diff options
Diffstat (limited to 'include/linux')
59 files changed, 1851 insertions, 492 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5ff5d99f6ead..fbf0c3a65f59 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -8,6 +8,7 @@ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H +#include <linux/cleanup.h> #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/resource_ext.h> @@ -221,6 +222,17 @@ void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); +static inline struct acpi_table_header *acpi_get_table_pointer(char *signature, u32 instance) +{ + struct acpi_table_header *table; + int status = acpi_get_table(signature, instance, &table); + + if (ACPI_FAILURE(status)) + return ERR_PTR(-ENOENT); + return table; +} +DEFINE_FREE(acpi_put_table, struct acpi_table_header *, if (!IS_ERR_OR_NULL(_T)) acpi_put_table(_T)) + int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init_or_acpilib acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, @@ -755,7 +767,6 @@ int acpi_reconfig_notifier_unregister(struct notifier_block *nb); int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); -int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER @@ -1146,12 +1157,7 @@ struct acpi_s2idle_dev_ops { #if defined(CONFIG_SUSPEND) && defined(CONFIG_X86) int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); -int acpi_get_lps0_constraint(struct acpi_device *adev); #else /* CONFIG_SUSPEND && CONFIG_X86 */ -static inline int acpi_get_lps0_constraint(struct device *dev) -{ - return ACPI_STATE_UNKNOWN; -} static inline int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg) { return -ENODEV; @@ -1349,9 +1355,6 @@ acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); -struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, - struct fwnode_handle *child); - struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); @@ -1451,13 +1454,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, } static inline struct fwnode_handle * -acpi_get_next_subnode(const struct fwnode_handle *fwnode, - struct fwnode_handle *child) -{ - return NULL; -} - -static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { @@ -1509,12 +1505,19 @@ static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); +const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, + unsigned int index); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } +static inline const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, + unsigned int index) +{ + return NULL; +} #endif #ifdef CONFIG_ACPI_LPIT @@ -1541,6 +1544,9 @@ int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); +void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, cpumask_t *cpus); +int find_acpi_cache_level_from_id(u32 cache_id); +int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id, cpumask_t *cpus); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { @@ -1562,6 +1568,17 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } +static inline void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, + cpumask_t *cpus) { } +static inline int find_acpi_cache_level_from_id(u32 cache_id) +{ + return -ENOENT; +} +static inline int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id, + cpumask_t *cpus) +{ + return -ENOENT; +} #endif void acpi_arch_init(void); diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index d72d6e5aa200..0c2a8b846c20 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -89,6 +89,21 @@ void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); int parse_acpi_topology(void); void freq_inv_set_max_ratio(int cpu, u64 max_rate); -#endif + +/* + * Architectures like ARM64 don't have reliable architectural way to get SMT + * information and depend on the firmware (ACPI/OF) report. Non-SMT core won't + * initialize thread_id so we can use this to detect the SMT implementation. + */ +static inline bool topology_core_has_smt(int cpu) +{ + return cpu_topology[cpu].thread_id != -1; +} + +#else + +static inline bool topology_core_has_smt(int cpu) { return false; } + +#endif /* CONFIG_GENERIC_ARCH_TOPOLOGY */ #endif /* _LINUX_ARCH_TOPOLOGY_H_ */ diff --git a/include/linux/arm_mpam.h b/include/linux/arm_mpam.h new file mode 100644 index 000000000000..7f00c5285a32 --- /dev/null +++ b/include/linux/arm_mpam.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2025 Arm Ltd. */ + +#ifndef __LINUX_ARM_MPAM_H +#define __LINUX_ARM_MPAM_H + +#include <linux/acpi.h> +#include <linux/types.h> + +struct mpam_msc; + +enum mpam_msc_iface { + MPAM_IFACE_MMIO, /* a real MPAM MSC */ + MPAM_IFACE_PCC, /* a fake MPAM MSC */ +}; + +enum mpam_class_types { + MPAM_CLASS_CACHE, /* Caches, e.g. L2, L3 */ + MPAM_CLASS_MEMORY, /* Main memory */ + MPAM_CLASS_UNKNOWN, /* Everything else, e.g. SMMU */ +}; + +#define MPAM_CLASS_ID_DEFAULT 255 + +#ifdef CONFIG_ACPI_MPAM +int acpi_mpam_parse_resources(struct mpam_msc *msc, + struct acpi_mpam_msc_node *tbl_msc); + +int acpi_mpam_count_msc(void); +#else +static inline int acpi_mpam_parse_resources(struct mpam_msc *msc, + struct acpi_mpam_msc_node *tbl_msc) +{ + return -EINVAL; +} + +static inline int acpi_mpam_count_msc(void) { return -EINVAL; } +#endif + +#ifdef CONFIG_ARM64_MPAM_DRIVER +int mpam_ris_create(struct mpam_msc *msc, u8 ris_idx, + enum mpam_class_types type, u8 class_id, int component_id); +#else +static inline int mpam_ris_create(struct mpam_msc *msc, u8 ris_idx, + enum mpam_class_types type, u8 class_id, + int component_id) +{ + return -EINVAL; +} +#endif + +/** + * mpam_register_requestor() - Register a requestor with the MPAM driver + * @partid_max: The maximum PARTID value the requestor can generate. + * @pmg_max: The maximum PMG value the requestor can generate. + * + * Registers a requestor with the MPAM driver to ensure the chosen system-wide + * minimum PARTID and PMG values will allow the requestors features to be used. + * + * Returns an error if the registration is too late, and a larger PARTID/PMG + * value has been advertised to user-space. In this case the requestor should + * not use its MPAM features. Returns 0 on success. + */ +int mpam_register_requestor(u16 partid_max, u8 pmg_max); + +#endif /* __LINUX_ARM_MPAM_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 595217b7a6e7..b0395e4ccf90 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -45,6 +45,7 @@ struct device; * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 + * bitmap_weighted_or(dst, src1, src2, nbits) *dst = *src1 | *src2. Returns Hamming Weight of dst * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) @@ -165,6 +166,8 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, @@ -338,6 +341,18 @@ void bitmap_or(unsigned long *dst, const unsigned long *src1, } static __always_inline +unsigned int bitmap_weighted_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) { + *dst = *src1 | *src2; + return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits)); + } else { + return __bitmap_weighted_or(dst, src1, src2, nbits); + } +} + +static __always_inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { diff --git a/include/linux/bug.h b/include/linux/bug.h index a9948a9f1093..17a4933c611b 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -42,6 +42,7 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); +enum bug_trap_type report_bug_entry(struct bug_entry *bug, struct pt_regs *regs); /* These are defined by the architecture */ int is_valid_bugaddr(unsigned long addr); @@ -62,6 +63,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, } struct bug_entry; + +static inline enum bug_trap_type +report_bug_entry(struct bug_entry *bug, struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_BUG; +} + static inline void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index b3705e8bbe2b..55a44199de87 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -173,6 +173,22 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words) } } +static inline void le64_to_cpu_array(u64 *buf, unsigned int words) +{ + while (words--) { + __le64_to_cpus(buf); + buf++; + } +} + +static inline void cpu_to_le64_array(u64 *buf, unsigned int words) +{ + while (words--) { + __cpu_to_le64s(buf); + buf++; + } +} + static inline void memcpy_from_le32(u32 *dst, const __le32 *src, size_t words) { size_t i; diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 7fcec025c5e0..559353ad64ac 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -74,7 +74,7 @@ enum cc_attr { CC_ATTR_GUEST_UNROLL_STRING_IO, /** - * @CC_ATTR_SEV_SNP: Guest SNP is active. + * @CC_ATTR_GUEST_SEV_SNP: Guest SNP is active. * * The platform/OS is running as a guest/virtual machine and actively * using AMD SEV-SNP features. diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index bacefa0f1512..0b55a8f6c59e 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -208,7 +208,7 @@ */ #define DEFINE_FREE(_name, _type, _free) \ - static inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } + static __always_inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } #define __free(_name) __cleanup(__free_##_name) @@ -220,7 +220,7 @@ __val; \ }) -static inline __must_check +static __always_inline __must_check const volatile void * __must_check_fn(const volatile void *val) { return val; } @@ -278,16 +278,16 @@ const volatile void * __must_check_fn(const volatile void *val) #define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...) \ typedef _type class_##_name##_t; \ -static inline void class_##_name##_destructor(_type *p) \ +static __always_inline void class_##_name##_destructor(_type *p) \ { _type _T = *p; _exit; } \ -static inline _type class_##_name##_constructor(_init_args) \ +static __always_inline _type class_##_name##_constructor(_init_args) \ { _type t = _init; return t; } #define EXTEND_CLASS(_name, ext, _init, _init_args...) \ typedef class_##_name##_t class_##_name##ext##_t; \ -static inline void class_##_name##ext##_destructor(class_##_name##_t *p)\ +static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *p) \ { class_##_name##_destructor(p); } \ -static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ +static __always_inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ { class_##_name##_t t = _init; return t; } #define CLASS(_name, var) \ @@ -360,7 +360,7 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond }) #define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ - static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ { \ void *_ptr = (void *)(__force unsigned long)*(_exp); \ if (IS_ERR(_ptr)) { \ @@ -368,7 +368,7 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond } \ return _ptr; \ } \ - static inline int class_##_name##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_lock_err(class_##_name##_t *_T) \ { \ long _rc = (__force unsigned long)*(_exp); \ if (!_rc) { \ @@ -397,9 +397,9 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond EXTEND_CLASS(_name, _ext, \ ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \ class_##_name##_t _T) \ - static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ { return class_##_name##_lock_ptr(_T); } \ - static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ { return class_##_name##_lock_err(_T); } /* @@ -479,7 +479,7 @@ typedef struct { \ __VA_ARGS__; \ } class_##_name##_t; \ \ -static inline void class_##_name##_destructor(class_##_name##_t *_T) \ +static __always_inline void class_##_name##_destructor(class_##_name##_t *_T) \ { \ if (!__GUARD_IS_ERR(_T->lock)) { _unlock; } \ } \ @@ -487,7 +487,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock) #define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ -static inline class_##_name##_t class_##_name##_constructor(_type *l) \ +static __always_inline class_##_name##_t class_##_name##_constructor(_type *l) \ { \ class_##_name##_t _t = { .lock = l }, *_T = &_t; \ _lock; \ @@ -495,7 +495,7 @@ static inline class_##_name##_t class_##_name##_constructor(_type *l) \ } #define __DEFINE_LOCK_GUARD_0(_name, _lock) \ -static inline class_##_name##_t class_##_name##_constructor(void) \ +static __always_inline class_##_name##_t class_##_name##_constructor(void) \ { \ class_##_name##_t _t = { .lock = (void*)1 }, \ *_T __maybe_unused = &_t; \ @@ -521,9 +521,9 @@ __DEFINE_LOCK_GUARD_0(_name, _lock) if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\ _t; }), \ typeof_member(class_##_name##_t, lock) l) \ - static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ { return class_##_name##_lock_ptr(_T); } \ - static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ { return class_##_name##_lock_err(_T); } #define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 0a1b9598940d..3eac51d68426 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -393,6 +393,21 @@ struct ftrace_likely_data { #define __counted_by_be(member) __counted_by(member) #endif +/* + * This designates the minimum number of elements a passed array parameter must + * have. For example: + * + * void some_function(u8 param[at_least 7]); + * + * If a caller passes an array with fewer than 7 elements, the compiler will + * emit a warning. + */ +#ifndef __CHECKER__ +#define at_least static +#else +#define at_least +#endif + /* Do not trap wrapping arithmetic within an annotated function. */ #ifdef CONFIG_UBSAN_INTEGER_WRAP # define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow"))) diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a9ee4fe55dcf..4073690504a7 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -248,7 +248,8 @@ extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv, struct cpuidle_device *dev, u64 latency_limit_ns); extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + u64 latency_limit_ns); extern void cpuidle_use_deepest_state(u64 latency_limit_ns); #else static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, @@ -256,7 +257,8 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv, u64 latency_limit_ns) {return -ENODEV; } static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, + u64 latency_limit_ns) {return -ENODEV; } static inline void cpuidle_use_deepest_state(u64 latency_limit_ns) { diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ff8f41ab7ce6..afedfd5bea07 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -126,6 +126,7 @@ extern struct cpumask __cpu_dying_mask; #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; +extern unsigned int __num_possible_cpus; extern cpumask_t cpus_booted_once_mask; @@ -729,6 +730,22 @@ void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, } /** + * cpumask_weighted_or - *dstp = *src1p | *src2p and return the weight of the result + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + * + * Return: The number of bits set in the resulting cpumask @dstp + */ +static __always_inline +unsigned int cpumask_weighted_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return bitmap_weighted_or(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), small_cpumask_bits); +} + +/** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input @@ -1005,6 +1022,7 @@ static __always_inline unsigned int cpumask_size(void) #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly +#define CPUMASK_VAR_NULL NULL bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); @@ -1051,6 +1069,7 @@ static __always_inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly +#define CPUMASK_VAR_NULL {} static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { @@ -1136,13 +1155,13 @@ void init_cpu_possible(const struct cpumask *src); #define __assign_cpu(cpu, mask, val) \ __assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); +void set_cpu_possible(unsigned int cpu, bool possible); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * @@ -1195,7 +1214,12 @@ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } -#define num_possible_cpus() cpumask_weight(cpu_possible_mask) + +static __always_inline unsigned int num_possible_cpus(void) +{ + return __num_possible_cpus; +} + #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) diff --git a/include/linux/delay.h b/include/linux/delay.h index 89866bab100d..46412c00033a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -68,7 +68,7 @@ void usleep_range_state(unsigned long min, unsigned long max, * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. */ @@ -82,10 +82,10 @@ static inline void usleep_range(unsigned long min, unsigned long max) * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The sleeping task has the state TASK_IDLE during the sleep to prevent - * contribution to the load avarage. + * contribution to the load average. */ static inline void usleep_range_idle(unsigned long min, unsigned long max) { @@ -96,7 +96,7 @@ static inline void usleep_range_idle(unsigned long min, unsigned long max) * ssleep - wrapper for seconds around msleep * @seconds: Requested sleep duration in seconds * - * Please refere to msleep() for detailed information. + * Please refer to msleep() for detailed information. */ static inline void ssleep(unsigned int seconds) { diff --git a/include/linux/devfreq-governor.h b/include/linux/devfreq-governor.h new file mode 100644 index 000000000000..dfdd0160a29f --- /dev/null +++ b/include/linux/devfreq-governor.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * governor.h - internal header for devfreq governors. + * + * Copyright (C) 2011 Samsung Electronics + * MyungJoo Ham <myungjoo.ham@samsung.com> + * + * This header is for devfreq governors + */ + +#ifndef __LINUX_DEVFREQ_DEVFREQ_H__ +#define __LINUX_DEVFREQ_DEVFREQ_H__ + +#include <linux/devfreq.h> + +#define DEVFREQ_NAME_LEN 16 + +#define to_devfreq(DEV) container_of((DEV), struct devfreq, dev) + +/* Devfreq events */ +#define DEVFREQ_GOV_START 0x1 +#define DEVFREQ_GOV_STOP 0x2 +#define DEVFREQ_GOV_UPDATE_INTERVAL 0x3 +#define DEVFREQ_GOV_SUSPEND 0x4 +#define DEVFREQ_GOV_RESUME 0x5 + +#define DEVFREQ_MIN_FREQ 0 +#define DEVFREQ_MAX_FREQ ULONG_MAX + +/* + * Definition of the governor feature flags + * - DEVFREQ_GOV_FLAG_IMMUTABLE + * : This governor is never changeable to other governors. + * - DEVFREQ_GOV_FLAG_IRQ_DRIVEN + * : The devfreq won't schedule the work for this governor. + */ +#define DEVFREQ_GOV_FLAG_IMMUTABLE BIT(0) +#define DEVFREQ_GOV_FLAG_IRQ_DRIVEN BIT(1) + +/* + * Definition of governor attribute flags except for common sysfs attributes + * - DEVFREQ_GOV_ATTR_POLLING_INTERVAL + * : Indicate polling_interval sysfs attribute + * - DEVFREQ_GOV_ATTR_TIMER + * : Indicate timer sysfs attribute + */ +#define DEVFREQ_GOV_ATTR_POLLING_INTERVAL BIT(0) +#define DEVFREQ_GOV_ATTR_TIMER BIT(1) + +/** + * struct devfreq_governor - Devfreq policy governor + * @node: list node - contains registered devfreq governors + * @name: Governor's name + * @attrs: Governor's sysfs attribute flags + * @flags: Governor's feature flags + * @get_target_freq: Returns desired operating frequency for the device. + * Basically, get_target_freq will run + * devfreq_dev_profile.get_dev_status() to get the + * status of the device (load = busy_time / total_time). + * @event_handler: Callback for devfreq core framework to notify events + * to governors. Events include per device governor + * init and exit, opp changes out of devfreq, suspend + * and resume of per device devfreq during device idle. + * + * Note that the callbacks are called with devfreq->lock locked by devfreq. + */ +struct devfreq_governor { + struct list_head node; + + const char name[DEVFREQ_NAME_LEN]; + const u64 attrs; + const u64 flags; + int (*get_target_freq)(struct devfreq *this, unsigned long *freq); + int (*event_handler)(struct devfreq *devfreq, + unsigned int event, void *data); +}; + +void devfreq_monitor_start(struct devfreq *devfreq); +void devfreq_monitor_stop(struct devfreq *devfreq); +void devfreq_monitor_suspend(struct devfreq *devfreq); +void devfreq_monitor_resume(struct devfreq *devfreq); +void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay); + +int devfreq_add_governor(struct devfreq_governor *governor); +int devfreq_remove_governor(struct devfreq_governor *governor); + +int devm_devfreq_add_governor(struct device *dev, + struct devfreq_governor *governor); + +int devfreq_update_status(struct devfreq *devfreq, unsigned long freq); +int devfreq_update_target(struct devfreq *devfreq, unsigned long freq); +void devfreq_get_freq_range(struct devfreq *devfreq, unsigned long *min_freq, + unsigned long *max_freq); + +static inline int devfreq_update_stats(struct devfreq *df) +{ + if (!df->profile->get_dev_status) + return -EINVAL; + + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} +#endif /* __LINUX_DEVFREQ_DEVFREQ_H__ */ diff --git a/include/linux/efi.h b/include/linux/efi.h index a98cc39e7aaa..b23ff8b83219 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1126,6 +1126,8 @@ static inline bool efi_runtime_disabled(void) { return true; } extern void efi_call_virt_check_flags(unsigned long flags, const void *caller); extern unsigned long efi_call_virt_save_flags(void); +void efi_runtime_assert_lock_held(void); + enum efi_secureboot_mode { efi_secureboot_mode_unset, efi_secureboot_mode_unknown, diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 61d50571ad88..43aa6153dc57 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -54,6 +54,8 @@ struct em_perf_table { /** * struct em_perf_domain - Performance domain * @em_table: Pointer to the runtime modifiable em_perf_table + * @node: node in em_pd_list (in energy_model.c) + * @id: A unique ID number for each performance domain * @nr_perf_states: Number of performance states * @min_perf_state: Minimum allowed Performance State index * @max_perf_state: Maximum allowed Performance State index @@ -71,6 +73,8 @@ struct em_perf_table { */ struct em_perf_domain { struct em_perf_table __rcu *em_table; + struct list_head node; + int id; int nr_perf_states; int min_perf_state; int max_perf_state; diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 7177436f0f9e..87efb38b7081 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -3,11 +3,11 @@ #define __LINUX_ENTRYCOMMON_H #include <linux/irq-entry-common.h> +#include <linux/livepatch.h> #include <linux/ptrace.h> +#include <linux/resume_user_mode.h> #include <linux/seccomp.h> #include <linux/sched.h> -#include <linux/livepatch.h> -#include <linux/resume_user_mode.h> #include <asm/entry-common.h> #include <asm/syscall.h> @@ -37,6 +37,7 @@ SYSCALL_WORK_SYSCALL_AUDIT | \ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \ ARCH_SYSCALL_WORK_ENTER) + #define SYSCALL_WORK_EXIT (SYSCALL_WORK_SYSCALL_TRACEPOINT | \ SYSCALL_WORK_SYSCALL_TRACE | \ SYSCALL_WORK_SYSCALL_AUDIT | \ @@ -44,25 +45,7 @@ SYSCALL_WORK_SYSCALL_EXIT_TRAP | \ ARCH_SYSCALL_WORK_EXIT) -/** - * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts - * @regs: Pointer to currents pt_regs - * - * Invoked from architecture specific syscall entry code with interrupts - * disabled. The calling code has to be non-instrumentable. When the - * function returns all state is correct, interrupts are enabled and the - * subsequent functions can be instrumented. - * - * This handles lockdep, RCU (context tracking) and tracing state, i.e. - * the functionality provided by enter_from_user_mode(). - * - * This is invoked when there is extra architecture specific functionality - * to be done between establishing state and handling user mode entry work. - */ -void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); - -long syscall_trace_enter(struct pt_regs *regs, long syscall, - unsigned long work); +long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work); /** * syscall_enter_from_user_mode_work - Check and handle work before invoking @@ -71,8 +54,8 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall, * @syscall: The syscall number * * Invoked from architecture specific syscall entry code with interrupts - * enabled after invoking syscall_enter_from_user_mode_prepare() and extra - * architecture specific work. + * enabled after invoking enter_from_user_mode(), enabling interrupts and + * extra architecture specific work. * * Returns: The original or a modified syscall number * @@ -108,8 +91,9 @@ static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *re * function returns all state is correct, interrupts are enabled and the * subsequent functions can be instrumented. * - * This is combination of syscall_enter_from_user_mode_prepare() and - * syscall_enter_from_user_mode_work(). + * This is the combination of enter_from_user_mode() and + * syscall_enter_from_user_mode_work() to be used when there is no + * architecture specific work to be done between the two. * * Returns: The original or a modified syscall number. See * syscall_enter_from_user_mode_work() for further explanation. @@ -162,7 +146,7 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs) local_irq_enable(); } - rseq_syscall(regs); + rseq_debug_syscall_return(regs); /* * Do one-time syscall specific work. If these work items are @@ -172,7 +156,7 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs) if (unlikely(work & SYSCALL_WORK_EXIT)) syscall_exit_work(regs, work); local_irq_disable_exit_to_user(); - exit_to_user_mode_prepare(regs); + syscall_exit_to_user_mode_prepare(regs); } /** diff --git a/include/linux/freezer.h b/include/linux/freezer.h index 32884c9721e5..0a8c6c4d1a82 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -22,14 +22,18 @@ extern bool pm_nosig_freezing; /* PM nosig freezing in effect */ extern unsigned int freeze_timeout_msecs; /* - * Check if a process has been frozen + * Check if a process has been frozen for PM or cgroup1 freezer. Note that + * cgroup2 freezer uses the job control mechanism and does not interact with + * the PM freezer. */ extern bool frozen(struct task_struct *p); extern bool freezing_slow_path(struct task_struct *p); /* - * Check if there is a request to freeze a process + * Check if there is a request to freeze a task from PM or cgroup1 freezer. + * Note that cgroup2 freezer uses the job control mechanism and does not + * interact with the PM freezer. */ static inline bool freezing(struct task_struct *p) { @@ -63,9 +67,9 @@ extern bool freeze_task(struct task_struct *p); extern bool set_freezable(void); #ifdef CONFIG_CGROUP_FREEZER -extern bool cgroup_freezing(struct task_struct *task); +extern bool cgroup1_freezing(struct task_struct *task); #else /* !CONFIG_CGROUP_FREEZER */ -static inline bool cgroup_freezing(struct task_struct *task) +static inline bool cgroup1_freezing(struct task_struct *task) { return false; } diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 71ac78b9f834..11cab07f322a 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -11,7 +11,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); -void huge_pmd_set_accessed(struct vm_fault *vmf); +bool huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index c0397423d3a8..e9ade2ff4af6 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -152,7 +152,7 @@ struct rapl_if_priv { union rapl_reg reg_unit; union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX]; int limits[RAPL_DOMAIN_MAX]; - int (*read_raw)(int id, struct reg_action *ra); + int (*read_raw)(int id, struct reg_action *ra, bool atomic); int (*write_raw)(int id, struct reg_action *ra); void *defaults; void *rpi; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 51b6484c0493..266f2b39213a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -109,6 +109,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @name: name of the device * @dev_id: cookie to identify the device * @percpu_dev_id: cookie to identify the device + * @affinity: CPUs this irqaction is allowed to run on * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @flags: flags (see IRQF_* above) @@ -121,8 +122,11 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); */ struct irqaction { irq_handler_t handler; - void *dev_id; - void __percpu *percpu_dev_id; + union { + void *dev_id; + void __percpu *percpu_dev_id; + }; + const struct cpumask *affinity; struct irqaction *next; irq_handler_t thread_fn; struct task_struct *thread; @@ -179,7 +183,7 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, extern int __must_check __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, - void __percpu *percpu_dev_id); + const cpumask_t *affinity, void __percpu *percpu_dev_id); extern int __must_check request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags, @@ -190,12 +194,21 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id) { return __request_percpu_irq(irq, handler, 0, - devname, percpu_dev_id); + devname, NULL, percpu_dev_id); +} + +static inline int __must_check +request_percpu_irq_affinity(unsigned int irq, irq_handler_t handler, + const char *devname, const cpumask_t *affinity, + void __percpu *percpu_dev_id) +{ + return __request_percpu_irq(irq, handler, 0, + devname, affinity, percpu_dev_id); } extern int __must_check -request_percpu_nmi(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *dev); +request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name, + const struct cpumask *affinity, void __percpu *dev_id); extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index ba1ed42f8a1c..6ab913e57da0 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -2,11 +2,12 @@ #ifndef __LINUX_IRQENTRYCOMMON_H #define __LINUX_IRQENTRYCOMMON_H +#include <linux/context_tracking.h> +#include <linux/kmsan.h> +#include <linux/rseq_entry.h> #include <linux/static_call_types.h> #include <linux/syscalls.h> -#include <linux/context_tracking.h> #include <linux/tick.h> -#include <linux/kmsan.h> #include <linux/unwind_deferred.h> #include <asm/entry-common.h> @@ -29,7 +30,7 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ - _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | _TIF_RSEQ | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @@ -67,6 +68,7 @@ static __always_inline bool arch_in_rcu_eqs(void) { return false; } /** * enter_from_user_mode - Establish state when coming from user mode + * @regs: Pointer to currents pt_regs * * Syscall/interrupt entry disables interrupts, but user mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. @@ -195,14 +197,11 @@ static __always_inline void arch_exit_to_user_mode(void) { } */ void arch_do_signal_or_restart(struct pt_regs *regs); -/** - * exit_to_user_mode_loop - do any pending work before leaving to user space - */ -unsigned long exit_to_user_mode_loop(struct pt_regs *regs, - unsigned long ti_work); +/* Handle pending TIF work */ +unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work); /** - * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * __exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required * @regs: Pointer to pt_regs on entry stack * * 1) check that interrupts are disabled @@ -210,8 +209,10 @@ unsigned long exit_to_user_mode_loop(struct pt_regs *regs, * 3) call exit_to_user_mode_loop() if any flags from * EXIT_TO_USER_MODE_WORK are set * 4) check that interrupts are still disabled + * + * Don't invoke directly, use the syscall/irqentry_ prefixed variants below */ -static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) +static __always_inline void __exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long ti_work; @@ -225,13 +226,52 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) ti_work = exit_to_user_mode_loop(regs, ti_work); arch_exit_to_user_mode_prepare(regs, ti_work); +} +static __always_inline void __exit_to_user_mode_validate(void) +{ /* Ensure that kernel state is sane for a return to userspace */ kmap_assert_nomap(); lockdep_assert_irqs_disabled(); lockdep_sys_exit(); } +/* Temporary workaround to keep ARM64 alive */ +static __always_inline void exit_to_user_mode_prepare_legacy(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_exit_to_user_mode_legacy(); + __exit_to_user_mode_validate(); +} + +/** + * syscall_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * @regs: Pointer to pt_regs on entry stack + * + * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for + * syscalls and interrupts. + */ +static __always_inline void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_syscall_exit_to_user_mode(); + __exit_to_user_mode_validate(); +} + +/** + * irqentry_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * @regs: Pointer to pt_regs on entry stack + * + * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for + * syscalls and interrupts. + */ +static __always_inline void irqentry_exit_to_user_mode_prepare(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_irqentry_exit_to_user_mode(); + __exit_to_user_mode_validate(); +} + /** * exit_to_user_mode - Fixup state when exiting to user mode * @@ -274,7 +314,11 @@ static __always_inline void exit_to_user_mode(void) * * The function establishes state (lockdep, RCU (context tracking), tracing) */ -void irqentry_enter_from_user_mode(struct pt_regs *regs); +static __always_inline void irqentry_enter_from_user_mode(struct pt_regs *regs) +{ + enter_from_user_mode(regs); + rseq_note_user_irq_entry(); +} /** * irqentry_exit_to_user_mode - Interrupt exit work @@ -289,7 +333,13 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs); * Interrupt exit is not invoking #1 which is the syscall specific one time * work. */ -void irqentry_exit_to_user_mode(struct pt_regs *regs); +static __always_inline void irqentry_exit_to_user_mode(struct pt_regs *regs) +{ + instrumentation_begin(); + irqentry_exit_to_user_mode_prepare(regs); + instrumentation_end(); + exit_to_user_mode(); +} #ifndef irqentry_state /** @@ -354,6 +404,7 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * Conditional reschedule with additional sanity checks. */ void raw_irqentry_exit_cond_resched(void); + #ifdef CONFIG_PREEMPT_DYNAMIC #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) #define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched diff --git a/include/linux/irq.h b/include/linux/irq.h index c67e76fbcc07..4a9f1d7b08c3 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -655,7 +655,6 @@ extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern void handle_fasteoi_nmi(struct irq_desc *desc); -extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); @@ -719,10 +718,6 @@ static inline void irq_set_chip_and_handler(unsigned int irq, } extern int irq_set_percpu_devid(unsigned int irq); -extern int irq_set_percpu_devid_partition(unsigned int irq, - const struct cpumask *affinity); -extern int irq_get_percpu_devid_partition(unsigned int irq, - struct cpumask *affinity); extern void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 136f2980cba3..c5afd053ae32 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -2,8 +2,9 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H -#include <linux/smp_types.h> +#include <linux/irq_work_types.h> #include <linux/rcuwait.h> +#include <linux/smp_types.h> /* * An entry can be in one of four states: @@ -14,12 +15,6 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ -struct irq_work { - struct __call_single_node node; - void (*func)(struct irq_work *); - struct rcuwait irqwait; -}; - #define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){ \ .node = { .u_flags = (_flags), }, \ .func = (_func), \ diff --git a/include/linux/irq_work_types.h b/include/linux/irq_work_types.h new file mode 100644 index 000000000000..73abec5bb06e --- /dev/null +++ b/include/linux/irq_work_types.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IRQ_WORK_TYPES_H +#define _LINUX_IRQ_WORK_TYPES_H + +#include <linux/smp_types.h> +#include <linux/types.h> + +struct irq_work { + struct __call_single_node node; + void (*func)(struct irq_work *); + struct rcuwait irqwait; +}; + +#endif diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index d5e6024cb2a8..bc4ddacd6ddc 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -17,12 +17,18 @@ #include <linux/of_irq.h> #include <linux/platform_device.h> +typedef int (*platform_irq_probe_t)(struct platform_device *, struct device_node *); + /* Undefined on purpose */ extern of_irq_init_cb_t typecheck_irq_init_cb; +extern platform_irq_probe_t typecheck_irq_probe; #define typecheck_irq_init_cb(fn) \ (__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn) +#define typecheck_irq_probe(fn) \ + (__typecheck(typecheck_irq_probe, &fn) ? fn : fn) + /* * This macro must be used by the different irqchip drivers to declare * the association between their DT compatible string and their @@ -42,7 +48,7 @@ extern int platform_irqchip_probe(struct platform_device *pdev); static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ - .data = typecheck_irq_init_cb(fn), }, + .data = typecheck_irq_probe(fn), }, #define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ diff --git a/include/linux/irqchip/irq-partition-percpu.h b/include/linux/irqchip/irq-partition-percpu.h deleted file mode 100644 index b35ee22c278f..000000000000 --- a/include/linux/irqchip/irq-partition-percpu.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 ARM Limited, All Rights Reserved. - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#ifndef __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H -#define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H - -#include <linux/fwnode.h> -#include <linux/cpumask_types.h> -#include <linux/irqdomain.h> - -struct partition_affinity { - cpumask_t mask; - void *partition_id; -}; - -struct partition_desc; - -#ifdef CONFIG_PARTITION_PERCPU -int partition_translate_id(struct partition_desc *desc, void *partition_id); -struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode, - struct partition_affinity *parts, - int nr_parts, - int chained_irq, - const struct irq_domain_ops *ops); -struct irq_domain *partition_get_domain(struct partition_desc *dsc); -#else -static inline int partition_translate_id(struct partition_desc *desc, - void *partition_id) -{ - return -EINVAL; -} - -static inline -struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode, - struct partition_affinity *parts, - int nr_parts, - int chained_irq, - const struct irq_domain_ops *ops) -{ - return NULL; -} - -static inline -struct irq_domain *partition_get_domain(struct partition_desc *dsc) -{ - return NULL; -} -#endif - -#endif /* __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index fd091c35d572..37e0b5b5600a 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -82,7 +82,6 @@ struct irq_desc { int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; - const struct cpumask *percpu_affinity; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 4a86e6b915dd..952d3c8dd6b7 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -44,6 +44,23 @@ struct irq_fwspec { u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS]; }; +/** + * struct irq_fwspec_info - firmware provided IRQ information structure + * + * @flags: Information validity flags + * @affinity: Affinity mask for this interrupt + * + * This structure reports firmware-specific information about an + * interrupt. The only significant information is the affinity of a + * per-CPU interrupt, but this is designed to be extended as required. + */ +struct irq_fwspec_info { + unsigned long flags; + const struct cpumask *affinity; +}; + +#define IRQ_FWSPEC_INFO_AFFINITY_VALID BIT(0) + /* Conversion function from of_phandle_args fields to fwspec */ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, unsigned int count, struct irq_fwspec *fwspec); @@ -69,6 +86,9 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, * @translate: Given @fwspec, decode the hardware irq number (@out_hwirq) and * linux irq type value (@out_type). This is a generalised @xlate * (over struct irq_fwspec) and is preferred if provided. + * @get_fwspec_info: + * Given @fwspec, report additional firmware-provided information in + * @info. Optional. * @debug_show: For domains to show specific data for an interrupt in debugfs. * * Functions below are provided by the driver and called whenever a new mapping @@ -96,6 +116,7 @@ struct irq_domain_ops { void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *out_hwirq, unsigned int *out_type); + int (*get_fwspec_info)(struct irq_fwspec *fwspec, struct irq_fwspec_info *info); #endif #ifdef CONFIG_GENERIC_IRQ_DEBUGFS void (*debug_show)(struct seq_file *m, struct irq_domain *d, @@ -602,6 +623,8 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_bas int irq_domain_disconnect_hierarchy(struct irq_domain *domain, unsigned int virq); +int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info); + static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY; @@ -685,6 +708,10 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain) return false; } +static inline int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info) +{ + return -EINVAL; +} #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #ifdef CONFIG_GENERIC_MSI_IRQ @@ -703,12 +730,6 @@ static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsig } #endif -/* Deprecated functions. Will be removed in the merge window */ -static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) -{ - return node ? &node->fwnode : NULL; -} - static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 490464c205b4..a568d8e6f4e8 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -11,8 +11,22 @@ #ifdef KVM_SUB_MODULES #define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol) \ EXPORT_SYMBOL_FOR_MODULES(symbol, __stringify(KVM_SUB_MODULES)) +#define EXPORT_SYMBOL_FOR_KVM(symbol) \ + EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm," __stringify(KVM_SUB_MODULES)) #else #define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol) +/* + * Allow architectures to provide a custom EXPORT_SYMBOL_FOR_KVM, but only + * if there are no submodules, e.g. to allow suppressing exports if KVM=m, but + * kvm.ko won't actually be built (due to lack of at least one submodule). + */ +#ifndef EXPORT_SYMBOL_FOR_KVM +#if IS_MODULE(CONFIG_KVM) +#define EXPORT_SYMBOL_FOR_KVM(symbol) EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm") +#else +#define EXPORT_SYMBOL_FOR_KVM(symbol) +#endif /* IS_MODULE(CONFIG_KVM) */ +#endif /* EXPORT_SYMBOL_FOR_KVM */ #endif #ifndef __ASSEMBLER__ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 67964dc4db95..dd634103b014 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -616,7 +616,7 @@ do { \ #define lockdep_assert_in_softirq() \ do { \ WARN_ON_ONCE(__lockdep_enabled && \ - (!in_softirq() || in_irq() || in_nmi())); \ + (!in_softirq() || in_hardirq() || in_nmi())); \ } while (0) extern void lockdep_assert_in_softirq_func(void); diff --git a/include/linux/memory.h b/include/linux/memory.h index 0c214256216f..ba1515160894 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,17 +96,8 @@ int set_memory_block_size_order(unsigned int order); #define MEM_GOING_ONLINE (1<<3) #define MEM_CANCEL_ONLINE (1<<4) #define MEM_CANCEL_OFFLINE (1<<5) -#define MEM_PREPARE_ONLINE (1<<6) -#define MEM_FINISH_OFFLINE (1<<7) struct memory_notify { - /* - * The altmap_start_pfn and altmap_nr_pages fields are designated for - * specifying the altmap range and are exclusively intended for use in - * MEM_PREPARE_ONLINE/MEM_FINISH_OFFLINE notifiers. - */ - unsigned long altmap_start_pfn; - unsigned long altmap_nr_pages; unsigned long start_pfn; unsigned long nr_pages; }; diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 23f038a16231..f2f16cdd73ee 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -58,22 +58,6 @@ typedef int __bitwise mhp_t; * implies the node id (nid). */ #define MHP_NID_IS_MGID ((__force mhp_t)BIT(2)) -/* - * The hotplugged memory is completely inaccessible while the memory is - * offline. The memory provider will handle MEM_PREPARE_ONLINE / - * MEM_FINISH_OFFLINE notifications and make the memory accessible. - * - * This flag is only relevant when used along with MHP_MEMMAP_ON_MEMORY, - * because the altmap cannot be written (e.g., poisoned) when adding - * memory -- before it is set online. - * - * This allows for adding memory with an altmap that is not currently - * made available by a hypervisor. When onlining that memory, the - * hypervisor can be instructed to make that memory available, and - * the onlining phase will not require any memory allocations, which is - * helpful in low-memory situations. - */ -#define MHP_OFFLINE_INACCESSIBLE ((__force mhp_t)BIT(3)) /* * Extended parameters for memory hotplug: @@ -123,7 +107,7 @@ extern void adjust_present_page_count(struct page *page, long nr_pages); /* VM interface that may be used by firmware interface */ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages, - struct zone *zone, bool mhp_off_inaccessible); + struct zone *zone); extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages); extern int online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index e5951ba12a28..30c7aecbd245 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -25,7 +25,6 @@ struct vmem_altmap { unsigned long free; unsigned long align; unsigned long alloc; - bool inaccessible; }; /* diff --git a/include/linux/mm.h b/include/linux/mm.h index 170594b5cb6b..8dc0a07570cc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2408,31 +2408,6 @@ struct zap_details { /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) -#ifdef CONFIG_SCHED_MM_CID -void sched_mm_cid_before_execve(struct task_struct *t); -void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); -void sched_mm_cid_exit_signals(struct task_struct *t); -static inline int task_mm_cid(struct task_struct *t) -{ - return t->mm_cid; -} -#else -static inline void sched_mm_cid_before_execve(struct task_struct *t) { } -static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } -static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } -static inline int task_mm_cid(struct task_struct *t) -{ - /* - * Use the processor id as a fall-back when the mm cid feature is - * disabled. This provides functional per-cpu data structure accesses - * in user-space, althrough it won't provide the memory usage benefits. - */ - return raw_smp_processor_id(); -} -#endif - #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 90e5790c318f..3b7d05e7169c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -20,6 +20,7 @@ #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <linux/types.h> +#include <linux/rseq_types.h> #include <linux/bitmap.h> #include <asm/mmu.h> @@ -922,14 +923,6 @@ struct vm_area_struct { #define vma_policy(vma) NULL #endif -#ifdef CONFIG_SCHED_MM_CID -struct mm_cid { - u64 time; - int cid; - int recent_cid; -}; -#endif - /* * Opaque type representing current mm_struct flag state. Must be accessed via * mm_flags_xxx() helper functions. @@ -991,44 +984,9 @@ struct mm_struct { */ atomic_t mm_users; -#ifdef CONFIG_SCHED_MM_CID - /** - * @pcpu_cid: Per-cpu current cid. - * - * Keep track of the currently allocated mm_cid for each cpu. - * The per-cpu mm_cid values are serialized by their respective - * runqueue locks. - */ - struct mm_cid __percpu *pcpu_cid; - /* - * @mm_cid_next_scan: Next mm_cid scan (in jiffies). - * - * When the next mm_cid scan is due (in jiffies). - */ - unsigned long mm_cid_next_scan; - /** - * @nr_cpus_allowed: Number of CPUs allowed for mm. - * - * Number of CPUs allowed in the union of all mm's - * threads allowed CPUs. - */ - unsigned int nr_cpus_allowed; - /** - * @max_nr_cid: Maximum number of allowed concurrency - * IDs allocated. - * - * Track the highest number of allowed concurrency IDs - * allocated for the mm. - */ - atomic_t max_nr_cid; - /** - * @cpus_allowed_lock: Lock protecting mm cpus_allowed. - * - * Provide mutual exclusion for mm cpus_allowed and - * mm nr_cpus_allowed updates. - */ - raw_spinlock_t cpus_allowed_lock; -#endif + /* MM CID related storage */ + struct mm_mm_cid mm_cid; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ #endif @@ -1370,37 +1328,6 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID - -enum mm_cid_state { - MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ - MM_CID_LAZY_PUT = (1U << 31), -}; - -static inline bool mm_cid_is_unset(int cid) -{ - return cid == MM_CID_UNSET; -} - -static inline bool mm_cid_is_lazy_put(int cid) -{ - return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); -} - -static inline bool mm_cid_is_valid(int cid) -{ - return !(cid & MM_CID_LAZY_PUT); -} - -static inline int mm_cid_set_lazy_put(int cid) -{ - return cid | MM_CID_LAZY_PUT; -} - -static inline int mm_cid_clear_lazy_put(int cid) -{ - return cid & ~MM_CID_LAZY_PUT; -} - /* * mm_cpus_allowed: Union of all mm's threads allowed CPUs. */ @@ -1415,37 +1342,21 @@ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) } /* Accessor for struct mm_struct's cidmask. */ -static inline cpumask_t *mm_cidmask(struct mm_struct *mm) +static inline unsigned long *mm_cidmask(struct mm_struct *mm) { unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm); /* Skip mm_cpus_allowed */ cid_bitmap += cpumask_size(); - return (struct cpumask *)cid_bitmap; + return (unsigned long *)cid_bitmap; } -static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) -{ - int i; - - for_each_possible_cpu(i) { - struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); - - pcpu_cid->cid = MM_CID_UNSET; - pcpu_cid->recent_cid = MM_CID_UNSET; - pcpu_cid->time = 0; - } - mm->nr_cpus_allowed = p->nr_cpus_allowed; - atomic_set(&mm->max_nr_cid, 0); - raw_spin_lock_init(&mm->cpus_allowed_lock); - cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); - cpumask_clear(mm_cidmask(mm)); -} +void mm_init_cid(struct mm_struct *mm, struct task_struct *p); static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p) { - mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); - if (!mm->pcpu_cid) + mm->mm_cid.pcpu = alloc_percpu_noprof(struct mm_cid_pcpu); + if (!mm->mm_cid.pcpu) return -ENOMEM; mm_init_cid(mm, p); return 0; @@ -1454,37 +1365,24 @@ static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct * static inline void mm_destroy_cid(struct mm_struct *mm) { - free_percpu(mm->pcpu_cid); - mm->pcpu_cid = NULL; + free_percpu(mm->mm_cid.pcpu); + mm->mm_cid.pcpu = NULL; } static inline unsigned int mm_cid_size(void) { - return 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */ + /* mm_cpus_allowed(), mm_cidmask(). */ + return cpumask_size() + bitmap_size(num_possible_cpus()); } -static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) -{ - struct cpumask *mm_allowed = mm_cpus_allowed(mm); - - if (!mm) - return; - /* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */ - raw_spin_lock(&mm->cpus_allowed_lock); - cpumask_or(mm_allowed, mm_allowed, cpumask); - WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed)); - raw_spin_unlock(&mm->cpus_allowed_lock); -} #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } - static inline unsigned int mm_cid_size(void) { return 0; } -static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; diff --git a/include/linux/msi.h b/include/linux/msi.h index d415dd15a0a9..8003e3218c46 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -701,9 +701,6 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); u32 pci_msi_map_rid_ctlr_node(struct pci_dev *pdev, struct device_node **node); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 1db8543dfc8a..1c2bc0281807 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -43,6 +43,8 @@ extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); extern int of_irq_get(struct device_node *dev, int index); +extern const struct cpumask *of_irq_get_affinity(struct device_node *dev, + int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); @@ -76,6 +78,11 @@ static inline int of_irq_get_byname(struct device_node *dev, const char *name) { return 0; } +static inline const struct cpumask *of_irq_get_affinity(struct device_node *dev, + int index) +{ + return NULL; +} static inline int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs) { diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 12d90360f6db..43c854a273c3 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -52,7 +52,7 @@ __section(".discard") __attribute__((unused)) /* - * s390 and alpha modules require percpu variables to be defined as + * alpha modules require percpu variables to be defined as * weak to force the compiler to generate GOT based external * references for them. This is necessary because percpu sections * will be located outside of the usually addressable area. diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 93c9a26492fc..52b37f7bdbf9 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -119,6 +119,7 @@ struct arm_pmu { /* PMUv3 only */ int pmuver; + bool has_smt; u64 reg_pmmir; u64 reg_brbidr; #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40 @@ -132,8 +133,6 @@ struct arm_pmu { #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) -DECLARE_PER_CPU(struct arm_pmu *, cpu_armpmu); - u64 armpmu_event_update(struct perf_event *event); int armpmu_event_set_period(struct perf_event *event); @@ -190,8 +189,8 @@ bool arm_pmu_irq_is_nmi(void); struct arm_pmu *armpmu_alloc(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); -int armpmu_request_irq(int irq, int cpu); -void armpmu_free_irq(int irq, int cpu); +int armpmu_request_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu); +void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu); #define ARMV8_PMU_PDEV_NAME "armv8-pmu" diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 32e8457ad535..ee3148ef87f6 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1232,6 +1232,10 @@ static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio) #define flush_tlb_fix_spurious_fault(vma, address, ptep) flush_tlb_page(vma, address) #endif +#ifndef flush_tlb_fix_spurious_fault_pmd +#define flush_tlb_fix_spurious_fault_pmd(vma, address, pmdp) do { } while (0) +#endif + /* * When walking page tables, get the address of the next boundary, * or the end address of the range if that comes earlier. Although no diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 074754c23d33..93c945331f39 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -102,6 +102,8 @@ devm_platform_ioremap_resource_byname(struct platform_device *pdev, extern int platform_get_irq(struct platform_device *, unsigned int); extern int platform_get_irq_optional(struct platform_device *, unsigned int); +extern int platform_get_irq_affinity(struct platform_device *, unsigned int, + const struct cpumask **); extern int platform_irq_count(struct platform_device *); extern int devm_platform_get_irqs_affinity(struct platform_device *dev, struct irq_affinity *affd, @@ -232,6 +234,7 @@ extern int platform_device_add_data(struct platform_device *pdev, extern int platform_device_add(struct platform_device *pdev); extern void platform_device_del(struct platform_device *pdev); extern void platform_device_put(struct platform_device *pdev); +DEFINE_FREE(platform_device_put, struct platform_device *, if (_T) platform_device_put(_T)) struct platform_driver { int (*probe)(struct platform_device *); diff --git a/include/linux/pm.h b/include/linux/pm.h index cc7b2dc28574..7f69f739f613 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -25,11 +25,12 @@ extern void (*pm_power_off)(void); struct device; /* we have a circular dep with device.h */ #ifdef CONFIG_VT_CONSOLE_SLEEP -extern void pm_vt_switch_required(struct device *dev, bool required); +extern int pm_vt_switch_required(struct device *dev, bool required); extern void pm_vt_switch_unregister(struct device *dev); #else -static inline void pm_vt_switch_required(struct device *dev, bool required) +static inline int pm_vt_switch_required(struct device *dev, bool required) { + return 0; } static inline void pm_vt_switch_unregister(struct device *dev) { @@ -507,6 +508,7 @@ const struct dev_pm_ops name = { \ * RECOVER Creation of a hibernation image or restoration of the main * memory contents from a hibernation image has failed, call * ->thaw() and ->complete() for all devices. + * POWEROFF System will poweroff, call ->poweroff() for all devices. * * The following PM_EVENT_ messages are defined for internal use by * kernel subsystems. They are never issued by the PM core. @@ -537,6 +539,7 @@ const struct dev_pm_ops name = { \ #define PM_EVENT_USER 0x0100 #define PM_EVENT_REMOTE 0x0200 #define PM_EVENT_AUTO 0x0400 +#define PM_EVENT_POWEROFF 0x0800 #define PM_EVENT_SLEEP (PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE) #define PM_EVENT_USER_SUSPEND (PM_EVENT_USER | PM_EVENT_SUSPEND) @@ -551,6 +554,7 @@ const struct dev_pm_ops name = { \ #define PMSG_QUIESCE ((struct pm_message){ .event = PM_EVENT_QUIESCE, }) #define PMSG_SUSPEND ((struct pm_message){ .event = PM_EVENT_SUSPEND, }) #define PMSG_HIBERNATE ((struct pm_message){ .event = PM_EVENT_HIBERNATE, }) +#define PMSG_POWEROFF ((struct pm_message){ .event = PM_EVENT_POWEROFF, }) #define PMSG_RESUME ((struct pm_message){ .event = PM_EVENT_RESUME, }) #define PMSG_THAW ((struct pm_message){ .event = PM_EVENT_THAW, }) #define PMSG_RESTORE ((struct pm_message){ .event = PM_EVENT_RESTORE, }) diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index f67a2cb7d781..93ba0143ca47 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -153,6 +153,7 @@ enum genpd_sync_state { }; struct dev_power_governor { + bool (*system_power_down_ok)(struct dev_pm_domain *domain); bool (*power_down_ok)(struct dev_pm_domain *domain); bool (*suspend_ok)(struct device *dev); }; diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 4a69d4af3ff8..6cea4455f867 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -162,6 +162,15 @@ static inline void cpu_latency_qos_update_request(struct pm_qos_request *req, static inline void cpu_latency_qos_remove_request(struct pm_qos_request *req) {} #endif +#ifdef CONFIG_PM_QOS_CPU_SYSTEM_WAKEUP +s32 cpu_wakeup_latency_qos_limit(void); +#else +static inline s32 cpu_wakeup_latency_qos_limit(void) +{ + return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; +} +#endif + #ifdef CONFIG_PM enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev, s32 mask); enum pm_qos_flags_status dev_pm_qos_flags(struct device *dev, s32 mask); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 0b436e15f4cd..911d7a4d32c1 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -637,6 +637,30 @@ DEFINE_GUARD_COND(pm_runtime_active_auto, _try, DEFINE_GUARD_COND(pm_runtime_active_auto, _try_enabled, pm_runtime_resume_and_get(_T), _RET == 0) +/* ACQUIRE() wrapper macros for the guards defined above. */ + +#define PM_RUNTIME_ACQUIRE(_dev, _var) \ + ACQUIRE(pm_runtime_active_try, _var)(_dev) + +#define PM_RUNTIME_ACQUIRE_AUTOSUSPEND(_dev, _var) \ + ACQUIRE(pm_runtime_active_auto_try, _var)(_dev) + +#define PM_RUNTIME_ACQUIRE_IF_ENABLED(_dev, _var) \ + ACQUIRE(pm_runtime_active_try_enabled, _var)(_dev) + +#define PM_RUNTIME_ACQUIRE_IF_ENABLED_AUTOSUSPEND(_dev, _var) \ + ACQUIRE(pm_runtime_active_auto_try_enabled, _var)(_dev) + +/* + * ACQUIRE_ERR() wrapper macro for guard pm_runtime_active. + * + * Always check PM_RUNTIME_ACQUIRE_ERR() after using one of the + * PM_RUNTIME_ACQUIRE*() macros defined above (yes, it can be used with + * any of them) and if it is nonzero, avoid accessing the given device. + */ +#define PM_RUNTIME_ACQUIRE_ERR(_var_ptr) \ + ACQUIRE_ERR(pm_runtime_active, _var_ptr) + /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. * @dev: Target device. diff --git a/include/linux/prandom.h b/include/linux/prandom.h index f2ed5b72b3d6..ff7dcc3fa105 100644 --- a/include/linux/prandom.h +++ b/include/linux/prandom.h @@ -47,10 +47,4 @@ static inline void prandom_seed_state(struct rnd_state *state, u64 seed) state->s4 = __seed(i, 128U); } -/* Pseudo random number generator from numerical recipes. */ -static inline u32 next_pseudo_random32(u32 seed) -{ - return seed * 1664525 + 1013904223; -} - #endif diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 102202185d7a..d964f965c8ff 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -134,11 +134,9 @@ static __always_inline unsigned char interrupt_context_level(void) /* * The following macros are deprecated and should not be used in new code: - * in_irq() - Obsolete version of in_hardirq() * in_softirq() - We have BH disabled, or are processing softirqs * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled */ -#define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) diff --git a/include/linux/prmt.h b/include/linux/prmt.h index c53ab287e932..8cdc987de963 100644 --- a/include/linux/prmt.h +++ b/include/linux/prmt.h @@ -4,9 +4,11 @@ #ifdef CONFIG_ACPI_PRMT void init_prmt(void); +bool acpi_prm_handler_available(const guid_t *handler_guid); int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer); #else static inline void init_prmt(void) { } +static inline bool acpi_prm_handler_available(const guid_t *handler_guid) { return false; } static inline int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer) { return -EOPNOTSUPP; diff --git a/include/linux/random.h b/include/linux/random.h index 333cecfca93f..8a8064dc3970 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -130,21 +130,6 @@ static inline int get_random_bytes_wait(void *buf, size_t nbytes) return ret; } -#define declare_get_random_var_wait(name, ret_type) \ - static inline int get_random_ ## name ## _wait(ret_type *out) { \ - int ret = wait_for_random_bytes(); \ - if (unlikely(ret)) \ - return ret; \ - *out = get_random_ ## name(); \ - return 0; \ - } -declare_get_random_var_wait(u8, u8) -declare_get_random_var_wait(u16, u16) -declare_get_random_var_wait(u32, u32) -declare_get_random_var_wait(u64, u32) -declare_get_random_var_wait(long, unsigned long) -#undef declare_get_random_var - #ifdef CONFIG_SMP int random_prepare_cpu(unsigned int cpu); int random_online_cpu(unsigned int cpu); diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a7d92718b653..54701668b3df 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -206,6 +206,8 @@ struct rdt_mon_domain { * @arch_has_sparse_bitmasks: True if a bitmask like f00f is valid. * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache * level has CPU scope. + * @io_alloc_capable: True if portion of the cache can be configured + * for I/O traffic. */ struct resctrl_cache { unsigned int cbm_len; @@ -213,6 +215,7 @@ struct resctrl_cache { unsigned int shareable_bits; bool arch_has_sparse_bitmasks; bool arch_has_per_cpu_cfg; + bool io_alloc_capable; }; /** @@ -654,6 +657,27 @@ void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, int cntr_id, enum resctrl_event_id eventid); +/** + * resctrl_arch_io_alloc_enable() - Enable/disable io_alloc feature. + * @r: The resctrl resource. + * @enable: Enable (true) or disable (false) io_alloc on resource @r. + * + * This can be called from any CPU. + * + * Return: + * 0 on success, <0 on error. + */ +int resctrl_arch_io_alloc_enable(struct rdt_resource *r, bool enable); + +/** + * resctrl_arch_get_io_alloc_enabled() - Get io_alloc feature state. + * @r: The resctrl resource. + * + * Return: + * true if io_alloc is enabled or false if disabled. + */ +bool resctrl_arch_get_io_alloc_enabled(struct rdt_resource *r); + extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 7e50bbc94e47..36ddfa1ec301 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -43,7 +43,7 @@ struct restart_block { struct __kernel_timespec __user *rmtp; struct old_timespec32 __user *compat_rmtp; }; - u64 expires; + ktime_t expires; } nanosleep; /* For poll */ struct { diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index e0135e0adae0..bf92227c78d0 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -59,7 +59,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); - rseq_handle_notify_resume(NULL, regs); + rseq_handle_slowpath(regs); } #endif /* LINUX_RESUME_USER_MODE_H */ diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 69553e7c14c1..2266f4dc77b6 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -3,134 +3,164 @@ #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ - -#include <linux/preempt.h> #include <linux/sched.h> -#ifdef CONFIG_MEMBARRIER -# define RSEQ_EVENT_GUARD irq -#else -# define RSEQ_EVENT_GUARD preempt -#endif - -/* - * Map the event mask on the user-space ABI enum rseq_cs_flags - * for direct mask checks. - */ -enum rseq_event_mask_bits { - RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, - RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, - RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, -}; - -enum rseq_event_mask { - RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), - RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), - RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), -}; - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ - if (t->rseq) - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); -} +#include <uapi/linux/rseq.h> -void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); +void __rseq_handle_slowpath(struct pt_regs *regs); -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) +/* Invoked from resume_user_mode_work() */ +static inline void rseq_handle_slowpath(struct pt_regs *regs) { - if (current->rseq) - __rseq_handle_notify_resume(ksig, regs); + if (IS_ENABLED(CONFIG_GENERIC_ENTRY)) { + if (current->rseq.event.slowpath) + __rseq_handle_slowpath(regs); + } else { + /* '&' is intentional to spare one conditional branch */ + if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + __rseq_handle_slowpath(regs); + } } -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ - scoped_guard(RSEQ_EVENT_GUARD) - __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); - rseq_handle_notify_resume(ksig, regs); -} +void __rseq_signal_deliver(int sig, struct pt_regs *regs); -/* rseq_preempt() requires preemption to be disabled. */ -static inline void rseq_preempt(struct task_struct *t) +/* + * Invoked from signal delivery to fixup based on the register context before + * switching to the signal delivery context. + */ +static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* '&' is intentional to spare one conditional branch */ + if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + __rseq_signal_deliver(ksig->sig, regs); + } else { + if (current->rseq.event.has_rseq) + __rseq_signal_deliver(ksig->sig, regs); + } } -/* rseq_migrate() requires preemption to be disabled. */ -static inline void rseq_migrate(struct task_struct *t) +static inline void rseq_raise_notify_resume(struct task_struct *t) { - __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); + set_tsk_thread_flag(t, TIF_RSEQ); } -/* - * If parent process has a registered restartable sequences area, the - * child inherits. Unregister rseq for a clone with CLONE_VM set. - */ -static inline void rseq_fork(struct task_struct *t, u64 clone_flags) +/* Invoked from context switch to force evaluation on exit to user */ +static __always_inline void rseq_sched_switch_event(struct task_struct *t) { - if (clone_flags & CLONE_VM) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; + struct rseq_event *ev = &t->rseq.event; + + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Avoid a boat load of conditionals by using simple logic + * to determine whether NOTIFY_RESUME needs to be raised. + * + * It's required when the CPU or MM CID has changed or + * the entry was from user space. + */ + bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + + if (raise) { + ev->sched_switch = true; + rseq_raise_notify_resume(t); + } } else { - t->rseq = current->rseq; - t->rseq_len = current->rseq_len; - t->rseq_sig = current->rseq_sig; - t->rseq_event_mask = current->rseq_event_mask; + if (ev->has_rseq) { + t->rseq.event.sched_switch = true; + rseq_raise_notify_resume(t); + } } } -static inline void rseq_execve(struct task_struct *t) +/* + * Invoked from __set_task_cpu() when a task migrates or from + * mm_cid_schedin() when the CID changes to enforce an IDs update. + * + * This does not raise TIF_NOTIFY_RESUME as that happens in + * rseq_sched_switch_event(). + */ +static __always_inline void rseq_sched_set_ids_changed(struct task_struct *t) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; + t->rseq.event.ids_changed = true; } -#else - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ -} -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) +/* Enforce a full update after RSEQ registration and when execve() failed */ +static inline void rseq_force_update(void) { + if (current->rseq.event.has_rseq) { + current->rseq.event.ids_changed = true; + current->rseq.event.sched_switch = true; + rseq_raise_notify_resume(current); + } } -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) + +/* + * KVM/HYPERV invoke resume_user_mode_work() before entering guest mode, + * which clears TIF_NOTIFY_RESUME on architectures that don't use the + * generic TIF bits and therefore can't provide a separate TIF_RSEQ flag. + * + * To avoid updating user space RSEQ in that case just to do it eventually + * again before returning to user space, because __rseq_handle_slowpath() + * does nothing when invoked with NULL register state. + * + * After returning from guest mode, before exiting to userspace, hypervisors + * must invoke this function to re-raise TIF_NOTIFY_RESUME if necessary. + */ +static inline void rseq_virt_userspace_exit(void) { + /* + * The generic optimization for deferring RSEQ updates until the next + * exit relies on having a dedicated TIF_RSEQ. + */ + if (!IS_ENABLED(CONFIG_HAVE_GENERIC_TIF_BITS) && + current->rseq.event.sched_switch) + rseq_raise_notify_resume(current); } -static inline void rseq_preempt(struct task_struct *t) + +static inline void rseq_reset(struct task_struct *t) { + memset(&t->rseq, 0, sizeof(t->rseq)); + t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } -static inline void rseq_migrate(struct task_struct *t) + +static inline void rseq_execve(struct task_struct *t) { + rseq_reset(t); } + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Unregister rseq for a clone with CLONE_VM set. + * + * On fork, keep the IDs (CPU, MMCID) of the parent, which avoids a fault + * on the COW page on exit to user space, when the child stays on the same + * CPU as the parent. That's obviously not guaranteed, but in overcommit + * scenarios it is more likely and optimizes for the fork/exec case without + * taking the fault. + */ static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { -} -static inline void rseq_execve(struct task_struct *t) -{ + if (clone_flags & CLONE_VM) + rseq_reset(t); + else + t->rseq = current->rseq; } -#endif +#else /* CONFIG_RSEQ */ +static inline void rseq_handle_slowpath(struct pt_regs *regs) { } +static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } +static inline void rseq_sched_switch_event(struct task_struct *t) { } +static inline void rseq_sched_set_ids_changed(struct task_struct *t) { } +static inline void rseq_force_update(void) { } +static inline void rseq_virt_userspace_exit(void) { } +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { } +static inline void rseq_execve(struct task_struct *t) { } +#endif /* !CONFIG_RSEQ */ #ifdef CONFIG_DEBUG_RSEQ - void rseq_syscall(struct pt_regs *regs); - -#else - -static inline void rseq_syscall(struct pt_regs *regs) -{ -} - -#endif +#else /* CONFIG_DEBUG_RSEQ */ +static inline void rseq_syscall(struct pt_regs *regs) { } +#endif /* !CONFIG_DEBUG_RSEQ */ #endif /* _LINUX_RSEQ_H */ diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h new file mode 100644 index 000000000000..c92167ff8a7f --- /dev/null +++ b/include/linux/rseq_entry.h @@ -0,0 +1,616 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RSEQ_ENTRY_H +#define _LINUX_RSEQ_ENTRY_H + +/* Must be outside the CONFIG_RSEQ guard to resolve the stubs */ +#ifdef CONFIG_RSEQ_STATS +#include <linux/percpu.h> + +struct rseq_stats { + unsigned long exit; + unsigned long signal; + unsigned long slowpath; + unsigned long fastpath; + unsigned long ids; + unsigned long cs; + unsigned long clear; + unsigned long fixup; +}; + +DECLARE_PER_CPU(struct rseq_stats, rseq_stats); + +/* + * Slow path has interrupts and preemption enabled, but the fast path + * runs with interrupts disabled so there is no point in having the + * preemption checks implied in __this_cpu_inc() for every operation. + */ +#ifdef RSEQ_BUILD_SLOW_PATH +#define rseq_stat_inc(which) this_cpu_inc((which)) +#else +#define rseq_stat_inc(which) raw_cpu_inc((which)) +#endif + +#else /* CONFIG_RSEQ_STATS */ +#define rseq_stat_inc(x) do { } while (0) +#endif /* !CONFIG_RSEQ_STATS */ + +#ifdef CONFIG_RSEQ +#include <linux/jump_label.h> +#include <linux/rseq.h> +#include <linux/uaccess.h> + +#include <linux/tracepoint-defs.h> + +#ifdef CONFIG_TRACEPOINTS +DECLARE_TRACEPOINT(rseq_update); +DECLARE_TRACEPOINT(rseq_ip_fixup); +void __rseq_trace_update(struct task_struct *t); +void __rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip); + +static inline void rseq_trace_update(struct task_struct *t, struct rseq_ids *ids) +{ + if (tracepoint_enabled(rseq_update) && ids) + __rseq_trace_update(t); +} + +static inline void rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip) +{ + if (tracepoint_enabled(rseq_ip_fixup)) + __rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); +} + +#else /* CONFIG_TRACEPOINT */ +static inline void rseq_trace_update(struct task_struct *t, struct rseq_ids *ids) { } +static inline void rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip) { } +#endif /* !CONFIG_TRACEPOINT */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE, rseq_debug_enabled); + +#ifdef RSEQ_BUILD_SLOW_PATH +#define rseq_inline +#else +#define rseq_inline __always_inline +#endif + +bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); +bool rseq_debug_validate_ids(struct task_struct *t); + +static __always_inline void rseq_note_user_irq_entry(void) +{ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) + current->rseq.event.user_irq = true; +} + +/* + * Check whether there is a valid critical section and whether the + * instruction pointer in @regs is inside the critical section. + * + * - If the critical section is invalid, terminate the task. + * + * - If valid and the instruction pointer is inside, set it to the abort IP. + * + * - If valid and the instruction pointer is outside, clear the critical + * section address. + * + * Returns true, if the section was valid and either fixup or clear was + * done, false otherwise. + * + * In the failure case task::rseq_event::fatal is set when a invalid + * section was found. It's clear when the failure was an unresolved page + * fault. + * + * If inlined into the exit to user path with interrupts disabled, the + * caller has to protect against page faults with pagefault_disable(). + * + * In preemptible task context this would be counterproductive as the page + * faults could not be fully resolved. As a consequence unresolved page + * faults in task context are fatal too. + */ + +#ifdef RSEQ_BUILD_SLOW_PATH +/* + * The debug version is put out of line, but kept here so the code stays + * together. + * + * @csaddr has already been checked by the caller to be in user space + */ +bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, + unsigned long csaddr) +{ + struct rseq_cs __user *ucs = (struct rseq_cs __user *)(unsigned long)csaddr; + u64 start_ip, abort_ip, offset, cs_end, head, tasksize = TASK_SIZE; + unsigned long ip = instruction_pointer(regs); + u64 __user *uc_head = (u64 __user *) ucs; + u32 usig, __user *uc_sig; + + scoped_user_rw_access(ucs, efault) { + /* + * Evaluate the user pile and exit if one of the conditions + * is not fulfilled. + */ + unsafe_get_user(start_ip, &ucs->start_ip, efault); + if (unlikely(start_ip >= tasksize)) + goto die; + /* If outside, just clear the critical section. */ + if (ip < start_ip) + goto clear; + + unsafe_get_user(offset, &ucs->post_commit_offset, efault); + cs_end = start_ip + offset; + /* Check for overflow and wraparound */ + if (unlikely(cs_end >= tasksize || cs_end < start_ip)) + goto die; + + /* If not inside, clear it. */ + if (ip >= cs_end) + goto clear; + + unsafe_get_user(abort_ip, &ucs->abort_ip, efault); + /* Ensure it's "valid" */ + if (unlikely(abort_ip >= tasksize || abort_ip < sizeof(*uc_sig))) + goto die; + /* Validate that the abort IP is not in the critical section */ + if (unlikely(abort_ip - start_ip < offset)) + goto die; + + /* + * Check version and flags for 0. No point in emitting + * deprecated warnings before dying. That could be done in + * the slow path eventually, but *shrug*. + */ + unsafe_get_user(head, uc_head, efault); + if (unlikely(head)) + goto die; + + /* abort_ip - 4 is >= 0. See abort_ip check above */ + uc_sig = (u32 __user *)(unsigned long)(abort_ip - sizeof(*uc_sig)); + unsafe_get_user(usig, uc_sig, efault); + if (unlikely(usig != t->rseq.sig)) + goto die; + + /* rseq_event.user_irq is only valid if CONFIG_GENERIC_IRQ_ENTRY=y */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* If not in interrupt from user context, let it die */ + if (unlikely(!t->rseq.event.user_irq)) + goto die; + } + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + instruction_pointer_set(regs, (unsigned long)abort_ip); + rseq_stat_inc(rseq_stats.fixup); + break; + clear: + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + rseq_stat_inc(rseq_stats.clear); + abort_ip = 0ULL; + } + + if (unlikely(abort_ip)) + rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +/* + * On debug kernels validate that user space did not mess with it if the + * debug branch is enabled. + */ +bool rseq_debug_validate_ids(struct task_struct *t) +{ + struct rseq __user *rseq = t->rseq.usrptr; + u32 cpu_id, uval, node_id; + + /* + * On the first exit after registering the rseq region CPU ID is + * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! + */ + node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? + cpu_to_node(t->rseq.ids.cpu_id) : 0; + + scoped_user_read_access(rseq, efault) { + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +#endif /* RSEQ_BUILD_SLOW_PATH */ + +/* + * This only ensures that abort_ip is in the user address space and + * validates that it is preceded by the signature. + * + * No other sanity checks are done here, that's what the debug code is for. + */ +static rseq_inline bool +rseq_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr) +{ + struct rseq_cs __user *ucs = (struct rseq_cs __user *)(unsigned long)csaddr; + unsigned long ip = instruction_pointer(regs); + unsigned long tasksize = TASK_SIZE; + u64 start_ip, abort_ip, offset; + u32 usig, __user *uc_sig; + + rseq_stat_inc(rseq_stats.cs); + + if (unlikely(csaddr >= tasksize)) { + t->rseq.event.fatal = true; + return false; + } + + if (static_branch_unlikely(&rseq_debug_enabled)) + return rseq_debug_update_user_cs(t, regs, csaddr); + + scoped_user_rw_access(ucs, efault) { + unsafe_get_user(start_ip, &ucs->start_ip, efault); + unsafe_get_user(offset, &ucs->post_commit_offset, efault); + unsafe_get_user(abort_ip, &ucs->abort_ip, efault); + + /* + * No sanity checks. If user space screwed it up, it can + * keep the pieces. That's what debug code is for. + * + * If outside, just clear the critical section. + */ + if (ip - start_ip >= offset) + goto clear; + + /* + * Two requirements for @abort_ip: + * - Must be in user space as x86 IRET would happily return to + * the kernel. + * - The four bytes preceding the instruction at @abort_ip must + * contain the signature. + * + * The latter protects against the following attack vector: + * + * An attacker with limited abilities to write, creates a critical + * section descriptor, sets the abort IP to a library function or + * some other ROP gadget and stores the address of the descriptor + * in TLS::rseq::rseq_cs. An RSEQ abort would then evade ROP + * protection. + */ + if (unlikely(abort_ip >= tasksize || abort_ip < sizeof(*uc_sig))) + goto die; + + /* The address is guaranteed to be >= 0 and < TASK_SIZE */ + uc_sig = (u32 __user *)(unsigned long)(abort_ip - sizeof(*uc_sig)); + unsafe_get_user(usig, uc_sig, efault); + if (unlikely(usig != t->rseq.sig)) + goto die; + + /* Invalidate the critical section */ + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + /* Update the instruction pointer */ + instruction_pointer_set(regs, (unsigned long)abort_ip); + rseq_stat_inc(rseq_stats.fixup); + break; + clear: + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + rseq_stat_inc(rseq_stats.clear); + abort_ip = 0ULL; + } + + if (unlikely(abort_ip)) + rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +/* + * Updates CPU ID, Node ID and MM CID and reads the critical section + * address, when @csaddr != NULL. This allows to put the ID update and the + * read under the same uaccess region to spare a separate begin/end. + * + * As this is either invoked from a C wrapper with @csaddr = NULL or from + * the fast path code with a valid pointer, a clever compiler should be + * able to optimize the read out. Spares a duplicate implementation. + * + * Returns true, if the operation was successful, false otherwise. + * + * In the failure case task::rseq_event::fatal is set when invalid data + * was found on debug kernels. It's clear when the failure was an unresolved page + * fault. + * + * If inlined into the exit to user path with interrupts disabled, the + * caller has to protect against page faults with pagefault_disable(). + * + * In preemptible task context this would be counterproductive as the page + * faults could not be fully resolved. As a consequence unresolved page + * faults in task context are fatal too. + */ +static rseq_inline +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, + u32 node_id, u64 *csaddr) +{ + struct rseq __user *rseq = t->rseq.usrptr; + + if (static_branch_unlikely(&rseq_debug_enabled)) { + if (!rseq_debug_validate_ids(t)) + return false; + } + + scoped_user_rw_access(rseq, efault) { + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); + unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); + unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); + if (csaddr) + unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); + } + + /* Cache the new values */ + t->rseq.ids.cpu_cid = ids->cpu_cid; + rseq_stat_inc(rseq_stats.ids); + rseq_trace_update(t, ids); + return true; +efault: + return false; +} + +/* + * Update user space with new IDs and conditionally check whether the task + * is in a critical section. + */ +static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, + struct rseq_ids *ids, u32 node_id) +{ + u64 csaddr; + + if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + return false; + + /* + * On architectures which utilize the generic entry code this + * allows to skip the critical section when the entry was not from + * a user space interrupt, unless debug mode is enabled. + */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + if (!static_branch_unlikely(&rseq_debug_enabled)) { + if (likely(!t->rseq.event.user_irq)) + return true; + } + } + if (likely(!csaddr)) + return true; + /* Sigh, this really needs to do work */ + return rseq_update_user_cs(t, regs, csaddr); +} + +/* + * If you want to use this then convert your architecture to the generic + * entry code. I'm tired of building workarounds for people who can't be + * bothered to make the maintenance of generic infrastructure less + * burdensome. Just sucking everything into the architecture code and + * thereby making others chase the horrible hacks and keep them working is + * neither acceptable nor sustainable. + */ +#ifdef CONFIG_GENERIC_ENTRY + +/* + * This is inlined into the exit path because: + * + * 1) It's a one time comparison in the fast path when there is no event to + * handle + * + * 2) The access to the user space rseq memory (TLS) is unlikely to fault + * so the straight inline operation is: + * + * - Four 32-bit stores only if CPU ID/ MM CID need to be updated + * - One 64-bit load to retrieve the critical section address + * + * 3) In the unlikely case that the critical section address is != NULL: + * + * - One 64-bit load to retrieve the start IP + * - One 64-bit load to retrieve the offset for calculating the end + * - One 64-bit load to retrieve the abort IP + * - One 64-bit load to retrieve the signature + * - One store to clear the critical section address + * + * The non-debug case implements only the minimal required checking. It + * provides protection against a rogue abort IP in kernel space, which + * would be exploitable at least on x86, and also against a rogue CS + * descriptor by checking the signature at the abort IP. Any fallout from + * invalid critical section descriptors is a user space problem. The debug + * case provides the full set of checks and terminates the task if a + * condition is not met. + * + * In case of a fault or an invalid value, this sets TIF_NOTIFY_RESUME and + * tells the caller to loop back into exit_to_user_mode_loop(). The rseq + * slow path there will handle the failure. + */ +static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct task_struct *t) +{ + /* + * Page faults need to be disabled as this is called with + * interrupts disabled + */ + guard(pagefault)(); + if (likely(!t->rseq.event.ids_changed)) { + struct rseq __user *rseq = t->rseq.usrptr; + /* + * If IDs have not changed rseq_event::user_irq must be true + * See rseq_sched_switch_event(). + */ + u64 csaddr; + + if (unlikely(get_user_inline(csaddr, &rseq->rseq_cs))) + return false; + + if (static_branch_unlikely(&rseq_debug_enabled) || unlikely(csaddr)) { + if (unlikely(!rseq_update_user_cs(t, regs, csaddr))) + return false; + } + return true; + } + + struct rseq_ids ids = { + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + }; + u32 node_id = cpu_to_node(ids.cpu_id); + + return rseq_update_usr(t, regs, &ids, node_id); +} + +static __always_inline bool __rseq_exit_to_user_mode_restart(struct pt_regs *regs) +{ + struct task_struct *t = current; + + /* + * If the task did not go through schedule or got the flag enforced + * by the rseq syscall or execve, then nothing to do here. + * + * CPU ID and MM CID can only change when going through a context + * switch. + * + * rseq_sched_switch_event() sets the rseq_event::sched_switch bit + * only when rseq_event::has_rseq is true. That conditional is + * required to avoid setting the TIF bit if RSEQ is not registered + * for a task. rseq_event::sched_switch is cleared when RSEQ is + * unregistered by a task so it's sufficient to check for the + * sched_switch bit alone. + * + * A sane compiler requires three instructions for the nothing to do + * case including clearing the events, but your mileage might vary. + */ + if (unlikely((t->rseq.event.sched_switch))) { + rseq_stat_inc(rseq_stats.fastpath); + + if (unlikely(!rseq_exit_user_update(regs, t))) + return true; + } + /* Clear state so next entry starts from a clean slate */ + t->rseq.event.events = 0; + return false; +} + +/* Required to allow conversion to GENERIC_ENTRY w/o GENERIC_TIF_BITS */ +#ifdef CONFIG_HAVE_GENERIC_TIF_BITS +static __always_inline bool test_tif_rseq(unsigned long ti_work) +{ + return ti_work & _TIF_RSEQ; +} + +static __always_inline void clear_tif_rseq(void) +{ + static_assert(TIF_RSEQ != TIF_NOTIFY_RESUME); + clear_thread_flag(TIF_RSEQ); +} +#else +static __always_inline bool test_tif_rseq(unsigned long ti_work) { return true; } +static __always_inline void clear_tif_rseq(void) { } +#endif + +static __always_inline bool +rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + if (likely(!test_tif_rseq(ti_work))) + return false; + + if (unlikely(__rseq_exit_to_user_mode_restart(regs))) { + current->rseq.event.slowpath = true; + set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); + return true; + } + + clear_tif_rseq(); + return false; +} + +#else /* CONFIG_GENERIC_ENTRY */ +static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + return false; +} +#endif /* !CONFIG_GENERIC_ENTRY */ + +static __always_inline void rseq_syscall_exit_to_user_mode(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + /* Needed to remove the store for the !lockdep case */ + if (IS_ENABLED(CONFIG_LOCKDEP)) { + WARN_ON_ONCE(ev->sched_switch); + ev->events = 0; + } +} + +static __always_inline void rseq_irqentry_exit_to_user_mode(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + lockdep_assert_once(!ev->sched_switch); + + /* + * Ensure that event (especially user_irq) is cleared when the + * interrupt did not result in a schedule and therefore the + * rseq processing could not clear it. + */ + ev->events = 0; +} + +/* Required to keep ARM64 working */ +static __always_inline void rseq_exit_to_user_mode_legacy(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + if (static_branch_unlikely(&rseq_debug_enabled)) + WARN_ON_ONCE(ev->sched_switch); + + /* + * Ensure that event (especially user_irq) is cleared when the + * interrupt did not result in a schedule and therefore the + * rseq processing did not clear it. + */ + ev->events = 0; +} + +void __rseq_debug_syscall_return(struct pt_regs *regs); + +static inline void rseq_debug_syscall_return(struct pt_regs *regs) +{ + if (static_branch_unlikely(&rseq_debug_enabled)) + __rseq_debug_syscall_return(regs); +} +#else /* CONFIG_RSEQ */ +static inline void rseq_note_user_irq_entry(void) { } +static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + return false; +} +static inline void rseq_syscall_exit_to_user_mode(void) { } +static inline void rseq_irqentry_exit_to_user_mode(void) { } +static inline void rseq_exit_to_user_mode_legacy(void) { } +static inline void rseq_debug_syscall_return(struct pt_regs *regs) { } +#endif /* !CONFIG_RSEQ */ + +#endif /* _LINUX_RSEQ_ENTRY_H */ diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h new file mode 100644 index 000000000000..332dc14b81c9 --- /dev/null +++ b/include/linux/rseq_types.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RSEQ_TYPES_H +#define _LINUX_RSEQ_TYPES_H + +#include <linux/irq_work_types.h> +#include <linux/types.h> +#include <linux/workqueue_types.h> + +#ifdef CONFIG_RSEQ +struct rseq; + +/** + * struct rseq_event - Storage for rseq related event management + * @all: Compound to initialize and clear the data efficiently + * @events: Compound to access events with a single load/store + * @sched_switch: True if the task was scheduled and needs update on + * exit to user + * @ids_changed: Indicator that IDs need to be updated + * @user_irq: True on interrupt entry from user mode + * @has_rseq: True if the task has a rseq pointer installed + * @error: Compound error code for the slow path to analyze + * @fatal: User space data corrupted or invalid + * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME + * is required + * + * @sched_switch and @ids_changed must be adjacent and the combo must be + * 16bit aligned to allow a single store, when both are set at the same + * time in the scheduler. + */ +struct rseq_event { + union { + u64 all; + struct { + union { + u32 events; + struct { + u8 sched_switch; + u8 ids_changed; + u8 user_irq; + }; + }; + + u8 has_rseq; + u8 __pad; + union { + u16 error; + struct { + u8 fatal; + u8 slowpath; + }; + }; + }; + }; +}; + +/** + * struct rseq_ids - Cache for ids, which need to be updated + * @cpu_cid: Compound of @cpu_id and @mm_cid to make the + * compiler emit a single compare on 64-bit + * @cpu_id: The CPU ID which was written last to user space + * @mm_cid: The MM CID which was written last to user space + * + * @cpu_id and @mm_cid are updated when the data is written to user space. + */ +struct rseq_ids { + union { + u64 cpu_cid; + struct { + u32 cpu_id; + u32 mm_cid; + }; + }; +}; + +/** + * struct rseq_data - Storage for all rseq related data + * @usrptr: Pointer to the registered user space RSEQ memory + * @len: Length of the RSEQ region + * @sig: Signature of critial section abort IPs + * @event: Storage for event management + * @ids: Storage for cached CPU ID and MM CID + */ +struct rseq_data { + struct rseq __user *usrptr; + u32 len; + u32 sig; + struct rseq_event event; + struct rseq_ids ids; +}; + +#else /* CONFIG_RSEQ */ +struct rseq_data { }; +#endif /* !CONFIG_RSEQ */ + +#ifdef CONFIG_SCHED_MM_CID + +#define MM_CID_UNSET BIT(31) +#define MM_CID_ONCPU BIT(30) +#define MM_CID_TRANSIT BIT(29) + +/** + * struct sched_mm_cid - Storage for per task MM CID data + * @active: MM CID is active for the task + * @cid: The CID associated to the task either permanently or + * borrowed from the CPU + */ +struct sched_mm_cid { + unsigned int active; + unsigned int cid; +}; + +/** + * struct mm_cid_pcpu - Storage for per CPU MM_CID data + * @cid: The CID associated to the CPU either permanently or + * while a task with a CID is running + */ +struct mm_cid_pcpu { + unsigned int cid; +}____cacheline_aligned_in_smp; + +/** + * struct mm_mm_cid - Storage for per MM CID data + * @pcpu: Per CPU storage for CIDs associated to a CPU + * @percpu: Set, when CIDs are in per CPU mode + * @transit: Set to MM_CID_TRANSIT during a mode change transition phase + * @max_cids: The exclusive maximum CID value for allocation and convergence + * @irq_work: irq_work to handle the affinity mode change case + * @work: Regular work to handle the affinity mode change case + * @lock: Spinlock to protect against affinity setting which can't take @mutex + * @mutex: Mutex to serialize forks and exits related to this mm + * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map + * is growth only. + * @users: The number of tasks sharing this MM. Separate from mm::mm_users + * as that is modified by mmget()/mm_put() by other entities which + * do not actually share the MM. + * @pcpu_thrs: Threshold for switching back from per CPU mode + * @update_deferred: A deferred switch back to per task mode is pending. + */ +struct mm_mm_cid { + /* Hotpath read mostly members */ + struct mm_cid_pcpu __percpu *pcpu; + unsigned int percpu; + unsigned int transit; + unsigned int max_cids; + + /* Rarely used. Moves @lock and @mutex into the second cacheline */ + struct irq_work irq_work; + struct work_struct work; + + raw_spinlock_t lock; + struct mutex mutex; + + /* Low frequency modified */ + unsigned int nr_cpus_allowed; + unsigned int users; + unsigned int pcpu_thrs; + unsigned int update_deferred; +}____cacheline_aligned_in_smp; +#else /* CONFIG_SCHED_MM_CID */ +struct mm_mm_cid { }; +struct sched_mm_cid { }; +#endif /* !CONFIG_SCHED_MM_CID */ + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index e84bc5bce816..fac12bb7dbe4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -41,7 +41,7 @@ #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> -#include <uapi/linux/rseq.h> +#include <linux/rseq_types.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> @@ -1406,33 +1406,8 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_RSEQ - struct rseq __user *rseq; - u32 rseq_len; - u32 rseq_sig; - /* - * RmW on rseq_event_mask must be performed atomically - * with respect to preemption. - */ - unsigned long rseq_event_mask; -# ifdef CONFIG_DEBUG_RSEQ - /* - * This is a place holder to save a copy of the rseq fields for - * validation of read-only fields. The struct rseq has a - * variable-length array at the end, so it cannot be used - * directly. Reserve a size large enough for the known fields. - */ - char rseq_fields[sizeof(struct rseq)]; -# endif -#endif - -#ifdef CONFIG_SCHED_MM_CID - int mm_cid; /* Current cid in mm */ - int last_mm_cid; /* Most recent cid in mm */ - int migrate_from_cpu; - int mm_cid_active; /* Whether cid bitmap is active */ - struct callback_head cid_work; -#endif + struct rseq_data rseq; + struct sched_mm_cid mm_cid; struct tlbflush_unmap_batch tlb_ubc; @@ -1901,6 +1876,7 @@ extern int sched_setscheduler(struct task_struct *, int, const struct sched_para extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); +extern void sched_set_fifo_secondary(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); @@ -2325,6 +2301,32 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #define alloc_tag_restore(_tag, _old) do {} while (0) #endif +/* Avoids recursive inclusion hell */ +#ifdef CONFIG_SCHED_MM_CID +void sched_mm_cid_before_execve(struct task_struct *t); +void sched_mm_cid_after_execve(struct task_struct *t); +void sched_mm_cid_fork(struct task_struct *t); +void sched_mm_cid_exit(struct task_struct *t); +static __always_inline int task_mm_cid(struct task_struct *t) +{ + return t->mm_cid.cid & ~(MM_CID_ONCPU | MM_CID_TRANSIT); +} +#else +static inline void sched_mm_cid_before_execve(struct task_struct *t) { } +static inline void sched_mm_cid_after_execve(struct task_struct *t) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } +static inline void sched_mm_cid_exit(struct task_struct *t) { } +static __always_inline int task_mm_cid(struct task_struct *t) +{ + /* + * Use the processor id as a fall-back when the mm cid feature is + * disabled. This provides functional per-cpu data structure accesses + * in user-space, althrough it won't provide the memory usage benefits. + */ + return task_cpu(t); +} +#endif + #ifndef MODULE #ifndef COMPILE_OFFSETS diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index dd925d84fa46..b40de9bab4b7 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -67,6 +67,11 @@ enum syscall_work_bit { #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif +#ifndef TIF_RSEQ +# define TIF_RSEQ TIF_NOTIFY_RESUME +# define _TIF_RSEQ _TIF_NOTIFY_RESUME +#endif + #ifdef __KERNEL__ #ifndef arch_set_restart_data diff --git a/include/linux/timer.h b/include/linux/timer.h index 0414d9e6b4fc..62e1cea71125 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -188,4 +188,13 @@ int timers_dead_cpu(unsigned int cpu); #define timers_dead_cpu NULL #endif +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask); +#else +static inline int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) +{ + return 0; +} +#endif + #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1beb5b395d81..be395f5f7ee3 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -2,6 +2,7 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ +#include <linux/cleanup.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> @@ -35,9 +36,17 @@ #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 +# ifndef masked_user_write_access_begin +# define masked_user_write_access_begin masked_user_access_begin +# endif +# ifndef masked_user_read_access_begin +# define masked_user_read_access_begin masked_user_access_begin +#endif #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define masked_user_read_access_begin(src) NULL + #define masked_user_write_access_begin(src) NULL #define mask_user_address(src) (src) #endif @@ -518,7 +527,34 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); -#ifndef __get_kernel_nofault +#ifdef arch_get_kernel_nofault +/* + * Wrap the architecture implementation so that @label can be outside of a + * cleanup() scope. A regular C goto works correctly, but ASM goto does + * not. Clang rejects such an attempt, but GCC silently emits buggy code. + */ +#define __get_kernel_nofault(dst, src, type, label) \ +do { \ + __label__ local_label; \ + arch_get_kernel_nofault(dst, src, type, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, label) \ +do { \ + __label__ local_label; \ + arch_put_kernel_nofault(dst, src, type, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#elif !defined(__get_kernel_nofault) /* arch_get_kernel_nofault */ + #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ @@ -535,7 +571,8 @@ do { \ if (__put_user(data, p)) \ goto label; \ } while (0) -#endif + +#endif /* !__get_kernel_nofault */ /** * get_kernel_nofault(): safely attempt to read from a location @@ -549,7 +586,42 @@ do { \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) -#ifndef user_access_begin +#ifdef user_access_begin + +#ifdef arch_unsafe_get_user +/* + * Wrap the architecture implementation so that @label can be outside of a + * cleanup() scope. A regular C goto works correctly, but ASM goto does + * not. Clang rejects such an attempt, but GCC silently emits buggy code. + * + * Some architectures use internal local labels already, but this extra + * indirection here is harmless because the compiler optimizes it out + * completely in any case. This construct just ensures that the ASM GOTO + * target is always in the local scope. The C goto 'label' works correctly + * when leaving a cleanup() scope. + */ +#define unsafe_get_user(x, ptr, label) \ +do { \ + __label__ local_label; \ + arch_unsafe_get_user(x, ptr, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#define unsafe_put_user(x, ptr, label) \ +do { \ + __label__ local_label; \ + arch_unsafe_put_user(x, ptr, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) +#endif /* arch_unsafe_get_user */ + +#else /* user_access_begin */ #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) @@ -559,7 +631,8 @@ do { \ #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } -#endif +#endif /* !user_access_begin */ + #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end @@ -569,6 +642,239 @@ static inline void user_access_restore(unsigned long flags) { } #define user_read_access_end user_access_end #endif +/* Define RW variant so the below _mode macro expansion works */ +#define masked_user_rw_access_begin(u) masked_user_access_begin(u) +#define user_rw_access_begin(u, s) user_access_begin(u, s) +#define user_rw_access_end() user_access_end() + +/* Scoped user access */ +#define USER_ACCESS_GUARD(_mode) \ +static __always_inline void __user * \ +class_user_##_mode##_begin(void __user *ptr) \ +{ \ + return ptr; \ +} \ + \ +static __always_inline void \ +class_user_##_mode##_end(void __user *ptr) \ +{ \ + user_##_mode##_access_end(); \ +} \ + \ +DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ + class_user_##_mode##_end(_T), \ + class_user_##_mode##_begin(ptr), void __user *ptr) \ + \ +static __always_inline class_user_##_mode##_access_t \ +class_user_##_mode##_access_ptr(void __user *scope) \ +{ \ + return scope; \ +} + +USER_ACCESS_GUARD(read) +USER_ACCESS_GUARD(write) +USER_ACCESS_GUARD(rw) +#undef USER_ACCESS_GUARD + +/** + * __scoped_user_access_begin - Start a scoped user access + * @mode: The mode of the access class (read, write, rw) + * @uptr: The pointer to access user space memory + * @size: Size of the access + * @elbl: Error label to goto when the access region is rejected + * + * Internal helper for __scoped_user_access(). Don't use directly. + */ +#define __scoped_user_access_begin(mode, uptr, size, elbl) \ +({ \ + typeof(uptr) __retptr; \ + \ + if (can_do_masked_user_access()) { \ + __retptr = masked_user_##mode##_access_begin(uptr); \ + } else { \ + __retptr = uptr; \ + if (!user_##mode##_access_begin(uptr, size)) \ + goto elbl; \ + } \ + __retptr; \ +}) + +/** + * __scoped_user_access - Open a scope for user access + * @mode: The mode of the access class (read, write, rw) + * @uptr: The pointer to access user space memory + * @size: Size of the access + * @elbl: Error label to goto when the access region is rejected. It + * must be placed outside the scope + * + * If the user access function inside the scope requires a fault label, it + * can use @elbl or a different label outside the scope, which requires + * that user access which is implemented with ASM GOTO has been properly + * wrapped. See unsafe_get_user() for reference. + * + * scoped_user_rw_access(ptr, efault) { + * unsafe_get_user(rval, &ptr->rval, efault); + * unsafe_put_user(wval, &ptr->wval, efault); + * } + * return 0; + * efault: + * return -EFAULT; + * + * The scope is internally implemented as a autoterminating nested for() + * loop, which can be left with 'return', 'break' and 'goto' at any + * point. + * + * When the scope is left user_##@_mode##_access_end() is automatically + * invoked. + * + * When the architecture supports masked user access and the access region + * which is determined by @uptr and @size is not a valid user space + * address, i.e. < TASK_SIZE, the scope sets the pointer to a faulting user + * space address and does not terminate early. This optimizes for the good + * case and lets the performance uncritical bad case go through the fault. + * + * The eventual modification of the pointer is limited to the scope. + * Outside of the scope the original pointer value is unmodified, so that + * the original pointer value is available for diagnostic purposes in an + * out of scope fault path. + * + * Nesting scoped user access into a user access scope is invalid and fails + * the build. Nesting into other guards, e.g. pagefault is safe. + * + * The masked variant does not check the size of the access and relies on a + * mapping hole (e.g. guard page) to catch an out of range pointer, the + * first access to user memory inside the scope has to be within + * @uptr ... @uptr + PAGE_SIZE - 1 + * + * Don't use directly. Use scoped_masked_user_$MODE_access() instead. + */ +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const typeof(uptr) uptr = _tmpptr; !done; done = true) + +/** + * scoped_user_read_access_size - Start a scoped user read access with given size + * @usrc: Pointer to the user space address to read from + * @size: Size of the access starting from @usrc + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_read_access_size(usrc, size, elbl) \ + __scoped_user_access(read, usrc, size, elbl) + +/** + * scoped_user_read_access - Start a scoped user read access + * @usrc: Pointer to the user space address to read from + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @usrc is determined via sizeof(*@usrc)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_read_access(usrc, elbl) \ + scoped_user_read_access_size(usrc, sizeof(*(usrc)), elbl) + +/** + * scoped_user_write_access_size - Start a scoped user write access with given size + * @udst: Pointer to the user space address to write to + * @size: Size of the access starting from @udst + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_write_access_size(udst, size, elbl) \ + __scoped_user_access(write, udst, size, elbl) + +/** + * scoped_user_write_access - Start a scoped user write access + * @udst: Pointer to the user space address to write to + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @udst is determined via sizeof(*@udst)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_write_access(udst, elbl) \ + scoped_user_write_access_size(udst, sizeof(*(udst)), elbl) + +/** + * scoped_user_rw_access_size - Start a scoped user read/write access with given size + * @uptr Pointer to the user space address to read from and write to + * @size: Size of the access starting from @uptr + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_rw_access_size(uptr, size, elbl) \ + __scoped_user_access(rw, uptr, size, elbl) + +/** + * scoped_user_rw_access - Start a scoped user read/write access + * @uptr Pointer to the user space address to read from and write to + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @uptr is determined via sizeof(*@uptr)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_rw_access(uptr, elbl) \ + scoped_user_rw_access_size(uptr, sizeof(*(uptr)), elbl) + +/** + * get_user_inline - Read user data inlined + * @val: The variable to store the value read from user memory + * @usrc: Pointer to the user space memory to read from + * + * Return: 0 if successful, -EFAULT when faulted + * + * Inlined variant of get_user(). Only use when there is a demonstrable + * performance reason. + */ +#define get_user_inline(val, usrc) \ +({ \ + __label__ efault; \ + typeof(usrc) _tmpsrc = usrc; \ + int _ret = 0; \ + \ + scoped_user_read_access(_tmpsrc, efault) \ + unsafe_get_user(val, _tmpsrc, efault); \ + if (0) { \ + efault: \ + _ret = -EFAULT; \ + } \ + _ret; \ +}) + +/** + * put_user_inline - Write to user memory inlined + * @val: The value to write + * @udst: Pointer to the user space memory to write to + * + * Return: 0 if successful, -EFAULT when faulted + * + * Inlined variant of put_user(). Only use when there is a demonstrable + * performance reason. + */ +#define put_user_inline(val, udst) \ +({ \ + __label__ efault; \ + typeof(udst) _tmpdst = udst; \ + int _ret = 0; \ + \ + scoped_user_write_access(_tmpdst, efault) \ + unsafe_put_user(val, _tmpdst, efault); \ + if (0) { \ + efault: \ + _ret = -EFAULT; \ + } \ + _ret; \ +}) + #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, |