Merge tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Remove socket skb caches

   - Add a SO_RESERVE_MEM socket op to forward allocate buffer space and
     avoid memory accounting overhead on each message sent

   - Introduce managed neighbor entries - added by control plane and
     resolved by the kernel for use in acceleration paths (BPF / XDP
     right now, HW offload users will benefit as well)

   - Make neighbor eviction on link down controllable by userspace to
     work around WiFi networks with bad roaming implementations

   - vrf: Rework interaction with netfilter/conntrack

   - fq_codel: implement L4S style ce_threshold_ect1 marking

   - sch: Eliminate unnecessary RCU waits in mini_qdisc_pair_swap()

  BPF:

   - Add support for new btf kind BTF_KIND_TAG, arbitrary type tagging
     as implemented in LLVM14

   - Introduce bpf_get_branch_snapshot() to capture Last Branch Records

   - Implement variadic trace_printk helper

   - Add a new Bloomfilter map type

   - Track <8-byte scalar spill and refill

   - Access hw timestamp through BPF's __sk_buff

   - Disallow unprivileged BPF by default

   - Document BPF licensing

  Netfilter:

   - Introduce egress hook for looking at raw outgoing packets

   - Allow matching on and modifying inner headers / payload data

   - Add NFT_META_IFTYPE to match on the interface type either from
     ingress or egress

  Protocols:

   - Multi-Path TCP:
      - increase default max additional subflows to 2
      - rework forward memory allocation
      - add getsockopts: MPTCP_INFO, MPTCP_TCPINFO, MPTCP_SUBFLOW_ADDRS

   - MCTP flow support allowing lower layer drivers to configure msg
     muxing as needed

   - Automatic Multicast Tunneling (AMT) driver based on RFC7450

   - HSR support the redbox supervision frames (IEC-62439-3:2018)

   - Support for the ip6ip6 encapsulation of IOAM

   - Netlink interface for CAN-FD's Transmitter Delay Compensation

   - Support SMC-Rv2 eliminating the current same-subnet restriction, by
     exploiting the UDP encapsulation feature of RoCE adapters

   - TLS: add SM4 GCM/CCM crypto support

   - Bluetooth: initial support for link quality and audio/codec offload

  Driver APIs:

   - Add a batched interface for RX buffer allocation in AF_XDP buffer
     pool

   - ethtool: Add ability to control transceiver modules' power mode

   - phy: Introduce supported interfaces bitmap to express MAC
     capabilities and simplify PHY code

   - Drop rtnl_lock from DSA .port_fdb_{add,del} callbacks

  New drivers:

   - WiFi driver for Realtek 8852AE 802.11ax devices (rtw89)

   - Ethernet driver for ASIX AX88796C SPI device (x88796c)

  Drivers:

   - Broadcom PHYs
      - support 72165, 7712 16nm PHYs
      - support IDDQ-SR for additional power savings

   - PHY support for QCA8081, QCA9561 PHYs

   - NXP DPAA2: support for IRQ coalescing

   - NXP Ethernet (enetc): support for software TCP segmentation

   - Renesas Ethernet (ravb) - support DMAC and EMAC blocks of
     Gigabit-capable IP found on RZ/G2L SoC

   - Intel 100G Ethernet
      - support for eswitch offload of TC/OvS flow API, including
        offload of GRE, VxLAN, Geneve tunneling
      - support application device queues - ability to assign Rx and Tx
        queues to application threads
      - PTP and PPS (pulse-per-second) extensions

   - Broadcom Ethernet (bnxt)
      - devlink health reporting and device reload extensions

   - Mellanox Ethernet (mlx5)
      - offload macvlan interfaces
      - support HW offload of TC rules involving OVS internal ports
      - support HW-GRO and header/data split
      - support application device queues

   - Marvell OcteonTx2:
      - add XDP support for PF
      - add PTP support for VF

   - Qualcomm Ethernet switch (qca8k): support for QCA8328

   - Realtek Ethernet DSA switch (rtl8366rb)
      - support bridge offload
      - support STP, fast aging, disabling address learning
      - support for Realtek RTL8365MB-VC, a 4+1 port 10M/100M/1GE switch

   - Mellanox Ethernet/IB switch (mlxsw)
      - multi-level qdisc hierarchy offload (e.g. RED, prio and shaping)
      - offload root TBF qdisc as port shaper
      - support multiple routing interface MAC address prefixes
      - support for IP-in-IP with IPv6 underlay

   - MediaTek WiFi (mt76)
      - mt7921 - ASPM, 6GHz, SDIO and testmode support
      - mt7915 - LED and TWT support

   - Qualcomm WiFi (ath11k)
      - include channel rx and tx time in survey dump statistics
      - support for 80P80 and 160 MHz bandwidths
      - support channel 2 in 6 GHz band
      - spectral scan support for QCN9074
      - support for rx decapsulation offload (data frames in 802.3
        format)

   - Qualcomm phone SoC WiFi (wcn36xx)
      - enable Idle Mode Power Save (IMPS) to reduce power consumption
        during idle

   - Bluetooth driver support for MediaTek MT7922 and MT7921

   - Enable support for AOSP Bluetooth extension in Qualcomm WCN399x and
     Realtek 8822C/8852A

   - Microsoft vNIC driver (mana)
      - support hibernation and kexec

   - Google vNIC driver (gve)
      - support for jumbo frames
      - implement Rx page reuse

  Refactor:

   - Make all writes to netdev->dev_addr go thru helpers, so that we can
     add this address to the address rbtree and handle the updates

   - Various TCP cleanups and optimizations including improvements to
     CPU cache use

   - Simplify the gnet_stats, Qdisc stats' handling and remove
     qdisc->running sequence counter

   - Driver changes and API updates to address devlink locking
     deficiencies"

* tag 'net-next-for-5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2122 commits)
  Revert "net: avoid double accounting for pure zerocopy skbs"
  selftests: net: add arp_ndisc_evict_nocarrier
  net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter
  net: arp: introduce arp_evict_nocarrier sysctl parameter
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  net: vmxnet3: remove multiple false checks in vmxnet3_ethtool.c
  net: avoid double accounting for pure zerocopy skbs
  tcp: rename sk_wmem_free_skb
  netdevsim: fix uninit value in nsim_drv_configure_vfs()
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  ...

1 files changed, 200 insertions, 0 deletions

diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
new file mode 100644
index 000000000000..fbc896323bec
--- /dev/null
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021. Huawei Technologies Co., Ltd
+ */
+#include <linux/kernel.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf.h>
+#include <linux/btf.h>
+
+extern struct bpf_struct_ops bpf_bpf_dummy_ops;
+
+/* A common type for test_N with return value in bpf_dummy_ops */
+typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...);
+
+struct bpf_dummy_ops_test_args {
+	u64 args[MAX_BPF_FUNC_ARGS];
+	struct bpf_dummy_ops_state state;
+};
+
+static struct bpf_dummy_ops_test_args *
+dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr)
+{
+	__u32 size_in;
+	struct bpf_dummy_ops_test_args *args;
+	void __user *ctx_in;
+	void __user *u_state;
+
+	size_in = kattr->test.ctx_size_in;
+	if (size_in != sizeof(u64) * nr)
+		return ERR_PTR(-EINVAL);
+
+	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	if (!args)
+		return ERR_PTR(-ENOMEM);
+
+	ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	if (copy_from_user(args->args, ctx_in, size_in))
+		goto out;
+
+	/* args[0] is 0 means state argument of test_N will be NULL */
+	u_state = u64_to_user_ptr(args->args[0]);
+	if (u_state && copy_from_user(&args->state, u_state,
+				      sizeof(args->state)))
+		goto out;
+
+	return args;
+out:
+	kfree(args);
+	return ERR_PTR(-EFAULT);
+}
+
+static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args)
+{
+	void __user *u_state;
+
+	u_state = u64_to_user_ptr(args->args[0]);
+	if (u_state && copy_to_user(u_state, &args->state, sizeof(args->state)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args)
+{
+	dummy_ops_test_ret_fn test = (void *)image;
+	struct bpf_dummy_ops_state *state = NULL;
+
+	/* state needs to be NULL if args[0] is 0 */
+	if (args->args[0])
+		state = &args->state;
+	return test(state, args->args[1], args->args[2],
+		    args->args[3], args->args[4]);
+}
+
+int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
+			    union bpf_attr __user *uattr)
+{
+	const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops;
+	const struct btf_type *func_proto;
+	struct bpf_dummy_ops_test_args *args;
+	struct bpf_tramp_progs *tprogs;
+	void *image = NULL;
+	unsigned int op_idx;
+	int prog_ret;
+	int err;
+
+	if (prog->aux->attach_btf_id != st_ops->type_id)
+		return -EOPNOTSUPP;
+
+	func_proto = prog->aux->attach_func_proto;
+	args = dummy_ops_init_args(kattr, btf_type_vlen(func_proto));
+	if (IS_ERR(args))
+		return PTR_ERR(args);
+
+	tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL);
+	if (!tprogs) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	image = bpf_jit_alloc_exec(PAGE_SIZE);
+	if (!image) {
+		err = -ENOMEM;
+		goto out;
+	}
+	set_vm_flush_reset_perms(image);
+
+	op_idx = prog->expected_attach_type;
+	err = bpf_struct_ops_prepare_trampoline(tprogs, prog,
+						&st_ops->func_models[op_idx],
+						image, image + PAGE_SIZE);
+	if (err < 0)
+		goto out;
+
+	set_memory_ro((long)image, 1);
+	set_memory_x((long)image, 1);
+	prog_ret = dummy_ops_call_op(image, args);
+
+	err = dummy_ops_copy_args(args);
+	if (err)
+		goto out;
+	if (put_user(prog_ret, &uattr->test.retval))
+		err = -EFAULT;
+out:
+	kfree(args);
+	bpf_jit_free_exec(image);
+	kfree(tprogs);
+	return err;
+}
+
+static int bpf_dummy_init(struct btf *btf)
+{
+	return 0;
+}
+
+static bool bpf_dummy_ops_is_valid_access(int off, int size,
+					  enum bpf_access_type type,
+					  const struct bpf_prog *prog,
+					  struct bpf_insn_access_aux *info)
+{
+	return bpf_tracing_btf_ctx_access(off, size, type, prog, info);
+}
+
+static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log,
+					   const struct btf *btf,
+					   const struct btf_type *t, int off,
+					   int size, enum bpf_access_type atype,
+					   u32 *next_btf_id)
+{
+	const struct btf_type *state;
+	s32 type_id;
+	int err;
+
+	type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state",
+					BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return -EINVAL;
+
+	state = btf_type_by_id(btf, type_id);
+	if (t != state) {
+		bpf_log(log, "only access to bpf_dummy_ops_state is supported\n");
+		return -EACCES;
+	}
+
+	err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id);
+	if (err < 0)
+		return err;
+
+	return atype == BPF_READ ? err : NOT_INIT;
+}
+
+static const struct bpf_verifier_ops bpf_dummy_verifier_ops = {
+	.is_valid_access = bpf_dummy_ops_is_valid_access,
+	.btf_struct_access = bpf_dummy_ops_btf_struct_access,
+};
+
+static int bpf_dummy_init_member(const struct btf_type *t,
+				 const struct btf_member *member,
+				 void *kdata, const void *udata)
+{
+	return -EOPNOTSUPP;
+}
+
+static int bpf_dummy_reg(void *kdata)
+{
+	return -EOPNOTSUPP;
+}
+
+static void bpf_dummy_unreg(void *kdata)
+{
+}
+
+struct bpf_struct_ops bpf_bpf_dummy_ops = {
+	.verifier_ops = &bpf_dummy_verifier_ops,
+	.init = bpf_dummy_init,
+	.init_member = bpf_dummy_init_member,
+	.reg = bpf_dummy_reg,
+	.unreg = bpf_dummy_unreg,
+	.name = "bpf_dummy_ops",
+};