diff options
Diffstat (limited to 'include/linux')
58 files changed, 474 insertions, 290 deletions
diff --git a/include/linux/bio.h b/include/linux/bio.h index bb6090aa165d..e584673c1881 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -120,19 +120,23 @@ static inline bool bio_full(struct bio *bio) return bio->bi_vcnt >= bio->bi_max_vecs; } -#define mp_bvec_for_each_segment(bv, bvl, i, iter_all) \ - for (bv = bvec_init_iter_all(&iter_all); \ - (iter_all.done < (bvl)->bv_len) && \ - (mp_bvec_next_segment((bvl), &iter_all), 1); \ - iter_all.done += bv->bv_len, i += 1) +static inline bool bio_next_segment(const struct bio *bio, + struct bvec_iter_all *iter) +{ + if (iter->idx >= bio->bi_vcnt) + return false; + + bvec_advance(&bio->bi_io_vec[iter->idx], iter); + return true; +} /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ -#define bio_for_each_segment_all(bvl, bio, i, iter_all) \ - for (i = 0, iter_all.idx = 0; iter_all.idx < (bio)->bi_vcnt; iter_all.idx++) \ - mp_bvec_for_each_segment(bvl, &((bio)->bi_io_vec[iter_all.idx]), i, iter_all) +#define bio_for_each_segment_all(bvl, bio, i, iter) \ + for (i = 0, bvl = bvec_init_iter_all(&iter); \ + bio_next_segment((bio), &iter); i++) static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, unsigned bytes) diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 50fb0dee23e8..d35b8ec1c485 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -34,41 +34,41 @@ static inline u32 __bitrev32(u32 x) #define __constant_bitrev32(x) \ ({ \ - u32 __x = x; \ - __x = (__x >> 16) | (__x << 16); \ - __x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8); \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = (___x >> 16) | (___x << 16); \ + ___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8); \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev16(x) \ ({ \ - u16 __x = x; \ - __x = (__x >> 8) | (__x << 8); \ - __x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4); \ - __x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2); \ - __x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1); \ - __x; \ + u16 ___x = x; \ + ___x = (___x >> 8) | (___x << 8); \ + ___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4); \ + ___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2); \ + ___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1); \ + ___x; \ }) #define __constant_bitrev8x4(x) \ ({ \ - u32 __x = x; \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev8(x) \ ({ \ - u8 __x = x; \ - __x = (__x >> 4) | (__x << 4); \ - __x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2); \ - __x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1); \ - __x; \ + u8 ___x = x; \ + ___x = (___x >> 4) | (___x << 4); \ + ___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2); \ + ___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1); \ + ___x; \ }) #define bitrev32(x) \ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index cb2aa7ecafff..db29928de467 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -302,6 +302,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); bool blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request_sync(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio); bool blk_mq_queue_stopped(struct request_queue *q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f02367faa58d..944ccc310201 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -510,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } \ _out: \ rcu_read_unlock(); \ - preempt_enable_no_resched(); \ + preempt_enable(); \ _ret; \ }) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f6275c4da13a..ff13cbc1887d 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -145,26 +145,33 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { - iter_all->bv.bv_page = NULL; iter_all->done = 0; + iter_all->idx = 0; return &iter_all->bv; } -static inline void mp_bvec_next_segment(const struct bio_vec *bvec, - struct bvec_iter_all *iter_all) +static inline void bvec_advance(const struct bio_vec *bvec, + struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; - if (bv->bv_page) { + if (iter_all->done) { bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset; + bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / + PAGE_SIZE); + bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); + iter_all->done += bv->bv_len; + + if (iter_all->done == bvec->bv_len) { + iter_all->idx++; + iter_all->done = 0; + } } /* diff --git a/include/linux/clk.h b/include/linux/clk.h index d8bc1a856b39..f689fc58d7be 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent) return true; } +static inline int clk_set_rate_range(struct clk *clk, unsigned long min, + unsigned long max) +{ + return 0; +} + +static inline int clk_set_min_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + +static inline int clk_set_max_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + static inline int clk_set_parent(struct clk *clk, struct clk *parent) { return 0; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 445348facea9..d58aa0db05f9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -67,7 +67,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, .line = __LINE__, \ }; \ ______r = !!(cond); \ - ______f.miss_hit[______r]++; \ + ______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\ ______r; \ })) #endif /* CONFIG_PROFILE_ALL_BRANCHES */ diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5041357d0297..732745f865b7 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void) return freeze_secondary_cpus(0); } extern void enable_nonboot_cpus(void); + +static inline int suspend_disable_secondary_cpus(void) +{ + int cpu = 0; + + if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) + cpu = -1; + + return freeze_secondary_cpus(cpu); +} +static inline void suspend_enable_secondary_cpus(void) +{ + return enable_nonboot_cpus(); +} + #else /* !CONFIG_PM_SLEEP_SMP */ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} +static inline int suspend_disable_secondary_cpus(void) { return 0; } +static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ void cpu_startup_entry(enum cpuhp_state state); @@ -175,6 +192,7 @@ enum cpuhp_smt_control { CPU_SMT_DISABLED, CPU_SMT_FORCE_DISABLED, CPU_SMT_NOT_SUPPORTED, + CPU_SMT_NOT_IMPLEMENTED, }; #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) @@ -182,9 +200,33 @@ extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology(void); #else -# define cpu_smt_control (CPU_SMT_ENABLED) +# define cpu_smt_control (CPU_SMT_NOT_IMPLEMENTED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } #endif +/* + * These are used for a global "mitigations=" cmdline option for toggling + * optional CPU mitigations. + */ +enum cpu_mitigations { + CPU_MITIGATIONS_OFF, + CPU_MITIGATIONS_AUTO, + CPU_MITIGATIONS_AUTO_NOSMT, +}; + +extern enum cpu_mitigations cpu_mitigations; + +/* mitigations=off */ +static inline bool cpu_mitigations_off(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_OFF; +} + +/* mitigations=auto,nosmt */ +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; +} + #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/dmi.h b/include/linux/dmi.h index c46fdb36700b..8de8c4f15163 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -102,9 +102,7 @@ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); -extern void dmi_scan_machine(void); -extern void dmi_memdev_walk(void); -extern void dmi_set_dump_stack_arch_desc(void); +extern void dmi_setup(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_get_bios_year(void); extern int dmi_name_in_vendors(const char *str); @@ -122,9 +120,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0; static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } -static inline void dmi_scan_machine(void) { return; } -static inline void dmi_memdev_walk(void) { } -static inline void dmi_set_dump_stack_arch_desc(void) { } +static inline void dmi_setup(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { if (yearp) diff --git a/include/linux/efi.h b/include/linux/efi.h index 54357a258b35..6ebc2098cfe1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1611,7 +1611,12 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size); -bool efi_runtime_disabled(void); +#ifdef CONFIG_EFI +extern bool efi_runtime_disabled(void); +#else +static inline bool efi_runtime_disabled(void) { return true; } +#endif + extern void efi_call_virt_check_flags(unsigned long flags, const char *call); extern unsigned long efi_call_virt_save_flags(void); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2e9e2763bf47..6e8bc53740f0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -31,6 +31,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -449,6 +449,18 @@ static inline void eth_addr_dec(u8 *addr) } /** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + +/** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address diff --git a/include/linux/filter.h b/include/linux/filter.h index 6074aa064b54..7d3abde3f183 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,6 +20,7 @@ #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> +#include <linux/vmalloc.h> #include <net/sch_generic.h> @@ -503,7 +504,6 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -733,24 +733,15 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - fp->undo_set_mem = 1; + set_vm_flush_reset_perms(fp); set_memory_ro((unsigned long)fp, fp->pages); } -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ - if (fp->undo_set_mem) - set_memory_rw((unsigned long)fp, fp->pages); -} - static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + set_vm_flush_reset_perms(hdr); set_memory_ro((unsigned long)hdr, hdr->pages); -} - -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - set_memory_rw((unsigned long)hdr, hdr->pages); + set_memory_x((unsigned long)hdr, hdr->pages); } static inline struct bpf_binary_header * @@ -788,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { - bpf_prog_unlock_ro(fp); __bpf_prog_free(fp); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 8b42df09b04c..dd28e7679089 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -158,6 +158,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) +/* File is stream-like */ +#define FMODE_STREAM ((__force fmode_t)0x200000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -3074,6 +3077,7 @@ extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); +extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 730876187344..20899919ead8 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,21 +241,11 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { #ifdef CONFIG_STACK_TRACER -#define STACK_TRACE_ENTRIES 500 - -struct stack_trace; - -extern unsigned stack_trace_index[]; -extern struct stack_trace stack_trace_max; -extern unsigned long stack_trace_max_size; -extern arch_spinlock_t stack_trace_max_lock; - extern int stack_tracer_enabled; -void stack_trace_print(void); -int -stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + +int stack_trace_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); diff --git a/include/linux/ima.h b/include/linux/ima.h index dc12fbcf484c..fd9f7cf4cdf5 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,7 +31,7 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif -#if defined(CONFIG_X86) && defined(CONFIG_EFI) +#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390) extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); #else diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 690b238a44d5..c7eef32e7739 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); -struct tasklet_hrtimer { - struct hrtimer timer; - struct tasklet_struct tasklet; - enum hrtimer_restart (*function)(struct hrtimer *); -}; - -extern void -tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode); - -static inline -void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) -{ - hrtimer_start(&ttimer->timer, time, mode); -} - -static inline -void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) -{ - hrtimer_cancel(&ttimer->timer); - tasklet_kill(&ttimer->tasklet); -} - /* * Autoprobing for irqs: * diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index a49f2b45b3f0..42710d5949ba 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -12,21 +12,79 @@ struct static_key_deferred { struct delayed_work work; }; -extern void static_key_slow_dec_deferred(struct static_key_deferred *key); -extern void static_key_deferred_flush(struct static_key_deferred *key); +struct static_key_true_deferred { + struct static_key_true key; + unsigned long timeout; + struct delayed_work work; +}; + +struct static_key_false_deferred { + struct static_key_false key; + unsigned long timeout; + struct delayed_work work; +}; + +#define static_key_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout) +#define static_branch_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout) + +#define static_key_deferred_flush(x) \ + __static_key_deferred_flush((x), &(x)->work) + +extern void +__static_key_slow_dec_deferred(struct static_key *key, + struct delayed_work *work, + unsigned long timeout); +extern void __static_key_deferred_flush(void *key, struct delayed_work *work); extern void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); +extern void jump_label_update_timeout(struct work_struct *work); + +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { \ + .key = { STATIC_KEY_INIT_TRUE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { \ + .key = { STATIC_KEY_INIT_FALSE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) + #else /* !CONFIG_JUMP_LABEL */ struct static_key_deferred { struct static_key key; }; +struct static_key_true_deferred { + struct static_key_true key; +}; +struct static_key_false_deferred { + struct static_key_false key; +}; +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT } +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT } + +#define static_branch_slow_dec_deferred(x) static_branch_dec(&(x)->key) + static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) { STATIC_KEY_CHECK_USE(key); static_key_slow_dec(&key->key); } -static inline void static_key_deferred_flush(struct static_key_deferred *key) +static inline void static_key_deferred_flush(void *key) { STATIC_KEY_CHECK_USE(key); } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 34a5036debd3..2d14e21c16c0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -47,8 +47,8 @@ #define u64_to_user_ptr(x) ( \ { \ - typecheck(u64, x); \ - (void __user *)(uintptr_t)x; \ + typecheck(u64, (x)); \ + (void __user *)(uintptr_t)(x); \ } \ ) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 201f0f2683f2..9a897256e481 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; }; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..640a03642766 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include <linux/irqbypass.h> #include <linux/swait.h> #include <linux/refcount.h> +#include <linux/nospec.h> #include <asm/signal.h> #include <linux/kvm.h> @@ -513,10 +514,10 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { - /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case - * the caller has read kvm->online_vcpus before (as is the case - * for kvm_for_each_vcpu, for example). - */ + int num_vcpus = atomic_read(&kvm->online_vcpus); + i = array_index_nospec(i, num_vcpus); + + /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return kvm->vcpus[i]; } @@ -600,6 +601,7 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { + as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 79c3873d58ac..6e2377e6c1d6 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -66,6 +66,11 @@ struct lock_class_key { extern struct lock_class_key __lockdep_no_validate__; +struct lock_trace { + unsigned int nr_entries; + unsigned int offset; +}; + #define LOCKSTAT_POINTS 4 /* @@ -100,7 +105,7 @@ struct lock_class { * IRQ/softirq usage tracking bits: */ unsigned long usage_mask; - struct stack_trace usage_traces[XXX_LOCK_USAGE_STATES]; + struct lock_trace usage_traces[XXX_LOCK_USAGE_STATES]; /* * Generation counter, when doing certain classes of graph walking, @@ -188,7 +193,7 @@ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; - struct stack_trace trace; + struct lock_trace trace; int distance; /* @@ -471,7 +476,7 @@ struct pin_cookie { }; #define NIL_COOKIE (struct pin_cookie){ } -#define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) +#define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1f3d880b7ca1..dbb6118370c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); -/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { diff --git a/include/linux/mii.h b/include/linux/mii.h index 6fee8b1a4400..5cd824c1c0ca 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -469,7 +469,7 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_CAP; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_ASYM; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 022541dc5dbf..0d0729648844 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -594,6 +594,8 @@ enum mlx5_pagefault_type_flags { }; struct mlx5_td { + /* protects tirs list changes while tirs refresh */ + struct mutex list_lock; struct list_head tirs_list; u32 tdn; }; diff --git a/include/linux/mm.h b/include/linux/mm.h index 76769749b5a5..083d7b4863ed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -966,6 +966,10 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } #endif /* CONFIG_DEV_PAGEMAP_OPS */ +/* 127: arbitrary random number, small enough to assemble well */ +#define page_ref_zero_or_close_to_overflow(page) \ + ((unsigned int) page_ref_count(page) + 127u <= 127u) + static inline void get_page(struct page *page) { page = compound_head(page); @@ -973,10 +977,19 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ - VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } +static inline __must_check bool try_get_page(struct page *page) +{ + page = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + page_ref_inc(page); + return true; +} + static inline void put_page(struct page *page) { page = compound_head(page); @@ -2597,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; -extern void __kernel_map_pages(struct page *page, int numpages, int enable); static inline bool debug_pagealloc_enabled(void) { - return _debug_pagealloc_enabled; + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled; } +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) +extern void __kernel_map_pages(struct page *page, int numpages, int enable); + static inline void kernel_map_pages(struct page *page, int numpages, int enable) { - if (!debug_pagealloc_enabled()) - return; - __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ -#else /* CONFIG_DEBUG_PAGEALLOC */ +#else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ -static inline bool debug_pagealloc_enabled(void) -{ - return false; -} -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7eade9132f02..4ef4bbe78a1d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -671,7 +671,7 @@ enum vm_fault_reason { /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) -#define VM_FAULT_GET_HINDEX(x) (((x) >> 16) & 0xf) +#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..324e872c91d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1500,6 +1500,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1532,6 +1533,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1563,6 +1565,7 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER +#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /** * struct net_device - The DEVICE structure. diff --git a/include/linux/nvme.h b/include/linux/nvme.h index baa49e6a23cc..c40720cb59ac 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -967,8 +967,13 @@ struct nvme_get_log_page_command { __le16 numdl; __le16 numdu; __u16 rsvd11; - __le32 lpol; - __le32 lpou; + union { + struct { + __le32 lpol; + __le32 lpou; + }; + __le64 lpo; + }; __u32 rsvd14[2]; }; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..15a82ff0aefe 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -240,7 +240,6 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 -#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 @@ -464,7 +463,7 @@ enum perf_addr_filter_action_t { /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage - * @inode: object file's inode for file-based filters + * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop @@ -888,6 +887,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); + +extern void perf_pmu_resched(struct pmu *pmu); + extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); @@ -1055,12 +1057,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 787d224ff43e..5c626fdc10db 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -101,18 +101,20 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. */ -static inline void pipe_buf_get(struct pipe_inode_info *pipe, +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - buf->ops->get(pipe, buf); + return buf->ops->get(pipe, buf); } /** @@ -171,9 +173,10 @@ struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); diff --git a/include/linux/platform_data/x86/clk-pmc-atom.h b/include/linux/platform_data/x86/clk-pmc-atom.h index 3ab892208343..7a37ac27d0fb 100644 --- a/include/linux/platform_data/x86/clk-pmc-atom.h +++ b/include/linux/platform_data/x86/clk-pmc-atom.h @@ -35,10 +35,13 @@ struct pmc_clk { * * @base: PMC clock register base offset * @clks: pointer to set of registered clocks, typically 0..5 + * @critical: flag to indicate if firmware enabled pmc_plt_clks + * should be marked as critial or not */ struct pmc_clk_data { void __iomem *base; const struct pmc_clk *clks; + bool critical; }; #endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index edb9b040c94c..d5084ebd9f03 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -9,6 +9,13 @@ #include <linux/bug.h> /* For BUG_ON. */ #include <linux/pid_namespace.h> /* For task_active_pid_ns. */ #include <uapi/linux/ptrace.h> +#include <linux/seccomp.h> + +/* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */ +struct syscall_info { + __u64 sp; + struct seccomp_data data; +}; extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); @@ -407,9 +414,7 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif -extern int task_current_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc); +extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6cdb1db776cf..922bb6848813 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -878,9 +878,11 @@ static inline void rcu_head_init(struct rcu_head *rhp) static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { - if (READ_ONCE(rhp->func) == f) + rcu_callback_t func = READ_ONCE(rhp->func); + + if (func == f) return true; - WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L); + WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 90bfa3279a01..563290fc194f 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -18,7 +18,7 @@ * awoken. */ struct rcuwait { - struct task_struct *task; + struct task_struct __rcu *task; }; #define __RCUWAIT_INITIALIZER(name) \ diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h deleted file mode 100644 index e47568363e5e..000000000000 --- a/include/linux/rwsem-spinlock.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem-spinlock.h: fallback C implementation - * - * Copyright (c) 2001 David Howells (dhowells@redhat.com). - * - Derived partially from ideas by Andrea Arcangeli <andrea@suse.de> - * - Derived also from comments by Linus - */ - -#ifndef _LINUX_RWSEM_SPINLOCK_H -#define _LINUX_RWSEM_SPINLOCK_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -/* - * the rw-semaphore definition - * - if count is 0 then there are no active readers or writers - * - if count is +ve then that is the number of active readers - * - if count is -1 then there is one active writer - * - if wait_list is not empty, then there are processes waiting for the semaphore - */ -struct rw_semaphore { - __s32 count; - raw_spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#define RWSEM_UNLOCKED_VALUE 0x00000000 - -extern void __down_read(struct rw_semaphore *sem); -extern int __must_check __down_read_killable(struct rw_semaphore *sem); -extern int __down_read_trylock(struct rw_semaphore *sem); -extern void __down_write(struct rw_semaphore *sem); -extern int __must_check __down_write_killable(struct rw_semaphore *sem); -extern int __down_write_trylock(struct rw_semaphore *sem); -extern void __up_read(struct rw_semaphore *sem); -extern void __up_write(struct rw_semaphore *sem); -extern void __downgrade_write(struct rw_semaphore *sem); -extern int rwsem_is_locked(struct rw_semaphore *sem); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_RWSEM_SPINLOCK_H */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 67dbb57508b1..2ea18a3def04 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -20,25 +20,30 @@ #include <linux/osq_lock.h> #endif -struct rw_semaphore; - -#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK -#include <linux/rwsem-spinlock.h> /* use a generic implementation */ -#define __RWSEM_INIT_COUNT(name) .count = RWSEM_UNLOCKED_VALUE -#else -/* All arch specific implementations share the same struct */ +/* + * For an uncontended rwsem, count and owner are the only fields a task + * needs to touch when acquiring the rwsem. So they are put next to each + * other to increase the chance that they will share the same cacheline. + * + * In a contended rwsem, the owner is likely the most frequently accessed + * field in the structure as the optimistic waiter that holds the osq lock + * will spin on owner. For an embedded rwsem, other hot fields in the + * containing structure should be moved further away from the rwsem to + * reduce the chance that they will share the same cacheline causing + * cacheline bouncing problem. + */ struct rw_semaphore { atomic_long_t count; - struct list_head wait_list; - raw_spinlock_t wait_lock; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; + struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif + raw_spinlock_t wait_lock; + struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif @@ -50,24 +55,14 @@ struct rw_semaphore { */ #define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - -/* Include the arch specific part */ -#include <asm/rwsem.h> - /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != 0; } +#define RWSEM_UNLOCKED_VALUE 0L #define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) -#endif /* Common initializer macros and functions */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 1549584a1538..50606a6e73d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1057,7 +1057,6 @@ struct task_struct { #ifdef CONFIG_RSEQ struct rseq __user *rseq; - u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically @@ -1855,12 +1854,10 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_THREAD) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } 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; } @@ -1869,7 +1866,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 2e97a2227045..f1227f2c38a4 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *); extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); +struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 57c7ed3fe465..cfc0a89a7159 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -76,8 +76,8 @@ struct sched_domain_shared { struct sched_domain { /* These fields must be setup */ - struct sched_domain *parent; /* top domain must be null terminated */ - struct sched_domain *child; /* bottom domain must be null terminated */ + struct sched_domain __rcu *parent; /* top domain must be null terminated */ + struct sched_domain __rcu *child; /* bottom domain must be null terminated */ struct sched_group *groups; /* the balancing groups of the domain */ unsigned long min_interval; /* Minimum balance interval ms */ unsigned long max_interval; /* Maximum balance interval ms */ diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 2a986d282a97..b5071497b8cb 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif +#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP +static inline int set_direct_map_invalid_noflush(struct page *page) +{ + return 0; +} +static inline int set_direct_map_default_noflush(struct page *page) +{ + return 0; +} +#endif + #ifndef set_mce_nospec static inline int set_mce_nospec(unsigned long pfn) { diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index d0884b525001..9d1bc65d226c 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -29,7 +29,7 @@ struct smpboot_thread_data; * @thread_comm: The base name of the thread */ struct smp_hotplug_thread { - struct task_struct __percpu **store; + struct task_struct * __percpu *store; struct list_head list; int (*thread_should_run)(unsigned int cpu); void (*thread_fn)(unsigned int cpu); diff --git a/include/linux/srcu.h b/include/linux/srcu.h index c495b2d51569..e432cc92c73d 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -56,45 +56,11 @@ struct srcu_struct { }; void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced); +void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. - */ -static inline void cleanup_srcu_struct(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, false); -} - -/** - * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. Also, - * all grace-period processing must have completed. - * - * "Completed" means that the last synchronize_srcu() and - * synchronize_srcu_expedited() calls must have returned before the call - * to cleanup_srcu_struct_quiesced(). It also means that the callback - * from the last call_srcu() must have been invoked before the call to - * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help - * with this last. Violating these rules will get you a WARN_ON() splat - * (with high probability, anyway), and will also cause the srcu_struct - * to be leaked. - */ -static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, true); -} - #ifdef CONFIG_DEBUG_LOCK_ALLOC /** diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 7978b3e2c1e1..0805dee1b6b8 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -23,10 +23,10 @@ typedef u32 depot_stack_handle_t; -struct stack_trace; +depot_stack_handle_t stack_depot_save(unsigned long *entries, + unsigned int nr_entries, gfp_t gfp_flags); -depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags); - -void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace); +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries); #endif diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index ba29a0613e66..f0cfd12cb45e 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -3,11 +3,64 @@ #define __LINUX_STACKTRACE_H #include <linux/types.h> +#include <asm/errno.h> struct task_struct; struct pt_regs; #ifdef CONFIG_STACKTRACE +void stack_trace_print(unsigned long *trace, unsigned int nr_entries, + int spaces); +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces); +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr); +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); + +/* Internal interfaces. Do not use in generic code */ +#ifdef CONFIG_ARCH_STACKWALK + +/** + * stack_trace_consume_fn - Callback for arch_stack_walk() + * @cookie: Caller supplied pointer handed back by arch_stack_walk() + * @addr: The stack entry address to consume + * @reliable: True when the stack entry is reliable. Required by + * some printk based consumers. + * + * Return: True, if the entry was consumed or skipped + * False, if there is no space left to store + */ +typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr, + bool reliable); +/** + * arch_stack_walk - Architecture specific function to walk the stack + * @consume_entry: Callback which is invoked by the architecture code for + * each entry. + * @cookie: Caller supplied pointer which is handed back to + * @consume_entry + * @task: Pointer to a task struct, can be NULL + * @regs: Pointer to registers, can be NULL + * + * ============ ======= ============================================ + * task regs + * ============ ======= ============================================ + * task NULL Stack trace from task (can be current) + * current regs Stack trace starting on regs->stackpointer + * ============ ======= ============================================ + */ +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs); +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task); +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs); + +#else /* CONFIG_ARCH_STACKWALK */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; @@ -21,24 +74,20 @@ extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); extern int save_stack_trace_tsk_reliable(struct task_struct *tsk, struct stack_trace *trace); - -extern void print_stack_trace(struct stack_trace *trace, int spaces); -extern int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces); - -#ifdef CONFIG_USER_STACKTRACE_SUPPORT extern void save_stack_trace_user(struct stack_trace *trace); +#endif /* !CONFIG_ARCH_STACKWALK */ +#endif /* CONFIG_STACKTRACE */ + +#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE) +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size); #else -# define save_stack_trace_user(trace) do { } while (0) +static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk, + unsigned long *store, + unsigned int size) +{ + return -ENOSYS; +} #endif -#else /* !CONFIG_STACKTRACE */ -# define save_stack_trace(trace) do { } while (0) -# define save_stack_trace_tsk(tsk, trace) do { } while (0) -# define save_stack_trace_user(trace) do { } while (0) -# define print_stack_trace(trace, spaces) do { } while (0) -# define snprint_stack_trace(buf, size, trace, spaces) do { } while (0) -# define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; }) -#endif /* CONFIG_STACKTRACE */ - #endif /* __LINUX_STACKTRACE_H */ diff --git a/include/linux/string.h b/include/linux/string.h index 7927b875f80c..6ab0a6fa512e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -150,6 +150,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ec861cd0cfe8..52d41d0c1ae1 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -304,12 +304,4 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) } #endif /* CONFIG_SUNRPC_SWAP */ -static inline bool -rpc_task_need_resched(const struct rpc_task *task) -{ - if (RPC_IS_QUEUED(task) || task->tk_callback) - return true; - return false; -} - #endif /* _LINUX_SUNRPC_SCHED_H_ */ diff --git a/include/linux/tick.h b/include/linux/tick.h index 55388ab45fd4..76acb48acdb7 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); +#else +static inline void tick_offline_cpu(unsigned int cpu) { } +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else diff --git a/include/linux/time64.h b/include/linux/time64.h index f38d382ffec1..a620ee610b9f 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -33,6 +33,17 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +/* + * Limits for settimeofday(): + * + * To prevent setting the time close to the wraparound point time setting + * is limited so a reasonable uptime can be accomodated. Uptime of 30 years + * should be really sufficient, which means the cutoff is 2232. At that + * point the cutoff is just a small part of the larger problem. + */ +#define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) +#define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { @@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts) return true; } +static inline bool timespec64_valid_settod(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ + if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) + return false; + return true; +} + /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 37b226e8df13..2b70130af585 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -268,6 +268,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #define user_access_end() do { } while (0) #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY diff --git a/include/linux/uio.h b/include/linux/uio.h index f184af1999a8..2d0131ad4604 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -60,7 +60,7 @@ struct iov_iter { static inline enum iter_type iov_iter_type(const struct iov_iter *i) { - return i->type & ~(READ | WRITE); + return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF); } static inline bool iter_is_iovec(const struct iov_iter *i) diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 103a48a48872..12bf0b68ed92 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -115,6 +115,7 @@ struct uprobes_state { struct xol_area *xol_area; }; +extern void __init uprobes_init(void); extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool is_swbp_insn(uprobe_opcode_t *insn); @@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, struct uprobes_state { }; +static inline void uprobes_init(void) +{ +} + #define uprobe_get_trap_addr(regs) instruction_pointer(regs) static inline int diff --git a/include/linux/usb.h b/include/linux/usb.h index 5e49e82c4368..ff010d1fd1c7 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. - * @pm_usage_cnt: PM usage counter for this interface * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. @@ -257,7 +256,6 @@ struct usb_interface { struct device dev; /* interface specific device info */ struct device *usb_dev; - atomic_t pm_usage_cnt; /* usage counter for autosuspend */ struct work_struct reset_ws; /* for resets in atomic context */ }; #define to_usb_interface(d) container_of(d, struct usb_interface, dev) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index fab02133a919..3dc70adfe5f5 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -63,7 +63,7 @@ struct virtqueue; /* * Creates a virtqueue and allocates the descriptor ring. If * may_reduce_num is set, then this may allocate a smaller ring than - * expected. The caller should query virtqueue_get_ring_size to learn + * expected. The caller should query virtqueue_get_vring_size to learn * the actual size of the ring. */ struct virtqueue *vring_create_virtqueue(unsigned int index, diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 398e9c95cd61..c6eebb839552 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -21,6 +21,11 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ +/* + * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with + * vfree_atomic(). + */ +#define VM_FLUSH_RESET_PERMS 0x00000100 /* Reset direct map and flush TLB on unmap */ /* bits [20..32] reserved for arch specific ioremap internals */ /* @@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); +static inline void set_vm_flush_reset_perms(void *addr) +{ + struct vm_struct *vm = find_vm_area(addr); + + if (vm) + vm->flags |= VM_FLUSH_RESET_PERMS; +} #else static inline int map_kernel_range_noflush(unsigned long start, unsigned long size, @@ -157,6 +169,9 @@ static inline void unmap_kernel_range(unsigned long addr, unsigned long size) { } +static inline void set_vm_flush_reset_perms(void *addr) +{ +} #endif /* Allocate/destroy a 'vmalloc' VM area. */ |