9/GSI version 2.9 * @IPA_VERSION_4_11: IPA version 4.11/GSI version 2.11 (2.1.1) * @IPA_VERSION_5_0: IPA version 5.0/GSI version 3.0 + * @IPA_VERSION_5_1: IPA version 5.1/GSI version 3.0 + * @IPA_VERSION_5_5: IPA version 5.5/GSI version 5.5 * @IPA_VERSION_COUNT: Number of defined IPA versions * * Defines the version of IPA (and GSI) hardware present on the platform. @@ -38,6 +40,8 @@ enum ipa_version { IPA_VERSION_4_9, IPA_VERSION_4_11, IPA_VERSION_5_0, + IPA_VERSION_5_1, + IPA_VERSION_5_5, IPA_VERSION_COUNT, /* Last; not a version */ }; diff --git a/drivers/net/ipa/reg.h b/drivers/net/ipa/reg.h new file mode 100644 index 000000000000..57b457f39b6e --- /dev/null +++ b/drivers/net/ipa/reg.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* *Copyright (C) 2022-2023 Linaro Ltd. */ + +#ifndef _REG_H_ +#define _REG_H_ + +#include <linux/types.h> +#include <linux/bits.h> + +/** + * struct reg - A register descriptor + * @offset: Register offset relative to base of register memory + * @stride: Distance between two instances, if parameterized + * @fcount: Number of entries in the @fmask array + * @fmask: Array of mask values defining position and width of fields + * @name: Upper-case name of the register + */ +struct reg { + u32 offset; + u32 stride; + u32 fcount; + const u32 *fmask; /* BIT(nr) or GENMASK(h, l) */ + const char *name; +}; + +/* Helper macro for defining "simple" (non-parameterized) registers */ +#define REG(__NAME, __reg_id, __offset) \ + REG_STRIDE(__NAME, __reg_id, __offset, 0) + +/* Helper macro for defining parameterized registers, specifying stride */ +#define REG_STRIDE(__NAME, __reg_id, __offset, __stride) \ + static const struct reg reg_ ## __reg_id = { \ + .name = #__NAME, \ + .offset = __offset, \ + .stride = __stride, \ + } + +#define REG_FIELDS(__NAME, __name, __offset) \ + REG_STRIDE_FIELDS(__NAME, __name, __offset, 0) + +#define REG_STRIDE_FIELDS(__NAME, __name, __offset, __stride) \ + static const struct reg reg_ ## __name = { \ + .name = #__NAME, \ + .offset = __offset, \ + .stride = __stride, \ + .fcount = ARRAY_SIZE(reg_ ## __name ## _fmask), \ + .fmask = reg_ ## __name ## _fmask, \ + } + +/** + * struct regs - Description of registers supported by hardware + * @reg_count: Number of registers in the @reg[] array + * @reg: Array of register descriptors + */ +struct regs { + u32 reg_count; + const struct reg **reg; +}; + +static inline const struct reg *reg(const struct regs *regs, u32 reg_id) +{ + if (WARN(reg_id >= regs->reg_count, + "reg out of range (%u > %u)\n", reg_id, regs->reg_count - 1)) + return NULL; + + return regs->reg[reg_id]; +} + +/* Return the field mask for a field in a register, or 0 on error */ +static inline u32 reg_fmask(const struct reg *reg, u32 field_id) +{ + if (!reg || WARN_ON(field_id >= reg->fcount)) + return 0; + + return reg->fmask[field_id]; +} + +/* Return the mask for a single-bit field in a register, or 0 on error */ +static inline u32 reg_bit(const struct reg *reg, u32 field_id) +{ + u32 fmask = reg_fmask(reg, field_id); + + if (WARN_ON(!is_power_of_2(fmask))) + return 0; + + return fmask; +} + +/* Return the maximum value representable by the given field; always 2^n - 1 */ +static inline u32 reg_field_max(const struct reg *reg, u32 field_id) +{ + u32 fmask = reg_fmask(reg, field_id); + + return fmask ? fmask >> __ffs(fmask) : 0; +} + +/* Encode a value into the given field of a register */ +static inline u32 reg_encode(const struct reg *reg, u32 field_id, u32 val) +{ + u32 fmask = reg_fmask(reg, field_id); + + if (!fmask) + return 0; + + val <<= __ffs(fmask); + if (WARN_ON(val & ~fmask)) + return 0; + + return val; +} + +/* Given a register value, decode (extract) the value in the given field */ +static inline u32 reg_decode(const struct reg *reg, u32 field_id, u32 val) +{ + u32 fmask = reg_fmask(reg, field_id); + + return fmask ? (val & fmask) >> __ffs(fmask) : 0; +} + +/* Returns 0 for NULL reg; warning should have already been issued */ +static inline u32 reg_offset(const struct reg *reg) +{ + return reg ? reg->offset : 0; +} + +/* Returns 0 for NULL reg; warning should have already been issued */ +static inline u32 reg_n_offset(const struct reg *reg, u32 n) +{ + return reg ? reg->offset + n * reg->stride : 0; +} + +#endif /* _REG_H_ */ diff --git a/drivers/net/ipa/reg/ipa_reg-v3.1.c b/drivers/net/ipa/reg/ipa_reg-v3.1.c index 677ece3bce9e..648dbfe1fce3 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.1.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [COMP_CFG_ENABLE] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -16,9 +16,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -39,9 +39,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -52,31 +52,31 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -87,9 +87,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -100,121 +100,121 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { [EOT_COAL_GRANULARITY] = GENMASK(3, 0), [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, - 0x00000408, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, + 0x00000408, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_67_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_67_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type, - 0x0000040c, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type, + 0x0000040c, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, - 0x00000508, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, + 0x00000508, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_67_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_67_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(7, 0), [X_MAX_LIM] = GENMASK(15, 8), [Y_MIN_LIM] = GENMASK(23, 16), [Y_MAX_LIM] = GENMASK(31, 24), }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type, - 0x0000050c, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type, + 0x0000050c, 0x0020); -static const u32 ipa_reg_endp_init_ctrl_fmask[] = { +static const u32 reg_endp_init_ctrl_fmask[] = { [ENDP_SUSPEND] = BIT(0), [ENDP_DELAY] = BIT(1), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -223,16 +223,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -245,9 +245,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -257,12 +257,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -274,9 +274,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -289,25 +289,25 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); /* Entire register is a tick count */ -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(31, 0), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -317,25 +317,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(2, 0), /* Bits 3-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -343,9 +342,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -366,84 +365,84 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [SRC_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_45_rsrc_type, - [SRC_RSRC_GRP_67_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_67_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_45_rsrc_type, - [DST_RSRC_GRP_67_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_67_rsrc_type, - [ENDP_INIT_CTRL] = &ipa_reg_endp_init_ctrl, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v3_1 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [SRC_RSRC_GRP_45_RSRC_TYPE] = ®_src_rsrc_grp_45_rsrc_type, + [SRC_RSRC_GRP_67_RSRC_TYPE] = ®_src_rsrc_grp_67_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_45_RSRC_TYPE] = ®_dst_rsrc_grp_45_rsrc_type, + [DST_RSRC_GRP_67_RSRC_TYPE] = ®_dst_rsrc_grp_67_rsrc_type, + [ENDP_INIT_CTRL] = ®_endp_init_ctrl, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v3_1 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c index b9c6a50de243..78b1bf60cd02 100644 --- a/drivers/net/ipa/reg/ipa_reg-v3.5.1.c +++ b/drivers/net/ipa/reg/ipa_reg-v3.5.1.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [COMP_CFG_ENABLE] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -16,9 +16,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -44,9 +44,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -57,31 +57,31 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -92,9 +92,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x000008c); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -105,42 +105,42 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x0000090); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x0000010c, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { [TX0_PREFETCH_DISABLE] = BIT(0), [TX1_PREFETCH_DISABLE] = BIT(1), [PREFETCH_ALMOST_EMPTY_SIZE] = GENMASK(4, 2), /* Bits 5-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -151,17 +151,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000220); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000220); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -172,10 +172,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -186,10 +186,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -200,10 +200,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -214,18 +214,18 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_ctrl_fmask[] = { +static const u32 reg_endp_init_ctrl_fmask[] = { [ENDP_SUSPEND] = BIT(0), [ENDP_DELAY] = BIT(1), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CTRL, endp_init_ctrl, 0x00000800, 0x0070); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -234,16 +234,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -256,9 +256,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -268,12 +268,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -285,9 +285,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -300,25 +300,25 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); /* Entire register is a tick count */ -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(31, 0), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -328,25 +328,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -354,9 +353,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -377,83 +376,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CTRL] = &ipa_reg_endp_init_ctrl, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v3_5_1 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CTRL] = ®_endp_init_ctrl, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v3_5_1 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.11.c b/drivers/net/ipa/reg/ipa_reg-v4.11.c index 9a315130530d..29e71cce4a84 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.11.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.11.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -36,9 +36,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { [GEN_QMB_0_DYNAMIC_ASIZE] = BIT(31), }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -73,9 +73,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -86,24 +86,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -111,9 +111,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -124,9 +124,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -137,23 +137,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -166,9 +166,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(4, 0), /* Bits 5-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -179,17 +179,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -199,26 +199,26 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), /* Bits 9-31 reserved */ }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -229,10 +229,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -243,10 +243,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -257,10 +257,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -271,10 +271,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -283,16 +283,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -305,9 +305,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -321,12 +321,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -338,9 +338,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -355,27 +355,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -385,24 +385,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -410,9 +409,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -433,83 +432,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_11 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_11 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.2.c b/drivers/net/ipa/reg/ipa_reg-v4.2.c index 7a95149f8ec7..bb7cf488144d 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.2.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.2.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { /* Bit 0 reserved */ [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -29,9 +29,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -65,9 +65,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -78,24 +78,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -103,9 +103,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -116,9 +116,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -129,33 +129,33 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -IPA_REG(IPA_BCR, ipa_bcr, 0x000001d0); +REG(IPA_BCR, ipa_bcr, 0x000001d0); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(16, 0), /* Bits 17-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_counter_cfg_fmask[] = { +static const u32 reg_counter_cfg_fmask[] = { /* Bits 0-3 reserved */ [AGGR_GRANULARITY] = GENMASK(8, 4), /* Bits 9-31 reserved */ }; -IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); +REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -169,9 +169,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 20-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -182,17 +182,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -203,10 +203,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -217,10 +217,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -231,10 +231,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -245,10 +245,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -257,16 +257,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -279,9 +279,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { /* Bits 29-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -291,12 +291,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 14-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), /* Bit 3 reserved */ [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -308,9 +308,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(9, 5), @@ -323,27 +323,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_BASE_VALUE] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_SCALE] = GENMASK(12, 8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -353,25 +353,24 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), [SEQ_REP_TYPE] = GENMASK(15, 8), /* Bits 16-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-7 reserved */ @@ -380,80 +379,80 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [IPA_BCR] = &ipa_reg_ipa_bcr, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [COUNTER_CFG] = &ipa_reg_counter_cfg, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_2 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [IPA_BCR] = ®_ipa_bcr, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [COUNTER_CFG] = ®_counter_cfg, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_2 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.5.c b/drivers/net/ipa/reg/ipa_reg-v4.5.c index 587eb8d4e00f..1c58f78851c2 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.5.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.5.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { /* Bit 0 reserved */ [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -30,9 +30,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -67,9 +67,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -80,24 +80,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -105,9 +105,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -118,9 +118,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -131,23 +131,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -159,9 +159,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 18-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -172,17 +172,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -192,25 +192,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -221,10 +221,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -235,10 +235,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -249,10 +249,10 @@ static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, - 0x00000408, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type, + 0x00000408, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -263,10 +263,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -277,10 +277,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -291,10 +291,10 @@ static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, - 0x00000508, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type, + 0x00000508, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -303,16 +303,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -325,9 +325,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -341,12 +341,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -357,9 +357,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -374,27 +374,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -404,24 +404,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(2, 0), /* Bits 3-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -429,9 +428,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -452,85 +451,85 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [SRC_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_45_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_45_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_45_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_5 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [SRC_RSRC_GRP_45_RSRC_TYPE] = ®_src_rsrc_grp_45_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_45_RSRC_TYPE] = ®_dst_rsrc_grp_45_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_5 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.7.c b/drivers/net/ipa/reg/ipa_reg-v4.7.c index 21f8a58e59a0..731824fce1d4 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.7.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.7.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -30,9 +30,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -67,9 +67,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -80,24 +80,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -105,9 +105,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -118,9 +118,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -131,23 +131,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -160,9 +160,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -173,17 +173,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -193,25 +193,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -222,10 +222,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -236,10 +236,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -250,10 +250,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -264,10 +264,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -276,16 +276,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -298,9 +298,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -314,12 +314,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -330,9 +330,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -347,27 +347,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -377,24 +377,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -402,9 +401,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -425,83 +424,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00003008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000300c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00003010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000301c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00003030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00003034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_7 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00003038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_7 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/ipa/reg/ipa_reg-v4.9.c b/drivers/net/ipa/reg/ipa_reg-v4.9.c index 1f67a03fe599..01f87b5290e0 100644 --- a/drivers/net/ipa/reg/ipa_reg-v4.9.c +++ b/drivers/net/ipa/reg/ipa_reg-v4.9.c @@ -7,7 +7,7 @@ #include "../ipa.h" #include "../ipa_reg.h" -static const u32 ipa_reg_comp_cfg_fmask[] = { +static const u32 reg_comp_cfg_fmask[] = { [RAM_ARB_PRI_CLIENT_SAMP_FIX_DIS] = BIT(0), [GSI_SNOC_BYPASS_DIS] = BIT(1), [GEN_QMB_0_SNOC_BYPASS_DIS] = BIT(2), @@ -35,9 +35,9 @@ static const u32 ipa_reg_comp_cfg_fmask[] = { [GEN_QMB_0_DYNAMIC_ASIZE] = BIT(31), }; -IPA_REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); +REG_FIELDS(COMP_CFG, comp_cfg, 0x0000003c); -static const u32 ipa_reg_clkon_cfg_fmask[] = { +static const u32 reg_clkon_cfg_fmask[] = { [CLKON_RX] = BIT(0), [CLKON_PROC] = BIT(1), [TX_WRAPPER] = BIT(2), @@ -72,9 +72,9 @@ static const u32 ipa_reg_clkon_cfg_fmask[] = { [DRBIP] = BIT(31), }; -IPA_REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); +REG_FIELDS(CLKON_CFG, clkon_cfg, 0x00000044); -static const u32 ipa_reg_route_fmask[] = { +static const u32 reg_route_fmask[] = { [ROUTE_DIS] = BIT(0), [ROUTE_DEF_PIPE] = GENMASK(5, 1), [ROUTE_DEF_HDR_TABLE] = BIT(6), @@ -85,24 +85,24 @@ static const u32 ipa_reg_route_fmask[] = { /* Bits 25-31 reserved */ }; -IPA_REG_FIELDS(ROUTE, route, 0x00000048); +REG_FIELDS(ROUTE, route, 0x00000048); -static const u32 ipa_reg_shared_mem_size_fmask[] = { +static const u32 reg_shared_mem_size_fmask[] = { [MEM_SIZE] = GENMASK(15, 0), [MEM_BADDR] = GENMASK(31, 16), }; -IPA_REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); +REG_FIELDS(SHARED_MEM_SIZE, shared_mem_size, 0x00000054); -static const u32 ipa_reg_qsb_max_writes_fmask[] = { +static const u32 reg_qsb_max_writes_fmask[] = { [GEN_QMB_0_MAX_WRITES] = GENMASK(3, 0), [GEN_QMB_1_MAX_WRITES] = GENMASK(7, 4), /* Bits 8-31 reserved */ }; -IPA_REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); +REG_FIELDS(QSB_MAX_WRITES, qsb_max_writes, 0x00000074); -static const u32 ipa_reg_qsb_max_reads_fmask[] = { +static const u32 reg_qsb_max_reads_fmask[] = { [GEN_QMB_0_MAX_READS] = GENMASK(3, 0), [GEN_QMB_1_MAX_READS] = GENMASK(7, 4), /* Bits 8-15 reserved */ @@ -110,9 +110,9 @@ static const u32 ipa_reg_qsb_max_reads_fmask[] = { [GEN_QMB_1_MAX_READS_BEATS] = GENMASK(31, 24), }; -IPA_REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); +REG_FIELDS(QSB_MAX_READS, qsb_max_reads, 0x00000078); -static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { +static const u32 reg_filt_rout_hash_en_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -123,9 +123,9 @@ static const u32 ipa_reg_filt_rout_hash_en_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); +REG_FIELDS(FILT_ROUT_HASH_EN, filt_rout_hash_en, 0x0000148); -static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { +static const u32 reg_filt_rout_hash_flush_fmask[] = { [IPV6_ROUTER_HASH] = BIT(0), /* Bits 1-3 reserved */ [IPV6_FILTER_HASH] = BIT(4), @@ -136,23 +136,23 @@ static const u32 ipa_reg_filt_rout_hash_flush_fmask[] = { /* Bits 13-31 reserved */ }; -IPA_REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); +REG_FIELDS(FILT_ROUT_HASH_FLUSH, filt_rout_hash_flush, 0x000014c); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); +REG_STRIDE(STATE_AGGR_ACTIVE, state_aggr_active, 0x000000b4, 0x0004); -static const u32 ipa_reg_local_pkt_proc_cntxt_fmask[] = { +static const u32 reg_local_pkt_proc_cntxt_fmask[] = { [IPA_BASE_ADDR] = GENMASK(17, 0), /* Bits 18-31 reserved */ }; /* Offset must be a multiple of 8 */ -IPA_REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); +REG_FIELDS(LOCAL_PKT_PROC_CNTXT, local_pkt_proc_cntxt, 0x000001e8); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); +REG_STRIDE(AGGR_FORCE_CLOSE, aggr_force_close, 0x000001ec, 0x0004); -static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { +static const u32 reg_ipa_tx_cfg_fmask[] = { /* Bits 0-1 reserved */ [PREFETCH_ALMOST_EMPTY_SIZE_TX0] = GENMASK(5, 2), [DMAW_SCND_OUTSD_PRED_THRESHOLD] = GENMASK(9, 6), @@ -165,9 +165,9 @@ static const u32 ipa_reg_ipa_tx_cfg_fmask[] = { /* Bits 19-31 reserved */ }; -IPA_REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); +REG_FIELDS(IPA_TX_CFG, ipa_tx_cfg, 0x000001fc); -static const u32 ipa_reg_flavor_0_fmask[] = { +static const u32 reg_flavor_0_fmask[] = { [MAX_PIPES] = GENMASK(3, 0), /* Bits 4-7 reserved */ [MAX_CONS_PIPES] = GENMASK(12, 8), @@ -178,17 +178,17 @@ static const u32 ipa_reg_flavor_0_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); +REG_FIELDS(FLAVOR_0, flavor_0, 0x00000210); -static const u32 ipa_reg_idle_indication_cfg_fmask[] = { +static const u32 reg_idle_indication_cfg_fmask[] = { [ENTER_IDLE_DEBOUNCE_THRESH] = GENMASK(15, 0), [CONST_NON_IDLE_ENABLE] = BIT(16), /* Bits 17-31 reserved */ }; -IPA_REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); +REG_FIELDS(IDLE_INDICATION_CFG, idle_indication_cfg, 0x00000240); -static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { +static const u32 reg_qtime_timestamp_cfg_fmask[] = { [DPL_TIMESTAMP_LSB] = GENMASK(4, 0), /* Bits 5-6 reserved */ [DPL_TIMESTAMP_SEL] = BIT(7), @@ -198,25 +198,25 @@ static const u32 ipa_reg_qtime_timestamp_cfg_fmask[] = { /* Bits 21-31 reserved */ }; -IPA_REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); +REG_FIELDS(QTIME_TIMESTAMP_CFG, qtime_timestamp_cfg, 0x0000024c); -static const u32 ipa_reg_timers_xo_clk_div_cfg_fmask[] = { +static const u32 reg_timers_xo_clk_div_cfg_fmask[] = { [DIV_VALUE] = GENMASK(8, 0), /* Bits 9-30 reserved */ [DIV_ENABLE] = BIT(31), }; -IPA_REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); +REG_FIELDS(TIMERS_XO_CLK_DIV_CFG, timers_xo_clk_div_cfg, 0x00000250); -static const u32 ipa_reg_timers_pulse_gran_cfg_fmask[] = { +static const u32 reg_timers_pulse_gran_cfg_fmask[] = { [PULSE_GRAN_0] = GENMASK(2, 0), [PULSE_GRAN_1] = GENMASK(5, 3), [PULSE_GRAN_2] = GENMASK(8, 6), }; -IPA_REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); +REG_FIELDS(TIMERS_PULSE_GRAN_CFG, timers_pulse_gran_cfg, 0x00000254); -static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -227,10 +227,10 @@ static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, - 0x00000400, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type, + 0x00000400, 0x0020); -static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_src_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -241,10 +241,10 @@ static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, - 0x00000404, 0x0020); +REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type, + 0x00000404, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -255,10 +255,10 @@ static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, - 0x00000500, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type, + 0x00000500, 0x0020); -static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { +static const u32 reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { [X_MIN_LIM] = GENMASK(5, 0), /* Bits 6-7 reserved */ [X_MAX_LIM] = GENMASK(13, 8), @@ -269,10 +269,10 @@ static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = { /* Bits 30-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, - 0x00000504, 0x0020); +REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type, + 0x00000504, 0x0020); -static const u32 ipa_reg_endp_init_cfg_fmask[] = { +static const u32 reg_endp_init_cfg_fmask[] = { [FRAG_OFFLOAD_EN] = BIT(0), [CS_OFFLOAD_EN] = GENMASK(2, 1), [CS_METADATA_HDR_OFFSET] = GENMASK(6, 3), @@ -281,16 +281,16 @@ static const u32 ipa_reg_endp_init_cfg_fmask[] = { /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_CFG, endp_init_cfg, 0x00000808, 0x0070); -static const u32 ipa_reg_endp_init_nat_fmask[] = { +static const u32 reg_endp_init_nat_fmask[] = { [NAT_EN] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_NAT, endp_init_nat, 0x0000080c, 0x0070); -static const u32 ipa_reg_endp_init_hdr_fmask[] = { +static const u32 reg_endp_init_hdr_fmask[] = { [HDR_LEN] = GENMASK(5, 0), [HDR_OFST_METADATA_VALID] = BIT(6), [HDR_OFST_METADATA] = GENMASK(12, 7), @@ -302,9 +302,9 @@ static const u32 ipa_reg_endp_init_hdr_fmask[] = { [HDR_OFST_METADATA_MSB] = GENMASK(31, 30), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR, endp_init_hdr, 0x00000810, 0x0070); -static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { +static const u32 reg_endp_init_hdr_ext_fmask[] = { [HDR_ENDIANNESS] = BIT(0), [HDR_TOTAL_LEN_OR_PAD_VALID] = BIT(1), [HDR_TOTAL_LEN_OR_PAD] = BIT(2), @@ -318,12 +318,12 @@ static const u32 ipa_reg_endp_init_hdr_ext_fmask[] = { /* Bits 22-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HDR_EXT, endp_init_hdr_ext, 0x00000814, 0x0070); -IPA_REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, - 0x00000818, 0x0070); +REG_STRIDE(ENDP_INIT_HDR_METADATA_MASK, endp_init_hdr_metadata_mask, + 0x00000818, 0x0070); -static const u32 ipa_reg_endp_init_mode_fmask[] = { +static const u32 reg_endp_init_mode_fmask[] = { [ENDP_MODE] = GENMASK(2, 0), [DCPH_ENABLE] = BIT(3), [DEST_PIPE_INDEX] = GENMASK(8, 4), @@ -335,9 +335,9 @@ static const u32 ipa_reg_endp_init_mode_fmask[] = { /* Bit 31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_MODE, endp_init_mode, 0x00000820, 0x0070); -static const u32 ipa_reg_endp_init_aggr_fmask[] = { +static const u32 reg_endp_init_aggr_fmask[] = { [AGGR_EN] = GENMASK(1, 0), [AGGR_TYPE] = GENMASK(4, 2), [BYTE_LIMIT] = GENMASK(10, 5), @@ -352,27 +352,27 @@ static const u32 ipa_reg_endp_init_aggr_fmask[] = { /* Bits 28-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_AGGR, endp_init_aggr, 0x00000824, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_en_fmask[] = { +static const u32 reg_endp_init_hol_block_en_fmask[] = { [HOL_BLOCK_EN] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, - 0x0000082c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_EN, endp_init_hol_block_en, + 0x0000082c, 0x0070); -static const u32 ipa_reg_endp_init_hol_block_timer_fmask[] = { +static const u32 reg_endp_init_hol_block_timer_fmask[] = { [TIMER_LIMIT] = GENMASK(4, 0), /* Bits 5-7 reserved */ [TIMER_GRAN_SEL] = BIT(8), /* Bits 9-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, - 0x00000830, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_HOL_BLOCK_TIMER, endp_init_hol_block_timer, + 0x00000830, 0x0070); -static const u32 ipa_reg_endp_init_deaggr_fmask[] = { +static const u32 reg_endp_init_deaggr_fmask[] = { [DEAGGR_HDR_LEN] = GENMASK(5, 0), [SYSPIPE_ERR_DETECTION] = BIT(6), [PACKET_OFFSET_VALID] = BIT(7), @@ -382,24 +382,23 @@ static const u32 ipa_reg_endp_init_deaggr_fmask[] = { [MAX_PACKET_LEN] = GENMASK(31, 16), }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_DEAGGR, endp_init_deaggr, 0x00000834, 0x0070); -static const u32 ipa_reg_endp_init_rsrc_grp_fmask[] = { +static const u32 reg_endp_init_rsrc_grp_fmask[] = { [ENDP_RSRC_GRP] = GENMASK(1, 0), /* Bits 2-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, - 0x00000838, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_RSRC_GRP, endp_init_rsrc_grp, 0x00000838, 0x0070); -static const u32 ipa_reg_endp_init_seq_fmask[] = { +static const u32 reg_endp_init_seq_fmask[] = { [SEQ_TYPE] = GENMASK(7, 0), /* Bits 8-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); +REG_STRIDE_FIELDS(ENDP_INIT_SEQ, endp_init_seq, 0x0000083c, 0x0070); -static const u32 ipa_reg_endp_status_fmask[] = { +static const u32 reg_endp_status_fmask[] = { [STATUS_EN] = BIT(0), [STATUS_ENDP] = GENMASK(5, 1), /* Bits 6-8 reserved */ @@ -407,9 +406,9 @@ static const u32 ipa_reg_endp_status_fmask[] = { /* Bits 10-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); +REG_STRIDE_FIELDS(ENDP_STATUS, endp_status, 0x00000840, 0x0070); -static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { +static const u32 reg_endp_filter_router_hsh_cfg_fmask[] = { [FILTER_HASH_MSK_SRC_ID] = BIT(0), [FILTER_HASH_MSK_SRC_IP] = BIT(1), [FILTER_HASH_MSK_DST_IP] = BIT(2), @@ -430,83 +429,83 @@ static const u32 ipa_reg_endp_filter_router_hsh_cfg_fmask[] = { /* Bits 23-31 reserved */ }; -IPA_REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, - 0x0000085c, 0x0070); +REG_STRIDE_FIELDS(ENDP_FILTER_ROUTER_HSH_CFG, endp_filter_router_hsh_cfg, + 0x0000085c, 0x0070); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_STTS, ipa_irq_stts, 0x00004008 + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_EN, ipa_irq_en, 0x0000400c + 0x1000 * GSI_EE_AP); /* Valid bits defined by enum ipa_irq_id; only used for GSI_EE_AP */ -IPA_REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); +REG(IPA_IRQ_CLR, ipa_irq_clr, 0x00004010 + 0x1000 * GSI_EE_AP); -static const u32 ipa_reg_ipa_irq_uc_fmask[] = { +static const u32 reg_ipa_irq_uc_fmask[] = { [UC_INTR] = BIT(0), /* Bits 1-31 reserved */ }; -IPA_REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); +REG_FIELDS(IPA_IRQ_UC, ipa_irq_uc, 0x0000401c + 0x1000 * GSI_EE_AP); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, - 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_INFO, irq_suspend_info, + 0x00004030 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, - 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); +REG_STRIDE(IRQ_SUSPEND_EN, irq_suspend_en, + 0x00004034 + 0x1000 * GSI_EE_AP, 0x0004); /* Valid bits defined by ipa->available */ -IPA_REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, - 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); - -static const struct ipa_reg *ipa_reg_array[] = { - [COMP_CFG] = &ipa_reg_comp_cfg, - [CLKON_CFG] = &ipa_reg_clkon_cfg, - [ROUTE] = &ipa_reg_route, - [SHARED_MEM_SIZE] = &ipa_reg_shared_mem_size, - [QSB_MAX_WRITES] = &ipa_reg_qsb_max_writes, - [QSB_MAX_READS] = &ipa_reg_qsb_max_reads, - [FILT_ROUT_HASH_EN] = &ipa_reg_filt_rout_hash_en, - [FILT_ROUT_HASH_FLUSH] = &ipa_reg_filt_rout_hash_flush, - [STATE_AGGR_ACTIVE] = &ipa_reg_state_aggr_active, - [LOCAL_PKT_PROC_CNTXT] = &ipa_reg_local_pkt_proc_cntxt, - [AGGR_FORCE_CLOSE] = &ipa_reg_aggr_force_close, - [IPA_TX_CFG] = &ipa_reg_ipa_tx_cfg, - [FLAVOR_0] = &ipa_reg_flavor_0, - [IDLE_INDICATION_CFG] = &ipa_reg_idle_indication_cfg, - [QTIME_TIMESTAMP_CFG] = &ipa_reg_qtime_timestamp_cfg, - [TIMERS_XO_CLK_DIV_CFG] = &ipa_reg_timers_xo_clk_div_cfg, - [TIMERS_PULSE_GRAN_CFG] = &ipa_reg_timers_pulse_gran_cfg, - [SRC_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_01_rsrc_type, - [SRC_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_src_rsrc_grp_23_rsrc_type, - [DST_RSRC_GRP_01_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_01_rsrc_type, - [DST_RSRC_GRP_23_RSRC_TYPE] = &ipa_reg_dst_rsrc_grp_23_rsrc_type, - [ENDP_INIT_CFG] = &ipa_reg_endp_init_cfg, - [ENDP_INIT_NAT] = &ipa_reg_endp_init_nat, - [ENDP_INIT_HDR] = &ipa_reg_endp_init_hdr, - [ENDP_INIT_HDR_EXT] = &ipa_reg_endp_init_hdr_ext, - [ENDP_INIT_HDR_METADATA_MASK] = &ipa_reg_endp_init_hdr_metadata_mask, - [ENDP_INIT_MODE] = &ipa_reg_endp_init_mode, - [ENDP_INIT_AGGR] = &ipa_reg_endp_init_aggr, - [ENDP_INIT_HOL_BLOCK_EN] = &ipa_reg_endp_init_hol_block_en, - [ENDP_INIT_HOL_BLOCK_TIMER] = &ipa_reg_endp_init_hol_block_timer, - [ENDP_INIT_DEAGGR] = &ipa_reg_endp_init_deaggr, - [ENDP_INIT_RSRC_GRP] = &ipa_reg_endp_init_rsrc_grp, - [ENDP_INIT_SEQ] = &ipa_reg_endp_init_seq, - [ENDP_STATUS] = &ipa_reg_endp_status, - [ENDP_FILTER_ROUTER_HSH_CFG] = &ipa_reg_endp_filter_router_hsh_cfg, - [IPA_IRQ_STTS] = &ipa_reg_ipa_irq_stts, - [IPA_IRQ_EN] = &ipa_reg_ipa_irq_en, - [IPA_IRQ_CLR] = &ipa_reg_ipa_irq_clr, - [IPA_IRQ_UC] = &ipa_reg_ipa_irq_uc, - [IRQ_SUSPEND_INFO] = &ipa_reg_irq_suspend_info, - [IRQ_SUSPEND_EN] = &ipa_reg_irq_suspend_en, - [IRQ_SUSPEND_CLR] = &ipa_reg_irq_suspend_clr, -}; - -const struct ipa_regs ipa_regs_v4_9 = { - .reg_count = ARRAY_SIZE(ipa_reg_array), - .reg = ipa_reg_array, +REG_STRIDE(IRQ_SUSPEND_CLR, irq_suspend_clr, + 0x00004038 + 0x1000 * GSI_EE_AP, 0x0004); + +static const struct reg *reg_array[] = { + [COMP_CFG] = ®_comp_cfg, + [CLKON_CFG] = ®_clkon_cfg, + [ROUTE] = ®_route, + [SHARED_MEM_SIZE] = ®_shared_mem_size, + [QSB_MAX_WRITES] = ®_qsb_max_writes, + [QSB_MAX_READS] = ®_qsb_max_reads, + [FILT_ROUT_HASH_EN] = ®_filt_rout_hash_en, + [FILT_ROUT_HASH_FLUSH] = ®_filt_rout_hash_flush, + [STATE_AGGR_ACTIVE] = ®_state_aggr_active, + [LOCAL_PKT_PROC_CNTXT] = ®_local_pkt_proc_cntxt, + [AGGR_FORCE_CLOSE] = ®_aggr_force_close, + [IPA_TX_CFG] = ®_ipa_tx_cfg, + [FLAVOR_0] = ®_flavor_0, + [IDLE_INDICATION_CFG] = ®_idle_indication_cfg, + [QTIME_TIMESTAMP_CFG] = ®_qtime_timestamp_cfg, + [TIMERS_XO_CLK_DIV_CFG] = ®_timers_xo_clk_div_cfg, + [TIMERS_PULSE_GRAN_CFG] = ®_timers_pulse_gran_cfg, + [SRC_RSRC_GRP_01_RSRC_TYPE] = ®_src_rsrc_grp_01_rsrc_type, + [SRC_RSRC_GRP_23_RSRC_TYPE] = ®_src_rsrc_grp_23_rsrc_type, + [DST_RSRC_GRP_01_RSRC_TYPE] = ®_dst_rsrc_grp_01_rsrc_type, + [DST_RSRC_GRP_23_RSRC_TYPE] = ®_dst_rsrc_grp_23_rsrc_type, + [ENDP_INIT_CFG] = ®_endp_init_cfg, + [ENDP_INIT_NAT] = ®_endp_init_nat, + [ENDP_INIT_HDR] = ®_endp_init_hdr, + [ENDP_INIT_HDR_EXT] = ®_endp_init_hdr_ext, + [ENDP_INIT_HDR_METADATA_MASK] = ®_endp_init_hdr_metadata_mask, + [ENDP_INIT_MODE] = ®_endp_init_mode, + [ENDP_INIT_AGGR] = ®_endp_init_aggr, + [ENDP_INIT_HOL_BLOCK_EN] = ®_endp_init_hol_block_en, + [ENDP_INIT_HOL_BLOCK_TIMER] = ®_endp_init_hol_block_timer, + [ENDP_INIT_DEAGGR] = ®_endp_init_deaggr, + [ENDP_INIT_RSRC_GRP] = ®_endp_init_rsrc_grp, + [ENDP_INIT_SEQ] = ®_endp_init_seq, + [ENDP_STATUS] = ®_endp_status, + [ENDP_FILTER_ROUTER_HSH_CFG] = ®_endp_filter_router_hsh_cfg, + [IPA_IRQ_STTS] = ®_ipa_irq_stts, + [IPA_IRQ_EN] = ®_ipa_irq_en, + [IPA_IRQ_CLR] = ®_ipa_irq_clr, + [IPA_IRQ_UC] = ®_ipa_irq_uc, + [IRQ_SUSPEND_INFO] = ®_irq_suspend_info, + [IRQ_SUSPEND_EN] = ®_irq_suspend_en, + [IRQ_SUSPEND_CLR] = ®_irq_suspend_clr, +}; + +const struct regs ipa_regs_v4_9 = { + .reg_count = ARRAY_SIZE(reg_array), + .reg = reg_array, }; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 6db6a75ff9b9..35fa1ca98671 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -286,6 +286,7 @@ static void nsim_setup(struct net_device *dev) NETIF_F_TSO; dev->hw_features |= NETIF_F_HW_TC; dev->max_mtu = ETH_MAX_MTU; + dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD; } static int nsim_init_netdevsim(struct netdevsim *ns) diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index c1424119e821..323bec5e57f8 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -121,15 +121,11 @@ static const char *index_to_string[MIIC_MODCTRL_CONF_CONV_NUM] = { * struct miic - MII converter structure * @base: base address of the MII converter * @dev: Device associated to the MII converter - * @clks: Clocks used for this device - * @nclk: Number of clocks * @lock: Lock used for read-modify-write access */ struct miic { void __iomem *base; struct device *dev; - struct clk_bulk_data *clks; - int nclk; spinlock_t lock; }; @@ -232,7 +228,7 @@ static int miic_config(struct phylink_pcs *pcs, unsigned int mode, } miic_reg_rmw(miic, MIIC_CONVCTRL(port), mask, val); - miic_converter_enable(miic_port->miic, miic_port->port, 1); + miic_converter_enable(miic, miic_port->port, 1); return 0; } diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 5e41658b1e2f..a6015cd03bff 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -261,6 +261,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, { PHY_ID_MATCH_EXACT(0x01803301), .name = "Meson G12A Internal PHY", diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index d5b80c31ab91..727de4f4a14d 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -268,6 +268,9 @@ struct kszphy_type { u16 interrupt_level_mask; u16 cable_diag_reg; unsigned long pair_mask; + u16 disable_dll_tx_bit; + u16 disable_dll_rx_bit; + u16 disable_dll_mask; bool has_broadcast_disable; bool has_nand_tree_disable; bool has_rmii_ref_clk_sel; @@ -364,6 +367,21 @@ static const struct kszphy_type ksz9021_type = { .interrupt_level_mask = BIT(14), }; +static const struct kszphy_type ksz9131_type = { + .interrupt_level_mask = BIT(14), + .disable_dll_tx_bit = BIT(12), + .disable_dll_rx_bit = BIT(12), + .disable_dll_mask = BIT_MASK(12), +}; + +static const struct kszphy_type lan8841_type = { + .disable_dll_tx_bit = BIT(14), + .disable_dll_rx_bit = BIT(14), + .disable_dll_mask = BIT_MASK(14), + .cable_diag_reg = LAN8814_CABLE_DIAG, + .pair_mask = LAN8814_WIRE_PAIR_MASK, +}; + static int kszphy_extended_write(struct phy_device *phydev, u32 regnum, u16 val) { @@ -1172,19 +1190,18 @@ static int ksz9131_of_load_skew_values(struct phy_device *phydev, #define KSZ9131RN_MMD_COMMON_CTRL_REG 2 #define KSZ9131RN_RXC_DLL_CTRL 76 #define KSZ9131RN_TXC_DLL_CTRL 77 -#define KSZ9131RN_DLL_CTRL_BYPASS BIT_MASK(12) #define KSZ9131RN_DLL_ENABLE_DELAY 0 -#define KSZ9131RN_DLL_DISABLE_DELAY BIT(12) static int ksz9131_config_rgmii_delay(struct phy_device *phydev) { + const struct kszphy_type *type = phydev->drv->driver_data; u16 rxcdll_val, txcdll_val; int ret; switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: - rxcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; - txcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + rxcdll_val = type->disable_dll_rx_bit; + txcdll_val = type->disable_dll_tx_bit; break; case PHY_INTERFACE_MODE_RGMII_ID: rxcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; @@ -1192,10 +1209,10 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) break; case PHY_INTERFACE_MODE_RGMII_RXID: rxcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; - txcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + txcdll_val = type->disable_dll_tx_bit; break; case PHY_INTERFACE_MODE_RGMII_TXID: - rxcdll_val = KSZ9131RN_DLL_DISABLE_DELAY; + rxcdll_val = type->disable_dll_rx_bit; txcdll_val = KSZ9131RN_DLL_ENABLE_DELAY; break; default: @@ -1203,13 +1220,13 @@ static int ksz9131_config_rgmii_delay(struct phy_device *phydev) } ret = phy_modify_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, - KSZ9131RN_RXC_DLL_CTRL, KSZ9131RN_DLL_CTRL_BYPASS, + KSZ9131RN_RXC_DLL_CTRL, type->disable_dll_mask, rxcdll_val); if (ret < 0) return ret; return phy_modify_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, - KSZ9131RN_TXC_DLL_CTRL, KSZ9131RN_DLL_CTRL_BYPASS, + KSZ9131RN_TXC_DLL_CTRL, type->disable_dll_mask, txcdll_val); } @@ -3152,6 +3169,146 @@ static int lan8814_probe(struct phy_device *phydev) return 0; } +#define LAN8841_MMD_TIMER_REG 0 +#define LAN8841_MMD0_REGISTER_17 17 +#define LAN8841_MMD0_REGISTER_17_DROP_OPT(x) ((x) & 0x3) +#define LAN8841_MMD0_REGISTER_17_XMIT_TOG_TX_DIS BIT(3) +#define LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG 2 +#define LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG_MAGJACK BIT(14) +#define LAN8841_MMD_ANALOG_REG 28 +#define LAN8841_ANALOG_CONTROL_1 1 +#define LAN8841_ANALOG_CONTROL_1_PLL_TRIM(x) (((x) & 0x3) << 5) +#define LAN8841_ANALOG_CONTROL_10 13 +#define LAN8841_ANALOG_CONTROL_10_PLL_DIV(x) ((x) & 0x3) +#define LAN8841_ANALOG_CONTROL_11 14 +#define LAN8841_ANALOG_CONTROL_11_LDO_REF(x) (((x) & 0x7) << 12) +#define LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT 69 +#define LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT_VAL 0xbffc +#define LAN8841_BTRX_POWER_DOWN 70 +#define LAN8841_BTRX_POWER_DOWN_QBIAS_CH_A BIT(0) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_A BIT(1) +#define LAN8841_BTRX_POWER_DOWN_QBIAS_CH_B BIT(2) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_B BIT(3) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_C BIT(5) +#define LAN8841_BTRX_POWER_DOWN_BTRX_CH_D BIT(7) +#define LAN8841_ADC_CHANNEL_MASK 198 + +static int lan8841_config_init(struct phy_device *phydev) +{ + int ret; + + ret = ksz9131_config_init(phydev); + if (ret) + return ret; + + /* 100BT Clause 40 improvenent errata */ + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_1, + LAN8841_ANALOG_CONTROL_1_PLL_TRIM(0x2)); + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_10, + LAN8841_ANALOG_CONTROL_10_PLL_DIV(0x1)); + + /* 10M/100M Ethernet Signal Tuning Errata for Shorted-Center Tap + * Magnetics + */ + ret = phy_read_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG); + if (ret & LAN8841_OPERATION_MODE_STRAP_OVERRIDE_LOW_REG_MAGJACK) { + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT, + LAN8841_TX_LOW_I_CH_C_D_POWER_MANAGMENT_VAL); + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_BTRX_POWER_DOWN, + LAN8841_BTRX_POWER_DOWN_QBIAS_CH_A | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_A | + LAN8841_BTRX_POWER_DOWN_QBIAS_CH_B | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_B | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_C | + LAN8841_BTRX_POWER_DOWN_BTRX_CH_D); + } + + /* LDO Adjustment errata */ + phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, + LAN8841_ANALOG_CONTROL_11, + LAN8841_ANALOG_CONTROL_11_LDO_REF(1)); + + /* 100BT RGMII latency tuning errata */ + phy_write_mmd(phydev, MDIO_MMD_PMAPMD, + LAN8841_ADC_CHANNEL_MASK, 0x0); + phy_write_mmd(phydev, LAN8841_MMD_TIMER_REG, + LAN8841_MMD0_REGISTER_17, + LAN8841_MMD0_REGISTER_17_DROP_OPT(2) | + LAN8841_MMD0_REGISTER_17_XMIT_TOG_TX_DIS); + + return 0; +} + +#define LAN8841_OUTPUT_CTRL 25 +#define LAN8841_OUTPUT_CTRL_INT_BUFFER BIT(14) + +static int lan8841_config_intr(struct phy_device *phydev) +{ + int err; + + phy_modify(phydev, LAN8841_OUTPUT_CTRL, + LAN8841_OUTPUT_CTRL_INT_BUFFER, 0); + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = phy_read(phydev, LAN8814_INTS); + if (err) + return err; + + err = phy_write(phydev, LAN8814_INTC, + LAN8814_INT_LINK); + } else { + err = phy_write(phydev, LAN8814_INTC, 0); + if (err) + return err; + + err = phy_read(phydev, LAN8814_INTS); + } + + return err; +} + +static irqreturn_t lan8841_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, LAN8814_INTS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (irq_status & LAN8814_INT_LINK) { + phy_trigger_machine(phydev); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +#define LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER 3 +#define LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER_STRAP_RGMII_EN BIT(0) + +static int lan8841_probe(struct phy_device *phydev) +{ + int err; + + err = kszphy_probe(phydev); + if (err) + return err; + + if (phy_read_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, + LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER) & + LAN8841_OPERATION_MODE_STRAP_LOW_REGISTER_STRAP_RGMII_EN) + phydev->interface = PHY_INTERFACE_MODE_RGMII_RXID; + + return 0; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -3362,12 +3519,30 @@ static struct phy_driver ksphy_driver[] = { .config_intr = lan8804_config_intr, .handle_interrupt = lan8804_handle_interrupt, }, { + .phy_id = PHY_ID_LAN8841, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Microchip LAN8841 Gigabit PHY", + .flags = PHY_POLL_CABLE_TEST, + .driver_data = &lan8841_type, + .config_init = lan8841_config_init, + .probe = lan8841_probe, + .soft_reset = genphy_soft_reset, + .config_intr = lan8841_config_intr, + .handle_interrupt = lan8841_handle_interrupt, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = genphy_resume, + .cable_test_start = lan8814_cable_test_start, + .cable_test_get_status = ksz886x_cable_test_get_status, +}, { .phy_id = PHY_ID_KSZ9131, .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Microchip KSZ9131 Gigabit PHY", /* PHY_GBIT_FEATURES */ .flags = PHY_POLL_CABLE_TEST, - .driver_data = &ksz9021_type, + .driver_data = &ksz9131_type, .probe = kszphy_probe, .config_init = ksz9131_config_init, .config_intr = kszphy_config_intr, @@ -3446,6 +3621,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ886X, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8814, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8804, MICREL_PHY_ID_MASK }, + { PHY_ID_LAN8841, MICREL_PHY_ID_MASK }, { } }; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 319790221d7f..ea8fcce5b2d9 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -1816,10 +1816,9 @@ int phylink_fwnode_phy_connect(struct phylink *pl, ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) { - phy_device_free(phy_dev); + phy_device_free(phy_dev); + if (ret) return ret; - } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) diff --git a/drivers/net/tap.c b/drivers/net/tap.c index a2be1994b389..8941aa199ea3 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -533,7 +533,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data(&q->sock, &q->sk); + sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a7d17c680f4a..ad653b32b2f0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1401,6 +1401,11 @@ static void tun_net_initialize(struct net_device *dev) eth_hw_addr_random(dev); + /* Currently tun does not support XDP, only tap does. */ + dev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; + break; } @@ -3448,7 +3453,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data(&tfile->socket, &tfile->sk); + sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; diff --git a/drivers/net/usb/plusb.c b/drivers/net/usb/plusb.c index 2c82fbcaab22..7a2b0094de51 100644 --- a/drivers/net/usb/plusb.c +++ b/drivers/net/usb/plusb.c @@ -57,9 +57,7 @@ static inline int pl_vendor_req(struct usbnet *dev, u8 req, u8 val, u8 index) { - return usbnet_read_cmd(dev, req, - USB_DIR_IN | USB_TYPE_VENDOR | - USB_RECIP_DEVICE, + return usbnet_write_cmd(dev, req, USB_TYPE_VENDOR | USB_RECIP_DEVICE, val, index, NULL, 0); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index ba3e05832843..1bb54de7124d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1686,6 +1686,10 @@ static void veth_setup(struct net_device *dev) dev->hw_enc_features = VETH_FEATURES; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; netif_set_tso_max_size(dev, GSO_MAX_SIZE); + + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG; } /* diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c6c62d0596bc..fb5e68ed3ec2 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2282,9 +2282,9 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { + virtnet_napi_tx_disable(&vi->sq[i].napi); napi_disable(&vi->rq[i].napi); xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); - virtnet_napi_tx_disable(&vi->sq[i].napi); } return 0; @@ -3283,7 +3283,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); } + if (!old_prog) + xdp_features_set_redirect_target(dev, true); } else { + xdp_features_clear_redirect_target(dev); vi->xdp_enabled = false; } @@ -3919,6 +3922,7 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_GRO_HW; dev->vlan_features = dev->features; + dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; /* MTU range: 68 - 65535 */ dev->min_mtu = MIN_MTU; @@ -3947,8 +3951,10 @@ static int virtnet_probe(struct virtio_device *vdev) INIT_WORK(&vi->config_work, virtnet_config_changed_work); spin_lock_init(&vi->refill_lock); - if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) + if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) { vi->mergeable_rx_bufs = true; + dev->xdp_features |= NETDEV_XDP_ACT_RX_SG; + } if (virtio_has_feature(vi->vdev, VIRTIO_NET_F_NOTF_COAL)) { vi->rx_usecs = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index ec6198f1b38c..3bdd6774716d 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -10,7 +10,7 @@ #include "fw/api/txq.h" /* Highest firmware API version supported */ -#define IWL_22000_UCODE_API_MAX 72 +#define IWL_22000_UCODE_API_MAX 74 /* Lowest firmware API version supported */ #define IWL_22000_UCODE_API_MIN 39 diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 0b052c2e563a..28c87a480246 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -153,6 +153,7 @@ enum iwl_legacy_cmds { /** * @TXPATH_FLUSH: &struct iwl_tx_path_flush_cmd + * response in &struct iwl_tx_path_flush_cmd_rsp */ TXPATH_FLUSH = 0x1e, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h index 9263413ee06f..8b38a0073077 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h @@ -83,7 +83,7 @@ enum iwl_data_path_subcmd_ids { MONITOR_NOTIF = 0xF4, /** - * @RX_NO_DATA_NOTIF: &struct iwl_rx_no_data + * @RX_NO_DATA_NOTIF: &struct iwl_rx_no_data or &struct iwl_rx_no_data_ver_3 */ RX_NO_DATA_NOTIF = 0xF5, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index 74a01888715b..1c4e84932058 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -273,7 +273,7 @@ enum iwl_rx_mpdu_mac_info { }; /* TSF overload low dword */ -enum iwl_rx_phy_data0 { +enum iwl_rx_phy_he_data0 { /* info type: HE any */ IWL_RX_PHY_DATA0_HE_BEAM_CHNG = 0x00000001, IWL_RX_PHY_DATA0_HE_UPLINK = 0x00000002, @@ -289,6 +289,25 @@ enum iwl_rx_phy_data0 { IWL_RX_PHY_DATA0_HE_DELIM_EOF = 0x80000000, }; +/* TSF overload low dword */ +enum iwl_rx_phy_eht_data0 { + /* info type: EHT any */ + /* 1 bits reserved */ + IWL_RX_PHY_DATA0_EHT_UPLINK = BIT(1), + IWL_RX_PHY_DATA0_EHT_BSS_COLOR_MASK = 0x000000fc, + IWL_RX_PHY_DATA0_ETH_SPATIAL_REUSE_MASK = 0x00000f00, + IWL_RX_PHY_DATA0_EHT_PS160 = BIT(12), + IWL_RX_PHY_DATA0_EHT_TXOP_DUR_MASK = 0x000fe000, + IWL_RX_PHY_DATA0_EHT_LDPC_EXT_SYM = BIT(20), + IWL_RX_PHY_DATA0_EHT_PRE_FEC_PAD_MASK = 0x00600000, + IWL_RX_PHY_DATA0_EHT_PE_DISAMBIG = BIT(23), + IWL_RX_PHY_DATA0_EHT_BW320_SLOT = BIT(24), + IWL_RX_PHY_DATA0_EHT_SIGA_CRC_OK = BIT(25), + IWL_RX_PHY_DATA0_EHT_PHY_VER = 0x1c000000, + /* 2 bits reserved */ + IWL_RX_PHY_DATA0_EHT_DELIM_EOF = BIT(31), +}; + enum iwl_rx_phy_info_type { IWL_RX_PHY_INFO_TYPE_NONE = 0, IWL_RX_PHY_INFO_TYPE_CCK = 1, @@ -301,19 +320,26 @@ enum iwl_rx_phy_info_type { IWL_RX_PHY_INFO_TYPE_HE_TB = 8, IWL_RX_PHY_INFO_TYPE_HE_MU_EXT = 9, IWL_RX_PHY_INFO_TYPE_HE_TB_EXT = 10, + IWL_RX_PHY_INFO_TYPE_EHT_MU = 11, + IWL_RX_PHY_INFO_TYPE_EHT_TB = 12, + IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT = 13, + IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT = 14, }; /* TSF overload high dword */ -enum iwl_rx_phy_data1 { +enum iwl_rx_phy_common_data1 { /* * check this first - if TSF overload is set, * see &enum iwl_rx_phy_info_type */ IWL_RX_PHY_DATA1_INFO_TYPE_MASK = 0xf0000000, - /* info type: HT/VHT/HE any */ + /* info type: HT/VHT/HE/EHT any */ IWL_RX_PHY_DATA1_LSIG_LEN_MASK = 0x0fff0000, +}; +/* TSF overload high dword For HE rates*/ +enum iwl_rx_phy_he_data1 { /* info type: HE MU/MU-EXT */ IWL_RX_PHY_DATA1_HE_MU_SIGB_COMPRESSION = 0x00000001, IWL_RX_PHY_DATA1_HE_MU_SIBG_SYM_OR_USER_NUM_MASK = 0x0000001e, @@ -329,8 +355,23 @@ enum iwl_rx_phy_data1 { IWL_RX_PHY_DATA1_HE_TB_LOW_SS_MASK = 0x0000000e, }; +/* TSF overload high dword For EHT-MU/TB rates*/ +enum iwl_rx_phy_eht_data1 { + /* info type: EHT-MU */ + IWL_RX_PHY_DATA1_EHT_MU_NUM_SIG_SYM_USIGA2 = 0x0000001f, + /* info type: EHT-TB */ + IWL_RX_PHY_DATA1_EHT_TB_PILOT_TYPE = BIT(0), + IWL_RX_PHY_DATA1_EHT_TB_LOW_SS = 0x0000001e, + + /* info type: EHT any */ + /* number of EHT-LTF symbols 0 - 1 EHT-LTF, 1 - 2 EHT-LTFs, 2 - 4 EHT-LTFs, + * 3 - 6 EHT-LTFs, 4 - 8 EHT-LTFs */ + IWL_RX_PHY_DATA1_EHT_SIG_LTF_NUM = 0x000000e0, + IWL_RX_PHY_DATA1_EHT_RU_ALLOC = 0x0000ff00, +}; + /* goes into Metadata DW 7 */ -enum iwl_rx_phy_data2 { +enum iwl_rx_phy_he_data2 { /* info type: HE MU-EXT */ /* the a1/a2/... is what the PHY/firmware calls the values */ IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU0 = 0x000000ff, /* a1 */ @@ -346,7 +387,7 @@ enum iwl_rx_phy_data2 { }; /* goes into Metadata DW 8 */ -enum iwl_rx_phy_data3 { +enum iwl_rx_phy_he_data3 { /* info type: HE MU-EXT */ IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU1 = 0x000000ff, /* c1 */ IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU3 = 0x0000ff00, /* c2 */ @@ -355,7 +396,7 @@ enum iwl_rx_phy_data3 { }; /* goes into Metadata DW 4 high 16 bits */ -enum iwl_rx_phy_data4 { +enum iwl_rx_phy_he_he_data4 { /* info type: HE MU-EXT */ IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CTR_RU = 0x0001, IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CTR_RU = 0x0002, @@ -366,6 +407,51 @@ enum iwl_rx_phy_data4 { IWL_RX_PHY_DATA4_HE_MU_EXT_PREAMBLE_PUNC_TYPE_MASK = 0x0600, }; +/* goes into Metadata DW 7 */ +enum iwl_rx_phy_eht_data2 { + /* info type: EHT-MU-EXT */ + /* OFDM_RX_VECTOR_COMMON_RU_ALLOC_0_OUT */ + IWL_RX_PHY_DATA2_EHT_MU_EXT_RU_ALLOC_A1 = 0x000001ff, + IWL_RX_PHY_DATA2_EHT_MU_EXT_RU_ALLOC_A2 = 0x0003fe00, + IWL_RX_PHY_DATA2_EHT_MU_EXT_RU_ALLOC_A3 = 0x01fc0000, + + /* info type: EHT-TB-EXT */ + IWL_RX_PHY_DATA2_EHT_TB_EXT_TRIG_SIGA1 = 0xffffffff, +}; + +/* goes into Metadata DW 8 */ +enum iwl_rx_phy_eht_data3 { + /* info type: EHT-MU-EXT */ + /* OFDM_RX_VECTOR_COMMON_RU_ALLOC_1_OUT */ + IWL_RX_PHY_DATA3_EHT_MU_EXT_RU_ALLOC_B1 = 0x000001ff, + IWL_RX_PHY_DATA3_EHT_MU_EXT_RU_ALLOC_B2 = 0x0003fe00, + IWL_RX_PHY_DATA3_EHT_MU_EXT_RU_ALLOC_B3 = 0x01fc0000, +}; + +/* goes into Metadata DW 4 */ +enum iwl_rx_phy_eht_data4 { + /* info type: EHT-MU-EXT */ + /* OFDM_RX_VECTOR_COMMON_RU_ALLOC_2_OUT */ + IWL_RX_PHY_DATA4_EHT_MU_EXT_RU_ALLOC_C1 = 0x000001ff, + IWL_RX_PHY_DATA4_EHT_MU_EXT_RU_ALLOC_C2 = 0x0003fe00, + IWL_RX_PHY_DATA4_EHT_MU_EXT_RU_ALLOC_C3 = 0x01fc0000, + IWL_RX_PHY_DATA4_EHT_MU_EXT_SIGB_MCS = 0x18000000, +}; + +/* goes into Metadata DW 16 */ +enum iwl_rx_phy_data5 { + /* info type: EHT any */ + IWL_RX_PHY_DATA5_EHT_TYPE_AND_COMP = 0x00000003, + /* info type: EHT-TB */ + IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE1 = 0x0000003c, + IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE2 = 0x000003c0, + /* info type: EHT-MU */ + IWL_RX_PHY_DATA5_EHT_MU_PUNC_CH_CODE = 0x0000007c, + IWL_RX_PHY_DATA5_EHT_MU_STA_ID_USR = 0x0003ff80, + IWL_RX_PHY_DATA5_EHT_MU_NUM_USR_NON_OFDMA = 0x001c0000, + IWL_RX_PHY_DATA5_EHT_MU_SPATIAL_CONF_USR_FIELD = 0x0fe00000, +}; + /** * struct iwl_rx_mpdu_desc_v1 - RX MPDU descriptor */ @@ -440,7 +526,9 @@ struct iwl_rx_mpdu_desc_v1 { /** * @phy_data1: valid only if * %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set, - * see &enum iwl_rx_phy_data1. + * see &enum iwl_rx_phy_common_data1 or + * &enum iwl_rx_phy_he_data1 or + * &enum iwl_rx_phy_eht_data1. */ __le32 phy_data1; }; @@ -540,11 +628,18 @@ struct iwl_rx_mpdu_desc_v3 { __le32 phy_data1; }; }; - /* DW16 & DW17 */ + /* DW16 */ + /** + * @phy_data5: valid only if + * %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set, + * see &enum iwl_rx_phy_data5. + */ + __le32 phy_data5; + /* DW17 */ /** * @reserved: reserved */ - __le32 reserved[2]; + __le32 reserved[1]; } __packed; /* RX_MPDU_RES_START_API_S_VER_3, RX_MPDU_RES_START_API_S_VER_5 */ @@ -639,12 +734,14 @@ struct iwl_rx_mpdu_desc { #define RX_NO_DATA_INFO_ERR_UNSUPPORTED_RATE 2 #define RX_NO_DATA_INFO_ERR_NO_DELIM 3 #define RX_NO_DATA_INFO_ERR_BAD_MAC_HDR 4 +#define RX_NO_DATA_INFO_LOW_ENERGY 5 #define RX_NO_DATA_FRAME_TIME_POS 0 #define RX_NO_DATA_FRAME_TIME_MSK (0xfffff << RX_NO_DATA_FRAME_TIME_POS) #define RX_NO_DATA_RX_VEC0_HE_NSTS_MSK 0x03800000 #define RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK 0x38000000 +#define RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK 0x00f00000 /** * struct iwl_rx_no_data - RX no data descriptor @@ -654,7 +751,8 @@ struct iwl_rx_mpdu_desc { * @on_air_rise_time: GP2 during on air rise * @fr_time: frame time * @rate: rate/mcs of frame - * @phy_info: &enum iwl_rx_phy_data0 and &enum iwl_rx_phy_info_type + * @phy_info: &enum iwl_rx_phy_he_data0 or &enum iwl_rx_phy_eht_data0 + * based on &enum iwl_rx_phy_info_type * @rx_vec: DW-12:9 raw RX vectors from DSP according to modulation type. * for VHT: OFDM_RX_VECTOR_SIGA1_OUT, OFDM_RX_VECTOR_SIGA2_OUT * for HE: OFDM_RX_VECTOR_HE_SIGA1_OUT, OFDM_RX_VECTOR_HE_SIGA2_OUT @@ -670,6 +768,33 @@ struct iwl_rx_no_data { } __packed; /* RX_NO_DATA_NTFY_API_S_VER_1, RX_NO_DATA_NTFY_API_S_VER_2 */ +/** + * struct iwl_rx_no_data_ver_3 - RX no data descriptor + * @info: 7:0 frame type, 15:8 RX error type + * @rssi: 7:0 energy chain-A, + * 15:8 chain-B, measured at FINA time (FINA_ENERGY), 16:23 channel + * @on_air_rise_time: GP2 during on air rise + * @fr_time: frame time + * @rate: rate/mcs of frame + * @phy_info: &enum iwl_rx_phy_eht_data0 and &enum iwl_rx_phy_info_type + * @rx_vec: DW-12:9 raw RX vectors from DSP according to modulation type. + * for VHT: OFDM_RX_VECTOR_SIGA1_OUT, OFDM_RX_VECTOR_SIGA2_OUT + * for HE: OFDM_RX_VECTOR_HE_SIGA1_OUT, OFDM_RX_VECTOR_HE_SIGA2_OUT + * for EHT: OFDM_RX_VECTOR_USIG_A1_OUT, OFDM_RX_VECTOR_USIG_A2_OUT, + * OFDM_RX_VECTOR_EHT_OUT, OFDM_RX_VECTOR_EHT_USER_FIELD_OUT + */ +struct iwl_rx_no_data_ver_3 { + __le32 info; + __le32 rssi; + __le32 on_air_rise_time; + __le32 fr_time; + __le32 rate; + __le32 phy_info[2]; + __le32 rx_vec[4]; +} __packed; /* RX_NO_DATA_NTFY_API_S_VER_1, + RX_NO_DATA_NTFY_API_S_VER_2 + RX_NO_DATA_NTFY_API_S_VER_3 */ + struct iwl_frame_release { u8 baid; u8 reserved; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c index 6d408cd0f517..0b6f694cf30d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright(c) 2021 Intel Corporation + * Copyright(c) 2021-2022 Intel Corporation */ #include "iwl-drv.h" @@ -246,6 +246,63 @@ void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len) return data; } +static int iwl_uefi_step_parse(struct uefi_cnv_common_step_data *common_step_data, + struct iwl_trans *trans) +{ + if (common_step_data->revision != 1) + return -EINVAL; + + trans->mbx_addr_0_step = (u32)common_step_data->revision | + (u32)common_step_data->cnvi_eq_channel << 8 | + (u32)common_step_data->cnvr_eq_channel << 16 | + (u32)common_step_data->radio1 << 24; + trans->mbx_addr_1_step = (u32)common_step_data->radio2; + return 0; +} + +void iwl_uefi_get_step_table(struct iwl_trans *trans) +{ + struct uefi_cnv_common_step_data *data; + unsigned long package_size; + efi_status_t status; + int ret; + + if (trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_AX210) + return; + + if (!efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE)) + return; + + /* TODO: we hardcode a maximum length here, because reading + * from the UEFI is not working. To implement this properly, + * we have to call efivar_entry_size(). + */ + package_size = IWL_HARDCODED_STEP_SIZE; + + data = kmalloc(package_size, GFP_KERNEL); + if (!data) + return; + + status = efi.get_variable(IWL_UEFI_STEP_NAME, &IWL_EFI_VAR_GUID, + NULL, &package_size, data); + if (status != EFI_SUCCESS) { + IWL_DEBUG_FW(trans, + "STEP UEFI variable not found 0x%lx\n", status); + goto out_free; + } + + IWL_DEBUG_FW(trans, "Read STEP from UEFI with size %lu\n", + package_size); + + ret = iwl_uefi_step_parse(data, trans); + if (ret < 0) + IWL_DEBUG_FW(trans, "Cannot read STEP tables. rev is invalid\n"); + +out_free: + kfree(data); +} +IWL_EXPORT_SYMBOL(iwl_uefi_get_step_table); + #ifdef CONFIG_ACPI static int iwl_uefi_sgom_parse(struct uefi_cnv_wlan_sgom_data *sgom_data, struct iwl_fw_runtime *fwrt) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h index 09d2a971b3a0..17089bc74cf9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright(c) 2021 Intel Corporation + * Copyright(c) 2021-2022 Intel Corporation */ #ifndef __iwl_fw_uefi__ #define __iwl_fw_uefi__ @@ -8,6 +8,7 @@ #define IWL_UEFI_OEM_PNVM_NAME L"UefiCnvWlanOemSignedPnvm" #define IWL_UEFI_REDUCED_POWER_NAME L"UefiCnvWlanReducedPower" #define IWL_UEFI_SGOM_NAME L"UefiCnvWlanSarGeoOffsetMapping" +#define IWL_UEFI_STEP_NAME L"UefiCnvCommonSTEP" /* * TODO: we have these hardcoded values that the caller must pass, @@ -18,6 +19,7 @@ #define IWL_HARDCODED_PNVM_SIZE 4096 #define IWL_HARDCODED_REDUCE_POWER_SIZE 32768 #define IWL_HARDCODED_SGOM_SIZE 339 +#define IWL_HARDCODED_STEP_SIZE 6 struct pnvm_sku_package { u8 rev; @@ -32,6 +34,15 @@ struct uefi_cnv_wlan_sgom_data { u8 offset_map[IWL_HARDCODED_SGOM_SIZE - 1]; } __packed; +struct uefi_cnv_common_step_data { + u8 revision; + u8 step_mode; + u8 cnvi_eq_channel; + u8 cnvr_eq_channel; + u8 radio1; + u8 radio2; +} __packed; + /* * This is known to be broken on v4.19 and to work on v5.4. Until we * figure out why this is the case and how to make it work, simply @@ -40,6 +51,7 @@ struct uefi_cnv_wlan_sgom_data { #ifdef CONFIG_EFI void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len); void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len); +void iwl_uefi_get_step_table(struct iwl_trans *trans); #else /* CONFIG_EFI */ static inline void *iwl_uefi_get_pnvm(struct iwl_trans *trans, size_t *len) @@ -52,6 +64,11 @@ void *iwl_uefi_get_reduced_power(struct iwl_trans *trans, size_t *len) { return ERR_PTR(-EOPNOTSUPP); } + +static inline +void iwl_uefi_get_step_table(struct iwl_trans *trans) +{ +} #endif /* CONFIG_EFI */ #if defined(CONFIG_EFI) && defined(CONFIG_ACPI) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h index b84884034c74..3f7278014009 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h @@ -141,12 +141,27 @@ struct iwl_prph_scratch_uefi_cfg { } __packed; /* PERIPH_SCRATCH_UEFI_CFG_S */ /* + * struct iwl_prph_scratch_step_cfg - prph scratch step configuration + * @mbx_addr_0: [0:7] revision, + * [8:15] cnvi_to_cnvr length, + * [16:23] cnvr_to_cnvi channel length, + * [24:31] radio1 reserved + * @mbx_addr_1: [0:7] radio2 reserved + */ + +struct iwl_prph_scratch_step_cfg { + __le32 mbx_addr_0; + __le32 mbx_addr_1; +} __packed; + +/* * struct iwl_prph_scratch_ctrl_cfg - prph scratch ctrl and config * @version: version information of context info and HW * @control: control flags of FH configurations * @pnvm_cfg: ror configuration * @hwm_cfg: hwm configuration * @rbd_cfg: default RX queue configuration + * @step_cfg: step configuration */ struct iwl_prph_scratch_ctrl_cfg { struct iwl_prph_scratch_version version; @@ -155,6 +170,7 @@ struct iwl_prph_scratch_ctrl_cfg { struct iwl_prph_scratch_hwm_cfg hwm_cfg; struct iwl_prph_scratch_rbd_cfg rbd_cfg; struct iwl_prph_scratch_uefi_cfg reduce_power_cfg; + struct iwl_prph_scratch_step_cfg step_cfg; } __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */ /* @@ -165,7 +181,7 @@ struct iwl_prph_scratch_ctrl_cfg { */ struct iwl_prph_scratch { struct iwl_prph_scratch_ctrl_cfg ctrl_cfg; - __le32 reserved[12]; + __le32 reserved[10]; struct iwl_context_info_dram dram; } __packed; /* PERIPH_SCRATCH_S */ @@ -265,5 +281,6 @@ int iwl_trans_pcie_ctx_info_gen3_set_pnvm(struct iwl_trans *trans, const void *data, u32 len); int iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans, const void *data, u32 len); - +int iwl_trans_pcie_ctx_info_gen3_set_step(struct iwl_trans *trans, + u32 mbx_addr_0_step, u32 mbx_addr_1_step); #endif /* __iwl_context_info_file_gen3_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index ab7065c93826..4c977ba9cd85 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -163,7 +163,6 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, static int iwl_request_firmware(struct iwl_drv *drv, bool first) { const struct iwl_cfg *cfg = drv->trans->cfg; - char tag[8]; if (drv->trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_9000 && (drv->trans->hw_rev_step != SILICON_B_STEP && @@ -174,13 +173,10 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) return -EINVAL; } - if (first) { + if (first) drv->fw_index = cfg->ucode_api_max; - sprintf(tag, "%d", drv->fw_index); - } else { + else drv->fw_index--; - sprintf(tag, "%d", drv->fw_index); - } if (drv->fw_index < cfg->ucode_api_min) { IWL_ERR(drv, "no suitable firmware found!\n"); @@ -200,8 +196,8 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) return -ENOENT; } - snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%s.ucode", - cfg->fw_name_pre, tag); + snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%d.ucode", + cfg->fw_name_pre, drv->fw_index); IWL_DEBUG_FW_INFO(drv, "attempting to load firmware '%s'\n", drv->firmware_name); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index 479a518c89a1..9aced3e44bc2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -1001,6 +1001,8 @@ struct iwl_trans_txqs { * This mode is set dynamically, depending on the WoWLAN values * configured from the userspace at runtime. * @iwl_trans_txqs: transport tx queues data. + * @mbx_addr_0_step: step address data 0 + * @mbx_addr_1_step: step address data 1 */ struct iwl_trans { bool csme_own; @@ -1057,6 +1059,8 @@ struct iwl_trans { const char *name; struct iwl_trans_txqs txqs; + u32 mbx_addr_0_step; + u32 mbx_addr_1_step; /* pointer to trans specific struct */ /*Ensure that this pointer will always be aligned to sizeof pointer */ diff --git a/drivers/net/wireless/intel/iwlwifi/mei/main.c b/drivers/net/wireless/intel/iwlwifi/mei/main.c index f9d11935ed97..67dfb77fedf7 100644 --- a/drivers/net/wireless/intel/iwlwifi/mei/main.c +++ b/drivers/net/wireless/intel/iwlwifi/mei/main.c @@ -788,7 +788,7 @@ static void iwl_mei_handle_amt_state(struct mei_cl_device *cldev, if (mei->amt_enabled) iwl_mei_set_init_conf(mei); else if (iwl_mei_cache.ops) - iwl_mei_cache.ops->rfkill(iwl_mei_cache.priv, false, false); + iwl_mei_cache.ops->rfkill(iwl_mei_cache.priv, false); schedule_work(&mei->netdev_work); @@ -829,7 +829,7 @@ static void iwl_mei_handle_csme_taking_ownership(struct mei_cl_device *cldev, */ mei->csme_taking_ownership = true; - iwl_mei_cache.ops->rfkill(iwl_mei_cache.priv, true, true); + iwl_mei_cache.ops->rfkill(iwl_mei_cache.priv, true); } else { iwl_mei_send_sap_msg(cldev, SAP_MSG_NOTIF_CSME_OWNERSHIP_CONFIRMED); @@ -1774,7 +1774,7 @@ int iwl_mei_register(void *priv, const struct iwl_mei_ops *ops) if (mei->amt_enabled) iwl_mei_send_sap_msg(mei->cldev, SAP_MSG_NOTIF_WIFIDR_UP); - ops->rfkill(priv, mei->link_prot_state, false); + ops->rfkill(priv, mei->link_prot_state); } } ret = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 1ce9450e5add..85b99316d029 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -324,12 +324,12 @@ static ssize_t iwl_dbgfs_sar_geo_profile_read(struct file *file, pos += scnprintf(buf + pos, bufsz - pos, "Use geographic profile %d\n", tbl_idx); pos += scnprintf(buf + pos, bufsz - pos, - "2.4GHz:\n\tChain A offset: %hhu dBm\n\tChain B offset: %hhu dBm\n\tmax tx power: %hhu dBm\n", + "2.4GHz:\n\tChain A offset: %u dBm\n\tChain B offset: %u dBm\n\tmax tx power: %u dBm\n", mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].chains[0], mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].chains[1], mvm->fwrt.geo_profiles[tbl_idx - 1].bands[0].max); pos += scnprintf(buf + pos, bufsz - pos, - "5.2GHz:\n\tChain A offset: %hhu dBm\n\tChain B offset: %hhu dBm\n\tmax tx power: %hhu dBm\n", + "5.2GHz:\n\tChain A offset: %u dBm\n\tChain B offset: %u dBm\n\tmax tx power: %u dBm\n", mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].chains[0], mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].chains[1], mvm->fwrt.geo_profiles[tbl_idx - 1].bands[1].max); @@ -1069,7 +1069,7 @@ iwl_dbgfs_scan_ant_rxchain_read(struct file *file, pos += scnprintf(buf + pos, bufsz - pos, "A"); if (mvm->scan_rx_ant & ANT_B) pos += scnprintf(buf + pos, bufsz - pos, "B"); - pos += scnprintf(buf + pos, bufsz - pos, " (%hhx)\n", mvm->scan_rx_ant); + pos += scnprintf(buf + pos, bufsz - pos, " (%x)\n", mvm->scan_rx_ant); return simple_read_from_buffer(user_buf, count, ppos, buf, pos); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c index 6eee3d0b2157..05f3136b1c43 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c @@ -1206,7 +1206,7 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) } IWL_DEBUG_INFO(mvm, "Range response received\n"); - IWL_DEBUG_INFO(mvm, "request id: %lld, num of entries: %hhu\n", + IWL_DEBUG_INFO(mvm, "request id: %lld, num of entries: %u\n", mvm->ftm_initiator.req->cookie, num_of_aps); for (i = 0; i < num_of_aps && i < IWL_MVM_TOF_MAX_APS; i++) { @@ -1298,7 +1298,7 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) if (fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_FTM_RTT_ACCURACY)) - IWL_DEBUG_INFO(mvm, "RTT confidence: %hhu\n", + IWL_DEBUG_INFO(mvm, "RTT confidence: %u\n", fw_ap->rttConfidence); iwl_mvm_debug_range_resp(mvm, i, &result); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 5273ade71117..565522466eba 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -5116,6 +5116,9 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo) case RATE_MCS_CHAN_WIDTH_160: rinfo->bw = RATE_INFO_BW_160; break; + case RATE_MCS_CHAN_WIDTH_320: + rinfo->bw = RATE_INFO_BW_320; + break; } if (format == RATE_MCS_CCK_MSK || @@ -5176,6 +5179,10 @@ static void iwl_mvm_set_sta_rate(u32 rate_n_flags, struct rate_info *rinfo) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; switch (format) { + case RATE_MCS_EHT_MSK: + /* TODO: GI/LTF/RU. How does the firmware encode them? */ + rinfo->flags |= RATE_INFO_FLAGS_EHT_MCS; + break; case RATE_MCS_HE_MSK: gi_ltf = u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index ebe6d9c4ccaf..f4e9446d9dc2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -1128,6 +1128,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, iwl_mvm_get_acpi_tables(mvm); iwl_uefi_get_sgom_table(trans, &mvm->fwrt); + iwl_uefi_get_step_table(trans); mvm->init_status = 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 97b67270f384..549dbe0be223 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -10,37 +10,11 @@ #include "mvm.h" #include "fw-api.h" -static void *iwl_mvm_skb_get_hdr(struct sk_buff *skb) -{ - struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - u8 *data = skb->data; - - /* Alignment concerns */ - BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he) % 4); - BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) % 4); - BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_lsig) % 4); - BUILD_BUG_ON(sizeof(struct ieee80211_vendor_radiotap) % 4); - - if (rx_status->flag & RX_FLAG_RADIOTAP_HE) - data += sizeof(struct ieee80211_radiotap_he); - if (rx_status->flag & RX_FLAG_RADIOTAP_HE_MU) - data += sizeof(struct ieee80211_radiotap_he_mu); - if (rx_status->flag & RX_FLAG_RADIOTAP_LSIG) - data += sizeof(struct ieee80211_radiotap_lsig); - if (rx_status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { - struct ieee80211_vendor_radiotap *radiotap = (void *)data; - - data += sizeof(*radiotap) + radiotap->len + radiotap->pad; - } - - return data; -} - static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb, int queue, struct ieee80211_sta *sta) { struct iwl_mvm_sta *mvmsta; - struct ieee80211_hdr *hdr = iwl_mvm_skb_get_hdr(skb); + struct ieee80211_hdr *hdr = (void *)skb_mac_header(skb); struct ieee80211_rx_status *stats = IEEE80211_SKB_RXCB(skb); struct iwl_mvm_key_pn *ptk_pn; int res; @@ -179,6 +153,10 @@ static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb, if (unlikely(headlen < hdrlen)) return -EINVAL; + /* Since data doesn't move data while putting data on skb and that is + * the only way we use, data + len is the next place that hdr would be put + */ + skb_set_mac_header(skb, skb->len); skb_put_data(skb, hdr, hdrlen); skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen); @@ -936,7 +914,7 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, struct iwl_rx_mpdu_desc *desc) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - struct ieee80211_hdr *hdr = iwl_mvm_skb_get_hdr(skb); + struct ieee80211_hdr *hdr = (void *)skb_mac_header(skb); struct iwl_mvm_sta *mvm_sta; struct iwl_mvm_baid_data *baid_data; struct iwl_mvm_reorder_buffer *buffer; @@ -1346,6 +1324,10 @@ static void iwl_mvm_decode_he_phy_data(struct iwl_mvm *mvm, case IWL_RX_PHY_INFO_TYPE_HT: case IWL_RX_PHY_INFO_TYPE_VHT_SU: case IWL_RX_PHY_INFO_TYPE_VHT_MU: + case IWL_RX_PHY_INFO_TYPE_EHT_MU: + case IWL_RX_PHY_INFO_TYPE_EHT_TB: + case IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT: + case IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT: return; case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT: he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN | @@ -1690,6 +1672,9 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm, case RATE_MCS_CHAN_WIDTH_160: rx_status->bw = RATE_INFO_BW_160; break; + case RATE_MCS_CHAN_WIDTH_320: + rx_status->bw = RATE_INFO_BW_320; + break; } /* must be before L-SIG data */ @@ -1726,6 +1711,9 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm, rx_status->he_dcm = !!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK); break; + case RATE_MCS_EHT_MSK: + rx_status->encoding = RX_ENC_EHT; + break; } switch (format) { @@ -1736,6 +1724,7 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm, break; case RATE_MCS_VHT_MSK: case RATE_MCS_HE_MSK: + case RATE_MCS_EHT_MSK: rx_status->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1; rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK; @@ -1747,10 +1736,11 @@ static void iwl_mvm_rx_fill_status(struct iwl_mvm *mvm, rx_status->rate_idx = rate; - if ((rate < 0 || rate > 0xFF) && net_ratelimit()) { - IWL_ERR(mvm, "Invalid rate flags 0x%x, band %d,\n", - rate_n_flags, rx_status->band); + if ((rate < 0 || rate > 0xFF)) { rx_status->rate_idx = 0; + if (net_ratelimit()) + IWL_ERR(mvm, "Invalid rate flags 0x%x, band %d,\n", + rate_n_flags, rx_status->band); } break; @@ -2065,7 +2055,7 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, { struct ieee80211_rx_status *rx_status; struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl_rx_no_data *desc = (void *)pkt->data; + struct iwl_rx_no_data_ver_3 *desc = (void *)pkt->data; u32 rssi; u32 info_type; struct ieee80211_sta *sta = NULL; @@ -2101,6 +2091,18 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK; + if (iwl_fw_lookup_notif_ver(mvm->fw, DATA_PATH_GROUP, + RX_NO_DATA_NOTIF, 0) >= 3) { + if (unlikely(iwl_rx_packet_payload_len(pkt) < + sizeof(struct iwl_rx_no_data_ver_3))) + /* invalid len for ver 3 */ + return; + } else { + if (format == RATE_MCS_EHT_MSK) + /* no support for EHT before version 3 API */ + return; + } + /* Dont use dev_alloc_skb(), we'll have enough headroom once * ieee80211_hdr pulled. */ @@ -2136,6 +2138,16 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, iwl_mvm_rx_fill_status(mvm, skb, &phy_data, queue); + /* no more radio tap info should be put after this point. + * + * We mark it as mac header, for upper layers to know where + * all radio tap header ends. + * + * Since data doesn't move data while putting data on skb and that is + * the only way we use, data + len is the next place that hdr would be put + */ + skb_set_mac_header(skb, skb->len); + /* * Override the nss from the rx_vec since the rate_n_flags has * only 2 bits for the nss which gives a max of 4 ss but there @@ -2152,6 +2164,10 @@ void iwl_mvm_rx_monitor_no_data(struct iwl_mvm *mvm, struct napi_struct *napi, le32_get_bits(desc->rx_vec[0], RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1; break; + case RATE_MCS_EHT_MSK: + rx_status->nss = + le32_get_bits(desc->rx_vec[2], + RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK) + 1; } rcu_read_lock(); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index fadaa683a416..9813d7fa1800 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -1107,8 +1107,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, spin_lock(&mvmsta->lock); /* nullfunc frames should go to the MGMT queue regardless of QOS, - * the condition of !ieee80211_is_qos_nullfunc(fc) keeps the default - * assignment of MGMT TID + * the conditions of !ieee80211_is_qos_nullfunc(fc) and + * !ieee80211_is_data_qos(fc) keep the default assignment of MGMT TID */ if (ieee80211_is_data_qos(fc) && !ieee80211_is_qos_nullfunc(fc)) { tid = ieee80211_get_tid(hdr); @@ -1133,7 +1133,8 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, /* update the tx_cmd hdr as it was already copied */ tx_cmd->hdr->seq_ctrl = hdr->seq_ctrl; } - } else if (ieee80211_is_data(fc) && !ieee80211_is_data_qos(fc)) { + } else if (ieee80211_is_data(fc) && !ieee80211_is_data_qos(fc) && + !ieee80211_is_nullfunc(fc)) { tid = IWL_TID_NON_QOS; } diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index 75fd386b048e..cb60ba40fe97 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -136,6 +136,10 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, &control_flags); prph_sc_ctrl->control.control_flags = cpu_to_le32(control_flags); + /* initialize the Step equalizer data */ + prph_sc_ctrl->step_cfg.mbx_addr_0 = cpu_to_le32(trans->mbx_addr_0_step); + prph_sc_ctrl->step_cfg.mbx_addr_1 = cpu_to_le32(trans->mbx_addr_1_step); + /* allocate ucode sections in dram and set addresses */ ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram); if (ret) @@ -343,3 +347,4 @@ int iwl_trans_pcie_ctx_info_gen3_set_reduce_power(struct iwl_trans *trans, return 0; } + diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 12b074286df9..47d54d8ea59d 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1741,6 +1741,8 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) * negotiate with the backend regarding supported features. */ netdev->features |= netdev->hw_features; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; netdev->ethtool_ops = &xennet_ethtool_ops; netdev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 4424f53a8a0a..b57630d1d3b8 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -45,6 +45,8 @@ struct nvme_dhchap_queue_context { int sess_key_len; }; +struct workqueue_struct *nvme_auth_wq; + #define nvme_auth_flags_from_qid(qid) \ (qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED #define nvme_auth_queue_from_qid(ctrl, qid) \ @@ -866,7 +868,7 @@ int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) chap = &ctrl->dhchap_ctxs[qid]; cancel_work_sync(&chap->auth_work); - queue_work(nvme_wq, &chap->auth_work); + queue_work(nvme_auth_wq, &chap->auth_work); return 0; } EXPORT_SYMBOL_GPL(nvme_auth_negotiate); @@ -1008,10 +1010,15 @@ EXPORT_SYMBOL_GPL(nvme_auth_free); int __init nvme_init_auth(void) { + nvme_auth_wq = alloc_workqueue("nvme-auth-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!nvme_auth_wq) + return -ENOMEM; + nvme_chap_buf_cache = kmem_cache_create("nvme-chap-buf-cache", CHAP_BUF_SIZE, 0, SLAB_HWCACHE_ALIGN, NULL); if (!nvme_chap_buf_cache) - return -ENOMEM; + goto err_destroy_workqueue; nvme_chap_buf_pool = mempool_create(16, mempool_alloc_slab, mempool_free_slab, nvme_chap_buf_cache); @@ -1021,6 +1028,8 @@ int __init nvme_init_auth(void) return 0; err_destroy_chap_buf_cache: kmem_cache_destroy(nvme_chap_buf_cache); +err_destroy_workqueue: + destroy_workqueue(nvme_auth_wq); return -ENOMEM; } @@ -1028,4 +1037,5 @@ void __exit nvme_exit_auth(void) { mempool_destroy(nvme_chap_buf_pool); kmem_cache_destroy(nvme_chap_buf_cache); + destroy_workqueue(nvme_auth_wq); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 505e16f20e57..8b6421141162 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4921,7 +4921,9 @@ out_cleanup_admin_q: blk_mq_destroy_queue(ctrl->admin_q); blk_put_queue(ctrl->admin_q); out_free_tagset: - blk_mq_free_tag_set(ctrl->admin_tagset); + blk_mq_free_tag_set(set); + ctrl->admin_q = NULL; + ctrl->fabrics_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set); @@ -4983,6 +4985,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, out_free_tag_set: blk_mq_free_tag_set(set); + ctrl->connect_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ab2627e17bb9..1ab6601fdd5c 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1685,8 +1685,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, else { queue = nvmet_fc_alloc_target_queue(iod->assoc, 0, be16_to_cpu(rqst->assoc_cmd.sqsize)); - if (!queue) + if (!queue) { ret = VERR_QUEUE_ALLOC_FAIL; + nvmet_fc_tgt_a_put(iod->assoc); + } } } diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c index 34130449f2d2..39aa27942f28 100644 --- a/drivers/nvmem/brcm_nvram.c +++ b/drivers/nvmem/brcm_nvram.c @@ -98,6 +98,9 @@ static int brcm_nvram_parse(struct brcm_nvram *priv) len = le32_to_cpu(header.len); data = kzalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + memcpy_fromio(data, priv->base, len); data[len - 1] = '\0'; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 321d7d63e068..34ee9d36ee7b 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -770,31 +770,32 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) return ERR_PTR(rval); } - if (config->wp_gpio) - nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + nvmem->id = rval; + + nvmem->dev.type = &nvmem_provider_type; + nvmem->dev.bus = &nvmem_bus_type; + nvmem->dev.parent = config->dev; + + device_initialize(&nvmem->dev); + + if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { - ida_free(&nvmem_ida, nvmem->id); rval = PTR_ERR(nvmem->wp_gpio); - kfree(nvmem); - return ERR_PTR(rval); + nvmem->wp_gpio = NULL; + goto err_put_device; } kref_init(&nvmem->refcnt); INIT_LIST_HEAD(&nvmem->cells); - nvmem->id = rval; nvmem->owner = config->owner; if (!nvmem->owner && config->dev->driver) nvmem->owner = config->dev->driver->owner; nvmem->stride = config->stride ?: 1; nvmem->word_size = config->word_size ?: 1; nvmem->size = config->size; - nvmem->dev.type = &nvmem_provider_type; - nvmem->dev.bus = &nvmem_bus_type; - nvmem->dev.parent = config->dev; nvmem->root_only = config->root_only; nvmem->priv = config->priv; nvmem->type = config->type; @@ -822,11 +823,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) break; } - if (rval) { - ida_free(&nvmem_ida, nvmem->id); - kfree(nvmem); - return ERR_PTR(rval); - } + if (rval) + goto err_put_device; nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; @@ -835,28 +833,22 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->dev.groups = nvmem_dev_groups; #endif - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - - rval = device_register(&nvmem->dev); - if (rval) - goto err_put_device; - if (nvmem->nkeepout) { rval = nvmem_validate_keepouts(nvmem); if (rval) - goto err_device_del; + goto err_put_device; } if (config->compat) { rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) - goto err_device_del; + goto err_put_device; } if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) - goto err_teardown_compat; + goto err_remove_cells; } rval = nvmem_add_cells_from_table(nvmem); @@ -867,17 +859,20 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); + + rval = device_add(&nvmem->dev); + if (rval) + goto err_remove_cells; + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; err_remove_cells: nvmem_device_remove_all_cells(nvmem); -err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); -err_device_del: - device_del(&nvmem->dev); err_put_device: put_device(&nvmem->dev); @@ -1242,16 +1237,21 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) if (!cell_np) return ERR_PTR(-ENOENT); - nvmem_np = of_get_next_parent(cell_np); - if (!nvmem_np) + nvmem_np = of_get_parent(cell_np); + if (!nvmem_np) { + of_node_put(cell_np); return ERR_PTR(-EINVAL); + } nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); - if (IS_ERR(nvmem)) + if (IS_ERR(nvmem)) { + of_node_put(cell_np); return ERR_CAST(nvmem); + } cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np); + of_node_put(cell_np); if (!cell_entry) { __nvmem_device_put(nvmem); return ERR_PTR(-ENOENT); diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c index 4fcb63507ecd..8499892044b7 100644 --- a/drivers/nvmem/qcom-spmi-sdam.c +++ b/drivers/nvmem/qcom-spmi-sdam.c @@ -166,6 +166,7 @@ static const struct of_device_id sdam_match_table[] = { { .compatible = "qcom,spmi-sdam" }, {}, }; +MODULE_DEVICE_TABLE(of, sdam_match_table); static struct platform_driver sdam_driver = { .driver = { diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 5750e1f4bcdb..92dfe4cb10e3 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -41,8 +41,21 @@ static int sunxi_sid_read(void *context, unsigned int offset, void *val, size_t bytes) { struct sunxi_sid *sid = context; + u32 word; + + /* .stride = 4 so offset is guaranteed to be aligned */ + __ioread32_copy(val, sid->base + sid->value_offset + offset, bytes / 4); - memcpy_fromio(val, sid->base + sid->value_offset + offset, bytes); + val += round_down(bytes, 4); + offset += round_down(bytes, 4); + bytes = bytes % 4; + + if (!bytes) + return 0; + + /* Handle any trailing bytes */ + word = readl_relaxed(sid->base + sid->value_offset + offset); + memcpy(val, &word, bytes); return 0; } diff --git a/drivers/of/address.c b/drivers/of/address.c index c34ac33b7338..67763e5b8c0e 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -965,8 +965,19 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } of_dma_range_parser_init(&parser, node); - for_each_of_range(&parser, &range) + for_each_of_range(&parser, &range) { + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } num_ranges++; + } + + if (!num_ranges) { + ret = -EINVAL; + goto out; + } r = kcalloc(num_ranges + 1, sizeof(*r), GFP_KERNEL); if (!r) { @@ -975,18 +986,16 @@ int of_dma_get_range(struct device_node *np, const struct bus_dma_region **map) } /* - * Record all info in the generic DMA ranges array for struct device. + * Record all info in the generic DMA ranges array for struct device, + * returning an error if we don't find any parsable ranges. */ *map = r; of_dma_range_parser_init(&parser, node); for_each_of_range(&parser, &range) { pr_debug("dma_addr(%llx) cpu_addr(%llx) size(%llx)\n", range.bus_addr, range.cpu_addr, range.size); - if (range.cpu_addr == OF_BAD_ADDR) { - pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", - range.bus_addr, node); + if (range.cpu_addr == OF_BAD_ADDR) continue; - } r->cpu_start = range.cpu_addr; r->dma_start = range.bus_addr; r->size = range.size; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index f08b25195ae7..d1a68b6d03b3 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -26,7 +26,6 @@ #include <linux/serial_core.h> #include <linux/sysfs.h> #include <linux/random.h> -#include <linux/kmemleak.h> #include <asm/setup.h> /* for COMMAND_LINE_SIZE */ #include <asm/page.h> @@ -525,12 +524,9 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, size = dt_mem_next_cell(dt_root_size_cells, &prop); if (size && - early_init_dt_reserve_memory(base, size, nomap) == 0) { + early_init_dt_reserve_memory(base, size, nomap) == 0) pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); - if (!nomap) - kmemleak_alloc_phys(base, size, 0); - } else pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 81c8c227ab6b..b3878a98d27f 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -525,6 +525,7 @@ static int __init of_platform_default_populate_init(void) if (IS_ENABLED(CONFIG_PPC)) { struct device_node *boot_display = NULL; struct platform_device *dev; + int display_number = 0; int ret; /* Check if we have a MacOS display without a node spec */ @@ -555,16 +556,23 @@ static int __init of_platform_default_populate_init(void) if (!of_get_property(node, "linux,opened", NULL) || !of_get_property(node, "linux,boot-display", NULL)) continue; - dev = of_platform_device_create(node, "of-display", NULL); + dev = of_platform_device_create(node, "of-display.0", NULL); + of_node_put(node); if (WARN_ON(!dev)) return -ENOMEM; boot_display = node; + display_number++; break; } for_each_node_by_type(node, "display") { + char buf[14]; + const char *of_display_format = "of-display.%d"; + if (!of_get_property(node, "linux,opened", NULL) || node == boot_display) continue; - of_platform_device_create(node, "of-display", NULL); + ret = snprintf(buf, sizeof(buf), of_display_format, display_number++); + if (ret < sizeof(buf)) + of_platform_device_create(node, buf, NULL); } } else { diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index d6af5726ddf3..2a18f7ba2398 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -274,8 +274,7 @@ pdcspath_hwpath_write(struct pdcspath_entry *entry, const char *buf, size_t coun /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0xff is a blank pattern */ memset(&hwpath, 0xff, sizeof(hwpath)); @@ -388,8 +387,7 @@ pdcspath_layer_write(struct pdcspath_entry *entry, const char *buf, size_t count /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0 is a blank pattern */ memset(&layers, 0, sizeof(layers)); @@ -756,8 +754,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj, /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Current flags are stored in primary boot path entry */ pathentry = &pdcspath_entry_primary; diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index e991cccdb6e9..1e8bc6cc1e12 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -188,9 +188,10 @@ static int efi_set_time(struct device *dev, struct rtc_time *tm) static int efi_procfs(struct device *dev, struct seq_file *seq) { - efi_time_t eft, alm; - efi_time_cap_t cap; - efi_bool_t enabled, pending; + efi_time_t eft, alm; + efi_time_cap_t cap; + efi_bool_t enabled, pending; + struct rtc_device *rtc = dev_get_drvdata(dev); memset(&eft, 0, sizeof(eft)); memset(&alm, 0, sizeof(alm)); @@ -213,23 +214,25 @@ static int efi_procfs(struct device *dev, struct seq_file *seq) /* XXX fixme: convert to string? */ seq_printf(seq, "Timezone\t: %u\n", eft.timezone); - seq_printf(seq, - "Alarm Time\t: %u:%u:%u.%09u\n" - "Alarm Date\t: %u-%u-%u\n" - "Alarm Daylight\t: %u\n" - "Enabled\t\t: %s\n" - "Pending\t\t: %s\n", - alm.hour, alm.minute, alm.second, alm.nanosecond, - alm.year, alm.month, alm.day, - alm.daylight, - enabled == 1 ? "yes" : "no", - pending == 1 ? "yes" : "no"); - - if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) - seq_puts(seq, "Timezone\t: unspecified\n"); - else - /* XXX fixme: convert to string? */ - seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + if (test_bit(RTC_FEATURE_ALARM, rtc->features)) { + seq_printf(seq, + "Alarm Time\t: %u:%u:%u.%09u\n" + "Alarm Date\t: %u-%u-%u\n" + "Alarm Daylight\t: %u\n" + "Enabled\t\t: %s\n" + "Pending\t\t: %s\n", + alm.hour, alm.minute, alm.second, alm.nanosecond, + alm.year, alm.month, alm.day, + alm.daylight, + enabled == 1 ? "yes" : "no", + pending == 1 ? "yes" : "no"); + + if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) + seq_puts(seq, "Timezone\t: unspecified\n"); + else + /* XXX fixme: convert to string? */ + seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + } /* * now prints the capabilities @@ -269,7 +272,10 @@ static int __init efi_rtc_probe(struct platform_device *dev) rtc->ops = &efi_rtc_ops; clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); - set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES)) + set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + else + clear_bit(RTC_FEATURE_ALARM, rtc->features); device_init_wakeup(&dev->dev, true); diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index e8e2ab1103fc..4b578e4d44f6 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -240,8 +240,8 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (IS_ERR(sp_rtc->reg_base)) return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base), "%s devm_ioremap_resource fail\n", RTC_REG_NAME); - dev_dbg(&plat_dev->dev, "res = 0x%x, reg_base = 0x%lx\n", - sp_rtc->res->start, (unsigned long)sp_rtc->reg_base); + dev_dbg(&plat_dev->dev, "res = %pR, reg_base = %p\n", + sp_rtc->res, sp_rtc->reg_base); sp_rtc->irq = platform_get_irq(plat_dev, 0); if (sp_rtc->irq < 0) diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index dfb84bb03d32..90ec477386a8 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -370,7 +370,7 @@ static void chx_rx(fsm_instance *fi, int event, void *arg) CTCM_FUNTAIL, dev->name, len); priv->stats.rx_dropped++; priv->stats.rx_length_errors++; - goto again; + goto again; } if (len > ch->max_bufsize) { CTCM_DBF_TEXT_(TRACE, CTC_DBF_NOTICE, @@ -378,7 +378,7 @@ static void chx_rx(fsm_instance *fi, int event, void *arg) CTCM_FUNTAIL, dev->name, len, ch->max_bufsize); priv->stats.rx_dropped++; priv->stats.rx_length_errors++; - goto again; + goto again; } /* @@ -403,7 +403,7 @@ static void chx_rx(fsm_instance *fi, int event, void *arg) *((__u16 *)skb->data) = len; priv->stats.rx_dropped++; priv->stats.rx_length_errors++; - goto again; + goto again; } if (block_len > 2) { *((__u16 *)skb->data) = block_len - 2; @@ -1006,7 +1006,7 @@ static void ctcm_chx_txretry(fsm_instance *fi, int event, void *arg) use gptr as mpc indicator */ if (!(gptr && (fsm_getstate(gptr->fsm) != MPCG_STATE_READY))) ctcm_chx_restart(fi, event, arg); - goto done; + goto done; } CTCM_DBF_TEXT_(TRACE, CTC_DBF_DEBUG, @@ -1024,7 +1024,7 @@ static void ctcm_chx_txretry(fsm_instance *fi, int event, void *arg) CTCM_FUNTAIL, ch->id); fsm_event(priv->fsm, DEV_EVENT_TXDOWN, dev); ctcm_chx_restart(fi, event, arg); - goto done; + goto done; } fsm_addtimer(&ch->timer, 1000, CTC_EVENT_TIMER, ch); if (event == CTC_EVENT_TIMER) /* for TIMER not yet locked */ @@ -1251,12 +1251,12 @@ static void ctcmpc_chx_txdone(fsm_instance *fi, int event, void *arg) if ((ch->collect_len <= 0) || (grp->in_sweep != 0)) { spin_unlock(&ch->collect_lock); fsm_newstate(fi, CTC_STATE_TXIDLE); - goto done; + goto done; } if (ctcm_checkalloc_buffer(ch)) { spin_unlock(&ch->collect_lock); - goto done; + goto done; } ch->trans_skb->data = ch->trans_skb_data; skb_reset_tail_pointer(ch->trans_skb); @@ -1389,7 +1389,7 @@ static void ctcmpc_chx_rx(fsm_instance *fi, int event, void *arg) CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR, "%s(%s): TRANS_SKB = NULL", CTCM_FUNTAIL, dev->name); - goto again; + goto again; } if (len < TH_HEADER_LENGTH) { @@ -1409,7 +1409,7 @@ static void ctcmpc_chx_rx(fsm_instance *fi, int event, void *arg) "%s(%s): skb allocation failed", CTCM_FUNTAIL, dev->name); fsm_event(priv->mpcg->fsm, MPCG_EVENT_INOP, dev); - goto again; + goto again; } switch (fsm_getstate(grp->fsm)) { case MPCG_STATE_RESET: @@ -1441,9 +1441,9 @@ again: skb_reset_tail_pointer(ch->trans_skb); ch->trans_skb->len = 0; ch->ccw[1].count = ch->max_bufsize; - if (do_debug_ccw) + if (do_debug_ccw) ctcmpc_dumpit((char *)&ch->ccw[0], - sizeof(struct ccw1) * 3); + sizeof(struct ccw1) * 3); dolock = !in_hardirq(); if (dolock) spin_lock_irqsave( @@ -1562,7 +1562,7 @@ void ctcmpc_chx_rxidle(fsm_instance *fi, int event, void *arg) if (rc != 0) { fsm_newstate(fi, CTC_STATE_RXINIT); ctcm_ccw_check_rc(ch, rc, "initial RX"); - goto done; + goto done; } break; default: @@ -1677,10 +1677,10 @@ static void ctcmpc_chx_attnbusy(fsm_instance *fsm, int event, void *arg) if (fsm_getstate(ch->fsm) == CH_XID0_INPROGRESS) { fsm_newstate(ch->fsm, CH_XID0_PENDING) ; fsm_deltimer(&grp->timer); - goto done; + goto done; } fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; case MPCG_STATE_XID2INITX: /* XID2 was received before ATTN Busy for second channel.Send yside xid for second channel. @@ -1768,7 +1768,7 @@ static void ctcmpc_chx_send_sweep(fsm_instance *fsm, int event, void *arg) /* give the previous IO time to complete */ fsm_addtimer(&wch->sweep_timer, 200, CTC_EVENT_RSWEEP_TIMER, wch); - goto done; + goto done; } skb = skb_dequeue(&wch->sweep_queue); @@ -1780,7 +1780,7 @@ static void ctcmpc_chx_send_sweep(fsm_instance *fsm, int event, void *arg) ctcm_clear_busy_do(dev); dev_kfree_skb_any(skb); fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; } else { refcount_inc(&skb->users); skb_queue_tail(&wch->io_queue, skb); diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index bdfab9ea0046..28db69d91f17 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -494,7 +494,7 @@ static int ctcm_transmit_skb(struct channel *ch, struct sk_buff *skb) ch->collect_len += l; } spin_unlock_irqrestore(&ch->collect_lock, saveflags); - goto done; + goto done; } spin_unlock_irqrestore(&ch->collect_lock, saveflags); /* @@ -685,7 +685,7 @@ static int ctcmpc_transmit_skb(struct channel *ch, struct sk_buff *skb) ch->collect_len += skb->len; spin_unlock_irqrestore(&ch->collect_lock, saveflags); - goto done; + goto done; } /* @@ -885,7 +885,7 @@ static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) "%s(%s): NULL sk_buff passed", CTCM_FUNTAIL, dev->name); priv->stats.tx_dropped++; - goto done; + goto done; } if (skb_headroom(skb) < (TH_HEADER_LENGTH + PDU_HEADER_LENGTH)) { CTCM_DBF_TEXT_(MPC_TRACE, CTC_DBF_ERROR, @@ -908,7 +908,7 @@ static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) priv->stats.tx_errors++; priv->stats.tx_carrier_errors++; fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; } newskb->protocol = skb->protocol; skb_reserve(newskb, TH_HEADER_LENGTH + PDU_HEADER_LENGTH); @@ -931,7 +931,7 @@ static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) priv->stats.tx_dropped++; priv->stats.tx_errors++; priv->stats.tx_carrier_errors++; - goto done; + goto done; } if (ctcm_test_and_set_busy(dev)) { @@ -943,7 +943,7 @@ static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) priv->stats.tx_errors++; priv->stats.tx_carrier_errors++; fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; } netif_trans_update(dev); @@ -957,7 +957,7 @@ static netdev_tx_t ctcmpc_tx(struct sk_buff *skb, struct net_device *dev) priv->stats.tx_carrier_errors++; ctcm_clear_busy(dev); fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; } ctcm_clear_busy(dev); done: @@ -1421,7 +1421,7 @@ static int add_channel(struct ccw_device *cdev, enum ctcm_channel_types type, "%s (%s) already in list, using old entry", __func__, (*c)->id); - goto free_return; + goto free_return; } spin_lock_init(&ch->collect_lock); diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 8ac213a55141..b8a226c6e1a9 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -481,7 +481,7 @@ void ctc_mpc_establish_connectivity(int port_num, grp->estconnfunc = NULL; } fsm_deltimer(&grp->timer); - goto done; + goto done; } if ((wch->in_mpcgroup) && (fsm_getstate(wch->fsm) == CH_XID0_PENDING)) @@ -495,7 +495,7 @@ void ctc_mpc_establish_connectivity(int port_num, grp->estconnfunc = NULL; } fsm_deltimer(&grp->timer); - goto done; + goto done; } break; case MPCG_STATE_XID0IOWAIT: @@ -896,8 +896,9 @@ void mpc_group_ready(unsigned long adev) grp->estconnfunc(grp->port_num, 0, grp->group_max_buflen); grp->estconnfunc = NULL; - } else if (grp->allochanfunc) + } else if (grp->allochanfunc) { grp->allochanfunc(grp->port_num, grp->group_max_buflen); + } grp->send_qllc_disc = 1; grp->changed_side = 0; @@ -1109,7 +1110,7 @@ static void ctcmpc_unpack_skb(struct channel *ch, struct sk_buff *pskb) priv->stats.rx_dropped++; priv->stats.rx_length_errors++; - goto done; + goto done; } skb_reset_mac_header(pskb); new_len = curr_pdu->pdu_offset; @@ -1132,7 +1133,7 @@ static void ctcmpc_unpack_skb(struct channel *ch, struct sk_buff *pskb) CTCM_FUNTAIL, dev->name); priv->stats.rx_dropped++; fsm_event(grp->fsm, MPCG_EVENT_INOP, dev); - goto done; + goto done; } skb_put_data(skb, pskb->data, new_len); @@ -1543,7 +1544,7 @@ static int mpc_validate_xid(struct mpcg_info *mpcginfo) CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR, "%s(%s): xid = NULL", CTCM_FUNTAIL, ch->id); - goto done; + goto done; } CTCM_D3_DUMP((char *)xid, XID2_LENGTH); @@ -1556,7 +1557,7 @@ static int mpc_validate_xid(struct mpcg_info *mpcginfo) CTCM_DBF_TEXT_(MPC_ERROR, CTC_DBF_ERROR, "%s(%s): r/w channel pairing mismatch", CTCM_FUNTAIL, ch->id); - goto done; + goto done; } if (xid->xid2_dlc_type == XID2_READ_SIDE) { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 8bd9fd51208c..1d5b207c2b9e 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -2801,9 +2801,11 @@ static void qeth_print_status_message(struct qeth_card *card) * of the level OSA sets the first character to zero * */ if (!card->info.mcl_level[0]) { - sprintf(card->info.mcl_level, "%02x%02x", - card->info.mcl_level[2], - card->info.mcl_level[3]); + scnprintf(card->info.mcl_level, + sizeof(card->info.mcl_level), + "%02x%02x", + card->info.mcl_level[2], + card->info.mcl_level[3]); break; } fallthrough; @@ -6090,7 +6092,7 @@ void qeth_dbf_longtext(debug_info_t *id, int level, char *fmt, ...) if (!debug_level_enabled(id, level)) return; va_start(args, fmt); - vsnprintf(dbf_txt_buf, sizeof(dbf_txt_buf), fmt, args); + vscnprintf(dbf_txt_buf, sizeof(dbf_txt_buf), fmt, args); va_end(args); debug_text_event(id, level, dbf_txt_buf); } @@ -6330,8 +6332,8 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_dev; } - snprintf(dbf_name, sizeof(dbf_name), "qeth_card_%s", - dev_name(&gdev->dev)); + scnprintf(dbf_name, sizeof(dbf_name), "qeth_card_%s", + dev_name(&gdev->dev)); card->debug = qeth_get_dbf_entry(dbf_name); if (!card->debug) { rc = qeth_add_dbf_entry(card, dbf_name); diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index d1adc4b83193..eea93f8f106f 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -23,15 +23,15 @@ static ssize_t qeth_dev_state_show(struct device *dev, switch (card->state) { case CARD_STATE_DOWN: - return sprintf(buf, "DOWN\n"); + return sysfs_emit(buf, "DOWN\n"); case CARD_STATE_SOFTSETUP: if (card->dev->flags & IFF_UP) - return sprintf(buf, "UP (LAN %s)\n", - netif_carrier_ok(card->dev) ? "ONLINE" : - "OFFLINE"); - return sprintf(buf, "SOFTSETUP\n"); + return sysfs_emit(buf, "UP (LAN %s)\n", + netif_carrier_ok(card->dev) ? + "ONLINE" : "OFFLINE"); + return sysfs_emit(buf, "SOFTSETUP\n"); default: - return sprintf(buf, "UNKNOWN\n"); + return sysfs_emit(buf, "UNKNOWN\n"); } } @@ -42,7 +42,7 @@ static ssize_t qeth_dev_chpid_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%02X\n", card->info.chpid); + return sysfs_emit(buf, "%02X\n", card->info.chpid); } static DEVICE_ATTR(chpid, 0444, qeth_dev_chpid_show, NULL); @@ -52,7 +52,7 @@ static ssize_t qeth_dev_if_name_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", netdev_name(card->dev)); + return sysfs_emit(buf, "%s\n", netdev_name(card->dev)); } static DEVICE_ATTR(if_name, 0444, qeth_dev_if_name_show, NULL); @@ -62,7 +62,7 @@ static ssize_t qeth_dev_card_type_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", qeth_get_cardname_short(card)); + return sysfs_emit(buf, "%s\n", qeth_get_cardname_short(card)); } static DEVICE_ATTR(card_type, 0444, qeth_dev_card_type_show, NULL); @@ -86,7 +86,7 @@ static ssize_t qeth_dev_inbuf_size_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", qeth_get_bufsize_str(card)); + return sysfs_emit(buf, "%s\n", qeth_get_bufsize_str(card)); } static DEVICE_ATTR(inbuf_size, 0444, qeth_dev_inbuf_size_show, NULL); @@ -96,7 +96,7 @@ static ssize_t qeth_dev_portno_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->dev->dev_port); + return sysfs_emit(buf, "%i\n", card->dev->dev_port); } static ssize_t qeth_dev_portno_store(struct device *dev, @@ -134,7 +134,7 @@ static DEVICE_ATTR(portno, 0644, qeth_dev_portno_show, qeth_dev_portno_store); static ssize_t qeth_dev_portname_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "no portname required\n"); + return sysfs_emit(buf, "no portname required\n"); } static ssize_t qeth_dev_portname_store(struct device *dev, @@ -157,18 +157,18 @@ static ssize_t qeth_dev_prioqing_show(struct device *dev, switch (card->qdio.do_prio_queueing) { case QETH_PRIO_Q_ING_PREC: - return sprintf(buf, "%s\n", "by precedence"); + return sysfs_emit(buf, "%s\n", "by precedence"); case QETH_PRIO_Q_ING_TOS: - return sprintf(buf, "%s\n", "by type of service"); + return sysfs_emit(buf, "%s\n", "by type of service"); case QETH_PRIO_Q_ING_SKB: - return sprintf(buf, "%s\n", "by skb-priority"); + return sysfs_emit(buf, "%s\n", "by skb-priority"); case QETH_PRIO_Q_ING_VLAN: - return sprintf(buf, "%s\n", "by VLAN headers"); + return sysfs_emit(buf, "%s\n", "by VLAN headers"); case QETH_PRIO_Q_ING_FIXED: - return sprintf(buf, "always queue %i\n", + return sysfs_emit(buf, "always queue %i\n", card->qdio.default_out_queue); default: - return sprintf(buf, "disabled\n"); + return sysfs_emit(buf, "disabled\n"); } } @@ -242,7 +242,7 @@ static ssize_t qeth_dev_bufcnt_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->qdio.in_buf_pool.buf_count); + return sysfs_emit(buf, "%i\n", card->qdio.in_buf_pool.buf_count); } static ssize_t qeth_dev_bufcnt_store(struct device *dev, @@ -298,7 +298,7 @@ static DEVICE_ATTR(recover, 0200, NULL, qeth_dev_recover_store); static ssize_t qeth_dev_performance_stats_show(struct device *dev, struct device_attribute *attr, char *buf) { - return sprintf(buf, "1\n"); + return sysfs_emit(buf, "1\n"); } static ssize_t qeth_dev_performance_stats_store(struct device *dev, @@ -335,7 +335,7 @@ static ssize_t qeth_dev_layer2_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->options.layer); + return sysfs_emit(buf, "%i\n", card->options.layer); } static ssize_t qeth_dev_layer2_store(struct device *dev, @@ -470,23 +470,25 @@ static ssize_t qeth_dev_switch_attrs_show(struct device *dev, int rc = 0; if (!qeth_card_hw_is_reachable(card)) - return sprintf(buf, "n/a\n"); + return sysfs_emit(buf, "n/a\n"); rc = qeth_query_switch_attributes(card, &sw_info); if (rc) return rc; if (!sw_info.capabilities) - rc = sprintf(buf, "unknown"); + rc = sysfs_emit(buf, "unknown"); if (sw_info.capabilities & QETH_SWITCH_FORW_802_1) - rc = sprintf(buf, (sw_info.settings & QETH_SWITCH_FORW_802_1 ? - "[802.1]" : "802.1")); + rc = sysfs_emit(buf, + (sw_info.settings & QETH_SWITCH_FORW_802_1 ? + "[802.1]" : "802.1")); if (sw_info.capabilities & QETH_SWITCH_FORW_REFL_RELAY) - rc += sprintf(buf + rc, - (sw_info.settings & QETH_SWITCH_FORW_REFL_RELAY ? - " [rr]" : " rr")); - rc += sprintf(buf + rc, "\n"); + rc += sysfs_emit_at(buf, rc, + (sw_info.settings & + QETH_SWITCH_FORW_REFL_RELAY ? + " [rr]" : " rr")); + rc += sysfs_emit_at(buf, rc, "\n"); return rc; } @@ -573,7 +575,7 @@ static ssize_t qeth_dev_blkt_total_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->info.blkt.time_total); + return sysfs_emit(buf, "%i\n", card->info.blkt.time_total); } static ssize_t qeth_dev_blkt_total_store(struct device *dev, @@ -593,7 +595,7 @@ static ssize_t qeth_dev_blkt_inter_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->info.blkt.inter_packet); + return sysfs_emit(buf, "%i\n", card->info.blkt.inter_packet); } static ssize_t qeth_dev_blkt_inter_store(struct device *dev, @@ -613,7 +615,7 @@ static ssize_t qeth_dev_blkt_inter_jumbo_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->info.blkt.inter_packet_jumbo); + return sysfs_emit(buf, "%i\n", card->info.blkt.inter_packet_jumbo); } static ssize_t qeth_dev_blkt_inter_jumbo_store(struct device *dev, diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index e250f49535fa..c1caf7734c3e 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -172,7 +172,7 @@ static void qeth_get_strings(struct net_device *dev, u32 stringset, u8 *data) qeth_add_stat_strings(&data, prefix, card_stats, CARD_STATS_LEN); for (i = 0; i < card->qdio.no_out_queues; i++) { - snprintf(prefix, ETH_GSTRING_LEN, "tx%u ", i); + scnprintf(prefix, ETH_GSTRING_LEN, "tx%u ", i); qeth_add_stat_strings(&data, prefix, txq_stats, TXQ_STATS_LEN); } @@ -192,8 +192,8 @@ static void qeth_get_drvinfo(struct net_device *dev, sizeof(info->driver)); strscpy(info->fw_version, card->info.mcl_level, sizeof(info->fw_version)); - snprintf(info->bus_info, sizeof(info->bus_info), "%s/%s/%s", - CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); + scnprintf(info->bus_info, sizeof(info->bus_info), "%s/%s/%s", + CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); } static void qeth_get_channels(struct net_device *dev, diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index c6ded3fdd715..9f13ed170a43 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1255,37 +1255,38 @@ static void qeth_bridge_emit_host_event(struct qeth_card *card, switch (evtype) { case anev_reg_unreg: - snprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=%s", - (code & IPA_ADDR_CHANGE_CODE_REMOVAL) - ? "deregister" : "register"); + scnprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=%s", + (code & IPA_ADDR_CHANGE_CODE_REMOVAL) + ? "deregister" : "register"); env[i] = str[i]; i++; if (code & IPA_ADDR_CHANGE_CODE_VLANID) { - snprintf(str[i], sizeof(str[i]), "VLAN=%d", - addr_lnid->lnid); + scnprintf(str[i], sizeof(str[i]), "VLAN=%d", + addr_lnid->lnid); env[i] = str[i]; i++; } if (code & IPA_ADDR_CHANGE_CODE_MACADDR) { - snprintf(str[i], sizeof(str[i]), "MAC=%pM", - addr_lnid->mac); + scnprintf(str[i], sizeof(str[i]), "MAC=%pM", + addr_lnid->mac); env[i] = str[i]; i++; } - snprintf(str[i], sizeof(str[i]), "NTOK_BUSID=%x.%x.%04x", - token->cssid, token->ssid, token->devnum); + scnprintf(str[i], sizeof(str[i]), "NTOK_BUSID=%x.%x.%04x", + token->cssid, token->ssid, token->devnum); env[i] = str[i]; i++; - snprintf(str[i], sizeof(str[i]), "NTOK_IID=%02x", token->iid); + scnprintf(str[i], sizeof(str[i]), "NTOK_IID=%02x", token->iid); env[i] = str[i]; i++; - snprintf(str[i], sizeof(str[i]), "NTOK_CHPID=%02x", - token->chpid); + scnprintf(str[i], sizeof(str[i]), "NTOK_CHPID=%02x", + token->chpid); env[i] = str[i]; i++; - snprintf(str[i], sizeof(str[i]), "NTOK_CHID=%04x", token->chid); + scnprintf(str[i], sizeof(str[i]), "NTOK_CHID=%04x", + token->chid); env[i] = str[i]; i++; break; case anev_abort: - snprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=abort"); + scnprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=abort"); env[i] = str[i]; i++; break; case anev_reset: - snprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=reset"); + scnprintf(str[i], sizeof(str[i]), "BRIDGEDHOST=reset"); env[i] = str[i]; i++; break; } @@ -1314,17 +1315,17 @@ static void qeth_bridge_state_change_worker(struct work_struct *work) NULL }; - snprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); - snprintf(env_role, sizeof(env_role), "ROLE=%s", - (data->role == QETH_SBP_ROLE_NONE) ? "none" : - (data->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : - (data->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : - "<INVALID>"); - snprintf(env_state, sizeof(env_state), "STATE=%s", - (data->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : - (data->state == QETH_SBP_STATE_STANDBY) ? "standby" : - (data->state == QETH_SBP_STATE_ACTIVE) ? "active" : - "<INVALID>"); + scnprintf(env_locrem, sizeof(env_locrem), "BRIDGEPORT=statechange"); + scnprintf(env_role, sizeof(env_role), "ROLE=%s", + (data->role == QETH_SBP_ROLE_NONE) ? "none" : + (data->role == QETH_SBP_ROLE_PRIMARY) ? "primary" : + (data->role == QETH_SBP_ROLE_SECONDARY) ? "secondary" : + "<INVALID>"); + scnprintf(env_state, sizeof(env_state), "STATE=%s", + (data->state == QETH_SBP_STATE_INACTIVE) ? "inactive" : + (data->state == QETH_SBP_STATE_STANDBY) ? "standby" : + (data->state == QETH_SBP_STATE_ACTIVE) ? "active" : + "<INVALID>"); kobject_uevent_env(&data->card->gdev->dev.kobj, KOBJ_CHANGE, env); kfree(data); diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index a617351fff57..7f592f912517 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -19,7 +19,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, char *word; if (!qeth_bridgeport_allowed(card)) - return sprintf(buf, "n/a (VNIC characteristics)\n"); + return sysfs_emit(buf, "n/a (VNIC characteristics)\n"); mutex_lock(&card->sbp_lock); if (qeth_card_hw_is_reachable(card) && @@ -53,7 +53,7 @@ static ssize_t qeth_bridge_port_role_state_show(struct device *dev, QETH_CARD_TEXT_(card, 2, "SBP%02x:%02x", card->options.sbp.role, state); else - rc = sprintf(buf, "%s\n", word); + rc = sysfs_emit(buf, "%s\n", word); } mutex_unlock(&card->sbp_lock); @@ -66,7 +66,7 @@ static ssize_t qeth_bridge_port_role_show(struct device *dev, struct qeth_card *card = dev_get_drvdata(dev); if (!qeth_bridgeport_allowed(card)) - return sprintf(buf, "n/a (VNIC characteristics)\n"); + return sysfs_emit(buf, "n/a (VNIC characteristics)\n"); return qeth_bridge_port_role_state_show(dev, attr, buf, 0); } @@ -117,7 +117,7 @@ static ssize_t qeth_bridge_port_state_show(struct device *dev, struct qeth_card *card = dev_get_drvdata(dev); if (!qeth_bridgeport_allowed(card)) - return sprintf(buf, "n/a (VNIC characteristics)\n"); + return sysfs_emit(buf, "n/a (VNIC characteristics)\n"); return qeth_bridge_port_role_state_show(dev, attr, buf, 1); } @@ -132,11 +132,11 @@ static ssize_t qeth_bridgeport_hostnotification_show(struct device *dev, int enabled; if (!qeth_bridgeport_allowed(card)) - return sprintf(buf, "n/a (VNIC characteristics)\n"); + return sysfs_emit(buf, "n/a (VNIC characteristics)\n"); enabled = card->options.sbp.hostnotification; - return sprintf(buf, "%d\n", enabled); + return sysfs_emit(buf, "%d\n", enabled); } static ssize_t qeth_bridgeport_hostnotification_store(struct device *dev, @@ -180,7 +180,7 @@ static ssize_t qeth_bridgeport_reflect_show(struct device *dev, char *state; if (!qeth_bridgeport_allowed(card)) - return sprintf(buf, "n/a (VNIC characteristics)\n"); + return sysfs_emit(buf, "n/a (VNIC characteristics)\n"); if (card->options.sbp.reflect_promisc) { if (card->options.sbp.reflect_promisc_primary) @@ -190,7 +190,7 @@ static ssize_t qeth_bridgeport_reflect_show(struct device *dev, } else state = "none"; - return sprintf(buf, "%s\n", state); + return sysfs_emit(buf, "%s\n", state); } static ssize_t qeth_bridgeport_reflect_store(struct device *dev, @@ -280,10 +280,10 @@ static ssize_t qeth_vnicc_timeout_show(struct device *dev, rc = qeth_l2_vnicc_get_timeout(card, &timeout); if (rc == -EBUSY) - return sprintf(buf, "n/a (BridgePort)\n"); + return sysfs_emit(buf, "n/a (BridgePort)\n"); if (rc == -EOPNOTSUPP) - return sprintf(buf, "n/a\n"); - return rc ? rc : sprintf(buf, "%d\n", timeout); + return sysfs_emit(buf, "n/a\n"); + return rc ? rc : sysfs_emit(buf, "%d\n", timeout); } /* change timeout setting */ @@ -318,10 +318,10 @@ static ssize_t qeth_vnicc_char_show(struct device *dev, rc = qeth_l2_vnicc_get_state(card, vnicc, &state); if (rc == -EBUSY) - return sprintf(buf, "n/a (BridgePort)\n"); + return sysfs_emit(buf, "n/a (BridgePort)\n"); if (rc == -EOPNOTSUPP) - return sprintf(buf, "n/a\n"); - return rc ? rc : sprintf(buf, "%d\n", state); + return sysfs_emit(buf, "n/a\n"); + return rc ? rc : sysfs_emit(buf, "%d\n", state); } /* change setting of characteristic */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index d8487a10cd55..af4e60d2917e 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -19,6 +19,7 @@ #include <linux/etherdevice.h> #include <linux/ip.h> #include <linux/in.h> +#include <linux/inet.h> #include <linux/ipv6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> @@ -46,9 +47,9 @@ int qeth_l3_ipaddr_to_string(enum qeth_prot_versions proto, const u8 *addr, char *buf) { if (proto == QETH_PROT_IPV4) - return sprintf(buf, "%pI4", addr); + return scnprintf(buf, INET_ADDRSTRLEN, "%pI4", addr); else - return sprintf(buf, "%pI6", addr); + return scnprintf(buf, INET6_ADDRSTRLEN, "%pI6", addr); } static struct qeth_ipaddr *qeth_l3_find_addr_by_ip(struct qeth_card *card, @@ -158,7 +159,7 @@ static int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) { int rc = 0; struct qeth_ipaddr *addr; - char buf[40]; + char buf[INET6_ADDRSTRLEN]; if (tmp_addr->type == QETH_IP_TYPE_RXIP) QETH_CARD_TEXT(card, 2, "addrxip"); diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c index 1082380b21f8..9f90a860ca2c 100644 --- a/drivers/s390/net/qeth_l3_sys.c +++ b/drivers/s390/net/qeth_l3_sys.c @@ -32,26 +32,26 @@ static ssize_t qeth_l3_dev_route_show(struct qeth_card *card, { switch (route->type) { case PRIMARY_ROUTER: - return sprintf(buf, "%s\n", "primary router"); + return sysfs_emit(buf, "%s\n", "primary router"); case SECONDARY_ROUTER: - return sprintf(buf, "%s\n", "secondary router"); + return sysfs_emit(buf, "%s\n", "secondary router"); case MULTICAST_ROUTER: if (card->info.broadcast_capable == QETH_BROADCAST_WITHOUT_ECHO) - return sprintf(buf, "%s\n", "multicast router+"); + return sysfs_emit(buf, "%s\n", "multicast router+"); else - return sprintf(buf, "%s\n", "multicast router"); + return sysfs_emit(buf, "%s\n", "multicast router"); case PRIMARY_CONNECTOR: if (card->info.broadcast_capable == QETH_BROADCAST_WITHOUT_ECHO) - return sprintf(buf, "%s\n", "primary connector+"); + return sysfs_emit(buf, "%s\n", "primary connector+"); else - return sprintf(buf, "%s\n", "primary connector"); + return sysfs_emit(buf, "%s\n", "primary connector"); case SECONDARY_CONNECTOR: if (card->info.broadcast_capable == QETH_BROADCAST_WITHOUT_ECHO) - return sprintf(buf, "%s\n", "secondary connector+"); + return sysfs_emit(buf, "%s\n", "secondary connector+"); else - return sprintf(buf, "%s\n", "secondary connector"); + return sysfs_emit(buf, "%s\n", "secondary connector"); default: - return sprintf(buf, "%s\n", "no"); + return sysfs_emit(buf, "%s\n", "no"); } } @@ -138,7 +138,7 @@ static ssize_t qeth_l3_dev_sniffer_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%i\n", card->options.sniffer ? 1 : 0); + return sysfs_emit(buf, "%i\n", card->options.sniffer ? 1 : 0); } static ssize_t qeth_l3_dev_sniffer_store(struct device *dev, @@ -200,7 +200,7 @@ static ssize_t qeth_l3_dev_hsuid_show(struct device *dev, memcpy(tmp_hsuid, card->options.hsuid, sizeof(tmp_hsuid)); EBCASC(tmp_hsuid, 8); - return sprintf(buf, "%s\n", tmp_hsuid); + return sysfs_emit(buf, "%s\n", tmp_hsuid); } static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, @@ -252,8 +252,8 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev, goto out; } - snprintf(card->options.hsuid, sizeof(card->options.hsuid), - "%-8s", tmp); + scnprintf(card->options.hsuid, sizeof(card->options.hsuid), + "%-8s", tmp); ASCEBC(card->options.hsuid, 8); memcpy(card->dev->perm_addr, card->options.hsuid, 9); @@ -285,7 +285,7 @@ static ssize_t qeth_l3_dev_ipato_enable_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%u\n", card->ipato.enabled ? 1 : 0); + return sysfs_emit(buf, "%u\n", card->ipato.enabled ? 1 : 0); } static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev, @@ -330,7 +330,7 @@ static ssize_t qeth_l3_dev_ipato_invert4_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%u\n", card->ipato.invert4 ? 1 : 0); + return sysfs_emit(buf, "%u\n", card->ipato.invert4 ? 1 : 0); } static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev, @@ -367,35 +367,21 @@ static ssize_t qeth_l3_dev_ipato_add_show(char *buf, struct qeth_card *card, enum qeth_prot_versions proto) { struct qeth_ipato_entry *ipatoe; - int str_len = 0; + char addr_str[INET6_ADDRSTRLEN]; + int offset = 0; mutex_lock(&card->ip_lock); list_for_each_entry(ipatoe, &card->ipato.entries, entry) { - char addr_str[40]; - int entry_len; - if (ipatoe->proto != proto) continue; - entry_len = qeth_l3_ipaddr_to_string(proto, ipatoe->addr, - addr_str); - if (entry_len < 0) - continue; - - /* Append /%mask to the entry: */ - entry_len += 1 + ((proto == QETH_PROT_IPV4) ? 2 : 3); - /* Enough room to format %entry\n into null terminated page? */ - if (entry_len + 1 > PAGE_SIZE - str_len - 1) - break; - - entry_len = scnprintf(buf, PAGE_SIZE - str_len, - "%s/%i\n", addr_str, ipatoe->mask_bits); - str_len += entry_len; - buf += entry_len; + qeth_l3_ipaddr_to_string(proto, ipatoe->addr, addr_str); + offset += sysfs_emit_at(buf, offset, "%s/%i\n", + addr_str, ipatoe->mask_bits); } mutex_unlock(&card->ip_lock); - return str_len ? str_len : scnprintf(buf, PAGE_SIZE, "\n"); + return offset ? offset : sysfs_emit(buf, "\n"); } static ssize_t qeth_l3_dev_ipato_add4_show(struct device *dev, @@ -413,7 +399,7 @@ static int qeth_l3_parse_ipatoe(const char *buf, enum qeth_prot_versions proto, int rc; /* Expected input pattern: %addr/%mask */ - sep = strnchr(buf, 40, '/'); + sep = strnchr(buf, INET6_ADDRSTRLEN, '/'); if (!sep) return -EINVAL; @@ -501,7 +487,7 @@ static ssize_t qeth_l3_dev_ipato_invert6_show(struct device *dev, { struct qeth_card *card = dev_get_drvdata(dev); - return sprintf(buf, "%u\n", card->ipato.invert6 ? 1 : 0); + return sysfs_emit(buf, "%u\n", card->ipato.invert6 ? 1 : 0); } static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev, @@ -586,35 +572,22 @@ static ssize_t qeth_l3_dev_ip_add_show(struct device *dev, char *buf, enum qeth_ip_types type) { struct qeth_card *card = dev_get_drvdata(dev); + char addr_str[INET6_ADDRSTRLEN]; struct qeth_ipaddr *ipaddr; - int str_len = 0; + int offset = 0; int i; mutex_lock(&card->ip_lock); hash_for_each(card->ip_htable, i, ipaddr, hnode) { - char addr_str[40]; - int entry_len; - if (ipaddr->proto != proto || ipaddr->type != type) continue; - entry_len = qeth_l3_ipaddr_to_string(proto, (u8 *)&ipaddr->u, - addr_str); - if (entry_len < 0) - continue; - - /* Enough room to format %addr\n into null terminated page? */ - if (entry_len + 1 > PAGE_SIZE - str_len - 1) - break; - - entry_len = scnprintf(buf, PAGE_SIZE - str_len, "%s\n", - addr_str); - str_len += entry_len; - buf += entry_len; + qeth_l3_ipaddr_to_string(proto, (u8 *)&ipaddr->u, addr_str); + offset += sysfs_emit_at(buf, offset, "%s\n", addr_str); } mutex_unlock(&card->ip_lock); - return str_len ? str_len : scnprintf(buf, PAGE_SIZE, "\n"); + return offset ? offset : sysfs_emit(buf, "\n"); } static ssize_t qeth_l3_dev_vipa_add4_show(struct device *dev, diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 37d6af2ec427..7fa66501792d 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -43,15 +43,23 @@ static void __dma_rx_complete(struct uart_8250_port *p) struct uart_8250_dma *dma = p->dma; struct tty_port *tty_port = &p->port.state->port; struct dma_tx_state state; + enum dma_status dma_status; int count; - dma->rx_running = 0; - dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + /* + * New DMA Rx can be started during the completion handler before it + * could acquire port's lock and it might still be ongoing. Don't to + * anything in such case. + */ + dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + if (dma_status == DMA_IN_PROGRESS) + return; count = dma->rx_size - state.residue; tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += count; + dma->rx_running = 0; tty_flip_buffer_push(tty_port); } @@ -62,9 +70,14 @@ static void dma_rx_complete(void *param) struct uart_8250_dma *dma = p->dma; unsigned long flags; - __dma_rx_complete(p); - spin_lock_irqsave(&p->port.lock, flags); + if (dma->rx_running) + __dma_rx_complete(p); + + /* + * Cannot be combined with the previous check because __dma_rx_complete() + * changes dma->rx_running. + */ if (!dma->rx_running && (serial_lsr_in(p) & UART_LSR_DR)) p->dma->rx_dma(p); spin_unlock_irqrestore(&p->port.lock, flags); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index a1490033aa16..409e91d6829a 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -797,25 +797,11 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) spin_unlock(&port->lock); } - if (stm32_usart_rx_dma_enabled(port)) - return IRQ_WAKE_THREAD; - else - return IRQ_HANDLED; -} - -static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr) -{ - struct uart_port *port = ptr; - struct tty_port *tport = &port->state->port; - struct stm32_port *stm32_port = to_stm32_port(port); - unsigned int size; - unsigned long flags; - /* Receiver timeout irq for DMA RX */ - if (!stm32_port->throttled) { - spin_lock_irqsave(&port->lock, flags); + if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) { + spin_lock(&port->lock); size = stm32_usart_receive_chars(port, false); - uart_unlock_and_check_sysrq_irqrestore(port, flags); + uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); } @@ -1015,10 +1001,8 @@ static int stm32_usart_startup(struct uart_port *port) u32 val; int ret; - ret = request_threaded_irq(port->irq, stm32_usart_interrupt, - stm32_usart_threaded_interrupt, - IRQF_ONESHOT | IRQF_NO_SUSPEND, - name, port); + ret = request_irq(port->irq, stm32_usart_interrupt, + IRQF_NO_SUSPEND, name, port); if (ret) return ret; @@ -1601,13 +1585,6 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port, struct dma_slave_config config; int ret; - /* - * Using DMA and threaded handler for the console could lead to - * deadlocks. - */ - if (uart_console(port)) - return -ENODEV; - stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L, &stm32port->rx_dma_buf, GFP_KERNEL); diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1850bacdb5b0..f566eb1839dc 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -386,10 +386,6 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) uni_mode = use_unicode(inode); attr = use_attributes(inode); - ret = -ENXIO; - vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; ret = -EINVAL; if (pos < 0) @@ -407,6 +403,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned int this_round, skip = 0; int size; + ret = -ENXIO; + vc = vcs_vc(inode, &viewed); + if (!vc) + goto unlock_out; + /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index b0a0351d2d8b..959fc925ca7c 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -901,7 +901,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev); /* enable vbus override for device mode */ - if (qcom->mode == USB_DR_MODE_PERIPHERAL) + if (qcom->mode != USB_DR_MODE_HOST) dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c index 87cca81bf4ac..eb076746f032 100644 --- a/drivers/usb/fotg210/fotg210-udc.c +++ b/drivers/usb/fotg210/fotg210-udc.c @@ -1014,7 +1014,6 @@ static int fotg210_udc_start(struct usb_gadget *g, int ret; /* hook up the driver */ - driver->driver.bus = NULL; fotg210->driver = driver; if (!IS_ERR_OR_NULL(fotg210->phy)) { diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 523a961b910b..8ad354741380 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -279,8 +279,10 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; - if (!req) + if (!req) { + spin_unlock_irq(&ffs->ev.waitq.lock); return -EINVAL; + } req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 08726e4c68a5..0219cd79493a 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1142,6 +1142,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) } std_as_out_if0_desc.bInterfaceNumber = ret; std_as_out_if1_desc.bInterfaceNumber = ret; + std_as_out_if1_desc.bNumEndpoints = 1; uac2->as_out_intf = ret; uac2->as_out_alt = 0; diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c index 2cdb07905bde..d04d72f5816e 100644 --- a/drivers/usb/gadget/udc/bcm63xx_udc.c +++ b/drivers/usb/gadget/udc/bcm63xx_udc.c @@ -1830,7 +1830,6 @@ static int bcm63xx_udc_start(struct usb_gadget *gadget, bcm63xx_select_phy_mode(udc, true); udc->driver = driver; - driver->driver.bus = NULL; udc->gadget.dev.of_node = udc->dev->of_node; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index bf745358e28e..3b1cc8fa30c8 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2285,7 +2285,6 @@ static int fsl_qe_start(struct usb_gadget *gadget, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc->driver = driver; udc->gadget.speed = driver->max_speed; diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 50435e804118..a67873a074b7 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1943,7 +1943,6 @@ static int fsl_udc_start(struct usb_gadget *g, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc_controller->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc_controller->driver = driver; spin_unlock_irqrestore(&udc_controller->lock, flags); diff --git a/drivers/usb/gadget/udc/fusb300_udc.c b/drivers/usb/gadget/udc/fusb300_udc.c index 9af8b415f303..5954800d652c 100644 --- a/drivers/usb/gadget/udc/fusb300_udc.c +++ b/drivers/usb/gadget/udc/fusb300_udc.c @@ -1311,7 +1311,6 @@ static int fusb300_udc_start(struct usb_gadget *g, struct fusb300 *fusb300 = to_fusb300(g); /* hook up the driver */ - driver->driver.bus = NULL; fusb300->driver = driver; return 0; diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c index bdc56b24b5c9..5ffb3d5c635b 100644 --- a/drivers/usb/gadget/udc/goku_udc.c +++ b/drivers/usb/gadget/udc/goku_udc.c @@ -1375,7 +1375,6 @@ static int goku_udc_start(struct usb_gadget *g, struct goku_udc *dev = to_goku_udc(g); /* hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index 22096f8505de..85cdc0af3bf9 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1906,7 +1906,6 @@ static int gr_udc_start(struct usb_gadget *gadget, spin_lock(&dev->lock); /* Hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* Get ready for host detection */ diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c index c7e421b449f3..06e21cee431b 100644 --- a/drivers/usb/gadget/udc/m66592-udc.c +++ b/drivers/usb/gadget/udc/m66592-udc.c @@ -1454,7 +1454,6 @@ static int m66592_udc_start(struct usb_gadget *g, struct m66592 *m66592 = to_m66592(g); /* hook up the driver */ - driver->driver.bus = NULL; m66592->driver = driver; m66592_bset(m66592, M66592_VBSE | M66592_URST, M66592_INTENB0); diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c index 3074da00c3df..ddf0ed3eb4f2 100644 --- a/drivers/usb/gadget/udc/max3420_udc.c +++ b/drivers/usb/gadget/udc/max3420_udc.c @@ -1108,7 +1108,6 @@ static int max3420_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; udc->gadget.speed = USB_SPEED_FULL; diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c index 598654a3cb41..411b6179782c 100644 --- a/drivers/usb/gadget/udc/mv_u3d_core.c +++ b/drivers/usb/gadget/udc/mv_u3d_core.c @@ -1243,7 +1243,6 @@ static int mv_u3d_start(struct usb_gadget *g, } /* hook up the driver ... */ - driver->driver.bus = NULL; u3d->driver = driver; u3d->ep0_dir = USB_DIR_OUT; diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index fdb17d86cd65..b397f3a848cf 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -1359,7 +1359,6 @@ static int mv_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver ... */ - driver->driver.bus = NULL; udc->driver = driver; udc->usb_state = USB_STATE_ATTACHED; diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 84605a4d0715..538c1b9a2883 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -1451,7 +1451,6 @@ static int net2272_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ dev->softconnect = 1; - driver->driver.bus = NULL; dev->driver = driver; /* ... then enable host detection and ep0; and we're ready diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index d6a68631354a..1b929c519cd7 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -2423,7 +2423,6 @@ static int net2280_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ - driver->driver.bus = NULL; dev->driver = driver; retval = device_create_file(&dev->pdev->dev, &dev_attr_function); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index bea346e362b2..f660ebfa1379 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2066,7 +2066,6 @@ static int omap_udc_start(struct usb_gadget *g, udc->softconnect = 1; /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c index 9bb7a9d7a2fb..4f8617210d85 100644 --- a/drivers/usb/gadget/udc/pch_udc.c +++ b/drivers/usb/gadget/udc/pch_udc.c @@ -2908,7 +2908,6 @@ static int pch_udc_start(struct usb_gadget *g, { struct pch_udc_dev *dev = to_pch_udc(g); - driver->driver.bus = NULL; dev->driver = driver; /* get ready for ep0 traffic */ diff --git a/drivers/usb/gadget/udc/snps_udc_core.c b/drivers/usb/gadget/udc/snps_udc_core.c index 52ea4dcf6a92..2fc5d4d277bc 100644 --- a/drivers/usb/gadget/udc/snps_udc_core.c +++ b/drivers/usb/gadget/udc/snps_udc_core.c @@ -1933,7 +1933,6 @@ static int amd5536_udc_start(struct usb_gadget *g, struct udc *dev = to_amd5536_udc(g); u32 tmp; - driver->driver.bus = NULL; dev->driver = driver; /* Some gadget drivers use both ep0 directions. diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index 1292241d581a..1cf8947c6d66 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1269,6 +1269,9 @@ err_unregister: con->port = NULL; } + kfree(ucsi->connector); + ucsi->connector = NULL; + err_reset: memset(&ucsi->cap, 0, sizeof(ucsi->cap)); ucsi_reset_ppm(ucsi); @@ -1300,7 +1303,8 @@ static void ucsi_resume_work(struct work_struct *work) int ucsi_resume(struct ucsi *ucsi) { - queue_work(system_long_wq, &ucsi->resume_work); + if (ucsi->connector) + queue_work(system_long_wq, &ucsi->resume_work); return 0; } EXPORT_SYMBOL_GPL(ucsi_resume); @@ -1420,6 +1424,9 @@ void ucsi_unregister(struct ucsi *ucsi) /* Disable notifications */ ucsi->ops->async_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd)); + if (!ucsi->connector) + return; + for (i = 0; i < ucsi->cap.num_connectors; i++) { cancel_work_sync(&ucsi->connector[i].work); ucsi_unregister_partner(&ucsi->connector[i]); diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 1fc8de4ecbeb..8187a7c4f910 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -49,7 +49,6 @@ struct atmel_lcdfb_info { struct clk *lcdc_clk; struct backlight_device *backlight; - u8 bl_power; u8 saved_lcdcon; u32 pseudo_palette[16]; @@ -109,22 +108,7 @@ static u32 contrast_ctr = ATMEL_LCDC_PS_DIV8 static int atmel_bl_update_status(struct backlight_device *bl) { struct atmel_lcdfb_info *sinfo = bl_get_data(bl); - int power = sinfo->bl_power; - int brightness = bl->props.brightness; - - /* REVISIT there may be a meaningful difference between - * fb_blank and power ... there seem to be some cases - * this doesn't handle correctly. - */ - if (bl->props.fb_blank != sinfo->bl_power) - power = bl->props.fb_blank; - else if (bl->props.power != sinfo->bl_power) - power = bl->props.power; - - if (brightness < 0 && power == FB_BLANK_UNBLANK) - brightness = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_VAL); - else if (power != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_VAL, brightness); if (contrast_ctr & ATMEL_LCDC_POL_POSITIVE) @@ -133,8 +117,6 @@ static int atmel_bl_update_status(struct backlight_device *bl) else lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, contrast_ctr); - bl->props.fb_blank = bl->props.power = sinfo->bl_power = power; - return 0; } @@ -155,8 +137,6 @@ static void init_backlight(struct atmel_lcdfb_info *sinfo) struct backlight_properties props; struct backlight_device *bl; - sinfo->bl_power = FB_BLANK_UNBLANK; - if (sinfo->backlight) return; diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index dd31b9d7d337..36a9ac05a340 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -1766,12 +1766,10 @@ static int aty128_bl_update_status(struct backlight_device *bd) unsigned int reg = aty_ld_le32(LVDS_GEN_CNTL); int level; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK || - !par->lcd_on) + if (!par->lcd_on) level = 0; else - level = bd->props.brightness; + level = backlight_get_brightness(bd); reg |= LVDS_BL_MOD_EN | LVDS_BLON; if (level > 0) { diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index d59215a4992e..b02e4e645035 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -2219,13 +2219,7 @@ static int aty_bl_update_status(struct backlight_device *bd) { struct atyfb_par *par = bl_get_data(bd); unsigned int reg = aty_ld_lcd(LCD_MISC_CNTL, par); - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); reg |= (BLMOD_EN | BIASMOD_EN); if (level > 0) { diff --git a/drivers/video/fbdev/aty/radeon_backlight.c b/drivers/video/fbdev/aty/radeon_backlight.c index d2c1263ad260..427adc838f77 100644 --- a/drivers/video/fbdev/aty/radeon_backlight.c +++ b/drivers/video/fbdev/aty/radeon_backlight.c @@ -57,11 +57,7 @@ static int radeon_bl_update_status(struct backlight_device *bd) * backlight. This provides some greater power saving and the display * is useless without backlight anyway. */ - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + level = backlight_get_brightness(bd); del_timer_sync(&rinfo->lvds_timer); radeon_engine_idle(); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 14a7d404062c..1b14c21af2b7 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2495,9 +2495,12 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; + if (font->width > 32 || font->height > 32) + return -EINVAL; + /* Make sure drawing engine can handle the font */ - if (!(info->pixmap.blit_x & (1 << (font->width - 1))) || - !(info->pixmap.blit_y & (1 << (font->height - 1)))) + if (!(info->pixmap.blit_x & BIT(font->width - 1)) || + !(info->pixmap.blit_y & BIT(font->height - 1))) return -EINVAL; /* Make sure driver can handle the font length */ diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index b0e690f41025..79e5bfbdd34c 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1050,7 +1050,7 @@ static u32 fb_get_vblank(u32 hfreq) } /** - * fb_get_hblank_by_freq - get horizontal blank time given hfreq + * fb_get_hblank_by_hfreq - get horizontal blank time given hfreq * @hfreq: horizontal freq * @xres: horizontal resolution in pixels * diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c index b945b68984b9..76771e126d0a 100644 --- a/drivers/video/fbdev/mx3fb.c +++ b/drivers/video/fbdev/mx3fb.c @@ -283,12 +283,7 @@ static int mx3fb_bl_get_brightness(struct backlight_device *bl) static int mx3fb_bl_update_status(struct backlight_device *bl) { struct mx3fb_data *fbd = bl_get_data(bl); - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); fbd->backlight_level = (fbd->backlight_level & ~0xFF) | brightness; diff --git a/drivers/video/fbdev/nvidia/nv_backlight.c b/drivers/video/fbdev/nvidia/nv_backlight.c index 2ce53529f636..503a7a683855 100644 --- a/drivers/video/fbdev/nvidia/nv_backlight.c +++ b/drivers/video/fbdev/nvidia/nv_backlight.c @@ -49,17 +49,11 @@ static int nvidia_bl_update_status(struct backlight_device *bd) { struct nvidia_par *par = bl_get_data(bd); u32 tmp_pcrt, tmp_pmc, fpcontrol; - int level; + int level = backlight_get_brightness(bd); if (!par->FlatPanel) return 0; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; - tmp_pmc = NV_RD32(par->PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->PCRTC0, 0x081C) & 0xFFFFFFFC; fpcontrol = NV_RD32(par->PRAMDAC, 0x0848) & 0xCFFFFFCC; diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index 4fc4b26a8d30..ba94a0a7bd4f 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -331,13 +331,7 @@ static int dsicm_bl_update_status(struct backlight_device *dev) struct panel_drv_data *ddata = dev_get_drvdata(&dev->dev); struct omap_dss_device *in = ddata->in; int r; - int level; - - if (dev->props.fb_blank == FB_BLANK_UNBLANK && - dev->props.power == FB_BLANK_UNBLANK) - level = dev->props.brightness; - else - level = 0; + int level = backlight_get_brightness(dev); dev_dbg(&ddata->pdev->dev, "update brightness to %d\n", level); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c index bc5a44c2a144..ae937854403b 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "DISPLAY" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/sysfs.h> @@ -36,7 +37,7 @@ static ssize_t display_enabled_store(struct omap_dss_device *dssdev, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -73,7 +74,7 @@ static ssize_t display_tear_store(struct omap_dss_device *dssdev, if (!dssdev->driver->enable_te || !dssdev->driver->get_te) return -ENOENT; - r = strtobool(buf, &te); + r = kstrtobool(buf, &te); if (r) return r; @@ -183,7 +184,7 @@ static ssize_t display_mirror_store(struct omap_dss_device *dssdev, if (!dssdev->driver->set_mirror || !dssdev->driver->get_mirror) return -ENOENT; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c index ba21c4a2633d..1b644be5fe2e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "MANAGER" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/platform_device.h> @@ -246,7 +247,7 @@ static ssize_t manager_trans_key_enabled_store(struct omap_overlay_manager *mgr, bool enable; int r; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -290,7 +291,7 @@ static ssize_t manager_alpha_blending_enabled_store( if(!dss_has_feature(FEAT_ALPHA_FIXED_ZORDER)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -329,7 +330,7 @@ static ssize_t manager_cpr_enable_store(struct omap_overlay_manager *mgr, if (!dss_has_feature(FEAT_CPR)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c index 601c0beb6de9..1da4fb1c77b4 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/sysfs.h> #include <linux/kobject.h> +#include <linux/kstrtox.h> #include <linux/platform_device.h> #include <video/omapfb_dss.h> @@ -210,7 +211,7 @@ static ssize_t overlay_enabled_store(struct omap_overlay *ovl, const char *buf, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c index 06dc41aa0354..831b2c2fbdf9 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/platform_device.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/omapfb.h> @@ -96,7 +97,7 @@ static ssize_t store_mirror(struct device *dev, int r; struct fb_var_screeninfo new_var; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c index 644278146d3b..41edc6e79460 100644 --- a/drivers/video/fbdev/riva/fbdev.c +++ b/drivers/video/fbdev/riva/fbdev.c @@ -293,13 +293,7 @@ static int riva_bl_update_status(struct backlight_device *bd) { struct riva_par *par = bl_get_data(bd); U032 tmp_pcrt, tmp_pmc; - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); tmp_pmc = NV_RD32(par->riva.PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->riva.PCRTC0, 0x081C) & 0xFFFFFFFC; diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 6a2cf754912d..ff4b1d583788 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1426,12 +1426,20 @@ static void rbio_update_error_bitmap(struct btrfs_raid_bio *rbio, struct bio *bi u32 bio_size = 0; struct bio_vec *bvec; struct bvec_iter_all iter_all; + int i; bio_for_each_segment_all(bvec, bio, iter_all) bio_size += bvec->bv_len; - bitmap_set(rbio->error_bitmap, total_sector_nr, - bio_size >> rbio->bioc->fs_info->sectorsize_bits); + /* + * Since we can have multiple bios touching the error_bitmap, we cannot + * call bitmap_set() without protection. + * + * Instead use set_bit() for each bit, as set_bit() itself is atomic. + */ + for (i = total_sector_nr; i < total_sector_nr + + (bio_size >> rbio->bioc->fs_info->sectorsize_bits); i++) + set_bit(i, rbio->error_bitmap); } /* Verify the data sectors at read time. */ @@ -1886,7 +1894,7 @@ pstripe: sector->uptodate = 1; } if (failb >= 0) { - ret = verify_one_sector(rbio, faila, sector_nr); + ret = verify_one_sector(rbio, failb, sector_nr); if (ret < 0) goto cleanup; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e65e6b6600a7..d50182b6deec 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -8073,10 +8073,10 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) /* * Check that we don't overflow at later allocations, we request * clone_sources_count + 1 items, and compare to unsigned long inside - * access_ok. + * access_ok. Also set an upper limit for allocation size so this can't + * easily exhaust memory. Max number of clone sources is about 200K. */ - if (arg->clone_sources_count > - ULONG_MAX / sizeof(struct clone_root) - 1) { + if (arg->clone_sources_count > SZ_8M / sizeof(struct clone_root)) { ret = -EINVAL; goto out; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bcfef75b97da..4cdadf30163d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1600,7 +1600,7 @@ again: if (ret < 0) goto out; - while (1) { + while (search_start < search_end) { l = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(l)) { @@ -1623,6 +1623,9 @@ again: if (key.type != BTRFS_DEV_EXTENT_KEY) goto next; + if (key.offset > search_end) + break; + if (key.offset > search_start) { hole_size = key.offset - search_start; dev_extent_hole_check(device, &search_start, &hole_size, @@ -1683,6 +1686,7 @@ next: else ret = 0; + ASSERT(max_hole_start + max_hole_size <= search_end); out: btrfs_free_path(path); *start = max_hole_start; diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c index 01a13de11832..da7bb9187b68 100644 --- a/fs/btrfs/zlib.c +++ b/fs/btrfs/zlib.c @@ -63,7 +63,7 @@ struct list_head *zlib_alloc_workspace(unsigned int level) workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL), zlib_inflate_workspacesize()); - workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL); + workspace->strm.workspace = kvzalloc(workspacesize, GFP_KERNEL); workspace->level = level; workspace->buf = NULL; /* diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c74871e37c9..cac4083e387a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -305,7 +305,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_osd_request *req; + struct ceph_osd_request *req = NULL; struct ceph_vino vino = ceph_vino(inode); struct iov_iter iter; struct page **pages; @@ -313,6 +313,11 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) int err = 0; u64 len = subreq->len; + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; @@ -563,6 +568,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p idx %lu\n", page, page->index); + if (ceph_inode_is_shutdown(inode)) + return -EIO; + /* verify this is a writeable snap context */ snapc = page_snap_context(page); if (!snapc) { @@ -1643,7 +1651,7 @@ int ceph_uninline_data(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_osd_request *req = NULL; - struct ceph_cap_flush *prealloc_cf; + struct ceph_cap_flush *prealloc_cf = NULL; struct folio *folio = NULL; u64 inline_version = CEPH_INLINE_NONE; struct page *pages[1]; @@ -1657,6 +1665,11 @@ int ceph_uninline_data(struct file *file) dout("uninline_data %p %llx.%llx inline_version %llu\n", inode, ceph_vinop(inode), inline_version); + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (inline_version == CEPH_INLINE_NONE) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f75ad432f375..210e40037881 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4078,6 +4078,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, void *p, *end; struct cap_extra_info extra_info = {}; bool queue_trunc; + bool close_sessions = false; dout("handle_caps from mds%d\n", session->s_mds); @@ -4215,9 +4216,13 @@ void ceph_handle_caps(struct ceph_mds_session *session, realm = NULL; if (snaptrace_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, snaptrace, - snaptrace + snaptrace_len, - false, &realm); + if (ceph_update_snap_trace(mdsc, snaptrace, + snaptrace + snaptrace_len, + false, &realm)) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + goto done; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -4277,6 +4282,11 @@ done_unlocked: iput(inode); out: ceph_put_string(extra_info.pool_ns); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); + return; flush_cap_releases: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 764598e1efd9..b5cff85925a1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2011,6 +2011,9 @@ static int ceph_zero_partial_object(struct inode *inode, loff_t zero = 0; int op; + if (ceph_inode_is_shutdown(inode)) + return -EIO; + if (!length) { op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE; length = &zero; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 26a0a8b9975e..e163f58ff3c5 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -806,6 +806,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *s; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return ERR_PTR(-EIO); + if (mds >= mdsc->mdsmap->possible_max_rank) return ERR_PTR(-EINVAL); @@ -1478,6 +1481,9 @@ static int __open_session(struct ceph_mds_client *mdsc, int mstate; int mds = session->s_mds; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return -EIO; + /* wait for mds to go active? */ mstate = ceph_mdsmap_get_state(mdsc->mdsmap, mds); dout("open_session to mds%d (%s)\n", mds, @@ -2860,6 +2866,11 @@ static void __do_request(struct ceph_mds_client *mdsc, return; } + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) { + dout("do_request metadata corrupted\n"); + err = -EIO; + goto finish; + } if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { dout("do_request timed out\n"); @@ -3245,6 +3256,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) u64 tid; int err, result; int mds = session->s_mds; + bool close_sessions = false; if (msg->front.iov_len < sizeof(*head)) { pr_err("mdsc_handle_reply got corrupt (short) reply\n"); @@ -3351,10 +3363,17 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) realm = NULL; if (rinfo->snapblob_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, rinfo->snapblob, + err = ceph_update_snap_trace(mdsc, rinfo->snapblob, rinfo->snapblob + rinfo->snapblob_len, le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP, &realm); + if (err) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + if (err == -EIO) + ceph_msg_dump(msg); + goto out_err; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -3412,6 +3431,10 @@ out_err: req->r_end_latency, err); out: ceph_mdsc_put_request(req); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } @@ -5011,7 +5034,7 @@ static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped) } /* - * called after sb is ro. + * called after sb is ro or when metadata corrupted. */ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) { @@ -5301,7 +5324,8 @@ static void mds_peer_reset(struct ceph_connection *con) struct ceph_mds_client *mdsc = s->s_mdsc; pr_warn("mds%d closed our session\n", s->s_mds); - send_mds_reconnect(mdsc, s); + if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO) + send_mds_reconnect(mdsc, s); } static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index e4151852184e..87007203f130 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> +#include <linux/fs.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/iversion.h> @@ -766,8 +767,10 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; struct ceph_snap_realm *realm_to_rebuild = NULL; + struct ceph_client *client = mdsc->fsc->client; int rebuild_snapcs; int err = -ENOMEM; + int ret; LIST_HEAD(dirty_realms); lockdep_assert_held_write(&mdsc->snap_rwsem); @@ -884,6 +887,27 @@ fail: if (first_realm) ceph_put_snap_realm(mdsc, first_realm); pr_err("%s error %d\n", __func__, err); + + /* + * When receiving a corrupted snap trace we don't know what + * exactly has happened in MDS side. And we shouldn't continue + * writing to OSD, which may corrupt the snapshot contents. + * + * Just try to blocklist this kclient and then this kclient + * must be remounted to continue after the corrupted metadata + * fixed in the MDS side. + */ + WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO); + ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr); + if (ret) + pr_err("%s failed to blocklist %s: %d\n", __func__, + ceph_pr_addr(&client->msgr.inst.addr), ret); + + WARN(1, "%s: %s%sdo remount to continue%s", + __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr), + ret ? "" : " was blocklisted, ", + err == -EIO ? " after corrupted snaptrace is fixed" : ""); + return err; } @@ -984,6 +1008,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, __le64 *split_inos = NULL, *split_realms = NULL; int i; int locked_rwsem = 0; + bool close_sessions = false; /* decode */ if (msg->front.iov_len < sizeof(*h)) @@ -1092,8 +1117,12 @@ skip_inode: * update using the provided snap trace. if we are deleting a * snap, we can avoid queueing cap_snaps. */ - ceph_update_snap_trace(mdsc, p, e, - op == CEPH_SNAP_OP_DESTROY, NULL); + if (ceph_update_snap_trace(mdsc, p, e, + op == CEPH_SNAP_OP_DESTROY, + NULL)) { + close_sessions = true; + goto bad; + } if (op == CEPH_SNAP_OP_SPLIT) /* we took a reference when we created the realm, above */ @@ -1112,6 +1141,9 @@ bad: out: if (locked_rwsem) up_write(&mdsc->snap_rwsem); + + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 0ed3be75bb9a..07c6906cda70 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -100,6 +100,17 @@ struct ceph_mount_options { char *mon_addr; }; +/* mount state */ +enum { + CEPH_MOUNT_MOUNTING, + CEPH_MOUNT_MOUNTED, + CEPH_MOUNT_UNMOUNTING, + CEPH_MOUNT_UNMOUNTED, + CEPH_MOUNT_SHUTDOWN, + CEPH_MOUNT_RECOVER, + CEPH_MOUNT_FENCE_IO, +}; + #define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 struct ceph_fs_client { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 22dfc1f8b4f1..b8d1cbadb689 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3889,7 +3889,7 @@ uncached_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } @@ -4665,7 +4665,7 @@ readpages_fill_pages(struct TCP_Server_Info *server, rdata->got_bytes += result; } - return rdata->got_bytes > 0 && result != -ECONNABORTED ? + return result != -ECONNABORTED && rdata->got_bytes > 0 ? rdata->got_bytes : result; } diff --git a/fs/coredump.c b/fs/coredump.c index de78bde2991b..a25ecec9ca7c 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -838,6 +838,30 @@ static int __dump_skip(struct coredump_params *cprm, size_t nr) } } +int dump_emit(struct coredump_params *cprm, const void *addr, int nr) +{ + if (cprm->to_skip) { + if (!__dump_skip(cprm, cprm->to_skip)) + return 0; + cprm->to_skip = 0; + } + return __dump_emit(cprm, addr, nr); +} +EXPORT_SYMBOL(dump_emit); + +void dump_skip_to(struct coredump_params *cprm, unsigned long pos) +{ + cprm->to_skip = pos - cprm->pos; +} +EXPORT_SYMBOL(dump_skip_to); + +void dump_skip(struct coredump_params *cprm, size_t nr) +{ + cprm->to_skip += nr; +} +EXPORT_SYMBOL(dump_skip); + +#ifdef CONFIG_ELF_CORE static int dump_emit_page(struct coredump_params *cprm, struct page *page) { struct bio_vec bvec = { @@ -871,30 +895,6 @@ static int dump_emit_page(struct coredump_params *cprm, struct page *page) return 1; } -int dump_emit(struct coredump_params *cprm, const void *addr, int nr) -{ - if (cprm->to_skip) { - if (!__dump_skip(cprm, cprm->to_skip)) - return 0; - cprm->to_skip = 0; - } - return __dump_emit(cprm, addr, nr); -} -EXPORT_SYMBOL(dump_emit); - -void dump_skip_to(struct coredump_params *cprm, unsigned long pos) -{ - cprm->to_skip = pos - cprm->pos; -} -EXPORT_SYMBOL(dump_skip_to); - -void dump_skip(struct coredump_params *cprm, size_t nr) -{ - cprm->to_skip += nr; -} -EXPORT_SYMBOL(dump_skip); - -#ifdef CONFIG_ELF_CORE int dump_user_range(struct coredump_params *cprm, unsigned long start, unsigned long len) { diff --git a/fs/freevxfs/Kconfig b/fs/freevxfs/Kconfig index c05c71d57291..0e2fc08f7de4 100644 --- a/fs/freevxfs/Kconfig +++ b/fs/freevxfs/Kconfig @@ -8,7 +8,7 @@ config VXFS_FS of SCO UnixWare (and possibly others) and optionally available for Sunsoft Solaris, HP-UX and many other operating systems. However these particular OS implementations of vxfs may differ in on-disk - data endianess and/or superblock offset. The vxfs module has been + data endianness and/or superblock offset. The vxfs module has been tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.) Currently only readonly access is supported and VxFX versions 2, 3 and 4. Tests were performed with HP-UX VxFS version 3. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e35a0398db63..af1c49ae11b1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -745,9 +745,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = pfn_swap_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index b3fdc8212c5f..95f8e8901768 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 659082e9e51d..72f6f4b37863 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -63,7 +63,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; bool panic_on_errors; const struct squashfs_decompressor_thread_ops *thread_ops; diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index d8a270d3ac4c..f1a463d8bfa0 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -10,12 +10,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 087cab8c78f4..b88d19e9581e 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids == 0) + if (*xattr_ids <= 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 9270cd87da3f..6470f67e63c4 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -263,7 +263,7 @@ struct vgic_dist { struct vgic_io_device dist_iodev; bool has_its; - bool save_its_tables_in_progress; + bool table_write_in_progress; /* * Contains the attributes and gpa of the LPI configuration table. diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f7f24defccb8..35c18a98c21a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -899,8 +899,12 @@ enum bpf_cgroup_storage_type { /* The argument is a structure. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) +/* The argument is signed. */ +#define BTF_FMODEL_SIGNED_ARG BIT(1) + struct btf_func_model { u8 ret_size; + u8 ret_flags; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; u8 arg_flags[MAX_BPF_FUNC_ARGS]; @@ -939,7 +943,13 @@ struct btf_func_model { /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ -#define BPF_MAX_TRAMP_LINKS 38 +enum { +#if defined(__s390x__) + BPF_MAX_TRAMP_LINKS = 27, +#else + BPF_MAX_TRAMP_LINKS = 38, +#endif +}; struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; @@ -1836,7 +1846,7 @@ struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog); -void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); +void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, enum btf_field_type type); diff --git a/include/linux/btf.h b/include/linux/btf.h index 5f628f323442..49e0fe6d8274 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -73,6 +73,14 @@ #define KF_RCU (1 << 7) /* kfunc only takes rcu pointer arguments */ /* + * Tag marking a kernel function as a kfunc. This is meant to minimize the + * amount of copy-paste that kfunc authors have to include for correctness so + * as to avoid issues such as the compiler inlining or eliding either a static + * kfunc, or a global kfunc in an LTO build. + */ +#define __bpf_kfunc __used noinline + +/* * Return the name of the passed struct, if exists, or halt the build if for * example the structure gets renamed. In this way, developers have to revisit * the code using that structure name, and update it accordingly. @@ -236,6 +244,16 @@ static inline bool btf_type_is_small_int(const struct btf_type *t) return btf_type_is_int(t) && t->size <= sizeof(u64); } +static inline u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(u32 *)(t + 1)); +} + +static inline bool btf_type_is_signed_int(const struct btf_type *t) +{ + return btf_type_is_int(t) && (btf_int_encoding(t) & BTF_INT_SIGNED); +} + static inline bool btf_type_is_enum(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; @@ -306,11 +324,6 @@ static inline u8 btf_int_offset(const struct btf_type *t) return BTF_INT_OFFSET(*(u32 *)(t + 1)); } -static inline u8 btf_int_encoding(const struct btf_type *t) -{ - return BTF_INT_ENCODING(*(u32 *)(t + 1)); -} - static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index ef0a77173e3c..9b8a9c39614b 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -116,7 +116,7 @@ struct can_tdc_const { #ifdef CONFIG_CAN_CALC_BITTIMING int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc); + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack); void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, const struct can_bittiming *dbt, @@ -124,7 +124,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt, - const struct can_bittiming_const *btc) + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack) { netdev_err(dev, "bit-timing calculation not available\n"); return -EINVAL; @@ -138,10 +138,16 @@ can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, } #endif /* CONFIG_CAN_CALC_BITTIMING */ +void can_sjw_set_default(struct can_bittiming *bt); + +int can_sjw_check(const struct net_device *dev, const struct can_bittiming *bt, + const struct can_bittiming_const *btc, struct netlink_ext_ack *extack); + int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc, const u32 *bitrate_const, - const unsigned int bitrate_const_cnt); + const unsigned int bitrate_const_cnt, + struct netlink_ext_ack *extack); /* * can_bit_time() - Duration of one bit diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 00af2c98da75..4497d0a6772c 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -99,16 +99,6 @@ struct ceph_options { #define CEPH_AUTH_NAME_DEFAULT "guest" -/* mount state */ -enum { - CEPH_MOUNT_MOUNTING, - CEPH_MOUNT_MOUNTED, - CEPH_MOUNT_UNMOUNTING, - CEPH_MOUNT_UNMOUNTED, - CEPH_MOUNT_SHUTDOWN, - CEPH_MOUNT_RECOVER, -}; - static inline unsigned long ceph_timeout_jiffies(unsigned long timeout) { return timeout ?: MAX_SCHEDULE_TIMEOUT; diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c2aa0aa26b45..7b16aede7ac5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -391,6 +391,26 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1, nr_cpumask_bits, cpumask_check(cpu)); } +/** + * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd. + * @srcp1: the cpumask pointer + * @srcp2: the cpumask pointer + * @srcp3: the cpumask pointer + * @cpu: the N'th cpu to find, starting from 0 + * + * Returns >= nr_cpu_ids if such cpu doesn't exist. + */ +static __always_inline +unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1, + const struct cpumask *srcp2, + const struct cpumask *srcp3) +{ + return find_nth_and_andnot_bit(cpumask_bits(srcp1), + cpumask_bits(srcp2), + cpumask_bits(srcp3), + nr_cpumask_bits, cpumask_check(cpu)); +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ diff --git a/include/linux/efi.h b/include/linux/efi.h index 4b27519143f5..98598bd1d2fa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -668,7 +668,8 @@ extern struct efi { #define EFI_RT_SUPPORTED_ALL 0x3fff -#define EFI_RT_SUPPORTED_TIME_SERVICES 0x000f +#define EFI_RT_SUPPORTED_TIME_SERVICES 0x0003 +#define EFI_RT_SUPPORTED_WAKEUP_SERVICES 0x000c #define EFI_RT_SUPPORTED_VARIABLE_SERVICES 0x0070 extern struct mm_struct efi_mm; diff --git a/include/linux/find.h b/include/linux/find.h index ccaf61a0f5fd..4647864a5ffd 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -22,6 +22,9 @@ unsigned long __find_nth_and_bit(const unsigned long *addr1, const unsigned long unsigned long size, unsigned long n); unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long n); +unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, + const unsigned long *addr3, unsigned long size, + unsigned long n); extern unsigned long _find_first_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); @@ -255,6 +258,36 @@ unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned lon return __find_nth_andnot_bit(addr1, addr2, size, n); } +/** + * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions, + * excluding those set in 3rd region + * @addr1: The 1st address to start the search at + * @addr2: The 2nd address to start the search at + * @addr3: The 3rd address to start the search at + * @size: The maximum number of bits to search + * @n: The number of set bit, which position is needed, counting from 0 + * + * Returns the bit number of the N'th set bit. + * If no such, returns @size. + */ +static __always_inline +unsigned long find_nth_and_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size, unsigned long n) +{ + if (n >= size) + return size; + + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & (~*addr3) & GENMASK(size - 1, 0); + + return val ? fns(val, n) : size; + } + + return __find_nth_and_andnot_bit(addr1, addr2, addr3, size, n); +} + #ifndef find_first_and_bit /** * find_first_and_bit - find the first set bit in both memory regions diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 034b1106d022..e098f38422af 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -200,7 +200,7 @@ static inline void *kmap_local_pfn(unsigned long pfn) static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } @@ -227,7 +227,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn) static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 551834cd5299..db194e2ba69f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> +#include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> @@ -1187,6 +1188,18 @@ static inline __init void hugetlb_cma_reserve(int order) } #endif +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return page_count(virt_to_page(pte)) > 1; +} +#else +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return false; +} +#endif + bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d3c8203cab6c..85dc9b88ea37 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1666,10 +1666,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + memcg = folio_memcg(folio); + if (unlikely(memcg && &memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 771e050883db..8bef1ab62bba 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,6 +31,7 @@ #define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_LAN8814 0x00221660 #define PHY_ID_LAN8804 0x00221670 +#define PHY_ID_LAN8841 0x00221650 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index bc531bd9804f..71b06ebad402 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -362,11 +362,13 @@ enum mlx5_event { enum mlx5_driver_event { MLX5_DRIVER_EVENT_TYPE_TRAP = 0, + MLX5_DRIVER_EVENT_UPLINK_NETDEV, }; enum { MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0, MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1, + MLX5_TRACER_SUBTYPE_STRINGS_DB_UPDATE = 0x2, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index cd529e051b4d..ecd3b5448fe9 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -49,6 +49,7 @@ #include <linux/notifier.h> #include <linux/refcount.h> #include <linux/auxiliary_bus.h> +#include <linux/mutex.h> #include <linux/mlx5/device.h> #include <linux/mlx5/doorbell.h> @@ -430,8 +431,6 @@ struct mlx5_core_health { u8 synd; u32 fatal_error; u32 crdump_size; - /* wq spinlock to synchronize draining */ - spinlock_t wq_lock; struct workqueue_struct *wq; unsigned long flags; struct work_struct fatal_report_work; @@ -573,6 +572,14 @@ struct mlx5_debugfs_entries { struct dentry *lag_debugfs; }; +enum mlx5_func_type { + MLX5_PF, + MLX5_VF, + MLX5_SF, + MLX5_HOST_PF, + MLX5_FUNC_TYPE_NUM, +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -583,11 +590,10 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - u32 vfs_pages; - u32 host_pf_pages; + u32 fw_pages; + u32 page_counters[MLX5_FUNC_TYPE_NUM]; u32 fw_pages_alloc_failed; u32 give_pages_dropped; u32 reclaim_pages_discard; @@ -674,6 +680,7 @@ struct mlx5e_resources { } hw_objs; struct devlink_port dl_port; struct net_device *uplink_netdev; + struct mutex uplink_netdev_lock; struct mlx5_crypto_dek_priv *dek_priv; }; @@ -1012,6 +1019,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); +void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); +void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); + int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1b6201bb04c1..1e530a8a2cf5 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1521,7 +1521,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 null_mkey[0x1]; u8 log_max_klm_list_size[0x6]; - u8 reserved_at_120[0xa]; + u8 reserved_at_120[0x2]; + u8 qpc_extension[0x1]; + u8 reserved_at_123[0x7]; u8 log_max_ra_req_dc[0x6]; u8 reserved_at_130[0x2]; u8 eth_wqe_too_small[0x1]; @@ -1687,7 +1689,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_bf_reg_size[0x5]; - u8 reserved_at_270[0x6]; + u8 reserved_at_270[0x3]; + u8 qp_error_syndrome[0x1]; + u8 reserved_at_274[0x2]; u8 lag_dct[0x2]; u8 lag_tx_port_affinity[0x1]; u8 lag_native_fdb_selection[0x1]; @@ -5393,6 +5397,37 @@ struct mlx5_ifc_query_rmp_in_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_cqe_error_syndrome_bits { + u8 hw_error_syndrome[0x8]; + u8 hw_syndrome_type[0x4]; + u8 reserved_at_c[0x4]; + u8 vendor_error_syndrome[0x8]; + u8 syndrome[0x8]; +}; + +struct mlx5_ifc_qp_context_extension_bits { + u8 reserved_at_0[0x60]; + + struct mlx5_ifc_cqe_error_syndrome_bits error_syndrome; + + u8 reserved_at_80[0x580]; +}; + +struct mlx5_ifc_qpc_extension_and_pas_list_in_bits { + struct mlx5_ifc_qp_context_extension_bits qpc_data_extension; + + u8 pas[0][0x40]; +}; + +struct mlx5_ifc_qp_pas_list_in_bits { + struct mlx5_ifc_cmd_pas_bits pas[0]; +}; + +union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits { + struct mlx5_ifc_qp_pas_list_in_bits qp_pas_list; + struct mlx5_ifc_qpc_extension_and_pas_list_in_bits qpc_ext_and_pas_list; +}; + struct mlx5_ifc_query_qp_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -5409,7 +5444,7 @@ struct mlx5_ifc_query_qp_out_bits { u8 reserved_at_800[0x80]; - u8 pas[][0x40]; + union mlx5_ifc_qp_pas_or_qpc_ext_and_pas_bits qp_pas_or_qpc_ext_and_pas; }; struct mlx5_ifc_query_qp_in_bits { @@ -5419,7 +5454,8 @@ struct mlx5_ifc_query_qp_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x8]; + u8 qpc_ext[0x1]; + u8 reserved_at_41[0x7]; u8 qpn[0x18]; u8 reserved_at_60[0x20]; @@ -8635,7 +8671,8 @@ struct mlx5_ifc_create_qp_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x8]; + u8 qpc_ext[0x1]; + u8 reserved_at_41[0x7]; u8 input_qpn[0x18]; u8 reserved_at_60[0x20]; @@ -9926,13 +9963,20 @@ struct mlx5_ifc_mpegc_reg_bits { }; enum { + MLX5_MTUTC_FREQ_ADJ_UNITS_PPB = 0x0, + MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM = 0x1, +}; + +enum { MLX5_MTUTC_OPERATION_SET_TIME_IMMEDIATE = 0x1, MLX5_MTUTC_OPERATION_ADJUST_TIME = 0x2, MLX5_MTUTC_OPERATION_ADJUST_FREQ_UTC = 0x3, }; struct mlx5_ifc_mtutc_reg_bits { - u8 reserved_at_0[0x1c]; + u8 reserved_at_0[0x5]; + u8 freq_adj_units[0x3]; + u8 reserved_at_8[0x14]; u8 operation[0x4]; u8 freq_adjustment[0x20]; @@ -10005,7 +10049,8 @@ struct mlx5_ifc_pcam_reg_bits { }; struct mlx5_ifc_mcam_enhanced_features_bits { - u8 reserved_at_0[0x51]; + u8 reserved_at_0[0x50]; + u8 mtutc_freq_adj_units[0x1]; u8 mtutc_time_adjustment_extended_range[0x1]; u8 reserved_at_52[0xb]; u8 mcia_32dwords[0x1]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d5ef4c1fedd2..d9cdbc047b49 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -47,6 +47,7 @@ #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> +#include <uapi/linux/netdev.h> #include <linux/hashtable.h> #include <linux/rbtree.h> #include <net/net_trackers.h> @@ -223,6 +224,7 @@ struct net_device_core_stats { #include <linux/static_key.h> extern struct static_key_false rps_needed; extern struct static_key_false rfs_needed; +extern struct cpumask rps_default_mask; #endif struct neighbour; @@ -1818,6 +1820,7 @@ enum netdev_ml_priv_type { * of Layer 2 headers. * * @flags: Interface flags (a la BSD) + * @xdp_features: XDP capability supported by the device * @priv_flags: Like 'flags' but invisible to userspace, * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) @@ -2059,6 +2062,7 @@ struct net_device { /* Read-mostly cache-line for fast-path access */ unsigned int flags; + xdp_features_t xdp_features; unsigned long long priv_flags; const struct net_device_ops *netdev_ops; const struct xdp_metadata_ops *xdp_metadata_ops; @@ -2845,6 +2849,7 @@ enum netdev_cmd { NETDEV_OFFLOAD_XSTATS_DISABLE, NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, + NETDEV_XDP_FEAT_CHANGE, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 50caa117cb62..bb15c9234e21 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,6 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if @@ -85,7 +84,6 @@ struct nvmem_config { const char *name; int id; struct module *owner; - struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; const struct nvmem_keepout *keepout; diff --git a/include/linux/poison.h b/include/linux/poison.h index 2d3249eb0e62..2823f90fdab4 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -81,6 +81,9 @@ /********** net/core/page_pool.c **********/ #define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) +/********** net/core/skbuff.c **********/ +#define SKB_LIST_POISON_NEXT ((void *)(0x800 + POISON_POINTER_DELTA)) + /********** kernel/bpf/ **********/ #define BPF_PTR_POISON ((void *)(0xeB9FUL + POISON_POINTER_DELTA)) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5ba12185f43e..47ab28a37f2f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -255,6 +255,14 @@ #define SKB_DATA_ALIGN(X) ALIGN(X, SMP_CACHE_BYTES) #define SKB_WITH_OVERHEAD(X) \ ((X) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + +/* For X bytes available in skb->head, what is the minimal + * allocation needed, knowing struct skb_shared_info needs + * to be aligned. + */ +#define SKB_HEAD_ALIGN(X) (SKB_DATA_ALIGN(X) + \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) + #define SKB_MAX_ORDER(X, ORDER) \ SKB_WITH_OVERHEAD((PAGE_SIZE << (ORDER)) - (X)) #define SKB_MAX_HEAD(X) (SKB_MAX_ORDER((X), 0)) @@ -1235,7 +1243,7 @@ static inline void consume_skb(struct sk_buff *skb) void __consume_stateless_skb(struct sk_buff *skb); void __kfree_skb(struct sk_buff *skb); -extern struct kmem_cache *skbuff_head_cache; +extern struct kmem_cache *skbuff_cache; void kfree_skb_partial(struct sk_buff *skb, bool head_stolen); bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, @@ -1738,6 +1746,13 @@ static inline void skb_mark_not_on_list(struct sk_buff *skb) skb->next = NULL; } +static inline void skb_poison_list(struct sk_buff *skb) +{ +#ifdef CONFIG_DEBUG_NET + skb->next = SKB_LIST_POISON_NEXT; +#endif +} + /* Iterate through singly-linked GSO fragments of an skb. */ #define skb_list_walk_safe(first, skb, next_skb) \ for ((skb) = (first), (next_skb) = (skb) ? (skb)->next : NULL; (skb); \ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1341f7d62da4..be48f1cb1878 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -476,6 +476,15 @@ extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) +extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock); +#define atomic_dec_and_raw_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock)) + +extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags))) + int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 8530c7328269..fae6beaaa217 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -11,6 +11,11 @@ struct device; struct file; struct task_struct; +static inline bool string_is_terminated(const char *s, int len) +{ + return memchr(s, '\0', len) ? true : false; +} + /* Descriptions of the types of units to * print in */ enum string_size_units { diff --git a/include/linux/swap.h b/include/linux/swap.h index 2787b84eaf12..0ceed49516ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask); + unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, diff --git a/include/linux/topology.h b/include/linux/topology.h index 4564faafd0e1..fea32377f7c7 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -245,5 +245,38 @@ static inline const struct cpumask *cpu_cpu_mask(int cpu) return cpumask_of_node(cpu_to_node(cpu)); } +#ifdef CONFIG_NUMA +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); +extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); +#else +static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) +{ + return cpumask_nth(cpu, cpus); +} + +static inline const struct cpumask * +sched_numa_hop_mask(unsigned int node, unsigned int hops) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif /* CONFIG_NUMA */ + +/** + * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance + * from a given node. + * @mask: the iteration variable. + * @node: the NUMA node to start the search from. + * + * Requires rcu_lock to be held. + * + * Yields cpu_online_mask for @node == NUMA_NO_NODE. + */ +#define for_each_numa_hop_mask(mask, node) \ + for (unsigned int __hops = 0; \ + mask = (node != NUMA_NO_NODE || __hops) ? \ + sched_numa_hop_mask(node, __hops) : \ + cpu_online_mask, \ + !IS_ERR_OR_NULL(mask); \ + __hops++) #endif /* _LINUX_TOPOLOGY_H */ diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 8d773b042c85..400f8a7d0c3f 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -2156,7 +2156,7 @@ struct hci_cp_le_big_create_sync { __u8 mse; __le16 timeout; __u8 num_bis; - __u8 bis[0]; + __u8 bis[]; } __packed; #define HCI_OP_LE_BIG_TERM_SYNC 0x206c @@ -2174,7 +2174,7 @@ struct hci_cp_le_setup_iso_path { __le16 codec_vid; __u8 delay[3]; __u8 codec_cfg_len; - __u8 codec_cfg[0]; + __u8 codec_cfg[]; } __packed; struct hci_rp_le_setup_iso_path { diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 743f6f59dff8..e18a927669c0 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -109,6 +109,8 @@ struct mgmt_rp_read_index_list { #define MGMT_SETTING_STATIC_ADDRESS 0x00008000 #define MGMT_SETTING_PHY_CONFIGURATION 0x00010000 #define MGMT_SETTING_WIDEBAND_SPEECH 0x00020000 +#define MGMT_SETTING_CIS_CENTRAL 0x00040000 +#define MGMT_SETTING_CIS_PERIPHERAL 0x00080000 #define MGMT_OP_READ_INFO 0x0004 #define MGMT_READ_INFO_SIZE 0 diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 6a2019aaa464..7bbab8f2b73d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -362,6 +362,10 @@ static inline struct nf_conntrack_net *nf_ct_pernet(const struct net *net) return net_generic(net, nf_conntrack_net_id); } +int nf_ct_skb_network_trim(struct sk_buff *skb, int family); +int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u16 zone, u8 family, u8 *proto, u16 *mru); + #define NF_CT_STAT_INC(net, count) __this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count) #define NF_CT_STAT_ADD_ATOMIC(net, count, v) this_cpu_add((net)->ct.stat->count, (v)) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 813c93499f20..34bf531ffc8d 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -386,7 +386,7 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid) static inline void page_pool_ring_lock(struct page_pool *pool) __acquires(&pool->ring.producer_lock) { - if (in_serving_softirq()) + if (in_softirq()) spin_lock(&pool->ring.producer_lock); else spin_lock_bh(&pool->ring.producer_lock); @@ -395,7 +395,7 @@ static inline void page_pool_ring_lock(struct page_pool *pool) static inline void page_pool_ring_unlock(struct page_pool *pool) __releases(&pool->ring.producer_lock) { - if (in_serving_softirq()) + if (in_softirq()) spin_unlock(&pool->ring.producer_lock); else spin_unlock_bh(&pool->ring.producer_lock); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 4cabb32a2ad9..cd410a87517b 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -788,16 +788,6 @@ struct tc_cls_bpf_offload { bool exts_integrated; }; -struct tc_mqprio_qopt_offload { - /* struct tc_mqprio_qopt must always be the first element */ - struct tc_mqprio_qopt qopt; - u16 mode; - u16 shaper; - u32 flags; - u64 min_rate[TC_QOPT_MAX_QUEUE]; - u64 max_rate[TC_QOPT_MAX_QUEUE]; -}; - /* This structure holds cookie structure that is passed from user * to the kernel for actions and classifiers */ diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 38207873eda6..2016839991a4 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -160,8 +160,28 @@ struct tc_etf_qopt_offload { s32 queue; }; +struct tc_mqprio_caps { + bool validate_queue_counts:1; +}; + +struct tc_mqprio_qopt_offload { + /* struct tc_mqprio_qopt must always be the first element */ + struct tc_mqprio_qopt qopt; + u16 mode; + u16 shaper; + u32 flags; + u64 min_rate[TC_QOPT_MAX_QUEUE]; + u64 max_rate[TC_QOPT_MAX_QUEUE]; +}; + struct tc_taprio_caps { bool supports_queue_max_sdu:1; + bool gate_mask_per_txq:1; + /* Device expects lower TXQ numbers to have higher priority over higher + * TXQs, regardless of their TC mapping. DO NOT USE FOR NEW DRIVERS, + * INSTEAD ENFORCE A PROPER TC:TXQ MAPPING COMING FROM USER SPACE. + */ + bool broken_mqprio:1; }; struct tc_taprio_sched_entry { @@ -173,6 +193,7 @@ struct tc_taprio_sched_entry { }; struct tc_taprio_qopt_offload { + struct tc_mqprio_qopt_offload mqprio; u8 enable; ktime_t base_time; u64 cycle_time; diff --git a/include/net/raw.h b/include/net/raw.h index 5e665934ebc7..2c004c20ed99 100644 --- a/include/net/raw.h +++ b/include/net/raw.h @@ -15,6 +15,8 @@ #include <net/inet_sock.h> #include <net/protocol.h> +#include <net/netns/hash.h> +#include <linux/hash.h> #include <linux/icmp.h> extern struct proto raw_prot; @@ -29,13 +31,20 @@ int raw_local_deliver(struct sk_buff *, int); int raw_rcv(struct sock *, struct sk_buff *); -#define RAW_HTABLE_SIZE MAX_INET_PROTOS +#define RAW_HTABLE_LOG 8 +#define RAW_HTABLE_SIZE (1U << RAW_HTABLE_LOG) struct raw_hashinfo { spinlock_t lock; - struct hlist_nulls_head ht[RAW_HTABLE_SIZE]; + + struct hlist_nulls_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned; }; +static inline u32 raw_hashfunc(const struct net *net, u32 proto) +{ + return hash_32(net_hash_mix(net) ^ proto, RAW_HTABLE_LOG); +} + static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo) { int i; diff --git a/include/net/sock.h b/include/net/sock.h index dcd72e6285b2..937e842dc930 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1956,7 +1956,12 @@ void sk_common_release(struct sock *sk); * Default socket callbacks and setup code */ -/* Initialise core socket variables */ +/* Initialise core socket variables using an explicit uid. */ +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); + +/* Initialise core socket variables. + * Assumes struct socket *sock is embedded in a struct socket_alloc. + */ void sock_init_data(struct socket *sock, struct sock *sk); /* diff --git a/include/net/xdp.h b/include/net/xdp.h index 91292aa13bc0..d517bfac937b 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -7,6 +7,7 @@ #define __LINUX_NET_XDP_H__ #include <linux/skbuff.h> /* skb_shared_info */ +#include <uapi/linux/netdev.h> /** * DOC: XDP RX-queue information @@ -43,6 +44,8 @@ enum xdp_mem_type { MEM_TYPE_MAX, }; +typedef u32 xdp_features_t; + /* XDP flags for ndo_xdp_xmit */ #define XDP_XMIT_FLUSH (1U << 0) /* doorbell signal consumer */ #define XDP_XMIT_FLAGS_MASK XDP_XMIT_FLUSH @@ -425,9 +428,21 @@ MAX_XDP_METADATA_KFUNC, #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); +void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg); +void xdp_features_clear_redirect_target(struct net_device *dev); #else static inline u32 bpf_xdp_metadata_kfunc_id(int id) { return 0; } static inline bool bpf_dev_bound_kfunc_id(u32 btf_id) { return false; } + +static inline void +xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) +{ +} + +static inline void +xdp_features_clear_redirect_target(struct net_device *dev) +{ +} #endif #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/soc/mscc/vsc7514_regs.h b/include/soc/mscc/vsc7514_regs.h index dfb91629c8bd..ffe343a9c04b 100644 --- a/include/soc/mscc/vsc7514_regs.h +++ b/include/soc/mscc/vsc7514_regs.h @@ -14,22 +14,6 @@ extern struct vcap_props vsc7514_vcap_props[]; extern const struct reg_field vsc7514_regfields[REGFIELD_MAX]; -extern const u32 vsc7514_ana_regmap[]; -extern const u32 vsc7514_qs_regmap[]; -extern const u32 vsc7514_qsys_regmap[]; -extern const u32 vsc7514_rew_regmap[]; -extern const u32 vsc7514_sys_regmap[]; -extern const u32 vsc7514_vcap_regmap[]; -extern const u32 vsc7514_ptp_regmap[]; -extern const u32 vsc7514_dev_gmii_regmap[]; - extern const u32 *vsc7514_regmap[TARGET_MAX]; -extern const struct vcap_field vsc7514_vcap_es0_keys[]; -extern const struct vcap_field vsc7514_vcap_es0_actions[]; -extern const struct vcap_field vsc7514_vcap_is1_keys[]; -extern const struct vcap_field vsc7514_vcap_is1_actions[]; -extern const struct vcap_field vsc7514_vcap_is2_keys[]; -extern const struct vcap_field vsc7514_vcap_is2_actions[]; - #endif diff --git a/include/trace/events/bridge.h b/include/trace/events/bridge.h index 6b200059c2c5..a6b3a4e409f0 100644 --- a/include/trace/events/bridge.h +++ b/include/trace/events/bridge.h @@ -122,6 +122,64 @@ TRACE_EVENT(br_fdb_update, __entry->flags) ); +TRACE_EVENT(br_mdb_full, + + TP_PROTO(const struct net_device *dev, + const struct br_ip *group), + + TP_ARGS(dev, group), + + TP_STRUCT__entry( + __string(dev, dev->name) + __field(int, af) + __field(u16, vid) + __array(__u8, src, 16) + __array(__u8, grp, 16) + __array(__u8, grpmac, ETH_ALEN) /* For af == 0. */ + ), + + TP_fast_assign( + struct in6_addr *in6; + + __assign_str(dev, dev->name); + __entry->vid = group->vid; + + if (!group->proto) { + __entry->af = 0; + + memset(__entry->src, 0, sizeof(__entry->src)); + memset(__entry->grp, 0, sizeof(__entry->grp)); + memcpy(__entry->grpmac, group->dst.mac_addr, ETH_ALEN); + } else if (group->proto == htons(ETH_P_IP)) { + __entry->af = AF_INET; + + in6 = (struct in6_addr *)__entry->src; + ipv6_addr_set_v4mapped(group->src.ip4, in6); + + in6 = (struct in6_addr *)__entry->grp; + ipv6_addr_set_v4mapped(group->dst.ip4, in6); + + memset(__entry->grpmac, 0, ETH_ALEN); + +#if IS_ENABLED(CONFIG_IPV6) + } else { + __entry->af = AF_INET6; + + in6 = (struct in6_addr *)__entry->src; + *in6 = group->src.ip6; + + in6 = (struct in6_addr *)__entry->grp; + *in6 = group->dst.ip6; + + memset(__entry->grpmac, 0, ETH_ALEN); +#endif + } + ), + + TP_printk("dev %s af %u src %pI6c grp %pI6c/%pM vid %u", + __get_str(dev), __entry->af, __entry->src, __entry->grp, + __entry->grpmac, __entry->vid) +); #endif /* _TRACE_BRIDGE_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d7bb4acf4580..c3c0b0aa8381 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1118,9 +1118,9 @@ TRACE_EVENT(rxrpc_tx_data, TRACE_EVENT(rxrpc_tx_ack, TP_PROTO(unsigned int call, rxrpc_serial_t serial, rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial, - u8 reason, u8 n_acks), + u8 reason, u8 n_acks, u16 rwind), - TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks), + TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind), TP_STRUCT__entry( __field(unsigned int, call) @@ -1129,6 +1129,7 @@ TRACE_EVENT(rxrpc_tx_ack, __field(rxrpc_serial_t, ack_serial) __field(u8, reason) __field(u8, n_acks) + __field(u16, rwind) ), TP_fast_assign( @@ -1138,15 +1139,17 @@ TRACE_EVENT(rxrpc_tx_ack, __entry->ack_serial = ack_serial; __entry->reason = reason; __entry->n_acks = n_acks; + __entry->rwind = rwind; ), - TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u", + TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u rw=%u", __entry->call, __entry->serial, __print_symbolic(__entry->reason, rxrpc_ack_names), __entry->ack_first, __entry->ack_serial, - __entry->n_acks) + __entry->n_acks, + __entry->rwind) ); TRACE_EVENT(rxrpc_receive, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba0f0cfb5e42..17afd2b35ee5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2801,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index d9de241d90f9..d60c456710b3 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -523,6 +523,8 @@ enum { BRIDGE_VLANDB_ENTRY_TUNNEL_INFO, BRIDGE_VLANDB_ENTRY_STATS, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, + BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, __BRIDGE_VLANDB_ENTRY_MAX, }; #define BRIDGE_VLANDB_ENTRY_MAX (__BRIDGE_VLANDB_ENTRY_MAX - 1) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 02b87e4c65be..57ceb788250f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -567,6 +567,8 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 874a92349bf5..283dec7e3645 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -18,6 +18,7 @@ #ifndef _UAPI_LINUX_IP_H #define _UAPI_LINUX_IP_H #include <linux/types.h> +#include <linux/stddef.h> #include <asm/byteorder.h> #define IPTOS_TOS_MASK 0x1E diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 81f4243bebb1..53326dfc59ec 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -4,6 +4,7 @@ #include <linux/libc-compat.h> #include <linux/types.h> +#include <linux/stddef.h> #include <linux/in6.h> #include <asm/byteorder.h> diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..9ee459872600 --- /dev/null +++ b/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * oflloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 5b3cb8068b4d..740bdb045b14 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6453,6 +6453,18 @@ static int __get_type_size(struct btf *btf, u32 btf_id, return -EINVAL; } +static u8 __get_type_fmodel_flags(const struct btf_type *t) +{ + u8 flags = 0; + + if (__btf_type_is_struct(t)) + flags |= BTF_FMODEL_STRUCT_ARG; + if (btf_type_is_signed_int(t)) + flags |= BTF_FMODEL_SIGNED_ARG; + + return flags; +} + int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func, @@ -6473,6 +6485,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->arg_flags[i] = 0; } m->ret_size = 8; + m->ret_flags = 0; m->nr_args = MAX_BPF_FUNC_REG_ARGS; return 0; } @@ -6492,6 +6505,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->ret_size = ret; + m->ret_flags = __get_type_fmodel_flags(t); for (i = 0; i < nargs; i++) { if (i == nargs - 1 && args[i].type == 0) { @@ -6516,7 +6530,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, return -EINVAL; } m->arg_size[i] = ret; - m->arg_flags[i] = __btf_type_is_struct(t) ? BTF_FMODEL_STRUCT_ARG : 0; + m->arg_flags[i] = __get_type_fmodel_flags(t); } m->nr_args = nargs; return 0; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e0b2d016f0bf..d2110c1f6fa6 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -361,7 +361,7 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 25355a0a367a..52b981512a35 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -48,10 +48,13 @@ __diag_ignore_all("-Wmissing-prototypes", * bpf_cpumask_create() allocates memory using the BPF memory allocator, and * will not block. It may return NULL if no memory is available. */ -struct bpf_cpumask *bpf_cpumask_create(void) +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_create(void) { struct bpf_cpumask *cpumask; + /* cpumask must be the first element so struct bpf_cpumask be cast to struct cpumask. */ + BUILD_BUG_ON(offsetof(struct bpf_cpumask, cpumask) != 0); + cpumask = bpf_mem_alloc(&bpf_cpumask_ma, sizeof(*cpumask)); if (!cpumask) return NULL; @@ -71,7 +74,7 @@ struct bpf_cpumask *bpf_cpumask_create(void) * must either be embedded in a map as a kptr, or freed with * bpf_cpumask_release(). */ -struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) { refcount_inc(&cpumask->usage); return cpumask; @@ -87,7 +90,7 @@ struct bpf_cpumask *bpf_cpumask_acquire(struct bpf_cpumask *cpumask) * kptr, or freed with bpf_cpumask_release(). This function may return NULL if * no BPF cpumask was found in the specified map value. */ -struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp) +__bpf_kfunc struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp) { struct bpf_cpumask *cpumask; @@ -113,7 +116,7 @@ struct bpf_cpumask *bpf_cpumask_kptr_get(struct bpf_cpumask **cpumaskp) * reference of the BPF cpumask has been released, it is subsequently freed in * an RCU callback in the BPF memory allocator. */ -void bpf_cpumask_release(struct bpf_cpumask *cpumask) +__bpf_kfunc void bpf_cpumask_release(struct bpf_cpumask *cpumask) { if (!cpumask) return; @@ -132,7 +135,7 @@ void bpf_cpumask_release(struct bpf_cpumask *cpumask) * Find the index of the first nonzero bit of the cpumask. A struct bpf_cpumask * pointer may be safely passed to this function. */ -u32 bpf_cpumask_first(const struct cpumask *cpumask) +__bpf_kfunc u32 bpf_cpumask_first(const struct cpumask *cpumask) { return cpumask_first(cpumask); } @@ -145,7 +148,7 @@ u32 bpf_cpumask_first(const struct cpumask *cpumask) * Find the index of the first unset bit of the cpumask. A struct bpf_cpumask * pointer may be safely passed to this function. */ -u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) +__bpf_kfunc u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) { return cpumask_first_zero(cpumask); } @@ -155,7 +158,7 @@ u32 bpf_cpumask_first_zero(const struct cpumask *cpumask) * @cpu: The CPU to be set in the cpumask. * @cpumask: The BPF cpumask in which a bit is being set. */ -void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +__bpf_kfunc void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) { if (!cpu_valid(cpu)) return; @@ -168,7 +171,7 @@ void bpf_cpumask_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) * @cpu: The CPU to be cleared from the cpumask. * @cpumask: The BPF cpumask in which a bit is being cleared. */ -void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +__bpf_kfunc void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) { if (!cpu_valid(cpu)) return; @@ -185,7 +188,7 @@ void bpf_cpumask_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) * * true - @cpu is set in the cpumask * * false - @cpu was not set in the cpumask, or @cpu is an invalid cpu. */ -bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) +__bpf_kfunc bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) { if (!cpu_valid(cpu)) return false; @@ -202,7 +205,7 @@ bool bpf_cpumask_test_cpu(u32 cpu, const struct cpumask *cpumask) * * true - @cpu is set in the cpumask * * false - @cpu was not set in the cpumask, or @cpu is invalid. */ -bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) +__bpf_kfunc bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) { if (!cpu_valid(cpu)) return false; @@ -220,7 +223,7 @@ bool bpf_cpumask_test_and_set_cpu(u32 cpu, struct bpf_cpumask *cpumask) * * true - @cpu is set in the cpumask * * false - @cpu was not set in the cpumask, or @cpu is invalid. */ -bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) +__bpf_kfunc bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) { if (!cpu_valid(cpu)) return false; @@ -232,7 +235,7 @@ bool bpf_cpumask_test_and_clear_cpu(u32 cpu, struct bpf_cpumask *cpumask) * bpf_cpumask_setall() - Set all of the bits in a BPF cpumask. * @cpumask: The BPF cpumask having all of its bits set. */ -void bpf_cpumask_setall(struct bpf_cpumask *cpumask) +__bpf_kfunc void bpf_cpumask_setall(struct bpf_cpumask *cpumask) { cpumask_setall((struct cpumask *)cpumask); } @@ -241,7 +244,7 @@ void bpf_cpumask_setall(struct bpf_cpumask *cpumask) * bpf_cpumask_clear() - Clear all of the bits in a BPF cpumask. * @cpumask: The BPF cpumask being cleared. */ -void bpf_cpumask_clear(struct bpf_cpumask *cpumask) +__bpf_kfunc void bpf_cpumask_clear(struct bpf_cpumask *cpumask) { cpumask_clear((struct cpumask *)cpumask); } @@ -258,9 +261,9 @@ void bpf_cpumask_clear(struct bpf_cpumask *cpumask) * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -bool bpf_cpumask_and(struct bpf_cpumask *dst, - const struct cpumask *src1, - const struct cpumask *src2) +__bpf_kfunc bool bpf_cpumask_and(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) { return cpumask_and((struct cpumask *)dst, src1, src2); } @@ -273,9 +276,9 @@ bool bpf_cpumask_and(struct bpf_cpumask *dst, * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -void bpf_cpumask_or(struct bpf_cpumask *dst, - const struct cpumask *src1, - const struct cpumask *src2) +__bpf_kfunc void bpf_cpumask_or(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) { cpumask_or((struct cpumask *)dst, src1, src2); } @@ -288,9 +291,9 @@ void bpf_cpumask_or(struct bpf_cpumask *dst, * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -void bpf_cpumask_xor(struct bpf_cpumask *dst, - const struct cpumask *src1, - const struct cpumask *src2) +__bpf_kfunc void bpf_cpumask_xor(struct bpf_cpumask *dst, + const struct cpumask *src1, + const struct cpumask *src2) { cpumask_xor((struct cpumask *)dst, src1, src2); } @@ -306,7 +309,7 @@ void bpf_cpumask_xor(struct bpf_cpumask *dst, * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) +__bpf_kfunc bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) { return cpumask_equal(src1, src2); } @@ -322,7 +325,7 @@ bool bpf_cpumask_equal(const struct cpumask *src1, const struct cpumask *src2) * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) +__bpf_kfunc bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *src2) { return cpumask_intersects(src1, src2); } @@ -338,7 +341,7 @@ bool bpf_cpumask_intersects(const struct cpumask *src1, const struct cpumask *sr * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) +__bpf_kfunc bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) { return cpumask_subset(src1, src2); } @@ -353,7 +356,7 @@ bool bpf_cpumask_subset(const struct cpumask *src1, const struct cpumask *src2) * * A struct bpf_cpumask pointer may be safely passed to @cpumask. */ -bool bpf_cpumask_empty(const struct cpumask *cpumask) +__bpf_kfunc bool bpf_cpumask_empty(const struct cpumask *cpumask) { return cpumask_empty(cpumask); } @@ -368,7 +371,7 @@ bool bpf_cpumask_empty(const struct cpumask *cpumask) * * A struct bpf_cpumask pointer may be safely passed to @cpumask. */ -bool bpf_cpumask_full(const struct cpumask *cpumask) +__bpf_kfunc bool bpf_cpumask_full(const struct cpumask *cpumask) { return cpumask_full(cpumask); } @@ -380,7 +383,7 @@ bool bpf_cpumask_full(const struct cpumask *cpumask) * * A struct bpf_cpumask pointer may be safely passed to @src. */ -void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) +__bpf_kfunc void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) { cpumask_copy((struct cpumask *)dst, src); } @@ -395,7 +398,7 @@ void bpf_cpumask_copy(struct bpf_cpumask *dst, const struct cpumask *src) * * A struct bpf_cpumask pointer may be safely passed to @src. */ -u32 bpf_cpumask_any(const struct cpumask *cpumask) +__bpf_kfunc u32 bpf_cpumask_any(const struct cpumask *cpumask) { return cpumask_any(cpumask); } @@ -412,7 +415,7 @@ u32 bpf_cpumask_any(const struct cpumask *cpumask) * * struct bpf_cpumask pointers may be safely passed to @src1 and @src2. */ -u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) +__bpf_kfunc u32 bpf_cpumask_any_and(const struct cpumask *src1, const struct cpumask *src2) { return cpumask_any_and(src1, src2); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index d01e4c55b376..2675fefc6cb6 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -474,7 +474,11 @@ static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, { int err; - if (!dev->netdev_ops->ndo_xdp_xmit) + if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return -EOPNOTSUPP; + + if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return -EOPNOTSUPP; err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); @@ -532,8 +536,14 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { - if (!obj || - !obj->dev->netdev_ops->ndo_xdp_xmit) + if (!obj) + return false; + + if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return false; + + if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) return false; if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 458db2db2f81..2dae44581922 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1776,7 +1776,7 @@ __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); -void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) +__bpf_kfunc void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; u64 size = local_type_id__k; @@ -1790,7 +1790,7 @@ void *bpf_obj_new_impl(u64 local_type_id__k, void *meta__ign) return p; } -void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) +__bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) { struct btf_struct_meta *meta = meta__ign; void *p = p__alloc; @@ -1811,12 +1811,12 @@ static void __bpf_list_add(struct bpf_list_node *node, struct bpf_list_head *hea tail ? list_add_tail(n, h) : list_add(n, h); } -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) { return __bpf_list_add(node, head, false); } -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) +__bpf_kfunc void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) { return __bpf_list_add(node, head, true); } @@ -1834,12 +1834,12 @@ static struct bpf_list_node *__bpf_list_del(struct bpf_list_head *head, bool tai return (struct bpf_list_node *)n; } -struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) { return __bpf_list_del(head, false); } -struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) +__bpf_kfunc struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) { return __bpf_list_del(head, true); } @@ -1850,7 +1850,7 @@ struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) * bpf_task_release(). * @p: The task on which a reference is being acquired. */ -struct task_struct *bpf_task_acquire(struct task_struct *p) +__bpf_kfunc struct task_struct *bpf_task_acquire(struct task_struct *p) { return get_task_struct(p); } @@ -1861,7 +1861,7 @@ struct task_struct *bpf_task_acquire(struct task_struct *p) * released by calling bpf_task_release(). * @p: The task on which a reference is being acquired. */ -struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) +__bpf_kfunc struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) { /* For the time being this function returns NULL, as it's not currently * possible to safely acquire a reference to a task with RCU protection @@ -1913,7 +1913,7 @@ struct task_struct *bpf_task_acquire_not_zero(struct task_struct *p) * be released by calling bpf_task_release(). * @pp: A pointer to a task kptr on which a reference is being acquired. */ -struct task_struct *bpf_task_kptr_get(struct task_struct **pp) +__bpf_kfunc struct task_struct *bpf_task_kptr_get(struct task_struct **pp) { /* We must return NULL here until we have clarity on how to properly * leverage RCU for ensuring a task's lifetime. See the comment above @@ -1926,7 +1926,7 @@ struct task_struct *bpf_task_kptr_get(struct task_struct **pp) * bpf_task_release - Release the reference acquired on a task. * @p: The task on which a reference is being released. */ -void bpf_task_release(struct task_struct *p) +__bpf_kfunc void bpf_task_release(struct task_struct *p) { if (!p) return; @@ -1941,7 +1941,7 @@ void bpf_task_release(struct task_struct *p) * calling bpf_cgroup_release(). * @cgrp: The cgroup on which a reference is being acquired. */ -struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) +__bpf_kfunc struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) { cgroup_get(cgrp); return cgrp; @@ -1953,7 +1953,7 @@ struct cgroup *bpf_cgroup_acquire(struct cgroup *cgrp) * be released by calling bpf_cgroup_release(). * @cgrpp: A pointer to a cgroup kptr on which a reference is being acquired. */ -struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) +__bpf_kfunc struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) { struct cgroup *cgrp; @@ -1985,7 +1985,7 @@ struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) * drops to 0. * @cgrp: The cgroup on which a reference is being released. */ -void bpf_cgroup_release(struct cgroup *cgrp) +__bpf_kfunc void bpf_cgroup_release(struct cgroup *cgrp) { if (!cgrp) return; @@ -2000,7 +2000,7 @@ void bpf_cgroup_release(struct cgroup *cgrp) * @cgrp: The cgroup for which we're performing a lookup. * @level: The level of ancestor to look up. */ -struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) +__bpf_kfunc struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) { struct cgroup *ancestor; @@ -2019,7 +2019,7 @@ struct cgroup *bpf_cgroup_ancestor(struct cgroup *cgrp, int level) * stored in a map, or released with bpf_task_release(). * @pid: The pid of the task being looked up. */ -struct task_struct *bpf_task_from_pid(s32 pid) +__bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid) { struct task_struct *p; @@ -2032,22 +2032,22 @@ struct task_struct *bpf_task_from_pid(s32 pid) return p; } -void *bpf_cast_to_kern_ctx(void *obj) +__bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) { return obj; } -void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) +__bpf_kfunc void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) { return obj__ign; } -void bpf_rcu_read_lock(void) +__bpf_kfunc void bpf_rcu_read_lock(void) { rcu_read_lock(); } -void bpf_rcu_read_unlock(void) +__bpf_kfunc void bpf_rcu_read_unlock(void) { rcu_read_unlock(); } diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 88aae38fde66..0c85e06f7ea7 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -136,7 +136,7 @@ static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) { WARN_ON(bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_FREE)); /* Make sure BPF_MAP_GET_NEXT_ID can't find this dead map */ - bpf_map_free_id(&offmap->map, true); + bpf_map_free_id(&offmap->map); list_del_init(&offmap->offloads); offmap->netdev = NULL; } diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c index 5106b5372f0c..b56f9f3314fd 100644 --- a/kernel/bpf/preload/bpf_preload_kern.c +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -3,7 +3,11 @@ #include <linux/init.h> #include <linux/module.h> #include "bpf_preload.h" -#include "iterators/iterators.lskel.h" +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#include "iterators/iterators.lskel-little-endian.h" +#else +#include "iterators/iterators.lskel-big-endian.h" +#endif static struct bpf_link *maps_link, *progs_link; static struct iterators_bpf *skel; diff --git a/kernel/bpf/preload/iterators/Makefile b/kernel/bpf/preload/iterators/Makefile index 6762b1260f2f..8937dc6bc8d0 100644 --- a/kernel/bpf/preload/iterators/Makefile +++ b/kernel/bpf/preload/iterators/Makefile @@ -35,20 +35,22 @@ endif .PHONY: all clean -all: iterators.lskel.h +all: iterators.lskel-little-endian.h + +big: iterators.lskel-big-endian.h clean: $(call msg,CLEAN) $(Q)rm -rf $(OUTPUT) iterators -iterators.lskel.h: $(OUTPUT)/iterators.bpf.o | $(BPFTOOL) +iterators.lskel-%.h: $(OUTPUT)/%/iterators.bpf.o | $(BPFTOOL) $(call msg,GEN-SKEL,$@) $(Q)$(BPFTOOL) gen skeleton -L $< > $@ - -$(OUTPUT)/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) +$(OUTPUT)/%/iterators.bpf.o: iterators.bpf.c $(BPFOBJ) | $(OUTPUT) $(call msg,BPF,$@) - $(Q)$(CLANG) -g -O2 -target bpf $(INCLUDES) \ + $(Q)mkdir -p $(@D) + $(Q)$(CLANG) -g -O2 -target bpf -m$* $(INCLUDES) \ -c $(filter %.c,$^) -o $@ && \ $(LLVM_STRIP) -g $@ diff --git a/kernel/bpf/preload/iterators/README b/kernel/bpf/preload/iterators/README index 7fd6d39a9ad2..98e7c90ea012 100644 --- a/kernel/bpf/preload/iterators/README +++ b/kernel/bpf/preload/iterators/README @@ -1,4 +1,7 @@ WARNING: -If you change "iterators.bpf.c" do "make -j" in this directory to rebuild "iterators.skel.h". +If you change "iterators.bpf.c" do "make -j" in this directory to +rebuild "iterators.lskel-little-endian.h". Then, on a big-endian +machine, do "make -j big" in this directory to rebuild +"iterators.lskel-big-endian.h". Commit both resulting headers. Make sure to have clang 10 installed. See Documentation/bpf/bpf_devel_QA.rst diff --git a/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h new file mode 100644 index 000000000000..ebdc6c0cdb70 --- /dev/null +++ b/kernel/bpf/preload/iterators/iterators.lskel-big-endian.h @@ -0,0 +1,419 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* THIS FILE IS AUTOGENERATED BY BPFTOOL! */ +#ifndef __ITERATORS_BPF_SKEL_H__ +#define __ITERATORS_BPF_SKEL_H__ + +#include <bpf/skel_internal.h> + +struct iterators_bpf { + struct bpf_loader_ctx ctx; + struct { + struct bpf_map_desc rodata; + } maps; + struct { + struct bpf_prog_desc dump_bpf_map; + struct bpf_prog_desc dump_bpf_prog; + } progs; + struct { + int dump_bpf_map_fd; + int dump_bpf_prog_fd; + } links; +}; + +static inline int +iterators_bpf__dump_bpf_map__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_map.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_map_fd = fd; + return fd; +} + +static inline int +iterators_bpf__dump_bpf_prog__attach(struct iterators_bpf *skel) +{ + int prog_fd = skel->progs.dump_bpf_prog.prog_fd; + int fd = skel_link_create(prog_fd, 0, BPF_TRACE_ITER); + + if (fd > 0) + skel->links.dump_bpf_prog_fd = fd; + return fd; +} + +static inline int +iterators_bpf__attach(struct iterators_bpf *skel) +{ + int ret = 0; + + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_map__attach(skel); + ret = ret < 0 ? ret : iterators_bpf__dump_bpf_prog__attach(skel); + return ret < 0 ? ret : 0; +} + +static inline void +iterators_bpf__detach(struct iterators_bpf *skel) +{ + skel_closenz(skel->links.dump_bpf_map_fd); + skel_closenz(skel->links.dump_bpf_prog_fd); +} +static void +iterators_bpf__destroy(struct iterators_bpf *skel) +{ + if (!skel) + return; + iterators_bpf__detach(skel); + skel_closenz(skel->progs.dump_bpf_map.prog_fd); + skel_closenz(skel->progs.dump_bpf_prog.prog_fd); + skel_closenz(skel->maps.rodata.map_fd); + skel_free(skel); +} +static inline struct iterators_bpf * +iterators_bpf__open(void) +{ + struct iterators_bpf *skel; + + skel = skel_alloc(sizeof(*skel)); + if (!skel) + goto cleanup; + skel->ctx.sz = (void *)&skel->links - (void *)skel; + return skel; +cleanup: + iterators_bpf__destroy(skel); + return NULL; +} + +static inline int +iterators_bpf__load(struct iterators_bpf *skel) +{ + struct bpf_load_and_run_opts opts = {}; + int err; + + opts.ctx = (struct bpf_loader_ctx *)skel; + opts.data_sz = 6008; + opts.data = (void *)"\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xeb\x9f\x01\0\ +\0\0\0\x18\0\0\0\0\0\0\x04\x1c\0\0\x04\x1c\0\0\x05\x18\0\0\0\0\x02\0\0\0\0\0\0\ +\x02\0\0\0\x01\x04\0\0\x02\0\0\0\x10\0\0\0\x13\0\0\0\x03\0\0\0\0\0\0\0\x18\0\0\ +\0\x04\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x08\0\0\0\0\x02\0\0\0\0\0\0\x0d\0\0\0\ +\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x01\0\0\0\x20\x01\0\0\0\0\0\0\x04\x01\ +\0\0\x20\0\0\0\x24\x0c\0\0\x01\0\0\0\x05\0\0\0\xc2\x04\0\0\x03\0\0\0\x18\0\0\0\ +\xd0\0\0\0\x09\0\0\0\0\0\0\0\xd4\0\0\0\x0b\0\0\0\x40\0\0\0\xdf\0\0\0\x0b\0\0\0\ +\x80\0\0\0\0\x02\0\0\0\0\0\0\x0a\0\0\0\xe7\x07\0\0\0\0\0\0\0\0\0\0\xf0\x08\0\0\ +\0\0\0\0\x0c\0\0\0\xf6\x01\0\0\0\0\0\0\x08\0\0\0\x40\0\0\x01\xb3\x04\0\0\x03\0\ +\0\0\x18\0\0\x01\xbb\0\0\0\x0e\0\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x01\ +\xc3\0\0\0\x0e\0\0\0\xa0\0\0\x01\xcf\x08\0\0\0\0\0\0\x0f\0\0\x01\xd5\x01\0\0\0\ +\0\0\0\x04\0\0\0\x20\0\0\x01\xe2\x01\0\0\0\0\0\0\x01\x01\0\0\x08\0\0\0\0\x03\0\ +\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x10\0\0\x01\xe7\x01\0\0\0\0\0\0\x04\0\0\ +\0\x20\0\0\0\0\x02\0\0\0\0\0\0\x14\0\0\x02\x4b\x04\0\0\x02\0\0\0\x10\0\0\0\x13\ +\0\0\0\x03\0\0\0\0\0\0\x02\x5e\0\0\0\x15\0\0\0\x40\0\0\0\0\x02\0\0\0\0\0\0\x18\ +\0\0\0\0\x0d\0\0\x01\0\0\0\x06\0\0\0\x1c\0\0\0\x13\0\0\x02\x63\x0c\0\0\x01\0\0\ +\0\x16\0\0\x02\xaf\x04\0\0\x01\0\0\0\x08\0\0\x02\xb8\0\0\0\x19\0\0\0\0\0\0\0\0\ +\x02\0\0\0\0\0\0\x1a\0\0\x03\x09\x04\0\0\x06\0\0\0\x38\0\0\x01\xbb\0\0\0\x0e\0\ +\0\0\0\0\0\x01\xbe\0\0\0\x11\0\0\0\x20\0\0\x03\x16\0\0\0\x1b\0\0\0\xc0\0\0\x03\ +\x27\0\0\0\x15\0\0\x01\0\0\0\x03\x30\0\0\0\x1d\0\0\x01\x40\0\0\x03\x3a\0\0\0\ +\x1e\0\0\x01\x80\0\0\0\0\x02\0\0\0\0\0\0\x1c\0\0\0\0\x0a\0\0\0\0\0\0\x10\0\0\0\ +\0\x02\0\0\0\0\0\0\x1f\0\0\0\0\x02\0\0\0\0\0\0\x20\0\0\x03\x84\x04\0\0\x02\0\0\ +\0\x08\0\0\x03\x92\0\0\0\x0e\0\0\0\0\0\0\x03\x9b\0\0\0\x0e\0\0\0\x20\0\0\x03\ +\x3a\x04\0\0\x03\0\0\0\x18\0\0\x03\xa5\0\0\0\x1b\0\0\0\0\0\0\x03\xad\0\0\0\x21\ +\0\0\0\x40\0\0\x03\xb3\0\0\0\x23\0\0\0\x80\0\0\0\0\x02\0\0\0\0\0\0\x22\0\0\0\0\ +\x02\0\0\0\0\0\0\x24\0\0\x03\xb7\x04\0\0\x01\0\0\0\x04\0\0\x03\xc2\0\0\0\x0e\0\ +\0\0\0\0\0\x04\x2b\x04\0\0\x01\0\0\0\x04\0\0\x04\x34\0\0\0\x0e\0\0\0\0\0\0\0\0\ +\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x23\0\0\x04\xaa\x0e\0\0\0\0\0\0\ +\x25\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\0\0\0\x0e\0\0\x04\ +\xbe\x0e\0\0\0\0\0\0\x27\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\x12\ +\0\0\0\x20\0\0\x04\xd4\x0e\0\0\0\0\0\0\x29\0\0\0\0\0\0\0\0\x03\0\0\0\0\0\0\0\0\ +\0\0\x1c\0\0\0\x12\0\0\0\x11\0\0\x04\xe9\x0e\0\0\0\0\0\0\x2b\0\0\0\0\0\0\0\0\ +\x03\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\x12\0\0\0\x04\0\0\x05\0\x0e\0\0\0\0\0\0\x2d\ +\0\0\0\x01\0\0\x05\x08\x0f\0\0\x04\0\0\0\x62\0\0\0\x26\0\0\0\0\0\0\0\x23\0\0\0\ +\x28\0\0\0\x23\0\0\0\x0e\0\0\0\x2a\0\0\0\x31\0\0\0\x20\0\0\0\x2c\0\0\0\x51\0\0\ +\0\x11\0\0\x05\x10\x0f\0\0\x01\0\0\0\x04\0\0\0\x2e\0\0\0\0\0\0\0\x04\0\x62\x70\ +\x66\x5f\x69\x74\x65\x72\x5f\x5f\x62\x70\x66\x5f\x6d\x61\x70\0\x6d\x65\x74\x61\ +\0\x6d\x61\x70\0\x63\x74\x78\0\x69\x6e\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\ +\x5f\x6d\x61\x70\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x6d\x61\x70\0\x30\x3a\ +\x30\0\x2f\x68\x6f\x6d\x65\x2f\x69\x69\x69\x2f\x6c\x69\x6e\x75\x78\x2d\x6b\x65\ +\x72\x6e\x65\x6c\x2d\x74\x6f\x6f\x6c\x63\x68\x61\x69\x6e\x2f\x73\x72\x63\x2f\ +\x6c\x69\x6e\x75\x78\x2f\x6b\x65\x72\x6e\x65\x6c\x2f\x62\x70\x66\x2f\x70\x72\ +\x65\x6c\x6f\x61\x64\x2f\x69\x74\x65\x72\x61\x74\x6f\x72\x73\x2f\x69\x74\x65\ +\x72\x61\x74\x6f\x72\x73\x2e\x62\x70\x66\x2e\x63\0\x09\x73\x74\x72\x75\x63\x74\ +\x20\x73\x65\x71\x5f\x66\x69\x6c\x65\x20\x2a\x73\x65\x71\x20\x3d\x20\x63\x74\ +\x78\x2d\x3e\x6d\x65\x74\x61\x2d\x3e\x73\x65\x71\x3b\0\x62\x70\x66\x5f\x69\x74\ +\x65\x72\x5f\x6d\x65\x74\x61\0\x73\x65\x71\0\x73\x65\x73\x73\x69\x6f\x6e\x5f\ +\x69\x64\0\x73\x65\x71\x5f\x6e\x75\x6d\0\x73\x65\x71\x5f\x66\x69\x6c\x65\0\x5f\ +\x5f\x75\x36\x34\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x6c\x6f\x6e\x67\x20\x6c\ +\x6f\x6e\x67\0\x30\x3a\x31\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\ +\x6d\x61\x70\x20\x2a\x6d\x61\x70\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\x61\x70\ +\x3b\0\x09\x69\x66\x20\x28\x21\x6d\x61\x70\x29\0\x30\x3a\x32\0\x09\x5f\x5f\x75\ +\x36\x34\x20\x73\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x20\x63\x74\x78\x2d\x3e\x6d\ +\x65\x74\x61\x2d\x3e\x73\x65\x71\x5f\x6e\x75\x6d\x3b\0\x09\x69\x66\x20\x28\x73\ +\x65\x71\x5f\x6e\x75\x6d\x20\x3d\x3d\x20\x30\x29\0\x09\x09\x42\x50\x46\x5f\x53\ +\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x20\x20\x69\ +\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x5c\x6e\x22\x29\x3b\0\x62\x70\x66\ +\x5f\x6d\x61\x70\0\x69\x64\0\x6e\x61\x6d\x65\0\x6d\x61\x78\x5f\x65\x6e\x74\x72\ +\x69\x65\x73\0\x5f\x5f\x75\x33\x32\0\x75\x6e\x73\x69\x67\x6e\x65\x64\x20\x69\ +\x6e\x74\0\x63\x68\x61\x72\0\x5f\x5f\x41\x52\x52\x41\x59\x5f\x53\x49\x5a\x45\ +\x5f\x54\x59\x50\x45\x5f\x5f\0\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\ +\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\x75\x20\x25\x2d\x31\x36\x73\ +\x25\x36\x64\x5c\x6e\x22\x2c\x20\x6d\x61\x70\x2d\x3e\x69\x64\x2c\x20\x6d\x61\ +\x70\x2d\x3e\x6e\x61\x6d\x65\x2c\x20\x6d\x61\x70\x2d\x3e\x6d\x61\x78\x5f\x65\ +\x6e\x74\x72\x69\x65\x73\x29\x3b\0\x7d\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\ +\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x70\x72\x6f\x67\0\x64\x75\x6d\x70\x5f\ +\x62\x70\x66\x5f\x70\x72\x6f\x67\0\x69\x74\x65\x72\x2f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\0\x09\x73\x74\x72\x75\x63\x74\x20\x62\x70\x66\x5f\x70\x72\x6f\x67\x20\ +\x2a\x70\x72\x6f\x67\x20\x3d\x20\x63\x74\x78\x2d\x3e\x70\x72\x6f\x67\x3b\0\x09\ +\x69\x66\x20\x28\x21\x70\x72\x6f\x67\x29\0\x62\x70\x66\x5f\x70\x72\x6f\x67\0\ +\x61\x75\x78\0\x09\x61\x75\x78\x20\x3d\x20\x70\x72\x6f\x67\x2d\x3e\x61\x75\x78\ +\x3b\0\x09\x09\x42\x50\x46\x5f\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\ +\x65\x71\x2c\x20\x22\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\x5c\x6e\x22\ +\x29\x3b\0\x62\x70\x66\x5f\x70\x72\x6f\x67\x5f\x61\x75\x78\0\x61\x74\x74\x61\ +\x63\x68\x5f\x66\x75\x6e\x63\x5f\x6e\x61\x6d\x65\0\x64\x73\x74\x5f\x70\x72\x6f\ +\x67\0\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\x62\x74\x66\0\x09\x42\x50\x46\x5f\ +\x53\x45\x51\x5f\x50\x52\x49\x4e\x54\x46\x28\x73\x65\x71\x2c\x20\x22\x25\x34\ +\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x5c\x6e\x22\x2c\x20\x61\ +\x75\x78\x2d\x3e\x69\x64\x2c\0\x30\x3a\x34\0\x30\x3a\x35\0\x09\x69\x66\x20\x28\ +\x21\x62\x74\x66\x29\0\x62\x70\x66\x5f\x66\x75\x6e\x63\x5f\x69\x6e\x66\x6f\0\ +\x69\x6e\x73\x6e\x5f\x6f\x66\x66\0\x74\x79\x70\x65\x5f\x69\x64\0\x30\0\x73\x74\ +\x72\x69\x6e\x67\x73\0\x74\x79\x70\x65\x73\0\x68\x64\x72\0\x62\x74\x66\x5f\x68\ +\x65\x61\x64\x65\x72\0\x73\x74\x72\x5f\x6c\x65\x6e\0\x09\x74\x79\x70\x65\x73\ +\x20\x3d\x20\x62\x74\x66\x2d\x3e\x74\x79\x70\x65\x73\x3b\0\x09\x62\x70\x66\x5f\ +\x70\x72\x6f\x62\x65\x5f\x72\x65\x61\x64\x5f\x6b\x65\x72\x6e\x65\x6c\x28\x26\ +\x74\x2c\x20\x73\x69\x7a\x65\x6f\x66\x28\x74\x29\x2c\x20\x74\x79\x70\x65\x73\ +\x20\x2b\x20\x62\x74\x66\x5f\x69\x64\x29\x3b\0\x09\x73\x74\x72\x20\x3d\x20\x62\ +\x74\x66\x2d\x3e\x73\x74\x72\x69\x6e\x67\x73\x3b\0\x62\x74\x66\x5f\x74\x79\x70\ +\x65\0\x6e\x61\x6d\x65\x5f\x6f\x66\x66\0\x09\x6e\x61\x6d\x65\x5f\x6f\x66\x66\ +\x20\x3d\x20\x42\x50\x46\x5f\x43\x4f\x52\x45\x5f\x52\x45\x41\x44\x28\x74\x2c\ +\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x29\x3b\0\x30\x3a\x32\x3a\x30\0\x09\x69\ +\x66\x20\x28\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x20\x3e\x3d\x20\x62\x74\x66\x2d\ +\x3e\x68\x64\x72\x2e\x73\x74\x72\x5f\x6c\x65\x6e\x29\0\x09\x72\x65\x74\x75\x72\ +\x6e\x20\x73\x74\x72\x20\x2b\x20\x6e\x61\x6d\x65\x5f\x6f\x66\x66\x3b\0\x30\x3a\ +\x33\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\ +\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x6d\x61\x70\x2e\x5f\x5f\x5f\x66\x6d\ +\x74\x2e\x31\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\x5f\ +\x5f\x66\x6d\x74\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\x6f\x67\x2e\x5f\ +\x5f\x5f\x66\x6d\x74\x2e\x32\0\x4c\x49\x43\x45\x4e\x53\x45\0\x2e\x72\x6f\x64\ +\x61\x74\x61\0\x6c\x69\x63\x65\x6e\x73\x65\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x09\x4c\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x02\0\0\0\x04\0\0\0\x62\0\0\0\ +\x01\0\0\0\x80\0\0\0\0\0\0\0\0\x69\x74\x65\x72\x61\x74\x6f\x72\x2e\x72\x6f\x64\ +\x61\x74\x61\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x2f\0\0\0\0\0\0\0\0\0\0\0\0\x20\ +\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\ +\x20\x20\x6d\x61\x78\x5f\x65\x6e\x74\x72\x69\x65\x73\x0a\0\x25\x34\x75\x20\x25\ +\x2d\x31\x36\x73\x25\x36\x64\x0a\0\x20\x20\x69\x64\x20\x6e\x61\x6d\x65\x20\x20\ +\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x20\x61\x74\x74\x61\x63\x68\x65\x64\ +\x0a\0\x25\x34\x75\x20\x25\x2d\x31\x36\x73\x20\x25\x73\x20\x25\x73\x0a\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x21\0\0\0\0\0\0\x79\x62\0\0\ +\0\0\0\0\x79\x71\0\x08\0\0\0\0\x15\x70\0\x1a\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\ +\x10\0\x08\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xe8\xbf\x16\0\0\ +\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\0\xb7\x30\0\0\0\0\0\x23\xb7\x50\0\0\ +\0\0\0\0\x85\0\0\0\0\0\0\x7e\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xe8\0\0\0\0\xb7\ +\x10\0\0\0\0\0\x04\xbf\x27\0\0\0\0\0\0\x0f\x21\0\0\0\0\0\0\x7b\xa2\xff\xf0\0\0\ +\0\0\x61\x17\0\x14\0\0\0\0\x7b\xa1\xff\xf8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\ +\0\0\xff\xff\xff\xe8\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x23\ +\xb7\x30\0\0\0\0\0\x0e\xb7\x50\0\0\0\0\0\x18\x85\0\0\0\0\0\0\x7e\xb7\0\0\0\0\0\ +\0\0\x95\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x07\0\0\0\0\0\0\0\x42\0\0\0\x9a\0\x01\x3c\ +\x1e\0\0\0\x01\0\0\0\x42\0\0\0\x9a\0\x01\x3c\x24\0\0\0\x02\0\0\0\x42\0\0\x01\ +\x0d\0\x01\x44\x1d\0\0\0\x03\0\0\0\x42\0\0\x01\x2e\0\x01\x4c\x06\0\0\0\x04\0\0\ +\0\x42\0\0\x01\x3d\0\x01\x40\x1d\0\0\0\x05\0\0\0\x42\0\0\x01\x62\0\x01\x58\x06\ +\0\0\0\x07\0\0\0\x42\0\0\x01\x75\0\x01\x5c\x03\0\0\0\x0e\0\0\0\x42\0\0\x01\xfb\ +\0\x01\x64\x02\0\0\0\x1e\0\0\0\x42\0\0\x02\x49\0\x01\x6c\x01\0\0\0\0\0\0\0\x02\ +\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\x10\0\0\0\x02\0\ +\0\x01\x09\0\0\0\0\0\0\0\x20\0\0\0\x08\0\0\x01\x39\0\0\0\0\0\0\0\x70\0\0\0\x0d\ +\0\0\0\x3e\0\0\0\0\0\0\0\x80\0\0\0\x0d\0\0\x01\x09\0\0\0\0\0\0\0\xa0\0\0\0\x0d\ +\0\0\x01\x39\0\0\0\0\0\0\0\x1a\0\0\0\x20\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\ +\x6d\x61\x70\0\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\ +\x01\0\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x09\0\0\0\x01\0\0\0\0\0\0\0\x07\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\ +\x62\x70\x66\x5f\x6d\x61\x70\0\0\0\0\0\0\0\0\x47\x50\x4c\0\0\0\0\0\x79\x21\0\0\ +\0\0\0\0\x79\x62\0\0\0\0\0\0\x79\x11\0\x08\0\0\0\0\x15\x10\0\x3b\0\0\0\0\x79\ +\x71\0\0\0\0\0\0\x79\x12\0\x10\0\0\0\0\x55\x10\0\x08\0\0\0\0\xbf\x4a\0\0\0\0\0\ +\0\x07\x40\0\0\xff\xff\xff\xd0\xbf\x16\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\x31\xb7\x30\0\0\0\0\0\x20\xb7\x50\0\0\0\0\0\0\x85\0\0\0\0\0\0\x7e\x7b\ +\xa6\xff\xc8\0\0\0\0\x61\x17\0\0\0\0\0\0\x7b\xa1\xff\xd0\0\0\0\0\xb7\x30\0\0\0\ +\0\0\x04\xbf\x97\0\0\0\0\0\0\x0f\x93\0\0\0\0\0\0\x79\x17\0\x28\0\0\0\0\x79\x87\ +\0\x30\0\0\0\0\x15\x80\0\x18\0\0\0\0\xb7\x20\0\0\0\0\0\0\x0f\x12\0\0\0\0\0\0\ +\x61\x11\0\x04\0\0\0\0\x79\x38\0\x08\0\0\0\0\x67\x10\0\0\0\0\0\x03\x0f\x31\0\0\ +\0\0\0\0\x79\x68\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf8\ +\xb7\x20\0\0\0\0\0\x08\x85\0\0\0\0\0\0\x71\xb7\x10\0\0\0\0\0\0\x79\x3a\xff\xf8\ +\0\0\0\0\x0f\x31\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\xf4\ +\xb7\x20\0\0\0\0\0\x04\x85\0\0\0\0\0\0\x71\xb7\x30\0\0\0\0\0\x04\x61\x1a\xff\ +\xf4\0\0\0\0\x61\x28\0\x10\0\0\0\0\x3d\x12\0\x02\0\0\0\0\x0f\x61\0\0\0\0\0\0\ +\xbf\x96\0\0\0\0\0\0\x7b\xa9\xff\xd8\0\0\0\0\x79\x17\0\x18\0\0\0\0\x7b\xa1\xff\ +\xe0\0\0\0\0\x79\x17\0\x20\0\0\0\0\x79\x11\0\0\0\0\0\0\x0f\x13\0\0\0\0\0\0\x7b\ +\xa1\xff\xe8\0\0\0\0\xbf\x4a\0\0\0\0\0\0\x07\x40\0\0\xff\xff\xff\xd0\x79\x1a\ +\xff\xc8\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\0\x51\xb7\x30\0\0\0\0\0\x11\ +\xb7\x50\0\0\0\0\0\x20\x85\0\0\0\0\0\0\x7e\xb7\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\0\0\0\0\0\0\0\x42\0\0\0\x9a\0\x01\x80\x1e\0\0\0\x01\0\0\0\ +\x42\0\0\0\x9a\0\x01\x80\x24\0\0\0\x02\0\0\0\x42\0\0\x02\x7f\0\x01\x88\x1f\0\0\ +\0\x03\0\0\0\x42\0\0\x02\xa3\0\x01\x94\x06\0\0\0\x04\0\0\0\x42\0\0\x02\xbc\0\ +\x01\xa0\x0e\0\0\0\x05\0\0\0\x42\0\0\x01\x3d\0\x01\x84\x1d\0\0\0\x06\0\0\0\x42\ +\0\0\x01\x62\0\x01\xa4\x06\0\0\0\x08\0\0\0\x42\0\0\x02\xce\0\x01\xa8\x03\0\0\0\ +\x10\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x17\0\0\0\x42\0\0\x03\x79\0\x01\ +\x04\x06\0\0\0\x1a\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x1b\0\0\0\x42\0\0\ +\x03\xca\0\x01\x10\x0f\0\0\0\x1c\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x2d\0\0\0\x1e\ +\0\0\0\x42\0\0\x04\x16\0\x01\x0c\x0d\0\0\0\x20\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\ +\x02\0\0\0\x21\0\0\0\x42\0\0\x03\xdf\0\x01\x14\x02\0\0\0\x24\0\0\0\x42\0\0\x04\ +\x3d\0\x01\x18\x0d\0\0\0\x27\0\0\0\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x28\0\0\ +\0\x42\0\0\x04\x3d\0\x01\x18\x0d\0\0\0\x2b\0\0\0\x42\0\0\x04\x3d\0\x01\x18\x0d\ +\0\0\0\x2c\0\0\0\x42\0\0\x04\x6b\0\x01\x1c\x1b\0\0\0\x2d\0\0\0\x42\0\0\x04\x6b\ +\0\x01\x1c\x06\0\0\0\x2e\0\0\0\x42\0\0\x04\x8e\0\x01\x24\x0d\0\0\0\x30\0\0\0\ +\x42\0\0\x03\x3e\0\x01\xb0\x02\0\0\0\x3f\0\0\0\x42\0\0\x02\x49\0\x01\xc0\x01\0\ +\0\0\0\0\0\0\x14\0\0\0\x3e\0\0\0\0\0\0\0\x08\0\0\0\x08\0\0\0\x3e\0\0\0\0\0\0\0\ +\x10\0\0\0\x14\0\0\x01\x09\0\0\0\0\0\0\0\x20\0\0\0\x18\0\0\0\x3e\0\0\0\0\0\0\0\ +\x28\0\0\0\x08\0\0\x01\x39\0\0\0\0\0\0\0\x80\0\0\0\x1a\0\0\0\x3e\0\0\0\0\0\0\0\ +\x90\0\0\0\x1a\0\0\x01\x09\0\0\0\0\0\0\0\xa8\0\0\0\x1a\0\0\x03\x71\0\0\0\0\0\0\ +\0\xb0\0\0\0\x1a\0\0\x03\x75\0\0\0\0\0\0\0\xc0\0\0\0\x1f\0\0\x03\xa3\0\0\0\0\0\ +\0\0\xd8\0\0\0\x20\0\0\x01\x09\0\0\0\0\0\0\0\xf0\0\0\0\x20\0\0\0\x3e\0\0\0\0\0\ +\0\x01\x18\0\0\0\x24\0\0\0\x3e\0\0\0\0\0\0\x01\x50\0\0\0\x1a\0\0\x01\x09\0\0\0\ +\0\0\0\x01\x60\0\0\0\x20\0\0\x04\x65\0\0\0\0\0\0\x01\x88\0\0\0\x1a\0\0\x01\x39\ +\0\0\0\0\0\0\x01\x98\0\0\0\x1a\0\0\x04\xa6\0\0\0\0\0\0\x01\xa0\0\0\0\x18\0\0\0\ +\x3e\0\0\0\0\0\0\0\x1a\0\0\0\x41\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x64\x75\x6d\x70\x5f\x62\x70\x66\x5f\x70\x72\ +\x6f\x67\0\0\0\0\0\0\0\0\0\0\x1c\0\0\0\0\0\0\0\x08\0\0\0\0\0\0\0\0\0\0\0\x01\0\ +\0\0\x10\0\0\0\0\0\0\0\0\0\0\0\x19\0\0\0\x01\0\0\0\0\0\0\0\x12\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x10\0\0\0\0\x62\x70\x66\x5f\x69\x74\x65\x72\x5f\x62\x70\ +\x66\x5f\x70\x72\x6f\x67\0\0\0\0\0\0\0"; + opts.insns_sz = 2216; + opts.insns = (void *)"\ +\xbf\x61\0\0\0\0\0\0\xbf\x1a\0\0\0\0\0\0\x07\x10\0\0\xff\xff\xff\x78\xb7\x20\0\ +\0\0\0\0\x88\xb7\x30\0\0\0\0\0\0\x85\0\0\0\0\0\0\x71\x05\0\0\x14\0\0\0\0\x61\ +\x1a\xff\x78\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x7c\ +\0\0\0\0\xd5\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x80\0\0\0\0\xd5\ +\x10\0\x01\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x1a\xff\x84\0\0\0\0\xd5\x10\0\x01\0\ +\0\0\0\x85\0\0\0\0\0\0\xa8\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x10\0\0\0\0\ +\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xbf\x07\0\0\ +\0\0\0\0\x95\0\0\0\0\0\0\0\x61\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0e\x68\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\ +\0\0\0\x0e\x64\x63\x10\0\0\0\0\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0e\x58\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x05\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0e\x50\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x12\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0e\x50\xb7\x30\0\0\0\0\0\x1c\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\xd4\0\0\0\0\x63\xa7\xff\x78\0\0\0\0\ +\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xa0\x63\x10\0\0\0\ +\0\0\0\x61\x06\0\x1c\0\0\0\0\x15\0\0\x03\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\ +\0\x0e\x7c\x63\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\0\ +\0\0\x0e\x70\xb7\x30\0\0\0\0\0\x48\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\ +\x70\xff\xc3\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x63\x17\0\0\0\0\0\0\ +\x79\x36\0\x20\0\0\0\0\x15\x30\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x0e\xb8\xb7\x20\0\0\0\0\0\x62\x61\x06\0\x04\0\0\0\0\x45\0\0\x02\0\0\0\x01\x85\ +\0\0\0\0\0\0\x94\x05\0\0\x01\0\0\0\0\x85\0\0\0\0\0\0\x71\x18\x26\0\0\0\0\0\0\0\ +\0\0\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x28\x63\ +\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x20\x18\x16\0\0\0\0\0\0\0\ +\0\0\0\0\0\x0f\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0e\xb8\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x38\x7b\x10\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\ +\x02\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x28\xb7\x30\0\0\0\0\0\x20\x85\0\0\0\0\ +\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x9f\0\0\0\0\x18\x26\0\0\0\0\0\0\0\0\0\ +\0\0\0\0\0\x61\x02\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x48\x63\x10\ +\0\0\0\0\0\0\xb7\x10\0\0\0\0\0\x16\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x48\xb7\ +\x30\0\0\0\0\0\x04\x85\0\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\xc5\x70\xff\x92\0\0\ +\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x50\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\ +\x11\x70\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x0f\x58\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x11\x68\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x10\x58\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xb0\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\x60\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xc0\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x10\xf0\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x11\xe0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\0\0\ +\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xd8\x7b\x10\0\0\0\0\0\0\x61\x06\0\x08\0\0\ +\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x78\x63\x10\0\0\0\0\0\0\x61\x06\0\x0c\ +\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x7c\x63\x10\0\0\0\0\0\0\x79\x06\0\ +\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\x80\x7b\x10\0\0\0\0\0\0\x61\ +\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xa8\x63\x10\0\0\0\0\0\ +\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x11\xf0\xb7\x20\0\0\0\0\0\x11\xb7\x30\0\0\0\ +\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\0\0\0\0\0\0\xc5\x70\ +\xff\x5c\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x11\x60\x63\x07\0\x6c\0\0\0\0\ +\x77\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\xb7\x10\0\0\0\0\0\x05\x18\x26\0\0\ +\0\0\0\0\0\0\0\0\0\0\x11\x60\xb7\x30\0\0\0\0\0\x8c\x85\0\0\0\0\0\0\xa6\xbf\x70\ +\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x11\xd0\x61\x10\0\0\0\0\0\0\xd5\ +\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\xc5\x70\xff\x4a\0\0\ +\0\0\x63\xa7\xff\x80\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x12\x08\x18\x16\0\ +\0\0\0\0\0\0\0\0\0\0\0\x16\xe0\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\ +\0\0\x12\x10\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd8\x7b\x10\0\0\0\0\0\0\x18\ +\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x18\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x20\ +\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x14\x20\x18\x16\0\0\0\0\0\ +\0\0\0\0\0\0\0\x17\x30\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x15\ +\xb0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x50\x7b\x10\0\0\0\0\0\0\x18\x06\0\0\0\ +\0\0\0\0\0\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x48\x7b\x10\0\0\0\0\ +\0\0\x61\x06\0\x08\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xe8\x63\x10\0\0\ +\0\0\0\0\x61\x06\0\x0c\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xec\x63\x10\ +\0\0\0\0\0\0\x79\x06\0\x10\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x16\xf0\x7b\ +\x10\0\0\0\0\0\0\x61\x0a\xff\x78\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\ +\x18\x63\x10\0\0\0\0\0\0\x18\x16\0\0\0\0\0\0\0\0\0\0\0\0\x17\x60\xb7\x20\0\0\0\ +\0\0\x12\xb7\x30\0\0\0\0\0\x0c\xb7\x40\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa7\xbf\x70\ +\0\0\0\0\0\0\xc5\x70\xff\x13\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd0\ +\x63\x07\0\x6c\0\0\0\0\x77\x70\0\0\0\0\0\x20\x63\x07\0\x70\0\0\0\0\xb7\x10\0\0\ +\0\0\0\x05\x18\x26\0\0\0\0\0\0\0\0\0\0\0\0\x16\xd0\xb7\x30\0\0\0\0\0\x8c\x85\0\ +\0\0\0\0\0\xa6\xbf\x70\0\0\0\0\0\0\x18\x06\0\0\0\0\0\0\0\0\0\0\0\0\x17\x40\x61\ +\x10\0\0\0\0\0\0\xd5\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\ +\xc5\x70\xff\x01\0\0\0\0\x63\xa7\xff\x84\0\0\0\0\x61\x1a\xff\x78\0\0\0\0\xd5\ +\x10\0\x02\0\0\0\0\xbf\x91\0\0\0\0\0\0\x85\0\0\0\0\0\0\xa8\x61\x0a\xff\x80\0\0\ +\0\0\x63\x60\0\x28\0\0\0\0\x61\x0a\xff\x84\0\0\0\0\x63\x60\0\x2c\0\0\0\0\x18\ +\x16\0\0\0\0\0\0\0\0\0\0\0\0\0\0\x61\x01\0\0\0\0\0\0\x63\x60\0\x18\0\0\0\0\xb7\ +\0\0\0\0\0\0\0\x95\0\0\0\0\0\0\0"; + err = bpf_load_and_run(&opts); + if (err < 0) + return err; + return 0; +} + +static inline struct iterators_bpf * +iterators_bpf__open_and_load(void) +{ + struct iterators_bpf *skel; + + skel = iterators_bpf__open(); + if (!skel) + return NULL; + if (iterators_bpf__load(skel)) { + iterators_bpf__destroy(skel); + return NULL; + } + return skel; +} + +__attribute__((unused)) static void +iterators_bpf__assert(struct iterators_bpf *s __attribute__((unused))) +{ +#ifdef __cplusplus +#define _Static_assert static_assert +#endif +#ifdef __cplusplus +#undef _Static_assert +#endif +} + +#endif /* __ITERATORS_BPF_SKEL_H__ */ diff --git a/kernel/bpf/preload/iterators/iterators.lskel.h b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h index 70f236a82fe1..70f236a82fe1 100644 --- a/kernel/bpf/preload/iterators/iterators.lskel.h +++ b/kernel/bpf/preload/iterators/iterators.lskel-little-endian.h diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 99417b387547..bcc97613de76 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -390,7 +390,7 @@ static int bpf_map_alloc_id(struct bpf_map *map) return id > 0 ? 0 : id; } -void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) +void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; @@ -402,18 +402,12 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) if (!map->id) return; - if (do_idr_lock) - spin_lock_irqsave(&map_idr_lock, flags); - else - __acquire(&map_idr_lock); + spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; - if (do_idr_lock) - spin_unlock_irqrestore(&map_idr_lock, flags); - else - __release(&map_idr_lock); + spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG_KMEM @@ -706,13 +700,13 @@ static void bpf_map_put_uref(struct bpf_map *map) } /* decrement map refcnt and schedule it for freeing via workqueue - * (unrelying map implementation ops->map_free() might sleep) + * (underlying map implementation ops->map_free() might sleep) */ -static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) +void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ - bpf_map_free_id(map, do_idr_lock); + bpf_map_free_id(map); btf_put(map->btf); INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend @@ -721,11 +715,6 @@ static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock) queue_work(system_unbound_wq, &map->work); } } - -void bpf_map_put(struct bpf_map *map) -{ - __bpf_map_put(map, true); -} EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 205dc9edcaa9..ca826bd1eba3 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void) /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed + * @new_cpus: the temp variable for the new effective_cpus mask * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_rwsem held, * cpuset membership stays stable. */ -static void update_tasks_cpumask(struct cpuset *cs) +static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) { struct css_task_iter it; struct task_struct *task; @@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs) if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; - set_cpus_allowed_ptr(task, cs->effective_cpus); + + cpumask_and(new_cpus, cs->effective_cpus, + task_cpu_possible_mask(task)); + set_cpus_allowed_ptr(task, new_cpus); } css_task_iter_end(&it); } @@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, spin_unlock_irq(&callback_lock); if (adding || deleting) - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmp->new_cpus); /* * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary. @@ -1661,7 +1665,7 @@ update_parent_subparts: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - update_tasks_cpumask(cp); + update_tasks_cpumask(cp, tmp->new_cpus); /* * On legacy hierarchy, if the effective cpumask of any non- @@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs) } } - update_tasks_cpumask(parent); + update_tasks_cpumask(parent, tmpmask.new_cpus); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmpmask); @@ -3348,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs, * as the tasks will be migrated to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); @@ -3385,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs, spin_unlock_irq(&callback_lock); if (cpus_updated) - update_tasks_cpumask(cs); + update_tasks_cpumask(cs, new_cpus); if (mems_updated) update_tasks_nodemask(cs); } @@ -3692,15 +3696,38 @@ void __init cpuset_init_smp(void) * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the - * tasks cpuset. + * tasks cpuset, except when the task is in the top cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; + struct cpuset *cs; spin_lock_irqsave(&callback_lock, flags); - guarantee_online_cpus(tsk, pmask); + rcu_read_lock(); + + cs = task_cs(tsk); + if (cs != &top_cpuset) + guarantee_online_cpus(tsk, pmask); + /* + * Tasks in the top cpuset won't get update to their cpumasks + * when a hotplug online/offline event happens. So we include all + * offline cpus in the allowed cpu list. + */ + if ((cs == &top_cpuset) || cpumask_empty(pmask)) { + const struct cpumask *possible_mask = task_cpu_possible_mask(tsk); + + /* + * We first exclude cpus allocated to partitions. If there is no + * allowable online cpu left, we fall back to all possible cpus. + */ + cpumask_andnot(pmask, possible_mask, top_cpuset.subparts_cpus); + if (!cpumask_intersects(pmask, cpu_online_mask)) + cpumask_copy(pmask, possible_mask); + } + + rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 793ecff29038..831f1f472bb8 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -26,7 +26,7 @@ static struct cgroup_rstat_cpu *cgroup_rstat_cpu(struct cgroup *cgrp, int cpu) * rstat_cpu->updated_children list. See the comment on top of * cgroup_rstat_cpu definition for details. */ -void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) +__bpf_kfunc void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) { raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, cpu); unsigned long flags; @@ -231,7 +231,7 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep) * * This function may block. */ -void cgroup_rstat_flush(struct cgroup *cgrp) +__bpf_kfunc void cgroup_rstat_flush(struct cgroup *cgrp) { might_sleep(); diff --git a/kernel/events/core.c b/kernel/events/core.c index d56328e5080e..c4be13e50547 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); epc = &cpc->epc; - + raw_spin_lock_irq(&ctx->lock); if (!epc->ctx) { atomic_set(&epc->refcount, 1); epc->embedded = 1; - raw_spin_lock_irq(&ctx->lock); list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; - raw_spin_unlock_irq(&ctx->lock); } else { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); } - + raw_spin_unlock_irq(&ctx->lock); return epc; } @@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head) static void put_pmu_ctx(struct perf_event_pmu_context *epc) { + struct perf_event_context *ctx = epc->ctx; unsigned long flags; - if (!atomic_dec_and_test(&epc->refcount)) + /* + * XXX + * + * lockdep_assert_held(&ctx->mutex); + * + * can't because of the call-site in _free_event()/put_event() + * which isn't always called under ctx->mutex. + */ + if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags)) return; - if (epc->ctx) { - struct perf_event_context *ctx = epc->ctx; + WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - /* - * XXX - * - * lockdep_assert_held(&ctx->mutex); - * - * can't because of the call-site in _free_event()/put_event() - * which isn't always called under ctx->mutex. - */ - - WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - raw_spin_lock_irqsave(&ctx->lock, flags); - list_del_init(&epc->pmu_ctx_entry); - epc->ctx = NULL; - raw_spin_unlock_irqrestore(&ctx->lock, flags); - } + list_del_init(&epc->pmu_ctx_entry); + epc->ctx = NULL; WARN_ON_ONCE(!list_empty(&epc->pinned_active)); WARN_ON_ONCE(!list_empty(&epc->flexible_active)); + raw_spin_unlock_irqrestore(&ctx->lock, flags); + if (epc->embedded) return; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 5c3fb6168eef..798a9042421f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1915,7 +1915,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { - debugfs_remove(debugfs_lookup(d->name, domain_dir)); + debugfs_lookup_and_remove(d->name, domain_dir); } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 969e8f52f7da..b1cf259854ca 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/btf.h> #include <linux/capability.h> #include <linux/mm.h> #include <linux/file.h> @@ -975,7 +976,7 @@ void __noclone __crash_kexec(struct pt_regs *regs) } STACK_FRAME_NON_STANDARD(__crash_kexec); -void crash_kexec(struct pt_regs *regs) +__bpf_kfunc void crash_kexec(struct pt_regs *regs) { int old_cpu, this_cpu; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8739c2a5a54e..1233affc106c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -3,6 +3,8 @@ * Scheduler topology setup/handling methods */ +#include <linux/bsearch.h> + DEFINE_MUTEX(sched_domains_mutex); /* Protected by sched_domains_mutex: */ @@ -2067,6 +2069,94 @@ unlock: return found; } +struct __cmp_key { + const struct cpumask *cpus; + struct cpumask ***masks; + int node; + int cpu; + int w; +}; + +static int hop_cmp(const void *a, const void *b) +{ + struct cpumask **prev_hop = *((struct cpumask ***)b - 1); + struct cpumask **cur_hop = *(struct cpumask ***)b; + struct __cmp_key *k = (struct __cmp_key *)a; + + if (cpumask_weight_and(k->cpus, cur_hop[k->node]) <= k->cpu) + return 1; + + k->w = (b == k->masks) ? 0 : cpumask_weight_and(k->cpus, prev_hop[k->node]); + if (k->w <= k->cpu) + return 0; + + return -1; +} + +/* + * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: Nth cpu to find + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) +{ + struct __cmp_key k = { .cpus = cpus, .node = node, .cpu = cpu }; + struct cpumask ***hop_masks; + int hop, ret = nr_cpu_ids; + + rcu_read_lock(); + + k.masks = rcu_dereference(sched_domains_numa_masks); + if (!k.masks) + goto unlock; + + hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp); + hop = hop_masks - k.masks; + + ret = hop ? + cpumask_nth_and_andnot(cpu - k.w, cpus, k.masks[hop][node], k.masks[hop-1][node]) : + cpumask_nth_and(cpu, cpus, k.masks[0][node]); +unlock: + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu); + +/** + * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away from + * @node + * @node: The node to count hops from. + * @hops: Include CPUs up to that many hops away. 0 means local node. + * + * Return: On success, a pointer to a cpumask of CPUs at most @hops away from + * @node, an error value otherwise. + * + * Requires rcu_lock to be held. Returned cpumask is only valid within that + * read-side section, copy it if required beyond that. + * + * Note that not all hops are equal in distance; see sched_init_numa() for how + * distances and masks are handled. + * Also note that this is a reflection of sched_domains_numa_masks, which may change + * during the lifetime of the system (offline nodes are taken out of the masks). + */ +const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops) +{ + struct cpumask ***masks; + + if (node >= nr_node_ids || hops >= sched_domains_numa_levels) + return ERR_PTR(-EINVAL); + + masks = rcu_dereference(sched_domains_numa_masks); + if (!masks) + return ERR_PTR(-EBUSY); + + return masks[hops][node]; +} +EXPORT_SYMBOL_GPL(sched_numa_hop_mask); + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index d1313435af2b..c58baf9983cc 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1237,7 +1237,7 @@ __diag_ignore_all("-Wmissing-prototypes", * Return: a bpf_key pointer with a valid key pointer if the key is found, a * NULL pointer otherwise. */ -struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) +__bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) { key_ref_t key_ref; struct bpf_key *bkey; @@ -1286,7 +1286,7 @@ struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags) * Return: a bpf_key pointer with an invalid key pointer set from the * pre-determined ID on success, a NULL pointer otherwise */ -struct bpf_key *bpf_lookup_system_key(u64 id) +__bpf_kfunc struct bpf_key *bpf_lookup_system_key(u64 id) { struct bpf_key *bkey; @@ -1310,7 +1310,7 @@ struct bpf_key *bpf_lookup_system_key(u64 id) * Decrement the reference count of the key inside *bkey*, if the pointer * is valid, and free *bkey*. */ -void bpf_key_put(struct bpf_key *bkey) +__bpf_kfunc void bpf_key_put(struct bpf_key *bkey) { if (bkey->has_ref) key_put(bkey->key); @@ -1330,7 +1330,7 @@ void bpf_key_put(struct bpf_key *bkey) * * Return: 0 on success, a negative value on error. */ -int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, +__bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, struct bpf_dynptr_kern *sig_ptr, struct bpf_key *trusted_keyring) { diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 78ed5f1baa8c..c9e40f692650 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9148,9 +9148,6 @@ buffer_percent_write(struct file *filp, const char __user *ubuf, if (val > 100) return -EINVAL; - if (!val) - val = 1; - tr->buffer_percent = val; (*ppos)++; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 36c34c9909fa..3509115a0e85 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -763,6 +763,7 @@ config DEBUG_KMEMLEAK select KALLSYMS select CRC32 select STACKDEPOT + select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF help Say Y here if you want to enable the memory leak detector. The memory allocation/freeing is traced in a way @@ -1216,7 +1217,7 @@ config SCHED_DEBUG depends on DEBUG_KERNEL && PROC_FS default y help - If you say Y here, the /proc/sched_debug file will be provided + If you say Y here, the /sys/kernel/debug/sched file will be provided that can help debug the scheduler. The runtime overhead of this option is minimal. diff --git a/lib/cpumask.c b/lib/cpumask.c index c7c392514fd3..e7258836b60b 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -110,15 +110,33 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) #endif /** - * cpumask_local_spread - select the i'th cpu with local numa cpu's first + * cpumask_local_spread - select the i'th cpu based on NUMA distances * @i: index number * @node: local numa_node * - * This function selects an online CPU according to a numa aware policy; - * local cpus are returned first, followed by non-local ones, then it - * wraps around. + * Returns online CPU according to a numa aware policy; local cpus are returned + * first, followed by non-local ones, then it wraps around. * - * It's not very efficient, but useful for setup. + * For those who wants to enumerate all CPUs based on their NUMA distances, + * i.e. call this function in a loop, like: + * + * for (i = 0; i < num_online_cpus(); i++) { + * cpu = cpumask_local_spread(i, node); + * do_something(cpu); + * } + * + * There's a better alternative based on for_each()-like iterators: + * + * for_each_numa_hop_mask(mask, node) { + * for_each_cpu_andnot(cpu, mask, prev) + * do_something(cpu); + * prev = mask; + * } + * + * It's simpler and more verbose than above. Complexity of iterator-based + * enumeration is O(sched_domains_numa_levels * nr_cpu_ids), while + * cpumask_local_spread() when called for each cpu is + * O(sched_domains_numa_levels * nr_cpu_ids * log(nr_cpu_ids)). */ unsigned int cpumask_local_spread(unsigned int i, int node) { @@ -127,24 +145,12 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus(); - if (node == NUMA_NO_NODE) { - cpu = cpumask_nth(i, cpu_online_mask); - if (cpu < nr_cpu_ids) - return cpu; - } else { - /* NUMA first. */ - cpu = cpumask_nth_and(i, cpu_online_mask, cpumask_of_node(node)); - if (cpu < nr_cpu_ids) - return cpu; - - i -= cpumask_weight_and(cpu_online_mask, cpumask_of_node(node)); - - /* Skip NUMA nodes, done above. */ - cpu = cpumask_nth_andnot(i, cpu_online_mask, cpumask_of_node(node)); - if (cpu < nr_cpu_ids) - return cpu; - } - BUG(); + cpu = (node == NUMA_NO_NODE) ? + cpumask_nth(i, cpu_online_mask) : + sched_numa_find_nth_cpu(cpu_online_mask, i, node); + + WARN_ON(cpu >= nr_cpu_ids); + return cpu; } EXPORT_SYMBOL(cpumask_local_spread); diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index 9555b68bb774..1dcca8f2e194 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -49,3 +49,34 @@ int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); + +int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock(lock); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock); + +int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock_irqsave(lock, *flags); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock_irqrestore(lock, *flags); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); diff --git a/lib/find_bit.c b/lib/find_bit.c index 18bc0a7ac8ee..c10920e66788 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -155,6 +155,15 @@ unsigned long __find_nth_andnot_bit(const unsigned long *addr1, const unsigned l } EXPORT_SYMBOL(__find_nth_andnot_bit); +unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, + const unsigned long *addr2, + const unsigned long *addr3, + unsigned long size, unsigned long n) +{ + return FIND_NTH_BIT(addr1[idx] & addr2[idx] & ~addr3[idx], size, n); +} +EXPORT_SYMBOL(__find_nth_and_andnot_bit); + #ifndef find_next_and_bit unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 26e2045d3cda..5a976393c9ae 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -670,12 +670,13 @@ static inline unsigned long mte_pivot(const struct maple_enode *mn, unsigned char piv) { struct maple_node *node = mte_to_node(mn); + enum maple_type type = mte_node_type(mn); - if (piv >= mt_pivots[piv]) { + if (piv >= mt_pivots[type]) { WARN_ON(1); return 0; } - switch (mte_node_type(mn)) { + switch (type) { case maple_arange_64: return node->ma64.pivot[piv]; case maple_range_64: @@ -4887,7 +4888,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; - unsigned long max, min, index; + unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) @@ -4909,8 +4910,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); - index = mas->index; - while (index <= max) { + while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; @@ -4941,10 +4941,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, offset); } - if (unlikely(index > max)) { - mas_set_err(mas, -EBUSY); - return false; - } + if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) + goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; @@ -4961,9 +4959,11 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) return false; ascend: - if (mte_is_root(mas->node)) - mas_set_err(mas, -EBUSY); + if (!mte_is_root(mas->node)) + return false; +no_space: + mas_set_err(mas, -EBUSY); return false; } diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 497fc93ccf9e..ec847bf4dcb4 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2517,6 +2517,91 @@ static noinline void check_bnode_min_spanning(struct maple_tree *mt) mt_set_non_kernel(0); } +static noinline void check_empty_area_window(struct maple_tree *mt) +{ + unsigned long i, nr_entries = 20; + MA_STATE(mas, mt, 0, 0); + + for (i = 1; i <= nr_entries; i++) + mtree_store_range(mt, i*10, i*10 + 9, + xa_mk_value(i), GFP_KERNEL); + + /* Create another hole besides the one at 0 */ + mtree_store_range(mt, 160, 169, NULL, GFP_KERNEL); + + /* Check lower bounds that don't fit */ + rcu_read_lock(); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 10) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 6, 90, 5) != -EBUSY); + + /* Check lower bound that does fit */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 5) != 0); + MT_BUG_ON(mt, mas.index != 5); + MT_BUG_ON(mt, mas.last != 9); + rcu_read_unlock(); + + /* Check one gap that doesn't fit and one that does */ + rcu_read_lock(); + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 217, 9) != 0); + MT_BUG_ON(mt, mas.index != 161); + MT_BUG_ON(mt, mas.last != 169); + + /* Check one gap that does fit above the min */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 3) != 0); + MT_BUG_ON(mt, mas.index != 216); + MT_BUG_ON(mt, mas.last != 218); + + /* Check size that doesn't fit any gap */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 16) != -EBUSY); + + /* + * Check size that doesn't fit the lower end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 167, 200, 4) != -EBUSY); + + /* + * Check size that doesn't fit the upper end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 162, 4) != -EBUSY); + + /* Check mas_empty_area forward */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 9) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 8); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 4) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 11) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 5, 100, 6) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 8, 10) != -EBUSY); + + mas_reset(&mas); + mas_empty_area(&mas, 100, 165, 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 100, 163, 6) != -EBUSY); + rcu_read_unlock(); +} + static DEFINE_MTREE(tree); static int maple_tree_seed(void) { @@ -2765,6 +2850,10 @@ static int maple_tree_seed(void) check_bnode_min_spanning(&tree); mtree_destroy(&tree); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_empty_area_window(&tree); + mtree_destroy(&tree); + #if defined(BENCH) skip: #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7fcdb98c9e68..bdbfeb6fb393 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5051,6 +5051,9 @@ again: entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { + /* No swap on hugetlb */ + WARN_ON_ONCE( + is_swapin_error_entry(pte_to_swp_entry(entry))); /* * We copy the pte marker only if the dst vma has * uffd-wp enabled. diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 79be13133322..90acfea40c13 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -847,6 +847,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_SUCCEED; } +/* + * See pmd_trans_unstable() for how the result may change out from + * underneath us, even if we hold mmap_lock in read. + */ static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) @@ -865,8 +869,12 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm, #endif if (pmd_none(pmde)) return SCAN_PMD_NONE; + if (!pmd_present(pmde)) + return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; + if (pmd_devmap(pmde)) + return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; @@ -1642,7 +1650,7 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * has higher cost too. It would also probably require locking * the anon_vma. */ - if (vma->anon_vma) { + if (READ_ONCE(vma->anon_vma)) { result = SCAN_PAGE_ANON; goto next; } @@ -1671,6 +1679,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, if ((cc->is_khugepaged || is_target) && mmap_write_trylock(mm)) { /* + * Re-check whether we have an ->anon_vma, because + * collapse_and_free_pmd() requires that either no + * ->anon_vma exists or the anon_vma is locked. + * We already checked ->anon_vma above, but that check + * is racy because ->anon_vma can be populated under the + * mmap lock in read mode. + */ + if (vma->anon_vma) { + result = SCAN_PAGE_ANON; + goto unlock_next; + } + /* * When a vma is registered with uffd-wp, we can't * recycle the pmd pgtable because there can be pte * markers installed. Skip it only, so the rest mm/vma diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 92f670edbf51..55dc8b8b0616 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2070,8 +2070,10 @@ static int __init kmemleak_boot_config(char *str) return -EINVAL; if (strcmp(str, "off") == 0) kmemleak_disable(); - else if (strcmp(str, "on") == 0) + else if (strcmp(str, "on") == 0) { kmemleak_skip_disable = 1; + stack_depot_want_early_init(); + } else return -EINVAL; return 0; @@ -2093,7 +2095,6 @@ void __init kmemleak_init(void) if (kmemleak_error) return; - stack_depot_init(); jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab457f0394ab..73afff8062f9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,7 +63,6 @@ #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/seq_buf.h> -#include <linux/parser.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -2393,8 +2392,7 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP, - NULL); + MEMCG_RECLAIM_MAY_SWAP); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2685,8 +2683,7 @@ retry: psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options, - NULL); + gfp_mask, reclaim_options); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -3506,8 +3503,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, } if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, - NULL)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { ret = -EBUSY; break; } @@ -3618,8 +3614,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return -EINTR; if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP, - NULL)) + MEMCG_RECLAIM_MAY_SWAP)) nr_retries--; } @@ -6429,8 +6424,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); if (!reclaimed && !nr_retries--) break; @@ -6479,8 +6473,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) nr_reclaims--; continue; } @@ -6603,54 +6596,21 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } -enum { - MEMORY_RECLAIM_NODES = 0, - MEMORY_RECLAIM_NULL, -}; - -static const match_table_t if_tokens = { - { MEMORY_RECLAIM_NODES, "nodes=%s" }, - { MEMORY_RECLAIM_NULL, NULL }, -}; - static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; - unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP | - MEMCG_RECLAIM_PROACTIVE; - char *old_buf, *start; - substring_t args[MAX_OPT_ARGS]; - int token; - char value[256]; - nodemask_t nodemask = NODE_MASK_ALL; - - buf = strstrip(buf); - - old_buf = buf; - nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE; - if (buf == old_buf) - return -EINVAL; + unsigned int reclaim_options; + int err; buf = strstrip(buf); + err = page_counter_memparse(buf, "", &nr_to_reclaim); + if (err) + return err; - while ((start = strsep(&buf, " ")) != NULL) { - if (!strlen(start)) - continue; - token = match_token(start, if_tokens, args); - match_strlcpy(value, args, sizeof(value)); - switch (token) { - case MEMORY_RECLAIM_NODES: - if (nodelist_parse(value, nodemask) < 0) - return -EINVAL; - break; - default: - return -EINVAL; - } - } - + reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { unsigned long reclaimed; @@ -6667,8 +6627,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim - nr_reclaimed, - GFP_KERNEL, reclaim_options, - &nodemask); + GFP_KERNEL, reclaim_options); if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/memory.c b/mm/memory.c index aad226daf41b..3e836fecd035 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -828,12 +828,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, return -EBUSY; return -ENOENT; } else if (is_pte_marker_entry(entry)) { - /* - * We're copying the pgtable should only because dst_vma has - * uffd-wp enabled, do sanity check. - */ - WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); - set_pte_at(dst_mm, addr, dst_pte, pte); + if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma)) + set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } if (!userfaultfd_wp(dst_vma)) @@ -3629,8 +3625,12 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf) /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. + * + * This should also cover the case where e.g. the pte changed + * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR. + * So is_pte_marker() check is not enough to safely drop the pte. */ - if (is_pte_marker(*vmf->pte)) + if (pte_same(vmf->orig_pte, *vmf->pte)) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 02c8a712282f..f940395667c8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -600,7 +600,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* diff --git a/mm/mprotect.c b/mm/mprotect.c index 908df12caa26..61cf60015a8b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -245,7 +245,13 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); - } else if (pte_marker_entry_uffd_wp(entry)) { + } else if (is_pte_marker_entry(entry)) { + /* + * Ignore swapin errors unconditionally, + * because any access should sigbus anyway. + */ + if (is_swapin_error_entry(entry)) + continue; /* * If this is uffd-wp pte marker and we'd like * to unprotect it, drop it; the next page diff --git a/mm/mremap.c b/mm/mremap.c index fe587c5d6591..930f65c315c0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1027,16 +1027,29 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, } /* - * Function vma_merge() is called on the extension we are adding to - * the already existing vma, vma_merge() will merge this extension with - * the already existing vma (expand operation itself) and possibly also - * with the next vma if it becomes adjacent to the expanded vma and - * otherwise compatible. + * Function vma_merge() is called on the extension we + * are adding to the already existing vma, vma_merge() + * will merge this extension with the already existing + * vma (expand operation itself) and possibly also with + * the next vma if it becomes adjacent to the expanded + * vma and otherwise compatible. + * + * However, vma_merge() can currently fail due to + * is_mergeable_vma() check for vm_ops->close (see the + * comment there). Yet this should not prevent vma + * expanding, so perform a simple expand for such vma. + * Ideally the check for close op should be only done + * when a vma would be actually removed due to a merge. */ - vma = vma_merge(mm, vma, extension_start, extension_end, + if (!vma->vm_ops || !vma->vm_ops->close) { + vma = vma_merge(mm, vma, extension_start, extension_end, vma->vm_flags, vma->anon_vma, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + } else if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + vma = NULL; + } if (!vma) { vm_unacct_memory(pages); ret = -ENOMEM; diff --git a/mm/swapfile.c b/mm/swapfile.c index 908a529bca12..4fa440e87cd6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1100,6 +1100,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: diff --git a/mm/vmscan.c b/mm/vmscan.c index bd6637fcd8f9..bf3eedf0209c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3323,13 +3323,16 @@ void lru_gen_migrate_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return; + /* migration can happen before addition */ + if (!mm->lru_gen.memcg) + return; + rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; - VM_WARN_ON_ONCE(!mm->lru_gen.memcg); VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); @@ -6754,8 +6757,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask) + unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; @@ -6770,7 +6772,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), - .nodemask = nodemask, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9445bee6b014..702bc3fd687a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -113,7 +113,23 @@ * have room for two bit at least. */ #define OBJ_ALLOCATED_TAG 1 -#define OBJ_TAG_BITS 1 + +#ifdef CONFIG_ZPOOL +/* + * The second least-significant bit in the object's header identifies if the + * value stored at the header is a deferred handle from the last reclaim + * attempt. + * + * As noted above, this is valid because we have room for two bits. + */ +#define OBJ_DEFERRED_HANDLE_TAG 2 +#define OBJ_TAG_BITS 2 +#define OBJ_TAG_MASK (OBJ_ALLOCATED_TAG | OBJ_DEFERRED_HANDLE_TAG) +#else +#define OBJ_TAG_BITS 1 +#define OBJ_TAG_MASK OBJ_ALLOCATED_TAG +#endif /* CONFIG_ZPOOL */ + #define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) @@ -222,6 +238,12 @@ struct link_free { * Handle of allocated object. */ unsigned long handle; +#ifdef CONFIG_ZPOOL + /* + * Deferred handle of a reclaimed object. + */ + unsigned long deferred_handle; +#endif }; }; @@ -272,8 +294,6 @@ struct zspage { /* links the zspage to the lru list in the pool */ struct list_head lru; bool under_reclaim; - /* list of unfreed handles whose objects have been reclaimed */ - unsigned long *deferred_handles; #endif struct zs_pool *pool; @@ -897,7 +917,8 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle, + int tag) { unsigned long handle; struct zspage *zspage = get_zspage(page); @@ -908,13 +929,27 @@ static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) } else handle = *(unsigned long *)obj; - if (!(handle & OBJ_ALLOCATED_TAG)) + if (!(handle & tag)) return false; - *phandle = handle & ~OBJ_ALLOCATED_TAG; + /* Clear all tags before returning the handle */ + *phandle = handle & ~OBJ_TAG_MASK; return true; } +static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +static bool obj_stores_deferred_handle(struct page *page, void *obj, + unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + static void reset_page(struct page *page) { __ClearPageMovable(page); @@ -946,22 +981,36 @@ unlock: } #ifdef CONFIG_ZPOOL +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx); + /* * Free all the deferred handles whose objects are freed in zs_free. */ -static void free_handles(struct zs_pool *pool, struct zspage *zspage) +static void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) { - unsigned long handle = (unsigned long)zspage->deferred_handles; + int obj_idx = 0; + struct page *page = get_first_page(zspage); + unsigned long handle; - while (handle) { - unsigned long nxt_handle = handle_to_obj(handle); + while (1) { + handle = find_deferred_handle_obj(class, page, &obj_idx); + if (!handle) { + page = get_next_page(page); + if (!page) + break; + obj_idx = 0; + continue; + } cache_free_handle(pool, handle); - handle = nxt_handle; + obj_idx++; } } #else -static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {} +static inline void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) {} #endif static void __free_zspage(struct zs_pool *pool, struct size_class *class, @@ -979,7 +1028,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, VM_BUG_ON(fg != ZS_EMPTY); /* Free all deferred handles from zs_free */ - free_handles(pool, zspage); + free_handles(pool, class, zspage); next = page = get_first_page(zspage); do { @@ -1067,7 +1116,6 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) #ifdef CONFIG_ZPOOL INIT_LIST_HEAD(&zspage->lru); zspage->under_reclaim = false; - zspage->deferred_handles = NULL; #endif set_freeobj(zspage, 0); @@ -1568,7 +1616,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) } EXPORT_SYMBOL_GPL(zs_malloc); -static void obj_free(int class_size, unsigned long obj) +static void obj_free(int class_size, unsigned long obj, unsigned long *handle) { struct link_free *link; struct zspage *zspage; @@ -1582,15 +1630,29 @@ static void obj_free(int class_size, unsigned long obj) zspage = get_zspage(f_page); vaddr = kmap_atomic(f_page); - - /* Insert this object in containing zspage's freelist */ link = (struct link_free *)(vaddr + f_offset); - if (likely(!ZsHugePage(zspage))) - link->next = get_freeobj(zspage) << OBJ_TAG_BITS; - else - f_page->index = 0; + + if (handle) { +#ifdef CONFIG_ZPOOL + /* Stores the (deferred) handle in the object's header */ + *handle |= OBJ_DEFERRED_HANDLE_TAG; + *handle &= ~OBJ_ALLOCATED_TAG; + + if (likely(!ZsHugePage(zspage))) + link->deferred_handle = *handle; + else + f_page->index = *handle; +#endif + } else { + /* Insert this object in containing zspage's freelist */ + if (likely(!ZsHugePage(zspage))) + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + else + f_page->index = 0; + set_freeobj(zspage, f_objidx); + } + kunmap_atomic(vaddr); - set_freeobj(zspage, f_objidx); mod_zspage_inuse(zspage, -1); } @@ -1615,7 +1677,6 @@ void zs_free(struct zs_pool *pool, unsigned long handle) zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); #ifdef CONFIG_ZPOOL @@ -1624,15 +1685,15 @@ void zs_free(struct zs_pool *pool, unsigned long handle) * Reclaim needs the handles during writeback. It'll free * them along with the zspage when it's done with them. * - * Record current deferred handle at the memory location - * whose address is given by handle. + * Record current deferred handle in the object's header. */ - record_obj(handle, (unsigned long)zspage->deferred_handles); - zspage->deferred_handles = (unsigned long *)handle; + obj_free(class->size, obj, &handle); spin_unlock(&pool->lock); return; } #endif + obj_free(class->size, obj, NULL); + fullness = fix_fullness_group(class, zspage); if (fullness == ZS_EMPTY) free_zspage(pool, class, zspage); @@ -1713,11 +1774,11 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, } /* - * Find alloced object in zspage from index object and + * Find object with a certain tag in zspage from index object and * return handle. */ -static unsigned long find_alloced_obj(struct size_class *class, - struct page *page, int *obj_idx) +static unsigned long find_tagged_obj(struct size_class *class, + struct page *page, int *obj_idx, int tag) { unsigned int offset; int index = *obj_idx; @@ -1728,7 +1789,7 @@ static unsigned long find_alloced_obj(struct size_class *class, offset += class->size * index; while (offset < PAGE_SIZE) { - if (obj_allocated(page, addr + offset, &handle)) + if (obj_tagged(page, addr + offset, &handle, tag)) break; offset += class->size; @@ -1742,6 +1803,28 @@ static unsigned long find_alloced_obj(struct size_class *class, return handle; } +/* + * Find alloced object in zspage from index object and + * return handle. + */ +static unsigned long find_alloced_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +/* + * Find object storing a deferred handle in header in zspage from index object + * and return handle. + */ +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + struct zs_compact_control { /* Source spage for migration which could be a subpage of zspage */ struct page *s_page; @@ -1784,7 +1867,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, zs_object_copy(class, free_obj, used_obj); obj_idx++; record_obj(handle, free_obj); - obj_free(class->size, used_obj); + obj_free(class->size, used_obj, NULL); } /* Remember last position in this iteration */ @@ -2478,6 +2561,90 @@ void zs_destroy_pool(struct zs_pool *pool) EXPORT_SYMBOL_GPL(zs_destroy_pool); #ifdef CONFIG_ZPOOL +static void restore_freelist(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + unsigned int obj_idx = 0; + unsigned long handle, off = 0; /* off is within-page offset */ + struct page *page = get_first_page(zspage); + struct link_free *prev_free = NULL; + void *prev_page_vaddr = NULL; + + /* in case no free object found */ + set_freeobj(zspage, (unsigned int)(-1UL)); + + while (page) { + void *vaddr = kmap_atomic(page); + struct page *next_page; + + while (off < PAGE_SIZE) { + void *obj_addr = vaddr + off; + + /* skip allocated object */ + if (obj_allocated(page, obj_addr, &handle)) { + obj_idx++; + off += class->size; + continue; + } + + /* free deferred handle from reclaim attempt */ + if (obj_stores_deferred_handle(page, obj_addr, &handle)) + cache_free_handle(pool, handle); + + if (prev_free) + prev_free->next = obj_idx << OBJ_TAG_BITS; + else /* first free object found */ + set_freeobj(zspage, obj_idx); + + prev_free = (struct link_free *)vaddr + off / sizeof(*prev_free); + /* if last free object in a previous page, need to unmap */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + obj_idx++; + off += class->size; + } + + /* + * Handle the last (full or partial) object on this page. + */ + next_page = get_next_page(page); + if (next_page) { + if (!prev_free || prev_page_vaddr) { + /* + * There is no free object in this page, so we can safely + * unmap it. + */ + kunmap_atomic(vaddr); + } else { + /* update prev_page_vaddr since prev_free is on this page */ + prev_page_vaddr = vaddr; + } + } else { /* this is the last page */ + if (prev_free) { + /* + * Reset OBJ_TAG_BITS bit to last link to tell + * whether it's allocated object or not. + */ + prev_free->next = -1UL << OBJ_TAG_BITS; + } + + /* unmap previous page (if not done yet) */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + kunmap_atomic(vaddr); + } + + page = next_page; + off %= PAGE_SIZE; + } +} + static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) { int i, obj_idx, ret = 0; @@ -2561,6 +2728,12 @@ next: return 0; } + /* + * Eviction fails on one of the handles, so we need to restore zspage. + * We need to rebuild its freelist (and free stored deferred handles), + * put it back to the correct size class, and add it to the LRU list. + */ + restore_freelist(pool, class, zspage); putback_zspage(class, zspage); list_add(&zspage->lru, &pool->lru); unlock_zspage(zspage); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index acf563fbdfd9..17b946f9ba31 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1061,8 +1061,15 @@ int hci_conn_del(struct hci_conn *conn) if (conn->type == ACL_LINK) { struct hci_conn *sco = conn->link; - if (sco) + if (sco) { sco->link = NULL; + /* Due to race, SCO connection might be not established + * yet at this point. Delete it now, otherwise it is + * possible for it to be stuck and can't be deleted. + */ + if (sco->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(sco); + } /* Unacked frames */ hdev->acl_cnt += conn->sent; @@ -1243,6 +1250,8 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) if (conn != hci_lookup_le_connect(hdev)) goto done; + /* Flush to make sure we send create conn cancel command if needed */ + flush_delayed_work(&conn->le_conn_timeout); hci_conn_failed(conn, bt_status(err)); done: @@ -1981,16 +1990,14 @@ static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, qos->latency = conn->le_conn_latency; } -static struct hci_conn *hci_bind_bis(struct hci_conn *conn, - struct bt_iso_qos *qos) +static void hci_bind_bis(struct hci_conn *conn, + struct bt_iso_qos *qos) { /* Update LINK PHYs according to QoS preference */ conn->le_tx_phy = qos->out.phy; conn->le_tx_phy = qos->out.phy; conn->iso_qos = *qos; conn->state = BT_BOUND; - - return conn; } static int create_big_sync(struct hci_dev *hdev, void *data) @@ -2119,11 +2126,7 @@ struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, if (IS_ERR(conn)) return conn; - conn = hci_bind_bis(conn, qos); - if (!conn) { - hci_conn_drop(conn); - return ERR_PTR(-ENOMEM); - } + hci_bind_bis(conn, qos); /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a3e0dc6a6e73..adfc3ea06d08 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2683,14 +2683,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); return len; } @@ -2735,14 +2727,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) if (IS_ERR(skb)) return PTR_ERR(skb); - /* Channel lock is released before requesting new skb and then - * reacquired thus we need to recheck channel state. - */ - if (chan->state != BT_CONNECTED) { - kfree_skb(skb); - return -ENOTCONN; - } - l2cap_do_send(chan, skb); err = len; break; @@ -2763,14 +2747,6 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) */ err = l2cap_segment_sdu(chan, &seg_queue, msg, len); - /* The channel could have been closed while segmenting, - * check that it is still connected. - */ - if (chan->state != BT_CONNECTED) { - __skb_queue_purge(&seg_queue); - err = -ENOTCONN; - } - if (err) break; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index ca8f07f3542b..eebe256104bc 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1624,6 +1624,14 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, if (!skb) return ERR_PTR(err); + /* Channel lock is released before requesting new skb and then + * reacquired thus we need to recheck channel state. + */ + if (chan->state != BT_CONNECTED) { + kfree_skb(skb); + return ERR_PTR(-ENOTCONN); + } + skb->priority = sk->sk_priority; bt_cb(skb)->l2cap.chan = chan; diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index d2ea8e19aa1b..7add66f30e4d 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -859,6 +859,12 @@ static u32 get_supported_settings(struct hci_dev *hdev) hdev->set_bdaddr) settings |= MGMT_SETTING_CONFIGURATION; + if (cis_central_capable(hdev)) + settings |= MGMT_SETTING_CIS_CENTRAL; + + if (cis_peripheral_capable(hdev)) + settings |= MGMT_SETTING_CIS_PERIPHERAL; + settings |= MGMT_SETTING_PHY_CONFIGURATION; return settings; @@ -932,6 +938,12 @@ static u32 get_current_settings(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) settings |= MGMT_SETTING_WIDEBAND_SPEECH; + if (cis_central_capable(hdev)) + settings |= MGMT_SETTING_CIS_CENTRAL; + + if (cis_peripheral_capable(hdev)) + settings |= MGMT_SETTING_CIS_PERIPHERAL; + return settings; } diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8da0d73b368e..b766a84c8536 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -234,7 +234,7 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes, int i, n; LIST_HEAD(list); - n = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, nframes, (void **)skbs); + n = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, (void **)skbs); if (unlikely(n == 0)) { for (i = 0; i < nframes; i++) xdp_return_frame(frames[i]); @@ -484,7 +484,7 @@ out: __diag_push(); __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); -int noinline bpf_fentry_test1(int a) +__bpf_kfunc int bpf_fentry_test1(int a) { return a + 1; } @@ -529,27 +529,35 @@ int noinline bpf_fentry_test8(struct bpf_fentry_test_t *arg) return (long)arg->a; } -int noinline bpf_modify_return_test(int a, int *b) +__bpf_kfunc int bpf_modify_return_test(int a, int *b) { *b += 1; return a + *b; } -u64 noinline bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) +__bpf_kfunc u64 bpf_kfunc_call_test1(struct sock *sk, u32 a, u64 b, u32 c, u64 d) { return a + b + c + d; } -int noinline bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) +__bpf_kfunc int bpf_kfunc_call_test2(struct sock *sk, u32 a, u32 b) { return a + b; } -struct sock * noinline bpf_kfunc_call_test3(struct sock *sk) +__bpf_kfunc struct sock *bpf_kfunc_call_test3(struct sock *sk) { return sk; } +long noinline bpf_kfunc_call_test4(signed char a, short b, int c, long d) +{ + /* Provoke the compiler to assume that the caller has sign-extended a, + * b and c on platforms where this is required (e.g. s390x). + */ + return (long)a + (long)b + (long)c + d; +} + struct prog_test_member1 { int a; }; @@ -574,21 +582,21 @@ static struct prog_test_ref_kfunc prog_test_struct = { .cnt = REFCOUNT_INIT(1), }; -noinline struct prog_test_ref_kfunc * +__bpf_kfunc struct prog_test_ref_kfunc * bpf_kfunc_call_test_acquire(unsigned long *scalar_ptr) { refcount_inc(&prog_test_struct.cnt); return &prog_test_struct; } -noinline struct prog_test_member * +__bpf_kfunc struct prog_test_member * bpf_kfunc_call_memb_acquire(void) { WARN_ON_ONCE(1); return NULL; } -noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) +__bpf_kfunc void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) { if (!p) return; @@ -596,11 +604,11 @@ noinline void bpf_kfunc_call_test_release(struct prog_test_ref_kfunc *p) refcount_dec(&p->cnt); } -noinline void bpf_kfunc_call_memb_release(struct prog_test_member *p) +__bpf_kfunc void bpf_kfunc_call_memb_release(struct prog_test_member *p) { } -noinline void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) +__bpf_kfunc void bpf_kfunc_call_memb1_release(struct prog_test_member1 *p) { WARN_ON_ONCE(1); } @@ -613,12 +621,14 @@ static int *__bpf_kfunc_call_test_get_mem(struct prog_test_ref_kfunc *p, const i return (int *)p; } -noinline int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, + const int rdwr_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdwr_buf_size); } -noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); } @@ -628,16 +638,17 @@ noinline int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, * Acquire functions must return struct pointers, so these ones are * failing. */ -noinline int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) +__bpf_kfunc int *bpf_kfunc_call_test_acq_rdonly_mem(struct prog_test_ref_kfunc *p, + const int rdonly_buf_size) { return __bpf_kfunc_call_test_get_mem(p, rdonly_buf_size); } -noinline void bpf_kfunc_call_int_mem_release(int *p) +__bpf_kfunc void bpf_kfunc_call_int_mem_release(int *p) { } -noinline struct prog_test_ref_kfunc * +__bpf_kfunc struct prog_test_ref_kfunc * bpf_kfunc_call_test_kptr_get(struct prog_test_ref_kfunc **pp, int a, int b) { struct prog_test_ref_kfunc *p = READ_ONCE(*pp); @@ -686,48 +697,53 @@ struct prog_test_fail3 { char arr2[]; }; -noinline void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +__bpf_kfunc void bpf_kfunc_call_test_pass_ctx(struct __sk_buff *skb) +{ +} + +__bpf_kfunc void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) { } -noinline void bpf_kfunc_call_test_pass1(struct prog_test_pass1 *p) +__bpf_kfunc void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) { } -noinline void bpf_kfunc_call_test_pass2(struct prog_test_pass2 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) { } -noinline void bpf_kfunc_call_test_fail1(struct prog_test_fail1 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) { } -noinline void bpf_kfunc_call_test_fail2(struct prog_test_fail2 *p) +__bpf_kfunc void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) { } -noinline void bpf_kfunc_call_test_fail3(struct prog_test_fail3 *p) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) { } -noinline void bpf_kfunc_call_test_mem_len_pass1(void *mem, int mem__sz) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) { } -noinline void bpf_kfunc_call_test_mem_len_fail1(void *mem, int len) +__bpf_kfunc void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) { } -noinline void bpf_kfunc_call_test_mem_len_fail2(u64 *mem, int len) +__bpf_kfunc void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) { } -noinline void bpf_kfunc_call_test_ref(struct prog_test_ref_kfunc *p) +__bpf_kfunc void bpf_kfunc_call_test_destructive(void) { } -noinline void bpf_kfunc_call_test_destructive(void) +__bpf_kfunc static u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) { + return arg; } __diag_pop(); @@ -746,6 +762,7 @@ BTF_SET8_START(test_sk_check_kfunc_ids) BTF_ID_FLAGS(func, bpf_kfunc_call_test1) BTF_ID_FLAGS(func, bpf_kfunc_call_test2) BTF_ID_FLAGS(func, bpf_kfunc_call_test3) +BTF_ID_FLAGS(func, bpf_kfunc_call_test4) BTF_ID_FLAGS(func, bpf_kfunc_call_test_acquire, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_kfunc_call_memb_acquire, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_kfunc_call_test_release, KF_RELEASE) @@ -767,6 +784,7 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail1) BTF_ID_FLAGS(func, bpf_kfunc_call_test_mem_len_fail2) BTF_ID_FLAGS(func, bpf_kfunc_call_test_ref, KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_kfunc_call_test_destructive, KF_DESTRUCTIVE) +BTF_ID_FLAGS(func, bpf_kfunc_call_test_static_unused_arg) BTF_SET8_END(test_sk_check_kfunc_ids) static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 00e5743647b0..25c48d81a597 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -259,7 +259,7 @@ static int __mdb_fill_info(struct sk_buff *skb, #endif } else { ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); - e.state = MDB_PG_FLAGS_PERMANENT; + e.state = MDB_PERMANENT; } e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, @@ -421,8 +421,6 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); - cb->seq = net->dev_base_seq; - for_each_netdev_rcu(net, dev) { if (netif_is_bridge_master(dev)) { struct net_bridge *br = netdev_priv(dev); @@ -685,51 +683,58 @@ static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; -static bool is_valid_mdb_entry(struct br_mdb_entry *entry, - struct netlink_ext_ack *extack) +static int validate_mdb_entry(const struct nlattr *attr, + struct netlink_ext_ack *extack) { + struct br_mdb_entry *entry = nla_data(attr); + + if (nla_len(attr) != sizeof(struct br_mdb_entry)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length"); + return -EINVAL; + } + if (entry->ifindex == 0) { NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed"); - return false; + return -EINVAL; } if (entry->addr.proto == htons(ETH_P_IP)) { if (!ipv4_is_multicast(entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast"); - return false; + return -EINVAL; } if (ipv4_is_local_multicast(entry->addr.u.ip4)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast"); - return false; + return -EINVAL; } #if IS_ENABLED(CONFIG_IPV6) } else if (entry->addr.proto == htons(ETH_P_IPV6)) { if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes"); - return false; + return -EINVAL; } #endif } else if (entry->addr.proto == 0) { /* L2 mdb */ if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) { NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast"); - return false; + return -EINVAL; } } else { NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol"); - return false; + return -EINVAL; } if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) { NL_SET_ERR_MSG_MOD(extack, "Unknown entry state"); - return false; + return -EINVAL; } if (entry->vid >= VLAN_VID_MASK) { NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id"); - return false; + return -EINVAL; } - return true; + return 0; } static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto, @@ -849,11 +854,10 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - MCAST_INCLUDE, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group"); + MCAST_INCLUDE, cfg->rt_protocol, extack); + if (unlikely(!p)) return -ENOMEM; - } + rcu_assign_pointer(*pp, p); if (!(flags & MDB_PG_FLAGS_PERMANENT) && !cfg->src_entry) mod_timer(&p->timer, @@ -1075,11 +1079,10 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - cfg->filter_mode, cfg->rt_protocol); - if (unlikely(!p)) { - NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group"); + cfg->filter_mode, cfg->rt_protocol, + extack); + if (unlikely(!p)) return -ENOMEM; - } err = br_mdb_add_group_srcs(cfg, p, brmctx, extack); if (err) @@ -1101,8 +1104,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, return 0; err_del_port_group: - hlist_del_init(&p->mglist); - kfree(p); + br_multicast_del_port_group(p); return err; } @@ -1297,6 +1299,14 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, return 0; } +static const struct nla_policy mdba_policy[MDBA_SET_ENTRY_MAX + 1] = { + [MDBA_SET_ENTRY_UNSPEC] = { .strict_start_type = MDBA_SET_ENTRY_ATTRS + 1 }, + [MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + validate_mdb_entry, + sizeof(struct br_mdb_entry)), + [MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED }, +}; + static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) @@ -1307,7 +1317,7 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, int err; err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb, - MDBA_SET_ENTRY_MAX, NULL, extack); + MDBA_SET_ENTRY_MAX, mdba_policy, extack); if (err) return err; @@ -1349,14 +1359,8 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute"); return -EINVAL; } - if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) { - NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length"); - return -EINVAL; - } cfg->entry = nla_data(tb[MDBA_SET_ENTRY]); - if (!is_valid_mdb_entry(cfg->entry, extack)) - return -EINVAL; if (cfg->entry->ifindex != cfg->br->dev->ifindex) { struct net_device *pdev; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index dea1ee1bd095..96d1fc78dd39 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -31,6 +31,7 @@ #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif +#include <trace/events/bridge.h> #include "br_private.h" #include "br_private_mcast_eht.h" @@ -234,6 +235,29 @@ out: return pmctx; } +static struct net_bridge_mcast_port * +br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx = NULL; + struct net_bridge_vlan *vlan; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return NULL; + + /* Take RCU to access the vlan. */ + rcu_read_lock(); + + vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); + if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) + pmctx = &vlan->port_mcast_ctx; + + rcu_read_unlock(); + + return pmctx; +} + /* when snooping we need to check if the contexts should be used * in the following order: * - if pmctx is non-NULL (port), check if it should be used @@ -668,6 +692,101 @@ void br_multicast_del_group_src(struct net_bridge_group_src *src, __br_multicast_del_group_src(src); } +static int +br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, + struct netlink_ext_ack *extack, + const char *what) +{ + u32 max = READ_ONCE(pmctx->mdb_max_entries); + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + if (max && n >= max) { + NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", + what, n, max); + return -E2BIG; + } + + WRITE_ONCE(pmctx->mdb_n_entries, n + 1); + return 0; +} + +static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx) +{ + u32 n = READ_ONCE(pmctx->mdb_n_entries); + + WARN_ON_ONCE(n == 0); + WRITE_ONCE(pmctx->mdb_n_entries, n - 1); +} + +static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, + const struct br_ip *group, + struct netlink_ext_ack *extack) +{ + struct net_bridge_mcast_port *pmctx; + int err; + + lockdep_assert_held_once(&port->br->multicast_lock); + + /* Always count on the port context. */ + err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack, + "Port"); + if (err) { + trace_br_mdb_full(port->dev, group); + return err; + } + + /* Only count on the VLAN context if VID is given, and if snooping on + * that VLAN is enabled. + */ + if (!group->vid) + return 0; + + pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid); + if (!pmctx) + return 0; + + err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN"); + if (err) { + trace_br_mdb_full(port->dev, group); + goto dec_one_out; + } + + return 0; + +dec_one_out: + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); + return err; +} + +static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) +{ + struct net_bridge_mcast_port *pmctx; + + lockdep_assert_held_once(&port->br->multicast_lock); + + if (vid) { + pmctx = br_multicast_port_vid_to_port_ctx(port, vid); + if (pmctx) + br_multicast_port_ngroups_dec_one(pmctx); + } + br_multicast_port_ngroups_dec_one(&port->multicast_ctx); +} + +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_n_entries); +} + +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) +{ + WRITE_ONCE(pmctx->mdb_max_entries, max); +} + +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) +{ + return READ_ONCE(pmctx->mdb_max_entries); +} + static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; @@ -702,6 +821,7 @@ void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, } else { br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); } + br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid); hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); @@ -1165,6 +1285,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, return mp; if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { + trace_br_mdb_full(br->dev, group); br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); @@ -1284,14 +1405,22 @@ struct net_bridge_port_group *br_multicast_new_port_group( unsigned char flags, const unsigned char *src, u8 filter_mode, - u8 rt_protocol) + u8 rt_protocol, + struct netlink_ext_ack *extack) { struct net_bridge_port_group *p; + int err; - p = kzalloc(sizeof(*p), GFP_ATOMIC); - if (unlikely(!p)) + err = br_multicast_port_ngroups_inc(port, group, extack); + if (err) return NULL; + p = kzalloc(sizeof(*p), GFP_ATOMIC); + if (unlikely(!p)) { + NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); + goto dec_out; + } + p->key.addr = *group; p->key.port = port; p->flags = flags; @@ -1305,8 +1434,8 @@ struct net_bridge_port_group *br_multicast_new_port_group( if (!br_multicast_is_star_g(group) && rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params)) { - kfree(p); - return NULL; + NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group"); + goto free_out; } rcu_assign_pointer(p->next, next); @@ -1320,6 +1449,25 @@ struct net_bridge_port_group *br_multicast_new_port_group( eth_broadcast_addr(p->eth_addr); return p; + +free_out: + kfree(p); +dec_out: + br_multicast_port_ngroups_dec(port, group->vid); + return NULL; +} + +void br_multicast_del_port_group(struct net_bridge_port_group *p) +{ + struct net_bridge_port *port = p->key.port; + __u16 vid = p->key.addr.vid; + + hlist_del_init(&p->mglist); + if (!br_multicast_is_star_g(&p->key.addr)) + rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, + br_sg_port_rht_params); + kfree(p); + br_multicast_port_ngroups_dec(port, vid); } void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1387,7 +1535,7 @@ __br_multicast_add_group(struct net_bridge_mcast *brmctx, } p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, - filter_mode, RTPROT_KERNEL); + filter_mode, RTPROT_KERNEL, NULL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; @@ -1933,6 +2081,25 @@ static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } + + if (br_multicast_port_ctx_is_vlan(pmctx)) { + struct net_bridge_port_group *pg; + u32 n = 0; + + /* The mcast_n_groups counter might be wrong. First, + * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries + * are flushed, thus mcast_n_groups after the toggle does not + * reflect the true values. And second, permanent entries added + * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected + * either. Thus we have to refresh the counter. + */ + + hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { + if (pg->key.addr.vid == pmctx->vlan->vid) + n++; + } + WRITE_ONCE(pmctx->mdb_n_entries, n); + } } void br_multicast_enable_port(struct net_bridge_port *port) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4316cc82ae17..9173e52b89e2 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -202,6 +202,8 @@ static inline size_t br_port_info_size(void) + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* IFLA_BRPORT_MCAST_MAX_GROUPS */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MRP_RING_OPEN */ @@ -298,7 +300,11 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, p->multicast_eht_hosts_limit) || nla_put_u32(skb, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, - p->multicast_eht_hosts_cnt)) + p->multicast_eht_hosts_cnt) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_N_GROUPS, + br_multicast_ngroups_get(&p->multicast_ctx)) || + nla_put_u32(skb, IFLA_BRPORT_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&p->multicast_ctx))) return -EMSGSIZE; #endif @@ -858,6 +864,8 @@ static int br_afspec(struct net_bridge *br, } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { + [IFLA_BRPORT_UNSPEC] = { .strict_start_type = + IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT + 1 }, [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, @@ -881,6 +889,8 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, + [IFLA_BRPORT_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [IFLA_BRPORT_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ @@ -1015,6 +1025,13 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], if (err) return err; } + + if (tb[IFLA_BRPORT_MCAST_MAX_GROUPS]) { + u32 max_groups; + + max_groups = nla_get_u32(tb[IFLA_BRPORT_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&p->multicast_ctx, max_groups); + } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { diff --git a/net/bridge/br_netlink_tunnel.c b/net/bridge/br_netlink_tunnel.c index 8914290c75d4..17abf092f7ca 100644 --- a/net/bridge/br_netlink_tunnel.c +++ b/net/bridge/br_netlink_tunnel.c @@ -188,6 +188,9 @@ initvars: } static const struct nla_policy vlan_tunnel_policy[IFLA_BRIDGE_VLAN_TUNNEL_MAX + 1] = { + [IFLA_BRIDGE_VLAN_TUNNEL_UNSPEC] = { + .strict_start_type = IFLA_BRIDGE_VLAN_TUNNEL_FLAGS + 1 + }, [IFLA_BRIDGE_VLAN_TUNNEL_ID] = { .type = NLA_U32 }, [IFLA_BRIDGE_VLAN_TUNNEL_VID] = { .type = NLA_U16 }, [IFLA_BRIDGE_VLAN_TUNNEL_FLAGS] = { .type = NLA_U16 }, diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 15ef7fd508ee..cef5f6ea850c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -126,6 +126,8 @@ struct net_bridge_mcast_port { struct hlist_node ip6_rlist; #endif /* IS_ENABLED(CONFIG_IPV6) */ unsigned char multicast_router; + u32 mdb_n_entries; + u32 mdb_max_entries; #endif /* CONFIG_BRIDGE_IGMP_SNOOPING */ }; @@ -956,7 +958,9 @@ br_multicast_new_port_group(struct net_bridge_port *port, const struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src, - u8 filter_mode, u8 rt_protocol); + u8 filter_mode, u8 rt_protocol, + struct netlink_ext_ack *extack); +void br_multicast_del_port_group(struct net_bridge_port_group *p); int br_mdb_hash_init(struct net_bridge *br); void br_mdb_hash_fini(struct net_bridge *br); void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp, @@ -974,6 +978,9 @@ void br_multicast_uninit_stats(struct net_bridge *br); void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest); +u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx); +void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max); +u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx); void br_mdb_init(void); void br_mdb_uninit(void); void br_multicast_host_join(const struct net_bridge_mcast *brmctx, @@ -1757,7 +1764,8 @@ static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) #ifdef CONFIG_BRIDGE_VLAN_FILTERING bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, const struct net_bridge_vlan *range_end); -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v); +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p); size_t br_vlan_opts_nl_size(void); int br_vlan_process_options(const struct net_bridge *br, const struct net_bridge_port *p, diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bc75fa1e4666..8a3dbc09ba38 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1816,6 +1816,7 @@ out_err: /* v_opts is used to dump the options which must be equal in the whole range */ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, const struct net_bridge_vlan *v_opts, + const struct net_bridge_port *p, u16 flags, bool dump_stats) { @@ -1842,7 +1843,7 @@ static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, goto out_err; if (v_opts) { - if (!br_vlan_opts_fill(skb, v_opts)) + if (!br_vlan_opts_fill(skb, v_opts, p)) goto out_err; if (dump_stats && !br_vlan_stats_fill(skb, v_opts)) @@ -1925,7 +1926,7 @@ void br_vlan_notify(const struct net_bridge *br, goto out_kfree; } - if (!br_vlan_fill_vids(skb, vid, vid_range, v, flags, false)) + if (!br_vlan_fill_vids(skb, vid, vid_range, v, p, flags, false)) goto out_err; nlmsg_end(skb, nlh); @@ -2030,7 +2031,7 @@ static int br_vlan_dump_dev(const struct net_device *dev, if (!br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - vlan_flags, dump_stats)) { + p, vlan_flags, dump_stats)) { err = -EMSGSIZE; break; } @@ -2056,7 +2057,7 @@ update_end: else if (!dump_global && !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, range_start, - br_vlan_flags(range_start, pvid), + p, br_vlan_flags(range_start, pvid), dump_stats)) err = -EMSGSIZE; } @@ -2131,6 +2132,8 @@ static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = [BRIDGE_VLANDB_ENTRY_STATE] = { .type = NLA_U8 }, [BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED }, [BRIDGE_VLANDB_ENTRY_MCAST_ROUTER] = { .type = NLA_U8 }, + [BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS] = { .type = NLA_REJECT }, + [BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS] = { .type = NLA_U32 }, }; static int br_vlan_rtm_process_one(struct net_device *dev, diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index a2724d03278c..e378c2f3a9e2 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -48,7 +48,8 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, curr_mc_rtr == range_mc_rtr; } -bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) +bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, + const struct net_bridge_port *p) { if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_STATE, br_vlan_get_state(v)) || !__vlan_tun_put(skb, v)) @@ -58,6 +59,12 @@ bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v) if (nla_put_u8(skb, BRIDGE_VLANDB_ENTRY_MCAST_ROUTER, br_vlan_multicast_router(v))) return false; + if (p && !br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx) && + (nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS, + br_multicast_ngroups_get(&v->port_mcast_ctx)) || + nla_put_u32(skb, BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS, + br_multicast_ngroups_get_max(&v->port_mcast_ctx)))) + return false; #endif return true; @@ -70,6 +77,8 @@ size_t br_vlan_opts_nl_size(void) + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_TINFO_ID */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* BRIDGE_VLANDB_ENTRY_MCAST_ROUTER */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_N_GROUPS */ + + nla_total_size(sizeof(u32)) /* BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS */ #endif + 0; } @@ -212,6 +221,22 @@ static int br_vlan_process_one_opts(const struct net_bridge *br, return err; *changed = true; } + if (tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]) { + u32 val; + + if (!p) { + NL_SET_ERR_MSG_MOD(extack, "Can't set mcast_max_groups for non-port vlans"); + return -EINVAL; + } + if (br_multicast_port_ctx_vlan_disabled(&v->port_mcast_ctx)) { + NL_SET_ERR_MSG_MOD(extack, "Multicast snooping disabled on this VLAN"); + return -EINVAL; + } + + val = nla_get_u32(tb[BRIDGE_VLANDB_ENTRY_MCAST_MAX_GROUPS]); + br_multicast_ngroups_set_max(&v->port_mcast_ctx, val); + *changed = true; + } #endif return 0; diff --git a/net/can/gw.c b/net/can/gw.c index 23a3d89cad81..37528826935e 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -1139,6 +1139,13 @@ static int cgw_create_job(struct sk_buff *skb, struct nlmsghdr *nlh, if (gwj->dst.dev->type != ARPHRD_CAN) goto out; + /* is sending the skb back to the incoming interface intended? */ + if (gwj->src.dev == gwj->dst.dev && + !(gwj->flags & CGW_FLAGS_CAN_IIF_TX_OK)) { + err = -EINVAL; + goto out; + } + ASSERT_RTNL(); err = cgw_register_filter(net, gwj); diff --git a/net/can/isotp.c b/net/can/isotp.c index fc81d77724a1..9bc344851704 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1220,6 +1220,9 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (len < ISOTP_MIN_NAMELEN) return -EINVAL; + if (addr->can_family != AF_CAN) + return -EINVAL; + /* sanitize tx CAN identifier */ if (tx_id & CAN_EFF_FLAG) tx_id &= (CAN_EFF_FLAG | CAN_EFF_MASK); diff --git a/net/can/j1939/address-claim.c b/net/can/j1939/address-claim.c index f33c47327927..ca4ad6cdd5cb 100644 --- a/net/can/j1939/address-claim.c +++ b/net/can/j1939/address-claim.c @@ -165,6 +165,46 @@ static void j1939_ac_process(struct j1939_priv *priv, struct sk_buff *skb) * leaving this function. */ ecu = j1939_ecu_get_by_name_locked(priv, name); + + if (ecu && ecu->addr == skcb->addr.sa) { + /* The ISO 11783-5 standard, in "4.5.2 - Address claim + * requirements", states: + * d) No CF shall begin, or resume, transmission on the + * network until 250 ms after it has successfully claimed + * an address except when responding to a request for + * address-claimed. + * + * But "Figure 6" and "Figure 7" in "4.5.4.2 - Address-claim + * prioritization" show that the CF begins the transmission + * after 250 ms from the first AC (address-claimed) message + * even if it sends another AC message during that time window + * to resolve the address contention with another CF. + * + * As stated in "4.4.2.3 - Address-claimed message": + * In order to successfully claim an address, the CF sending + * an address claimed message shall not receive a contending + * claim from another CF for at least 250 ms. + * + * As stated in "4.4.3.2 - NAME management (NM) message": + * 1) A commanding CF can + * d) request that a CF with a specified NAME transmit + * the address-claimed message with its current NAME. + * 2) A target CF shall + * d) send an address-claimed message in response to a + * request for a matching NAME + * + * Taking the above arguments into account, the 250 ms wait is + * requested only during network initialization. + * + * Do not restart the timer on AC message if both the NAME and + * the address match and so if the address has already been + * claimed (timer has expired) or the AC message has been sent + * to resolve the contention with another CF (timer is still + * running). + */ + goto out_ecu_put; + } + if (!ecu && j1939_address_is_unicast(skcb->addr.sa)) ecu = j1939_ecu_create_locked(priv, name); diff --git a/net/can/raw.c b/net/can/raw.c index ba86782ba8bb..f64469b98260 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -523,6 +523,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, struct can_filter sfilter; /* single filter */ struct net_device *dev = NULL; can_err_mask_t err_mask = 0; + int fd_frames; int count = 0; int err = 0; @@ -664,17 +665,17 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, break; case CAN_RAW_FD_FRAMES: - if (optlen != sizeof(ro->fd_frames)) + if (optlen != sizeof(fd_frames)) return -EINVAL; - if (copy_from_sockptr(&ro->fd_frames, optval, optlen)) + if (copy_from_sockptr(&fd_frames, optval, optlen)) return -EFAULT; /* Enabling CAN XL includes CAN FD */ - if (ro->xl_frames && !ro->fd_frames) { - ro->fd_frames = ro->xl_frames; + if (ro->xl_frames && !fd_frames) return -EINVAL; - } + + ro->fd_frames = fd_frames; break; case CAN_RAW_XL_FRAMES: diff --git a/net/core/Makefile b/net/core/Makefile index 10edd66a8a37..8f367813bc68 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o flow_offload.o gro.o + fib_notifier.o xdp.o flow_offload.o gro.o \ + netdev-genl.o netdev-genl-gen.o obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o diff --git a/net/core/dev.c b/net/core/dev.c index bb42150a38ec..7307a0c15c9f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) + N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; diff --git a/net/core/dev.h b/net/core/dev.h index a065b7571441..e075e198092c 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -9,6 +9,7 @@ struct net_device; struct netdev_bpf; struct netdev_phys_item_id; struct netlink_ext_ack; +struct cpumask; /* Random bits of netdevice that don't need to be exposed */ #define FLOW_LIMIT_HISTORY (1 << 7) /* must be ^2 and !overflow buckets */ @@ -134,4 +135,5 @@ static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, WRITE_ONCE(dev->gro_ipv4_max_size, size); } +int rps_cpumask_housekeeping(struct cpumask *mask); #endif diff --git a/net/core/filter.c b/net/core/filter.c index d8f9b53f3db6..2ce06a72a5ba 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4318,16 +4318,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; - /* XDP_REDIRECT is not fully supported yet for xdp frags since - * not all XDP capable drivers can map non-linear xdp_frame in - * ndo_xdp_xmit. - */ - if (unlikely(xdp_buff_has_frags(xdp) && - map_type != BPF_MAP_TYPE_CPUMAP)) - return -EOPNOTSUPP; + if (map_type == BPF_MAP_TYPE_XSKMAP) { + /* XDP_REDIRECT is not supported AF_XDP yet. */ + if (unlikely(xdp_buff_has_frags(xdp))) + return -EOPNOTSUPP; - if (map_type == BPF_MAP_TYPE_XSKMAP) return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + } return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), xdp_prog); @@ -7536,7 +7533,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = { .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct iphdr), .arg2_type = ARG_PTR_TO_MEM, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph, @@ -7568,7 +7565,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = { .arg1_type = ARG_PTR_TO_FIXED_SIZE_MEM, .arg1_size = sizeof(struct ipv6hdr), .arg2_type = ARG_PTR_TO_MEM, - .arg3_type = ARG_CONST_SIZE, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph, diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 57258110bccd..6798f6d2423b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -269,7 +269,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || - time_after(tref, n->updated)) + !time_in_range(n->updated, tref, jiffies)) remove = true; write_unlock(&n->lock); @@ -289,7 +289,17 @@ static int neigh_forced_gc(struct neigh_table *tbl) static void neigh_add_timer(struct neighbour *n, unsigned long when) { + /* Use safe distance from the jiffies - LONG_MAX point while timer + * is running in DELAY/PROBE state but still show to user space + * large times in the past. + */ + unsigned long mint = jiffies - (LONG_MAX - 86400 * HZ); + neigh_hold(n); + if (!time_in_range(n->confirmed, mint, jiffies)) + n->confirmed = mint; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; if (unlikely(mod_timer(&n->timer, when))) { printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state); @@ -1001,12 +1011,14 @@ static void neigh_periodic_work(struct work_struct *work) goto next_elt; } - if (time_before(n->used, n->confirmed)) + if (time_before(n->used, n->confirmed) && + time_is_before_eq_jiffies(n->confirmed)) n->used = n->confirmed; if (refcount_read(&n->refcnt) == 1 && (state == NUD_FAILED || - time_after(jiffies, n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { + !time_in_range_open(jiffies, n->used, + n->used + NEIGH_VAR(n->parms, GC_STALETIME)))) { *np = n->next; neigh_mark_dead(n); write_unlock(&n->lock); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ca55dd747d6c..4b361ac6a252 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -831,42 +831,18 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf) return len < PAGE_SIZE ? len : -EINVAL; } -static ssize_t store_rps_map(struct netdev_rx_queue *queue, - const char *buf, size_t len) +static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue, + cpumask_var_t mask) { - struct rps_map *old_map, *map; - cpumask_var_t mask; - int err, cpu, i; static DEFINE_MUTEX(rps_map_mutex); - - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); - if (err) { - free_cpumask_var(mask); - return err; - } - - if (!cpumask_empty(mask)) { - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); - cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); - if (cpumask_empty(mask)) { - free_cpumask_var(mask); - return -EINVAL; - } - } + struct rps_map *old_map, *map; + int cpu, i; map = kzalloc(max_t(unsigned int, RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES), GFP_KERNEL); - if (!map) { - free_cpumask_var(mask); + if (!map) return -ENOMEM; - } i = 0; for_each_cpu_and(cpu, mask, cpu_online_mask) @@ -893,9 +869,45 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, if (old_map) kfree_rcu(old_map, rcu); + return 0; +} +int rps_cpumask_housekeeping(struct cpumask *mask) +{ + if (!cpumask_empty(mask)) { + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ)); + if (cpumask_empty(mask)) + return -EINVAL; + } + return 0; +} + +static ssize_t store_rps_map(struct netdev_rx_queue *queue, + const char *buf, size_t len) +{ + cpumask_var_t mask; + int err; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) + goto out; + + err = rps_cpumask_housekeeping(mask); + if (err) + goto out; + + err = netdev_rx_queue_set_rps_mask(queue, mask); + +out: free_cpumask_var(mask); - return len; + return err ? : len; } static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, @@ -1071,6 +1083,13 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) goto err; } +#if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL) + if (!cpumask_empty(&rps_default_mask)) { + error = netdev_rx_queue_set_rps_mask(queue, &rps_default_mask); + if (error) + goto err; + } +#endif kobject_uevent(kobj, KOBJ_ADD); return error; diff --git a/net/core/net-traces.c b/net/core/net-traces.c index ee7006bbe49b..805b7385dd8d 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -41,6 +41,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_add); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_external_learn_add); EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); +EXPORT_TRACEPOINT_SYMBOL_GPL(br_mdb_full); #endif #if IS_ENABLED(CONFIG_PAGE_POOL) diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c new file mode 100644 index 000000000000..48812ec843f5 --- /dev/null +++ b/net/core/netdev-genl-gen.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: BSD-3-Clause +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "netdev-genl-gen.h" + +#include <linux/netdev.h> + +/* NETDEV_CMD_DEV_GET - do */ +static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = { + [NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1), +}; + +/* Ops table for netdev */ +static const struct genl_split_ops netdev_nl_ops[2] = { + { + .cmd = NETDEV_CMD_DEV_GET, + .doit = netdev_nl_dev_get_doit, + .policy = netdev_dev_get_nl_policy, + .maxattr = NETDEV_A_DEV_IFINDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = NETDEV_CMD_DEV_GET, + .dumpit = netdev_nl_dev_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, +}; + +static const struct genl_multicast_group netdev_nl_mcgrps[] = { + [NETDEV_NLGRP_MGMT] = { "mgmt", }, +}; + +struct genl_family netdev_nl_family __ro_after_init = { + .name = NETDEV_FAMILY_NAME, + .version = NETDEV_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = netdev_nl_ops, + .n_split_ops = ARRAY_SIZE(netdev_nl_ops), + .mcgrps = netdev_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(netdev_nl_mcgrps), +}; diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h new file mode 100644 index 000000000000..b16dc7e026bb --- /dev/null +++ b/net/core/netdev-genl-gen.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_NETDEV_GEN_H +#define _LINUX_NETDEV_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <linux/netdev.h> + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info); +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); + +enum { + NETDEV_NLGRP_MGMT, +}; + +extern struct genl_family netdev_nl_family; + +#endif /* _LINUX_NETDEV_GEN_H */ diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c new file mode 100644 index 000000000000..a4270fafdf11 --- /dev/null +++ b/net/core/netdev-genl.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/netdevice.h> +#include <linux/notifier.h> +#include <linux/rtnetlink.h> +#include <net/net_namespace.h> +#include <net/sock.h> + +#include "netdev-genl-gen.h" + +static int +netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp, + u32 portid, u32 seq, int flags, u32 cmd) +{ + void *hdr; + + hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) || + nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES, + netdev->xdp_features, NETDEV_A_DEV_PAD)) { + genlmsg_cancel(rsp, hdr); + return -EINVAL; + } + + genlmsg_end(rsp, hdr); + + return 0; +} + +static void +netdev_genl_dev_notify(struct net_device *netdev, int cmd) +{ + struct sk_buff *ntf; + + if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev), + NETDEV_NLGRP_MGMT)) + return; + + ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!ntf) + return; + + if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) { + nlmsg_free(ntf); + return; + } + + genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf, + 0, NETDEV_NLGRP_MGMT, GFP_KERNEL); +} + +int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct net_device *netdev; + struct sk_buff *rsp; + u32 ifindex; + int err; + + if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX)) + return -EINVAL; + + ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]); + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + rtnl_lock(); + + netdev = __dev_get_by_index(genl_info_net(info), ifindex); + if (netdev) + err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid, + info->snd_seq, 0, info->genlhdr->cmd); + else + err = -ENODEV; + + rtnl_unlock(); + + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + int idx = 0, s_idx; + int h, s_h; + int err; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rtnl_lock(); + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + struct hlist_head *head; + + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(netdev, head, index_hlist) { + if (idx < s_idx) + goto cont; + err = netdev_nl_dev_fill(netdev, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NETDEV_CMD_DEV_GET); + if (err < 0) + break; +cont: + idx++; + } + } + + rtnl_unlock(); + + if (err != -EMSGSIZE) + return err; + + cb->args[1] = idx; + cb->args[0] = h; + cb->seq = net->dev_base_seq; + + return skb->len; +} + +static int netdev_genl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_REGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF); + break; + case NETDEV_UNREGISTER: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF); + break; + case NETDEV_XDP_FEAT_CHANGE: + netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF); + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block netdev_genl_nb = { + .notifier_call = netdev_genl_netdevice_event, +}; + +static int __init netdev_genl_init(void) +{ + int err; + + err = register_netdevice_notifier(&netdev_genl_nb); + if (err) + return err; + + err = genl_register_family(&netdev_nl_family); + if (err) + goto err_unreg_ntf; + + return 0; + +err_unreg_ntf: + unregister_netdevice_notifier(&netdev_genl_nb); + return err; +} + +subsys_initcall(netdev_genl_init); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b203d8660e4..193c18799865 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -511,8 +511,8 @@ static void page_pool_return_page(struct page_pool *pool, struct page *page) static bool page_pool_recycle_in_ring(struct page_pool *pool, struct page *page) { int ret; - /* BH protection not needed if current is serving softirq */ - if (in_serving_softirq()) + /* BH protection not needed if current is softirq */ + if (in_softirq()) ret = ptr_ring_produce(&pool->ring, page); else ret = ptr_ring_produce_bh(&pool->ring, page); @@ -570,7 +570,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, page_pool_dma_sync_for_device(pool, page, dma_sync_size); - if (allow_direct && in_serving_softirq() && + if (allow_direct && in_softirq() && page_pool_recycle_in_cache(page, pool)) return NULL; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b9f584955b77..5d8eb57867a9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -58,7 +58,7 @@ #include "dev.h" #define RTNL_MAX_TYPE 50 -#define RTNL_SLAVE_MAX_TYPE 40 +#define RTNL_SLAVE_MAX_TYPE 42 struct rtnl_link { rtnl_doit_func doit; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 44a19805c355..13ea10cf8544 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -84,11 +84,39 @@ #include "dev.h" #include "sock_destructor.h" -struct kmem_cache *skbuff_head_cache __ro_after_init; +struct kmem_cache *skbuff_cache __ro_after_init; static struct kmem_cache *skbuff_fclone_cache __ro_after_init; #ifdef CONFIG_SKB_EXTENSIONS static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif + +/* skb_small_head_cache and related code is only supported + * for CONFIG_SLAB and CONFIG_SLUB. + * As soon as SLOB is removed from the kernel, we can clean up this. + */ +#if !defined(CONFIG_SLOB) +# define HAVE_SKB_SMALL_HEAD_CACHE 1 +#endif + +#ifdef HAVE_SKB_SMALL_HEAD_CACHE +static struct kmem_cache *skb_small_head_cache __ro_after_init; + +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) + +/* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. + * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique + * size, and we can differentiate heads from skb_small_head_cache + * vs system slabs by looking at their size (skb_end_offset()). + */ +#define SKB_SMALL_HEAD_CACHE_SIZE \ + (is_power_of_2(SKB_SMALL_HEAD_SIZE) ? \ + (SKB_SMALL_HEAD_SIZE + L1_CACHE_BYTES) : \ + SKB_SMALL_HEAD_SIZE) + +#define SKB_SMALL_HEAD_HEADROOM \ + SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) +#endif /* HAVE_SKB_SMALL_HEAD_CACHE */ + int sysctl_max_skb_frags __read_mostly = MAX_SKB_FRAGS; EXPORT_SYMBOL(sysctl_max_skb_frags); @@ -257,7 +285,7 @@ static struct sk_buff *napi_skb_cache_get(void) struct sk_buff *skb; if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(skbuff_head_cache, + nc->skb_count = kmem_cache_alloc_bulk(skbuff_cache, GFP_ATOMIC, NAPI_SKB_CACHE_BULK, nc->skb_cache); @@ -266,7 +294,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_unpoison_object_data(skbuff_head_cache, skb); + kasan_unpoison_object_data(skbuff_cache, skb); return skb; } @@ -324,7 +352,7 @@ struct sk_buff *slab_build_skb(void *data) struct sk_buff *skb; unsigned int size; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -375,7 +403,7 @@ struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -478,17 +506,37 @@ EXPORT_SYMBOL(napi_build_skb); * may be used. Otherwise, the packet data may be discarded until enough * memory is free */ -static void *kmalloc_reserve(size_t size, gfp_t flags, int node, +static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, bool *pfmemalloc) { - void *obj; bool ret_pfmemalloc = false; + unsigned int obj_size; + void *obj; + + obj_size = SKB_HEAD_ALIGN(*size); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (obj_size <= SKB_SMALL_HEAD_CACHE_SIZE && + !(flags & KMALLOC_NOT_NORMAL_BITS)) { + /* skb_small_head_cache has non power of two size, + * likely forcing SLUB to use order-3 pages. + * We deliberately attempt a NOMEMALLOC allocation only. + */ + obj = kmem_cache_alloc_node(skb_small_head_cache, + flags | __GFP_NOMEMALLOC | __GFP_NOWARN, + node); + if (obj) { + *size = SKB_SMALL_HEAD_CACHE_SIZE; + goto out; + } + } +#endif + *size = obj_size = kmalloc_size_roundup(obj_size); /* * Try a regular allocation, when that fails and we're not entitled * to the reserves, fail. */ - obj = kmalloc_node_track_caller(size, + obj = kmalloc_node_track_caller(obj_size, flags | __GFP_NOMEMALLOC | __GFP_NOWARN, node); if (obj || !(gfp_pfmemalloc_allowed(flags))) @@ -496,7 +544,7 @@ static void *kmalloc_reserve(size_t size, gfp_t flags, int node, /* Try again but now we are using pfmemalloc reserves */ ret_pfmemalloc = true; - obj = kmalloc_node_track_caller(size, flags, node); + obj = kmalloc_node_track_caller(obj_size, flags, node); out: if (pfmemalloc) @@ -533,12 +581,11 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - unsigned int osize; bool pfmemalloc; u8 *data; cache = (flags & SKB_ALLOC_FCLONE) - ? skbuff_fclone_cache : skbuff_head_cache; + ? skbuff_fclone_cache : skbuff_cache; if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; @@ -558,18 +605,14 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * aligned memory blocks, unless SLUB/SLAB debug is enabled. * Both skb->head and skb_shared_info are cache line aligned. */ - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - osize = kmalloc_size_roundup(size); - data = kmalloc_reserve(osize, gfp_mask, node, &pfmemalloc); + data = kmalloc_reserve(&size, gfp_mask, node, &pfmemalloc); if (unlikely(!data)) goto nodata; /* kmalloc_size_roundup() might give us more room than requested. * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(osize); - prefetchw(data + size); + prefetchw(data + SKB_WITH_OVERHEAD(size)); /* * Only clear those fields we need to clear, not those that we will @@ -577,7 +620,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, osize); + __build_skb_around(skb, data, size); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { @@ -632,8 +675,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, goto skb_success; } - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; @@ -732,8 +774,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, data = page_frag_alloc_1k(&nc->page_small, gfp_mask); pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); } else { - len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - len = SKB_DATA_ALIGN(len); + len = SKB_HEAD_ALIGN(len); data = page_frag_alloc(&nc->page, len, gfp_mask); pfmemalloc = nc->page.pfmemalloc; @@ -809,6 +850,16 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data) return page_pool_return_skb_page(virt_to_page(data)); } +static void skb_kfree_head(void *head, unsigned int end_offset) +{ +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + if (end_offset == SKB_SMALL_HEAD_HEADROOM) + kmem_cache_free(skb_small_head_cache, head); + else +#endif + kfree(head); +} + static void skb_free_head(struct sk_buff *skb) { unsigned char *head = skb->head; @@ -818,7 +869,7 @@ static void skb_free_head(struct sk_buff *skb) return; skb_free_frag(head); } else { - kfree(head); + skb_kfree_head(head, skb_end_offset(skb)); } } @@ -870,7 +921,7 @@ static void kfree_skbmem(struct sk_buff *skb) switch (skb->fclone) { case SKB_FCLONE_UNAVAILABLE: - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); return; case SKB_FCLONE_ORIG: @@ -984,7 +1035,7 @@ static void kfree_skb_add_bulk(struct sk_buff *skb, sa->skb_array[sa->skb_count++] = skb; if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) { - kmem_cache_free_bulk(skbuff_head_cache, KFREE_SKB_BULK_SIZE, + kmem_cache_free_bulk(skbuff_cache, KFREE_SKB_BULK_SIZE, sa->skb_array); sa->skb_count = 0; } @@ -1000,15 +1051,16 @@ kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason) while (segs) { struct sk_buff *next = segs->next; - if (__kfree_skb_reason(segs, reason)) + if (__kfree_skb_reason(segs, reason)) { + skb_poison_list(segs); kfree_skb_add_bulk(segs, &sa, reason); + } segs = next; } if (sa.skb_count) - kmem_cache_free_bulk(skbuff_head_cache, sa.skb_count, - sa.skb_array); + kmem_cache_free_bulk(skbuff_cache, sa.skb_count, sa.skb_array); } EXPORT_SYMBOL(kfree_skb_list_reason); @@ -1162,15 +1214,15 @@ static void napi_skb_cache_put(struct sk_buff *skb) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; - kasan_poison_object_data(skbuff_head_cache, skb); + kasan_poison_object_data(skbuff_cache, skb); nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) - kasan_unpoison_object_data(skbuff_head_cache, + kasan_unpoison_object_data(skbuff_cache, nc->skb_cache[i]); - kmem_cache_free_bulk(skbuff_head_cache, NAPI_SKB_CACHE_HALF, + kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); nc->skb_count = NAPI_SKB_CACHE_HALF; } @@ -1754,7 +1806,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - n = kmem_cache_alloc(skbuff_head_cache, gfp_mask); + n = kmem_cache_alloc(skbuff_cache, gfp_mask); if (!n) return NULL; @@ -1936,10 +1988,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) goto nodata; size = SKB_WITH_OVERHEAD(size); @@ -2002,7 +2051,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, return 0; nofrags: - kfree(data); + skb_kfree_head(data, size); nodata: return -ENOMEM; } @@ -4627,7 +4676,7 @@ static void skb_extensions_init(void) {} void __init skb_init(void) { - skbuff_head_cache = kmem_cache_create_usercopy("skbuff_head_cache", + skbuff_cache = kmem_cache_create_usercopy("skbuff_head_cache", sizeof(struct sk_buff), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, @@ -4639,6 +4688,19 @@ void __init skb_init(void) 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +#ifdef HAVE_SKB_SMALL_HEAD_CACHE + /* usercopy should only access first SKB_SMALL_HEAD_HEADROOM bytes. + * struct skb_shared_info is located at the end of skb->head, + * and should not be copied to/from user. + */ + skb_small_head_cache = kmem_cache_create_usercopy("skbuff_small_head", + SKB_SMALL_HEAD_CACHE_SIZE, + 0, + SLAB_HWCACHE_ALIGN | SLAB_PANIC, + 0, + SKB_SMALL_HEAD_HEADROOM, + NULL); +#endif skb_extensions_init(); } @@ -5493,7 +5555,7 @@ void kfree_skb_partial(struct sk_buff *skb, bool head_stolen) { if (head_stolen) { skb_release_head_state(skb); - kmem_cache_free(skbuff_head_cache, skb); + kmem_cache_free(skbuff_cache, skb); } else { __kfree_skb(skb); } @@ -6287,10 +6349,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6306,7 +6365,7 @@ static int pskb_carve_inside_header(struct sk_buff *skb, const u32 off, if (skb_cloned(skb)) { /* drop the old head gracefully */ if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) @@ -6406,10 +6465,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_pfmemalloc(skb)) gfp_mask |= __GFP_MEMALLOC; - size = SKB_DATA_ALIGN(size); - size += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - size = kmalloc_size_roundup(size); - data = kmalloc_reserve(size, gfp_mask, NUMA_NO_NODE, NULL); + data = kmalloc_reserve(&size, gfp_mask, NUMA_NO_NODE, NULL); if (!data) return -ENOMEM; size = SKB_WITH_OVERHEAD(size); @@ -6417,7 +6473,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, memcpy((struct skb_shared_info *)(data + size), skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } shinfo = (struct skb_shared_info *)(data + size); @@ -6453,7 +6509,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ if (skb_has_frag_list(skb)) kfree_skb_list(skb_shinfo(skb)->frag_list); - kfree(data); + skb_kfree_head(data, size); return -ENOMEM; } skb_release_data(skb, SKB_CONSUMED); diff --git a/net/core/sock.c b/net/core/sock.c index f08b76acde9b..afbb02984d5f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1531,6 +1531,8 @@ set_sndbuf: ret = -EINVAL; break; } + if ((u8)val == SOCK_TXREHASH_DEFAULT) + val = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); /* Paired with READ_ONCE() in tcp_rtx_synack() */ WRITE_ONCE(sk->sk_txrehash, (u8)val); break; @@ -3383,7 +3385,7 @@ void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) } EXPORT_SYMBOL(sk_stop_timer_sync); -void sock_init_data(struct socket *sock, struct sock *sk) +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; @@ -3403,11 +3405,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_type = sock->type; RCU_INIT_POINTER(sk->sk_wq, &sock->wq); sock->sk = sk; - sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { RCU_INIT_POINTER(sk->sk_wq, NULL); - sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } + sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) @@ -3455,7 +3456,6 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_pacing_rate = ~0UL; WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; - sk->sk_txrehash = SOCK_TXREHASH_DEFAULT; sk_rx_queue_clear(sk); /* @@ -3466,6 +3466,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data_uid); + +void sock_init_data(struct socket *sock, struct sock *sk) +{ + kuid_t uid = sock ? + SOCK_INODE(sock)->i_uid : + make_kuid(sock_net(sk)->user_ns, 0); + + sock_init_data_uid(sock, sk, uid); +} EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index e7b98162c632..7130e6d9e263 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -16,6 +16,7 @@ #include <linux/vmalloc.h> #include <linux/init.h> #include <linux/slab.h> +#include <linux/sched/isolation.h> #include <net/ip.h> #include <net/sock.h> @@ -45,7 +46,59 @@ EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); int sysctl_devconf_inherit_init_net __read_mostly; EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); +#if IS_ENABLED(CONFIG_NET_FLOW_LIMIT) || IS_ENABLED(CONFIG_RPS) +static void dump_cpumask(void *buffer, size_t *lenp, loff_t *ppos, + struct cpumask *mask) +{ + char kbuf[128]; + int len; + + if (*ppos || !*lenp) { + *lenp = 0; + return; + } + + len = min(sizeof(kbuf) - 1, *lenp); + len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); + if (!len) { + *lenp = 0; + return; + } + + if (len < *lenp) + kbuf[len++] = '\n'; + memcpy(buffer, kbuf, len); + *lenp = len; + *ppos += len; +} +#endif + #ifdef CONFIG_RPS +struct cpumask rps_default_mask; + +static int rps_default_mask_sysctl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int err = 0; + + rtnl_lock(); + if (write) { + err = cpumask_parse(buffer, &rps_default_mask); + if (err) + goto done; + + err = rps_cpumask_housekeeping(&rps_default_mask); + if (err) + goto done; + } else { + dump_cpumask(buffer, lenp, ppos, &rps_default_mask); + } + +done: + rtnl_unlock(); + return err; +} + static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -155,13 +208,6 @@ static int flow_limit_cpu_sysctl(struct ctl_table *table, int write, write_unlock: mutex_unlock(&flow_limit_update_mutex); } else { - char kbuf[128]; - - if (*ppos || !*lenp) { - *lenp = 0; - goto done; - } - cpumask_clear(mask); rcu_read_lock(); for_each_possible_cpu(i) { @@ -171,17 +217,7 @@ write_unlock: } rcu_read_unlock(); - len = min(sizeof(kbuf) - 1, *lenp); - len = scnprintf(kbuf, len, "%*pb", cpumask_pr_args(mask)); - if (!len) { - *lenp = 0; - goto done; - } - if (len < *lenp) - kbuf[len++] = '\n'; - memcpy(buffer, kbuf, len); - *lenp = len; - *ppos += len; + dump_cpumask(buffer, lenp, ppos, mask); } done: @@ -472,6 +508,11 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = rps_sock_flow_sysctl }, + { + .procname = "rps_default_mask", + .mode = 0644, + .proc_handler = rps_default_mask_sysctl + }, #endif #ifdef CONFIG_NET_FLOW_LIMIT { @@ -675,6 +716,10 @@ static __net_initdata struct pernet_operations sysctl_core_ops = { static __init int sysctl_core_init(void) { +#if IS_ENABLED(CONFIG_RPS) + cpumask_copy(&rps_default_mask, cpu_none_mask); +#endif + register_net_sysctl(&init_net, "net/core", net_core_table); return register_pernet_subsys(&sysctl_core_ops); } diff --git a/net/core/xdp.c b/net/core/xdp.c index a5a7ecf6391c..8c92fc553317 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -4,6 +4,7 @@ * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/types.h> @@ -603,8 +604,7 @@ EXPORT_SYMBOL_GPL(xdp_warn); int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp) { - n_skb = kmem_cache_alloc_bulk(skbuff_head_cache, gfp, - n_skb, skbs); + n_skb = kmem_cache_alloc_bulk(skbuff_cache, gfp, n_skb, skbs); if (unlikely(!n_skb)) return -ENOMEM; @@ -673,7 +673,7 @@ struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf, { struct sk_buff *skb; - skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC); + skb = kmem_cache_alloc(skbuff_cache, GFP_ATOMIC); if (unlikely(!skb)) return NULL; @@ -722,7 +722,7 @@ __diag_ignore_all("-Wmissing-prototypes", * * Returns 0 on success or ``-errno`` on error. */ -int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) +__bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { return -EOPNOTSUPP; } @@ -734,7 +734,7 @@ int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) * * Returns 0 on success or ``-errno`` on error. */ -int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) { return -EOPNOTSUPP; } @@ -773,3 +773,21 @@ static int __init xdp_metadata_init(void) return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set); } late_initcall(xdp_metadata_init); + +void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg) +{ + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; + if (support_sg) + dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG; + + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); +} +EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target); + +void xdp_features_clear_redirect_target(struct net_device *dev) +{ + dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT | + NETDEV_XDP_ACT_NDO_XMIT_SG); + call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev); +} +EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target); diff --git a/net/devlink/Makefile b/net/devlink/Makefile index 1b1eeac59cb3..daad4521c61e 100644 --- a/net/devlink/Makefile +++ b/net/devlink/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y := leftover.o core.o netlink.o +obj-y := leftover.o core.o netlink.o dev.o diff --git a/net/devlink/core.c b/net/devlink/core.c index aeffd1b8206d..a4f47dafb864 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -205,7 +205,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, goto err_xa_alloc; devlink->netdevice_nb.notifier_call = devlink_port_netdevice_event; - ret = register_netdevice_notifier_net(net, &devlink->netdevice_nb); + ret = register_netdevice_notifier(&devlink->netdevice_nb); if (ret) goto err_register_netdevice_notifier; @@ -266,8 +266,7 @@ void devlink_free(struct devlink *devlink) xa_destroy(&devlink->snapshot_ids); xa_destroy(&devlink->ports); - WARN_ON_ONCE(unregister_netdevice_notifier_net(devlink_net(devlink), - &devlink->netdevice_nb)); + WARN_ON_ONCE(unregister_netdevice_notifier(&devlink->netdevice_nb)); xa_erase(&devlinks, devlink->index); diff --git a/net/devlink/dev.c b/net/devlink/dev.c new file mode 100644 index 000000000000..78d824eda5ec --- /dev/null +++ b/net/devlink/dev.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (c) 2016 Mellanox Technologies. All rights reserved. + * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> + */ + +#include <net/genetlink.h> +#include <net/sock.h> +#include "devl_internal.h" + +struct devlink_info_req { + struct sk_buff *msg; + void (*version_cb)(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv); + void *version_cb_priv; +}; + +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int +devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr, *act_info, *act_stats; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && + !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC) + continue; + act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); + if (!act_info) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) + goto action_info_nest_cancel; + act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); + if (!act_stats) + goto action_info_nest_cancel; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. + * Stats of actions with unspecified limit are shown + * though drivers don't need to register unspecified + * limit. + */ + if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, j, value)) + goto action_stats_nest_cancel; + } + nla_nest_end(msg, act_stats); + nla_nest_end(msg, act_info); + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +action_stats_nest_cancel: + nla_nest_cancel(msg, act_stats); +action_info_nest_cancel: + nla_nest_cancel(msg, act_info); +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + +static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *dev_stats; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) + goto nla_put_failure; + + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); + genlmsg_end(msg, hdr); + return 0; + +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +void devlink_notify(struct devlink *devlink, enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI); +} + +const struct devlink_cmd devl_cmd_get = { + .dump_one = devlink_nl_cmd_get_dump_one, +}; + +static void devlink_reload_failed_set(struct devlink *devlink, + bool reload_failed) +{ + if (devlink->reload_failed == reload_failed) + return; + devlink->reload_failed = reload_failed; + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +bool devlink_is_reload_failed(const struct devlink *devlink) +{ + return devlink->reload_failed; +} +EXPORT_SYMBOL_GPL(devlink_is_reload_failed); + +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *curr_net, + struct net *dest_net) +{ + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + devlink_notify_unregister(devlink); + move_netdevice_notifier_net(curr_net, dest_net, + &devlink->netdevice_nb); + write_pnet(&devlink->_net, dest_net); + devlink_notify_register(devlink); +} + +int devlink_reload(struct devlink *devlink, struct net *dest_net, + enum devlink_reload_action action, + enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) +{ + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + struct net *curr_net; + int err; + + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + + err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); + if (err) + return err; + + curr_net = devlink_net(devlink); + if (dest_net && !net_eq(dest_net, curr_net)) + devlink_reload_netns_change(devlink, curr_net, dest_net); + + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); + devlink_reload_failed_set(devlink, !!err); + if (err) + return err; + + WARN_ON(!(*actions_performed & BIT(action))); + /* Catch driver on updating the remote action within devlink reload */ + WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; + struct net *dest_net = NULL; + u32 actions_performed; + int err; + + err = devlink_resources_validate(devlink, NULL, info); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); + return err; + } + + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); + + if (dest_net) + put_net(dest_net); + + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); +} + +bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + +static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + void *hdr; + int err = 0; + u16 mode; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = devlink_nl_put_handle(msg, devlink); + if (err) + goto nla_put_failure; + + if (ops->eswitch_mode_get) { + err = ops->eswitch_mode_get(devlink, &mode); + if (err) + goto nla_put_failure; + err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_inline_mode_get) { + err = ops->eswitch_inline_mode_get(devlink, &inline_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, + inline_mode); + if (err) + goto nla_put_failure; + } + + if (ops->eswitch_encap_mode_get) { + err = ops->eswitch_encap_mode_get(devlink, &encap_mode); + if (err) + goto nla_put_failure; + err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); + if (err) + goto nla_put_failure; + } + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, + info->snd_portid, info->snd_seq, 0); + + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const struct devlink_ops *ops = devlink->ops; + enum devlink_eswitch_encap_mode encap_mode; + u8 inline_mode; + int err = 0; + u16 mode; + + if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { + if (!ops->eswitch_mode_set) + return -EOPNOTSUPP; + mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); + err = devlink_rate_nodes_check(devlink, mode, info->extack); + if (err) + return err; + err = ops->eswitch_mode_set(devlink, mode, info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { + if (!ops->eswitch_inline_mode_set) + return -EOPNOTSUPP; + inline_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); + err = ops->eswitch_inline_mode_set(devlink, inline_mode, + info->extack); + if (err) + return err; + } + + if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { + if (!ops->eswitch_encap_mode_set) + return -EOPNOTSUPP; + encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); + err = ops->eswitch_encap_mode_set(devlink, encap_mode, + info->extack); + if (err) + return err; + } + + return 0; +} + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +int devlink_info_board_serial_number_put(struct devlink_info_req *req, + const char *bsn) +{ + if (!req->msg) + return 0; + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, + bsn); +} +EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + struct nlattr *nest; + int err; + + if (req->version_cb) + req->version_cb(version_name, version_type, + req->version_cb_priv); + + if (!req->msg) + return 0; + + nest = nla_nest_start_noflag(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_stored_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + DEVLINK_INFO_VERSION_TYPE_NONE); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +int devlink_info_version_running_put_ext(struct devlink_info_req *req, + const char *version_name, + const char *version_value, + enum devlink_info_version_type version_type) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value, + version_type); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); + +static int devlink_nl_driver_info_get(struct device_driver *drv, + struct devlink_info_req *req) +{ + if (!drv) + return 0; + + if (drv->name[0]) + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, + drv->name); + + return 0; +} + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct device *dev = devlink_to_dev(devlink); + struct devlink_info_req req = {}; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + if (devlink->ops->info_get) { + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + } + + err = devlink_nl_driver_info_get(dev->driver, &req); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, + struct netlink_callback *cb) +{ + int err; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + if (err == -EOPNOTSUPP) + err = 0; + return err; +} + +const struct devlink_cmd devl_cmd_info_get = { + .dump_one = devlink_nl_cmd_info_get_dump_one, +}; + +static int devlink_nl_flash_update_fill(struct sk_buff *msg, + struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + void *hdr; + + hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) + goto out; + + if (params->status_msg && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, + params->status_msg)) + goto nla_put_failure; + if (params->component && + nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, + params->component)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, + params->done, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + +out: + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static void __devlink_flash_update_notify(struct devlink *devlink, + enum devlink_command cmd, + struct devlink_flash_notify *params) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && + cmd != DEVLINK_CMD_FLASH_UPDATE_END && + cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); + if (err) + goto out_free_msg; + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + return; + +out_free_msg: + nlmsg_free(msg); +} + +static void devlink_flash_update_begin_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE, + ¶ms); +} + +static void devlink_flash_update_end_notify(struct devlink *devlink) +{ + struct devlink_flash_notify params = {}; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_END, + ¶ms); +} + +void devlink_flash_update_status_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long done, + unsigned long total) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); + +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + +struct devlink_flash_component_lookup_ctx { + const char *lookup_name; + bool lookup_name_found; +}; + +static void +devlink_flash_component_lookup_cb(const char *version_name, + enum devlink_info_version_type version_type, + void *version_cb_priv) +{ + struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; + + if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || + lookup_ctx->lookup_name_found) + return; + + lookup_ctx->lookup_name_found = + !strcmp(lookup_ctx->lookup_name, version_name); +} + +static int devlink_flash_component_get(struct devlink *devlink, + struct nlattr *nla_component, + const char **p_component, + struct netlink_ext_ack *extack) +{ + struct devlink_flash_component_lookup_ctx lookup_ctx = {}; + struct devlink_info_req req = {}; + const char *component; + int ret; + + if (!nla_component) + return 0; + + component = nla_data(nla_component); + + if (!devlink->ops->info_get) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + + lookup_ctx.lookup_name = component; + req.version_cb = devlink_flash_component_lookup_cb; + req.version_cb_priv = &lookup_ctx; + + ret = devlink->ops->info_get(devlink, &req, NULL); + if (ret) + return ret; + + if (!lookup_ctx.lookup_name_found) { + NL_SET_ERR_MSG_ATTR(extack, nla_component, + "selected component is not supported by this device"); + return -EINVAL; + } + *p_component = component; + return 0; +} + +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_overwrite_mask, *nla_file_name; + struct devlink_flash_update_params params = {}; + struct devlink *devlink = info->user_ptr[0]; + const char *file_name; + u32 supported_params; + int ret; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) + return -EINVAL; + + ret = devlink_flash_component_get(devlink, + info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], + ¶ms.component, info->extack); + if (ret) + return ret; + + supported_params = devlink->ops->supported_flash_update_params; + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } + + nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; + file_name = nla_data(nla_file_name); + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, + "failed to locate the requested firmware file"); + return ret; + } + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); + + return ret; +} + +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + struct devlink_info_req req = {}; + const struct nlattr *nlattr; + struct sk_buff *msg; + int rem, err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + if (!devlink->ops->info_get) + return; + + devl_lock(devlink); + if (devl_is_registered(devlink)) + __devlink_compat_running_version(devlink, buf, len); + devl_unlock(devlink); +} + +int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) +{ + struct devlink_flash_update_params params = {}; + int ret; + + devl_lock(devlink); + if (!devl_is_registered(devlink)) { + ret = -ENODEV; + goto out_unlock; + } + + if (!devlink->ops->flash_update) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + + ret = request_firmware(¶ms.fw, file_name, devlink->dev); + if (ret) + goto out_unlock; + + devlink_flash_update_begin_notify(devlink); + ret = devlink->ops->flash_update(devlink, ¶ms, NULL); + devlink_flash_update_end_notify(devlink); + + release_firmware(params.fw); +out_unlock: + devl_unlock(devlink); + + return ret; +} + +static int +devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, + u32 portid, u32 seq, int flags, + struct netlink_ext_ack *extack) +{ + struct nlattr *selftests; + void *hdr; + int err; + int i; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, + DEVLINK_CMD_SELFTESTS_GET); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto err_cancel_msg; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + if (devlink->ops->selftest_check(devlink, i, extack)) { + err = nla_put_flag(msg, i); + if (err) + goto err_cancel_msg; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops->selftest_check) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, + info->snd_seq, 0, info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, + struct devlink *devlink, + struct netlink_callback *cb) +{ + if (!devlink->ops->selftest_check) + return 0; + + return devlink_nl_selftests_fill(msg, devlink, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); +} + +const struct devlink_cmd devl_cmd_selftests_get = { + .dump_one = devlink_nl_cmd_selftests_get_dump_one, +}; + +static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, + enum devlink_selftest_status test_status) +{ + struct nlattr *result_attr; + + result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); + if (!result_attr) + return -EMSGSIZE; + + if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || + nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, + test_status)) + goto nla_put_failure; + + nla_nest_end(skb, result_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, result_attr); + return -EMSGSIZE; +} + +static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, +}; + +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; + struct devlink *devlink = info->user_ptr[0]; + struct nlattr *attrs, *selftests; + struct sk_buff *msg; + void *hdr; + int err; + int i; + + if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) + return -EOPNOTSUPP; + + if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) + return -EINVAL; + + attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; + + err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, + devlink_selftest_nl_policy, info->extack); + if (err < 0) + return err; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = -EMSGSIZE; + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, + &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); + if (!selftests) + goto genlmsg_cancel; + + for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; + i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { + enum devlink_selftest_status test_status; + + if (nla_get_flag(tb[i])) { + if (!devlink->ops->selftest_check(devlink, i, + info->extack)) { + if (devlink_selftest_result_put(msg, i, + DEVLINK_SELFTEST_STATUS_SKIP)) + goto selftests_nest_cancel; + continue; + } + + test_status = devlink->ops->selftest_run(devlink, i, + info->extack); + if (devlink_selftest_result_put(msg, i, test_status)) + goto selftests_nest_cancel; + } + } + + nla_nest_end(msg, selftests); + genlmsg_end(msg, hdr); + return genlmsg_reply(msg, info); + +selftests_nest_cancel: + nla_nest_cancel(msg, selftests); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return err; +} diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index bdd7ad25c7e8..941174e157d4 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -139,6 +139,16 @@ devlink_dump_state(struct netlink_callback *cb) return (struct devlink_nl_dump_state *)cb->ctx; } +static inline int +devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) +{ + if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) + return -EMSGSIZE; + if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) + return -EMSGSIZE; + return 0; +} + /* Commands */ extern const struct devlink_cmd devl_cmd_get; extern const struct devlink_cmd devl_cmd_port_get; @@ -157,6 +167,9 @@ extern const struct devlink_cmd devl_cmd_rate_get; extern const struct devlink_cmd devl_cmd_linecard_get; extern const struct devlink_cmd devl_cmd_selftests_get; +/* Notify */ +void devlink_notify(struct devlink *devlink, enum devlink_command cmd); + /* Ports */ int devlink_port_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr); @@ -176,6 +189,12 @@ static inline bool devlink_reload_supported(const struct devlink_ops *ops) return ops->reload_down && ops->reload_up; } +/* Resources */ +struct devlink_resource; +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info); + /* Line cards */ struct devlink_linecard; @@ -183,8 +202,19 @@ struct devlink_linecard * devlink_linecard_get_from_info(struct devlink *devlink, struct genl_info *info); /* Rates */ +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack); struct devlink_rate * devlink_rate_get_from_info(struct devlink *devlink, struct genl_info *info); struct devlink_rate * devlink_rate_node_get_from_info(struct devlink *devlink, struct genl_info *info); +/* Devlink nl cmds */ +int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); diff --git a/net/devlink/leftover.c b/net/devlink/leftover.c index 056d9ca14a3d..f05ab093d231 100644 --- a/net/devlink/leftover.c +++ b/net/devlink/leftover.c @@ -143,10 +143,6 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), }; -static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { - [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, -}; - #define ASSERT_DEVLINK_PORT_REGISTERED(devlink_port) \ WARN_ON_ONCE(!(devlink_port)->registered) #define ASSERT_DEVLINK_PORT_NOT_REGISTERED(devlink_port) \ @@ -596,15 +592,6 @@ devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) return NULL; } -static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) -{ - if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) - return -EMSGSIZE; - if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) - return -EMSGSIZE; - return 0; -} - static int devlink_nl_put_nested_handle(struct sk_buff *msg, struct devlink *devlink) { struct nlattr *nested_attr; @@ -641,185 +628,6 @@ size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ } -struct devlink_reload_combination { - enum devlink_reload_action action; - enum devlink_reload_limit limit; -}; - -static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { - { - /* can't reinitialize driver with no down time */ - .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, - }, -}; - -static bool -devlink_reload_combination_is_invalid(enum devlink_reload_action action, - enum devlink_reload_limit limit) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) - if (devlink_reload_invalid_combinations[i].action == action && - devlink_reload_invalid_combinations[i].limit == limit) - return true; - return false; -} - -static bool -devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) -{ - return test_bit(action, &devlink->ops->reload_actions); -} - -static bool -devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) -{ - return test_bit(limit, &devlink->ops->reload_limits); -} - -static int devlink_reload_stat_put(struct sk_buff *msg, - enum devlink_reload_limit limit, u32 value) -{ - struct nlattr *reload_stats_entry; - - reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); - if (!reload_stats_entry) - return -EMSGSIZE; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || - nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) - goto nla_put_failure; - nla_nest_end(msg, reload_stats_entry); - return 0; - -nla_put_failure: - nla_nest_cancel(msg, reload_stats_entry); - return -EMSGSIZE; -} - -static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) -{ - struct nlattr *reload_stats_attr, *act_info, *act_stats; - int i, j, stat_idx; - u32 value; - - if (!is_remote) - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); - else - reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); - - if (!reload_stats_attr) - return -EMSGSIZE; - - for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { - if ((!is_remote && - !devlink_reload_action_is_supported(devlink, i)) || - i == DEVLINK_RELOAD_ACTION_UNSPEC) - continue; - act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO); - if (!act_info) - goto nla_put_failure; - - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i)) - goto action_info_nest_cancel; - act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS); - if (!act_stats) - goto action_info_nest_cancel; - - for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { - /* Remote stats are shown even if not locally supported. - * Stats of actions with unspecified limit are shown - * though drivers don't need to register unspecified - * limit. - */ - if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && - !devlink_reload_limit_is_supported(devlink, j)) || - devlink_reload_combination_is_invalid(i, j)) - continue; - - stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; - if (!is_remote) - value = devlink->stats.reload_stats[stat_idx]; - else - value = devlink->stats.remote_reload_stats[stat_idx]; - if (devlink_reload_stat_put(msg, j, value)) - goto action_stats_nest_cancel; - } - nla_nest_end(msg, act_stats); - nla_nest_end(msg, act_info); - } - nla_nest_end(msg, reload_stats_attr); - return 0; - -action_stats_nest_cancel: - nla_nest_cancel(msg, act_stats); -action_info_nest_cancel: - nla_nest_cancel(msg, act_info); -nla_put_failure: - nla_nest_cancel(msg, reload_stats_attr); - return -EMSGSIZE; -} - -static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - struct nlattr *dev_stats; - void *hdr; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) - goto nla_put_failure; - - dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); - if (!dev_stats) - goto nla_put_failure; - - if (devlink_reload_stats_put(msg, devlink, false)) - goto dev_stats_nest_cancel; - if (devlink_reload_stats_put(msg, devlink, true)) - goto dev_stats_nest_cancel; - - nla_nest_end(msg, dev_stats); - genlmsg_end(msg, hdr); - return 0; - -dev_stats_nest_cancel: - nla_nest_cancel(msg, dev_stats); -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); - WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); - if (err) { - nlmsg_free(msg); - return; - } - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); -} - static int devlink_nl_port_attrs_put(struct sk_buff *msg, struct devlink_port *devlink_port) { @@ -1274,39 +1082,6 @@ devlink_rate_is_parent_node(struct devlink_rate *devlink_rate, return false; } -static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - info->snd_portid, info->snd_seq, 0); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - return devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI); -} - -const struct devlink_cmd devl_cmd_get = { - .dump_one = devlink_nl_cmd_get_dump_one, -}; - static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -3064,85 +2839,8 @@ static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags) -{ - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - void *hdr; - int err = 0; - u16 mode; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = devlink_nl_put_handle(msg, devlink); - if (err) - goto nla_put_failure; - - if (ops->eswitch_mode_get) { - err = ops->eswitch_mode_get(devlink, &mode); - if (err) - goto nla_put_failure; - err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_inline_mode_get) { - err = ops->eswitch_inline_mode_get(devlink, &inline_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, - inline_mode); - if (err) - goto nla_put_failure; - } - - if (ops->eswitch_encap_mode_get) { - err = ops->eswitch_encap_mode_get(devlink, &encap_mode); - if (err) - goto nla_put_failure; - err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); - if (err) - goto nla_put_failure; - } - - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, - info->snd_portid, info->snd_seq, 0); - - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, - struct netlink_ext_ack *extack) +int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, + struct netlink_ext_ack *extack) { struct devlink_rate *devlink_rate; @@ -3154,52 +2852,6 @@ static int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, return 0; } -static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - const struct devlink_ops *ops = devlink->ops; - enum devlink_eswitch_encap_mode encap_mode; - u8 inline_mode; - int err = 0; - u16 mode; - - if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { - if (!ops->eswitch_mode_set) - return -EOPNOTSUPP; - mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); - err = devlink_rate_nodes_check(devlink, mode, info->extack); - if (err) - return err; - err = ops->eswitch_mode_set(devlink, mode, info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { - if (!ops->eswitch_inline_mode_set) - return -EOPNOTSUPP; - inline_mode = nla_get_u8( - info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); - err = ops->eswitch_inline_mode_set(devlink, inline_mode, - info->extack); - if (err) - return err; - } - - if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { - if (!ops->eswitch_encap_mode_set) - return -EOPNOTSUPP; - encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); - err = ops->eswitch_encap_mode_set(devlink, encap_mode, - info->extack); - if (err) - return err; - } - - return 0; -} - int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match) { @@ -4170,10 +3822,9 @@ static int devlink_nl_cmd_resource_dump(struct sk_buff *skb, return devlink_resource_fill(info, DEVLINK_CMD_RESOURCE_DUMP, 0); } -static int -devlink_resources_validate(struct devlink *devlink, - struct devlink_resource *resource, - struct genl_info *info) +int devlink_resources_validate(struct devlink *devlink, + struct devlink_resource *resource, + struct genl_info *info) { struct list_head *resource_list; int err = 0; @@ -4193,698 +3844,6 @@ devlink_resources_validate(struct devlink *devlink, return err; } -static struct net *devlink_netns_get(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; - struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; - struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; - struct net *net; - - if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { - NL_SET_ERR_MSG_MOD(info->extack, "multiple netns identifying attributes specified"); - return ERR_PTR(-EINVAL); - } - - if (netns_pid_attr) { - net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); - } else if (netns_fd_attr) { - net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); - } else if (netns_id_attr) { - net = get_net_ns_by_id(sock_net(skb->sk), - nla_get_u32(netns_id_attr)); - if (!net) - net = ERR_PTR(-EINVAL); - } else { - WARN_ON(1); - net = ERR_PTR(-EINVAL); - } - if (IS_ERR(net)) { - NL_SET_ERR_MSG_MOD(info->extack, "Unknown network namespace"); - return ERR_PTR(-EINVAL); - } - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { - put_net(net); - return ERR_PTR(-EPERM); - } - return net; -} - -static void devlink_reload_netns_change(struct devlink *devlink, - struct net *curr_net, - struct net *dest_net) -{ - /* Userspace needs to be notified about devlink objects - * removed from original and entering new network namespace. - * The rest of the devlink objects are re-created during - * reload process so the notifications are generated separatelly. - */ - devlink_notify_unregister(devlink); - move_netdevice_notifier_net(curr_net, dest_net, - &devlink->netdevice_nb); - write_pnet(&devlink->_net, dest_net); - devlink_notify_register(devlink); -} - -static void devlink_reload_failed_set(struct devlink *devlink, - bool reload_failed) -{ - if (devlink->reload_failed == reload_failed) - return; - devlink->reload_failed = reload_failed; - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -bool devlink_is_reload_failed(const struct devlink *devlink) -{ - return devlink->reload_failed; -} -EXPORT_SYMBOL_GPL(devlink_is_reload_failed); - -static void -__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, - enum devlink_reload_limit limit, u32 actions_performed) -{ - unsigned long actions = actions_performed; - int stat_idx; - int action; - - for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { - stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; - reload_stats[stat_idx]++; - } - devlink_notify(devlink, DEVLINK_CMD_NEW); -} - -static void -devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, - u32 actions_performed) -{ - __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, - actions_performed); -} - -/** - * devlink_remote_reload_actions_performed - Update devlink on reload actions - * performed which are not a direct result of devlink reload call. - * - * This should be called by a driver after performing reload actions in case it was not - * a result of devlink reload call. For example fw_activate was performed as a result - * of devlink reload triggered fw_activate on another host. - * The motivation for this function is to keep data on reload actions performed on this - * function whether it was done due to direct devlink reload call or not. - * - * @devlink: devlink - * @limit: reload limit - * @actions_performed: bitmask of actions performed - */ -void devlink_remote_reload_actions_performed(struct devlink *devlink, - enum devlink_reload_limit limit, - u32 actions_performed) -{ - if (WARN_ON(!actions_performed || - actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || - limit > DEVLINK_RELOAD_LIMIT_MAX)) - return; - - __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, - actions_performed); -} -EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); - -int devlink_reload(struct devlink *devlink, struct net *dest_net, - enum devlink_reload_action action, - enum devlink_reload_limit limit, - u32 *actions_performed, struct netlink_ext_ack *extack) -{ - u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; - struct net *curr_net; - int err; - - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats)); - - err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); - if (err) - return err; - - curr_net = devlink_net(devlink); - if (dest_net && !net_eq(dest_net, curr_net)) - devlink_reload_netns_change(devlink, curr_net, dest_net); - - err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); - devlink_reload_failed_set(devlink, !!err); - if (err) - return err; - - WARN_ON(!(*actions_performed & BIT(action))); - /* Catch driver on updating the remote action within devlink reload */ - WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, - sizeof(remote_reload_stats))); - devlink_reload_stats_update(devlink, limit, *actions_performed); - return 0; -} - -static int -devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, - enum devlink_command cmd, struct genl_info *info) -{ - struct sk_buff *msg; - void *hdr; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, - actions_performed)) - goto nla_put_failure; - genlmsg_end(msg, hdr); - - return genlmsg_reply(msg, info); - -nla_put_failure: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - enum devlink_reload_action action; - enum devlink_reload_limit limit; - struct net *dest_net = NULL; - u32 actions_performed; - int err; - - err = devlink_resources_validate(devlink, NULL, info); - if (err) { - NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); - return err; - } - - if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) - action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); - else - action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; - - if (!devlink_reload_action_is_supported(devlink, action)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested reload action is not supported by the driver"); - return -EOPNOTSUPP; - } - - limit = DEVLINK_RELOAD_LIMIT_UNSPEC; - if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { - struct nla_bitfield32 limits; - u32 limits_selected; - - limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); - limits_selected = limits.value & limits.selector; - if (!limits_selected) { - NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); - return -EINVAL; - } - for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) - if (limits_selected & BIT(limit)) - break; - /* UAPI enables multiselection, but currently it is not used */ - if (limits_selected != BIT(limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Multiselection of limit is not supported"); - return -EOPNOTSUPP; - } - if (!devlink_reload_limit_is_supported(devlink, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is not supported by the driver"); - return -EOPNOTSUPP; - } - if (devlink_reload_combination_is_invalid(action, limit)) { - NL_SET_ERR_MSG_MOD(info->extack, - "Requested limit is invalid for this action"); - return -EINVAL; - } - } - if (info->attrs[DEVLINK_ATTR_NETNS_PID] || - info->attrs[DEVLINK_ATTR_NETNS_FD] || - info->attrs[DEVLINK_ATTR_NETNS_ID]) { - dest_net = devlink_netns_get(skb, info); - if (IS_ERR(dest_net)) - return PTR_ERR(dest_net); - } - - err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); - - if (dest_net) - put_net(dest_net); - - if (err) - return err; - /* For backward compatibility generate reply only if attributes used by user */ - if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) - return 0; - - return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, - DEVLINK_CMD_RELOAD, info); -} - -static int devlink_nl_flash_update_fill(struct sk_buff *msg, - struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - void *hdr; - - hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd); - if (!hdr) - return -EMSGSIZE; - - if (devlink_nl_put_handle(msg, devlink)) - goto nla_put_failure; - - if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) - goto out; - - if (params->status_msg && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - params->status_msg)) - goto nla_put_failure; - if (params->component && - nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - params->component)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - params->done, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - params->total, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, - params->timeout, DEVLINK_ATTR_PAD)) - goto nla_put_failure; - -out: - genlmsg_end(msg, hdr); - return 0; - -nla_put_failure: - genlmsg_cancel(msg, hdr); - return -EMSGSIZE; -} - -static void __devlink_flash_update_notify(struct devlink *devlink, - enum devlink_command cmd, - struct devlink_flash_notify *params) -{ - struct sk_buff *msg; - int err; - - WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && - cmd != DEVLINK_CMD_FLASH_UPDATE_END && - cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); - - if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) - return; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); - if (err) - goto out_free_msg; - - genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); - return; - -out_free_msg: - nlmsg_free(msg); -} - -static void devlink_flash_update_begin_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE, - ¶ms); -} - -static void devlink_flash_update_end_notify(struct devlink *devlink) -{ - struct devlink_flash_notify params = {}; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_END, - ¶ms); -} - -void devlink_flash_update_status_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .done = done, - .total = total, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); - -void devlink_flash_update_timeout_notify(struct devlink *devlink, - const char *status_msg, - const char *component, - unsigned long timeout) -{ - struct devlink_flash_notify params = { - .status_msg = status_msg, - .component = component, - .timeout = timeout, - }; - - __devlink_flash_update_notify(devlink, - DEVLINK_CMD_FLASH_UPDATE_STATUS, - ¶ms); -} -EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); - -struct devlink_info_req { - struct sk_buff *msg; - void (*version_cb)(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv); - void *version_cb_priv; -}; - -struct devlink_flash_component_lookup_ctx { - const char *lookup_name; - bool lookup_name_found; -}; - -static void -devlink_flash_component_lookup_cb(const char *version_name, - enum devlink_info_version_type version_type, - void *version_cb_priv) -{ - struct devlink_flash_component_lookup_ctx *lookup_ctx = version_cb_priv; - - if (version_type != DEVLINK_INFO_VERSION_TYPE_COMPONENT || - lookup_ctx->lookup_name_found) - return; - - lookup_ctx->lookup_name_found = - !strcmp(lookup_ctx->lookup_name, version_name); -} - -static int devlink_flash_component_get(struct devlink *devlink, - struct nlattr *nla_component, - const char **p_component, - struct netlink_ext_ack *extack) -{ - struct devlink_flash_component_lookup_ctx lookup_ctx = {}; - struct devlink_info_req req = {}; - const char *component; - int ret; - - if (!nla_component) - return 0; - - component = nla_data(nla_component); - - if (!devlink->ops->info_get) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "component update is not supported by this device"); - return -EOPNOTSUPP; - } - - lookup_ctx.lookup_name = component; - req.version_cb = devlink_flash_component_lookup_cb; - req.version_cb_priv = &lookup_ctx; - - ret = devlink->ops->info_get(devlink, &req, NULL); - if (ret) - return ret; - - if (!lookup_ctx.lookup_name_found) { - NL_SET_ERR_MSG_ATTR(extack, nla_component, - "selected component is not supported by this device"); - return -EINVAL; - } - *p_component = component; - return 0; -} - -static int devlink_nl_cmd_flash_update(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *nla_overwrite_mask, *nla_file_name; - struct devlink_flash_update_params params = {}; - struct devlink *devlink = info->user_ptr[0]; - const char *file_name; - u32 supported_params; - int ret; - - if (!devlink->ops->flash_update) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME)) - return -EINVAL; - - ret = devlink_flash_component_get(devlink, - info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT], - ¶ms.component, info->extack); - if (ret) - return ret; - - supported_params = devlink->ops->supported_flash_update_params; - - nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; - if (nla_overwrite_mask) { - struct nla_bitfield32 sections; - - if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, - "overwrite settings are not supported by this device"); - return -EOPNOTSUPP; - } - sections = nla_get_bitfield32(nla_overwrite_mask); - params.overwrite_mask = sections.value & sections.selector; - } - - nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]; - file_name = nla_data(nla_file_name); - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) { - NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file"); - return ret; - } - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, info->extack); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); - - return ret; -} - -static int -devlink_nl_selftests_fill(struct sk_buff *msg, struct devlink *devlink, - u32 portid, u32 seq, int flags, - struct netlink_ext_ack *extack) -{ - struct nlattr *selftests; - void *hdr; - int err; - int i; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, - DEVLINK_CMD_SELFTESTS_GET); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto err_cancel_msg; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - if (devlink->ops->selftest_check(devlink, i, extack)) { - err = nla_put_flag(msg, i); - if (err) - goto err_cancel_msg; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_selftests_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - if (!devlink->ops->selftest_check) - return -EOPNOTSUPP; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_selftests_fill(msg, devlink, info->snd_portid, - info->snd_seq, 0, info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_selftests_get_dump_one(struct sk_buff *msg, - struct devlink *devlink, - struct netlink_callback *cb) -{ - if (!devlink->ops->selftest_check) - return 0; - - return devlink_nl_selftests_fill(msg, devlink, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); -} - -const struct devlink_cmd devl_cmd_selftests_get = { - .dump_one = devlink_nl_cmd_selftests_get_dump_one, -}; - -static int devlink_selftest_result_put(struct sk_buff *skb, unsigned int id, - enum devlink_selftest_status test_status) -{ - struct nlattr *result_attr; - - result_attr = nla_nest_start(skb, DEVLINK_ATTR_SELFTEST_RESULT); - if (!result_attr) - return -EMSGSIZE; - - if (nla_put_u32(skb, DEVLINK_ATTR_SELFTEST_RESULT_ID, id) || - nla_put_u8(skb, DEVLINK_ATTR_SELFTEST_RESULT_STATUS, - test_status)) - goto nla_put_failure; - - nla_nest_end(skb, result_attr); - return 0; - -nla_put_failure: - nla_nest_cancel(skb, result_attr); - return -EMSGSIZE; -} - -static int devlink_nl_cmd_selftests_run(struct sk_buff *skb, - struct genl_info *info) -{ - struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; - struct devlink *devlink = info->user_ptr[0]; - struct nlattr *attrs, *selftests; - struct sk_buff *msg; - void *hdr; - int err; - int i; - - if (!devlink->ops->selftest_run || !devlink->ops->selftest_check) - return -EOPNOTSUPP; - - if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_SELFTESTS)) - return -EINVAL; - - attrs = info->attrs[DEVLINK_ATTR_SELFTESTS]; - - err = nla_parse_nested(tb, DEVLINK_ATTR_SELFTEST_ID_MAX, attrs, - devlink_selftest_nl_policy, info->extack); - if (err < 0) - return err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = -EMSGSIZE; - hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &devlink_nl_family, 0, DEVLINK_CMD_SELFTESTS_RUN); - if (!hdr) - goto free_msg; - - if (devlink_nl_put_handle(msg, devlink)) - goto genlmsg_cancel; - - selftests = nla_nest_start(msg, DEVLINK_ATTR_SELFTESTS); - if (!selftests) - goto genlmsg_cancel; - - for (i = DEVLINK_ATTR_SELFTEST_ID_UNSPEC + 1; - i <= DEVLINK_ATTR_SELFTEST_ID_MAX; i++) { - enum devlink_selftest_status test_status; - - if (nla_get_flag(tb[i])) { - if (!devlink->ops->selftest_check(devlink, i, - info->extack)) { - if (devlink_selftest_result_put(msg, i, - DEVLINK_SELFTEST_STATUS_SKIP)) - goto selftests_nest_cancel; - continue; - } - - test_status = devlink->ops->selftest_run(devlink, i, - info->extack); - if (devlink_selftest_result_put(msg, i, test_status)) - goto selftests_nest_cancel; - } - } - - nla_nest_end(msg, selftests); - genlmsg_end(msg, hdr); - return genlmsg_reply(msg, info); - -selftests_nest_cancel: - nla_nest_cancel(msg, selftests); -genlmsg_cancel: - genlmsg_cancel(msg, hdr); -free_msg: - nlmsg_free(msg); - return err; -} - static const struct devlink_param devlink_param_generic[] = { { .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, @@ -6430,205 +5389,6 @@ out_unlock: return err; } -int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); -} -EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); - -int devlink_info_board_serial_number_put(struct devlink_info_req *req, - const char *bsn) -{ - if (!req->msg) - return 0; - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_BOARD_SERIAL_NUMBER, - bsn); -} -EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put); - -static int devlink_info_version_put(struct devlink_info_req *req, int attr, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - struct nlattr *nest; - int err; - - if (req->version_cb) - req->version_cb(version_name, version_type, - req->version_cb_priv); - - if (!req->msg) - return 0; - - nest = nla_nest_start_noflag(req->msg, attr); - if (!nest) - return -EMSGSIZE; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, - version_name); - if (err) - goto nla_put_failure; - - err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, - version_value); - if (err) - goto nla_put_failure; - - nla_nest_end(req->msg, nest); - - return 0; - -nla_put_failure: - nla_nest_cancel(req->msg, nest); - return err; -} - -int devlink_info_version_fixed_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); - -int devlink_info_version_stored_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); - -int devlink_info_version_stored_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_stored_put_ext); - -int devlink_info_version_running_put(struct devlink_info_req *req, - const char *version_name, - const char *version_value) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - DEVLINK_INFO_VERSION_TYPE_NONE); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put); - -int devlink_info_version_running_put_ext(struct devlink_info_req *req, - const char *version_name, - const char *version_value, - enum devlink_info_version_type version_type) -{ - return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, - version_name, version_value, - version_type); -} -EXPORT_SYMBOL_GPL(devlink_info_version_running_put_ext); - -static int devlink_nl_driver_info_get(struct device_driver *drv, - struct devlink_info_req *req) -{ - if (!drv) - return 0; - - if (drv->name[0]) - return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, - drv->name); - - return 0; -} - -static int -devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, - enum devlink_command cmd, u32 portid, - u32 seq, int flags, struct netlink_ext_ack *extack) -{ - struct device *dev = devlink_to_dev(devlink); - struct devlink_info_req req = {}; - void *hdr; - int err; - - hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); - if (!hdr) - return -EMSGSIZE; - - err = -EMSGSIZE; - if (devlink_nl_put_handle(msg, devlink)) - goto err_cancel_msg; - - req.msg = msg; - if (devlink->ops->info_get) { - err = devlink->ops->info_get(devlink, &req, extack); - if (err) - goto err_cancel_msg; - } - - err = devlink_nl_driver_info_get(dev->driver, &req); - if (err) - goto err_cancel_msg; - - genlmsg_end(msg, hdr); - return 0; - -err_cancel_msg: - genlmsg_cancel(msg, hdr); - return err; -} - -static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, - struct genl_info *info) -{ - struct devlink *devlink = info->user_ptr[0]; - struct sk_buff *msg; - int err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return -ENOMEM; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - info->snd_portid, info->snd_seq, 0, - info->extack); - if (err) { - nlmsg_free(msg); - return err; - } - - return genlmsg_reply(msg, info); -} - -static int -devlink_nl_cmd_info_get_dump_one(struct sk_buff *msg, struct devlink *devlink, - struct netlink_callback *cb) -{ - int err; - - err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, NLM_F_MULTI, - cb->extack); - if (err == -EOPNOTSUPP) - err = 0; - return err; -} - -const struct devlink_cmd devl_cmd_info_get = { - .dump_one = devlink_nl_cmd_info_get_dump_one, -}; - struct devlink_fmsg_item { struct list_head list; int attrtype; @@ -7866,18 +6626,22 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, err = devlink_fmsg_obj_nest_start(fmsg); if (err) - return err; + goto out; err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) - return err; + goto out; err = devlink_fmsg_obj_nest_end(fmsg); if (err) - return err; + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); - return devlink_fmsg_snd(fmsg, info, - DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); +out: + devlink_fmsg_free(fmsg); + return err; } static int @@ -9257,35 +8021,6 @@ const struct genl_small_ops devlink_nl_ops[56] = { /* -- No new ops here! Use split ops going forward! -- */ }; -bool devlink_reload_actions_valid(const struct devlink_ops *ops) -{ - const struct devlink_reload_combination *comb; - int i; - - if (!devlink_reload_supported(ops)) { - if (WARN_ON(ops->reload_actions)) - return false; - return true; - } - - if (WARN_ON(!ops->reload_actions || - ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || - ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) - return false; - - if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || - ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) - return false; - - for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { - comb = &devlink_reload_invalid_combinations[i]; - if (ops->reload_actions == BIT(comb->action) && - ops->reload_limits == BIT(comb->limit)) - return false; - } - return true; -} - static void devlink_trap_policer_notify(struct devlink *devlink, const struct devlink_trap_policer_item *policer_item, @@ -9695,6 +8430,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, break; case NETDEV_REGISTER: case NETDEV_CHANGENAME: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Set the netdev on top of previously set type. Note this * event happens also during net namespace change so here * we take into account netdev pointer appearing in this @@ -9704,6 +8441,8 @@ int devlink_port_netdevice_event(struct notifier_block *nb, netdev); break; case NETDEV_UNREGISTER: + if (devlink_net(devlink) != dev_net(netdev)) + return NOTIFY_OK; /* Clear netdev pointer, but not the type. This event happens * also during net namespace change so we need to clear * pointer to netdev that is going to another net namespace. @@ -12068,85 +10807,6 @@ devl_trap_policers_unregister(struct devlink *devlink, } EXPORT_SYMBOL_GPL(devl_trap_policers_unregister); -static void __devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - struct devlink_info_req req = {}; - const struct nlattr *nlattr; - struct sk_buff *msg; - int rem, err; - - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) - return; - - req.msg = msg; - err = devlink->ops->info_get(devlink, &req, NULL); - if (err) - goto free_msg; - - nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { - const struct nlattr *kv; - int rem_kv; - - if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) - continue; - - nla_for_each_nested(kv, nlattr, rem_kv) { - if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) - continue; - - strlcat(buf, nla_data(kv), len); - strlcat(buf, " ", len); - } - } -free_msg: - nlmsg_free(msg); -} - -void devlink_compat_running_version(struct devlink *devlink, - char *buf, size_t len) -{ - if (!devlink->ops->info_get) - return; - - devl_lock(devlink); - if (devl_is_registered(devlink)) - __devlink_compat_running_version(devlink, buf, len); - devl_unlock(devlink); -} - -int devlink_compat_flash_update(struct devlink *devlink, const char *file_name) -{ - struct devlink_flash_update_params params = {}; - int ret; - - devl_lock(devlink); - if (!devl_is_registered(devlink)) { - ret = -ENODEV; - goto out_unlock; - } - - if (!devlink->ops->flash_update) { - ret = -EOPNOTSUPP; - goto out_unlock; - } - - ret = request_firmware(¶ms.fw, file_name, devlink->dev); - if (ret) - goto out_unlock; - - devlink_flash_update_begin_notify(devlink); - ret = devlink->ops->flash_update(devlink, ¶ms, NULL); - devlink_flash_update_end_notify(devlink); - - release_firmware(params.fw); -out_unlock: - devl_unlock(devlink); - - return ret; -} - int devlink_compat_phys_port_name_get(struct net_device *dev, char *name, size_t len) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 26c458f50ac6..6957971c2db2 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -2692,7 +2692,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (!err) dsa_bridge_mtu_normalization(dp); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_WEAK_MOD(extack, "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2705,8 +2706,8 @@ static int dsa_slave_changeupper(struct net_device *dev, err = dsa_port_lag_join(dp, info->upper_dev, info->upper_info, extack); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); @@ -2718,8 +2719,8 @@ static int dsa_slave_changeupper(struct net_device *dev, if (info->linking) { err = dsa_port_hsr_join(dp, info->upper_dev); if (err == -EOPNOTSUPP) { - NL_SET_ERR_MSG_MOD(info->info.extack, - "Offloading not supported"); + NL_SET_ERR_MSG_WEAK_MOD(extack, + "Offloading not supported"); err = 0; } err = notifier_from_errno(err); diff --git a/net/ethtool/mm.c b/net/ethtool/mm.c index 7e51f7633001..e612856eed8c 100644 --- a/net/ethtool/mm.c +++ b/net/ethtool/mm.c @@ -56,7 +56,7 @@ static int mm_prepare_data(const struct ethnl_req_info *req_base, out_complete: ethnl_ops_complete(dev); - return 0; + return ret; } static int mm_reply_size(const struct ethnl_req_info *req_base, diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 2f992a323b95..2c778b013cb0 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -347,6 +347,7 @@ lookup_protocol: sk->sk_destruct = inet_sock_destruct; sk->sk_protocol = protocol; sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); inet->uc_ttl = -1; inet->mc_loop = 1; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6ed7e65de494..7d206a10ad14 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1246,9 +1246,6 @@ int inet_csk_listen_start(struct sock *sk) sk->sk_ack_backlog = 0; inet_csk_delack_init(sk); - if (sk->sk_txrehash == SOCK_TXREHASH_DEFAULT) - sk->sk_txrehash = READ_ONCE(sock_net(sk)->core.sysctl_txrehash); - /* There is race window here: we announce ourselves listening, * but this transition is still not validated by get_port(). * It is OK, because this socket enters to hash table only diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 006c1f0ed8b4..94df935ee0c5 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -93,7 +93,7 @@ int raw_hash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_nulls_head *hlist; - hlist = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)]; + hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)]; spin_lock(&h->lock); __sk_nulls_add_node_rcu(sk, hlist); @@ -160,9 +160,9 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) * RFC 1122: SHOULD pass TOS value up to the transport layer. * -> It does. And not only TOS, but all IP header. */ -static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) +static int raw_v4_input(struct net *net, struct sk_buff *skb, + const struct iphdr *iph, int hash) { - struct net *net = dev_net(skb->dev); struct hlist_nulls_head *hlist; struct hlist_nulls_node *hnode; int sdif = inet_sdif(skb); @@ -193,9 +193,10 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) int raw_local_deliver(struct sk_buff *skb, int protocol) { - int hash = protocol & (RAW_HTABLE_SIZE - 1); + struct net *net = dev_net(skb->dev); - return raw_v4_input(skb, ip_hdr(skb), hash); + return raw_v4_input(net, skb, ip_hdr(skb), + raw_hashfunc(net, protocol)); } static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) @@ -271,7 +272,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) struct sock *sk; int hash; - hash = protocol & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, protocol); hlist = &raw_v4_hashinfo.ht[hash]; rcu_read_lock(); @@ -287,11 +288,13 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + /* Charge it to the socket. */ ipv4_pktinfo_prepare(sk, skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -302,7 +305,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) { if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } nf_reset_ct(skb); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index d2c470524e58..146792cd26fe 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -295,7 +295,7 @@ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) } /* override sysctl_tcp_min_tso_segs */ -static u32 bbr_min_tso_segs(struct sock *sk) +__bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2; } @@ -328,7 +328,7 @@ static void bbr_save_cwnd(struct sock *sk) bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp)); } -static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) +__bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); @@ -1023,7 +1023,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_update_gains(sk); } -static void bbr_main(struct sock *sk, const struct rate_sample *rs) +__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs) { struct bbr *bbr = inet_csk_ca(sk); u32 bw; @@ -1035,7 +1035,7 @@ static void bbr_main(struct sock *sk, const struct rate_sample *rs) bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain); } -static void bbr_init(struct sock *sk) +__bpf_kfunc static void bbr_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); @@ -1077,7 +1077,7 @@ static void bbr_init(struct sock *sk) cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } -static u32 bbr_sndbuf_expand(struct sock *sk) +__bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk) { /* Provision 3 * cwnd since BBR may slow-start even during recovery. */ return 3; @@ -1086,7 +1086,7 @@ static u32 bbr_sndbuf_expand(struct sock *sk) /* In theory BBR does not need to undo the cwnd since it does not * always reduce cwnd on losses (see bbr_main()). Keep it for now. */ -static u32 bbr_undo_cwnd(struct sock *sk) +__bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk) { struct bbr *bbr = inet_csk_ca(sk); @@ -1097,7 +1097,7 @@ static u32 bbr_undo_cwnd(struct sock *sk) } /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ -static u32 bbr_ssthresh(struct sock *sk) +__bpf_kfunc static u32 bbr_ssthresh(struct sock *sk) { bbr_save_cwnd(sk); return tcp_sk(sk)->snd_ssthresh; @@ -1125,7 +1125,7 @@ static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, return 0; } -static void bbr_set_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state) { struct bbr *bbr = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index d3cae40749e8..db8b4b488c31 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -403,7 +403,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and * returns the leftover acks to adjust cwnd in congestion avoidance mode. */ -u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) +__bpf_kfunc u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { u32 cwnd = min(tcp_snd_cwnd(tp) + acked, tp->snd_ssthresh); @@ -417,7 +417,7 @@ EXPORT_SYMBOL_GPL(tcp_slow_start); /* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w), * for every packet that was ACKed. */ -void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) +__bpf_kfunc void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked) { /* If credits accumulated at a higher w, apply them gently now. */ if (tp->snd_cwnd_cnt >= w) { @@ -443,7 +443,7 @@ EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai); /* This is Jacobson's slow start and congestion avoidance. * SIGCOMM '88, p. 328. */ -void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) +__bpf_kfunc void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); @@ -462,7 +462,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid); /* Slow start threshold is half the congestion window (min 2) */ -u32 tcp_reno_ssthresh(struct sock *sk) +__bpf_kfunc u32 tcp_reno_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -470,7 +470,7 @@ u32 tcp_reno_ssthresh(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_reno_ssthresh); -u32 tcp_reno_undo_cwnd(struct sock *sk) +__bpf_kfunc u32 tcp_reno_undo_cwnd(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 768c10c1f649..0fd78ecb67e7 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -126,7 +126,7 @@ static inline void bictcp_hystart_reset(struct sock *sk) ca->sample_cnt = 0; } -static void cubictcp_init(struct sock *sk) +__bpf_kfunc static void cubictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); @@ -139,7 +139,7 @@ static void cubictcp_init(struct sock *sk) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } -static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) +__bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); @@ -321,7 +321,7 @@ tcp_friendliness: ca->cnt = max(ca->cnt, 2U); } -static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) +__bpf_kfunc static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); @@ -338,7 +338,7 @@ static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) tcp_cong_avoid_ai(tp, ca->cnt, acked); } -static u32 cubictcp_recalc_ssthresh(struct sock *sk) +__bpf_kfunc static u32 cubictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); @@ -355,7 +355,7 @@ static u32 cubictcp_recalc_ssthresh(struct sock *sk) return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } -static void cubictcp_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void cubictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); @@ -445,7 +445,7 @@ static void hystart_update(struct sock *sk, u32 delay) } } -static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) +__bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index e0a2ca7456ff..bb23bb5b387a 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -75,7 +75,7 @@ static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) ca->old_delivered_ce = tp->delivered_ce; } -static void dctcp_init(struct sock *sk) +__bpf_kfunc static void dctcp_init(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); @@ -104,7 +104,7 @@ static void dctcp_init(struct sock *sk) INET_ECN_dontxmit(sk); } -static u32 dctcp_ssthresh(struct sock *sk) +__bpf_kfunc static u32 dctcp_ssthresh(struct sock *sk) { struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -113,7 +113,7 @@ static u32 dctcp_ssthresh(struct sock *sk) return max(tcp_snd_cwnd(tp) - ((tcp_snd_cwnd(tp) * ca->dctcp_alpha) >> 11U), 2U); } -static void dctcp_update_alpha(struct sock *sk, u32 flags) +__bpf_kfunc static void dctcp_update_alpha(struct sock *sk, u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); @@ -169,7 +169,7 @@ static void dctcp_react_to_loss(struct sock *sk) tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U); } -static void dctcp_state(struct sock *sk, u8 new_state) +__bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Recovery && new_state != inet_csk(sk)->icsk_ca_state) @@ -179,7 +179,7 @@ static void dctcp_state(struct sock *sk, u8 new_state) */ } -static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) +__bpf_kfunc static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { struct dctcp *ca = inet_csk_ca(sk); @@ -229,7 +229,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, return 0; } -static u32 dctcp_cwnd_undo(struct sock *sk) +__bpf_kfunc static u32 dctcp_cwnd_undo(struct sock *sk) { const struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index fee9163382c2..847934763868 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -222,6 +222,7 @@ lookup_protocol: np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ESTABLISHED; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; + sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash); /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index ada087b50541..bac9ba747bde 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -152,7 +152,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -338,7 +338,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, struct sock *sk; int hash; - hash = nexthdr & (RAW_HTABLE_SIZE - 1); + hash = raw_hashfunc(net, nexthdr); hlist = &raw_v6_hashinfo.ht[hash]; rcu_read_lock(); sk_nulls_for_each(sk, hnode, hlist) { @@ -355,17 +355,19 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr, static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; + if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); - if (sock_queue_rcv_skb(sk, skb) < 0) { - kfree_skb(skb); + if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) { + kfree_skb_reason(skb, reason); return NET_RX_DROP; } @@ -386,7 +388,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_XFRM_POLICY); return NET_RX_DROP; } @@ -410,7 +412,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, SKB_DROP_REASON_SKB_CSUM); return NET_RX_DROP; } } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index db07cc5b4fcb..56628b52d100 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1002,8 +1002,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, { int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; - struct mptcp_sock *msk; struct socket *ssock; + struct sock *newsk; int backlog = 1024; int err; @@ -1012,11 +1012,13 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; - msk = mptcp_sk(entry->lsk->sk); - if (!msk) + newsk = entry->lsk->sk; + if (!newsk) return -EINVAL; - ssock = __mptcp_nmpc_socket(msk); + lock_sock(newsk); + ssock = __mptcp_nmpc_socket(mptcp_sk(newsk)); + release_sock(newsk); if (!ssock) return -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 1ff2efbab29e..c9817aa0f413 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2902,6 +2902,7 @@ bool __mptcp_close(struct sock *sk, long timeout) struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; + int subflows_alive = 0; sk->sk_shutdown = SHUTDOWN_MASK; @@ -2928,6 +2929,8 @@ cleanup: struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + subflows_alive += ssk->sk_state != TCP_CLOSE; + /* since the close timeout takes precedence on the fail one, * cancel the latter */ @@ -2943,6 +2946,12 @@ cleanup: } sock_orphan(sk); + /* all the subflows are closed, only timeout can change the msk + * state, let's not keep resources busy for no reasons + */ + if (subflows_alive == 0) + inet_sk_state_store(sk, TCP_CLOSE); + sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (msk->token) diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 9986681aaf40..8a9656248b0f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -760,14 +760,21 @@ static int mptcp_setsockopt_v4(struct mptcp_sock *msk, int optname, static int mptcp_setsockopt_first_sf_only(struct mptcp_sock *msk, int level, int optname, sockptr_t optval, unsigned int optlen) { + struct sock *sk = (struct sock *)msk; struct socket *sock; + int ret = -EINVAL; /* Limit to first subflow, before the connection establishment */ + lock_sock(sk); sock = __mptcp_nmpc_socket(msk); if (!sock) - return -EINVAL; + goto unlock; - return tcp_setsockopt(sock->sk, level, optname, optval, optlen); + ret = tcp_setsockopt(sock->sk, level, optname, optval, optlen); + +unlock: + release_sock(sk); + return ret; } static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index beaec843f5ca..4ae1a7304cf0 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1400,6 +1400,7 @@ void __mptcp_error_report(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); int err = sock_error(ssk); + int ssk_state; if (!err) continue; @@ -1410,7 +1411,14 @@ void __mptcp_error_report(struct sock *sk) if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk)) continue; - inet_sk_state_store(sk, inet_sk_state_load(ssk)); + /* We need to propagate only transition to CLOSE state. + * Orphaned socket will see such state change via + * subflow_sched_work_if_closed() and that path will properly + * destroy the msk as needed. + */ + ssk_state = inet_sk_state_load(ssk); + if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD)) + inet_sk_state_store(sk, ssk_state); sk->sk_err = -err; /* This barrier is coupled with smp_rmb() in mptcp_poll() */ @@ -1682,7 +1690,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, if (err) return err; - lock_sock(sf->sk); + lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING); /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f71b41c7ce2f..4d6737160857 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -189,6 +189,9 @@ config NF_CONNTRACK_LABELS to connection tracking entries. It can be used with xtables connlabel match and the nftables ct expression. +config NF_CONNTRACK_OVS + bool + config NF_CT_PROTO_DCCP bool 'DCCP protocol connection tracking support' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index ba2a6b5e93d9..5ffef1cd6143 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -11,6 +11,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_OVS) += nf_conntrack_ovs.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 24002bc61e07..34913521c385 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -249,7 +249,7 @@ __diag_ignore_all("-Wmissing-prototypes", * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn___init * +__bpf_kfunc struct nf_conn___init * bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -283,7 +283,7 @@ bpf_xdp_ct_alloc(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn * +__bpf_kfunc struct nf_conn * bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -316,7 +316,7 @@ bpf_xdp_ct_lookup(struct xdp_md *xdp_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn___init * +__bpf_kfunc struct nf_conn___init * bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -351,7 +351,7 @@ bpf_skb_ct_alloc(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @opts__sz - Length of the bpf_ct_opts structure * Must be NF_BPF_CT_OPTS_SZ (12) */ -struct nf_conn * +__bpf_kfunc struct nf_conn * bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, u32 tuple__sz, struct bpf_ct_opts *opts, u32 opts__sz) { @@ -376,7 +376,7 @@ bpf_skb_ct_lookup(struct __sk_buff *skb_ctx, struct bpf_sock_tuple *bpf_tuple, * @nfct - Pointer to referenced nf_conn___init object, obtained * using bpf_xdp_ct_alloc or bpf_skb_ct_alloc. */ -struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) +__bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) { struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; @@ -400,7 +400,7 @@ struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) * @nf_conn - Pointer to referenced nf_conn object, obtained using * bpf_xdp_ct_lookup or bpf_skb_ct_lookup. */ -void bpf_ct_release(struct nf_conn *nfct) +__bpf_kfunc void bpf_ct_release(struct nf_conn *nfct) { if (!nfct) return; @@ -417,7 +417,7 @@ void bpf_ct_release(struct nf_conn *nfct) * bpf_xdp_ct_alloc or bpf_skb_ct_alloc. * @timeout - Timeout in msecs. */ -void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) +__bpf_kfunc void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) { __nf_ct_set_timeout((struct nf_conn *)nfct, msecs_to_jiffies(timeout)); } @@ -432,7 +432,7 @@ void bpf_ct_set_timeout(struct nf_conn___init *nfct, u32 timeout) * bpf_ct_insert_entry, bpf_xdp_ct_lookup, or bpf_skb_ct_lookup. * @timeout - New timeout in msecs. */ -int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) +__bpf_kfunc int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) { return __nf_ct_change_timeout(nfct, msecs_to_jiffies(timeout)); } @@ -447,7 +447,7 @@ int bpf_ct_change_timeout(struct nf_conn *nfct, u32 timeout) * bpf_xdp_ct_alloc or bpf_skb_ct_alloc. * @status - New status value. */ -int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) +__bpf_kfunc int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) { return nf_ct_change_status_common((struct nf_conn *)nfct, status); } @@ -462,7 +462,7 @@ int bpf_ct_set_status(const struct nf_conn___init *nfct, u32 status) * bpf_ct_insert_entry, bpf_xdp_ct_lookup or bpf_skb_ct_lookup. * @status - New status value. */ -int bpf_ct_change_status(struct nf_conn *nfct, u32 status) +__bpf_kfunc int bpf_ct_change_status(struct nf_conn *nfct, u32 status) { return nf_ct_change_status_common(nfct, status); } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 48ea6d0264b5..0c4db2f2ac43 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -242,104 +242,6 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); -/* 'skb' should already be pulled to nh_ofs. */ -int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo, u16 proto) -{ - const struct nf_conntrack_helper *helper; - const struct nf_conn_help *help; - unsigned int protoff; - int err; - - if (ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - if (helper->tuple.src.l3num != NFPROTO_UNSPEC && - helper->tuple.src.l3num != proto) - return NF_ACCEPT; - - switch (proto) { - case NFPROTO_IPV4: - protoff = ip_hdrlen(skb); - proto = ip_hdr(skb)->protocol; - break; - case NFPROTO_IPV6: { - u8 nexthdr = ipv6_hdr(skb)->nexthdr; - __be16 frag_off; - int ofs; - - ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - protoff = ofs; - proto = nexthdr; - break; - } - default: - WARN_ONCE(1, "helper invoked on non-IP family!"); - return NF_DROP; - } - - if (helper->tuple.dst.protonum != proto) - return NF_ACCEPT; - - err = helper->help(skb, protoff, ct, ctinfo); - if (err != NF_ACCEPT) - return err; - - /* Adjust seqs after helper. This is needed due to some helpers (e.g., - * FTP with NAT) adusting the TCP payload size when mangling IP - * addresses and/or port numbers in the text-based control connection. - */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) - return NF_DROP; - return NF_ACCEPT; -} -EXPORT_SYMBOL_GPL(nf_ct_helper); - -int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, - u8 proto, bool nat, struct nf_conntrack_helper **hp) -{ - struct nf_conntrack_helper *helper; - struct nf_conn_help *help; - int ret = 0; - - helper = nf_conntrack_helper_try_module_get(name, family, proto); - if (!helper) - return -EINVAL; - - help = nf_ct_helper_ext_add(ct, GFP_KERNEL); - if (!help) { - nf_conntrack_helper_put(helper); - return -ENOMEM; - } -#if IS_ENABLED(CONFIG_NF_NAT) - if (nat) { - ret = nf_nat_helper_try_module_get(name, family, proto); - if (ret) { - nf_conntrack_helper_put(helper); - return ret; - } - } -#endif - rcu_assign_pointer(help->helper, helper); - *hp = helper; - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_add_helper); - /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { diff --git a/net/netfilter/nf_conntrack_ovs.c b/net/netfilter/nf_conntrack_ovs.c new file mode 100644 index 000000000000..52b776bdf526 --- /dev/null +++ b/net/netfilter/nf_conntrack_ovs.c @@ -0,0 +1,178 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Support ct functions for openvswitch and used by OVS and TC conntrack. */ + +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_seqadj.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> +#include <net/ipv6_frag.h> +#include <net/ip.h> + +/* 'skb' should already be pulled to nh_ofs. */ +int nf_ct_helper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo, u16 proto) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + unsigned int protoff; + int err; + + if (ctinfo == IP_CT_RELATED_REPLY) + return NF_ACCEPT; + + help = nfct_help(ct); + if (!help) + return NF_ACCEPT; + + helper = rcu_dereference(help->helper); + if (!helper) + return NF_ACCEPT; + + if (helper->tuple.src.l3num != NFPROTO_UNSPEC && + helper->tuple.src.l3num != proto) + return NF_ACCEPT; + + switch (proto) { + case NFPROTO_IPV4: + protoff = ip_hdrlen(skb); + proto = ip_hdr(skb)->protocol; + break; + case NFPROTO_IPV6: { + u8 nexthdr = ipv6_hdr(skb)->nexthdr; + __be16 frag_off; + int ofs; + + ofs = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, + &frag_off); + if (ofs < 0 || (frag_off & htons(~0x7)) != 0) { + pr_debug("proto header not found\n"); + return NF_ACCEPT; + } + protoff = ofs; + proto = nexthdr; + break; + } + default: + WARN_ONCE(1, "helper invoked on non-IP family!"); + return NF_DROP; + } + + if (helper->tuple.dst.protonum != proto) + return NF_ACCEPT; + + err = helper->help(skb, protoff, ct, ctinfo); + if (err != NF_ACCEPT) + return err; + + /* Adjust seqs after helper. This is needed due to some helpers (e.g., + * FTP with NAT) adusting the TCP payload size when mangling IP + * addresses and/or port numbers in the text-based control connection. + */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) + return NF_DROP; + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_ct_helper); + +int nf_ct_add_helper(struct nf_conn *ct, const char *name, u8 family, + u8 proto, bool nat, struct nf_conntrack_helper **hp) +{ + struct nf_conntrack_helper *helper; + struct nf_conn_help *help; + int ret = 0; + + helper = nf_conntrack_helper_try_module_get(name, family, proto); + if (!helper) + return -EINVAL; + + help = nf_ct_helper_ext_add(ct, GFP_KERNEL); + if (!help) { + nf_conntrack_helper_put(helper); + return -ENOMEM; + } +#if IS_ENABLED(CONFIG_NF_NAT) + if (nat) { + ret = nf_nat_helper_try_module_get(name, family, proto); + if (ret) { + nf_conntrack_helper_put(helper); + return ret; + } + } +#endif + rcu_assign_pointer(help->helper, helper); + *hp = helper; + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_add_helper); + +/* Trim the skb to the length specified by the IP/IPv6 header, + * removing any trailing lower-layer padding. This prepares the skb + * for higher-layer processing that assumes skb->len excludes padding + * (such as nf_ip_checksum). The caller needs to pull the skb to the + * network header, and ensure ip_hdr/ipv6_hdr points to valid data. + */ +int nf_ct_skb_network_trim(struct sk_buff *skb, int family) +{ + unsigned int len; + + switch (family) { + case NFPROTO_IPV4: + len = skb_ip_totlen(skb); + break; + case NFPROTO_IPV6: + len = sizeof(struct ipv6hdr) + + ntohs(ipv6_hdr(skb)->payload_len); + break; + default: + len = skb->len; + } + + return pskb_trim_rcsum(skb, len); +} +EXPORT_SYMBOL_GPL(nf_ct_skb_network_trim); + +/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero + * value if 'skb' is freed. + */ +int nf_ct_handle_fragments(struct net *net, struct sk_buff *skb, + u16 zone, u8 family, u8 *proto, u16 *mru) +{ + int err; + + if (family == NFPROTO_IPV4) { + enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + local_bh_disable(); + err = ip_defrag(net, skb, user); + local_bh_enable(); + if (err) + return err; + + *mru = IPCB(skb)->frag_max_size; +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + } else if (family == NFPROTO_IPV6) { + enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; + + memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); + err = nf_ct_frag6_gather(net, skb, user); + if (err) { + if (err != -EINPROGRESS) + kfree_skb(skb); + return err; + } + + *proto = ipv6_hdr(skb)->nexthdr; + *mru = IP6CB(skb)->frag_max_size; +#endif + } else { + kfree_skb(skb); + return -EPFNOSUPPORT; + } + + skb_clear_hash(skb); + skb->ignore_df = 1; + + return 0; +} +EXPORT_SYMBOL_GPL(nf_ct_handle_fragments); diff --git a/net/netfilter/nf_nat_bpf.c b/net/netfilter/nf_nat_bpf.c index 0fa5a0bbb0ff..141ee7783223 100644 --- a/net/netfilter/nf_nat_bpf.c +++ b/net/netfilter/nf_nat_bpf.c @@ -30,9 +30,9 @@ __diag_ignore_all("-Wmissing-prototypes", * interpreted as select a random port. * @manip - NF_NAT_MANIP_SRC or NF_NAT_MANIP_DST */ -int bpf_ct_set_nat_info(struct nf_conn___init *nfct, - union nf_inet_addr *addr, int port, - enum nf_nat_manip_type manip) +__bpf_kfunc int bpf_ct_set_nat_info(struct nf_conn___init *nfct, + union nf_inet_addr *addr, int port, + enum nf_nat_manip_type manip) { struct nf_conn *ct = (struct nf_conn *)nfct; u16 proto = nf_ct_l3num(ct); diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 600993c80050..04c4036bf406 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -13,7 +13,7 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> -#include <linux/string.h> +#include <linux/string_helpers.h> #include <linux/skbuff.h> #include <linux/mutex.h> #include <linux/bitmap.h> @@ -457,7 +457,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family) if (WARN_ON(grp->name[0] == '\0')) return -EINVAL; - if (WARN_ON(memchr(grp->name, '\0', GENL_NAMSIZ) == NULL)) + if (WARN_ON(!string_is_terminated(grp->name, GENL_NAMSIZ))) return -EINVAL; } diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig index 747d537a3f06..29a7081858cd 100644 --- a/net/openvswitch/Kconfig +++ b/net/openvswitch/Kconfig @@ -15,6 +15,7 @@ config OPENVSWITCH select NET_MPLS_GSO select DST_CACHE select NET_NSH + select NF_CONNTRACK_OVS if NF_CONNTRACK select NF_NAT_OVS if NF_NAT help Open vSwitch is a multilayer Ethernet switch targeted at virtualized diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 2172930b1f17..331730fd3580 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -9,6 +9,7 @@ #include <linux/udp.h> #include <linux/sctp.h> #include <linux/static_key.h> +#include <linux/string_helpers.h> #include <net/ip.h> #include <net/genetlink.h> #include <net/netfilter/nf_conntrack_core.h> @@ -434,52 +435,21 @@ static int ovs_ct_set_labels(struct nf_conn *ct, struct sw_flow_key *key, return 0; } -/* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero - * value if 'skb' is freed. - */ -static int handle_fragments(struct net *net, struct sw_flow_key *key, - u16 zone, struct sk_buff *skb) +static int ovs_ct_handle_fragments(struct net *net, struct sw_flow_key *key, + u16 zone, int family, struct sk_buff *skb) { struct ovs_skb_cb ovs_cb = *OVS_CB(skb); int err; - if (key->eth.type == htons(ETH_P_IP)) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - err = ip_defrag(net, skb, user); - if (err) - return err; - - ovs_cb.mru = IPCB(skb)->frag_max_size; -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - } else if (key->eth.type == htons(ETH_P_IPV6)) { - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err) { - if (err != -EINPROGRESS) - kfree_skb(skb); - return err; - } - - key->ip.proto = ipv6_hdr(skb)->nexthdr; - ovs_cb.mru = IP6CB(skb)->frag_max_size; -#endif - } else { - kfree_skb(skb); - return -EPFNOSUPPORT; - } + err = nf_ct_handle_fragments(net, skb, zone, family, &key->ip.proto, &ovs_cb.mru); + if (err) + return err; /* The key extracted from the fragment that completed this datagram * likely didn't have an L4 header, so regenerate it. */ ovs_flow_key_update_l3l4(skb, key); - key->ip.frag = OVS_FRAG_TYPE_NONE; - skb_clear_hash(skb); - skb->ignore_df = 1; *OVS_CB(skb) = ovs_cb; return 0; @@ -1090,36 +1060,6 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int ovs_skb_network_trim(struct sk_buff *skb) -{ - unsigned int len; - int err; - - switch (skb->protocol) { - case htons(ETH_P_IP): - len = skb_ip_totlen(skb); - break; - case htons(ETH_P_IPV6): - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - err = pskb_trim_rcsum(skb, len); - if (err) - kfree_skb(skb); - - return err; -} - /* Returns 0 on success, -EINPROGRESS if 'skb' is stolen, or other nonzero * value if 'skb' is freed. */ @@ -1134,12 +1074,15 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, nh_ofs = skb_network_offset(skb); skb_pull_rcsum(skb, nh_ofs); - err = ovs_skb_network_trim(skb); - if (err) + err = nf_ct_skb_network_trim(skb, info->family); + if (err) { + kfree_skb(skb); return err; + } if (key->ip.frag != OVS_FRAG_TYPE_NONE) { - err = handle_fragments(net, key, info->zone.id, skb); + err = ovs_ct_handle_fragments(net, key, info->zone.id, + info->family, skb); if (err) return err; } @@ -1383,7 +1326,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #endif case OVS_CT_ATTR_HELPER: *helper = nla_data(a); - if (!memchr(*helper, '\0', nla_len(a))) { + if (!string_is_terminated(*helper, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack helper"); return -EINVAL; } @@ -1404,7 +1347,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); - if (!memchr(info->timeout, '\0', nla_len(a))) { + if (!string_is_terminated(info->timeout, nla_len(a))) { OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e20d1a973417..416976f70322 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -107,7 +107,8 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, rcu_assign_pointer(flow->stats[cpu], new_stats); - cpumask_set_cpu(cpu, &flow->cpu_used_mask); + cpumask_set_cpu(cpu, + flow->cpu_used_mask); goto unlock; } } @@ -135,7 +136,8 @@ void ovs_flow_stats_get(const struct sw_flow *flow, memset(ovs_stats, 0, sizeof(*ovs_stats)); /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { @@ -159,7 +161,8 @@ void ovs_flow_stats_clear(struct sw_flow *flow) int cpu; /* We open code this to make sure cpu 0 is always considered */ - for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + for (cpu = 0; cpu < nr_cpu_ids; + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 073ab73ffeaa..b5711aff6e76 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -229,7 +229,7 @@ struct sw_flow { */ struct sw_flow_key key; struct sw_flow_id id; - struct cpumask cpu_used_mask; + struct cpumask *cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 0a0e4c283f02..791504b7f42b 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -79,6 +79,7 @@ struct sw_flow *ovs_flow_alloc(void) return ERR_PTR(-ENOMEM); flow->stats_last_writer = -1; + flow->cpu_used_mask = (struct cpumask *)&flow->stats[nr_cpu_ids]; /* Initialize the default stat node. */ stats = kmem_cache_alloc_node(flow_stats_cache, @@ -91,7 +92,7 @@ struct sw_flow *ovs_flow_alloc(void) RCU_INIT_POINTER(flow->stats[0], stats); - cpumask_set_cpu(0, &flow->cpu_used_mask); + cpumask_set_cpu(0, flow->cpu_used_mask); return flow; err: @@ -115,7 +116,7 @@ static void flow_free(struct sw_flow *flow) flow->sf_acts); /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; - cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { + cpu = cpumask_next(cpu, flow->cpu_used_mask)) { if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, (struct sw_flow_stats __force *)flow->stats[cpu]); @@ -1196,7 +1197,8 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct sw_flow_stats *)), + * sizeof(struct sw_flow_stats *)) + + cpumask_size(), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; diff --git a/net/rds/message.c b/net/rds/message.c index b47e4f0a1639..c19c93561227 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6eaffb0d8fdc..e9f1f49d18c2 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -54,12 +54,14 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); + if (!busy && !rxrpc_try_get_call(call, rxrpc_call_get_poke)) + busy = true; if (!busy) { - rxrpc_get_call(call, rxrpc_call_get_poke); list_add_tail(&call->attend_link, &local->call_attend_q); } spin_unlock_bh(&local->lock); - rxrpc_wake_up_io_thread(local); + if (!busy) + rxrpc_wake_up_io_thread(local); } } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 44414e724415..95f4bc206b3d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -163,7 +163,7 @@ void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), - pkt.ack.reason, 0); + pkt.ack.reason, 0, rxrpc_rx_window_size); break; default: diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 6b2022240076..5e53429c6922 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -80,7 +80,8 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_txbuf *txb) + struct rxrpc_txbuf *txb, + u16 *_rwind) { struct rxrpc_ackinfo ackinfo; unsigned int qsize, sack, wrap, to; @@ -124,6 +125,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, jmax = rxrpc_rx_jumbo_max; qsize = (window - 1) - call->rx_consumed; rsize = max_t(int, call->rx_winsize - qsize, 0); + *_rwind = rsize; ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(rsize); @@ -190,6 +192,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_serial_t serial; size_t len, n; int ret, rtt_slot = -1; + u16 rwind; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; @@ -205,7 +208,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; - n = rxrpc_fill_out_ack(conn, call, txb); + n = rxrpc_fill_out_ack(conn, call, txb, &rwind); if (n == 0) return 0; @@ -217,7 +220,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), - ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks, + rwind); if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 50d263a6359d..76eb2b9cd936 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -137,7 +137,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) /* Check to see if there's an ACK that needs sending. */ acked = atomic_add_return(call->rx_consumed - old_consumed, &call->ackr_nr_consumed); - if (acked > 2 && + if (acked > 8 && !test_and_set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) rxrpc_poke_call(call, rxrpc_call_poke_idle); } diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 944320e65ea8..3bcd6ee80396 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -63,7 +63,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); - kfree_skb_reason(skb, SKB_CONSUMED); + consume_skb(skb); } } @@ -78,6 +78,6 @@ void rxrpc_purge_queue(struct sk_buff_head *list) int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); - kfree_skb_reason(skb, SKB_CONSUMED); + consume_skb(skb); } } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index de18a0dda6df..4f7b52f5a11c 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -195,8 +195,14 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_MQPRIO_LIB + tristate + help + Common library for manipulating mqprio queue configurations. + config NET_SCH_TAPRIO tristate "Time Aware Priority (taprio) Scheduler" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Time Aware Priority (taprio) packet scheduling algorithm. @@ -253,6 +259,7 @@ config NET_SCH_DRR config NET_SCH_MQPRIO tristate "Multi-queue priority scheduler (MQPRIO)" + select NET_SCH_MQPRIO_LIB help Say Y here if you want to use the Multi-queue Priority scheduler. This scheduler allows QOS to be offloaded on NICs that have support @@ -977,6 +984,7 @@ config NET_ACT_TUNNEL_KEY config NET_ACT_CT tristate "connection tracking tc action" depends on NET_CLS_ACT && NF_CONNTRACK && (!NF_NAT || NF_NAT) && NF_FLOW_TABLE + select NF_CONNTRACK_OVS select NF_NAT_OVS if NF_NAT help Say Y here to allow sending the packets to conntrack module. diff --git a/net/sched/Makefile b/net/sched/Makefile index dd14ef413fda..7911eec09837 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o obj-$(CONFIG_NET_SCH_ETS) += sch_ets.o obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o +obj-$(CONFIG_NET_SCH_MQPRIO_LIB) += sch_mqprio_lib.o obj-$(CONFIG_NET_SCH_SKBPRIO) += sch_skbprio.o obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index b126f03c1bb6..9cc0bc7c71ed 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -726,31 +726,6 @@ drop_ct: return false; } -/* Trim the skb to the length specified by the IP/IPv6 header, - * removing any trailing lower-layer padding. This prepares the skb - * for higher-layer processing that assumes skb->len excludes padding - * (such as nf_ip_checksum). The caller needs to pull the skb to the - * network header, and ensure ip_hdr/ipv6_hdr points to valid data. - */ -static int tcf_ct_skb_network_trim(struct sk_buff *skb, int family) -{ - unsigned int len; - - switch (family) { - case NFPROTO_IPV4: - len = skb_ip_totlen(skb); - break; - case NFPROTO_IPV6: - len = sizeof(struct ipv6hdr) - + ntohs(ipv6_hdr(skb)->payload_len); - break; - default: - len = skb->len; - } - - return pskb_trim_rcsum(skb, len); -} - static u8 tcf_ct_skb_nf_family(struct sk_buff *skb) { u8 family = NFPROTO_UNSPEC; @@ -810,6 +785,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, struct nf_conn *ct; int err = 0; bool frag; + u8 proto; u16 mru; /* Previously seen (loopback)? Ignore. */ @@ -825,50 +801,14 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, return err; skb_get(skb); - mru = tc_skb_cb(skb)->mru; - - if (family == NFPROTO_IPV4) { - enum ip_defrag_users user = IP_DEFRAG_CONNTRACK_IN + zone; - - memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); - local_bh_disable(); - err = ip_defrag(net, skb, user); - local_bh_enable(); - if (err && err != -EINPROGRESS) - return err; - - if (!err) { - *defrag = true; - mru = IPCB(skb)->frag_max_size; - } - } else { /* NFPROTO_IPV6 */ -#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - enum ip6_defrag_users user = IP6_DEFRAG_CONNTRACK_IN + zone; - - memset(IP6CB(skb), 0, sizeof(struct inet6_skb_parm)); - err = nf_ct_frag6_gather(net, skb, user); - if (err && err != -EINPROGRESS) - goto out_free; - - if (!err) { - *defrag = true; - mru = IP6CB(skb)->frag_max_size; - } -#else - err = -EOPNOTSUPP; - goto out_free; -#endif - } + err = nf_ct_handle_fragments(net, skb, zone, family, &proto, &mru); + if (err) + return err; - if (err != -EINPROGRESS) - tc_skb_cb(skb)->mru = mru; - skb_clear_hash(skb); - skb->ignore_df = 1; - return err; + *defrag = true; + tc_skb_cb(skb)->mru = mru; -out_free: - kfree_skb(skb); - return err; + return 0; } static void tcf_ct_params_free(struct tcf_ct_params *params) @@ -1011,7 +951,7 @@ TC_INDIRECT_SCOPE int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, if (err) goto drop; - err = tcf_ct_skb_network_trim(skb, family); + err = nf_ct_skb_network_trim(skb, family); if (err) goto drop; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c14018a8052c..e9780631b5b5 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1282,12 +1282,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (err) goto err_out3; - if (ops->init) { - err = ops->init(sch, tca[TCA_OPTIONS], extack); - if (err != 0) - goto err_out5; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { @@ -1296,11 +1290,18 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } rcu_assign_pointer(sch->stab, stab); } + + if (ops->init) { + err = ops->init(sch, tca[TCA_OPTIONS], extack); + if (err != 0) + goto err_out5; + } + if (tca[TCA_RATE]) { err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); - goto err_out4; + goto err_out5; } err = gen_new_estimator(&sch->bstats, @@ -1311,7 +1312,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); - goto err_out4; + goto err_out5; } } @@ -1321,6 +1322,8 @@ static struct Qdisc *qdisc_create(struct net_device *dev, return sch; err_out5: + qdisc_put_stab(rtnl_dereference(sch->stab)); +err_out4: /* ops->init() failed, we call ->destroy() like qdisc_create_dflt() */ if (ops->destroy) ops->destroy(sch); @@ -1332,16 +1335,6 @@ err_out2: err_out: *errp = err; return NULL; - -err_out4: - /* - * Any broken qdiscs that would require a ops->reset() here? - * The qdisc was never in action so it shouldn't be necessary. - */ - qdisc_put_stab(rtnl_dereference(sch->stab)); - if (ops->destroy) - ops->destroy(sch); - goto err_out3; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index cc28e41fb745..92f2975b6a82 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -433,7 +433,7 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (m) { unsigned int prio = ffz(~m); - if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + if (WARN_ON_ONCE(prio >= ARRAY_SIZE(p->inner.clprio))) break; m &= ~(1 << prio); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 4c68abaa289b..48ed87b91086 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -17,6 +17,8 @@ #include <net/sch_generic.h> #include <net/pkt_cls.h> +#include "sch_mqprio_lib.h" + struct mqprio_sched { struct Qdisc **qdiscs; u16 mode; @@ -27,6 +29,62 @@ struct mqprio_sched { u64 max_rate[TC_QOPT_MAX_QUEUE]; }; +static int mqprio_enable_offload(struct Qdisc *sch, + const struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int err, i; + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + if (priv->shaper != TC_MQPRIO_SHAPER_DCB) + return -EINVAL; + break; + case TC_MQPRIO_MODE_CHANNEL: + mqprio.flags = priv->flags; + if (priv->flags & TC_MQPRIO_F_MODE) + mqprio.mode = priv->mode; + if (priv->flags & TC_MQPRIO_F_SHAPER) + mqprio.shaper = priv->shaper; + if (priv->flags & TC_MQPRIO_F_MIN_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.min_rate[i] = priv->min_rate[i]; + if (priv->flags & TC_MQPRIO_F_MAX_RATE) + for (i = 0; i < mqprio.qopt.num_tc; i++) + mqprio.max_rate[i] = priv->max_rate[i]; + break; + default: + return -EINVAL; + } + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + if (err) + return err; + + priv->hw_offload = mqprio.qopt.hw; + + return 0; +} + +static void mqprio_disable_offload(struct Qdisc *sch) +{ + struct tc_mqprio_qopt_offload mqprio = { { 0 } }; + struct mqprio_sched *priv = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + switch (priv->mode) { + case TC_MQPRIO_MODE_DCB: + case TC_MQPRIO_MODE_CHANNEL: + dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO, + &mqprio); + break; + } +} + static void mqprio_destroy(struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); @@ -41,37 +99,17 @@ static void mqprio_destroy(struct Qdisc *sch) kfree(priv->qdiscs); } - if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) { - struct tc_mqprio_qopt_offload mqprio = { { 0 } }; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - case TC_MQPRIO_MODE_CHANNEL: - dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); - break; - default: - return; - } - } else { + if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) + mqprio_disable_offload(sch); + else netdev_set_num_tc(dev, 0); - } } -static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + const struct tc_mqprio_caps *caps, + struct netlink_ext_ack *extack) { - int i, j; - - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) - return -EINVAL; - - /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) - return -EINVAL; - } + int err; /* Limit qopt->hw to maximum supported offload value. Drivers have * the option of overriding this later if they don't support the a @@ -80,31 +118,23 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX) qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX; - /* If hardware offload is requested we will leave it to the device - * to either populate the queue counts itself or to validate the - * provided queue counts. If ndo_setup_tc is not present then - * hardware doesn't support offload and we should return an error. + /* If hardware offload is requested, we will leave 3 options to the + * device driver: + * - populate the queue counts itself (and ignore what was requested) + * - validate the provided queue counts by itself (and apply them) + * - request queue count validation here (and apply them) */ - if (qopt->hw) - return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL; - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->real_num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) - return -EINVAL; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) - return -EINVAL; - } - } + err = mqprio_validate_qopt(dev, qopt, + !qopt->hw || caps->validate_queue_counts, + false, extack); + if (err) + return err; + + /* If ndo_setup_tc is not present then hardware doesn't support offload + * and we should return an error. + */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; return 0; } @@ -130,6 +160,67 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, return 0; } +static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt, + struct nlattr *opt) +{ + struct mqprio_sched *priv = qdisc_priv(sch); + struct nlattr *tb[TCA_MQPRIO_MAX + 1]; + struct nlattr *attr; + int i, rem, err; + + err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, + sizeof(*qopt)); + if (err < 0) + return err; + + if (!qopt->hw) + return -EINVAL; + + if (tb[TCA_MQPRIO_MODE]) { + priv->flags |= TC_MQPRIO_F_MODE; + priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); + } + + if (tb[TCA_MQPRIO_SHAPER]) { + priv->flags |= TC_MQPRIO_F_SHAPER; + priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); + } + + if (tb[TCA_MQPRIO_MIN_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->min_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MIN_RATE; + } + + if (tb[TCA_MQPRIO_MAX_RATE64]) { + if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) + return -EINVAL; + i = 0; + nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], + rem) { + if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) + return -EINVAL; + if (i >= qopt->num_tc) + break; + priv->max_rate[i] = *(u64 *)nla_data(attr); + i++; + } + priv->flags |= TC_MQPRIO_F_MAX_RATE; + } + + return 0; +} + static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -139,9 +230,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *qdisc; int i, err = -EOPNOTSUPP; struct tc_mqprio_qopt *qopt = NULL; - struct nlattr *tb[TCA_MQPRIO_MAX + 1]; - struct nlattr *attr; - int rem; + struct tc_mqprio_caps caps; int len; BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); @@ -160,61 +249,18 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO, + &caps, sizeof(caps)); + qopt = nla_data(opt); - if (mqprio_parse_opt(dev, qopt)) + if (mqprio_parse_opt(dev, qopt, &caps, extack)) return -EINVAL; len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt)); if (len > 0) { - err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy, - sizeof(*qopt)); - if (err < 0) + err = mqprio_parse_nlattr(sch, qopt, opt); + if (err) return err; - - if (!qopt->hw) - return -EINVAL; - - if (tb[TCA_MQPRIO_MODE]) { - priv->flags |= TC_MQPRIO_F_MODE; - priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]); - } - - if (tb[TCA_MQPRIO_SHAPER]) { - priv->flags |= TC_MQPRIO_F_SHAPER; - priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]); - } - - if (tb[TCA_MQPRIO_MIN_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->min_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MIN_RATE; - } - - if (tb[TCA_MQPRIO_MAX_RATE64]) { - if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) - return -EINVAL; - i = 0; - nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64], - rem) { - if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) - return -EINVAL; - if (i >= qopt->num_tc) - break; - priv->max_rate[i] = *(u64 *)nla_data(attr); - i++; - } - priv->flags |= TC_MQPRIO_F_MAX_RATE; - } } /* pre-allocate qdisc, attachment can't fail */ @@ -241,36 +287,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt, * supplied and verified mapping */ if (qopt->hw) { - struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt}; - - switch (priv->mode) { - case TC_MQPRIO_MODE_DCB: - if (priv->shaper != TC_MQPRIO_SHAPER_DCB) - return -EINVAL; - break; - case TC_MQPRIO_MODE_CHANNEL: - mqprio.flags = priv->flags; - if (priv->flags & TC_MQPRIO_F_MODE) - mqprio.mode = priv->mode; - if (priv->flags & TC_MQPRIO_F_SHAPER) - mqprio.shaper = priv->shaper; - if (priv->flags & TC_MQPRIO_F_MIN_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.min_rate[i] = priv->min_rate[i]; - if (priv->flags & TC_MQPRIO_F_MAX_RATE) - for (i = 0; i < mqprio.qopt.num_tc; i++) - mqprio.max_rate[i] = priv->max_rate[i]; - break; - default: - return -EINVAL; - } - err = dev->netdev_ops->ndo_setup_tc(dev, - TC_SETUP_QDISC_MQPRIO, - &mqprio); + err = mqprio_enable_offload(sch, qopt, extack); if (err) return err; - - priv->hw_offload = mqprio.qopt.hw; } else { netdev_set_num_tc(dev, qopt->num_tc); for (i = 0; i < qopt->num_tc; i++) @@ -387,7 +406,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb); struct tc_mqprio_qopt opt = { 0 }; struct Qdisc *qdisc; - unsigned int ntx, tc; + unsigned int ntx; sch->q.qlen = 0; gnet_stats_basic_sync_init(&sch->bstats); @@ -411,15 +430,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) spin_unlock_bh(qdisc_lock(qdisc)); } - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + mqprio_qopt_reconstruct(dev, &opt); opt.hw = priv->hw_offload; - for (tc = 0; tc < netdev_get_num_tc(dev); tc++) { - opt.count[tc] = dev->tc_to_txq[tc].count; - opt.offset[tc] = dev->tc_to_txq[tc].offset; - } - if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c new file mode 100644 index 000000000000..c58a533b8ec5 --- /dev/null +++ b/net/sched/sch_mqprio_lib.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/netlink.h> +#include <linux/types.h> +#include <net/pkt_sched.h> + +#include "sch_mqprio_lib.h" + +/* Returns true if the intervals [a, b) and [c, d) overlap. */ +static bool intervals_overlap(int a, int b, int c, int d) +{ + int left = max(a, c), right = min(b, d); + + return left < right; +} + +static int mqprio_validate_queue_counts(struct net_device *dev, + const struct tc_mqprio_qopt *qopt, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, j; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + if (!qopt->count[i]) { + NL_SET_ERR_MSG_FMT_MOD(extack, "No queues for TC %d", + i); + return -EINVAL; + } + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "Queues %d:%d for TC %d exceed the %d TX queues available", + qopt->count[i], qopt->offset[i], + i, dev->real_num_tx_queues); + return -EINVAL; + } + + if (allow_overlapping_txqs) + continue; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (intervals_overlap(qopt->offset[i], last, + qopt->offset[j], + qopt->offset[j] + + qopt->count[j])) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "TC %d queues %d@%d overlap with TC %d queues %d@%d", + i, qopt->count[i], qopt->offset[i], + j, qopt->count[j], qopt->offset[j]); + return -EINVAL; + } + } + } + + return 0; +} + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack) +{ + int i, err; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, + "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i <= TC_BITMASK; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, + "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + if (validate_queue_counts) { + err = mqprio_validate_queue_counts(dev, qopt, + allow_overlapping_txqs, + extack); + if (err) + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(mqprio_validate_qopt); + +void mqprio_qopt_reconstruct(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int tc, num_tc = netdev_get_num_tc(dev); + + qopt->num_tc = num_tc; + memcpy(qopt->prio_tc_map, dev->prio_tc_map, sizeof(qopt->prio_tc_map)); + + for (tc = 0; tc < num_tc; tc++) { + qopt->count[tc] = dev->tc_to_txq[tc].count; + qopt->offset[tc] = dev->tc_to_txq[tc].offset; + } +} +EXPORT_SYMBOL_GPL(mqprio_qopt_reconstruct); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_mqprio_lib.h b/net/sched/sch_mqprio_lib.h new file mode 100644 index 000000000000..63f725ab8761 --- /dev/null +++ b/net/sched/sch_mqprio_lib.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SCH_MQPRIO_LIB_H +#define __SCH_MQPRIO_LIB_H + +#include <linux/types.h> + +struct net_device; +struct netlink_ext_ack; +struct tc_mqprio_qopt; + +int mqprio_validate_qopt(struct net_device *dev, struct tc_mqprio_qopt *qopt, + bool validate_queue_counts, + bool allow_overlapping_txqs, + struct netlink_ext_ack *extack); +void mqprio_qopt_reconstruct(struct net_device *dev, + struct tc_mqprio_qopt *qopt); + +#endif diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index c322a61eaeea..9781b47962bb 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -26,7 +26,11 @@ #include <net/sock.h> #include <net/tcp.h> +#include "sch_mqprio_lib.h" + static LIST_HEAD(taprio_list); +static struct static_key_false taprio_have_broken_mqprio; +static struct static_key_false taprio_have_working_mqprio; #define TAPRIO_ALL_GATES_OPEN -1 @@ -35,15 +39,19 @@ static LIST_HEAD(taprio_list); #define TAPRIO_FLAGS_INVALID U32_MAX struct sched_entry { - struct list_head list; - - /* The instant that this entry "closes" and the next one - * should open, the qdisc will make some effort so that no - * packet leaves after this time. + /* Durations between this GCL entry and the GCL entry where the + * respective traffic class gate closes */ - ktime_t close_time; + u64 gate_duration[TC_MAX_QUEUE]; + atomic_t budget[TC_MAX_QUEUE]; + /* The qdisc makes some effort so that no packet leaves + * after this time + */ + ktime_t gate_close_time[TC_MAX_QUEUE]; + struct list_head list; + /* Used to calculate when to advance the schedule */ + ktime_t end_time; ktime_t next_txtime; - atomic_t budget; int index; u32 gate_mask; u32 interval; @@ -51,10 +59,16 @@ struct sched_entry { }; struct sched_gate_list { + /* Longest non-zero contiguous gate durations per traffic class, + * or 0 if a traffic class gate never opens during the schedule. + */ + u64 max_open_gate_duration[TC_MAX_QUEUE]; + u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ + u32 max_sdu[TC_MAX_QUEUE]; /* for dump */ struct rcu_head rcu; struct list_head entries; size_t num_entries; - ktime_t cycle_close_time; + ktime_t cycle_end_time; s64 cycle_time; s64 cycle_time_extension; s64 base_time; @@ -67,6 +81,8 @@ struct taprio_sched { enum tk_offsets tk_offset; int clockid; bool offloaded; + bool detected_mqprio; + bool broken_mqprio; atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+ * speeds it's sub-nanoseconds per byte */ @@ -78,8 +94,8 @@ struct taprio_sched { struct sched_gate_list __rcu *admin_sched; struct hrtimer advance_timer; struct list_head taprio_list; - u32 max_frm_len[TC_MAX_QUEUE]; /* for the fast path */ - u32 max_sdu[TC_MAX_QUEUE]; /* for dump and offloading */ + int cur_txq[TC_MAX_QUEUE]; + u32 max_sdu[TC_MAX_QUEUE]; /* save info from the user */ u32 txtime_delay; }; @@ -88,6 +104,57 @@ struct __tc_taprio_qopt_offload { struct tc_taprio_qopt_offload offload; }; +static void taprio_calculate_gate_durations(struct taprio_sched *q, + struct sched_gate_list *sched) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + struct sched_entry *entry, *cur; + int tc; + + list_for_each_entry(entry, &sched->entries, list) { + u32 gates_still_open = entry->gate_mask; + + /* For each traffic class, calculate each open gate duration, + * starting at this schedule entry and ending at the schedule + * entry containing a gate close event for that TC. + */ + cur = entry; + + do { + if (!gates_still_open) + break; + + for (tc = 0; tc < num_tc; tc++) { + if (!(gates_still_open & BIT(tc))) + continue; + + if (cur->gate_mask & BIT(tc)) + entry->gate_duration[tc] += cur->interval; + else + gates_still_open &= ~BIT(tc); + } + + cur = list_next_entry_circular(cur, &sched->entries, list); + } while (cur != entry); + + /* Keep track of the maximum gate duration for each traffic + * class, taking care to not confuse a traffic class which is + * temporarily closed with one that is always closed. + */ + for (tc = 0; tc < num_tc; tc++) + if (entry->gate_duration[tc] && + sched->max_open_gate_duration[tc] < entry->gate_duration[tc]) + sched->max_open_gate_duration[tc] = entry->gate_duration[tc]; + } +} + +static bool taprio_entry_allows_tx(ktime_t skb_end_time, + struct sched_entry *entry, int tc) +{ + return ktime_before(skb_end_time, entry->gate_close_time[tc]); +} + static ktime_t sched_base_time(const struct sched_gate_list *sched) { if (!sched) @@ -180,6 +247,55 @@ static int length_to_duration(struct taprio_sched *q, int len) return div_u64(len * atomic64_read(&q->picos_per_byte), PSEC_PER_NSEC); } +static int duration_to_length(struct taprio_sched *q, u64 duration) +{ + return div_u64(duration * PSEC_PER_NSEC, atomic64_read(&q->picos_per_byte)); +} + +/* Sets sched->max_sdu[] and sched->max_frm_len[] to the minimum between the + * q->max_sdu[] requested by the user and the max_sdu dynamically determined by + * the maximum open gate durations at the given link speed. + */ +static void taprio_update_queue_max_sdu(struct taprio_sched *q, + struct sched_gate_list *sched, + struct qdisc_size_table *stab) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + u32 max_sdu_from_user; + u32 max_sdu_dynamic; + u32 max_sdu; + int tc; + + for (tc = 0; tc < num_tc; tc++) { + max_sdu_from_user = q->max_sdu[tc] ?: U32_MAX; + + /* TC gate never closes => keep the queueMaxSDU + * selected by the user + */ + if (sched->max_open_gate_duration[tc] == sched->cycle_time) { + max_sdu_dynamic = U32_MAX; + } else { + u32 max_frm_len; + + max_frm_len = duration_to_length(q, sched->max_open_gate_duration[tc]); + if (stab) + max_frm_len -= stab->szopts.overhead; + max_sdu_dynamic = max_frm_len - dev->hard_header_len; + } + + max_sdu = min(max_sdu_dynamic, max_sdu_from_user); + + if (max_sdu != U32_MAX) { + sched->max_frm_len[tc] = max_sdu + dev->hard_header_len; + sched->max_sdu[tc] = max_sdu; + } else { + sched->max_frm_len[tc] = U32_MAX; /* never oversized */ + sched->max_sdu[tc] = 0; + } + } +} + /* Returns the entry corresponding to next available interval. If * validate_interval is set, it only validates whether the timestamp occurs * when the gate corresponding to the skb's traffic class is open. @@ -413,14 +529,33 @@ done: return txtime; } -static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, - struct Qdisc *child, struct sk_buff **to_free) +/* Devices with full offload are expected to honor this in hardware */ +static bool taprio_skb_exceeds_queue_max_sdu(struct Qdisc *sch, + struct sk_buff *skb) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); + struct sched_gate_list *sched; int prio = skb->priority; + bool exceeds = false; u8 tc; + tc = netdev_get_prio_tc_map(dev, prio); + + rcu_read_lock(); + sched = rcu_dereference(q->oper_sched); + if (sched && skb->len > sched->max_frm_len[tc]) + exceeds = true; + rcu_read_unlock(); + + return exceeds; +} + +static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + /* sk_flags are only safe to use on full sockets. */ if (skb->sk && sk_fullsock(skb->sk) && sock_flag(skb->sk, SOCK_TXTIME)) { if (!is_valid_interval(skb, sch)) @@ -431,17 +566,53 @@ static int taprio_enqueue_one(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); } - /* Devices with full offload are expected to honor this in hardware */ - tc = netdev_get_prio_tc_map(dev, prio); - if (skb->len > q->max_frm_len[tc]) - return qdisc_drop(skb, sch, to_free); - qdisc_qstats_backlog_inc(sch, skb); sch->q.qlen++; return qdisc_enqueue(skb, child, to_free); } +static int taprio_enqueue_segmented(struct sk_buff *skb, struct Qdisc *sch, + struct Qdisc *child, + struct sk_buff **to_free) +{ + unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); + netdev_features_t features = netif_skb_features(skb); + struct sk_buff *segs, *nskb; + int ret; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR_OR_NULL(segs)) + return qdisc_drop(skb, sch, to_free); + + skb_list_walk_safe(segs, segs, nskb) { + skb_mark_not_on_list(segs); + qdisc_skb_cb(segs)->pkt_len = segs->len; + slen += segs->len; + + /* FIXME: we should be segmenting to a smaller size + * rather than dropping these + */ + if (taprio_skb_exceeds_queue_max_sdu(sch, segs)) + ret = qdisc_drop(segs, sch, to_free); + else + ret = taprio_enqueue_one(segs, sch, child, to_free); + + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + numsegs++; + } + } + + if (numsegs > 1) + qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); + consume_skb(skb); + + return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + /* Will not be called in the full offload case, since the TX queues are * attached to the Qdisc created using qdisc_create_dflt() */ @@ -458,97 +629,190 @@ static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (unlikely(!child)) return qdisc_drop(skb, sch, to_free); - /* Large packets might not be transmitted when the transmission duration - * exceeds any configured interval. Therefore, segment the skb into - * smaller chunks. Drivers with full offload are expected to handle - * this in hardware. - */ - if (skb_is_gso(skb)) { - unsigned int slen = 0, numsegs = 0, len = qdisc_pkt_len(skb); - netdev_features_t features = netif_skb_features(skb); - struct sk_buff *segs, *nskb; - int ret; - - segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); - if (IS_ERR_OR_NULL(segs)) - return qdisc_drop(skb, sch, to_free); + if (taprio_skb_exceeds_queue_max_sdu(sch, skb)) { + /* Large packets might not be transmitted when the transmission + * duration exceeds any configured interval. Therefore, segment + * the skb into smaller chunks. Drivers with full offload are + * expected to handle this in hardware. + */ + if (skb_is_gso(skb)) + return taprio_enqueue_segmented(skb, sch, child, + to_free); - skb_list_walk_safe(segs, segs, nskb) { - skb_mark_not_on_list(segs); - qdisc_skb_cb(segs)->pkt_len = segs->len; - slen += segs->len; + return qdisc_drop(skb, sch, to_free); + } - ret = taprio_enqueue_one(segs, sch, child, to_free); - if (ret != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(ret)) - qdisc_qstats_drop(sch); - } else { - numsegs++; - } - } + return taprio_enqueue_one(skb, sch, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + WARN_ONCE(1, "taprio only supports operating as root qdisc, peek() not implemented"); + return NULL; +} + +static void taprio_set_budgets(struct taprio_sched *q, + struct sched_gate_list *sched, + struct sched_entry *entry) +{ + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); + int tc, budget; - if (numsegs > 1) - qdisc_tree_reduce_backlog(sch, 1 - numsegs, len - slen); - consume_skb(skb); + for (tc = 0; tc < num_tc; tc++) { + /* Traffic classes which never close have infinite budget */ + if (entry->gate_duration[tc] == sched->cycle_time) + budget = INT_MAX; + else + budget = div64_u64((u64)entry->gate_duration[tc] * PSEC_PER_NSEC, + atomic64_read(&q->picos_per_byte)); - return numsegs > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; + atomic_set(&entry->budget[tc], budget); } +} - return taprio_enqueue_one(skb, sch, child, to_free); +/* When an skb is sent, it consumes from the budget of all traffic classes */ +static int taprio_update_budgets(struct sched_entry *entry, size_t len, + int tc_consumed, int num_tc) +{ + int tc, budget, new_budget = 0; + + for (tc = 0; tc < num_tc; tc++) { + budget = atomic_read(&entry->budget[tc]); + /* Don't consume from infinite budget */ + if (budget == INT_MAX) { + if (tc == tc_consumed) + new_budget = budget; + continue; + } + + if (tc == tc_consumed) + new_budget = atomic_sub_return(len, &entry->budget[tc]); + else + atomic_sub(len, &entry->budget[tc]); + } + + return new_budget; } -/* Will not be called in the full offload case, since the TX queues are - * attached to the Qdisc created using qdisc_create_dflt() - */ -static struct sk_buff *taprio_peek(struct Qdisc *sch) +static struct sk_buff *taprio_dequeue_from_txq(struct Qdisc *sch, int txq, + struct sched_entry *entry, + u32 gate_mask) { struct taprio_sched *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - struct sched_entry *entry; + struct Qdisc *child = q->qdiscs[txq]; + int num_tc = netdev_get_num_tc(dev); struct sk_buff *skb; - u32 gate_mask; - int i; + ktime_t guard; + int prio; + int len; + u8 tc; - rcu_read_lock(); - entry = rcu_dereference(q->current_entry); - gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - rcu_read_unlock(); + if (unlikely(!child)) + return NULL; - if (!gate_mask) + if (TXTIME_ASSIST_IS_ENABLED(q->flags)) + goto skip_peek_checks; + + skb = child->ops->peek(child); + if (!skb) return NULL; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - int prio; - u8 tc; + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); - if (unlikely(!child)) - continue; + if (!(gate_mask & BIT(tc))) + return NULL; - skb = child->ops->peek(child); - if (!skb) - continue; + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(taprio_get_time(q), length_to_duration(q, len)); - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) - return skb; + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + !taprio_entry_allows_tx(guard, entry, tc)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + taprio_update_budgets(entry, len, tc, num_tc) < 0) + return NULL; + +skip_peek_checks: + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; +} + +static void taprio_next_tc_txq(struct net_device *dev, int tc, int *txq) +{ + int offset = dev->tc_to_txq[tc].offset; + int count = dev->tc_to_txq[tc].count; + + (*txq)++; + if (*txq == offset + count) + *txq = offset; +} - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); +/* Prioritize higher traffic classes, and select among TXQs belonging to the + * same TC using round robin + */ +static struct sk_buff *taprio_dequeue_tc_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + int num_tc = netdev_get_num_tc(dev); + struct sk_buff *skb; + int tc; + + for (tc = num_tc - 1; tc >= 0; tc--) { + int first_txq = q->cur_txq[tc]; if (!(gate_mask & BIT(tc))) continue; - return skb; + do { + skb = taprio_dequeue_from_txq(sch, q->cur_txq[tc], + entry, gate_mask); + + taprio_next_tc_txq(dev, tc, &q->cur_txq[tc]); + + if (skb) + return skb; + } while (q->cur_txq[tc] != first_txq); } return NULL; } -static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) +/* Broken way of prioritizing smaller TXQ indices and ignoring the traffic + * class other than to determine whether the gate is open or not + */ +static struct sk_buff *taprio_dequeue_txq_priority(struct Qdisc *sch, + struct sched_entry *entry, + u32 gate_mask) { - atomic_set(&entry->budget, - div64_u64((u64)entry->interval * PSEC_PER_NSEC, - atomic64_read(&q->picos_per_byte))); + struct net_device *dev = qdisc_dev(sch); + struct sk_buff *skb; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + skb = taprio_dequeue_from_txq(sch, i, entry, gate_mask); + if (skb) + return skb; + } + + return NULL; } /* Will not be called in the full offload case, since the TX queues are @@ -557,11 +821,9 @@ static void taprio_set_budget(struct taprio_sched *q, struct sched_entry *entry) static struct sk_buff *taprio_dequeue(struct Qdisc *sch) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); struct sk_buff *skb = NULL; struct sched_entry *entry; u32 gate_mask; - int i; rcu_read_lock(); entry = rcu_dereference(q->current_entry); @@ -571,69 +833,23 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) * "AdminGateStates" */ gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; - if (!gate_mask) goto done; - for (i = 0; i < dev->num_tx_queues; i++) { - struct Qdisc *child = q->qdiscs[i]; - ktime_t guard; - int prio; - int len; - u8 tc; - - if (unlikely(!child)) - continue; - - if (TXTIME_ASSIST_IS_ENABLED(q->flags)) { - skb = child->ops->dequeue(child); - if (!skb) - continue; - goto skb_found; - } - - skb = child->ops->peek(child); - if (!skb) - continue; - - prio = skb->priority; - tc = netdev_get_prio_tc_map(dev, prio); - - if (!(gate_mask & BIT(tc))) { - skb = NULL; - continue; - } - - len = qdisc_pkt_len(skb); - guard = ktime_add_ns(taprio_get_time(q), - length_to_duration(q, len)); - - /* In the case that there's no gate entry, there's no - * guard band ... - */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) { - skb = NULL; - continue; - } - - /* ... and no budget. */ - if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) { - skb = NULL; - continue; - } - - skb = child->ops->dequeue(child); - if (unlikely(!skb)) - goto done; - -skb_found: - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - goto done; + if (static_branch_unlikely(&taprio_have_broken_mqprio) && + !static_branch_likely(&taprio_have_working_mqprio)) { + /* Single NIC kind which is broken */ + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + } else if (static_branch_likely(&taprio_have_working_mqprio) && + !static_branch_unlikely(&taprio_have_broken_mqprio)) { + /* Single NIC kind which prioritizes properly */ + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); + } else { + /* Mixed NIC kinds present in system, need dynamic testing */ + if (q->broken_mqprio) + skb = taprio_dequeue_txq_priority(sch, entry, gate_mask); + else + skb = taprio_dequeue_tc_priority(sch, entry, gate_mask); } done: @@ -648,7 +864,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, if (list_is_last(&entry->list, &oper->entries)) return true; - if (ktime_compare(entry->close_time, oper->cycle_close_time) == 0) + if (ktime_compare(entry->end_time, oper->cycle_end_time) == 0) return true; return false; @@ -656,7 +872,7 @@ static bool should_restart_cycle(const struct sched_gate_list *oper, static bool should_change_schedules(const struct sched_gate_list *admin, const struct sched_gate_list *oper, - ktime_t close_time) + ktime_t end_time) { ktime_t next_base_time, extension_time; @@ -665,18 +881,18 @@ static bool should_change_schedules(const struct sched_gate_list *admin, next_base_time = sched_base_time(admin); - /* This is the simple case, the close_time would fall after + /* This is the simple case, the end_time would fall after * the next schedule base_time. */ - if (ktime_compare(next_base_time, close_time) <= 0) + if (ktime_compare(next_base_time, end_time) <= 0) return true; - /* This is the cycle_time_extension case, if the close_time + /* This is the cycle_time_extension case, if the end_time * plus the amount that can be extended would fall after the * next schedule base_time, we can extend the current schedule * for that amount. */ - extension_time = ktime_add_ns(close_time, oper->cycle_time_extension); + extension_time = ktime_add_ns(end_time, oper->cycle_time_extension); /* FIXME: the IEEE 802.1Q-2018 Specification isn't clear about * how precisely the extension should be made. So after @@ -692,10 +908,13 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) { struct taprio_sched *q = container_of(timer, struct taprio_sched, advance_timer); + struct net_device *dev = qdisc_dev(q->root); struct sched_gate_list *oper, *admin; + int num_tc = netdev_get_num_tc(dev); struct sched_entry *entry, *next; struct Qdisc *sch = q->root; - ktime_t close_time; + ktime_t end_time; + int tc; spin_lock(&q->current_entry_lock); entry = rcu_dereference_protected(q->current_entry, @@ -714,41 +933,49 @@ static enum hrtimer_restart advance_sched(struct hrtimer *timer) * entry of all schedules are pre-calculated during the * schedule initialization. */ - if (unlikely(!entry || entry->close_time == oper->base_time)) { + if (unlikely(!entry || entry->end_time == oper->base_time)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - close_time = next->close_time; + end_time = next->end_time; goto first_run; } if (should_restart_cycle(oper, entry)) { next = list_first_entry(&oper->entries, struct sched_entry, list); - oper->cycle_close_time = ktime_add_ns(oper->cycle_close_time, - oper->cycle_time); + oper->cycle_end_time = ktime_add_ns(oper->cycle_end_time, + oper->cycle_time); } else { next = list_next_entry(entry, list); } - close_time = ktime_add_ns(entry->close_time, next->interval); - close_time = min_t(ktime_t, close_time, oper->cycle_close_time); + end_time = ktime_add_ns(entry->end_time, next->interval); + end_time = min_t(ktime_t, end_time, oper->cycle_end_time); + + for (tc = 0; tc < num_tc; tc++) { + if (next->gate_duration[tc] == oper->cycle_time) + next->gate_close_time[tc] = KTIME_MAX; + else + next->gate_close_time[tc] = ktime_add_ns(entry->end_time, + next->gate_duration[tc]); + } - if (should_change_schedules(admin, oper, close_time)) { + if (should_change_schedules(admin, oper, end_time)) { /* Set things so the next time this runs, the new * schedule runs. */ - close_time = sched_base_time(admin); + end_time = sched_base_time(admin); switch_schedules(q, &admin, &oper); } - next->close_time = close_time; - taprio_set_budget(q, next); + next->end_time = end_time; + taprio_set_budgets(q, oper, next); first_run: rcu_assign_pointer(q->current_entry, next); spin_unlock(&q->current_entry_lock); - hrtimer_set_expires(&q->advance_timer, close_time); + hrtimer_set_expires(&q->advance_timer, end_time); rcu_read_lock(); __netif_schedule(sch); @@ -916,6 +1143,8 @@ static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, new->cycle_time = cycle; } + taprio_calculate_gate_durations(q, new); + return 0; } @@ -924,7 +1153,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, struct netlink_ext_ack *extack, u32 taprio_flags) { - int i, j; + bool allow_overlapping_txqs = TXTIME_ASSIST_IS_ENABLED(taprio_flags); if (!qopt && !dev->num_tc) { NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); @@ -937,52 +1166,17 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, if (dev->num_tc) return 0; - /* Verify num_tc is not out of max range */ - if (qopt->num_tc > TC_MAX_QUEUE) { - NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); - return -EINVAL; - } - /* taprio imposes that traffic classes map 1:n to tx queues */ if (qopt->num_tc > dev->num_tx_queues) { NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); return -EINVAL; } - /* Verify priority mapping uses valid tcs */ - for (i = 0; i <= TC_BITMASK; i++) { - if (qopt->prio_tc_map[i] >= qopt->num_tc) { - NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); - return -EINVAL; - } - } - - for (i = 0; i < qopt->num_tc; i++) { - unsigned int last = qopt->offset[i] + qopt->count[i]; - - /* Verify the queue count is in tx range being equal to the - * real_num_tx_queues indicates the last queue is in use. - */ - if (qopt->offset[i] >= dev->num_tx_queues || - !qopt->count[i] || - last > dev->real_num_tx_queues) { - NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); - return -EINVAL; - } - - if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) - continue; - - /* Verify that the offset and counts do not overlap */ - for (j = i + 1; j < qopt->num_tc; j++) { - if (last > qopt->offset[j]) { - NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); - return -EINVAL; - } - } - } - - return 0; + /* For some reason, in txtime-assist mode, we allow TXQ ranges for + * different TCs to overlap, and just validate the TXQ ranges. + */ + return mqprio_validate_qopt(dev, qopt, true, allow_overlapping_txqs, + extack); } static int taprio_get_start_time(struct Qdisc *sch, @@ -1019,11 +1213,14 @@ static int taprio_get_start_time(struct Qdisc *sch, return 0; } -static void setup_first_close_time(struct taprio_sched *q, - struct sched_gate_list *sched, ktime_t base) +static void setup_first_end_time(struct taprio_sched *q, + struct sched_gate_list *sched, ktime_t base) { + struct net_device *dev = qdisc_dev(q->root); + int num_tc = netdev_get_num_tc(dev); struct sched_entry *first; ktime_t cycle; + int tc; first = list_first_entry(&sched->entries, struct sched_entry, list); @@ -1031,10 +1228,18 @@ static void setup_first_close_time(struct taprio_sched *q, cycle = sched->cycle_time; /* FIXME: find a better place to do this */ - sched->cycle_close_time = ktime_add_ns(base, cycle); + sched->cycle_end_time = ktime_add_ns(base, cycle); + + first->end_time = ktime_add_ns(base, first->interval); + taprio_set_budgets(q, sched, first); + + for (tc = 0; tc < num_tc; tc++) { + if (first->gate_duration[tc] == sched->cycle_time) + first->gate_close_time[tc] = KTIME_MAX; + else + first->gate_close_time[tc] = ktime_add_ns(base, first->gate_duration[tc]); + } - first->close_time = ktime_add_ns(base, first->interval); - taprio_set_budget(q, first); rcu_assign_pointer(q->current_entry, NULL); } @@ -1088,6 +1293,8 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct sched_gate_list *oper, *admin; + struct qdisc_size_table *stab; struct taprio_sched *q; ASSERT_RTNL(); @@ -1100,6 +1307,17 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, continue; taprio_set_picos_per_byte(dev, q); + + stab = rtnl_dereference(q->root->stab); + + oper = rtnl_dereference(q->oper_sched); + if (oper) + taprio_update_queue_max_sdu(q, oper, stab); + + admin = rtnl_dereference(q->admin_sched); + if (admin) + taprio_update_queue_max_sdu(q, admin, stab); + break; } @@ -1203,7 +1421,8 @@ static u32 tc_map_to_queue_mask(struct net_device *dev, u32 tc_mask) static void taprio_sched_to_offload(struct net_device *dev, struct sched_gate_list *sched, - struct tc_taprio_qopt_offload *offload) + struct tc_taprio_qopt_offload *offload, + const struct tc_taprio_caps *caps) { struct sched_entry *entry; int i = 0; @@ -1217,7 +1436,11 @@ static void taprio_sched_to_offload(struct net_device *dev, e->command = entry->command; e->interval = entry->interval; - e->gate_mask = tc_map_to_queue_mask(dev, entry->gate_mask); + if (caps->gate_mask_per_txq) + e->gate_mask = tc_map_to_queue_mask(dev, + entry->gate_mask); + else + e->gate_mask = entry->gate_mask; i++; } @@ -1225,6 +1448,34 @@ static void taprio_sched_to_offload(struct net_device *dev, offload->num_entries = i; } +static void taprio_detect_broken_mqprio(struct taprio_sched *q) +{ + struct net_device *dev = qdisc_dev(q->root); + struct tc_taprio_caps caps; + + qdisc_offload_query_caps(dev, TC_SETUP_QDISC_TAPRIO, + &caps, sizeof(caps)); + + q->broken_mqprio = caps.broken_mqprio; + if (q->broken_mqprio) + static_branch_inc(&taprio_have_broken_mqprio); + else + static_branch_inc(&taprio_have_working_mqprio); + + q->detected_mqprio = true; +} + +static void taprio_cleanup_broken_mqprio(struct taprio_sched *q) +{ + if (!q->detected_mqprio) + return; + + if (q->broken_mqprio) + static_branch_dec(&taprio_have_broken_mqprio); + else + static_branch_dec(&taprio_have_working_mqprio); +} + static int taprio_enable_offload(struct net_device *dev, struct taprio_sched *q, struct sched_gate_list *sched, @@ -1261,7 +1512,8 @@ static int taprio_enable_offload(struct net_device *dev, return -ENOMEM; } offload->enable = 1; - taprio_sched_to_offload(dev, sched, offload); + mqprio_qopt_reconstruct(dev, &offload->mqprio.qopt); + taprio_sched_to_offload(dev, sched, offload, &caps); for (tc = 0; tc < TC_MAX_QUEUE; tc++) offload->max_sdu[tc] = q->max_sdu[tc]; @@ -1452,7 +1704,6 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, struct netlink_ext_ack *extack) { struct taprio_sched *q = qdisc_priv(sch); - struct net_device *dev = qdisc_dev(sch); u32 max_sdu[TC_QOPT_MAX_QUEUE]; unsigned long seen_tcs = 0; struct nlattr *n; @@ -1466,18 +1717,14 @@ static int taprio_parse_tc_entries(struct Qdisc *sch, if (nla_type(n) != TCA_TAPRIO_ATTR_TC_ENTRY) continue; - err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, extack); + err = taprio_parse_tc_entry(sch, n, max_sdu, &seen_tcs, + extack); if (err) goto out; } - for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) { + for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) q->max_sdu[tc] = max_sdu[tc]; - if (max_sdu[tc]) - q->max_frm_len[tc] = max_sdu[tc] + dev->hard_header_len; - else - q->max_frm_len[tc] = U32_MAX; /* never oversized */ - } out: return err; @@ -1533,6 +1780,7 @@ static int taprio_new_flags(const struct nlattr *attr, u32 old, static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { + struct qdisc_size_table *stab = rtnl_dereference(sch->stab); struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; struct sched_gate_list *oper, *admin, *new_admin; struct taprio_sched *q = qdisc_priv(sch); @@ -1600,15 +1848,18 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; taprio_set_picos_per_byte(dev, q); + taprio_update_queue_max_sdu(q, new_admin, stab); if (mqprio) { err = netdev_set_num_tc(dev, mqprio->num_tc); if (err) goto free_sched; - for (i = 0; i < mqprio->num_tc; i++) + for (i = 0; i < mqprio->num_tc; i++) { netdev_set_tc_queue(dev, i, mqprio->count[i], mqprio->offset[i]); + q->cur_txq[i] = mqprio->offset[i]; + } /* Always use supplied priority mappings */ for (i = 0; i <= TC_BITMASK; i++) @@ -1663,7 +1914,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); } else { - setup_first_close_time(q, new_admin, start); + setup_first_end_time(q, new_admin, start); /* Protects against advance_sched() */ spin_lock_irqsave(&q->current_entry_lock, flags); @@ -1683,6 +1934,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, new_admin = NULL; err = 0; + if (!stab) + NL_SET_ERR_MSG_MOD(extack, + "Size table not specified, frame length estimations may be inaccurate"); + unlock: spin_unlock_bh(qdisc_lock(sch)); @@ -1743,6 +1998,8 @@ static void taprio_destroy(struct Qdisc *sch) if (admin) call_rcu(&admin->rcu, taprio_free_sched_cb); + + taprio_cleanup_broken_mqprio(q); } static int taprio_init(struct Qdisc *sch, struct nlattr *opt, @@ -1807,6 +2064,8 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt, q->qdiscs[i] = qdisc; } + taprio_detect_broken_mqprio(q); + return taprio_change(sch, opt, extack); } @@ -1947,7 +2206,8 @@ error_nest: return -1; } -static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) +static int taprio_dump_tc_entries(struct sk_buff *skb, + struct sched_gate_list *sched) { struct nlattr *n; int tc; @@ -1961,7 +2221,7 @@ static int taprio_dump_tc_entries(struct taprio_sched *q, struct sk_buff *skb) goto nla_put_failure; if (nla_put_u32(skb, TCA_TAPRIO_TC_ENTRY_MAX_SDU, - q->max_sdu[tc])) + sched->max_sdu[tc])) goto nla_put_failure; nla_nest_end(skb, n); @@ -1981,18 +2241,11 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) struct sched_gate_list *oper, *admin; struct tc_mqprio_qopt opt = { 0 }; struct nlattr *nest, *sched_nest; - unsigned int i; oper = rtnl_dereference(q->oper_sched); admin = rtnl_dereference(q->admin_sched); - opt.num_tc = netdev_get_num_tc(dev); - memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); - - for (i = 0; i < netdev_get_num_tc(dev); i++) { - opt.count[i] = dev->tc_to_txq[i].count; - opt.offset[i] = dev->tc_to_txq[i].offset; - } + mqprio_qopt_reconstruct(dev, &opt); nest = nla_nest_start_noflag(skb, TCA_OPTIONS); if (!nest) @@ -2012,7 +2265,7 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay)) goto options_error; - if (taprio_dump_tc_entries(q, skb)) + if (oper && taprio_dump_tc_entries(skb, oper)) goto options_error; if (oper && dump_schedule(skb, oper)) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 1c0fe9ba5358..b163266e581a 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -502,7 +502,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, return -EINVAL; /* protect against parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -510,7 +510,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link, if (rc) break; } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); return rc; } @@ -519,15 +519,30 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, struct smc_buf_desc *rmb_desc) { struct smc_link_group *lgr = link->lgr; + bool do_slow = false; int i, rc = 0; rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (rc) return rc; + + down_read(&lgr->llc_conf_mutex); + for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { + if (!smc_link_active(&lgr->lnk[i])) + continue; + if (!rmb_desc->is_reg_mr[link->link_idx]) { + up_read(&lgr->llc_conf_mutex); + goto slow_path; + } + } + /* mr register already */ + goto fast_path; +slow_path: + do_slow = true; /* protect against parallel smc_llc_cli_rkey_exchange() and * parallel smcr_link_reg_buf() */ - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (!smc_link_active(&lgr->lnk[i])) continue; @@ -535,7 +550,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, if (rc) goto out; } - +fast_path: /* exchange confirm_rkey msg with peer */ rc = smc_llc_do_confirm_rkey(link, rmb_desc); if (rc) { @@ -544,7 +559,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link, } rmb_desc->is_conf_rkey = true; out: - mutex_unlock(&lgr->llc_conf_mutex); + do_slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 7642b16c41d1..b330a1fa453e 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -854,8 +854,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->freeing = 0; lgr->vlan_id = ini->vlan_id; refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */ - mutex_init(&lgr->sndbufs_lock); - mutex_init(&lgr->rmbs_lock); + init_rwsem(&lgr->sndbufs_lock); + init_rwsem(&lgr->rmbs_lock); rwlock_init(&lgr->conns_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { INIT_LIST_HEAD(&lgr->sndbufs[i]); @@ -1098,7 +1098,7 @@ err_out: static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, struct smc_link_group *lgr) { - struct mutex *lock; /* lock buffer list */ + struct rw_semaphore *lock; /* lock buffer list */ int rc; if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) { @@ -1106,10 +1106,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY); if (!rc) { /* protect against smc_llc_cli_rkey_exchange() */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); smc_llc_do_delete_rkey(lgr, buf_desc); buf_desc->is_conf_rkey = false; - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl); } } @@ -1118,9 +1118,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb, /* buf registration failed, reuse not possible */ lock = is_rmb ? &lgr->rmbs_lock : &lgr->sndbufs_lock; - mutex_lock(lock); + down_write(lock); list_del(&buf_desc->list); - mutex_unlock(lock); + up_write(lock); smc_buf_free(lgr, is_rmb, buf_desc); } else { @@ -1224,15 +1224,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk) int i; for (i = 0; i < SMC_RMBE_SIZES; i++) { - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) smcr_buf_unmap_link(buf_desc, true, lnk); - mutex_unlock(&lgr->rmbs_lock); - mutex_lock(&lgr->sndbufs_lock); + up_write(&lgr->rmbs_lock); + + down_write(&lgr->sndbufs_lock); list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) smcr_buf_unmap_link(buf_desc, false, lnk); - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); } } @@ -1377,12 +1378,12 @@ static void smc_lgr_free(struct smc_link_group *lgr) int i; if (!lgr->is_smcd) { - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { if (lgr->lnk[i].state != SMC_LNK_UNUSED) smcr_link_clear(&lgr->lnk[i], false); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); smc_llc_lgr_clear(lgr); } @@ -1696,12 +1697,12 @@ static void smcr_link_down(struct smc_link *lnk) } else { if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) { /* another llc task is ongoing */ - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); wait_event_timeout(lgr->llc_flow_waiter, (list_empty(&lgr->list) || lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE), SMC_LLC_WAIT_TIME); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); } if (!list_empty(&lgr->list)) { smc_llc_send_delete_link(to_lnk, del_link_id, @@ -1761,9 +1762,9 @@ static void smc_link_down_work(struct work_struct *work) if (list_empty(&lgr->list)) return; wake_up_all(&lgr->llc_msg_waiter); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); smcr_link_down(link); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev, @@ -1990,19 +1991,19 @@ int smc_uncompress_bufsize(u8 compressed) * buffer size; if not available, return NULL */ static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize, - struct mutex *lock, + struct rw_semaphore *lock, struct list_head *buf_list) { struct smc_buf_desc *buf_slot; - mutex_lock(lock); + down_read(lock); list_for_each_entry(buf_slot, buf_list, list) { if (cmpxchg(&buf_slot->used, 0, 1) == 0) { - mutex_unlock(lock); + up_read(lock); return buf_slot; } } - mutex_unlock(lock); + up_read(lock); return NULL; } @@ -2111,13 +2112,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc) return 0; } -static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, +static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock, struct list_head *lst, bool is_rmb) { struct smc_buf_desc *buf_desc, *bf; int rc = 0; - mutex_lock(lock); + down_write(lock); list_for_each_entry_safe(buf_desc, bf, lst, list) { if (!buf_desc->used) continue; @@ -2126,7 +2127,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock, goto out; } out: - mutex_unlock(lock); + up_write(lock); return rc; } @@ -2159,37 +2160,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk) int i, rc = 0; /* reg all RMBs for a new link */ - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) { if (!buf_desc->used) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } } } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); if (lgr->buf_type == SMCR_PHYS_CONT_BUFS) return rc; /* reg all vzalloced sndbufs for a new link */ - mutex_lock(&lgr->sndbufs_lock); + down_write(&lgr->sndbufs_lock); for (i = 0; i < SMC_RMBE_SIZES; i++) { list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) { if (!buf_desc->used || !buf_desc->is_vm) continue; rc = smcr_link_reg_buf(lnk, buf_desc); if (rc) { - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } } } - mutex_unlock(&lgr->sndbufs_lock); + up_write(&lgr->sndbufs_lock); return rc; } @@ -2247,7 +2248,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, int i, rc = 0, cnt = 0; /* protect against parallel link reconfiguration */ - mutex_lock(&lgr->llc_conf_mutex); + down_read(&lgr->llc_conf_mutex); for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) { struct smc_link *lnk = &lgr->lnk[i]; @@ -2260,7 +2261,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr, cnt++; } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_read(&lgr->llc_conf_mutex); if (!rc && !cnt) rc = -EINVAL; return rc; @@ -2309,8 +2310,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) struct smc_link_group *lgr = conn->lgr; struct list_head *buf_list; int bufsize, bufsize_short; + struct rw_semaphore *lock; /* lock buffer list */ bool is_dgraded = false; - struct mutex *lock; /* lock buffer list */ int sk_buf_size; if (is_rmb) @@ -2358,9 +2359,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb) SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb); SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize); buf_desc->used = 1; - mutex_lock(lock); + down_write(lock); list_add(&buf_desc->list, buf_list); - mutex_unlock(lock); + up_write(lock); break; /* found */ } @@ -2434,9 +2435,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd) /* create rmb */ rc = __smc_buf_create(smc, is_smcd, true); if (rc) { - mutex_lock(&smc->conn.lgr->sndbufs_lock); + down_write(&smc->conn.lgr->sndbufs_lock); list_del(&smc->conn.sndbuf_desc->list); - mutex_unlock(&smc->conn.lgr->sndbufs_lock); + up_write(&smc->conn.lgr->sndbufs_lock); smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc); smc->conn.sndbuf_desc = NULL; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 285f9bd8e232..08b457c2d294 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -252,9 +252,9 @@ struct smc_link_group { unsigned short vlan_id; /* vlan id of link group */ struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */ - struct mutex sndbufs_lock; /* protects tx buffers */ + struct rw_semaphore sndbufs_lock; /* protects tx buffers */ struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */ - struct mutex rmbs_lock; /* protects rx buffers */ + struct rw_semaphore rmbs_lock; /* protects rx buffers */ u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */ struct delayed_work free_work; /* delayed freeing of an lgr */ @@ -298,7 +298,7 @@ struct smc_link_group { /* queue for llc events */ spinlock_t llc_event_q_lock; /* protects llc_event_q */ - struct mutex llc_conf_mutex; + struct rw_semaphore llc_conf_mutex; /* protects lgr reconfig. */ struct work_struct llc_add_link_work; struct work_struct llc_del_link_work; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index 524649d0ab65..a0840b8c935b 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -608,7 +608,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, prim_lnk_idx = link->link_idx; lnk_idx = link_new->link_idx; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); ext->num_rkeys = lgr->conns_num; if (!ext->num_rkeys) goto out; @@ -628,7 +628,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext, } len += i * sizeof(ext->rt[0]); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return len; } @@ -889,7 +889,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -916,7 +916,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link, break; } while (num_rkeys_send || num_rkeys_recv); - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -999,14 +999,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link, ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 + SMC_WR_TX_SIZE); max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2); - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); for (i = 0; i < max; i++) { smc_rtoken_set(lgr, link->link_idx, link_new->link_idx, ext->rt[i].rmb_key, ext->rt[i].rmb_vaddr_new, ext->rt[i].rmb_key_new); } - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); } static void smc_llc_save_add_link_info(struct smc_link *link, @@ -1202,12 +1202,12 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); if (smc_llc_is_local_add_link(&qentry->msg)) smc_llc_cli_add_link_invite(qentry->link, qentry); else smc_llc_cli_add_link(qentry->link, qentry); - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); } static int smc_llc_active_link_count(struct smc_link_group *lgr) @@ -1313,7 +1313,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, int rc = 0; int i; - mutex_lock(&lgr->rmbs_lock); + down_write(&lgr->rmbs_lock); num_rkeys_send = lgr->conns_num; buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst); do { @@ -1338,7 +1338,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link, smc_llc_flow_qentry_del(&lgr->llc_flow_lcl); } while (num_rkeys_send || num_rkeys_recv); out: - mutex_unlock(&lgr->rmbs_lock); + up_write(&lgr->rmbs_lock); return rc; } @@ -1509,13 +1509,13 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr) qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); rc = smc_llc_srv_add_link(link, qentry); if (!rc && lgr->type == SMC_LGR_SYMMETRIC) { /* delete any asymmetric link */ smc_llc_delete_asym_link(lgr); } - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -1582,7 +1582,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); goto out; } - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); /* delete single link */ for (lnk_idx = 0; lnk_idx < SMC_LINKS_PER_LGR_MAX; lnk_idx++) { if (lgr->lnk[lnk_idx].link_id != del_llc->link_num) @@ -1616,7 +1616,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr) smc_lgr_terminate_sched(lgr); } out_unlock: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); out: kfree(qentry); } @@ -1652,7 +1652,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) int active_links; int i; - mutex_lock(&lgr->llc_conf_mutex); + down_write(&lgr->llc_conf_mutex); qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl); lnk = qentry->link; del_llc = &qentry->msg.delete_link; @@ -1708,7 +1708,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr) smc_llc_add_link_local(lnk); } out: - mutex_unlock(&lgr->llc_conf_mutex); + up_write(&lgr->llc_conf_mutex); kfree(qentry); } @@ -2126,7 +2126,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) spin_lock_init(&lgr->llc_flow_lock); init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); - mutex_init(&lgr->llc_conf_mutex); + init_rwsem(&lgr->llc_conf_mutex); lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time); } diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index dfea27a906f2..9b47c8409231 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -39,6 +39,7 @@ #include "node.h" #include "net.h" #include <net/genetlink.h> +#include <linux/string_helpers.h> #include <linux/tipc_config.h> /* The legacy API had an artificial message length limit called @@ -173,11 +174,6 @@ static struct sk_buff *tipc_get_err_tlv(char *str) return buf; } -static inline bool string_is_valid(char *s, int len) -{ - return memchr(s, '\0', len) ? true : false; -} - static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg, struct sk_buff *arg) @@ -445,7 +441,7 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(b->name, len)) + if (!string_is_terminated(b->name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, b->name)) @@ -486,7 +482,7 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_BEARER_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_BEARER_NAME, name)) @@ -584,7 +580,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (strcmp(name, nla_data(link[TIPC_NLA_LINK_NAME])) != 0) @@ -819,7 +815,7 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(lc->name, len)) + if (!string_is_terminated(lc->name, len)) return -EINVAL; media = tipc_media_find(lc->name); @@ -856,7 +852,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, return -EINVAL; len = min_t(int, len, TIPC_MAX_LINK_NAME); - if (!string_is_valid(name, len)) + if (!string_is_terminated(name, len)) return -EINVAL; if (nla_put_string(skb, TIPC_NLA_LINK_NAME, name)) diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index ed6c71826d31..b2df1e0f8153 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -140,6 +140,10 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } +#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \ + NETDEV_XDP_ACT_REDIRECT | \ + NETDEV_XDP_ACT_XSK_ZEROCOPY) + int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { @@ -178,8 +182,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, /* For copy-mode, we are done. */ return 0; - if (!netdev->netdev_ops->ndo_bpf || - !netdev->netdev_ops->ndo_xsk_wakeup) { + if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) { err = -EOPNOTSUPP; goto err_unreg_pool; } diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index a0f62fa02e06..8cbf45a8bcdc 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -5,6 +5,7 @@ * Based on code and translator idea by: Florian Westphal <fw@strlen.de> */ #include <linux/compat.h> +#include <linux/nospec.h> #include <linux/xfrm.h> #include <net/xfrm.h> @@ -302,7 +303,7 @@ static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src) nla_for_each_attr(nla, attrs, len, remaining) { int err; - switch (type) { + switch (nlh_src->nlmsg_type) { case XFRM_MSG_NEWSPDINFO: err = xfrm_nla_cpy(dst, nla, nla_len(nla)); break; @@ -437,6 +438,7 @@ static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla, NL_SET_ERR_MSG(extack, "Bad attribute"); return -EOPNOTSUPP; } + type = array_index_nospec(type, XFRMA_MAX + 1); if (nla_len(nla) < compat_policy[type].len) { NL_SET_ERR_MSG(extack, "Attribute bad length"); return -EOPNOTSUPP; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index c06e54a10540..436d29640ac2 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -279,8 +279,7 @@ static int xfrm6_remove_tunnel_encap(struct xfrm_state *x, struct sk_buff *skb) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6_hdr(skb)), - ipipv6_hdr(skb)); + ipv6_copy_dscp(XFRM_MODE_SKB_CB(skb)->tos, ipipv6_hdr(skb)); if (!(x->props.flags & XFRM_STATE_NOECN)) ipip6_ecn_decapsulate(skb); diff --git a/net/xfrm/xfrm_interface_bpf.c b/net/xfrm/xfrm_interface_bpf.c index 1ef2162cebcf..d74f3fd20f2b 100644 --- a/net/xfrm/xfrm_interface_bpf.c +++ b/net/xfrm/xfrm_interface_bpf.c @@ -39,8 +39,7 @@ __diag_ignore_all("-Wmissing-prototypes", * @to - Pointer to memory to which the metadata will be copied * Cannot be NULL */ -__used noinline -int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) +__bpf_kfunc int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) { struct sk_buff *skb = (struct sk_buff *)skb_ctx; struct xfrm_md_info *info; @@ -62,9 +61,7 @@ int bpf_skb_get_xfrm_info(struct __sk_buff *skb_ctx, struct bpf_xfrm_info *to) * @from - Pointer to memory from which the metadata will be copied * Cannot be NULL */ -__used noinline -int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, - const struct bpf_xfrm_info *from) +__bpf_kfunc int bpf_skb_set_xfrm_info(struct __sk_buff *skb_ctx, const struct bpf_xfrm_info *from) { struct sk_buff *skb = (struct sk_buff *)skb_ctx; struct metadata_dst *md_dst; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 1f99dc469027..35279c220bd7 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -310,6 +310,52 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) skb->mark = 0; } +static int xfrmi_input(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type, unsigned short family) +{ + struct sec_path *sp; + + sp = skb_sec_path(skb); + if (sp && (sp->len || sp->olen) && + !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) + goto discard; + + XFRM_SPI_SKB_CB(skb)->family = family; + if (family == AF_INET) { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; + } else { + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr); + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 = NULL; + } + + return xfrm_input(skb, nexthdr, spi, encap_type); +discard: + kfree_skb(skb); + return 0; +} + +static int xfrmi4_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, ip_hdr(skb)->protocol, 0, 0, AF_INET); +} + +static int xfrmi6_rcv(struct sk_buff *skb) +{ + return xfrmi_input(skb, skb_network_header(skb)[IP6CB(skb)->nhoff], + 0, 0, AF_INET6); +} + +static int xfrmi4_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET); +} + +static int xfrmi6_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) +{ + return xfrmi_input(skb, nexthdr, spi, encap_type, AF_INET6); +} + static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; @@ -945,8 +991,8 @@ static struct pernet_operations xfrmi_net_ops = { }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { - .handler = xfrm6_rcv, - .input_handler = xfrm_input, + .handler = xfrmi6_rcv, + .input_handler = xfrmi6_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, @@ -996,8 +1042,8 @@ static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = { #endif static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { - .handler = xfrm4_rcv, - .input_handler = xfrm_input, + .handler = xfrmi4_rcv, + .input_handler = xfrmi4_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e9eb82c5457d..5c61ec04b839 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -336,7 +336,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -354,7 +354,7 @@ static void xfrm_policy_timer(struct timer_list *t) } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + - (xp->curlft.use_time ? : xp->curlft.add_time) - now; + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; @@ -3661,7 +3661,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, return 1; } - pol->curlft.use_time = ktime_get_real_seconds(); + /* This lockless write can happen from different cpus. */ + WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; @@ -3676,7 +3677,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, xfrm_pol_put(pols[0]); return 0; } - pols[1]->curlft.use_time = ktime_get_real_seconds(); + /* This write can happen from different cpus. */ + WRITE_ONCE(pols[1]->curlft.use_time, + ktime_get_real_seconds()); npols++; } } @@ -3742,6 +3745,9 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, goto reject; } + if (if_id) + secpath_reset(skb); + xfrm_pols_put(pols, npols); return 1; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 59fffa02d1cc..2ab3e09e2227 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -577,7 +577,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { - long tmo = x->lft.hard_add_expires_seconds + + time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { @@ -594,8 +594,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) next = tmo; } if (x->lft.hard_use_expires_seconds) { - long tmo = x->lft.hard_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.hard_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) @@ -604,7 +604,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { - long tmo = x->lft.soft_add_expires_seconds + + time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; @@ -616,8 +616,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) } } if (x->lft.soft_use_expires_seconds) { - long tmo = x->lft.soft_use_expires_seconds + - (x->curlft.use_time ? : now) - now; + time64_t tmo = x->lft.soft_use_expires_seconds + + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) @@ -1906,7 +1906,7 @@ out: hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); - if (x1->curlft.use_time) + if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { @@ -1940,8 +1940,8 @@ int xfrm_state_check_expire(struct xfrm_state *x) { xfrm_dev_state_update_curlft(x); - if (!x->curlft.use_time) - x->curlft.use_time = ktime_get_real_seconds(); + if (!READ_ONCE(x->curlft.use_time)) + WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 50231c2eff9c..e7121dd1ee37 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -58,6 +58,13 @@ int trace_enter_open_at(struct syscalls_enter_open_args *ctx) return 0; } +SEC("tracepoint/syscalls/sys_enter_openat2") +int trace_enter_open_at2(struct syscalls_enter_open_args *ctx) +{ + count(&enter_open_map); + return 0; +} + SEC("tracepoint/syscalls/sys_exit_open") int trace_enter_exit(struct syscalls_exit_open_args *ctx) { @@ -71,3 +78,10 @@ int trace_enter_exit_at(struct syscalls_exit_open_args *ctx) count(&exit_open_map); return 0; } + +SEC("tracepoint/syscalls/sys_exit_openat2") +int trace_enter_exit_at2(struct syscalls_exit_open_args *ctx) +{ + count(&exit_open_map); + return 0; +} diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 836391e5d209..4815a8e32227 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -66,9 +66,13 @@ endif # Don't stop modules_install even if we can't sign external modules. # ifeq ($(CONFIG_MODULE_SIG_ALL),y) +ifeq ($(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),) sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY) +else +sig-key := $(CONFIG_MODULE_SIG_KEY) +endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \ + cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) else quiet_cmd_sign := diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index cfc9fdc1e863..e87738dbffc1 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -2233,10 +2233,38 @@ static void profile_close_perf_events(struct profiler_bpf *obj) profile_perf_event_cnt = 0; } +static int profile_open_perf_event(int mid, int cpu, int map_fd) +{ + int pmu_fd; + + pmu_fd = syscall(__NR_perf_event_open, &metrics[mid].attr, + -1 /*pid*/, cpu, -1 /*group_fd*/, 0); + if (pmu_fd < 0) { + if (errno == ENODEV) { + p_info("cpu %d may be offline, skip %s profiling.", + cpu, metrics[mid].name); + profile_perf_event_cnt++; + return 0; + } + return -1; + } + + if (bpf_map_update_elem(map_fd, + &profile_perf_event_cnt, + &pmu_fd, BPF_ANY) || + ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + close(pmu_fd); + return -1; + } + + profile_perf_events[profile_perf_event_cnt++] = pmu_fd; + return 0; +} + static int profile_open_perf_events(struct profiler_bpf *obj) { unsigned int cpu, m; - int map_fd, pmu_fd; + int map_fd; profile_perf_events = calloc( sizeof(int), obj->rodata->num_cpu * obj->rodata->num_metric); @@ -2255,17 +2283,11 @@ static int profile_open_perf_events(struct profiler_bpf *obj) if (!metrics[m].selected) continue; for (cpu = 0; cpu < obj->rodata->num_cpu; cpu++) { - pmu_fd = syscall(__NR_perf_event_open, &metrics[m].attr, - -1/*pid*/, cpu, -1/*group_fd*/, 0); - if (pmu_fd < 0 || - bpf_map_update_elem(map_fd, &profile_perf_event_cnt, - &pmu_fd, BPF_ANY) || - ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + if (profile_open_perf_event(m, cpu, map_fd)) { p_err("failed to create event %s on cpu %d", metrics[m].name, cpu); return -1; } - profile_perf_events[profile_perf_event_cnt++] = pmu_fd; } } return 0; diff --git a/tools/bpf/resolve_btfids/Build b/tools/bpf/resolve_btfids/Build index ae82da03f9bf..077de3829c72 100644 --- a/tools/bpf/resolve_btfids/Build +++ b/tools/bpf/resolve_btfids/Build @@ -1,3 +1,5 @@ +hostprogs := resolve_btfids + resolve_btfids-y += main.o resolve_btfids-y += rbtree.o resolve_btfids-y += zalloc.o @@ -7,4 +9,4 @@ resolve_btfids-y += str_error_r.o $(OUTPUT)%.o: ../../lib/%.c FORCE $(call rule_mkdir) - $(call if_changed_dep,cc_o_c) + $(call if_changed_dep,host_cc_o_c) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index daed388aa5d7..ac548a7baa73 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -17,11 +17,14 @@ else MAKEFLAGS=--no-print-directory endif -# always use the host compiler +# Overrides for the prepare step libraries. HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \ - EXTRA_CFLAGS="$(HOSTCFLAGS) $(KBUILD_HOSTCFLAGS)" + CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)" RM ?= rm +HOSTCC ?= gcc +HOSTLD ?= ld +HOSTAR ?= ar CROSS_COMPILE = OUTPUT ?= $(srctree)/tools/bpf/resolve_btfids/ @@ -64,7 +67,7 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) -CFLAGS += -g \ +HOSTCFLAGS += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ -I$(LIBBPF_INCLUDE) \ @@ -73,11 +76,11 @@ CFLAGS += -g \ LIBS = $(LIBELF_LIBS) -lz -export srctree OUTPUT CFLAGS Q +export srctree OUTPUT HOSTCFLAGS Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) - $(Q)$(MAKE) $(build)=resolve_btfids $(HOST_OVERRIDES) + $(Q)$(MAKE) $(build)=resolve_btfids $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile index 8b3d87b82b7a..47acf6936516 100644 --- a/tools/bpf/runqslower/Makefile +++ b/tools/bpf/runqslower/Makefile @@ -13,6 +13,8 @@ BPF_DESTDIR := $(BPFOBJ_OUTPUT) BPF_INCLUDE := $(BPF_DESTDIR)/include INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi) CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS) +CFLAGS += $(EXTRA_CFLAGS) +LDFLAGS += $(EXTRA_LDFLAGS) # Try to detect best kernel BTF source KERNEL_REL := $(shell uname -r) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7f024ac22edd..17afd2b35ee5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2801,7 +2801,7 @@ union bpf_attr { * * long bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) * Description - * For en eBPF program attached to a perf event, retrieve the + * For an eBPF program attached to a perf event, retrieve the * value of the event counter associated to *ctx* and store it in * the structure pointed by *buf* and of size *buf_size*. Enabled * and running times are also stored in the structure (see @@ -5817,8 +5817,8 @@ enum { BPF_F_ADJ_ROOM_ENCAP_L4_UDP = (1ULL << 4), BPF_F_ADJ_ROOM_NO_CSUM_RESET = (1ULL << 5), BPF_F_ADJ_ROOM_ENCAP_L2_ETH = (1ULL << 6), - BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), - BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), + BPF_F_ADJ_ROOM_DECAP_L3_IPV4 = (1ULL << 7), + BPF_F_ADJ_ROOM_DECAP_L3_IPV6 = (1ULL << 8), }; enum { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h new file mode 100644 index 000000000000..9ee459872600 --- /dev/null +++ b/tools/include/uapi/linux/netdev.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/netdev.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_NETDEV_H +#define _UAPI_LINUX_NETDEV_H + +#define NETDEV_FAMILY_NAME "netdev" +#define NETDEV_FAMILY_VERSION 1 + +/** + * enum netdev_xdp_act + * @NETDEV_XDP_ACT_BASIC: XDP feautues set supported by all drivers + * (XDP_ABORTED, XDP_DROP, XDP_PASS, XDP_TX) + * @NETDEV_XDP_ACT_REDIRECT: The netdev supports XDP_REDIRECT + * @NETDEV_XDP_ACT_NDO_XMIT: This feature informs if netdev implements + * ndo_xdp_xmit callback. + * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP + * in zero copy mode. + * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw + * oflloading. + * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear + * XDP buffer support in the driver napi callback. + * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements + * non-linear XDP buffer support in ndo_xdp_xmit callback. + */ +enum netdev_xdp_act { + NETDEV_XDP_ACT_BASIC = 1, + NETDEV_XDP_ACT_REDIRECT = 2, + NETDEV_XDP_ACT_NDO_XMIT = 4, + NETDEV_XDP_ACT_XSK_ZEROCOPY = 8, + NETDEV_XDP_ACT_HW_OFFLOAD = 16, + NETDEV_XDP_ACT_RX_SG = 32, + NETDEV_XDP_ACT_NDO_XMIT_SG = 64, +}; + +enum { + NETDEV_A_DEV_IFINDEX = 1, + NETDEV_A_DEV_PAD, + NETDEV_A_DEV_XDP_FEATURES, + + __NETDEV_A_DEV_MAX, + NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) +}; + +enum { + NETDEV_CMD_DEV_GET = 1, + NETDEV_CMD_DEV_ADD_NTF, + NETDEV_CMD_DEV_DEL_NTF, + NETDEV_CMD_DEV_CHANGE_NTF, + + __NETDEV_CMD_MAX, + NETDEV_CMD_MAX = (__NETDEV_CMD_MAX - 1) +}; + +#define NETDEV_MCGRP_MGMT "mgmt" + +#endif /* _UAPI_LINUX_NETDEV_H */ diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h index 496e6a8ee0dc..1ac57bb7ac55 100644 --- a/tools/lib/bpf/bpf_core_read.h +++ b/tools/lib/bpf/bpf_core_read.h @@ -364,7 +364,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_INTO() */ #define BPF_PROBE_READ_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) @@ -400,7 +400,7 @@ enum bpf_enum_value_kind { /* Non-CO-RE variant of BPF_CORE_READ_STR_INTO() */ #define BPF_PROBE_READ_STR_INTO(dst, src, a, ...) ({ \ - ___core_read(bpf_probe_read_str, bpf_probe_read, \ + ___core_read(bpf_probe_read_kernel_str, bpf_probe_read_kernel, \ dst, (src), a, ##__VA_ARGS__) \ }) diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index d37c4fe2849d..5ec1871acb2f 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -109,7 +109,7 @@ * This is a variable-specific variant of more global barrier(). */ #ifndef barrier_var -#define barrier_var(var) asm volatile("" : "=r"(var) : "0"(var)) +#define barrier_var(var) asm volatile("" : "+r"(var)) #endif /* diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index eed5cec6f510..35a698eb825d 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -34,7 +34,6 @@ #include <linux/limits.h> #include <linux/perf_event.h> #include <linux/ring_buffer.h> -#include <linux/version.h> #include <sys/epoll.h> #include <sys/ioctl.h> #include <sys/mman.h> @@ -870,42 +869,6 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data, return 0; } -__u32 get_kernel_version(void) -{ - /* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, - * but Ubuntu provides /proc/version_signature file, as described at - * https://ubuntu.com/kernel, with an example contents below, which we - * can use to get a proper LINUX_VERSION_CODE. - * - * Ubuntu 5.4.0-12.15-generic 5.4.8 - * - * In the above, 5.4.8 is what kernel is actually expecting, while - * uname() call will return 5.4.0 in info.release. - */ - const char *ubuntu_kver_file = "/proc/version_signature"; - __u32 major, minor, patch; - struct utsname info; - - if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) == 0) { - FILE *f; - - f = fopen(ubuntu_kver_file, "r"); - if (f) { - if (fscanf(f, "%*s %*s %d.%d.%d\n", &major, &minor, &patch) == 3) { - fclose(f); - return KERNEL_VERSION(major, minor, patch); - } - fclose(f); - } - /* something went wrong, fall back to uname() approach */ - } - - uname(&info); - if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) - return 0; - return KERNEL_VERSION(major, minor, patch); -} - static const struct btf_member * find_member_by_offset(const struct btf_type *t, __u32 bit_offset) { @@ -11710,17 +11673,22 @@ struct perf_buffer *perf_buffer__new(int map_fd, size_t page_cnt, const size_t attr_sz = sizeof(struct perf_event_attr); struct perf_buffer_params p = {}; struct perf_event_attr attr; + __u32 sample_period; if (!OPTS_VALID(opts, perf_buffer_opts)) return libbpf_err_ptr(-EINVAL); + sample_period = OPTS_GET(opts, sample_period, 1); + if (!sample_period) + sample_period = 1; + memset(&attr, 0, attr_sz); attr.size = attr_sz; attr.config = PERF_COUNT_SW_BPF_OUTPUT; attr.type = PERF_TYPE_SOFTWARE; attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; + attr.sample_period = sample_period; + attr.wakeup_events = sample_period; p.attr = &attr; p.sample_cb = sample_cb; diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8777ff21ea1d..2efd80f6f7b9 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -1048,9 +1048,10 @@ struct bpf_xdp_query_opts { __u32 hw_prog_id; /* output */ __u32 skb_prog_id; /* output */ __u8 attach_mode; /* output */ + __u64 feature_flags; /* output */ size_t :0; }; -#define bpf_xdp_query_opts__last_field attach_mode +#define bpf_xdp_query_opts__last_field feature_flags LIBBPF_API int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts); @@ -1246,8 +1247,10 @@ typedef void (*perf_buffer_lost_fn)(void *ctx, int cpu, __u64 cnt); /* common use perf buffer options */ struct perf_buffer_opts { size_t sz; + __u32 sample_period; + size_t :0; }; -#define perf_buffer_opts__last_field sz +#define perf_buffer_opts__last_field sample_period /** * @brief **perf_buffer__new()** creates BPF perfbuf manager for a specified diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index b44fcbb4b42e..4f3bc968ff8e 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -12,11 +12,94 @@ #include <linux/btf.h> #include <linux/filter.h> #include <linux/kernel.h> +#include <linux/version.h> #include "bpf.h" #include "libbpf.h" #include "libbpf_internal.h" +/* On Ubuntu LINUX_VERSION_CODE doesn't correspond to info.release, + * but Ubuntu provides /proc/version_signature file, as described at + * https://ubuntu.com/kernel, with an example contents below, which we + * can use to get a proper LINUX_VERSION_CODE. + * + * Ubuntu 5.4.0-12.15-generic 5.4.8 + * + * In the above, 5.4.8 is what kernel is actually expecting, while + * uname() call will return 5.4.0 in info.release. + */ +static __u32 get_ubuntu_kernel_version(void) +{ + const char *ubuntu_kver_file = "/proc/version_signature"; + __u32 major, minor, patch; + int ret; + FILE *f; + + if (faccessat(AT_FDCWD, ubuntu_kver_file, R_OK, AT_EACCESS) != 0) + return 0; + + f = fopen(ubuntu_kver_file, "r"); + if (!f) + return 0; + + ret = fscanf(f, "%*s %*s %u.%u.%u\n", &major, &minor, &patch); + fclose(f); + if (ret != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +/* On Debian LINUX_VERSION_CODE doesn't correspond to info.release. + * Instead, it is provided in info.version. An example content of + * Debian 10 looks like the below. + * + * utsname::release 4.19.0-22-amd64 + * utsname::version #1 SMP Debian 4.19.260-1 (2022-09-29) + * + * In the above, 4.19.260 is what kernel is actually expecting, while + * uname() call will return 4.19.0 in info.release. + */ +static __u32 get_debian_kernel_version(struct utsname *info) +{ + __u32 major, minor, patch; + char *p; + + p = strstr(info->version, "Debian "); + if (!p) { + /* This is not a Debian kernel. */ + return 0; + } + + if (sscanf(p, "Debian %u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + +__u32 get_kernel_version(void) +{ + __u32 major, minor, patch, version; + struct utsname info; + + /* Check if this is an Ubuntu kernel. */ + version = get_ubuntu_kernel_version(); + if (version != 0) + return version; + + uname(&info); + + /* Check if this is a Debian kernel. */ + version = get_debian_kernel_version(&info); + if (version != 0) + return version; + + if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3) + return 0; + + return KERNEL_VERSION(major, minor, patch); +} + static int probe_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insns_cnt, char *log_buf, size_t log_buf_sz) diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 35104580870c..cb082a04ffa8 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -9,6 +9,7 @@ #include <linux/if_ether.h> #include <linux/pkt_cls.h> #include <linux/rtnetlink.h> +#include <linux/netdev.h> #include <sys/socket.h> #include <errno.h> #include <time.h> @@ -39,9 +40,15 @@ struct xdp_id_md { int ifindex; __u32 flags; struct xdp_link_info info; + __u64 feature_flags; }; -static int libbpf_netlink_open(__u32 *nl_pid) +struct xdp_features_md { + int ifindex; + __u64 flags; +}; + +static int libbpf_netlink_open(__u32 *nl_pid, int proto) { struct sockaddr_nl sa; socklen_t addrlen; @@ -51,7 +58,7 @@ static int libbpf_netlink_open(__u32 *nl_pid) memset(&sa, 0, sizeof(sa)); sa.nl_family = AF_NETLINK; - sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, proto); if (sock < 0) return -errno; @@ -212,14 +219,14 @@ done: } static int libbpf_netlink_send_recv(struct libbpf_nla_req *req, - __dump_nlmsg_t parse_msg, + int proto, __dump_nlmsg_t parse_msg, libbpf_dump_nlmsg_t parse_attr, void *cookie) { __u32 nl_pid = 0; int sock, ret; - sock = libbpf_netlink_open(&nl_pid); + sock = libbpf_netlink_open(&nl_pid, proto); if (sock < 0) return sock; @@ -238,6 +245,43 @@ out: return ret; } +static int parse_genl_family_id(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[CTRL_ATTR_FAMILY_ID + 1]; + __u16 *id = cookie; + + libbpf_nla_parse(tb, CTRL_ATTR_FAMILY_ID, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + if (!tb[CTRL_ATTR_FAMILY_ID]) + return NL_CONT; + + *id = libbpf_nla_getattr_u16(tb[CTRL_ATTR_FAMILY_ID]); + return NL_DONE; +} + +static int libbpf_netlink_resolve_genl_family_id(const char *name, + __u16 len, __u16 *id) +{ + struct libbpf_nla_req req = { + .nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN), + .nh.nlmsg_type = GENL_ID_CTRL, + .nh.nlmsg_flags = NLM_F_REQUEST, + .gnl.cmd = CTRL_CMD_GETFAMILY, + .gnl.version = 2, + }; + int err; + + err = nlattr_add(&req, CTRL_ATTR_FAMILY_NAME, name, len); + if (err < 0) + return err; + + return libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_genl_family_id, NULL, id); +} + static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, __u32 flags) { @@ -271,7 +315,7 @@ static int __bpf_set_link_xdp_fd_replace(int ifindex, int fd, int old_fd, } nlattr_end_nested(&req, nla); - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_xdp_attach(int ifindex, int prog_fd, __u32 flags, const struct bpf_xdp_attach_opts *opts) @@ -357,6 +401,29 @@ static int get_xdp_info(void *cookie, void *msg, struct nlattr **tb) return 0; } +static int parse_xdp_features(struct nlmsghdr *nh, libbpf_dump_nlmsg_t fn, + void *cookie) +{ + struct genlmsghdr *gnl = NLMSG_DATA(nh); + struct nlattr *na = (struct nlattr *)((void *)gnl + GENL_HDRLEN); + struct nlattr *tb[NETDEV_CMD_MAX + 1]; + struct xdp_features_md *md = cookie; + __u32 ifindex; + + libbpf_nla_parse(tb, NETDEV_CMD_MAX, na, + NLMSG_PAYLOAD(nh, sizeof(*gnl)), NULL); + + if (!tb[NETDEV_A_DEV_IFINDEX] || !tb[NETDEV_A_DEV_XDP_FEATURES]) + return NL_CONT; + + ifindex = libbpf_nla_getattr_u32(tb[NETDEV_A_DEV_IFINDEX]); + if (ifindex != md->ifindex) + return NL_CONT; + + md->flags = libbpf_nla_getattr_u64(tb[NETDEV_A_DEV_XDP_FEATURES]); + return NL_DONE; +} + int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) { struct libbpf_nla_req req = { @@ -366,6 +433,10 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) .ifinfo.ifi_family = AF_PACKET, }; struct xdp_id_md xdp_id = {}; + struct xdp_features_md md = { + .ifindex = ifindex, + }; + __u16 id; int err; if (!OPTS_VALID(opts, bpf_xdp_query_opts)) @@ -382,7 +453,7 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) xdp_id.ifindex = ifindex; xdp_id.flags = xdp_flags; - err = libbpf_netlink_send_recv(&req, __dump_link_nlmsg, + err = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, __dump_link_nlmsg, get_xdp_info, &xdp_id); if (err) return libbpf_err(err); @@ -393,6 +464,31 @@ int bpf_xdp_query(int ifindex, int xdp_flags, struct bpf_xdp_query_opts *opts) OPTS_SET(opts, skb_prog_id, xdp_id.info.skb_prog_id); OPTS_SET(opts, attach_mode, xdp_id.info.attach_mode); + if (!OPTS_HAS(opts, feature_flags)) + return 0; + + err = libbpf_netlink_resolve_genl_family_id("netdev", sizeof("netdev"), &id); + if (err < 0) + return libbpf_err(err); + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + req.nh.nlmsg_flags = NLM_F_REQUEST; + req.nh.nlmsg_type = id; + req.gnl.cmd = NETDEV_CMD_DEV_GET; + req.gnl.version = 2; + + err = nlattr_add(&req, NETDEV_A_DEV_IFINDEX, &ifindex, sizeof(ifindex)); + if (err < 0) + return libbpf_err(err); + + err = libbpf_netlink_send_recv(&req, NETLINK_GENERIC, + parse_xdp_features, NULL, &md); + if (err) + return libbpf_err(err); + + opts->feature_flags = md.flags; + return 0; } @@ -493,7 +589,7 @@ static int tc_qdisc_modify(struct bpf_tc_hook *hook, int cmd, int flags) if (ret < 0) return ret; - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } static int tc_qdisc_create_excl(struct bpf_tc_hook *hook) @@ -673,7 +769,8 @@ int bpf_tc_attach(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) @@ -739,7 +836,7 @@ static int __bpf_tc_detach(const struct bpf_tc_hook *hook, return ret; } - return libbpf_netlink_send_recv(&req, NULL, NULL, NULL); + return libbpf_netlink_send_recv(&req, NETLINK_ROUTE, NULL, NULL, NULL); } int bpf_tc_detach(const struct bpf_tc_hook *hook, @@ -804,7 +901,8 @@ int bpf_tc_query(const struct bpf_tc_hook *hook, struct bpf_tc_opts *opts) info.opts = opts; - ret = libbpf_netlink_send_recv(&req, get_tc_info, NULL, &info); + ret = libbpf_netlink_send_recv(&req, NETLINK_ROUTE, get_tc_info, NULL, + &info); if (ret < 0) return libbpf_err(ret); if (!info.processed) diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 3900d052ed19..975e265eab3b 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -178,7 +178,7 @@ int libbpf_nla_dump_errormsg(struct nlmsghdr *nlh) hlen += nlmsg_len(&err->msg); attr = (struct nlattr *) ((void *) err + hlen); - alen = nlh->nlmsg_len - hlen; + alen = (void *)nlh + nlh->nlmsg_len - (void *)attr; if (libbpf_nla_parse(tb, NLMSGERR_ATTR_MAX, attr, alen, extack_policy) != 0) { diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 4d15ae2ff812..d92d1c1de700 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -14,6 +14,7 @@ #include <errno.h> #include <linux/netlink.h> #include <linux/rtnetlink.h> +#include <linux/genetlink.h> /* avoid multiple definition of netlink features */ #define __LINUX_NETLINK_H @@ -58,6 +59,7 @@ struct libbpf_nla_req { union { struct ifinfomsg ifinfo; struct tcmsg tc; + struct genlmsghdr gnl; }; char buf[128]; }; @@ -89,11 +91,21 @@ static inline uint8_t libbpf_nla_getattr_u8(const struct nlattr *nla) return *(uint8_t *)libbpf_nla_data(nla); } +static inline uint16_t libbpf_nla_getattr_u16(const struct nlattr *nla) +{ + return *(uint16_t *)libbpf_nla_data(nla); +} + static inline uint32_t libbpf_nla_getattr_u32(const struct nlattr *nla) { return *(uint32_t *)libbpf_nla_data(nla); } +static inline uint64_t libbpf_nla_getattr_u64(const struct nlattr *nla) +{ + return *(uint64_t *)libbpf_nla_data(nla); +} + static inline const char *libbpf_nla_getattr_str(const struct nlattr *nla) { return (const char *)libbpf_nla_data(nla); diff --git a/tools/lib/bpf/usdt.bpf.h b/tools/lib/bpf/usdt.bpf.h index fdfd235e52c4..0bd4c135acc2 100644 --- a/tools/lib/bpf/usdt.bpf.h +++ b/tools/lib/bpf/usdt.bpf.h @@ -130,7 +130,10 @@ int bpf_usdt_arg(struct pt_regs *ctx, __u64 arg_num, long *res) if (!spec) return -ESRCH; - if (arg_num >= BPF_USDT_MAX_ARG_CNT || arg_num >= spec->arg_cnt) + if (arg_num >= BPF_USDT_MAX_ARG_CNT) + return -ENOENT; + barrier_var(arg_num); + if (arg_num >= spec->arg_cnt) return -ENOENT; arg_spec = &spec->args[arg_num]; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 4aa5bba956ff..116fecf80ca1 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -48,3 +48,4 @@ xskxceiver xdp_redirect_multi xdp_synproxy xdp_hw_metadata +xdp_features diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 50924611e5bb..b89eb87034e4 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -1,93 +1,24 @@ # TEMPORARY # Alphabetical order -atomics # attach(add): actual -524 <= expected 0 (trampoline) bloom_filter_map # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) bpf_cookie # failed to open_and_load program: -524 (trampoline) -bpf_iter_setsockopt # JIT does not support calling kernel function (kfunc) bpf_loop # attaches to __x64_sys_nanosleep -bpf_mod_race # BPF trampoline -bpf_nf # JIT does not support calling kernel function -bpf_tcp_ca # JIT does not support calling kernel function (kfunc) -cb_refs # expected error message unexpected error: -524 (trampoline) -cgroup_hierarchical_stats # JIT does not support calling kernel function (kfunc) -cgrp_kfunc # JIT does not support calling kernel function cgrp_local_storage # prog_attach unexpected error: -524 (trampoline) -core_read_macros # unknown func bpf_probe_read#4 (overlapping) -cpumask # JIT does not support calling kernel function -d_path # failed to auto-attach program 'prog_stat': -524 (trampoline) -decap_sanity # JIT does not support calling kernel function (kfunc) -deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -dummy_st_ops # test_run unexpected error: -524 (errno 524) (trampoline) -fentry_fexit # fentry attach failed: -524 (trampoline) -fentry_test # fentry_first_attach unexpected error: -524 (trampoline) -fexit_bpf2bpf # freplace_attach_trace unexpected error: -524 (trampoline) fexit_sleep # fexit_skel_load fexit skeleton failed (trampoline) -fexit_stress # fexit attach failed prog 0 failed: -524 (trampoline) -fexit_test # fexit_first_attach unexpected error: -524 (trampoline) -get_func_args_test # trampoline -get_func_ip_test # get_func_ip_test__attach unexpected error: -524 (trampoline) get_stack_raw_tp # user_stack corrupted user stack (no backchain userspace) -htab_update # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -jit_probe_mem # jit_probe_mem__open_and_load unexpected error: -524 (kfunc) -kfree_skb # attach fentry unexpected error: -524 (trampoline) -kfunc_call # 'bpf_prog_active': not found in kernel BTF (?) -kfunc_dynptr_param # JIT does not support calling kernel function (kfunc) kprobe_multi_bench_attach # bpf_program__attach_kprobe_multi_opts unexpected error: -95 kprobe_multi_test # relies on fentry ksyms_module # test_ksyms_module__open_and_load unexpected error: -9 (?) ksyms_module_libbpf # JIT does not support calling kernel function (kfunc) ksyms_module_lskel # test_ksyms_module_lskel__open_and_load unexpected error: -9 (?) -libbpf_get_fd_by_id_opts # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -linked_list # JIT does not support calling kernel function (kfunc) -lookup_key # JIT does not support calling kernel function (kfunc) -lru_bug # prog 'printk': failed to auto-attach: -524 -map_kptr # failed to open_and_load program: -524 (trampoline) -modify_return # modify_return attach failed: -524 (trampoline) module_attach # skel_attach skeleton attach failed: -524 (trampoline) -mptcp -nested_trust # JIT does not support calling kernel function -netcnt # failed to load BPF skeleton 'netcnt_prog': -7 (?) -probe_user # check_kprobe_res wrong kprobe res from probe read (?) -rcu_read_lock # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?) -recursion # skel_attach unexpected error: -524 (trampoline) ringbuf # skel_load skeleton load failed (?) -select_reuseport # intermittently fails on new s390x setup -send_signal # intermittently fails to receive signal -setget_sockopt # attach unexpected error: -524 (trampoline) -sk_assign # Can't read on server: Invalid argument (?) -sk_lookup # endianness problem -sk_storage_tracing # test_sk_storage_tracing__attach unexpected error: -524 (trampoline) -skc_to_unix_sock # could not attach BPF object unexpected error: -524 (trampoline) -socket_cookie # prog_attach unexpected error: -524 (trampoline) stacktrace_build_id # compare_map_keys stackid_hmap vs. stackmap err -2 errno 2 (?) -tailcalls # tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls (?) -task_kfunc # JIT does not support calling kernel function -task_local_storage # failed to auto-attach program 'trace_exit_creds': -524 (trampoline) -test_bpffs # bpffs test failed 255 (iterator) -test_bprm_opts # failed to auto-attach program 'secure_exec': -524 (trampoline) -test_ima # failed to auto-attach program 'ima': -524 (trampoline) -test_local_storage # failed to auto-attach program 'unlink_hook': -524 (trampoline) test_lsm # attach unexpected error: -524 (trampoline) -test_overhead # attach_fentry unexpected error: -524 (trampoline) -test_profiler # unknown func bpf_probe_read_str#45 (overlapping) -timer # failed to auto-attach program 'test1': -524 (trampoline) -timer_crash # trampoline -timer_mim # failed to auto-attach program 'test1': -524 (trampoline) -trace_ext # failed to auto-attach program 'test_pkt_md_access_new': -524 (trampoline) trace_printk # trace_printk__load unexpected error: -2 (errno 2) (?) trace_vprintk # trace_vprintk__open_and_load unexpected error: -9 (?) -tracing_struct # failed to auto-attach: -524 (trampoline) -trampoline_count # prog 'prog1': failed to attach: ERROR: strerror_r(-524)=22 (trampoline) -type_cast # JIT does not support calling kernel function unpriv_bpf_disabled # fentry user_ringbuf # failed to find kernel BTF type ID of '__s390x_sys_prctl': -3 (?) verif_stats # trace_vprintk__open_and_load unexpected error: -9 (?) -verify_pkcs7_sig # JIT does not support calling kernel function (kfunc) -vmlinux # failed to auto-attach program 'handle__fentry': -524 (trampoline) -xdp_adjust_tail # case-128 err 0 errno 28 retval 1 size 128 expect-size 3520 (?) xdp_bonding # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_bpf2bpf # failed to auto-attach program 'trace_on_entry': -524 (trampoline) -xdp_do_redirect # prog_run_max_size unexpected error: -22 (errno 22) xdp_metadata # JIT does not support calling kernel function (kfunc) -xdp_synproxy # JIT does not support calling kernel function (kfunc) -xfrm_info # JIT does not support calling kernel function (kfunc) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 53eae7be8dff..c4b5c44cdee2 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -22,10 +22,11 @@ endif BPF_GCC ?= $(shell command -v bpf-gcc;) SAN_CFLAGS ?= +SAN_LDFLAGS ?= $(SAN_CFLAGS) CFLAGS += -g -O0 -rdynamic -Wall -Werror $(GENFLAGS) $(SAN_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ -I$(TOOLSINCDIR) -I$(APIDIR) -I$(OUTPUT) -LDFLAGS += $(SAN_CFLAGS) +LDFLAGS += $(SAN_LDFLAGS) LDLIBS += -lelf -lz -lrt -lpthread # Silence some warnings when compiled with clang @@ -73,7 +74,8 @@ TEST_PROGS := test_kmod.sh \ test_bpftool.sh \ test_bpftool_metadata.sh \ test_doc_build.sh \ - test_xsk.sh + test_xsk.sh \ + test_xdp_features.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ @@ -83,7 +85,8 @@ TEST_PROGS_EXTENDED := with_addr.sh \ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \ - xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata + xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \ + xdp_features TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read $(OUTPUT)/sign-file TEST_GEN_FILES += liburandom_read.so @@ -189,7 +192,7 @@ $(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c $(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so $(call msg,BINARY,,$@) $(Q)$(CLANG) $(filter-out -static,$(CFLAGS) $(LDFLAGS)) $(filter %.c,$^) \ - liburandom_read.so $(filter-out -static,$(LDLIBS)) \ + -lurandom_read $(filter-out -static,$(LDLIBS)) -L$(OUTPUT) \ -fuse-ld=$(LLD) -Wl,-znoseparate-code -Wl,--build-id=sha1 \ -Wl,-rpath=. -o $@ @@ -212,7 +215,9 @@ $(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT) OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF) \ BPFTOOL_OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf \ - BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) && \ + BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' && \ cp $(RUNQSLOWER_OUTPUT)runqslower $@ TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL) @@ -246,7 +251,7 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL) $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ - ARCH= CROSS_COMPILE= CC=$(HOSTCC) LD=$(HOSTLD) \ + ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \ EXTRA_CFLAGS='-g -O0' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ @@ -269,7 +274,8 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ $(APIDIR)/linux/bpf.h \ | $(BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \ - EXTRA_CFLAGS='-g -O0' \ + EXTRA_CFLAGS='-g -O0 $(SAN_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS)' \ DESTDIR=$(SCRATCH_DIR) prefix= all install_headers ifneq ($(BPFOBJ),$(HOST_BPFOBJ)) @@ -278,7 +284,8 @@ $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile) \ | $(HOST_BUILD_DIR)/libbpf $(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) \ EXTRA_CFLAGS='-g -O0' ARCH= CROSS_COMPILE= \ - OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \ + OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ + CC="$(HOSTCC)" LD="$(HOSTLD)" \ DESTDIR=$(HOST_SCRATCH_DIR)/ prefix= all install_headers endif @@ -299,7 +306,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(TOOLSDIR)/lib/ctype.c \ $(TOOLSDIR)/lib/str_error_r.c $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ - CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \ + CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) @@ -385,6 +392,7 @@ test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.bpf.o test_subskeleton test_usdt.skel.h-deps := test_usdt.bpf.o test_usdt_multispec.bpf.o xsk_xdp_progs.skel.h-deps := xsk_xdp_progs.bpf.o xdp_hw_metadata.skel.h-deps := xdp_hw_metadata.bpf.o +xdp_features.skel.h-deps := xdp_features.bpf.o LINKED_BPF_SRCS := $(patsubst %.bpf.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps))) @@ -519,7 +527,8 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ $(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.bpf.o $$@ - $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool $(if $2,$2/)bpftool + $(Q)ln -sf $(if $2,..,.)/tools/build/bpftool/bootstrap/bpftool \ + $(OUTPUT)/$(if $2,$2/)bpftool endef @@ -586,6 +595,10 @@ $(OUTPUT)/xdp_hw_metadata: xdp_hw_metadata.c $(OUTPUT)/network_helpers.o $(OUTPU $(call msg,BINARY,,$@) $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ +$(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp_features.skel.h | $(OUTPUT) + $(call msg,BINARY,,$@) + $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ + # Make sure we are able to include and link libbpf against c++. $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 5085fea3cac5..46500636d8cd 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -59,7 +59,7 @@ bpf_testmod_test_struct_arg_5(void) { return bpf_testmod_test_struct_arg_result; } -noinline void +__bpf_kfunc void bpf_testmod_test_mod_kfunc(int i) { *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; diff --git a/tools/testing/selftests/bpf/netcnt_common.h b/tools/testing/selftests/bpf/netcnt_common.h index 0ab1c88041cd..2d4a58e4e39c 100644 --- a/tools/testing/selftests/bpf/netcnt_common.h +++ b/tools/testing/selftests/bpf/netcnt_common.h @@ -8,11 +8,11 @@ /* sizeof(struct bpf_local_storage_elem): * - * It really is about 128 bytes on x86_64, but allocate more to account for - * possible layout changes, different architectures, etc. + * It is about 128 bytes on x86_64 and 512 bytes on s390x, but allocate more to + * account for possible layout changes, different architectures, etc. * The kernel will wrap up to PAGE_SIZE internally anyway. */ -#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 256 +#define SIZEOF_BPF_LOCAL_STORAGE_ELEM 768 /* Try to estimate kernel's BPF_LOCAL_STORAGE_MAX_VALUE_SIZE: */ #define BPF_LOCAL_STORAGE_MAX_VALUE_SIZE (0xFFFF - \ diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c index 9566d9d2f6ee..56374c8b5436 100644 --- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c +++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c @@ -33,8 +33,8 @@ void test_attach_probe(void) struct test_attach_probe* skel; ssize_t uprobe_offset, ref_ctr_offset; struct bpf_link *uprobe_err_link; + FILE *devnull; bool legacy; - char *mem; /* Check if new-style kprobe/uprobe API is supported. * Kernels that support new FD-based kprobe and uprobe BPF attachment @@ -147,7 +147,7 @@ void test_attach_probe(void) /* test attach by name for a library function, using the library * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo(). */ - uprobe_opts.func_name = "malloc"; + uprobe_opts.func_name = "fopen"; uprobe_opts.retprobe = false; skel->links.handle_uprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2, @@ -157,7 +157,7 @@ void test_attach_probe(void) if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2")) goto cleanup; - uprobe_opts.func_name = "free"; + uprobe_opts.func_name = "fclose"; uprobe_opts.retprobe = true; skel->links.handle_uretprobe_byname2 = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2, @@ -195,8 +195,8 @@ void test_attach_probe(void) usleep(1); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(1); - free(mem); + devnull = fopen("/dev/null", "r"); + fclose(devnull); /* trigger & validate uprobe & uretprobe */ trigger_func(); diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c index 2be2d61954bc..26b2d1bffdfd 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c @@ -472,6 +472,7 @@ static void lsm_subtest(struct test_bpf_cookie *skel) int prog_fd; int lsm_fd = -1; LIBBPF_OPTS(bpf_link_create_opts, link_opts); + int err; skel->bss->lsm_res = 0; @@ -482,8 +483,9 @@ static void lsm_subtest(struct test_bpf_cookie *skel) if (!ASSERT_GE(lsm_fd, 0, "lsm.link_create")) goto cleanup; - stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) goto cleanup; usleep(1); diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 33a2776737e7..2cc759956e3b 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -16,7 +16,7 @@ struct socket_cookie { __u64 cookie_key; - __u32 cookie_value; + __u64 cookie_value; }; static void test_tp_btf(int cgroup_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c index 0b2f73b88c53..2853883b7cbb 100644 --- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c +++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c @@ -80,6 +80,6 @@ fail: bpf_tc_hook_destroy(&qdisc_hook); close_netns(nstoken); } - system("ip netns del " NS_TEST " >& /dev/null"); + system("ip netns del " NS_TEST " &> /dev/null"); decap_sanity__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c index 5a7e6011f6bf..596536def43d 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_stress.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_stress.c @@ -2,14 +2,19 @@ /* Copyright (c) 2019 Facebook */ #include <test_progs.h> -/* that's kernel internal BPF_MAX_TRAMP_PROGS define */ -#define CNT 38 - void serial_test_fexit_stress(void) { - int fexit_fd[CNT] = {}; - int link_fd[CNT] = {}; - int err, i; + int bpf_max_tramp_links, err, i; + int *fd, *fexit_fd, *link_fd; + + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + fd = calloc(bpf_max_tramp_links * 2, sizeof(*fd)); + if (!ASSERT_OK_PTR(fd, "fd")) + return; + fexit_fd = fd; + link_fd = fd + bpf_max_tramp_links; const struct bpf_insn trace_program[] = { BPF_MOV64_IMM(BPF_REG_0, 0), @@ -28,7 +33,7 @@ void serial_test_fexit_stress(void) goto out; trace_opts.attach_btf_id = err; - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { fexit_fd[i] = bpf_prog_load(BPF_PROG_TYPE_TRACING, NULL, "GPL", trace_program, sizeof(trace_program) / sizeof(struct bpf_insn), @@ -44,10 +49,11 @@ void serial_test_fexit_stress(void) ASSERT_OK(err, "bpf_prog_test_run_opts"); out: - for (i = 0; i < CNT; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { if (link_fd[i]) close(link_fd[i]); if (fexit_fd[i]) close(fexit_fd[i]); } + free(fd); } diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c index 73579370bfbd..c07991544a78 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c +++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c @@ -36,7 +36,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size) "cb32_0 %x != %x\n", meta->cb32_0, cb.cb32[0])) return; - if (CHECK(pkt_v6->eth.h_proto != 0xdd86, "check_eth", + if (CHECK(pkt_v6->eth.h_proto != htons(ETH_P_IPV6), "check_eth", "h_proto %x\n", pkt_v6->eth.h_proto)) return; if (CHECK(pkt_v6->iph.nexthdr != 6, "check_ip", diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c index 5af1ee8f0e6e..a543742cd7bd 100644 --- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c +++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c @@ -72,10 +72,12 @@ static struct kfunc_test_params kfunc_tests[] = { /* success cases */ TC_TEST(kfunc_call_test1, 12), TC_TEST(kfunc_call_test2, 3), + TC_TEST(kfunc_call_test4, -1234), TC_TEST(kfunc_call_test_ref_btf_id, 0), TC_TEST(kfunc_call_test_get_mem, 42), SYSCALL_TEST(kfunc_syscall_test, 0), SYSCALL_NULL_CTX_TEST(kfunc_syscall_test_null, 0), + TC_TEST(kfunc_call_test_static_unused_arg, 0), }; struct syscall_test_args { diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c index 3e190ed63976..1374b626a985 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c @@ -29,7 +29,23 @@ static int stop, duration; static bool configure_stack(void) { + char tc_version[128]; char tc_cmd[BUFSIZ]; + char *prog; + FILE *tc; + + /* Check whether tc is built with libbpf. */ + tc = popen("tc -V", "r"); + if (CHECK_FAIL(!tc)) + return false; + if (CHECK_FAIL(!fgets(tc_version, sizeof(tc_version), tc))) + return false; + if (strstr(tc_version, ", libbpf ")) + prog = "test_sk_assign_libbpf.bpf.o"; + else + prog = "test_sk_assign.bpf.o"; + if (CHECK_FAIL(pclose(tc))) + return false; /* Move to a new networking namespace */ if (CHECK_FAIL(unshare(CLONE_NEWNET))) @@ -46,8 +62,8 @@ configure_stack(void) /* Load qdisc, BPF program */ if (CHECK_FAIL(system("tc qdisc add dev lo clsact"))) return false; - sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf", - "direct-action object-file ./test_sk_assign.bpf.o", + sprintf(tc_cmd, "%s %s %s %s %s", "tc filter add dev lo ingress bpf", + "direct-action object-file", prog, "section tc", (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose"); if (CHECK(system(tc_cmd), "BPF load failed;", @@ -129,15 +145,12 @@ get_port(int fd) static ssize_t rcv_msg(int srv_client, int type) { - struct sockaddr_storage ss; char buf[BUFSIZ]; - socklen_t slen; if (type == SOCK_STREAM) return read(srv_client, &buf, sizeof(buf)); else - return recvfrom(srv_client, &buf, sizeof(buf), 0, - (struct sockaddr *)&ss, &slen); + return recvfrom(srv_client, &buf, sizeof(buf), 0, NULL, NULL); } static int diff --git a/tools/testing/selftests/bpf/prog_tests/test_lsm.c b/tools/testing/selftests/bpf/prog_tests/test_lsm.c index 244c01125126..16175d579bc7 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_lsm.c +++ b/tools/testing/selftests/bpf/prog_tests/test_lsm.c @@ -75,7 +75,8 @@ static int test_lsm(struct lsm *skel) skel->bss->monitored_pid = getpid(); err = stack_mprotect(); - if (!ASSERT_EQ(errno, EPERM, "stack_mprotect")) + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) return err; ASSERT_EQ(skel->bss->mprotect_count, 1, "mprotect_count"); diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c index 564b75bc087f..8fd4c0d78089 100644 --- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c +++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c @@ -2,8 +2,6 @@ #define _GNU_SOURCE #include <test_progs.h> -#define MAX_TRAMP_PROGS 38 - struct inst { struct bpf_object *obj; struct bpf_link *link; @@ -37,14 +35,21 @@ void serial_test_trampoline_count(void) { char *file = "test_trampoline_count.bpf.o"; char *const progs[] = { "fentry_test", "fmod_ret_test", "fexit_test" }; - struct inst inst[MAX_TRAMP_PROGS + 1] = {}; + int bpf_max_tramp_links, err, i, prog_fd; struct bpf_program *prog; struct bpf_link *link; - int prog_fd, err, i; + struct inst *inst; LIBBPF_OPTS(bpf_test_run_opts, opts); + bpf_max_tramp_links = get_bpf_max_tramp_links(); + if (!ASSERT_GE(bpf_max_tramp_links, 1, "bpf_max_tramp_links")) + return; + inst = calloc(bpf_max_tramp_links + 1, sizeof(*inst)); + if (!ASSERT_OK_PTR(inst, "inst")) + return; + /* attach 'allowed' trampoline programs */ - for (i = 0; i < MAX_TRAMP_PROGS; i++) { + for (i = 0; i < bpf_max_tramp_links; i++) { prog = load_prog(file, progs[i % ARRAY_SIZE(progs)], &inst[i]); if (!prog) goto cleanup; @@ -91,4 +96,5 @@ cleanup: bpf_link__destroy(inst[i].link); bpf_object__close(inst[i].obj); } + free(inst); } diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c index 82807def0d24..6558c857e620 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c @@ -16,10 +16,10 @@ static noinline int autoattach_trigger_func(int arg1, int arg2, int arg3, void test_uprobe_autoattach(void) { + const char *devnull_str = "/dev/null"; struct test_uprobe_autoattach *skel; int trigger_ret; - size_t malloc_sz = 1; - char *mem; + FILE *devnull; skel = test_uprobe_autoattach__open_and_load(); if (!ASSERT_OK_PTR(skel, "skel_open")) @@ -36,16 +36,18 @@ void test_uprobe_autoattach(void) skel->bss->test_pid = getpid(); /* trigger & validate shared library u[ret]probes attached by name */ - mem = malloc(malloc_sz); + devnull = fopen(devnull_str, "r"); ASSERT_EQ(skel->bss->uprobe_byname_parm1, 1, "check_uprobe_byname_parm1"); ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran"); ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc"); ASSERT_EQ(skel->bss->uretprobe_byname_ret, trigger_ret, "check_uretprobe_byname_ret"); ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran"); - ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1"); + ASSERT_EQ(skel->bss->uprobe_byname2_parm1, (__u64)(long)devnull_str, + "check_uprobe_byname2_parm1"); ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran"); - ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc"); + ASSERT_EQ(skel->bss->uretprobe_byname2_rc, (__u64)(long)devnull, + "check_uretprobe_byname2_rc"); ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran"); ASSERT_EQ(skel->bss->a[0], 1, "arg1"); @@ -67,7 +69,7 @@ void test_uprobe_autoattach(void) ASSERT_EQ(skel->bss->a[7], 8, "arg8"); #endif - free(mem); + fclose(devnull); cleanup: test_uprobe_autoattach__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c index 9ad9da0f215e..56ed1eb9b527 100644 --- a/tools/testing/selftests/bpf/prog_tests/usdt.c +++ b/tools/testing/selftests/bpf/prog_tests/usdt.c @@ -314,6 +314,7 @@ static FILE *urand_spawn(int *pid) if (fscanf(f, "%d", pid) != 1) { pclose(f); + errno = EINVAL; return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c index 579d6ee83ce0..dd7f2bc70048 100644 --- a/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/prog_tests/verify_pkcs7_sig.c @@ -61,6 +61,9 @@ static bool kfunc_not_supported; static int libbpf_print_cb(enum libbpf_print_level level, const char *fmt, va_list args) { + if (level == LIBBPF_WARN) + vprintf(fmt, args); + if (strcmp(fmt, "libbpf: extern (func ksym) '%s': not found in kernel or module BTFs\n")) return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 39973ea1ce43..f09505f8b038 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -76,10 +76,15 @@ static void test_xdp_adjust_tail_grow2(void) { const char *file = "./test_xdp_adjust_tail_grow.bpf.o"; char buf[4096]; /* avoid segfault: large buf to hold grow results */ - int tailroom = 320; /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info))*/; struct bpf_object *obj; int err, cnt, i; int max_grow, prog_fd; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__s390x__) + int tailroom = 512; +#else + int tailroom = 320; +#endif LIBBPF_OPTS(bpf_test_run_opts, tattr, .repeat = 1, diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index a50971c6cf4a..2666c84dbd01 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -4,10 +4,12 @@ #include <net/if.h> #include <linux/if_ether.h> #include <linux/if_packet.h> +#include <linux/if_link.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <linux/udp.h> #include <bpf/bpf_endian.h> +#include <uapi/linux/netdev.h> #include "test_xdp_do_redirect.skel.h" #define SYS(fmt, ...) \ @@ -65,7 +67,11 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd) /* The maximum permissible size is: PAGE_SIZE - sizeof(struct xdp_page_head) - * sizeof(struct skb_shared_info) - XDP_PACKET_HEADROOM = 3368 bytes */ +#if defined(__s390x__) +#define MAX_PKT_SIZE 3176 +#else #define MAX_PKT_SIZE 3368 +#endif static void test_max_pkt_size(int fd) { char data[MAX_PKT_SIZE + 1] = {}; @@ -92,7 +98,7 @@ void test_xdp_do_redirect(void) struct test_xdp_do_redirect *skel = NULL; struct nstoken *nstoken = NULL; struct bpf_link *link; - + LIBBPF_OPTS(bpf_xdp_query_opts, query_opts); struct xdp_md ctx_in = { .data = sizeof(__u32), .data_end = sizeof(data) }; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, @@ -153,6 +159,29 @@ void test_xdp_do_redirect(void) !ASSERT_NEQ(ifindex_dst, 0, "ifindex_dst")) goto out; + /* Check xdp features supported by veth driver */ + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_src query_opts.feature_flags")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags")) + goto out; + memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); skel->rodata->ifindex_out = ifindex_src; /* redirect back to the same iface */ skel->rodata->ifindex_in = ifindex_src; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c index cd3aa340e65e..286c21ecdc65 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c @@ -8,6 +8,7 @@ void serial_test_xdp_info(void) { __u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id; const char *file = "./xdp_dummy.bpf.o"; + LIBBPF_OPTS(bpf_xdp_query_opts, opts); struct bpf_prog_info info = {}; struct bpf_object *obj; int err, prog_fd; @@ -61,6 +62,13 @@ void serial_test_xdp_info(void) if (CHECK(prog_id, "prog_id_drv", "unexpected prog_id=%u\n", prog_id)) goto out; + /* Check xdp features supported by lo device */ + opts.feature_flags = ~0; + err = bpf_xdp_query(IFINDEX_LO, XDP_FLAGS_DRV_MODE, &opts); + if (!ASSERT_OK(err, "bpf_xdp_query")) + goto out; + + ASSERT_EQ(opts.feature_flags, 0, "opts.feature_flags"); out: bpf_xdp_detach(IFINDEX_LO, 0, NULL); out_close: diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index e033d48288c0..aa4beae99f4f 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -121,7 +121,7 @@ static void close_xsk(struct xsk *xsk) xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); - munmap(xsk->umem, UMEM_SIZE); + munmap(xsk->umem_area, UMEM_SIZE); } static void ip_csum(struct iphdr *iph) @@ -205,9 +205,8 @@ static void complete_tx(struct xsk *xsk) if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) { addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx); - printf("%p: refill idx=%u addr=%llx\n", xsk, idx, addr); - *xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr; - xsk_ring_prod__submit(&xsk->fill, 1); + printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr); + xsk_ring_cons__release(&xsk->comp, 1); } } diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index f636e50be259..7daa8f5720b9 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -3,6 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> +extern long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym; extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym; extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b, __u32 c, __u64 d) __ksym; @@ -16,6 +17,24 @@ extern void bpf_kfunc_call_test_mem_len_pass1(void *mem, int len) __ksym; extern void bpf_kfunc_call_test_mem_len_fail2(__u64 *mem, int len) __ksym; extern int *bpf_kfunc_call_test_get_rdwr_mem(struct prog_test_ref_kfunc *p, const int rdwr_buf_size) __ksym; extern int *bpf_kfunc_call_test_get_rdonly_mem(struct prog_test_ref_kfunc *p, const int rdonly_buf_size) __ksym; +extern u32 bpf_kfunc_call_test_static_unused_arg(u32 arg, u32 unused) __ksym; + +SEC("tc") +int kfunc_call_test4(struct __sk_buff *skb) +{ + struct bpf_sock *sk = skb->sk; + long tmp; + + if (!sk) + return -1; + + sk = bpf_sk_fullsock(sk); + if (!sk) + return -1; + + tmp = bpf_kfunc_call_test4(-3, -30, -200, -1000); + return (tmp >> 32) + tmp; +} SEC("tc") int kfunc_call_test2(struct __sk_buff *skb) @@ -163,4 +182,14 @@ int kfunc_call_test_get_mem(struct __sk_buff *skb) return ret; } +SEC("tc") +int kfunc_call_test_static_unused_arg(struct __sk_buff *skb) +{ + + u32 expected = 5, actual; + + actual = bpf_kfunc_call_test_static_unused_arg(expected, 0xdeadbeef); + return actual != expected ? -1 : 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/lsm.c b/tools/testing/selftests/bpf/progs/lsm.c index d8d8af623bc2..dc93887ed34c 100644 --- a/tools/testing/selftests/bpf/progs/lsm.c +++ b/tools/testing/selftests/bpf/progs/lsm.c @@ -6,9 +6,10 @@ #include "bpf_misc.h" #include "vmlinux.h" +#include <bpf/bpf_core_read.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include <errno.h> +#include <errno.h> struct { __uint(type, BPF_MAP_TYPE_ARRAY); @@ -164,8 +165,8 @@ int copy_test = 0; SEC("fentry.s/" SYS_PREFIX "sys_setdomainname") int BPF_PROG(test_sys_setdomainname, struct pt_regs *regs) { - void *ptr = (void *)PT_REGS_PARM1(regs); - int len = PT_REGS_PARM2(regs); + void *ptr = (void *)PT_REGS_PARM1_SYSCALL(regs); + int len = PT_REGS_PARM2_SYSCALL(regs); int buf = 0; long ret; diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 92331053dba3..68a3fd7387a4 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -156,10 +156,10 @@ probe_read_lim(void* dst, void* src, unsigned long len, unsigned long max) { len = len < max ? len : max; if (len > 1) { - if (bpf_probe_read(dst, len, src)) + if (bpf_probe_read_kernel(dst, len, src)) return 0; } else if (len == 1) { - if (bpf_probe_read(dst, 1, src)) + if (bpf_probe_read_kernel(dst, 1, src)) return 0; } return len; @@ -216,7 +216,8 @@ static INLINE void* read_full_cgroup_path(struct kernfs_node* cgroup_node, #endif for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) { filepart_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(cgroup_node, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(cgroup_node, name)); if (!cgroup_node) return payload; if (cgroup_node == cgroup_root_node) @@ -303,7 +304,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, cgroup_data->cgroup_full_length = 0; size_t cgroup_root_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(root_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(root_kernfs, name)); barrier_var(cgroup_root_length); if (cgroup_root_length <= MAX_PATH) { barrier_var(cgroup_root_length); @@ -312,7 +314,8 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, } size_t cgroup_proc_length = - bpf_probe_read_str(payload, MAX_PATH, BPF_CORE_READ(proc_kernfs, name)); + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= MAX_PATH) { barrier_var(cgroup_proc_length); @@ -395,7 +398,8 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) arr_struct = bpf_map_lookup_elem(&data_heap, &zero); if (arr_struct == NULL) return 0; - bpf_probe_read(&arr_struct->array[0], sizeof(arr_struct->array[0]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[0], + sizeof(arr_struct->array[0]), kill_data); } else { int index = get_var_spid_index(arr_struct, spid); @@ -409,8 +413,9 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) #endif for (int i = 0; i < ARRAY_SIZE(arr_struct->array); i++) if (arr_struct->array[i].meta.pid == 0) { - bpf_probe_read(&arr_struct->array[i], - sizeof(arr_struct->array[i]), kill_data); + bpf_probe_read_kernel(&arr_struct->array[i], + sizeof(arr_struct->array[i]), + kill_data); bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -427,17 +432,17 @@ static INLINE int trace_var_sys_kill(void* ctx, int tpid, int sig) if (delta_sec < STALE_INFO) { kill_data->kill_count++; kill_data->last_kill_time = bpf_ktime_get_ns(); - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } else { struct var_kill_data_t* kill_data = get_var_kill_data(ctx, spid, tpid, sig); if (kill_data == NULL) return 0; - bpf_probe_read(&arr_struct->array[index], - sizeof(arr_struct->array[index]), - kill_data); + bpf_probe_read_kernel(&arr_struct->array[index], + sizeof(arr_struct->array[index]), + kill_data); } } bpf_map_update_elem(&var_tpid_to_data, &tpid, arr_struct, 0); @@ -487,8 +492,9 @@ read_absolute_file_path_from_dentry(struct dentry* filp_dentry, void* payload) #pragma unroll #endif for (int i = 0; i < MAX_PATH_DEPTH; i++) { - filepart_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp_dentry, d_name.name)); + filepart_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp_dentry, d_name.name)); barrier_var(filepart_length); if (filepart_length > MAX_PATH) break; @@ -572,7 +578,8 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, sysctl_data->sysctl_val_length = 0; sysctl_data->sysctl_path_length = 0; - size_t sysctl_val_length = bpf_probe_read_str(payload, CTL_MAXNAME, buf); + size_t sysctl_val_length = bpf_probe_read_kernel_str(payload, + CTL_MAXNAME, buf); barrier_var(sysctl_val_length); if (sysctl_val_length <= CTL_MAXNAME) { barrier_var(sysctl_val_length); @@ -580,8 +587,10 @@ ssize_t BPF_KPROBE(kprobe__proc_sys_write, payload += sysctl_val_length; } - size_t sysctl_path_length = bpf_probe_read_str(payload, MAX_PATH, - BPF_CORE_READ(filp, f_path.dentry, d_name.name)); + size_t sysctl_path_length = + bpf_probe_read_kernel_str(payload, MAX_PATH, + BPF_CORE_READ(filp, f_path.dentry, + d_name.name)); barrier_var(sysctl_path_length); if (sysctl_path_length <= MAX_PATH) { barrier_var(sysctl_path_length); @@ -638,7 +647,8 @@ int raw_tracepoint__sched_process_exit(void* ctx) struct var_kill_data_t* past_kill_data = &arr_struct->array[i]; if (past_kill_data != NULL && past_kill_data->kill_target_pid == tpid) { - bpf_probe_read(kill_data, sizeof(*past_kill_data), past_kill_data); + bpf_probe_read_kernel(kill_data, sizeof(*past_kill_data), + past_kill_data); void* payload = kill_data->payload; size_t offset = kill_data->payload_length; if (offset >= MAX_METADATA_PAYLOAD_LEN + MAX_CGROUP_PAYLOAD_LEN) @@ -656,8 +666,10 @@ int raw_tracepoint__sched_process_exit(void* ctx) payload += comm_length; } - size_t cgroup_proc_length = bpf_probe_read_str(payload, KILL_TARGET_LEN, - BPF_CORE_READ(proc_kernfs, name)); + size_t cgroup_proc_length = + bpf_probe_read_kernel_str(payload, + KILL_TARGET_LEN, + BPF_CORE_READ(proc_kernfs, name)); barrier_var(cgroup_proc_length); if (cgroup_proc_length <= KILL_TARGET_LEN) { barrier_var(cgroup_proc_length); @@ -718,7 +730,8 @@ int raw_tracepoint__sched_process_exec(struct bpf_raw_tracepoint_args* ctx) proc_exec_data->parent_start_time = BPF_CORE_READ(parent_task, start_time); const char* filename = BPF_CORE_READ(bprm, filename); - size_t bin_path_length = bpf_probe_read_str(payload, MAX_FILENAME_LEN, filename); + size_t bin_path_length = + bpf_probe_read_kernel_str(payload, MAX_FILENAME_LEN, filename); barrier_var(bin_path_length); if (bin_path_length <= MAX_FILENAME_LEN) { barrier_var(bin_path_length); @@ -922,7 +935,8 @@ int BPF_KPROBE(kprobe__vfs_symlink, struct inode* dir, struct dentry* dentry, filemod_data->payload); payload = populate_cgroup_info(&filemod_data->cgroup_data, task, payload); - size_t len = bpf_probe_read_str(payload, MAX_FILEPATH_LENGTH, oldname); + size_t len = bpf_probe_read_kernel_str(payload, MAX_FILEPATH_LENGTH, + oldname); barrier_var(len); if (len <= MAX_FILEPATH_LENGTH) { barrier_var(len); diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c index a1e45fec8938..3b5dc34d23e9 100644 --- a/tools/testing/selftests/bpf/progs/test_attach_probe.c +++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c @@ -92,18 +92,19 @@ int handle_uretprobe_byname(struct pt_regs *ctx) } SEC("uprobe") -int handle_uprobe_byname2(struct pt_regs *ctx) +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { - unsigned int size = PT_REGS_PARM1(ctx); + char mode_buf[2] = {}; - /* verify malloc size */ - if (size == 1) + /* verify fopen mode */ + bpf_probe_read_user(mode_buf, sizeof(mode_buf), mode); + if (mode_buf[0] == 'r' && mode_buf[1] == 0) uprobe_byname2_res = 7; return 0; } SEC("uretprobe") -int handle_uretprobe_byname2(struct pt_regs *ctx) +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { uretprobe_byname2_res = 8; return 0; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c index 98c6493d9b91..21b19b758c4e 100644 --- a/tools/testing/selftests/bpf/progs/test_sk_assign.c +++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c @@ -16,6 +16,16 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#if defined(IPROUTE2_HAVE_LIBBPF) +/* Use a new-style map definition. */ +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __type(key, int); + __type(value, __u64); + __uint(pinning, LIBBPF_PIN_BY_NAME); + __uint(max_entries, 1); +} server_map SEC(".maps"); +#else /* Pin map under /sys/fs/bpf/tc/globals/<map name> */ #define PIN_GLOBAL_NS 2 @@ -35,6 +45,7 @@ struct { .max_elem = 1, .pinning = PIN_GLOBAL_NS, }; +#endif char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c new file mode 100644 index 000000000000..dcf46adfda04 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sk_assign_libbpf.c @@ -0,0 +1,3 @@ +// SPDX-License-Identifier: GPL-2.0 +#define IPROUTE2_HAVE_LIBBPF +#include "test_sk_assign.c" diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c index 774ddeb45898..da4bf89d004c 100644 --- a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c +++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c @@ -13,9 +13,9 @@ int uprobe_byname_ran = 0; int uretprobe_byname_rc = 0; int uretprobe_byname_ret = 0; int uretprobe_byname_ran = 0; -size_t uprobe_byname2_parm1 = 0; +u64 uprobe_byname2_parm1 = 0; int uprobe_byname2_ran = 0; -char *uretprobe_byname2_rc = NULL; +u64 uretprobe_byname2_rc = 0; int uretprobe_byname2_ran = 0; int test_pid; @@ -88,28 +88,28 @@ int BPF_URETPROBE(handle_uretprobe_byname, int ret) } -SEC("uprobe/libc.so.6:malloc") -int handle_uprobe_byname2(struct pt_regs *ctx) +SEC("uprobe/libc.so.6:fopen") +int BPF_UPROBE(handle_uprobe_byname2, const char *pathname, const char *mode) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uprobe_byname2_parm1 = PT_REGS_PARM1_CORE(ctx); + uprobe_byname2_parm1 = (u64)(long)pathname; uprobe_byname2_ran = 3; return 0; } -SEC("uretprobe/libc.so.6:malloc") -int handle_uretprobe_byname2(struct pt_regs *ctx) +SEC("uretprobe/libc.so.6:fopen") +int BPF_URETPROBE(handle_uretprobe_byname2, void *ret) { int pid = bpf_get_current_pid_tgid() >> 32; /* ignore irrelevant invocations */ if (test_pid != pid) return 0; - uretprobe_byname2_rc = (char *)PT_REGS_RC_CORE(ctx); + uretprobe_byname2_rc = (u64)(long)ret; uretprobe_byname2_ran = 4; return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c index ce419304ff1f..7748cc23de8a 100644 --- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c +++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c @@ -59,10 +59,14 @@ int BPF_PROG(bpf, int cmd, union bpf_attr *attr, unsigned int size) if (!data_val) return 0; - bpf_probe_read(&value, sizeof(value), &attr->value); - - bpf_copy_from_user(data_val, sizeof(struct data), - (void *)(unsigned long)value); + ret = bpf_probe_read_kernel(&value, sizeof(value), &attr->value); + if (ret) + return ret; + + ret = bpf_copy_from_user(data_val, sizeof(struct data), + (void *)(unsigned long)value); + if (ret) + return ret; if (data_val->data_len > sizeof(data_val->data)) return -EINVAL; diff --git a/tools/testing/selftests/bpf/progs/test_vmlinux.c b/tools/testing/selftests/bpf/progs/test_vmlinux.c index e9dfa0313d1b..4b8e37f7fd06 100644 --- a/tools/testing/selftests/bpf/progs/test_vmlinux.c +++ b/tools/testing/selftests/bpf/progs/test_vmlinux.c @@ -42,7 +42,7 @@ int BPF_PROG(handle__raw_tp, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; @@ -60,7 +60,7 @@ int BPF_PROG(handle__tp_btf, struct pt_regs *regs, long id) if (id != __NR_nanosleep) return 0; - ts = (void *)PT_REGS_PARM1_CORE(regs); + ts = (void *)PT_REGS_PARM1_CORE_SYSCALL(regs); if (bpf_probe_read_user(&tv_nsec, sizeof(ts->tv_nsec), &ts->tv_nsec) || tv_nsec != MY_TV_NSEC) return 0; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 53b64c999450..297c260fc364 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -9,6 +9,12 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) void *data = (void *)(long)xdp->data; int data_len = bpf_xdp_get_buff_len(xdp); int offset = 0; + /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ +#if defined(__TARGET_ARCH_s390) + int tailroom = 512; +#else + int tailroom = 320; +#endif /* Data length determine test case */ @@ -20,7 +26,7 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) offset = 128; } else if (data_len == 128) { /* Max tail grow 3520 */ - offset = 4096 - 256 - 320 - data_len; + offset = 4096 - 256 - tailroom - data_len; } else if (data_len == 9000) { offset = 10; } else if (data_len == 9001) { diff --git a/tools/testing/selftests/bpf/progs/xdp_features.c b/tools/testing/selftests/bpf/progs/xdp_features.c new file mode 100644 index 000000000000..87c247d56f72 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_features.c @@ -0,0 +1,269 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdbool.h> +#include <linux/bpf.h> +#include <linux/netdev.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +#include <bpf/bpf_tracing.h> +#include <linux/if_ether.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/udp.h> +#include <asm-generic/errno-base.h> + +#include "xdp_features.h" + +#define ipv6_addr_equal(a, b) ((a).s6_addr32[0] == (b).s6_addr32[0] && \ + (a).s6_addr32[1] == (b).s6_addr32[1] && \ + (a).s6_addr32[2] == (b).s6_addr32[2] && \ + (a).s6_addr32[3] == (b).s6_addr32[3]) + +struct net_device; +struct bpf_prog; + +struct xdp_cpumap_stats { + unsigned int redirect; + unsigned int pass; + unsigned int drop; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, __u32); + __type(value, __u32); + __uint(max_entries, 1); +} dut_stats SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CPUMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_cpumap_val)); + __uint(max_entries, 1); +} cpu_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_DEVMAP); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct bpf_devmap_val)); + __uint(max_entries, 1); +} dev_map SEC(".maps"); + +const volatile struct in6_addr tester_addr; +const volatile struct in6_addr dut_addr; + +static __always_inline int +xdp_process_echo_packet(struct xdp_md *xdp, bool dut) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + struct tlv_hdr *tlv; + struct udphdr *uh; + __be16 port; + __u8 *cmd; + + if (eh + 1 > (struct ethhdr *)data_end) + return -EINVAL; + + if (eh->h_proto == bpf_htons(ETH_P_IP)) { + struct iphdr *ih = (struct iphdr *)(eh + 1); + __be32 saddr = dut ? tester_addr.s6_addr32[3] + : dut_addr.s6_addr32[3]; + __be32 daddr = dut ? dut_addr.s6_addr32[3] + : tester_addr.s6_addr32[3]; + + ih = (struct iphdr *)(eh + 1); + if (ih + 1 > (struct iphdr *)data_end) + return -EINVAL; + + if (saddr != ih->saddr) + return -EINVAL; + + if (daddr != ih->daddr) + return -EINVAL; + + if (ih->protocol != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih + 1); + } else if (eh->h_proto == bpf_htons(ETH_P_IPV6)) { + struct in6_addr saddr = dut ? tester_addr : dut_addr; + struct in6_addr daddr = dut ? dut_addr : tester_addr; + struct ipv6hdr *ih6 = (struct ipv6hdr *)(eh + 1); + + if (ih6 + 1 > (struct ipv6hdr *)data_end) + return -EINVAL; + + if (!ipv6_addr_equal(saddr, ih6->saddr)) + return -EINVAL; + + if (!ipv6_addr_equal(daddr, ih6->daddr)) + return -EINVAL; + + if (ih6->nexthdr != IPPROTO_UDP) + return -EINVAL; + + uh = (struct udphdr *)(ih6 + 1); + } else { + return -EINVAL; + } + + if (uh + 1 > (struct udphdr *)data_end) + return -EINVAL; + + port = dut ? uh->dest : uh->source; + if (port != bpf_htons(DUT_ECHO_PORT)) + return -EINVAL; + + tlv = (struct tlv_hdr *)(uh + 1); + if (tlv + 1 > data_end) + return -EINVAL; + + return bpf_htons(tlv->type) == CMD_ECHO ? 0 : -EINVAL; +} + +static __always_inline int +xdp_update_stats(struct xdp_md *xdp, bool tx, bool dut) +{ + __u32 *val, key = 0; + + if (xdp_process_echo_packet(xdp, tx)) + return -EINVAL; + + if (dut) + val = bpf_map_lookup_elem(&dut_stats, &key); + else + val = bpf_map_lookup_elem(&stats, &key); + + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +/* Tester */ + +SEC("xdp") +int xdp_tester_check_tx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, false); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_tester_check_rx(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, false, false); + + return XDP_PASS; +} + +/* DUT */ + +SEC("xdp") +int xdp_do_pass(struct xdp_md *xdp) +{ + xdp_update_stats(xdp, true, true); + + return XDP_PASS; +} + +SEC("xdp") +int xdp_do_drop(struct xdp_md *xdp) +{ + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + return XDP_DROP; +} + +SEC("xdp") +int xdp_do_aborted(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return XDP_ABORTED; +} + +SEC("xdp") +int xdp_do_tx(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_update_stats(xdp, true, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return XDP_TX; +} + +SEC("xdp") +int xdp_do_redirect(struct xdp_md *xdp) +{ + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + return bpf_redirect_map(&cpu_map, 0, 0); +} + +SEC("tp_btf/xdp_exception") +int BPF_PROG(xdp_exception, const struct net_device *dev, + const struct bpf_prog *xdp, __u32 act) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("tp_btf/xdp_cpumap_kthread") +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed, + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats) +{ + __u32 *val, key = 0; + + val = bpf_map_lookup_elem(&dut_stats, &key); + if (val) + __sync_add_and_fetch(val, 1); + + return 0; +} + +SEC("xdp/cpumap") +int xdp_do_redirect_cpumap(struct xdp_md *xdp) +{ + void *data = (void *)(long)xdp->data; + struct ethhdr *eh = data; + __u8 tmp_mac[ETH_ALEN]; + + if (xdp_process_echo_packet(xdp, true)) + return XDP_PASS; + + __builtin_memcpy(tmp_mac, eh->h_source, ETH_ALEN); + __builtin_memcpy(eh->h_source, eh->h_dest, ETH_ALEN); + __builtin_memcpy(eh->h_dest, tmp_mac, ETH_ALEN); + + return bpf_redirect_map(&dev_map, 0, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 25b8178735ee..4c55b4d79d3d 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -70,10 +70,14 @@ int rx(struct xdp_md *ctx) } if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %u", meta->rx_timestamp); + bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); + else + meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) bpf_printk("populated rx_hash with %u", meta->rx_hash); + else + meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 736686e903f6..07d786329105 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -310,7 +310,7 @@ static __always_inline void values_get_tcpipopts(__u16 *mss, __u8 *wscale, static __always_inline void values_inc_synacks(void) { __u32 key = 1; - __u32 *value; + __u64 *value; value = bpf_map_lookup_elem(&values, &key); if (value) diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index c5f852163246..6d5e3022c75f 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -17,6 +17,7 @@ #include <sys/select.h> #include <sys/socket.h> #include <sys/un.h> +#include <bpf/btf.h> static bool verbose(void) { @@ -967,6 +968,43 @@ int write_sysctl(const char *sysctl, const char *value) return 0; } +int get_bpf_max_tramp_links_from(struct btf *btf) +{ + const struct btf_enum *e; + const struct btf_type *t; + __u32 i, type_cnt; + const char *name; + __u16 j, vlen; + + for (i = 1, type_cnt = btf__type_cnt(btf); i < type_cnt; i++) { + t = btf__type_by_id(btf, i); + if (!t || !btf_is_enum(t) || t->name_off) + continue; + e = btf_enum(t); + for (j = 0, vlen = btf_vlen(t); j < vlen; j++, e++) { + name = btf__str_by_offset(btf, e->name_off); + if (name && !strcmp(name, "BPF_MAX_TRAMP_LINKS")) + return e->val; + } + } + + return -1; +} + +int get_bpf_max_tramp_links(void) +{ + struct btf *vmlinux_btf; + int ret; + + vmlinux_btf = btf__load_vmlinux_btf(); + if (!ASSERT_OK_PTR(vmlinux_btf, "vmlinux btf")) + return -1; + ret = get_bpf_max_tramp_links_from(vmlinux_btf); + btf__free(vmlinux_btf); + + return ret; +} + #define MAX_BACKTRACE_SZ 128 void crash_handler(int signum) { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 3f058dfadbaf..d5d51ec97ec8 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -394,6 +394,8 @@ int kern_sync_rcu(void); int trigger_module_test_read(int read_sz); int trigger_module_test_write(int write_sz); int write_sysctl(const char *sysctl, const char *value); +int get_bpf_max_tramp_links_from(struct btf *btf); +int get_bpf_max_tramp_links(void); #ifdef __x86_64__ #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep" diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 8c808551dfd7..887c49dc5abd 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -209,7 +209,7 @@ loop: insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_push), + BPF_FUNC_skb_vlan_push); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } @@ -220,7 +220,7 @@ loop: i++; insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - BPF_FUNC_skb_vlan_pop), + BPF_FUNC_skb_vlan_pop); insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 3); i++; } diff --git a/tools/testing/selftests/bpf/test_xdp_features.sh b/tools/testing/selftests/bpf/test_xdp_features.sh new file mode 100755 index 000000000000..0aa71c4455c0 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_features.sh @@ -0,0 +1,107 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +readonly NS="ns1-$(mktemp -u XXXXXX)" +readonly V0_IP4=10.10.0.11 +readonly V1_IP4=10.10.0.1 +readonly V0_IP6=2001:db8::11 +readonly V1_IP6=2001:db8::1 + +ret=1 + +setup() { + { + ip netns add ${NS} + + ip link add v1 type veth peer name v0 netns ${NS} + + ip link set v1 up + ip addr add $V1_IP4/24 dev v1 + ip addr add $V1_IP6/64 nodad dev v1 + ip -n ${NS} link set dev v0 up + ip -n ${NS} addr add $V0_IP4/24 dev v0 + ip -n ${NS} addr add $V0_IP6/64 nodad dev v0 + + # Enable XDP mode and disable checksum offload + ethtool -K v1 gro on + ethtool -K v1 tx-checksumming off + ip netns exec ${NS} ethtool -K v0 gro on + ip netns exec ${NS} ethtool -K v0 tx-checksumming off + } > /dev/null 2>&1 +} + +cleanup() { + ip link del v1 2> /dev/null + ip netns del ${NS} 2> /dev/null + [ "$(pidof xdp_features)" = "" ] || kill $(pidof xdp_features) 2> /dev/null +} + +wait_for_dut_server() { + while sleep 1; do + ss -tlp | grep -q xdp_features + [ $? -eq 0 ] && break + done +} + +test_xdp_features() { + setup + + ## XDP_PASS + ./xdp_features -f XDP_PASS -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_PASS \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_DROP + ./xdp_features -f XDP_DROP -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_DROP \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_ABORTED + ./xdp_features -f XDP_ABORTED -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_ABORTED \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_TX + ./xdp_features -f XDP_TX -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_TX \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + [ $? -ne 0 ] && exit + + ## XDP_REDIRECT + ./xdp_features -f XDP_REDIRECT -D $V1_IP6 -T $V0_IP6 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_REDIRECT \ + -D $V1_IP6 -C $V1_IP6 \ + -T $V0_IP6 v0 + [ $? -ne 0 ] && exit + + ## XDP_NDO_XMIT + ./xdp_features -f XDP_NDO_XMIT -D ::ffff:$V1_IP4 -T ::ffff:$V0_IP4 v1 & + wait_for_dut_server + ip netns exec ${NS} ./xdp_features -t -f XDP_NDO_XMIT \ + -D ::ffff:$V1_IP4 \ + -C ::ffff:$V1_IP4 \ + -T ::ffff:$V0_IP4 v0 + ret=$? + cleanup +} + +set -e +trap cleanup 2 3 6 9 + +test_xdp_features + +exit $ret diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh index 316a56d680f2..685034528018 100755 --- a/tools/testing/selftests/bpf/vmtest.sh +++ b/tools/testing/selftests/bpf/vmtest.sh @@ -13,7 +13,7 @@ s390x) QEMU_BINARY=qemu-system-s390x QEMU_CONSOLE="ttyS1" QEMU_FLAGS=(-smp 2) - BZIMAGE="arch/s390/boot/compressed/vmlinux" + BZIMAGE="arch/s390/boot/vmlinux" ;; x86_64) QEMU_BINARY=qemu-system-x86_64 diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c new file mode 100644 index 000000000000..fce12165213b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.c @@ -0,0 +1,699 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <uapi/linux/bpf.h> +#include <uapi/linux/netdev.h> +#include <linux/if_link.h> +#include <signal.h> +#include <argp.h> +#include <net/if.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <unistd.h> +#include <arpa/inet.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> +#include <pthread.h> + +#include <network_helpers.h> + +#include "xdp_features.skel.h" +#include "xdp_features.h" + +#define RED(str) "\033[0;31m" str "\033[0m" +#define GREEN(str) "\033[0;32m" str "\033[0m" +#define YELLOW(str) "\033[0;33m" str "\033[0m" + +static struct env { + bool verbosity; + int ifindex; + bool is_tester; + struct { + enum netdev_xdp_act drv_feature; + enum xdp_action action; + } feature; + struct sockaddr_storage dut_ctrl_addr; + struct sockaddr_storage dut_addr; + struct sockaddr_storage tester_addr; +} env; + +#define BUFSIZE 128 + +void test__fail(void) { /* for network_helpers.c */ } + +static int libbpf_print_fn(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG && !env.verbosity) + return 0; + return vfprintf(stderr, format, args); +} + +static volatile bool exiting; + +static void sig_handler(int sig) +{ + exiting = true; +} + +const char *argp_program_version = "xdp-features 0.0"; +const char argp_program_doc[] = +"XDP features detection application.\n" +"\n" +"XDP features application checks the XDP advertised features match detected ones.\n" +"\n" +"USAGE: ./xdp-features [-vt] [-f <xdp-feature>] [-D <dut-data-ip>] [-T <tester-data-ip>] [-C <dut-ctrl-ip>] <iface-name>\n" +"\n" +"dut-data-ip, tester-data-ip, dut-ctrl-ip: IPv6 or IPv4-mapped-IPv6 addresses;\n" +"\n" +"XDP features\n:" +"- XDP_PASS\n" +"- XDP_DROP\n" +"- XDP_ABORTED\n" +"- XDP_REDIRECT\n" +"- XDP_NDO_XMIT\n" +"- XDP_TX\n"; + +static const struct argp_option opts[] = { + { "verbose", 'v', NULL, 0, "Verbose debug output" }, + { "tester", 't', NULL, 0, "Tester mode" }, + { "feature", 'f', "XDP-FEATURE", 0, "XDP feature to test" }, + { "dut_data_ip", 'D', "DUT-DATA-IP", 0, "DUT IP data channel" }, + { "dut_ctrl_ip", 'C', "DUT-CTRL-IP", 0, "DUT IP control channel" }, + { "tester_data_ip", 'T', "TESTER-DATA-IP", 0, "Tester IP data channel" }, + {}, +}; + +static int get_xdp_feature(const char *arg) +{ + if (!strcmp(arg, "XDP_PASS")) { + env.feature.action = XDP_PASS; + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + } else if (!strcmp(arg, "XDP_DROP")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_DROP; + } else if (!strcmp(arg, "XDP_ABORTED")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_ABORTED; + } else if (!strcmp(arg, "XDP_TX")) { + env.feature.drv_feature = NETDEV_XDP_ACT_BASIC; + env.feature.action = XDP_TX; + } else if (!strcmp(arg, "XDP_REDIRECT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_REDIRECT; + env.feature.action = XDP_REDIRECT; + } else if (!strcmp(arg, "XDP_NDO_XMIT")) { + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + } else { + return -EINVAL; + } + + return 0; +} + +static char *get_xdp_feature_str(void) +{ + switch (env.feature.action) { + case XDP_PASS: + return YELLOW("XDP_PASS"); + case XDP_DROP: + return YELLOW("XDP_DROP"); + case XDP_ABORTED: + return YELLOW("XDP_ABORTED"); + case XDP_TX: + return YELLOW("XDP_TX"); + case XDP_REDIRECT: + return YELLOW("XDP_REDIRECT"); + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return YELLOW("XDP_NDO_XMIT"); + + return ""; +} + +static error_t parse_arg(int key, char *arg, struct argp_state *state) +{ + switch (key) { + case 'v': + env.verbosity = true; + break; + case 't': + env.is_tester = true; + break; + case 'f': + if (get_xdp_feature(arg) < 0) { + fprintf(stderr, "Invalid xdp feature: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + case 'D': + if (make_sockaddr(AF_INET6, arg, DUT_ECHO_PORT, + &env.dut_addr, NULL)) { + fprintf(stderr, "Invalid DUT address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'C': + if (make_sockaddr(AF_INET6, arg, DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL)) { + fprintf(stderr, "Invalid DUT CTRL address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case 'T': + if (make_sockaddr(AF_INET6, arg, 0, &env.tester_addr, NULL)) { + fprintf(stderr, "Invalid Tester address: %s\n", arg); + return ARGP_ERR_UNKNOWN; + } + break; + case ARGP_KEY_ARG: + errno = 0; + if (strlen(arg) >= IF_NAMESIZE) { + fprintf(stderr, "Invalid device name: %s\n", arg); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + + env.ifindex = if_nametoindex(arg); + if (!env.ifindex) + env.ifindex = strtoul(arg, NULL, 0); + if (!env.ifindex) { + fprintf(stderr, + "Bad interface index or name (%d): %s\n", + errno, strerror(errno)); + argp_usage(state); + return ARGP_ERR_UNKNOWN; + } + break; + default: + return ARGP_ERR_UNKNOWN; + } + + return 0; +} + +static const struct argp argp = { + .options = opts, + .parser = parse_arg, + .doc = argp_program_doc, +}; + +static void set_env_default(void) +{ + env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; + env.feature.action = -EINVAL; + env.ifindex = -ENODEV; + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, + &env.dut_ctrl_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, + &env.dut_addr, NULL); + make_sockaddr(AF_INET6, "::ffff:127.0.0.1", 0, &env.tester_addr, NULL); +} + +static void *dut_echo_thread(void *arg) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + int sockfd = *(int *)arg; + + while (!exiting) { + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + struct sockaddr_storage addr; + socklen_t addrlen; + size_t n; + + n = recvfrom(sockfd, buf, sizeof(buf), MSG_WAITALL, + (struct sockaddr *)&addr, &addrlen); + if (n != ntohs(tlv->len)) + continue; + + if (ntohs(tlv->type) != CMD_ECHO) + continue; + + sendto(sockfd, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&addr, addrlen); + } + + pthread_exit((void *)0); + close(sockfd); + + return NULL; +} + +static int dut_run_echo_thread(pthread_t *t, int *sockfd) +{ + int err; + + sockfd = start_reuseport_server(AF_INET6, SOCK_DGRAM, NULL, + DUT_ECHO_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + /* start echo channel */ + err = pthread_create(t, NULL, dut_echo_thread, sockfd); + if (err) { + fprintf(stderr, "Failed creating dut_echo thread: %s\n", + strerror(-err)); + free_fds(sockfd, 1); + return -EINVAL; + } + + return 0; +} + +static int dut_attach_xdp_prog(struct xdp_features *skel, int flags) +{ + enum xdp_action action = env.feature.action; + struct bpf_program *prog; + unsigned int key = 0; + int err, fd = 0; + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) { + struct bpf_devmap_val entry = { + .ifindex = env.ifindex, + }; + + err = bpf_map__update_elem(skel->maps.dev_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + fd = bpf_program__fd(skel->progs.xdp_do_redirect_cpumap); + action = XDP_REDIRECT; + } + + switch (action) { + case XDP_TX: + prog = skel->progs.xdp_do_tx; + break; + case XDP_DROP: + prog = skel->progs.xdp_do_drop; + break; + case XDP_ABORTED: + prog = skel->progs.xdp_do_aborted; + break; + case XDP_PASS: + prog = skel->progs.xdp_do_pass; + break; + case XDP_REDIRECT: { + struct bpf_cpumap_val entry = { + .qsize = 2048, + .bpf_prog.fd = fd, + }; + + err = bpf_map__update_elem(skel->maps.cpu_map, + &key, sizeof(key), + &entry, sizeof(entry), 0); + if (err < 0) + return err; + + prog = skel->progs.xdp_do_redirect; + break; + } + default: + return -EINVAL; + } + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) + fprintf(stderr, + "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + return err; +} + +static int recv_msg(int sockfd, void *buf, size_t bufsize, void *val, + size_t val_size) +{ + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + size_t len; + + len = recv(sockfd, buf, bufsize, 0); + if (len != ntohs(tlv->len) || len < sizeof(*tlv)) + return -EINVAL; + + if (val) { + len -= sizeof(*tlv); + if (len > val_size) + return -ENOMEM; + + memcpy(val, tlv->data, len); + } + + return 0; +} + +static int dut_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + int state, err, *sockfd, ctrl_sockfd, echo_sockfd; + struct sockaddr_storage ctrl_addr; + pthread_t dut_thread; + socklen_t addrlen; + + sockfd = start_reuseport_server(AF_INET6, SOCK_STREAM, NULL, + DUT_CTRL_PORT, 0, 1); + if (!sockfd) { + fprintf(stderr, "Failed to create DUT socket\n"); + return -errno; + } + + ctrl_sockfd = accept(*sockfd, (struct sockaddr *)&ctrl_addr, &addrlen); + if (ctrl_sockfd < 0) { + fprintf(stderr, "Failed to accept connection on DUT socket\n"); + free_fds(sockfd, 1); + return -errno; + } + + /* CTRL loop */ + while (!exiting) { + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + + err = recv_msg(ctrl_sockfd, buf, BUFSIZE, NULL, 0); + if (err) + continue; + + switch (ntohs(tlv->type)) { + case CMD_START: { + if (state == CMD_START) + continue; + + state = CMD_START; + /* Load the XDP program on the DUT */ + err = dut_attach_xdp_prog(skel, flags); + if (err) + goto out; + + err = dut_run_echo_thread(&dut_thread, &echo_sockfd); + if (err < 0) + goto out; + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_STOP: + if (state != CMD_START) + break; + + state = CMD_STOP; + + exiting = true; + bpf_xdp_detach(env.ifindex, flags, NULL); + + tlv->type = htons(CMD_ACK); + tlv->len = htons(sizeof(*tlv)); + err = send(ctrl_sockfd, buf, sizeof(*tlv), 0); + goto end_thread; + case CMD_GET_XDP_CAP: { + LIBBPF_OPTS(bpf_xdp_query_opts, opts); + unsigned long long val; + size_t n; + + err = bpf_xdp_query(env.ifindex, XDP_FLAGS_DRV_MODE, + &opts); + if (err) { + fprintf(stderr, + "Failed to query XDP cap for ifindex %d\n", + env.ifindex); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(opts.feature_flags); + tlv->len = htons(n); + + val = htobe64(opts.feature_flags); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + case CMD_GET_STATS: { + unsigned int key = 0, val; + size_t n; + + err = bpf_map__lookup_elem(skel->maps.dut_stats, + &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + goto end_thread; + } + + tlv->type = htons(CMD_ACK); + n = sizeof(*tlv) + sizeof(val); + tlv->len = htons(n); + + val = htonl(val); + memcpy(tlv->data, &val, sizeof(val)); + + err = send(ctrl_sockfd, buf, n, 0); + if (err < 0) + goto end_thread; + break; + } + default: + break; + } + } + +end_thread: + pthread_join(dut_thread, NULL); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(ctrl_sockfd); + free_fds(sockfd, 1); + + return err; +} + +static bool tester_collect_detected_cap(struct xdp_features *skel, + unsigned int dut_stats) +{ + unsigned int err, key = 0, val; + + if (!dut_stats) + return false; + + err = bpf_map__lookup_elem(skel->maps.stats, &key, sizeof(key), + &val, sizeof(val), 0); + if (err) { + fprintf(stderr, "bpf_map_lookup_elem failed\n"); + return false; + } + + switch (env.feature.action) { + case XDP_PASS: + case XDP_TX: + case XDP_REDIRECT: + return val > 0; + case XDP_DROP: + case XDP_ABORTED: + return val == 0; + default: + break; + } + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT) + return val > 0; + + return false; +} + +static int send_and_recv_msg(int sockfd, enum test_commands cmd, void *val, + size_t val_size) +{ + unsigned char buf[BUFSIZE] = {}; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int err; + + tlv->type = htons(cmd); + tlv->len = htons(sizeof(*tlv)); + + err = send(sockfd, buf, sizeof(*tlv), 0); + if (err < 0) + return err; + + err = recv_msg(sockfd, buf, BUFSIZE, val, val_size); + if (err < 0) + return err; + + return ntohs(tlv->type) == CMD_ACK ? 0 : -EINVAL; +} + +static int send_echo_msg(void) +{ + unsigned char buf[sizeof(struct tlv_hdr)]; + struct tlv_hdr *tlv = (struct tlv_hdr *)buf; + int sockfd, n; + + sockfd = socket(AF_INET6, SOCK_DGRAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create echo socket\n"); + return -errno; + } + + tlv->type = htons(CMD_ECHO); + tlv->len = htons(sizeof(*tlv)); + + n = sendto(sockfd, buf, sizeof(*tlv), MSG_NOSIGNAL | MSG_CONFIRM, + (struct sockaddr *)&env.dut_addr, sizeof(env.dut_addr)); + close(sockfd); + + return n == ntohs(tlv->len) ? 0 : -EINVAL; +} + +static int tester_run(struct xdp_features *skel) +{ + int flags = XDP_FLAGS_UPDATE_IF_NOEXIST | XDP_FLAGS_DRV_MODE; + unsigned long long advertised_feature; + struct bpf_program *prog; + unsigned int stats; + int i, err, sockfd; + bool detected_cap; + + sockfd = socket(AF_INET6, SOCK_STREAM, 0); + if (sockfd < 0) { + fprintf(stderr, "Failed to create tester socket\n"); + return -errno; + } + + if (settimeo(sockfd, 1000) < 0) + return -EINVAL; + + err = connect(sockfd, (struct sockaddr *)&env.dut_ctrl_addr, + sizeof(env.dut_ctrl_addr)); + if (err) { + fprintf(stderr, "Failed to connect to the DUT\n"); + return -errno; + } + + err = send_and_recv_msg(sockfd, CMD_GET_XDP_CAP, &advertised_feature, + sizeof(advertised_feature)); + if (err < 0) { + close(sockfd); + return err; + } + + advertised_feature = be64toh(advertised_feature); + + if (env.feature.drv_feature == NETDEV_XDP_ACT_NDO_XMIT || + env.feature.action == XDP_TX) + prog = skel->progs.xdp_tester_check_tx; + else + prog = skel->progs.xdp_tester_check_rx; + + err = bpf_xdp_attach(env.ifindex, bpf_program__fd(prog), flags, NULL); + if (err) { + fprintf(stderr, "Failed to attach XDP program to ifindex %d\n", + env.ifindex); + goto out; + } + + err = send_and_recv_msg(sockfd, CMD_START, NULL, 0); + if (err) + goto out; + + for (i = 0; i < 10 && !exiting; i++) { + err = send_echo_msg(); + if (err < 0) + goto out; + + sleep(1); + } + + err = send_and_recv_msg(sockfd, CMD_GET_STATS, &stats, sizeof(stats)); + if (err) + goto out; + + /* stop the test */ + err = send_and_recv_msg(sockfd, CMD_STOP, NULL, 0); + /* send a new echo message to wake echo thread of the dut */ + send_echo_msg(); + + detected_cap = tester_collect_detected_cap(skel, ntohl(stats)); + + fprintf(stdout, "Feature %s: [%s][%s]\n", get_xdp_feature_str(), + detected_cap ? GREEN("DETECTED") : RED("NOT DETECTED"), + env.feature.drv_feature & advertised_feature ? GREEN("ADVERTISED") + : RED("NOT ADVERTISED")); +out: + bpf_xdp_detach(env.ifindex, flags, NULL); + close(sockfd); + return err < 0 ? err : 0; +} + +int main(int argc, char **argv) +{ + struct xdp_features *skel; + int err; + + libbpf_set_strict_mode(LIBBPF_STRICT_ALL); + libbpf_set_print(libbpf_print_fn); + + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + + set_env_default(); + + /* Parse command line arguments */ + err = argp_parse(&argp, argc, argv, 0, NULL, NULL); + if (err) + return err; + + if (env.ifindex < 0) { + fprintf(stderr, "Invalid ifindex\n"); + return -ENODEV; + } + + /* Load and verify BPF application */ + skel = xdp_features__open(); + if (!skel) { + fprintf(stderr, "Failed to open and load BPF skeleton\n"); + return -EINVAL; + } + + skel->rodata->tester_addr = + ((struct sockaddr_in6 *)&env.tester_addr)->sin6_addr; + skel->rodata->dut_addr = + ((struct sockaddr_in6 *)&env.dut_addr)->sin6_addr; + + /* Load & verify BPF programs */ + err = xdp_features__load(skel); + if (err) { + fprintf(stderr, "Failed to load and verify BPF skeleton\n"); + goto cleanup; + } + + err = xdp_features__attach(skel); + if (err) { + fprintf(stderr, "Failed to attach BPF skeleton\n"); + goto cleanup; + } + + if (env.is_tester) { + /* Tester */ + fprintf(stdout, "Starting tester on device %d\n", env.ifindex); + err = tester_run(skel); + } else { + /* DUT */ + fprintf(stdout, "Starting DUT on device %d\n", env.ifindex); + err = dut_run(skel); + } + +cleanup: + xdp_features__destroy(skel); + + return err < 0 ? -err : 0; +} diff --git a/tools/testing/selftests/bpf/xdp_features.h b/tools/testing/selftests/bpf/xdp_features.h new file mode 100644 index 000000000000..2670c541713b --- /dev/null +++ b/tools/testing/selftests/bpf/xdp_features.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* test commands */ +enum test_commands { + CMD_STOP, /* CMD */ + CMD_START, /* CMD */ + CMD_ECHO, /* CMD */ + CMD_ACK, /* CMD + data */ + CMD_GET_XDP_CAP, /* CMD */ + CMD_GET_STATS, /* CMD */ +}; + +#define DUT_CTRL_PORT 12345 +#define DUT_ECHO_PORT 12346 + +struct tlv_hdr { + __be16 type; + __be16 len; + __u8 data[]; +}; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3823b1c499cc..1c8acb68b977 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -24,7 +24,6 @@ #include <linux/net_tstamp.h> #include <linux/udp.h> #include <linux/sockios.h> -#include <linux/net_tstamp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -121,7 +120,7 @@ static void close_xsk(struct xsk *xsk) xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); - munmap(xsk->umem, UMEM_SIZE); + munmap(xsk->umem_area, UMEM_SIZE); } static void refill_rx(struct xsk *xsk, __u64 addr) @@ -165,7 +164,7 @@ static void verify_skb_metadata(int fd) hdr.msg_controllen = sizeof(cmsg_buf); if (recvmsg(fd, &hdr, 0) < 0) - error(-1, errno, "recvmsg"); + error(1, errno, "recvmsg"); for (cmsg = CMSG_FIRSTHDR(&hdr); cmsg != NULL; cmsg = CMSG_NXTHDR(&hdr, cmsg)) { @@ -270,16 +269,16 @@ static int rxq_num(const char *ifname) struct ifreq ifr = { .ifr_data = (void *)&ch, }; - strcpy(ifr.ifr_name, ifname); + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); if (fd < 0) - error(-1, errno, "socket"); + error(1, errno, "socket"); ret = ioctl(fd, SIOCETHTOOL, &ifr); if (ret < 0) - error(-1, errno, "ioctl(SIOCETHTOOL)"); + error(1, errno, "ioctl(SIOCETHTOOL)"); close(fd); @@ -291,16 +290,16 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c struct ifreq ifr = { .ifr_data = (void *)cfg, }; - strcpy(ifr.ifr_name, ifname); + strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); if (fd < 0) - error(-1, errno, "socket"); + error(1, errno, "socket"); ret = ioctl(fd, op, &ifr); if (ret < 0) - error(-1, errno, "ioctl(%d)", op); + error(1, errno, "ioctl(%d)", op); close(fd); } @@ -360,7 +359,7 @@ static void timestamping_enable(int fd, int val) ret = setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val)); if (ret < 0) - error(-1, errno, "setsockopt(SO_TIMESTAMPING)"); + error(1, errno, "setsockopt(SO_TIMESTAMPING)"); } int main(int argc, char *argv[]) @@ -386,13 +385,13 @@ int main(int argc, char *argv[]) rx_xsk = malloc(sizeof(struct xsk) * rxq); if (!rx_xsk) - error(-1, ENOMEM, "malloc"); + error(1, ENOMEM, "malloc"); for (i = 0; i < rxq; i++) { printf("open_xsk(%s, %p, %d)\n", ifname, &rx_xsk[i], i); ret = open_xsk(ifindex, &rx_xsk[i], i); if (ret) - error(-1, -ret, "open_xsk"); + error(1, -ret, "open_xsk"); printf("xsk_socket__fd() -> %d\n", xsk_socket__fd(rx_xsk[i].socket)); } @@ -400,7 +399,7 @@ int main(int argc, char *argv[]) printf("open bpf program...\n"); bpf_obj = xdp_hw_metadata__open(); if (libbpf_get_error(bpf_obj)) - error(-1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open"); + error(1, libbpf_get_error(bpf_obj), "xdp_hw_metadata__open"); prog = bpf_object__find_program_by_name(bpf_obj->obj, "rx"); bpf_program__set_ifindex(prog, ifindex); @@ -409,12 +408,12 @@ int main(int argc, char *argv[]) printf("load bpf program...\n"); ret = xdp_hw_metadata__load(bpf_obj); if (ret) - error(-1, -ret, "xdp_hw_metadata__load"); + error(1, -ret, "xdp_hw_metadata__load"); printf("prepare skb endpoint...\n"); server_fd = start_server(AF_INET6, SOCK_DGRAM, NULL, 9092, 1000); if (server_fd < 0) - error(-1, errno, "start_server"); + error(1, errno, "start_server"); timestamping_enable(server_fd, SOF_TIMESTAMPING_SOFTWARE | SOF_TIMESTAMPING_RAW_HARDWARE); @@ -427,7 +426,7 @@ int main(int argc, char *argv[]) printf("map[%d] = %d\n", queue_id, sock_fd); ret = bpf_map_update_elem(bpf_map__fd(bpf_obj->maps.xsk), &queue_id, &sock_fd, 0); if (ret) - error(-1, -ret, "bpf_map_update_elem"); + error(1, -ret, "bpf_map_update_elem"); } printf("attach bpf program...\n"); @@ -435,12 +434,12 @@ int main(int argc, char *argv[]) bpf_program__fd(bpf_obj->progs.rx), XDP_FLAGS, NULL); if (ret) - error(-1, -ret, "bpf_xdp_attach"); + error(1, -ret, "bpf_xdp_attach"); signal(SIGINT, handle_signal); ret = verify_metadata(rx_xsk, rxq, server_fd); close(server_fd); cleanup(); if (ret) - error(-1, -ret, "verify_metadata"); + error(1, -ret, "verify_metadata"); } diff --git a/tools/testing/selftests/bpf/xdp_synproxy.c b/tools/testing/selftests/bpf/xdp_synproxy.c index 410a1385a01d..6dbe0b745198 100644 --- a/tools/testing/selftests/bpf/xdp_synproxy.c +++ b/tools/testing/selftests/bpf/xdp_synproxy.c @@ -116,6 +116,7 @@ static void parse_options(int argc, char *argv[], unsigned int *ifindex, __u32 * *tcpipopts = 0; *ports = NULL; *single = false; + *tc = false; while (true) { int opt; diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index 9c79bbcce5a8..aff0a59f92d9 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -246,7 +246,7 @@ test_vlan_ingress_modify() bridge vlan add dev $swp2 vid 300 tc filter add dev $swp1 ingress chain $(IS1 2) pref 3 \ - protocol 802.1Q flower skip_sw vlan_id 200 \ + protocol 802.1Q flower skip_sw vlan_id 200 src_mac $h1_mac \ action vlan modify id 300 \ action goto chain $(IS2 0 0) diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh index 7f35dc3d15df..7f35dc3d15df 100644..100755 --- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh +++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index beb944fa6fd4..54680dc5887f 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -237,6 +237,11 @@ static void guest_check_s1ptw_wr_in_dirty_log(void) GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG); } +static void guest_check_no_s1ptw_wr_in_dirty_log(void) +{ + GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG); +} + static void guest_exec(void) { int (*code)(void) = (int (*)(void))TEST_EXEC_GVA; @@ -304,7 +309,7 @@ static struct uffd_args { /* Returns true to continue the test, and false if it should be skipped. */ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, - struct uffd_args *args, bool expect_write) + struct uffd_args *args) { uint64_t addr = msg->arg.pagefault.address; uint64_t flags = msg->arg.pagefault.flags; @@ -313,7 +318,6 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING, "The only expected UFFD mode is MISSING"); - ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write); ASSERT_EQ(addr, (uint64_t)args->hva); pr_debug("uffd fault: addr=%p write=%d\n", @@ -337,19 +341,14 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, return 0; } -static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg) -{ - return uffd_generic_handler(mode, uffd, msg, &pt_args, true); -} - -static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, true); + return uffd_generic_handler(mode, uffd, msg, &pt_args); } -static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, false); + return uffd_generic_handler(mode, uffd, msg, &data_args); } static void setup_uffd_args(struct userspace_mem_region *region, @@ -471,9 +470,12 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) { struct userspace_mem_region *data_region, *pt_region; bool continue_test = true; + uint64_t pte_gpa, pte_pg; data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); pt_region = vm_get_mem_region(vm, MEM_REGION_PT); + pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA)); + pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize(); if (cmd == CMD_SKIP_TEST) continue_test = false; @@ -486,13 +488,13 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0), "Missing write in dirty log"); if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg), "Missing s1ptw write in dirty log"); if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG) TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0), "Unexpected write in dirty log"); if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg), "Unexpected s1ptw write in dirty log"); return continue_test; @@ -797,7 +799,7 @@ static void help(char *name) .expected_events = { .uffd_faults = _uffd_faults, }, \ } -#define TEST_DIRTY_LOG(_access, _with_af, _test_check) \ +#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check) \ { \ .name = SCAT3(dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -805,13 +807,12 @@ static void help(char *name) .guest_prepare = { _PREPARE(_with_af), \ _PREPARE(_access) }, \ .guest_test = _access, \ - .guest_test_check = { _CHECK(_with_af), _test_check, \ - guest_check_s1ptw_wr_in_dirty_log}, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .expected_events = { 0 }, \ } #define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler, \ - _uffd_faults, _test_check) \ + _uffd_faults, _test_check, _pt_check) \ { \ .name = SCAT3(uffd_and_dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -820,16 +821,17 @@ static void help(char *name) _PREPARE(_access) }, \ .guest_test = _access, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ - .guest_test_check = { _CHECK(_with_af), _test_check }, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .expected_events = { .uffd_faults = _uffd_faults, }, \ } #define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .mmio_handler = _mmio_handler, \ @@ -840,6 +842,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_test = _access, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1 }, \ @@ -848,9 +851,9 @@ static void help(char *name) #define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits, \ _test_check) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ @@ -862,7 +865,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syn_and_dlog, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ @@ -874,11 +877,12 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_uffd, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .mmio_handler = _mmio_handler, \ .expected_events = { .mmio_exits = _mmio_exits, \ .uffd_faults = _uffd_faults }, \ @@ -889,10 +893,11 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1, \ .uffd_faults = _uffd_faults }, \ @@ -933,44 +938,51 @@ static struct test_desc tests[] = { * (S1PTW). */ TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* no_af should also lead to a PT write. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* Note how that cas invokes the read handler. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Can't test guest_at with_af as it's IMPDEF whether the AF is set. * The S1PTW fault should still be marked as a write. */ TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 1), + uffd_no_handler, uffd_pt_handler, 1), TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Try accesses when the data and PT memory regions are both * tracked for dirty logging. */ - TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_ld_preidx, with_af, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* * Access when the data and PT memory regions are both marked for @@ -980,29 +992,43 @@ static struct test_desc tests[] = { * fault, and nothing in the dirty log. Any S1PTW should result in * a write in the dirty log and a userfaultfd write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler, - 2, guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2, - guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, + uffd_data_handler, + 2, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af, - uffd_data_write_handler, 2, - guest_check_write_in_dirty_log), - + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* - * Try accesses when the data memory region is marked read-only + * Access when both the PT and data regions are marked read-only * (with KVM_MEM_READONLY). Writes with a syndrome result in an * MMIO exit, writes with no syndrome (e.g., CAS) result in a * failed vcpu run, and reads/execs with and without syndroms do @@ -1018,7 +1044,7 @@ static struct test_desc tests[] = { TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx), /* - * Access when both the data region is both read-only and marked + * The PT and data regions are both read-only and marked * for dirty logging at the same time. The expected result is that * for writes there should be no write in the dirty log. The * readonly handling is the same as if the memslot was not marked @@ -1043,7 +1069,7 @@ static struct test_desc tests[] = { guest_check_no_write_in_dirty_log), /* - * Access when the data region is both read-only and punched with + * The PT and data regions are both read-only and punched with * holes tracked with userfaultfd. The expected result is the * union of both userfaultfd and read-only behaviors. For example, * write accesses result in a userfaultfd write fault and an MMIO @@ -1051,22 +1077,15 @@ static struct test_desc tests[] = { * no userfaultfd write fault. Reads result in userfaultfd getting * triggered. */ - TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, - uffd_data_read_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, uffd_no_handler, 1), + TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, uffd_data_handler, 2), TEST_RO_MEMSLOT_AND_UFFD(guest_write64, mmio_on_test_gpa_handler, 1, - uffd_data_write_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, - uffd_no_handler, 1), + uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, uffd_no_handler, 1), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, uffd_no_handler, 1), { 0 } }; diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 951bd5342bc6..3364c548a23b 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -46,6 +46,7 @@ TEST_PROGS += stress_reuseport_listen.sh TEST_PROGS += l2_tos_ttl_inherit.sh TEST_PROGS += bind_bhash.sh TEST_PROGS += ip_local_port_range.sh +TEST_PROGS += rps_default_mask.sh TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh TEST_GEN_FILES = socket nettest diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index bd89198cd817..cc9fd55ab869 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -3,6 +3,9 @@ CONFIG_NET_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m CONFIG_NUMA=y +CONFIG_RPS=y +CONFIG_SYSFS=y +CONFIG_PROC_SYSCTL=y CONFIG_NET_VRF=y CONFIG_NET_L3_MASTER_DEV=y CONFIG_IPV6=y diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile index 453ae006fbcf..91201ab3c4fc 100644 --- a/tools/testing/selftests/net/forwarding/Makefile +++ b/tools/testing/selftests/net/forwarding/Makefile @@ -4,6 +4,7 @@ TEST_PROGS = bridge_igmp.sh \ bridge_locked_port.sh \ bridge_mdb.sh \ bridge_mdb_host.sh \ + bridge_mdb_max.sh \ bridge_mdb_port_down.sh \ bridge_mld.sh \ bridge_port_isolation.sh \ diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 2fa5973c0c28..ae3f9462a2b6 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -742,10 +742,109 @@ cfg_test_port() cfg_test_port_l2 } +ipv4_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "239.1.1.$i" + done +} + +ipv6_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "ff0e::$(printf %x $i)" + done +} + +l2_grps_get() +{ + local max_grps=$1; shift + local i + + for i in $(seq 0 $((max_grps - 1))); do + echo "01:00:00:00:00:$(printf %02x $i)" + done +} + +cfg_test_dump_common() +{ + local name=$1; shift + local fn=$1; shift + local max_bridges=2 + local max_grps=256 + local max_ports=32 + local num_entries + local batch_file + local grp + local i j + + RET=0 + + # Create net devices. + for i in $(seq 1 $max_bridges); do + ip link add name br-test${i} up type bridge vlan_filtering 1 \ + mcast_snooping 1 + for j in $(seq 1 $max_ports); do + ip link add name br-test${i}-du${j} up \ + master br-test${i} type dummy + done + done + + # Create batch file with MDB entries. + batch_file=$(mktemp) + for i in $(seq 1 $max_bridges); do + for j in $(seq 1 $max_ports); do + for grp in $($fn $max_grps); do + echo "mdb add dev br-test${i} \ + port br-test${i}-du${j} grp $grp \ + permanent vid 1" >> $batch_file + done + done + done + + # Program the batch file and check for expected number of entries. + bridge -b $batch_file + for i in $(seq 1 $max_bridges); do + num_entries=$(bridge mdb show dev br-test${i} | \ + grep "permanent" | wc -l) + [[ $num_entries -eq $((max_grps * max_ports)) ]] + check_err $? "Wrong number of entries in br-test${i}" + done + + # Cleanup. + rm $batch_file + for i in $(seq 1 $max_bridges); do + ip link del dev br-test${i} + for j in $(seq $max_ports); do + ip link del dev br-test${i}-du${j} + done + done + + log_test "$name large scale dump tests" +} + +# Check large scale dump. +cfg_test_dump() +{ + echo + log_info "# Large scale dump tests" + + cfg_test_dump_common "IPv4" ipv4_grps_get + cfg_test_dump_common "IPv6" ipv6_grps_get + cfg_test_dump_common "L2" l2_grps_get +} + cfg_test() { cfg_test_host cfg_test_port + cfg_test_dump } __fwd_test_host_ip() @@ -1018,26 +1117,6 @@ fwd_test() ip -6 address del fe80::1/64 dev br0 } -igmpv3_is_in_get() -{ - local igmpv3 - - igmpv3=$(: - )"22:"$( : Type - Membership Report - )"00:"$( : Reserved - )"2a:f8:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ef:01:01:01:"$( : Multicast Address - 239.1.1.1 - )"c0:00:02:02"$( : Source Address - 192.0.2.2 - ) - - echo $igmpv3 -} - ctrl_igmpv3_is_in_test() { RET=0 @@ -1049,7 +1128,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -q 192.0.2.2 check_fail $? "Permanent entry affected by IGMP packet" @@ -1062,7 +1141,7 @@ ctrl_igmpv3_is_in_test() # IS_IN ( 192.0.2.2 ) $MZ $h1.10 -c 1 -A 192.0.2.1 -B 239.1.1.1 \ - -t ip proto=2,p=$(igmpv3_is_in_get) -q + -t ip proto=2,p=$(igmpv3_is_in_get 239.1.1.1 192.0.2.2) -q bridge -d mdb show dev br0 vid 10 | grep 239.1.1.1 | grep -v "src" | \ grep -q 192.0.2.2 @@ -1074,36 +1153,7 @@ ctrl_igmpv3_is_in_test() bridge mdb del dev br0 port $swp1 grp 239.1.1.1 vid 10 - log_test "IGMPv3 MODE_IS_INCLUE tests" -} - -mldv2_is_in_get() -{ - local hbh - local icmpv6 - - hbh=$(: - )"3a:"$( : Next Header - ICMPv6 - )"00:"$( : Hdr Ext Len - )"00:00:00:00:00:00:"$( : Options and Padding - ) - - icmpv6=$(: - )"8f:"$( : Type - MLDv2 Report - )"00:"$( : Code - )"45:39:"$( : Checksum - )"00:00:"$( : Reserved - )"00:01:"$( : Number of Group Records - )"01:"$( : Record Type - IS_IN - )"00:"$( : Aux Data Len - )"00:01:"$( : Number of Sources - )"ff:0e:00:00:00:00:00:00:"$( : Multicast address - ff0e::1 - )"00:00:00:00:00:00:00:01:"$( : - )"20:01:0d:b8:00:01:00:00:"$( : Source Address - 2001:db8:1::2 - )"00:00:00:00:00:00:00:02:"$( : - ) - - echo ${hbh}${icmpv6} + log_test "IGMPv3 MODE_IS_INCLUDE tests" } ctrl_mldv2_is_in_test() @@ -1116,8 +1166,9 @@ ctrl_mldv2_is_in_test() filter_mode include source_list 2001:db8:1::1 # IS_IN ( 2001:db8:1::2 ) + local p=$(mldv2_is_in_get fe80::1 ff0e::1 2001:db8:1::2) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | \ grep -q 2001:db8:1::2 @@ -1131,7 +1182,7 @@ ctrl_mldv2_is_in_test() # IS_IN ( 2001:db8:1::2 ) $MZ -6 $h1.10 -c 1 -A fe80::1 -B ff0e::1 \ - -t ip hop=1,next=0,p=$(mldv2_is_in_get) -q + -t ip hop=1,next=0,p="$p" -q bridge -d mdb show dev br0 vid 10 | grep ff0e::1 | grep -v "src" | \ grep -q 2001:db8:1::2 diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh new file mode 100755 index 000000000000..ae255b662ba3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_mdb_max.sh @@ -0,0 +1,1336 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +-----------------------+ +------------------------+ +# | H1 (vrf) | | H2 (vrf) | +# | + $h1.10 | | + $h2.10 | +# | | 192.0.2.1/28 | | | 192.0.2.2/28 | +# | | 2001:db8:1::1/64 | | | 2001:db8:1::2/64 | +# | | | | | | +# | | + $h1.20 | | | + $h2.20 | +# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 | +# | \ | 2001:db8:2::1/64 | | \ | 2001:db8:2::2/64 | +# | \| | | \| | +# | + $h1 | | + $h2 | +# +----|------------------+ +----|-------------------+ +# | | +# +----|--------------------------------------------------|-------------------+ +# | SW | | | +# | +--|--------------------------------------------------|-----------------+ | +# | | + $swp1 BR0 (802.1q) + $swp2 | | +# | | vid 10 vid 10 | | +# | | vid 20 vid 20 | | +# | | | | +# | +-----------------------------------------------------------------------+ | +# +---------------------------------------------------------------------------+ + +ALL_TESTS=" + test_8021d + test_8021q + test_8021qvs +" + +NUM_NETIFS=4 +source lib.sh +source tc_common.sh + +h1_create() +{ + simple_if_init $h1 + vlan_create $h1 10 v$h1 192.0.2.1/28 2001:db8:1::1/64 + vlan_create $h1 20 v$h1 198.51.100.1/24 2001:db8:2::1/64 +} + +h1_destroy() +{ + vlan_destroy $h1 20 + vlan_destroy $h1 10 + simple_if_fini $h1 +} + +h2_create() +{ + simple_if_init $h2 + vlan_create $h2 10 v$h2 192.0.2.2/28 + vlan_create $h2 20 v$h2 198.51.100.2/24 +} + +h2_destroy() +{ + vlan_destroy $h2 20 + vlan_destroy $h2 10 + simple_if_fini $h2 +} + +switch_create_8021d() +{ + log_info "802.1d tests" + + ip link add name br0 type bridge vlan_filtering 0 \ + mcast_snooping 1 \ + mcast_igmp_version 3 mcast_mld_version 2 + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up +} + +switch_create_8021q() +{ + local br_flags=$1; shift + + log_info "802.1q $br_flags${br_flags:+ }tests" + + ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + mcast_snooping 1 $br_flags \ + mcast_igmp_version 3 mcast_mld_version 2 + bridge vlan add vid 10 dev br0 self + bridge vlan add vid 20 dev br0 self + ip link set dev br0 up + + ip link set dev $swp1 master br0 + ip link set dev $swp1 up + bridge link set dev $swp1 fastleave on + bridge vlan add vid 10 dev $swp1 + bridge vlan add vid 20 dev $swp1 + + ip link set dev $swp2 master br0 + ip link set dev $swp2 up + bridge vlan add vid 10 dev $swp2 + bridge vlan add vid 20 dev $swp2 +} + +switch_create_8021qvs() +{ + switch_create_8021q "mcast_vlan_snooping 1" + bridge vlan global set dev br0 vid 10 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 10 mcast_mld_version 2 + bridge vlan global set dev br0 vid 20 mcast_igmp_version 3 + bridge vlan global set dev br0 vid 20 mcast_mld_version 2 +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp2 nomaster + + ip link set dev $swp1 down + ip link set dev $swp1 nomaster + + ip link set dev br0 down + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy 2>/dev/null + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +cfg_src_list() +{ + local IPs=("$@") + local IPstr=$(echo ${IPs[@]} | tr '[:space:]' , | sed 's/,$//') + + echo ${IPstr:+source_list }${IPstr} +} + +cfg_group_op() +{ + local op=$1; shift + local locus=$1; shift + local GRP=$1; shift + local state=$1; shift + local IPs=("$@") + + local source_list=$(cfg_src_list ${IPs[@]}) + + # Everything besides `bridge mdb' uses the "dev X vid Y" syntax, + # so we use it here as well and convert. + local br_locus=$(echo "$locus" | sed 's/^dev /port /') + + bridge mdb $op dev br0 $br_locus grp $GRP $state \ + filter_mode include $source_list +} + +cfg4_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=239.1.1.${grp} + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg4_entries_add() +{ + cfg4_entries_op add "$@" +} + +cfg4_entries_del() +{ + cfg4_entries_op del "$@" +} + +cfg6_entries_op() +{ + local op=$1; shift + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local GRP=ff0e::${grp} + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + cfg_group_op "$op" "$locus" "$GRP" "$state" ${IPs[@]} +} + +cfg6_entries_add() +{ + cfg6_entries_op add "$@" +} + +cfg6_entries_del() +{ + cfg6_entries_op del "$@" +} + +locus_dev_peer() +{ + local dev_kw=$1; shift + local dev=$1; shift + local vid_kw=$1; shift + local vid=$1; shift + + echo "$h1.${vid:-10}" +} + +locus_dev() +{ + local dev_kw=$1; shift + local dev=$1; shift + + echo $dev +} + +ctl4_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(seq -f 192.0.2.%g 1 $((n - 1))) + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B $GRP \ + -t ip proto=2,p=$(igmpv3_is_in_get $GRP $IPs) -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl4_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local GRP=239.1.1.${grp} + $MZ $peer -c 1 -A 192.0.2.1 -B 224.0.0.2 \ + -t ip proto=2,p=$(igmpv2_leave_get $GRP) -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +ctl6_entries_add() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local IPs=$(printf "2001:db8:1::%x\n" $(seq 1 $((n - 1)))) + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv2_is_in_get $SIP $GRP $IPs) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + + local nn=$(bridge mdb show dev br0 | grep $GRP | wc -l) + if ((nn != n)); then + echo mcast_max_groups > /dev/stderr + false + fi +} + +ctl6_entries_del() +{ + local locus=$1; shift + local state=$1; shift + local n=$1; shift + local grp=${1:-1}; shift + + local peer=$(locus_dev_peer $locus) + local SIP=fe80::1 + local GRP=ff0e::${grp} + local p=$(mldv1_done_get $SIP $GRP) + $MZ -6 $peer -c 1 -A $SIP -B $GRP -t ip hop=1,next=0,p="$p" -q + sleep 1 + ! bridge mdb show dev br0 | grep -q $GRP +} + +bridge_maxgroups_errmsg_check_cfg() +{ + local msg=$1; shift + local needle=$1; shift + + echo "$msg" | grep -q mcast_max_groups + check_err $? "Adding MDB entries failed for the wrong reason: $msg" +} + +bridge_maxgroups_errmsg_check_cfg4() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_cfg6() +{ + bridge_maxgroups_errmsg_check_cfg "$@" +} + +bridge_maxgroups_errmsg_check_ctl4() +{ + : +} + +bridge_maxgroups_errmsg_check_ctl6() +{ + : +} + +bridge_port_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_n_groups' +} + +bridge_port_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d link show $locus | + jq '.[].mcast_max_groups' +} + +bridge_port_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge link set dev $(locus_dev $locus) mcast_max_groups $max +} + +bridge_port_vlan_ngroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_n_groups' +} + +bridge_port_vlan_maxgroups_get() +{ + local locus=$1; shift + + bridge -j -d vlan show $locus | + jq '.[].vlans[].mcast_max_groups' +} + +bridge_port_vlan_maxgroups_set() +{ + local locus=$1; shift + local max=$1; shift + + bridge vlan set $locus mcast_max_groups $max +} + +test_ngroups_reporting() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n0=$(bridge_${context}_ngroups_get "$locus") + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Couldn't add MDB entries" + local n1=$(bridge_${context}_ngroups_get "$locus") + + ((n1 == n0 + 5)) + check_err $? "Number of groups was $n0, now is $n1, but $((n0 + 5)) expected" + + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + local n2=$(bridge_${context}_ngroups_get "$locus") + + ((n2 == n0)) + check_err $? "Number of groups was $n0, now is $n2, but should be back to $n0" + + log_test "$CFG: $context: ngroups reporting" +} + +test_8021d_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1" +} + +test_8021d_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1" +} + +test_8021d_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1" +} + +test_8021q_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port "dev $swp1 vid 10" +} + +test_8021q_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg4() +{ + test_ngroups_reporting cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl4() +{ + test_ngroups_reporting ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_cfg6() +{ + test_ngroups_reporting cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_ngroups_reporting_ctl6() +{ + test_ngroups_reporting ctl6 port_vlan "dev $swp1 vid 10" +} + +test_ngroups_cross_vlan() +{ + local CFG=$1; shift + + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + + RET=0 + + local n10=$(bridge_port_vlan_ngroups_get "$locus1") + local n20=$(bridge_port_vlan_ngroups_get "$locus2") + ${CFG}_entries_add "$locus1" temp 5 111 + check_err $? "Couldn't add MDB entries to VLAN 10" + local n11=$(bridge_port_vlan_ngroups_get "$locus1") + local n21=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n11 == n10 + 5)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n11, but 5 entries added on VLAN 10, $((n10 + 5)) expected" + + ((n21 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n21, but no change expected on VLAN 20" + + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add MDB entries to VLAN 20" + local n12=$(bridge_port_vlan_ngroups_get "$locus1") + local n22=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n12 == n11)) + check_err $? "Number of groups at VLAN 10 was $n11, now is $n12, but no change expected on VLAN 10" + + ((n22 == n21 + 5)) + check_err $? "Number of groups at VLAN 20 was $n21, now is $n22, but 5 entries added on VLAN 20, $((n21 + 5)) expected" + + ${CFG}_entries_del "$locus1" temp 5 111 + check_err $? "Couldn't delete MDB entries from VLAN 10" + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries from VLAN 20" + local n13=$(bridge_port_vlan_ngroups_get "$locus1") + local n23=$(bridge_port_vlan_ngroups_get "$locus2") + + ((n13 == n10)) + check_err $? "Number of groups at VLAN 10 was $n10, now is $n13, but should be back to $n10" + + ((n23 == n20)) + check_err $? "Number of groups at VLAN 20 was $n20, now is $n23, but should be back to $n20" + + log_test "$CFG: port_vlan: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_ngroups_cross_vlan_cfg4() +{ + test_ngroups_cross_vlan cfg4 +} + +test_8021qvs_ngroups_cross_vlan_ctl4() +{ + test_ngroups_cross_vlan ctl4 +} + +test_8021qvs_ngroups_cross_vlan_cfg6() +{ + test_ngroups_cross_vlan cfg6 +} + +test_8021qvs_ngroups_cross_vlan_ctl6() +{ + test_ngroups_cross_vlan ctl6 +} + +test_maxgroups_zero() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + local max + + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 0)) + check_err $? "Max groups on $locus should be 0, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100, but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Couldn't set maximum to 0" + + # Test that setting 0 explicitly still serves as infinity. + ${CFG}_entries_add "$locus" temp 5 + check_err $? "Adding 5 MDB entries failed but should have passed" + ${CFG}_entries_del "$locus" temp 5 + check_err $? "Couldn't delete MDB entries" + + log_test "$CFG: $context maxgroups: reporting and treatment of 0" +} + +test_8021d_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg4() +{ + test_maxgroups_zero cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl4() +{ + test_maxgroups_zero ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_cfg6() +{ + test_maxgroups_zero cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_zero_ctl6() +{ + test_maxgroups_zero ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_zero_cross_vlan() +{ + local CFG=$1; shift + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local max + + RET=0 + + bridge_port_vlan_maxgroups_set "$locus1" 100 + check_err $? "$locus1: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 100 + check_err $? "$locus2: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_maxgroups_set "$locus0" 100 + check_err $? "$locus0: Failed to set max to 100" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 100)) + check_err $? "$locus2: Max groups expected to be 100, but $max reported" + + bridge_port_vlan_maxgroups_set "$locus2" 0 + check_err $? "$locus2: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 100)) + check_err $? "$locus0: Max groups expected to be 100, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0 but $max reported" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Failed to set max to 0" + + max=$(bridge_port_maxgroups_get "$locus0") + ((max == 0)) + check_err $? "$locus0: Max groups expected to be 0, but $max reported" + + max=$(bridge_port_vlan_maxgroups_get "$locus2") + ((max == 0)) + check_err $? "$locus2: Max groups expected to be 0, but $max reported" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN maximums" +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg4() +{ + test_maxgroups_zero_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl4() +{ + test_maxgroups_zero_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_zero_cross_vlan_cfg6() +{ + test_maxgroups_zero_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_zero_cross_vlan_ctl6() +{ + test_maxgroups_zero_cross_vlan ctl6 +} + +test_maxgroups_too_low() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + ${CFG}_entries_add "$locus" temp 5 111 + check_err $? "$locus: Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" $((n+2)) + check_err $? "$locus: Setting maxgroups to $((n+2)) failed" + + msg=$(${CFG}_entries_add "$locus" temp 2 112 2>&1) + check_fail $? "$locus: Adding more entries passed when max<n" + bridge_maxgroups_errmsg_check_cfg "$msg" + + ${CFG}_entries_del "$locus" temp 5 111 + check_err $? "$locus: Couldn't delete MDB entries" + + ${CFG}_entries_add "$locus" temp 2 112 + check_err $? "$locus: Adding more entries failed" + + ${CFG}_entries_del "$locus" temp 2 112 + check_err $? "$locus: Deleting more entries failed" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: configure below ngroups" +} + +test_8021d_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg4() +{ + test_maxgroups_too_low cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl4() +{ + test_maxgroups_too_low ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_cfg6() +{ + test_maxgroups_too_low cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_low_ctl6() +{ + test_maxgroups_too_low ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_entries() +{ + local CFG=$1; shift + local context=$1; shift + local locus=$1; shift + + RET=0 + + local n=$(bridge_${context}_ngroups_get "$locus") + local msg + + # Configure a low maximum + bridge_${context}_maxgroups_set "$locus" $((n+1)) + check_err $? "$locus: Couldn't set maximum" + + # Try to add more entries than the configured maximum + msg=$(${CFG}_entries_add "$locus" temp 5 2>&1) + check_fail $? "Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # When adding entries through the control path, as many as possible + # get created. That's consistent with the mcast_hash_max behavior. + # So there, drop the entries explicitly. + if [[ ${CFG%[46]} == ctl ]]; then + ${CFG}_entries_del "$locus" temp 17 2>&1 + fi + + local n2=$(bridge_${context}_ngroups_get "$locus") + ((n2 == n)) + check_err $? "Number of groups was $n, but after a failed attempt to add MDB entries it changed to $n2" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "$locus: Couldn't set maximum to 0" + + log_test "$CFG: $context maxgroups: add too many MDB entries" +} + +test_8021d_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1" +} + +test_8021d_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1" +} + +test_8021q_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port "dev $swp1 vid 10" +} + +test_8021q_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg4() +{ + test_maxgroups_too_many_entries cfg4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl4() +{ + test_maxgroups_too_many_entries ctl4 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_cfg6() +{ + test_maxgroups_too_many_entries cfg6 port_vlan "dev $swp1 vid 10" +} + +test_8021qvs_maxgroups_too_many_entries_ctl6() +{ + test_maxgroups_too_many_entries ctl6 port_vlan "dev $swp1 vid 10" +} + +test_maxgroups_too_many_cross_vlan() +{ + local CFG=$1; shift + + RET=0 + + local locus0="dev $swp1" + local locus1="dev $swp1 vid 10" + local locus2="dev $swp1 vid 20" + local n1=$(bridge_port_vlan_ngroups_get "$locus1") + local n2=$(bridge_port_vlan_ngroups_get "$locus2") + local msg + + if ((n1 > n2)); then + local tmp=$n1 + n1=$n2 + n2=$tmp + + tmp="$locus1" + locus1="$locus2" + locus2="$tmp" + fi + + # Now 0 <= n1 <= n2. + ${CFG}_entries_add "$locus2" temp 5 112 + check_err $? "Couldn't add 5 entries" + + n2=$(bridge_port_vlan_ngroups_get "$locus2") + # Now 0 <= n1 < n2-1. + + # Setting locus1'maxgroups to n2-1 should pass. The number is + # smaller than both the absolute number of MDB entries, and in + # particular than number of locus2's number of entries, but it is + # large enough to cover locus1's entries. Thus we check that + # individual VLAN's ngroups are independent. + bridge_port_vlan_maxgroups_set "$locus1" $((n2-1)) + check_err $? "Setting ${locus1}'s maxgroups to $((n2-1)) failed" + + msg=$(${CFG}_entries_add "$locus1" temp $n2 111 2>&1) + check_fail $? "$locus1: Adding $n2 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + bridge_port_maxgroups_set "$locus0" $((n1 + n2 + 2)) + check_err $? "$locus0: Couldn't set maximum" + + msg=$(${CFG}_entries_add "$locus1" temp 5 111 2>&1) + check_fail $? "$locus1: Adding 5 MDB entries passed, but should have failed" + bridge_maxgroups_errmsg_check_${CFG} "$msg" + + # IGMP/MLD packets can cause several entries to be added, before + # the maximum is hit and the rest is then bounced. Remove what was + # committed, if anything. + ${CFG}_entries_del "$locus1" temp 5 111 2>/dev/null + + ${CFG}_entries_add "$locus1" temp 2 111 + check_err $? "$locus1: Adding 2 MDB entries failed, but should have passed" + + ${CFG}_entries_del "$locus1" temp 2 111 + check_err $? "Couldn't delete MDB entries" + + ${CFG}_entries_del "$locus2" temp 5 112 + check_err $? "Couldn't delete MDB entries" + + bridge_port_vlan_maxgroups_set "$locus1" 0 + check_err $? "$locus1: Couldn't set maximum to 0" + + bridge_port_maxgroups_set "$locus0" 0 + check_err $? "$locus0: Couldn't set maximum to 0" + + log_test "$CFG: port_vlan maxgroups: isolation of port and per-VLAN ngroups" +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg4() +{ + test_maxgroups_too_many_cross_vlan cfg4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl4() +{ + test_maxgroups_too_many_cross_vlan ctl4 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_cfg6() +{ + test_maxgroups_too_many_cross_vlan cfg6 +} + +test_8021qvs_maxgroups_too_many_cross_vlan_ctl6() +{ + test_maxgroups_too_many_cross_vlan ctl6 +} + +test_vlan_attributes() +{ + local locus=$1; shift + local expect=$1; shift + + RET=0 + + local max=$(bridge_port_vlan_maxgroups_get "$locus") + local n=$(bridge_port_vlan_ngroups_get "$locus") + + eval "[[ $max $expect ]]" + check_err $? "$locus: maxgroups attribute expected to be $expect, but was $max" + + eval "[[ $n $expect ]]" + check_err $? "$locus: ngroups attribute expected to be $expect, but was $n" + + log_test "port_vlan: presence of ngroups and maxgroups attributes" +} + +test_8021q_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "== null" +} + +test_8021qvs_vlan_attributes() +{ + test_vlan_attributes "dev $swp1 vid 10" "-ge 0" +} + +test_toggle_vlan_snooping() +{ + local mode=$1; shift + + RET=0 + + local CFG=cfg4 + local context=port_vlan + local locus="dev $swp1 vid 10" + + ${CFG}_entries_add "$locus" $mode 5 + check_err $? "Couldn't add MDB entries" + + bridge_${context}_maxgroups_set "$locus" 100 + check_err $? "Failed to set max to 100" + + ip link set dev br0 type bridge mcast_vlan_snooping 0 + sleep 1 + ip link set dev br0 type bridge mcast_vlan_snooping 1 + + local n=$(bridge_${context}_ngroups_get "$locus") + local nn=$(bridge mdb show dev br0 | grep $swp1 | wc -l) + ((nn == n)) + check_err $? "mcast_n_groups expected to be $nn, but $n reported" + + local max=$(bridge_${context}_maxgroups_get "$locus") + ((max == 100)) + check_err $? "Max groups expected to be 100 but $max reported" + + bridge_${context}_maxgroups_set "$locus" 0 + check_err $? "Failed to set max to 0" + + log_test "$CFG: $context: $mode: mcast_vlan_snooping toggle" +} + +test_toggle_vlan_snooping_temp() +{ + test_toggle_vlan_snooping temp +} + +test_toggle_vlan_snooping_permanent() +{ + test_toggle_vlan_snooping permanent +} + +# ngroup test suites + +test_8021d_ngroups_cfg4() +{ + test_8021d_ngroups_reporting_cfg4 +} + +test_8021d_ngroups_ctl4() +{ + test_8021d_ngroups_reporting_ctl4 +} + +test_8021d_ngroups_cfg6() +{ + test_8021d_ngroups_reporting_cfg6 +} + +test_8021d_ngroups_ctl6() +{ + test_8021d_ngroups_reporting_ctl6 +} + +test_8021q_ngroups_cfg4() +{ + test_8021q_ngroups_reporting_cfg4 +} + +test_8021q_ngroups_ctl4() +{ + test_8021q_ngroups_reporting_ctl4 +} + +test_8021q_ngroups_cfg6() +{ + test_8021q_ngroups_reporting_cfg6 +} + +test_8021q_ngroups_ctl6() +{ + test_8021q_ngroups_reporting_ctl6 +} + +test_8021qvs_ngroups_cfg4() +{ + test_8021qvs_ngroups_reporting_cfg4 + test_8021qvs_ngroups_cross_vlan_cfg4 +} + +test_8021qvs_ngroups_ctl4() +{ + test_8021qvs_ngroups_reporting_ctl4 + test_8021qvs_ngroups_cross_vlan_ctl4 +} + +test_8021qvs_ngroups_cfg6() +{ + test_8021qvs_ngroups_reporting_cfg6 + test_8021qvs_ngroups_cross_vlan_cfg6 +} + +test_8021qvs_ngroups_ctl6() +{ + test_8021qvs_ngroups_reporting_ctl6 + test_8021qvs_ngroups_cross_vlan_ctl6 +} + +# maxgroups test suites + +test_8021d_maxgroups_cfg4() +{ + test_8021d_maxgroups_zero_cfg4 + test_8021d_maxgroups_too_low_cfg4 + test_8021d_maxgroups_too_many_entries_cfg4 +} + +test_8021d_maxgroups_ctl4() +{ + test_8021d_maxgroups_zero_ctl4 + test_8021d_maxgroups_too_low_ctl4 + test_8021d_maxgroups_too_many_entries_ctl4 +} + +test_8021d_maxgroups_cfg6() +{ + test_8021d_maxgroups_zero_cfg6 + test_8021d_maxgroups_too_low_cfg6 + test_8021d_maxgroups_too_many_entries_cfg6 +} + +test_8021d_maxgroups_ctl6() +{ + test_8021d_maxgroups_zero_ctl6 + test_8021d_maxgroups_too_low_ctl6 + test_8021d_maxgroups_too_many_entries_ctl6 +} + +test_8021q_maxgroups_cfg4() +{ + test_8021q_maxgroups_zero_cfg4 + test_8021q_maxgroups_too_low_cfg4 + test_8021q_maxgroups_too_many_entries_cfg4 +} + +test_8021q_maxgroups_ctl4() +{ + test_8021q_maxgroups_zero_ctl4 + test_8021q_maxgroups_too_low_ctl4 + test_8021q_maxgroups_too_many_entries_ctl4 +} + +test_8021q_maxgroups_cfg6() +{ + test_8021q_maxgroups_zero_cfg6 + test_8021q_maxgroups_too_low_cfg6 + test_8021q_maxgroups_too_many_entries_cfg6 +} + +test_8021q_maxgroups_ctl6() +{ + test_8021q_maxgroups_zero_ctl6 + test_8021q_maxgroups_too_low_ctl6 + test_8021q_maxgroups_too_many_entries_ctl6 +} + +test_8021qvs_maxgroups_cfg4() +{ + test_8021qvs_maxgroups_zero_cfg4 + test_8021qvs_maxgroups_zero_cross_vlan_cfg4 + test_8021qvs_maxgroups_too_low_cfg4 + test_8021qvs_maxgroups_too_many_entries_cfg4 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg4 +} + +test_8021qvs_maxgroups_ctl4() +{ + test_8021qvs_maxgroups_zero_ctl4 + test_8021qvs_maxgroups_zero_cross_vlan_ctl4 + test_8021qvs_maxgroups_too_low_ctl4 + test_8021qvs_maxgroups_too_many_entries_ctl4 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl4 +} + +test_8021qvs_maxgroups_cfg6() +{ + test_8021qvs_maxgroups_zero_cfg6 + test_8021qvs_maxgroups_zero_cross_vlan_cfg6 + test_8021qvs_maxgroups_too_low_cfg6 + test_8021qvs_maxgroups_too_many_entries_cfg6 + test_8021qvs_maxgroups_too_many_cross_vlan_cfg6 +} + +test_8021qvs_maxgroups_ctl6() +{ + test_8021qvs_maxgroups_zero_ctl6 + test_8021qvs_maxgroups_zero_cross_vlan_ctl6 + test_8021qvs_maxgroups_too_low_ctl6 + test_8021qvs_maxgroups_too_many_entries_ctl6 + test_8021qvs_maxgroups_too_many_cross_vlan_ctl6 +} + +# other test suites + +test_8021qvs_toggle_vlan_snooping() +{ + test_toggle_vlan_snooping_temp + test_toggle_vlan_snooping_permanent +} + +# test groups + +test_8021d() +{ + # Tests for vlan_filtering 0 mcast_vlan_snooping 0. + + switch_create_8021d + setup_wait + + test_8021d_ngroups_cfg4 + test_8021d_ngroups_ctl4 + test_8021d_ngroups_cfg6 + test_8021d_ngroups_ctl6 + test_8021d_maxgroups_cfg4 + test_8021d_maxgroups_ctl4 + test_8021d_maxgroups_cfg6 + test_8021d_maxgroups_ctl6 + + switch_destroy +} + +test_8021q() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 0. + + switch_create_8021q + setup_wait + + test_8021q_vlan_attributes + test_8021q_ngroups_cfg4 + test_8021q_ngroups_ctl4 + test_8021q_ngroups_cfg6 + test_8021q_ngroups_ctl6 + test_8021q_maxgroups_cfg4 + test_8021q_maxgroups_ctl4 + test_8021q_maxgroups_cfg6 + test_8021q_maxgroups_ctl6 + + switch_destroy +} + +test_8021qvs() +{ + # Tests for vlan_filtering 1 mcast_vlan_snooping 1. + + switch_create_8021qvs + setup_wait + + test_8021qvs_vlan_attributes + test_8021qvs_ngroups_cfg4 + test_8021qvs_ngroups_ctl4 + test_8021qvs_ngroups_cfg6 + test_8021qvs_ngroups_ctl6 + test_8021qvs_maxgroups_cfg4 + test_8021qvs_maxgroups_ctl4 + test_8021qvs_maxgroups_cfg6 + test_8021qvs_maxgroups_ctl6 + test_8021qvs_toggle_vlan_snooping + + switch_destroy +} + +trap cleanup EXIT + +setup_prepare +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 29cd4705c752..d47499ba81c7 100755 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -893,14 +893,14 @@ sysctl_set() local value=$1; shift SYSCTL_ORIG[$key]=$(sysctl -n $key) - sysctl -qw $key=$value + sysctl -qw $key="$value" } sysctl_restore() { local key=$1; shift - sysctl -qw $key=${SYSCTL_ORIG["$key"]} + sysctl -qw $key="${SYSCTL_ORIG[$key]}" } forwarding_enable() @@ -1671,3 +1671,219 @@ hw_stats_monitor_test() log_test "${type}_stats notifications" } + +ipv4_to_bytes() +{ + local IP=$1; shift + + printf '%02x:' ${IP//./ } | + sed 's/:$//' +} + +# Convert a given IPv6 address, `IP' such that the :: token, if present, is +# expanded, and each 16-bit group is padded with zeroes to be 4 hexadecimal +# digits. An optional `BYTESEP' parameter can be given to further separate +# individual bytes of each 16-bit group. +expand_ipv6() +{ + local IP=$1; shift + local bytesep=$1; shift + + local cvt_ip=${IP/::/_} + local colons=${cvt_ip//[^:]/} + local allcol=::::::: + # IP where :: -> the appropriate number of colons: + local allcol_ip=${cvt_ip/_/${allcol:${#colons}}} + + echo $allcol_ip | tr : '\n' | + sed s/^/0000/ | + sed 's/.*\(..\)\(..\)/\1'"$bytesep"'\2/' | + tr '\n' : | + sed 's/:$//' +} + +ipv6_to_bytes() +{ + local IP=$1; shift + + expand_ipv6 "$IP" : +} + +u16_to_bytes() +{ + local u16=$1; shift + + printf "%04x" $u16 | sed 's/^/000/;s/^.*\(..\)\(..\)$/\1:\2/' +} + +# Given a mausezahn-formatted payload (colon-separated bytes given as %02x), +# possibly with a keyword CHECKSUM stashed where a 16-bit checksum should be, +# calculate checksum as per RFC 1071, assuming the CHECKSUM field (if any) +# stands for 00:00. +payload_template_calc_checksum() +{ + local payload=$1; shift + + ( + # Set input radix. + echo "16i" + # Push zero for the initial checksum. + echo 0 + + # Pad the payload with a terminating 00: in case we get an odd + # number of bytes. + echo "${payload%:}:00:" | + sed 's/CHECKSUM/00:00/g' | + tr '[:lower:]' '[:upper:]' | + # Add the word to the checksum. + sed 's/\(..\):\(..\):/\1\2+\n/g' | + # Strip the extra odd byte we pushed if left unconverted. + sed 's/\(..\):$//' + + echo "10000 ~ +" # Calculate and add carry. + echo "FFFF r - p" # Bit-flip and print. + ) | + dc | + tr '[:upper:]' '[:lower:]' +} + +payload_template_expand_checksum() +{ + local payload=$1; shift + local checksum=$1; shift + + local ckbytes=$(u16_to_bytes $checksum) + + echo "$payload" | sed "s/CHECKSUM/$ckbytes/g" +} + +payload_template_nbytes() +{ + local payload=$1; shift + + payload_template_expand_checksum "${payload%:}" 0 | + sed 's/:/\n/g' | wc -l +} + +igmpv3_is_in_get() +{ + local GRP=$1; shift + local sources=("$@") + + local igmpv3 + local nsources=$(u16_to_bytes ${#sources[@]}) + + # IS_IN ( $sources ) + igmpv3=$(: + )"22:"$( : Type - Membership Report + )"00:"$( : Reserved + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv4_to_bytes $GRP):"$( : Multicast Address + )"$(for src in "${sources[@]}"; do + ipv4_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + local checksum=$(payload_template_calc_checksum "$igmpv3") + + payload_template_expand_checksum "$igmpv3" $checksum +} + +igmpv2_leave_get() +{ + local GRP=$1; shift + + local payload=$(: + )"17:"$( : Type - Leave Group + )"00:"$( : Max Resp Time - not meaningful + )"CHECKSUM:"$( : Checksum + )"$(ipv4_to_bytes $GRP)"$( : Group Address + ) + local checksum=$(payload_template_calc_checksum "$payload") + + payload_template_expand_checksum "$payload" $checksum +} + +mldv2_is_in_get() +{ + local SIP=$1; shift + local GRP=$1; shift + local sources=("$@") + + local hbh + local icmpv6 + local nsources=$(u16_to_bytes ${#sources[@]}) + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"8f:"$( : Type - MLDv2 Report + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Reserved + )"00:01:"$( : Number of Group Records + )"01:"$( : Record Type - IS_IN + )"00:"$( : Aux Data Len + )"${nsources}:"$( : Number of Sources + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + )"$(for src in "${sources[@]}"; do + ipv6_to_bytes $src + echo -n : + done)"$( : Source Addresses + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} + +mldv1_done_get() +{ + local SIP=$1; shift + local GRP=$1; shift + + local hbh + local icmpv6 + + hbh=$(: + )"3a:"$( : Next Header - ICMPv6 + )"00:"$( : Hdr Ext Len + )"00:00:00:00:00:00:"$( : Options and Padding + ) + + icmpv6=$(: + )"84:"$( : Type - MLDv1 Done + )"00:"$( : Code + )"CHECKSUM:"$( : Checksum + )"00:00:"$( : Max Resp Delay - not meaningful + )"00:00:"$( : Reserved + )"$(ipv6_to_bytes $GRP):"$( : Multicast address + ) + + local len=$(u16_to_bytes $(payload_template_nbytes $icmpv6)) + local sudohdr=$(: + )"$(ipv6_to_bytes $SIP):"$( : SIP + )"$(ipv6_to_bytes $GRP):"$( : DIP is multicast address + )"${len}:"$( : Upper-layer length + )"00:3a:"$( : Zero and next-header + ) + local checksum=$(payload_template_calc_checksum ${sudohdr}${icmpv6}) + + payload_template_expand_checksum "$hbh$icmpv6" $checksum +} diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 387abdcec011..42e3bd1a05f5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -498,6 +498,12 @@ kill_events_pids() kill_wait $evts_ns2_pid } +kill_tests_wait() +{ + kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1) + wait +} + pm_nl_set_limits() { local ns=$1 @@ -1687,6 +1693,7 @@ chk_subflow_nr() local subflow_nr=$3 local cnt1 local cnt2 + local dump_stats if [ -n "${need_title}" ]; then printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" @@ -1704,7 +1711,12 @@ chk_subflow_nr() echo "[ ok ]" fi - [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint ) + if [ "${dump_stats}" = 1 ]; then + ss -N $ns1 -tOni + ss -N $ns1 -tOni | grep token + ip -n $ns1 mptcp endpoint + dump_stats + fi } chk_link_usage() @@ -3083,7 +3095,7 @@ endpoint_tests() pm_nl_set_limits $ns1 2 2 pm_nl_set_limits $ns2 2 2 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow 2>/dev/null & wait_mpj $ns1 pm_nl_check_endpoint 1 "creation" \ @@ -3096,14 +3108,14 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 flags signal pm_nl_check_endpoint 0 "modif is allowed" \ $ns2 10.0.2.2 id 1 flags signal - wait + kill_tests_wait fi if reset "delete and re-add"; then pm_nl_set_limits $ns1 1 1 pm_nl_set_limits $ns2 1 1 pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow & + run_tests $ns1 $ns2 10.0.1.1 4 0 0 speed_20 2>/dev/null & wait_mpj $ns2 pm_nl_del_endpoint $ns2 2 10.0.2.2 @@ -3113,7 +3125,7 @@ endpoint_tests() pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow wait_mpj $ns2 chk_subflow_nr "" "after re-add" 2 - wait + kill_tests_wait fi } diff --git a/tools/testing/selftests/net/rps_default_mask.sh b/tools/testing/selftests/net/rps_default_mask.sh new file mode 100755 index 000000000000..c81c0ac7ddfe --- /dev/null +++ b/tools/testing/selftests/net/rps_default_mask.sh @@ -0,0 +1,57 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +readonly ksft_skip=4 +readonly cpus=$(nproc) +ret=0 + +[ $cpus -gt 2 ] || exit $ksft_skip + +readonly INITIAL_RPS_DEFAULT_MASK=$(cat /proc/sys/net/core/rps_default_mask) +readonly NETNS="ns-$(mktemp -u XXXXXX)" + +setup() { + ip netns add "${NETNS}" + ip -netns "${NETNS}" link set lo up +} + +cleanup() { + echo $INITIAL_RPS_DEFAULT_MASK > /proc/sys/net/core/rps_default_mask + ip netns del $NETNS +} + +chk_rps() { + local rps_mask expected_rps_mask=$3 + local dev_name=$2 + local msg=$1 + + rps_mask=$(ip netns exec $NETNS cat /sys/class/net/$dev_name/queues/rx-0/rps_cpus) + printf "%-60s" "$msg" + if [ $rps_mask -eq $expected_rps_mask ]; then + echo "[ ok ]" + else + echo "[fail] expected $expected_rps_mask found $rps_mask" + ret=1 + fi +} + +trap cleanup EXIT + +echo 0 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "empty rps_default_mask" lo 0 +cleanup + +echo 1 > /proc/sys/net/core/rps_default_mask +setup +chk_rps "non zero rps_default_mask" lo 1 + +echo 3 > /proc/sys/net/core/rps_default_mask +chk_rps "changing rps_default_mask dont affect existing netns" lo 1 + +ip -n $NETNS link add type veth +ip -n $NETNS link set dev veth0 up +ip -n $NETNS link set dev veth1 up +chk_rps "changing rps_default_mask affect newly created devices" veth0 3 +chk_rps "changing rps_default_mask affect newly created devices[II]" veth1 3 +exit $ret diff --git a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh index 704997ffc244..8c3ac0a72545 100755 --- a/tools/testing/selftests/net/test_vxlan_vnifiltering.sh +++ b/tools/testing/selftests/net/test_vxlan_vnifiltering.sh @@ -293,19 +293,11 @@ setup-vm() { elif [[ -n $vtype && $vtype == "vnifilterg" ]]; then # Add per vni group config with 'bridge vni' api if [ -n "$group" ]; then - if [ "$family" == "v4" ]; then - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group - fi - else - if [ $mcast -eq 1 ]; then - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group6 $group - else - bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote6 $group - fi - fi + if [ $mcast -eq 1 ]; then + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid group $group + else + bridge -netns hv-$hvid vni add dev $vxlandev vni $tid remote $group + fi fi fi done diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c index a634f47d1e56..9a127a8fe176 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -17,7 +17,6 @@ #include <stdio.h> #include <unistd.h> #include <sys/mman.h> -#define __USE_GNU #include <fcntl.h> #define MIN_FREE_PAGES 20 |