From a849a0273d0f73a252d14d31c5003a8059ea51fc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 11 Sep 2024 15:17:37 +0200 Subject: ntp: Remove unused tick_nsec tick_nsec is only updated in the NTP core, but there are no users. Remove it. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/all/20240911-devel-anna-maria-b4-timers-ptp-ntp-v1-1-2d52f4e13476@linutronix.de --- include/linux/timex.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 3871b06bd302..7f7a12fd8200 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -145,7 +145,6 @@ unsigned long random_get_entropy_fallback(void); * estimated error = NTP dispersion. */ extern unsigned long tick_usec; /* USER_HZ period (usec) */ -extern unsigned long tick_nsec; /* SHIFTED_HZ period (nsec) */ /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ -- cgit v1.2.3 From 66606a93849bfe3cbe9f0b801b40f60b87c54e11 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 11 Sep 2024 15:17:38 +0200 Subject: ntp: Make tick_usec static There are no users of tick_usec outside of the NTP core code. Therefore make tick_usec static. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/all/20240911-devel-anna-maria-b4-timers-ptp-ntp-v1-2-2d52f4e13476@linutronix.de --- include/linux/timex.h | 7 ------- kernel/time/ntp.c | 5 ++++- 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/timex.h b/include/linux/timex.h index 7f7a12fd8200..4ee32eff3f22 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -139,13 +139,6 @@ unsigned long random_get_entropy_fallback(void); #define MAXSEC 2048 /* max interval between updates (s) */ #define NTP_PHASE_LIMIT ((MAXPHASE / NSEC_PER_USEC) << 5) /* beyond max. dispersion */ -/* - * kernel variables - * Note: maximum error = NTP sync distance = dispersion + delay / 2; - * estimated error = NTP dispersion. - */ -extern unsigned long tick_usec; /* USER_HZ period (usec) */ - /* Required to safely shift negative values */ #define shift_right(x, s) ({ \ __typeof__(x) __x = (x); \ diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index c17cc9d857bc..ed15ec993a82 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -31,7 +31,7 @@ /* USER_HZ period (usecs): */ -unsigned long tick_usec = USER_TICK_USEC; +static unsigned long tick_usec = USER_TICK_USEC; static u64 tick_length; static u64 tick_length_base; @@ -44,6 +44,9 @@ static u64 tick_length_base; /* * phase-lock loop variables + * + * Note: maximum error = NTP sync distance = dispersion + delay / 2; + * estimated error = NTP dispersion. */ /* -- cgit v1.2.3 From 8102c4daf44ab86c2d2226a8136bec905d6e2bd1 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 11 Sep 2024 10:30:20 +0100 Subject: timekeeping: Add the boot clock to system time snapshot For tracing purpose, the boot clock is interesting as it doesn't stop on suspend. Export it as part of the time snapshot. This will later allow the hypervisor to add boot clock timestamps to its events. Signed-off-by: Vincent Donnefort Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/all/20240911093029.3279154-5-vdonnefort@google.com --- include/linux/timekeeping.h | 2 ++ kernel/time/timekeeping.c | 4 ++++ 2 files changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..e85c27347e44 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -275,6 +275,7 @@ struct ktime_timestamps { * counter value * @cycles: Clocksource counter value to produce the system times * @real: Realtime system time + * @boot: Boot time * @raw: Monotonic raw system time * @cs_id: Clocksource ID * @clock_was_set_seq: The sequence number of clock-was-set events @@ -283,6 +284,7 @@ struct ktime_timestamps { struct system_time_snapshot { u64 cycles; ktime_t real; + ktime_t boot; ktime_t raw; enum clocksource_ids cs_id; unsigned int clock_was_set_seq; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 7e6f409bf311..47e44b9d2671 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1060,6 +1060,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) unsigned int seq; ktime_t base_raw; ktime_t base_real; + ktime_t base_boot; u64 nsec_raw; u64 nsec_real; u64 now; @@ -1074,6 +1075,8 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); + base_boot = ktime_add(tk->tkr_mono.base, + tk_core.timekeeper.offs_boot); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); @@ -1081,6 +1084,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); + systime_snapshot->boot = ktime_add_ns(base_boot, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); -- cgit v1.2.3 From 70c8fd00a9bd0509bbf7bccd9baea8bbd5ddc756 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:16 -0400 Subject: timekeeping: Add interfaces for handling timestamps with a floor value Multigrain timestamps allow the kernel to use fine-grained timestamps when an inode's attributes is being actively observed via ->getattr(). With this support, it's possible for a file to get a fine-grained timestamp, and another modified after it to get a coarse-grained stamp that is earlier than the fine-grained time. If this happens then the files can appear to have been modified in reverse order, which breaks VFS ordering guarantees [1]. To prevent this, maintain a floor value for multigrain timestamps. Whenever a fine-grained timestamp is handed out, record it, and when later coarse-grained stamps are handed out, ensure they are not earlier than that value. If the coarse-grained timestamp is earlier than the fine-grained floor, return the floor value instead. Add a static singleton atomic64_t into timekeeper.c that is used to keep track of the latest fine-grained time ever handed out. This is tracked as a monotonic ktime_t value to ensure that it isn't affected by clock jumps. Because it is updated at different times than the rest of the timekeeper object, the floor value is managed independently of the timekeeper via a cmpxchg() operation, and sits on its own cacheline. Add two new public interfaces: - ktime_get_coarse_real_ts64_mg() fills a timespec64 with the later of the coarse-grained clock and the floor time - ktime_get_real_ts64_mg() gets the fine-grained clock value, and tries to swap it into the floor. A timespec64 is filled with the result. The floor value is global and updated via a single try_cmpxchg(). If that fails then the operation raced with a concurrent update. Any concurrent update must be later than the existing floor value, so any racing tasks can accept any resulting floor value without retrying. [1]: POSIX requires that files be stamped with realtime clock values, and makes no provision for dealing with backward clock jumps. If a backward realtime clock jump occurs, then files can appear to have been modified in reverse order. Signed-off-by: Jeff Layton Signed-off-by: Thomas Gleixner Tested-by: Randy Dunlap # documentation bits Acked-by: John Stultz Link: https://lore.kernel.org/all/20241002-mgtime-v10-1-d1c4717f5284@kernel.org --- include/linux/timekeeping.h | 4 ++ kernel/time/timekeeping.c | 104 ++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 108 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index fc12a9ba2c88..7aa85246c183 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -45,6 +45,10 @@ extern void ktime_get_real_ts64(struct timespec64 *tv); extern void ktime_get_coarse_ts64(struct timespec64 *ts); extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); +/* Multigrain timestamp interfaces */ +extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); +extern void ktime_get_real_ts64_mg(struct timespec64 *ts); + void getboottime64(struct timespec64 *ts); /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 7e6f409bf311..441792c907fa 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -114,6 +114,23 @@ static struct tk_fast tk_fast_raw ____cacheline_aligned = { .base[1] = FAST_TK_INIT, }; +/* + * Multigrain timestamps require tracking the latest fine-grained timestamp + * that has been issued, and never returning a coarse-grained timestamp that is + * earlier than that value. + * + * mg_floor represents the latest fine-grained time that has been handed out as + * a file timestamp on the system. This is tracked as a monotonic ktime_t, and + * converted to a realtime clock value on an as-needed basis. + * + * Maintaining mg_floor ensures the multigrain interfaces never issue a + * timestamp earlier than one that has been previously issued. + * + * The exception to this rule is when there is a backward realtime clock jump. If + * such an event occurs, a timestamp can appear to be earlier than a previous one. + */ +static __cacheline_aligned_in_smp atomic64_t mg_floor; + static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { @@ -2394,6 +2411,93 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts) } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); +/** + * ktime_get_coarse_real_ts64_mg - return latter of coarse grained time or floor + * @ts: timespec64 to be filled + * + * Fetch the global mg_floor value, convert it to realtime and compare it + * to the current coarse-grained time. Fill @ts with whichever is + * latest. Note that this is a filesystem-specific interface and should be + * avoided outside of that context. + */ +void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + u64 floor = atomic64_read(&mg_floor); + ktime_t f_real, offset, coarse; + unsigned int seq; + + do { + seq = read_seqcount_begin(&tk_core.seq); + *ts = tk_xtime(tk); + offset = tk_core.timekeeper.offs_real; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + coarse = timespec64_to_ktime(*ts); + f_real = ktime_add(floor, offset); + if (ktime_after(f_real, coarse)) + *ts = ktime_to_timespec64(f_real); +} + +/** + * ktime_get_real_ts64_mg - attempt to update floor value and return result + * @ts: pointer to the timespec to be set + * + * Get a monotonic fine-grained time value and attempt to swap it into + * mg_floor. If that succeeds then accept the new floor value. If it fails + * then another task raced in during the interim time and updated the + * floor. Since any update to the floor must be later than the previous + * floor, either outcome is acceptable. + * + * Typically this will be called after calling ktime_get_coarse_real_ts64_mg(), + * and determining that the resulting coarse-grained timestamp did not effect + * a change in ctime. Any more recent floor value would effect a change to + * ctime, so there is no need to retry the atomic64_try_cmpxchg() on failure. + * + * @ts will be filled with the latest floor value, regardless of the outcome of + * the cmpxchg. Note that this is a filesystem specific interface and should be + * avoided outside of that context. + */ +void ktime_get_real_ts64_mg(struct timespec64 *ts) +{ + struct timekeeper *tk = &tk_core.timekeeper; + ktime_t old = atomic64_read(&mg_floor); + ktime_t offset, mono; + unsigned int seq; + u64 nsecs; + + do { + seq = read_seqcount_begin(&tk_core.seq); + + ts->tv_sec = tk->xtime_sec; + mono = tk->tkr_mono.base; + nsecs = timekeeping_get_ns(&tk->tkr_mono); + offset = tk_core.timekeeper.offs_real; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + mono = ktime_add_ns(mono, nsecs); + + /* + * Attempt to update the floor with the new time value. As any + * update must be later then the existing floor, and would effect + * a change to ctime from the perspective of the current task, + * accept the resulting floor value regardless of the outcome of + * the swap. + */ + if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { + ts->tv_nsec = 0; + timespec64_add_ns(ts, nsecs); + } else { + /* + * Another task changed mg_floor since "old" was fetched. + * "old" has been updated with the latest value of "mg_floor". + * That value is newer than the previous floor value, which + * is enough to effect a change to ctime. Accept it. + */ + *ts = ktime_to_timespec64(ktime_add(old, offset)); + } +} + void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; -- cgit v1.2.3 From 96f9a366ec8abe027326d7aab84d64370019f0f1 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 2 Oct 2024 17:27:17 -0400 Subject: timekeeping: Add percpu counter for tracking floor swap events The mgtime_floor value is a global variable for tracking the latest fine-grained timestamp handed out. Because it's a global, track the number of times that a new floor value is assigned. Add a new percpu counter to the timekeeping code to track the number of floor swap events that have occurred. A later patch will add a debugfs file to display this counter alongside other stats involving multigrain timestamps. Signed-off-by: Jeff Layton Signed-off-by: Thomas Gleixner Tested-by: Randy Dunlap # documentation bits Link: https://lore.kernel.org/all/20241002-mgtime-v10-2-d1c4717f5284@kernel.org --- include/linux/timekeeping.h | 1 + kernel/time/timekeeping.c | 1 + kernel/time/timekeeping_debug.c | 13 +++++++++++++ kernel/time/timekeeping_internal.h | 15 +++++++++++++++ 4 files changed, 30 insertions(+) (limited to 'include') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 7aa85246c183..84a035e86ac8 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -48,6 +48,7 @@ extern void ktime_get_coarse_real_ts64(struct timespec64 *ts); /* Multigrain timestamp interfaces */ extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts); extern void ktime_get_real_ts64_mg(struct timespec64 *ts); +extern unsigned long timekeeping_get_mg_floor_swaps(void); void getboottime64(struct timespec64 *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 441792c907fa..962b2a31f015 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2487,6 +2487,7 @@ void ktime_get_real_ts64_mg(struct timespec64 *ts) if (atomic64_try_cmpxchg(&mg_floor, &old, mono)) { ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); + timekeeping_inc_mg_floor_swaps(); } else { /* * Another task changed mg_floor since "old" was fetched. diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index b73e8850e58d..badeb222eab9 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -17,6 +17,9 @@ #define NUM_BINS 32 +/* Incremented every time mg_floor is updated */ +DEFINE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps); + static unsigned int sleep_time_bin[NUM_BINS] = {0}; static int tk_debug_sleep_time_show(struct seq_file *s, void *data) @@ -53,3 +56,13 @@ void tk_debug_account_sleep_time(const struct timespec64 *t) (s64)t->tv_sec, t->tv_nsec / NSEC_PER_MSEC); } +unsigned long timekeeping_get_mg_floor_swaps(void) +{ + unsigned long sum = 0; + int cpu; + + for_each_possible_cpu(cpu) + sum += data_race(per_cpu(timekeeping_mg_floor_swaps, cpu)); + + return sum; +} diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 4ca2787d1642..0bbae825bc02 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -10,9 +10,24 @@ * timekeeping debug functions */ #ifdef CONFIG_DEBUG_FS + +DECLARE_PER_CPU(unsigned long, timekeeping_mg_floor_swaps); + +static inline void timekeeping_inc_mg_floor_swaps(void) +{ + this_cpu_inc(timekeeping_mg_floor_swaps); +} + extern void tk_debug_account_sleep_time(const struct timespec64 *t); + #else + #define tk_debug_account_sleep_time(x) + +static inline void timekeeping_inc_mg_floor_swaps(void) +{ +} + #endif #ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE -- cgit v1.2.3 From bafffd56c608106d11e7aec851f114dcd66b2091 Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Thu, 10 Oct 2024 14:54:46 +0100 Subject: clocksource: Remove unused clocksource_change_rating clocksource_change_rating() has been unused since 2017's commit 63ed4e0c67df ("Drivers: hv: vmbus: Consolidate all Hyper-V specific clocksource code") Remove it. __clocksource_change_rating now only has one use which is ifdef'd. Move it into the ifdef'd section. Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20241010135446.213098-1-linux@treblig.org --- include/linux/clocksource.h | 1 - kernel/time/clocksource.c | 40 ++++++++++------------------------------ 2 files changed, 10 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index d35b677b08fe..ef1b16da6ad5 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -215,7 +215,6 @@ static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift) extern int clocksource_unregister(struct clocksource*); extern void clocksource_touch_watchdog(void); -extern void clocksource_change_rating(struct clocksource *cs, int rating); extern void clocksource_suspend(void); extern void clocksource_resume(void); extern struct clocksource * __init clocksource_default_clock(void); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 23336eecb4f4..aab6472853fa 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -20,6 +20,8 @@ #include "tick-internal.h" #include "timekeeping_internal.h" +static void clocksource_enqueue(struct clocksource *cs); + static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { u64 delta = clocksource_delta(end, start, cs->mask); @@ -171,7 +173,6 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) } static int clocksource_watchdog_kthread(void *data); -static void __clocksource_change_rating(struct clocksource *cs, int rating); static void clocksource_watchdog_work(struct work_struct *work) { @@ -191,6 +192,13 @@ static void clocksource_watchdog_work(struct work_struct *work) kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); } +static void clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); @@ -697,7 +705,7 @@ static int __clocksource_watchdog_kthread(void) list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); - __clocksource_change_rating(cs, 0); + clocksource_change_rating(cs, 0); select = 1; } if (cs->flags & CLOCK_SOURCE_RESELECT) { @@ -1255,34 +1263,6 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) } EXPORT_SYMBOL_GPL(__clocksource_register_scale); -static void __clocksource_change_rating(struct clocksource *cs, int rating) -{ - list_del(&cs->list); - cs->rating = rating; - clocksource_enqueue(cs); -} - -/** - * clocksource_change_rating - Change the rating of a registered clocksource - * @cs: clocksource to be changed - * @rating: new rating - */ -void clocksource_change_rating(struct clocksource *cs, int rating) -{ - unsigned long flags; - - mutex_lock(&clocksource_mutex); - clocksource_watchdog_lock(&flags); - __clocksource_change_rating(cs, rating); - clocksource_watchdog_unlock(&flags); - - clocksource_select(); - clocksource_select_watchdog(false); - clocksource_suspend_select(false); - mutex_unlock(&clocksource_mutex); -} -EXPORT_SYMBOL(clocksource_change_rating); - /* * Unbind clocksource @cs. Called with clocksource_mutex held */ -- cgit v1.2.3 From 102f085d84607462234ac60f6027973b45a9bde2 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:21 +0200 Subject: timers: Rename usleep_idle_range() to usleep_range_idle() usleep_idle_range() is a variant of usleep_range(). Both are using usleep_range_state() as a base. To be able to find all the related functions in one go, rename it usleep_idle_range() to usleep_range_idle(). No functional change. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Reviewed-by: SeongJae Park Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-4-dc8b907cb62f@linutronix.de --- include/linux/delay.h | 2 +- mm/damon/core.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/delay.h b/include/linux/delay.h index ff9cda975e30..2bc586aa2068 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -68,7 +68,7 @@ static inline void usleep_range(unsigned long min, unsigned long max) usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); } -static inline void usleep_idle_range(unsigned long min, unsigned long max) +static inline void usleep_range_idle(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_IDLE); } diff --git a/mm/damon/core.c b/mm/damon/core.c index a83f3b736d51..c725c78b43f0 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1896,7 +1896,7 @@ static void kdamond_usleep(unsigned long usecs) if (usecs > 20 * USEC_PER_MSEC) schedule_timeout_idle(usecs_to_jiffies(usecs)); else - usleep_idle_range(usecs, usecs + 1); + usleep_range_idle(usecs, usecs + 1); } /* Returns negative error code if it's not activated but should return */ -- cgit v1.2.3 From f36eb171410839325fff9cd9b7b7400f7e606962 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:22 +0200 Subject: timers: Update function descriptions of sleep/delay related functions A lot of commonly used functions for inserting a sleep or delay lack a proper function description. Add function descriptions to all of them to have important information in a central place close to the code. No functional change. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-5-dc8b907cb62f@linutronix.de --- include/asm-generic/delay.h | 41 +++++++++++++++++++++++++++++++---- include/linux/delay.h | 48 ++++++++++++++++++++++++++++++---------- kernel/time/sleep_timeout.c | 53 ++++++++++++++++++++++++++++++++++++++++----- 3 files changed, 120 insertions(+), 22 deletions(-) (limited to 'include') diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h index e448ac61430c..a8cee41cc51b 100644 --- a/include/asm-generic/delay.h +++ b/include/asm-generic/delay.h @@ -12,11 +12,39 @@ extern void __const_udelay(unsigned long xloops); extern void __delay(unsigned long loops); /* - * The weird n/20000 thing suppresses a "comparison is always false due to - * limited range of data type" warning with non-const 8-bit arguments. + * Implementation details: + * + * * The weird n/20000 thing suppresses a "comparison is always false due to + * limited range of data type" warning with non-const 8-bit arguments. + * * 0x10c7 is 2**32 / 1000000 (rounded up) -> udelay + * * 0x5 is 2**32 / 1000000000 (rounded up) -> ndelay */ -/* 0x10c7 is 2**32 / 1000000 (rounded up) */ +/** + * udelay - Inserting a delay based on microseconds with busy waiting + * @usec: requested delay in microseconds + * + * When delaying in an atomic context ndelay(), udelay() and mdelay() are the + * only valid variants of delaying/sleeping to go with. + * + * When inserting delays in non atomic context which are shorter than the time + * which is required to queue e.g. an hrtimer and to enter then the scheduler, + * it is also valuable to use udelay(). But it is not simple to specify a + * generic threshold for this which will fit for all systems. An approximation + * is a threshold for all delays up to 10 microseconds. + * + * When having a delay which is larger than the architecture specific + * %MAX_UDELAY_MS value, please make sure mdelay() is used. Otherwise a overflow + * risk is given. + * + * Please note that ndelay(), udelay() and mdelay() may return early for several + * reasons (https://lists.openwall.net/linux-kernel/2011/01/09/56): + * + * #. computed loops_per_jiffy too low (due to the time taken to execute the + * timer interrupt.) + * #. cache behaviour affecting the time it takes to execute the loop function. + * #. CPU clock rate changes. + */ #define udelay(n) \ ({ \ if (__builtin_constant_p(n)) { \ @@ -29,7 +57,12 @@ extern void __delay(unsigned long loops); } \ }) -/* 0x5 is 2**32 / 1000000000 (rounded up) */ +/** + * ndelay - Inserting a delay based on nanoseconds with busy waiting + * @nsec: requested delay in nanoseconds + * + * See udelay() for basic information about ndelay() and it's variants. + */ #define ndelay(n) \ ({ \ if (__builtin_constant_p(n)) { \ diff --git a/include/linux/delay.h b/include/linux/delay.h index 2bc586aa2068..2de509e4adce 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -6,17 +6,7 @@ * Copyright (C) 1993 Linus Torvalds * * Delay routines, using a pre-computed "loops_per_jiffy" value. - * - * Please note that ndelay(), udelay() and mdelay() may return early for - * several reasons: - * 1. computed loops_per_jiffy too low (due to the time taken to - * execute the timer interrupt.) - * 2. cache behaviour affecting the time it takes to execute the - * loop function. - * 3. CPU clock rate changes. - * - * Please see this thread: - * https://lists.openwall.net/linux-kernel/2011/01/09/56 + * Sleep routines using timer list timers or hrtimers. */ #include @@ -35,12 +25,21 @@ extern unsigned long loops_per_jiffy; * The 2nd mdelay() definition ensures GCC will optimize away the * while loop for the common cases where n <= MAX_UDELAY_MS -- Paul G. */ - #ifndef MAX_UDELAY_MS #define MAX_UDELAY_MS 5 #endif #ifndef mdelay +/** + * mdelay - Inserting a delay based on milliseconds with busy waiting + * @n: requested delay in milliseconds + * + * See udelay() for basic information about mdelay() and it's variants. + * + * Please double check, whether mdelay() is the right way to go or whether a + * refactoring of the code is the better variant to be able to use msleep() + * instead. + */ #define mdelay(n) (\ (__builtin_constant_p(n) && (n)<=MAX_UDELAY_MS) ? udelay((n)*1000) : \ ({unsigned long __ms=(n); while (__ms--) udelay(1000);})) @@ -63,16 +62,41 @@ unsigned long msleep_interruptible(unsigned int msecs); void usleep_range_state(unsigned long min, unsigned long max, unsigned int state); +/** + * usleep_range - Sleep for an approximate time + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. + */ static inline void usleep_range(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); } +/** + * usleep_range_idle - Sleep for an approximate time with idle time accounting + * @min: Minimum time in microseconds to sleep + * @max: Maximum time in microseconds to sleep + * + * For basic information please refere to usleep_range_state(). + * + * The sleeping task has the state TASK_IDLE during the sleep to prevent + * contribution to the load avarage. + */ static inline void usleep_range_idle(unsigned long min, unsigned long max) { usleep_range_state(min, max, TASK_IDLE); } +/** + * ssleep - wrapper for seconds around msleep + * @seconds: Requested sleep duration in seconds + * + * Please refere to msleep() for detailed information. + */ static inline void ssleep(unsigned int seconds) { msleep(seconds * 1000); diff --git a/kernel/time/sleep_timeout.c b/kernel/time/sleep_timeout.c index 560d17c30aa5..f3f246e4c8d1 100644 --- a/kernel/time/sleep_timeout.c +++ b/kernel/time/sleep_timeout.c @@ -281,7 +281,34 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout); /** * msleep - sleep safely even with waitqueue interruptions - * @msecs: Time in milliseconds to sleep for + * @msecs: Requested sleep duration in milliseconds + * + * msleep() uses jiffy based timeouts for the sleep duration. Because of the + * design of the timer wheel, the maximum additional percentage delay (slack) is + * 12.5%. This is only valid for timers which will end up in level 1 or a higher + * level of the timer wheel. For explanation of those 12.5% please check the + * detailed description about the basics of the timer wheel. + * + * The slack of timers which will end up in level 0 depends on sleep duration + * (msecs) and HZ configuration and can be calculated in the following way (with + * the timer wheel design restriction that the slack is not less than 12.5%): + * + * ``slack = MSECS_PER_TICK / msecs`` + * + * When the allowed slack of the callsite is known, the calculation could be + * turned around to find the minimal allowed sleep duration to meet the + * constraints. For example: + * + * * ``HZ=1000`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 1 / (1/4) = 4``: + * all sleep durations greater or equal 4ms will meet the constraints. + * * ``HZ=1000`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 1 / (1/8) = 8``: + * all sleep durations greater or equal 8ms will meet the constraints. + * * ``HZ=250`` with ``slack=25%``: ``MSECS_PER_TICK / slack = 4 / (1/4) = 16``: + * all sleep durations greater or equal 16ms will meet the constraints. + * * ``HZ=250`` with ``slack=12.5%``: ``MSECS_PER_TICK / slack = 4 / (1/8) = 32``: + * all sleep durations greater or equal 32ms will meet the constraints. + * + * See also the signal aware variant msleep_interruptible(). */ void msleep(unsigned int msecs) { @@ -294,7 +321,15 @@ EXPORT_SYMBOL(msleep); /** * msleep_interruptible - sleep waiting for signals - * @msecs: Time in milliseconds to sleep for + * @msecs: Requested sleep duration in milliseconds + * + * See msleep() for some basic information. + * + * The difference between msleep() and msleep_interruptible() is that the sleep + * could be interrupted by a signal delivery and then returns early. + * + * Returns: The remaining time of the sleep duration transformed to msecs (see + * schedule_timeout() for details). */ unsigned long msleep_interruptible(unsigned int msecs) { @@ -312,11 +347,17 @@ EXPORT_SYMBOL(msleep_interruptible); * @max: Maximum time in usecs to sleep * @state: State of the current task that will be while sleeping * + * usleep_range_state() sleeps at least for the minimum specified time but not + * longer than the maximum specified amount of time. The range might reduce + * power usage by allowing hrtimers to coalesce an already scheduled interrupt + * with this hrtimer. In the worst case, an interrupt is scheduled for the upper + * bound. + * + * The sleeping task is set to the specified state before starting the sleep. + * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range_state() instead of udelay(). The sleep improves responsiveness - * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces - * power usage by allowing hrtimers to take advantage of an already- - * scheduled interrupt instead of scheduling a new one just for this sleep. + * usleep_range() or its variants instead of udelay(). The sleep improves + * responsiveness by avoiding the CPU-hogging busy-wait of udelay(). */ void __sched usleep_range_state(unsigned long min, unsigned long max, unsigned int state) { -- cgit v1.2.3 From 19e2d91d8cb1f333adf04731f2788ff6ca06cebd Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:23 +0200 Subject: delay: Rework udelay and ndelay udelay() as well as ndelay() are defines and no functions and are using constants to be able to transform a sleep time into loops and to prevent too long udelays/ndelays. There was a compiler error with non-const 8 bit arguments which was fixed by commit a87e553fabe8 ("asm-generic: delay.h fix udelay and ndelay for 8 bit args"). When using a function, the non-const 8 bit argument is type casted and the problem would be gone. Transform udelay() and ndelay() into proper functions, remove the no longer and confusing division, add defines for the magic values and add some explanations as well. Suggested-by: Thomas Gleixner Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-6-dc8b907cb62f@linutronix.de --- include/asm-generic/delay.h | 65 ++++++++++++++++++++++++++------------------- 1 file changed, 37 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/include/asm-generic/delay.h b/include/asm-generic/delay.h index a8cee41cc51b..76cf237b6e4c 100644 --- a/include/asm-generic/delay.h +++ b/include/asm-generic/delay.h @@ -2,6 +2,9 @@ #ifndef __ASM_GENERIC_DELAY_H #define __ASM_GENERIC_DELAY_H +#include +#include + /* Undefined functions to get compile-time errors */ extern void __bad_udelay(void); extern void __bad_ndelay(void); @@ -12,13 +15,18 @@ extern void __const_udelay(unsigned long xloops); extern void __delay(unsigned long loops); /* - * Implementation details: - * - * * The weird n/20000 thing suppresses a "comparison is always false due to - * limited range of data type" warning with non-const 8-bit arguments. - * * 0x10c7 is 2**32 / 1000000 (rounded up) -> udelay - * * 0x5 is 2**32 / 1000000000 (rounded up) -> ndelay + * The microseconds/nanosecond delay multiplicators are used to convert a + * constant microseconds/nanoseconds value to a value which can be used by the + * architectures specific implementation to transform it into loops. + */ +#define UDELAY_CONST_MULT ((unsigned long)DIV_ROUND_UP(1ULL << 32, USEC_PER_SEC)) +#define NDELAY_CONST_MULT ((unsigned long)DIV_ROUND_UP(1ULL << 32, NSEC_PER_SEC)) + +/* + * The maximum constant udelay/ndelay value picked out of thin air to prevent + * too long constant udelays/ndelays. */ +#define DELAY_CONST_MAX 20000 /** * udelay - Inserting a delay based on microseconds with busy waiting @@ -45,17 +53,17 @@ extern void __delay(unsigned long loops); * #. cache behaviour affecting the time it takes to execute the loop function. * #. CPU clock rate changes. */ -#define udelay(n) \ - ({ \ - if (__builtin_constant_p(n)) { \ - if ((n) / 20000 >= 1) \ - __bad_udelay(); \ - else \ - __const_udelay((n) * 0x10c7ul); \ - } else { \ - __udelay(n); \ - } \ - }) +static __always_inline void udelay(unsigned long usec) +{ + if (__builtin_constant_p(usec)) { + if (usec >= DELAY_CONST_MAX) + __bad_udelay(); + else + __const_udelay(usec * UDELAY_CONST_MULT); + } else { + __udelay(usec); + } +} /** * ndelay - Inserting a delay based on nanoseconds with busy waiting @@ -63,16 +71,17 @@ extern void __delay(unsigned long loops); * * See udelay() for basic information about ndelay() and it's variants. */ -#define ndelay(n) \ - ({ \ - if (__builtin_constant_p(n)) { \ - if ((n) / 20000 >= 1) \ - __bad_ndelay(); \ - else \ - __const_udelay((n) * 5ul); \ - } else { \ - __ndelay(n); \ - } \ - }) +static __always_inline void ndelay(unsigned long nsec) +{ + if (__builtin_constant_p(nsec)) { + if (nsec >= DELAY_CONST_MAX) + __bad_udelay(); + else + __const_udelay(nsec * NDELAY_CONST_MULT); + } else { + __udelay(nsec); + } +} +#define ndelay(x) ndelay(x) #endif /* __ASM_GENERIC_DELAY_H */ -- cgit v1.2.3 From 82e11e47c1880362e05c065bef7dbe28a749555c Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:24 +0200 Subject: timers: Adjust flseep() to reflect reality fsleep() simply implements the recommendations of the outdated documentation in "Documentation/timers/timers-howto.rst". This should be a user friendly interface to choose always the best timeout function approach: - udelay() for very short sleep durations shorter than 10 microseconds - usleep_range() for sleep durations until 20 milliseconds - msleep() for the others The actual implementation has several problems: - It does not take into account that HZ resolution also has an impact on granularity of jiffies and has also an impact on the granularity of the buckets of timer wheel levels. This means that accuracy for the timeout does not have an upper limit. When executing fsleep(20000) on a HZ=100 system, the possible additional slack will be 50% as the granularity of the buckets in the lowest level is 10 milliseconds. - The upper limit of usleep_range() is twice the requested timeout. When no other interrupts occur in this range, the maximum value is used. This means that the requested sleep length has then an additional delay of 100%. Change the thresholds for the decisions in fsleep() to make sure the maximum slack which is added to the sleep duration is 25%. Note: Outdated documentation will be updated in a followup patch. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-7-dc8b907cb62f@linutronix.de --- include/linux/delay.h | 29 +++++++++++++++++++++++++---- 1 file changed, 25 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/delay.h b/include/linux/delay.h index 2de509e4adce..89866bab100d 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -11,6 +11,7 @@ #include #include +#include extern unsigned long loops_per_jiffy; @@ -102,15 +103,35 @@ static inline void ssleep(unsigned int seconds) msleep(seconds * 1000); } -/* see Documentation/timers/timers-howto.rst for the thresholds */ +static const unsigned int max_slack_shift = 2; +#define USLEEP_RANGE_UPPER_BOUND ((TICK_NSEC << max_slack_shift) / NSEC_PER_USEC) + +/** + * fsleep - flexible sleep which autoselects the best mechanism + * @usecs: requested sleep duration in microseconds + * + * flseep() selects the best mechanism that will provide maximum 25% slack + * to the requested sleep duration. Therefore it uses: + * + * * udelay() loop for sleep durations <= 10 microseconds to avoid hrtimer + * overhead for really short sleep durations. + * * usleep_range() for sleep durations which would lead with the usage of + * msleep() to a slack larger than 25%. This depends on the granularity of + * jiffies. + * * msleep() for all other sleep durations. + * + * Note: When %CONFIG_HIGH_RES_TIMERS is not set, all sleeps are processed with + * the granularity of jiffies and the slack might exceed 25% especially for + * short sleep durations. + */ static inline void fsleep(unsigned long usecs) { if (usecs <= 10) udelay(usecs); - else if (usecs <= 20000) - usleep_range(usecs, 2 * usecs); + else if (usecs < USLEEP_RANGE_UPPER_BOUND) + usleep_range(usecs, usecs + (usecs >> max_slack_shift)); else - msleep(DIV_ROUND_UP(usecs, 1000)); + msleep(DIV_ROUND_UP(usecs, USEC_PER_MSEC)); } #endif /* defined(_LINUX_DELAY_H) */ -- cgit v1.2.3 From 89124747f096fc0fe44be0162c7b4fb3271739e8 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Mon, 14 Oct 2024 10:22:29 +0200 Subject: iopoll/regmap/phy/snd: Fix comment referencing outdated timer documentation Function descriptions in iopoll.h, regmap.h, phy.h and sound/soc/sof/ops.h copied all the same outdated documentation about sleep/delay function limitations. In those comments, the generic (and still outdated) timer documentation file is referenced. As proper function descriptions for used delay and sleep functions are in place, simply update the descriptions to reference to them. While at it fix missing colon after "Returns" in function description and move return value description to the end of the function description. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Reviewed-by: Andrew Lunn # for phy.h Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241014-devel-anna-maria-b4-timers-flseep-v3-12-dc8b907cb62f@linutronix.de --- include/linux/iopoll.h | 52 +++++++++++++++++++++++++------------------------- include/linux/phy.h | 9 +++++---- include/linux/regmap.h | 38 ++++++++++++++++++------------------ sound/soc/sof/ops.h | 8 ++++---- 4 files changed, 54 insertions(+), 53 deletions(-) (limited to 'include') diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h index 19a7b00baff4..91324c331a4b 100644 --- a/include/linux/iopoll.h +++ b/include/linux/iopoll.h @@ -19,19 +19,19 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \ sleep_before_read, args...) \ @@ -64,22 +64,22 @@ * @op: accessor function (takes @args as its arguments) * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @delay_before_read: if it is true, delay @delay_us before read. * @args: arguments for @op poll * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @args is stored in @val. - * * This macro does not rely on timekeeping. Hence it is safe to call even when * timekeeping is suspended, at the expense of an underestimation of wall clock * time, which is rather minimal with a non-zero delay_us. * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @args is stored in @val. */ #define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \ delay_before_read, args...) \ @@ -119,17 +119,17 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. Must not - * be called from atomic context if sleep_us or timeout_us are used. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. Must not + * be called from atomic context if sleep_us or timeout_us are used. */ #define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us) \ read_poll_timeout(op, val, cond, sleep_us, timeout_us, false, addr) @@ -140,16 +140,16 @@ * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). Should - * be less than ~10us since udelay is used (see - * Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either - * case, the last read value at @addr is stored in @val. - * * When available, you'll probably want to use one of the specialized * macros defined below rather than this macro directly. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either + * case, the last read value at @addr is stored in @val. */ #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \ read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr) diff --git a/include/linux/phy.h b/include/linux/phy.h index a98bc91a0cde..504766d4b2d5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1378,12 +1378,13 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); * @regnum: The register on the MMD to read * @val: Variable to read the register into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * @sleep_before_read: if it is true, sleep @sleep_us before read. - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @args is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index f9ccad32fc5c..75f162b60ba1 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -106,17 +106,17 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_read_poll_timeout(map, addr, val, cond, sleep_us, timeout_us) \ ({ \ @@ -133,20 +133,20 @@ struct reg_sequence { * @addr: Address to poll * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @delay_us: Time to udelay between reads in us (0 tight-loops). - * Should be less than ~10us since udelay is used - * (see Documentation/timers/timers-howto.rst). + * @delay_us: Time to udelay between reads in us (0 tight-loops). Please + * read udelay() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_read - * error return value in case of a error read. In the two former cases, - * the last read value at @addr is stored in @val. - * * This is modelled after the readx_poll_timeout_atomic macros in linux/iopoll.h. * * Note: In general regmap cannot be used in atomic context. If you want to use * this macro then first setup your regmap for atomic use (flat or no cache * and MMIO regmap). + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_read + * error return value in case of a error read. In the two former cases, + * the last read value at @addr is stored in @val. */ #define regmap_read_poll_timeout_atomic(map, addr, val, cond, delay_us, timeout_us) \ ({ \ @@ -177,17 +177,17 @@ struct reg_sequence { * @field: Regmap field to read from * @val: Unsigned integer variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read + * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. + * + * Returns: 0 on success and -ETIMEDOUT upon a timeout or the regmap_field_read * error return value in case of a error read. In the two former cases, * the last read value at @addr is stored in @val. Must not be called * from atomic context if sleep_us or timeout_us are used. - * - * This is modelled after the readx_poll_timeout macros in linux/iopoll.h. */ #define regmap_field_read_poll_timeout(field, val, cond, sleep_us, timeout_us) \ ({ \ diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h index 2584621c3b2d..d73644e85b6e 100644 --- a/sound/soc/sof/ops.h +++ b/sound/soc/sof/ops.h @@ -597,12 +597,12 @@ snd_sof_is_chain_dma_supported(struct snd_sof_dev *sdev, u32 dai_type) * @addr: Address to poll * @val: Variable to read the value into * @cond: Break condition (usually involving @val) - * @sleep_us: Maximum time to sleep between reads in us (0 - * tight-loops). Should be less than ~20ms since usleep_range - * is used (see Documentation/timers/timers-howto.rst). + * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please + * read usleep_range() function description for details and + * limitations. * @timeout_us: Timeout in us, 0 means never timeout * - * Returns 0 on success and -ETIMEDOUT upon a timeout. In either + * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either * case, the last read value at @addr is stored in @val. Must not * be called from atomic context if sleep_us or timeout_us are used. * -- cgit v1.2.3 From 6860d28ccb2390b4eeda32ab2ce7eb10f71921e1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 15 Oct 2024 12:08:39 +0200 Subject: timekeeping: Reorder struct timekeeper struct timekeeper is ordered suboptimal vs. cachelines. The layout, including the preceding seqcount (see struct tk_core in timekeeper.c) is: cacheline 0: seqcount, tkr_mono cacheline 1: tkr_raw, xtime_sec cacheline 2: ktime_sec ... tai_offset, internal variables cacheline 3: next_leap_ktime, raw_sec, internal variables cacheline 4: internal variables So any access to via ktime_get*() except for access to CLOCK_MONOTONIC_RAW will use either cachelines 0 + 1 or cachelines 0 + 2. Access to CLOCK_MONOTONIC_RAW uses cachelines 0 + 1 + 3. Reorder the members so that the result is more efficient: cacheline 0: seqcount, tkr_mono cacheline 1: xtime_sec, ktime_sec ... tai_offset cacheline 2: tkr_raw, raw_sec cacheline 3: internal variables cacheline 4: internal variables That means ktime_get*() will access cacheline 0 + 1 and CLOCK_MONOTONIC_RAW access will use cachelines 0 + 2. Update kernel-doc and fix formatting issues while at it. Also fix a typo in struct tk_read_base kernel-doc. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Behnsen Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/all/20241015100839.12702-1-anna-maria@linutronix.de --- include/linux/timekeeper_internal.h | 106 ++++++++++++++++++++++-------------- 1 file changed, 65 insertions(+), 41 deletions(-) (limited to 'include') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 902c20ef495a..a3b6380a7777 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -26,7 +26,7 @@ * occupies a single 64byte cache line. * * The struct is separate from struct timekeeper as it is also used - * for a fast NMI safe accessors. + * for the fast NMI safe accessors. * * @base_real is for the fast NMI safe accessor to allow reading clock * realtime from any context. @@ -44,33 +44,41 @@ struct tk_read_base { /** * struct timekeeper - Structure holding internal timekeeping values. - * @tkr_mono: The readout base structure for CLOCK_MONOTONIC - * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW - * @xtime_sec: Current CLOCK_REALTIME time in seconds - * @ktime_sec: Current CLOCK_MONOTONIC time in seconds - * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset - * @offs_real: Offset clock monotonic -> clock realtime - * @offs_boot: Offset clock monotonic -> clock boottime - * @offs_tai: Offset clock monotonic -> clock tai - * @tai_offset: The current UTC to TAI offset in seconds - * @clock_was_set_seq: The sequence number of clock was set events - * @cs_was_changed_seq: The sequence number of clocksource change events - * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second - * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds - * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset - * @cycle_interval: Number of clock cycles in one NTP interval - * @xtime_interval: Number of clock shifted nano seconds in one NTP - * interval. - * @xtime_remainder: Shifted nano seconds left over when rounding - * @cycle_interval - * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. - * @ntp_error: Difference between accumulated time and NTP time in ntp - * shifted nano seconds. - * @ntp_error_shift: Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. - * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) - * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) - * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) + * @tkr_mono: The readout base structure for CLOCK_MONOTONIC + * @xtime_sec: Current CLOCK_REALTIME time in seconds + * @ktime_sec: Current CLOCK_MONOTONIC time in seconds + * @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset + * @offs_real: Offset clock monotonic -> clock realtime + * @offs_boot: Offset clock monotonic -> clock boottime + * @offs_tai: Offset clock monotonic -> clock tai + * @tai_offset: The current UTC to TAI offset in seconds + * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW + * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds + * @clock_was_set_seq: The sequence number of clock was set events + * @cs_was_changed_seq: The sequence number of clocksource change events + * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset + * @cycle_interval: Number of clock cycles in one NTP interval + * @xtime_interval: Number of clock shifted nano seconds in one NTP + * interval. + * @xtime_remainder: Shifted nano seconds left over when rounding + * @cycle_interval + * @raw_interval: Shifted raw nano seconds accumulated per NTP interval. + * @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second + * @ntp_tick: The ntp_tick_length() value currently being + * used. This cached copy ensures we consistently + * apply the tick length for an entire tick, as + * ntp_tick_length may change mid-tick, and we don't + * want to apply that new value to the tick in + * progress. + * @ntp_error: Difference between accumulated time and NTP time in ntp + * shifted nano seconds. + * @ntp_error_shift: Shift conversion between clock shifted nano seconds and + * ntp shifted nano seconds. + * @ntp_err_mult: Multiplication factor for scaled math conversion + * @skip_second_overflow: Flag used to avoid updating NTP twice with same second + * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) + * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) + * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -88,10 +96,28 @@ struct tk_read_base { * * @monotonic_to_boottime is a timespec64 representation of @offs_boot to * accelerate the VDSO update for CLOCK_BOOTTIME. + * + * The cacheline ordering of the structure is optimized for in kernel usage of + * the ktime_get() and ktime_get_ts64() family of time accessors. Struct + * timekeeper is prepended in the core timekeeping code with a sequence count, + * which results in the following cacheline layout: + * + * 0: seqcount, tkr_mono + * 1: xtime_sec ... tai_offset + * 2: tkr_raw, raw_sec + * 3,4: Internal variables + * + * Cacheline 0,1 contain the data which is used for accessing + * CLOCK_MONOTONIC/REALTIME/BOOTTIME/TAI, while cacheline 2 contains the + * data for accessing CLOCK_MONOTONIC_RAW. Cacheline 3,4 are internal + * variables which are only accessed during timekeeper updates once per + * tick. */ struct timekeeper { + /* Cacheline 0 (together with prepended seqcount of timekeeper core): */ struct tk_read_base tkr_mono; - struct tk_read_base tkr_raw; + + /* Cacheline 1: */ u64 xtime_sec; unsigned long ktime_sec; struct timespec64 wall_to_monotonic; @@ -99,31 +125,29 @@ struct timekeeper { ktime_t offs_boot; ktime_t offs_tai; s32 tai_offset; + + /* Cacheline 2: */ + struct tk_read_base tkr_raw; + u64 raw_sec; + + /* Cachline 3 and 4 (timekeeping internal variables): */ unsigned int clock_was_set_seq; u8 cs_was_changed_seq; - ktime_t next_leap_ktime; - u64 raw_sec; + struct timespec64 monotonic_to_boot; - /* The following members are for timekeeping internal use */ u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; u64 raw_interval; - /* The ntp_tick_length() value currently being used. - * This cached copy ensures we consistently apply the tick - * length for an entire tick, as ntp_tick_length may change - * mid-tick, and we don't want to apply that new value to - * the tick in progress. - */ + + ktime_t next_leap_ktime; u64 ntp_tick; - /* Difference between accumulated time and NTP time in ntp - * shifted nano seconds. */ s64 ntp_error; u32 ntp_error_shift; u32 ntp_err_mult; - /* Flag used to avoid updating NTP twice with same second */ u32 skip_second_overflow; + #ifdef CONFIG_DEBUG_TIMEKEEPING long last_warning; /* -- cgit v1.2.3 From 92b043fd995a63a57aae29ff85a39b6f30cd440c Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Fri, 25 Oct 2024 13:01:41 +0200 Subject: time: Fix references to _msecs_to_jiffies() handling of values The details about the handling of the "normal" values were moved to the _msecs_to_jiffies() helpers in commit ca42aaf0c861 ("time: Refactor msecs_to_jiffies"). However, the same commit still mentioned __msecs_to_jiffies() in the added documentation. Thus point to _msecs_to_jiffies() instead. Fixes: ca42aaf0c861 ("time: Refactor msecs_to_jiffies") Signed-off-by: Miguel Ojeda Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20241025110141.157205-2-ojeda@kernel.org --- include/linux/jiffies.h | 2 +- kernel/time/time.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 1220f0fbe5bf..5d21dacd62bc 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -502,7 +502,7 @@ static inline unsigned long _msecs_to_jiffies(const unsigned int m) * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. - * for the details see __msecs_to_jiffies() + * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the diff --git a/kernel/time/time.c b/kernel/time/time.c index b1809a1b0827..1b69caa87480 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -556,7 +556,7 @@ EXPORT_SYMBOL(ns_to_timespec64); * - all other values are converted to jiffies by either multiplying * the input value by a factor or dividing it with a factor and * handling any 32-bit overflows. - * for the details see __msecs_to_jiffies() + * for the details see _msecs_to_jiffies() * * msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the -- cgit v1.2.3 From 68f99be287a59d50a9ad231d523f7e578f8bd28a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Oct 2024 10:42:00 +0200 Subject: signal: Confine POSIX_TIMERS properly Move the itimer rearming out of the signal code and consolidate all posix timer related functions in the signal code under one ifdef. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241001083835.314100569@linutronix.de --- include/linux/posix-timers.h | 5 +- kernel/signal.c | 125 +++++++++++++++---------------------------- kernel/time/itimer.c | 22 +++++++- kernel/time/posix-timers.c | 15 +++++- 4 files changed, 81 insertions(+), 86 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 453691710839..670bf03a56ef 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -100,6 +100,8 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } +void posixtimer_rearm_itimer(struct task_struct *p); +void posixtimer_rearm(struct kernel_siginfo *info); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ @@ -122,6 +124,8 @@ struct cpu_timer { }; static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } +static inline void posixtimer_rearm_itimer(struct task_struct *p) { } +static inline void posixtimer_rearm(struct kernel_siginfo *info) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -196,5 +200,4 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); -void posixtimer_rearm(struct kernel_siginfo *info); #endif diff --git a/kernel/signal.c b/kernel/signal.c index 4344860ffcac..b65cc1853a09 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -478,42 +478,6 @@ void flush_signals(struct task_struct *t) } EXPORT_SYMBOL(flush_signals); -#ifdef CONFIG_POSIX_TIMERS -static void __flush_itimer_signals(struct sigpending *pending) -{ - sigset_t signal, retain; - struct sigqueue *q, *n; - - signal = pending->signal; - sigemptyset(&retain); - - list_for_each_entry_safe(q, n, &pending->list, list) { - int sig = q->info.si_signo; - - if (likely(q->info.si_code != SI_TIMER)) { - sigaddset(&retain, sig); - } else { - sigdelset(&signal, sig); - list_del_init(&q->list); - __sigqueue_free(q); - } - } - - sigorsets(&pending->signal, &signal, &retain); -} - -void flush_itimer_signals(void) -{ - struct task_struct *tsk = current; - unsigned long flags; - - spin_lock_irqsave(&tsk->sighand->siglock, flags); - __flush_itimer_signals(&tsk->pending); - __flush_itimer_signals(&tsk->signal->shared_pending); - spin_unlock_irqrestore(&tsk->sighand->siglock, flags); -} -#endif - void ignore_signals(struct task_struct *t) { int i; @@ -636,31 +600,9 @@ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); -#ifdef CONFIG_POSIX_TIMERS - /* - * itimer signal ? - * - * itimers are process shared and we restart periodic - * itimers in the signal delivery path to prevent DoS - * attacks in the high resolution timer case. This is - * compliant with the old way of self-restarting - * itimers, as the SIGALRM is a legacy signal and only - * queued once. Changing the restart behaviour to - * restart the timer in the signal dequeue path is - * reducing the timer noise on heavy loaded !highres - * systems too. - */ - if (unlikely(signr == SIGALRM)) { - struct hrtimer *tmr = &tsk->signal->real_timer; - - if (!hrtimer_is_queued(tmr) && - tsk->signal->it_real_incr != 0) { - hrtimer_forward(tmr, tmr->base->get_time(), - tsk->signal->it_real_incr); - hrtimer_restart(tmr); - } - } -#endif + + if (unlikely(signr == SIGALRM)) + posixtimer_rearm_itimer(tsk); } recalc_sigpending(); @@ -682,22 +624,12 @@ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) */ current->jobctl |= JOBCTL_STOP_DEQUEUED; } -#ifdef CONFIG_POSIX_TIMERS - if (resched_timer) { - /* - * Release the siglock to ensure proper locking order - * of timer locks outside of siglocks. Note, we leave - * irqs disabled here, since the posix-timers code is - * about to disable them again anyway. - */ - spin_unlock(&tsk->sighand->siglock); - posixtimer_rearm(info); - spin_lock(&tsk->sighand->siglock); - /* Don't expose the si_sys_private value to userspace */ - info->si_sys_private = 0; + if (IS_ENABLED(CONFIG_POSIX_TIMERS)) { + if (unlikely(resched_timer)) + posixtimer_rearm(info); } -#endif + return signr; } EXPORT_SYMBOL_GPL(dequeue_signal); @@ -1922,15 +1854,43 @@ int kill_pid(struct pid *pid, int sig, int priv) } EXPORT_SYMBOL(kill_pid); +#ifdef CONFIG_POSIX_TIMERS /* - * These functions support sending signals using preallocated sigqueue - * structures. This is needed "because realtime applications cannot - * afford to lose notifications of asynchronous events, like timer - * expirations or I/O completions". In the case of POSIX Timers - * we allocate the sigqueue structure from the timer_create. If this - * allocation fails we are able to report the failure to the application - * with an EAGAIN error. + * These functions handle POSIX timer signals. POSIX timers use + * preallocated sigqueue structs for sending signals. */ +static void __flush_itimer_signals(struct sigpending *pending) +{ + sigset_t signal, retain; + struct sigqueue *q, *n; + + signal = pending->signal; + sigemptyset(&retain); + + list_for_each_entry_safe(q, n, &pending->list, list) { + int sig = q->info.si_signo; + + if (likely(q->info.si_code != SI_TIMER)) { + sigaddset(&retain, sig); + } else { + sigdelset(&signal, sig); + list_del_init(&q->list); + __sigqueue_free(q); + } + } + + sigorsets(&pending->signal, &signal, &retain); +} + +void flush_itimer_signals(void) +{ + struct task_struct *tsk = current; + + guard(spinlock_irqsave)(&tsk->sighand->siglock); + __flush_itimer_signals(&tsk->pending); + __flush_itimer_signals(&tsk->signal->shared_pending); +} + struct sigqueue *sigqueue_alloc(void) { return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); @@ -2027,6 +1987,7 @@ ret: rcu_read_unlock(); return ret; } +#endif /* CONFIG_POSIX_TIMERS */ void do_notify_pidfd(struct task_struct *task) { diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 00629e658ca1..876d389b2e21 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -151,7 +151,27 @@ COMPAT_SYSCALL_DEFINE2(getitimer, int, which, #endif /* - * The timer is automagically restarted, when interval != 0 + * Invoked from dequeue_signal() when SIG_ALRM is delivered. + * + * Restart the ITIMER_REAL timer if it is armed as periodic timer. Doing + * this in the signal delivery path instead of self rearming prevents a DoS + * with small increments in the high reolution timer case and reduces timer + * noise in general. + */ +void posixtimer_rearm_itimer(struct task_struct *tsk) +{ + struct hrtimer *tmr = &tsk->signal->real_timer; + + if (!hrtimer_is_queued(tmr) && tsk->signal->it_real_incr != 0) { + hrtimer_forward(tmr, tmr->base->get_time(), + tsk->signal->it_real_incr); + hrtimer_restart(tmr); + } +} + +/* + * Interval timers are restarted in the signal delivery path. See + * posixtimer_rearm_itimer(). */ enum hrtimer_restart it_real_fn(struct hrtimer *timer) { diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index fc40dacabe78..d461a32b7260 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -251,7 +251,7 @@ static void common_hrtimer_rearm(struct k_itimer *timr) /* * This function is called from the signal delivery code if - * info->si_sys_private is not zero, which indicates that the timer has to + * info::si_sys_private is not zero, which indicates that the timer has to * be rearmed. Restart the timer and update info::si_overrun. */ void posixtimer_rearm(struct kernel_siginfo *info) @@ -259,9 +259,15 @@ void posixtimer_rearm(struct kernel_siginfo *info) struct k_itimer *timr; unsigned long flags; + /* + * Release siglock to ensure proper locking order versus + * timr::it_lock. Keep interrupts disabled. + */ + spin_unlock(¤t->sighand->siglock); + timr = lock_timer(info->si_tid, &flags); if (!timr) - return; + goto out; if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) { timr->kclock->timer_rearm(timr); @@ -275,6 +281,11 @@ void posixtimer_rearm(struct kernel_siginfo *info) } unlock_timer(timr, flags); +out: + spin_lock(¤t->sighand->siglock); + + /* Don't expose the si_sys_private value to userspace */ + info->si_sys_private = 0; } int posix_timer_queue_signal(struct k_itimer *timr) -- cgit v1.2.3 From 4febce44cfebcb490b196d5d10ae9f403ca4c956 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Oct 2024 10:42:03 +0200 Subject: posix-timers: Cure si_sys_private race The si_sys_private member of the siginfo which is embedded in the preallocated sigqueue is used by the posix timer code to decide whether a timer must be reprogrammed on signal delivery. The handling of this is racy as a long standing comment in that code documents. It is modified with the timer lock held, but without sighand lock being held. The actual signal delivery code checks for it under sighand lock without holding the timer lock. Hand the new value to send_sigqueue() as argument and store it with sighand lock held. This is an intermediate change to address this issue. The arguments to this function will be cleanup in subsequent changes. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241001083835.434338954@linutronix.de --- include/linux/sched/signal.h | 2 +- kernel/signal.c | 10 +++++++++- kernel/time/posix-timers.c | 15 +-------------- 3 files changed, 11 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index c8ed09ac29ac..bd9f569231d9 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -340,7 +340,7 @@ extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); +extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type, int si_private); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) diff --git a/kernel/signal.c b/kernel/signal.c index f420c430b24a..1563c83ff224 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1919,7 +1919,7 @@ void sigqueue_free(struct sigqueue *q) __sigqueue_free(q); } -int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) +int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type, int si_private) { int sig = q->info.si_signo; struct sigpending *pending; @@ -1954,6 +1954,14 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type) if (!likely(lock_task_sighand(t, &flags))) goto ret; + /* + * Update @q::info::si_sys_private for posix timer signals with + * sighand locked to prevent a race against dequeue_signal() which + * decides based on si_sys_private whether to invoke + * posixtimer_rearm() or not. + */ + q->info.si_sys_private = si_private; + ret = 1; /* the signal is ignored */ result = TRACE_SIGNAL_IGNORED; if (!prepare_signal(sig, t, false)) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index d461a32b7260..05af074285fa 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -299,21 +299,8 @@ int posix_timer_queue_signal(struct k_itimer *timr) if (timr->it_interval) si_private = ++timr->it_requeue_pending; - /* - * FIXME: if ->sigq is queued we can race with - * dequeue_signal()->posixtimer_rearm(). - * - * If dequeue_signal() sees the "right" value of - * si_sys_private it calls posixtimer_rearm(). - * We re-queue ->sigq and drop ->it_lock(). - * posixtimer_rearm() locks the timer - * and re-schedules it while ->sigq is pending. - * Not really bad, but not that we want. - */ - timr->sigq->info.si_sys_private = si_private; - type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; - ret = send_sigqueue(timr->sigq, timr->it_pid, type); + ret = send_sigqueue(timr->sigq, timr->it_pid, type, si_private); /* If we failed to send the signal the timer stops. */ return ret > 0; } -- cgit v1.2.3 From c775ea28d4e23f5e58b6953645ef90c1b27a8e83 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Oct 2024 10:42:04 +0200 Subject: signal: Allow POSIX timer signals to be dropped In case that a timer was reprogrammed or deleted an already pending signal is obsolete. Right now such signals are kept around and eventually delivered. While POSIX is blury about this: - "The effect of disarming or resetting a timer with pending expiration notifications is unspecified." - "The disposition of pending signals for the deleted timer is unspecified." it is reasonable in both cases to expect that pending signals are discarded as they have no meaning anymore. Prepare the signal code to allow dropping posix timer signals. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241001083835.494416923@linutronix.de --- include/linux/posix-timers.h | 5 +++-- kernel/signal.c | 7 ++++--- kernel/time/posix-timers.c | 3 ++- 3 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 670bf03a56ef..4ab49e5c42af 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -100,8 +100,9 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, { pct->bases[CPUCLOCK_SCHED].nextevt = runtime; } + void posixtimer_rearm_itimer(struct task_struct *p); -void posixtimer_rearm(struct kernel_siginfo *info); +bool posixtimer_deliver_signal(struct kernel_siginfo *info); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ @@ -125,7 +126,7 @@ static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } -static inline void posixtimer_rearm(struct kernel_siginfo *info) { } +static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info) { return false; } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK diff --git a/kernel/signal.c b/kernel/signal.c index 1563c83ff224..df34aa47181e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -594,6 +594,7 @@ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) lockdep_assert_held(&tsk->sighand->siglock); +again: *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { @@ -625,9 +626,9 @@ int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) current->jobctl |= JOBCTL_STOP_DEQUEUED; } - if (IS_ENABLED(CONFIG_POSIX_TIMERS)) { - if (unlikely(resched_timer)) - posixtimer_rearm(info); + if (IS_ENABLED(CONFIG_POSIX_TIMERS) && unlikely(resched_timer)) { + if (!posixtimer_deliver_signal(info)) + goto again; } return signr; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 05af074285fa..dd0b1dff54d9 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -254,7 +254,7 @@ static void common_hrtimer_rearm(struct k_itimer *timr) * info::si_sys_private is not zero, which indicates that the timer has to * be rearmed. Restart the timer and update info::si_overrun. */ -void posixtimer_rearm(struct kernel_siginfo *info) +bool posixtimer_deliver_signal(struct kernel_siginfo *info) { struct k_itimer *timr; unsigned long flags; @@ -286,6 +286,7 @@ out: /* Don't expose the si_sys_private value to userspace */ info->si_sys_private = 0; + return true; } int posix_timer_queue_signal(struct k_itimer *timr) -- cgit v1.2.3 From cd1e93aedab7f749760a33e9e094381973b1120e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Oct 2024 10:42:07 +0200 Subject: posix-timers: Rename k_itimer:: It_requeue_pending Prepare for using this struct member to do a proper reprogramming and deletion accounting so that stale signals can be dropped. No functional change. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241001083835.611997737@linutronix.de --- include/linux/posix-timers.h | 5 ++--- kernel/time/alarmtimer.c | 2 +- kernel/time/posix-cpu-timers.c | 4 ++-- kernel/time/posix-timers.c | 12 ++++++------ 4 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 4ab49e5c42af..253d106fac2c 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -150,8 +150,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_active: Marker that timer is active * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal - * @it_requeue_pending: Indicator that timer waits for being requeued on - * signal delivery + * @it_signal_seq: Sequence count to control signal delivery * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct @@ -172,7 +171,7 @@ struct k_itimer { int it_active; s64 it_overrun; s64 it_overrun_last; - int it_requeue_pending; + unsigned int it_signal_seq; int it_sigev_notify; ktime_t it_interval; struct signal_struct *it_signal; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 8bf888641694..75f844385070 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -584,7 +584,7 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, * small intervals cannot starve the system. */ ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); - ++ptr->it_requeue_pending; + ++ptr->it_signal_seq; ptr->it_active = 1; result = ALARMTIMER_RESTART; } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 6bcee4704059..993243b5be98 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -608,7 +608,7 @@ static void cpu_timer_fire(struct k_itimer *timer) * ticking in case the signal is deliverable next time. */ posix_cpu_timer_rearm(timer); - ++timer->it_requeue_pending; + ++timer->it_signal_seq; } } @@ -745,7 +745,7 @@ static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *i * - Timers which expired, but the signal has not yet been * delivered */ - if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none)) + if (iv && ((timer->it_signal_seq & REQUEUE_PENDING) || sigev_none)) expires = bump_cpu_timer(timer, now); else expires = cpu_timer_getexpires(&timer->it.cpu); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 22e1d6bf349b..fd321fcc3f6c 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -269,13 +269,13 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info) if (!timr) goto out; - if (timr->it_interval && timr->it_requeue_pending == info->si_sys_private) { + if (timr->it_interval && timr->it_signal_seq == info->si_sys_private) { timr->kclock->timer_rearm(timr); timr->it_active = 1; timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1LL; - ++timr->it_requeue_pending; + ++timr->it_signal_seq; info->si_overrun = timer_overrun_to_int(timr, info->si_overrun); } @@ -299,7 +299,7 @@ int posix_timer_queue_signal(struct k_itimer *timr) timr->it_active = 0; if (timr->it_interval) - si_private = ++timr->it_requeue_pending; + si_private = ++timr->it_signal_seq; type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; ret = send_sigqueue(timr->sigq, timr->it_pid, type, si_private); @@ -366,7 +366,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval); ret = HRTIMER_RESTART; - ++timr->it_requeue_pending; + ++timr->it_signal_seq; timr->it_active = 1; } } @@ -660,7 +660,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) * is a SIGEV_NONE timer move the expiry time forward by intervals, * so expiry is > now. */ - if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none)) + if (iv && (timr->it_signal_seq & REQUEUE_PENDING || sig_none)) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); @@ -861,7 +861,7 @@ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_set timer->it_interval = 0; /* Prevent reloading in case there is a signal pending */ - timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING; + timer->it_signal_seq = (timer->it_signal_seq + 2) & ~REQUEUE_PENDING; /* Reset overrun accounting */ timer->it_overrun_last = 0; timer->it_overrun = -1LL; -- cgit v1.2.3 From 1550dde8a537b35dbf066c7f9cfe5f9b360bce0d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 1 Oct 2024 10:42:09 +0200 Subject: posix-timers: Add proper state tracking Right now the state tracking is done by two struct members: - it_active: A boolean which tracks armed/disarmed state - it_signal_seq: A sequence counter which is used to invalidate settings and prevent rearming Replace it_active with it_status and keep properly track about the states in one place. This allows to reuse it_signal_seq to track reprogramming, disarm and delete operations in order to drop signals which are related to the state previous of those operations. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241001083835.670337048@linutronix.de --- include/linux/posix-timers.h | 4 ++-- kernel/time/alarmtimer.c | 2 +- kernel/time/posix-cpu-timers.c | 15 ++++++++------- kernel/time/posix-timers.c | 22 +++++++++++++--------- kernel/time/posix-timers.h | 6 ++++++ 5 files changed, 30 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 253d106fac2c..02afbb4da7f7 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -147,7 +147,7 @@ static inline void posix_cputimers_init_work(void) { } * @kclock: Pointer to the k_clock struct handling this timer * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer - * @it_active: Marker that timer is active + * @it_status: The status of the timer * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery @@ -168,7 +168,7 @@ struct k_itimer { const struct k_clock *kclock; clockid_t it_clock; timer_t it_id; - int it_active; + int it_status; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 75f844385070..452d8aa2f6e0 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -585,7 +585,7 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, */ ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_signal_seq; - ptr->it_active = 1; + ptr->it_status = POSIX_TIMER_ARMED; result = ALARMTIMER_RESTART; } spin_unlock_irqrestore(&ptr->it_lock, flags); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 993243b5be98..12f828d704b1 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -453,7 +453,6 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; - timer->it_active = 0; if (!cpu_timer_dequeue(ctmr)) return; @@ -494,11 +493,12 @@ static int posix_cpu_timer_del(struct k_itimer *timer) */ WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { - if (timer->it.cpu.firing) + if (timer->it.cpu.firing) { ret = TIMER_RETRY; - else + } else { disarm_timer(timer, p); - + timer->it_status = POSIX_TIMER_DISARMED; + } unlock_task_sighand(p, &flags); } @@ -560,7 +560,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); - timer->it_active = 1; + timer->it_status = POSIX_TIMER_ARMED; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; @@ -586,7 +586,8 @@ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; - timer->it_active = 0; + timer->it_status = POSIX_TIMER_DISARMED; + if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, @@ -671,7 +672,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); - timer->it_active = 0; + timer->it_status = POSIX_TIMER_DISARMED; } /* diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index fd321fcc3f6c..dd72b8e72697 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -272,7 +272,7 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info) if (timr->it_interval && timr->it_signal_seq == info->si_sys_private) { timr->kclock->timer_rearm(timr); - timr->it_active = 1; + timr->it_status = POSIX_TIMER_ARMED; timr->it_overrun_last = timr->it_overrun; timr->it_overrun = -1LL; ++timr->it_signal_seq; @@ -292,14 +292,17 @@ out: int posix_timer_queue_signal(struct k_itimer *timr) { + enum posix_timer_state state = POSIX_TIMER_DISARMED; int ret, si_private = 0; enum pid_type type; lockdep_assert_held(&timr->it_lock); - timr->it_active = 0; - if (timr->it_interval) + if (timr->it_interval) { + state = POSIX_TIMER_REQUEUE_PENDING; si_private = ++timr->it_signal_seq; + } + timr->it_status = state; type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; ret = send_sigqueue(timr->sigq, timr->it_pid, type, si_private); @@ -367,7 +370,7 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval); ret = HRTIMER_RESTART; ++timr->it_signal_seq; - timr->it_active = 1; + timr->it_status = POSIX_TIMER_ARMED; } } @@ -640,10 +643,10 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) /* interval timer ? */ if (iv) { cur_setting->it_interval = ktime_to_timespec64(iv); - } else if (!timr->it_active) { + } else if (timr->it_status == POSIX_TIMER_DISARMED) { /* * SIGEV_NONE oneshot timers are never queued and therefore - * timr->it_active is always false. The check below + * timr->it_status is always DISARMED. The check below * vs. remaining time will handle this case. * * For all other timers there is nothing to update here, so @@ -888,7 +891,7 @@ int common_timer_set(struct k_itimer *timr, int flags, if (kc->timer_try_to_cancel(timr) < 0) return TIMER_RETRY; - timr->it_active = 0; + timr->it_status = POSIX_TIMER_DISARMED; posix_timer_set_common(timr, new_setting); /* Keep timer disarmed when it_value is zero */ @@ -901,7 +904,8 @@ int common_timer_set(struct k_itimer *timr, int flags, sigev_none = timr->it_sigev_notify == SIGEV_NONE; kc->timer_arm(timr, expires, flags & TIMER_ABSTIME, sigev_none); - timr->it_active = !sigev_none; + if (!sigev_none) + timr->it_status = POSIX_TIMER_ARMED; return 0; } @@ -1000,7 +1004,7 @@ int common_timer_del(struct k_itimer *timer) timer->it_interval = 0; if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; - timer->it_active = 0; + timer->it_status = POSIX_TIMER_DISARMED; return 0; } diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 4784ea65f685..4d09677e584e 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -1,6 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ #define TIMER_RETRY 1 +enum posix_timer_state { + POSIX_TIMER_DISARMED, + POSIX_TIMER_ARMED, + POSIX_TIMER_REQUEUE_PENDING, +}; + struct k_clock { int (*clock_getres)(const clockid_t which_clock, struct timespec64 *tp); -- cgit v1.2.3 From b35108a51cf7bab58d7eace1267d7965978bcdb8 Mon Sep 17 00:00:00 2001 From: Easwar Hariharan Date: Wed, 30 Oct 2024 17:47:35 +0000 Subject: jiffies: Define secs_to_jiffies() secs_to_jiffies() is defined in hci_event.c and cannot be reused by other call sites. Hoist it into the core code to allow conversion of the ~1150 usages of msecs_to_jiffies() that either: - use a multiplier value of 1000 or equivalently MSEC_PER_SEC, or - have timeouts that are denominated in seconds (i.e. end in 000) It's implemented as a macro to allow usage in static initializers. This will also allow conversion of yet more sites that use (sec * HZ) directly, and improve their readability. Suggested-by: Michael Kelley Signed-off-by: Easwar Hariharan Signed-off-by: Thomas Gleixner Reviewed-by: Luiz Augusto von Dentz Link: https://lore.kernel.org/all/20241030-open-coded-timeouts-v3-1-9ba123facf88@linux.microsoft.com --- include/linux/jiffies.h | 13 +++++++++++++ net/bluetooth/hci_event.c | 2 -- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 5d21dacd62bc..ed945f42e064 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -526,6 +526,19 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) } } +/** + * secs_to_jiffies: - convert seconds to jiffies + * @_secs: time in seconds + * + * Conversion is done by simple multiplication with HZ + * + * secs_to_jiffies() is defined as a macro rather than a static inline + * function so it can be used in static initializers. + * + * Return: jiffies value + */ +#define secs_to_jiffies(_secs) ((_secs) * HZ) + extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) static inline unsigned long _usecs_to_jiffies(const unsigned int u) diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 1c82dcdf6e8f..4bd94d432bcf 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -42,8 +42,6 @@ #define ZERO_KEY "\x00\x00\x00\x00\x00\x00\x00\x00" \ "\x00\x00\x00\x00\x00\x00\x00\x00" -#define secs_to_jiffies(_secs) msecs_to_jiffies((_secs) * 1000) - /* Handle HCI Event packets */ static void *hci_ev_skb_pull(struct hci_dev *hdev, struct sk_buff *skb, -- cgit v1.2.3 From 3b1596a21fbf210f5b763fd3c0be280650475b52 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 29 Oct 2024 13:54:43 +0100 Subject: clockevents: Shutdown and unregister current clockevents at CPUHP_AP_TICK_DYING The way the clockevent devices are finally stopped while a CPU is offlining is currently chaotic. The layout being by order: 1) tick_sched_timer_dying() stops the tick and the underlying clockevent but only for oneshot case. The periodic tick and its related clockevent still runs. 2) tick_broadcast_offline() detaches and stops the per-cpu oneshot broadcast and append it to the released list. 3) Some individual clockevent drivers stop the clockevents (a second time if the tick is oneshot) 4) Once the CPU is dead, a control CPU remotely detaches and stops (a 3rd time if oneshot mode) the CPU clockevent and adds it to the released list. 5) The released list containing the broadcast device released on step 2) and the remotely detached clockevent from step 4) are unregistered. These random events can be factorized if the current clockevent is detached and stopped by the dying CPU at the generic layer, that is from the dying CPU: a) Stop the tick b) Stop/detach the underlying per-cpu oneshot broadcast clockevent c) Stop/detach the underlying clockevent d) Release / unregister the clockevents from b) and c) e) Release / unregister the remaining clockevents from the dying CPU. This part could be performed by the dying CPU This way the drivers and the tick layer don't need to care about clockevent operations during cpuhotplug down. This also unifies the tick behaviour on offline CPUs between oneshot and periodic modes, avoiding offline ticks altogether for sanity. Adopt the simplification. [ tglx: Remove the WARN_ON() in clockevents_register_device() as that is called from an upcoming CPU before the CPU is marked online ] Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20241029125451.54574-3-frederic@kernel.org --- include/linux/tick.h | 2 -- kernel/cpu.c | 2 -- kernel/time/clockevents.c | 30 +++++++++++------------------- kernel/time/tick-internal.h | 3 +-- 4 files changed, 12 insertions(+), 25 deletions(-) (limited to 'include') diff --git a/include/linux/tick.h b/include/linux/tick.h index 72744638c5b0..b0c74bfe0600 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -20,12 +20,10 @@ extern void __init tick_init(void); extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); -extern void tick_cleanup_dead_cpu(int cpu); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } -static inline void tick_cleanup_dead_cpu(int cpu) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU) diff --git a/kernel/cpu.c b/kernel/cpu.c index d293d52a3e00..895f3287e3f3 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1338,8 +1338,6 @@ static int takedown_cpu(unsigned int cpu) cpuhp_bp_sync_dead(cpu); - tick_cleanup_dead_cpu(cpu); - /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 4af27994db93..f3e831f62906 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -618,39 +618,30 @@ void clockevents_resume(void) #ifdef CONFIG_HOTPLUG_CPU -# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST /** - * tick_offline_cpu - Take CPU out of the broadcast mechanism + * tick_offline_cpu - Shutdown all clock events related + * to this CPU and take it out of the + * broadcast mechanism. * @cpu: The outgoing CPU * - * Called on the outgoing CPU after it took itself offline. + * Called by the dying CPU during teardown. */ void tick_offline_cpu(unsigned int cpu) -{ - raw_spin_lock(&clockevents_lock); - tick_broadcast_offline(cpu); - raw_spin_unlock(&clockevents_lock); -} -# endif - -/** - * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu - * @cpu: The dead CPU - */ -void tick_cleanup_dead_cpu(int cpu) { struct clock_event_device *dev, *tmp; - unsigned long flags; - raw_spin_lock_irqsave(&clockevents_lock, flags); + raw_spin_lock(&clockevents_lock); + tick_broadcast_offline(cpu); tick_shutdown(cpu); + /* * Unregister the clock event devices which were - * released from the users in the notify chain. + * released above. */ list_for_each_entry_safe(dev, tmp, &clockevents_released, list) list_del(&dev->list); + /* * Now check whether the CPU has left unused per cpu devices */ @@ -662,7 +653,8 @@ void tick_cleanup_dead_cpu(int cpu) list_del(&dev->list); } } - raw_spin_unlock_irqrestore(&clockevents_lock, flags); + + raw_spin_unlock(&clockevents_lock); } #endif diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 5f2105e637bd..faac36de35b9 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -25,6 +25,7 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); extern void tick_check_new_device(struct clock_event_device *dev); +extern void tick_offline_cpu(unsigned int cpu); extern void tick_shutdown(unsigned int cpu); extern void tick_suspend(void); extern void tick_resume(void); @@ -142,10 +143,8 @@ static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_ #endif /* !(BROADCAST && ONESHOT) */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) -extern void tick_offline_cpu(unsigned int cpu); extern void tick_broadcast_offline(unsigned int cpu); #else -static inline void tick_offline_cpu(unsigned int cpu) { } static inline void tick_broadcast_offline(unsigned int cpu) { } #endif -- cgit v1.2.3 From d44d26987bb3df6d76556827097fc9ce17565cb8 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 31 Oct 2024 13:04:07 +0100 Subject: timekeeping: Remove CONFIG_DEBUG_TIMEKEEPING Since 135225a363ae timekeeping_cycles_to_ns() handles large offsets which would lead to 64bit multiplication overflows correctly. It's also protected against negative motion of the clocksource unconditionally, which was exclusive to x86 before. timekeeping_advance() handles large offsets already correctly. That means the value of CONFIG_DEBUG_TIMEKEEPING which analyzed these cases is very close to zero. Remove all of it. Signed-off-by: Thomas Gleixner Acked-by: John Stultz Link: https://lore.kernel.org/all/20241031120328.536010148@linutronix.de --- arch/riscv/configs/defconfig | 1 - include/linux/timekeeper_internal.h | 16 --- kernel/time/timekeeping.c | 108 +-------------------- lib/Kconfig.debug | 13 --- .../testing/selftests/wireguard/qemu/debug.config | 1 - 5 files changed, 3 insertions(+), 136 deletions(-) (limited to 'include') diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 2341393cfac1..26c01b9e3434 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -301,7 +301,6 @@ CONFIG_DEBUG_MEMORY_INIT=y CONFIG_DEBUG_PER_CPU_MAPS=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_WQ_WATCHDOG=y -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y CONFIG_DEBUG_MUTEXES=y diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index a3b6380a7777..e39d4d563b19 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -76,9 +76,6 @@ struct tk_read_base { * ntp shifted nano seconds. * @ntp_err_mult: Multiplication factor for scaled math conversion * @skip_second_overflow: Flag used to avoid updating NTP twice with same second - * @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING) - * @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING) - * @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING) * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -147,19 +144,6 @@ struct timekeeper { u32 ntp_error_shift; u32 ntp_err_mult; u32 skip_second_overflow; - -#ifdef CONFIG_DEBUG_TIMEKEEPING - long last_warning; - /* - * These simple flag variables are managed - * without locks, which is racy, but they are - * ok since we don't really care about being - * super precise about how many events were - * seen, just that a problem was observed. - */ - int underflow_seen; - int overflow_seen; -#endif }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 17cae886ca82..d115adebc418 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -226,97 +226,6 @@ static inline u64 tk_clock_read(const struct tk_read_base *tkr) return clock->read(clock); } -#ifdef CONFIG_DEBUG_TIMEKEEPING -#define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ - -static void timekeeping_check_update(struct timekeeper *tk, u64 offset) -{ - - u64 max_cycles = tk->tkr_mono.clock->max_cycles; - const char *name = tk->tkr_mono.clock->name; - - if (offset > max_cycles) { - printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", - offset, name, max_cycles); - printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); - } else { - if (offset > (max_cycles >> 1)) { - printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", - offset, name, max_cycles >> 1); - printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); - } - } - - if (tk->underflow_seen) { - if (jiffies - tk->last_warning > WARNING_FREQ) { - printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); - printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); - printk_deferred(" Your kernel is probably still fine.\n"); - tk->last_warning = jiffies; - } - tk->underflow_seen = 0; - } - - if (tk->overflow_seen) { - if (jiffies - tk->last_warning > WARNING_FREQ) { - printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); - printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); - printk_deferred(" Your kernel is probably still fine.\n"); - tk->last_warning = jiffies; - } - tk->overflow_seen = 0; - } -} - -static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); - -static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) -{ - struct timekeeper *tk = &tk_core.timekeeper; - u64 now, last, mask, max, delta; - unsigned int seq; - - /* - * Since we're called holding a seqcount, the data may shift - * under us while we're doing the calculation. This can cause - * false positives, since we'd note a problem but throw the - * results away. So nest another seqcount here to atomically - * grab the points we are checking with. - */ - do { - seq = read_seqcount_begin(&tk_core.seq); - now = tk_clock_read(tkr); - last = tkr->cycle_last; - mask = tkr->mask; - max = tkr->clock->max_cycles; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - delta = clocksource_delta(now, last, mask); - - /* - * Try to catch underflows by checking if we are seeing small - * mask-relative negative values. - */ - if (unlikely((~delta & mask) < (mask >> 3))) - tk->underflow_seen = 1; - - /* Check for multiplication overflows */ - if (unlikely(delta > max)) - tk->overflow_seen = 1; - - /* timekeeping_cycles_to_ns() handles both under and overflow */ - return timekeeping_cycles_to_ns(tkr, now); -} -#else -static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) -{ -} -static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) -{ - BUG(); -} -#endif - /** * tk_setup_internals - Set up internals to use clocksource clock. * @@ -421,19 +330,11 @@ static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 c return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } -static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) +static __always_inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } -static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) -{ - if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) - return timekeeping_debug_get_ns(tkr); - - return __timekeeping_get_ns(tkr); -} - /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update @@ -477,7 +378,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - now += __timekeeping_get_ns(tkr); + now += timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -593,7 +494,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - delta = __timekeeping_get_ns(tkr); + delta = timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) @@ -2333,9 +2234,6 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; - /* Do some additional sanity checking */ - timekeeping_check_update(tk, offset); - /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 7315f643817a..14977b9fc254 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1328,19 +1328,6 @@ config SCHEDSTATS endmenu -config DEBUG_TIMEKEEPING - bool "Enable extra timekeeping sanity checking" - help - This option will enable additional timekeeping sanity checks - which may be helpful when diagnosing issues where timekeeping - problems are suspected. - - This may include checks in the timekeeping hotpaths, so this - option may have a (very small) performance impact to some - workloads. - - If unsure, say N. - config DEBUG_PREEMPT bool "Debug preemptible kernel" depends on DEBUG_KERNEL && PREEMPTION && TRACE_IRQFLAGS_SUPPORT diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 9d172210e2c6..139fd9aa8b12 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -31,7 +31,6 @@ CONFIG_SCHED_DEBUG=y CONFIG_SCHED_INFO=y CONFIG_SCHEDSTATS=y CONFIG_SCHED_STACK_END_CHECK=y -CONFIG_DEBUG_TIMEKEEPING=y CONFIG_DEBUG_PREEMPT=y CONFIG_DEBUG_RT_MUTEXES=y CONFIG_DEBUG_SPINLOCK=y -- cgit v1.2.3 From 513793bc6ab331b947111e8efaf8fcef33fb83e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:31 +0100 Subject: posix-timers: Make signal delivery consistent Signals of timers which are reprogammed, disarmed or deleted can deliver signals related to the past. The POSIX spec is blury about this: - "The effect of disarming or resetting a timer with pending expiration notifications is unspecified." - "The disposition of pending signals for the deleted timer is unspecified." In both cases it is reasonable to expect that pending signals are discarded. Especially in the reprogramming case it does not make sense to account for previous overruns or to deliver a signal for a timer which has been disarmed. This makes the behaviour consistent and understandable. Remove the si_sys_private check from the signal delivery code and invoke posix_timer_deliver_signal() unconditionally for posix timer related signals. Change posix_timer_deliver_signal() so it controls the actual signal delivery via the return value. It now instructs the signal code to drop the signal when: 1) The timer does not longer exist in the hash table 2) The timer signal_seq value is not the same as the si_sys_private value which was set when the signal was queued. This is also a preparatory change to embed the sigqueue into the k_itimer structure, which in turn allows to remove the si_sys_private magic. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241105064213.040348644@linutronix.de --- include/linux/posix-timers.h | 2 -- kernel/signal.c | 6 ++---- kernel/time/posix-cpu-timers.c | 2 +- kernel/time/posix-timers.c | 28 ++++++++++++++++------------ 4 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 02afbb4da7f7..8c6d97412526 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -137,8 +137,6 @@ static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif -#define REQUEUE_PENDING 1 - /** * struct k_itimer - POSIX.1b interval timer structure. * @list: List head for binding the timer to signals->posix_timers diff --git a/kernel/signal.c b/kernel/signal.c index df34aa47181e..68e6bc70ccf2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -550,10 +550,8 @@ still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); - *resched_timer = - (first->flags & SIGQUEUE_PREALLOC) && - (info->si_code == SI_TIMER) && - (info->si_sys_private); + *resched_timer = (first->flags & SIGQUEUE_PREALLOC) && + (info->si_code == SI_TIMER); __sigqueue_free(first); } else { diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 5f444e372464..4305c003c8d4 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -746,7 +746,7 @@ static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *i * - Timers which expired, but the signal has not yet been * delivered */ - if (iv && ((timer->it_signal_seq & REQUEUE_PENDING) || sigev_none)) + if (iv && timer->it_status != POSIX_TIMER_ARMED) expires = bump_cpu_timer(timer, now); else expires = cpu_timer_getexpires(&timer->it.cpu); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index dd72b8e72697..b380e25d4947 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -269,7 +269,10 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info) if (!timr) goto out; - if (timr->it_interval && timr->it_signal_seq == info->si_sys_private) { + if (timr->it_signal_seq != info->si_sys_private) + goto out_unlock; + + if (timr->it_interval && !WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) { timr->kclock->timer_rearm(timr); timr->it_status = POSIX_TIMER_ARMED; @@ -281,6 +284,7 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info) } ret = true; +out_unlock: unlock_timer(timr, flags); out: spin_lock(¤t->sighand->siglock); @@ -293,19 +297,18 @@ out: int posix_timer_queue_signal(struct k_itimer *timr) { enum posix_timer_state state = POSIX_TIMER_DISARMED; - int ret, si_private = 0; enum pid_type type; + int ret; lockdep_assert_held(&timr->it_lock); - if (timr->it_interval) { + if (timr->it_interval) state = POSIX_TIMER_REQUEUE_PENDING; - si_private = ++timr->it_signal_seq; - } + timr->it_status = state; type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; - ret = send_sigqueue(timr->sigq, timr->it_pid, type, si_private); + ret = send_sigqueue(timr->sigq, timr->it_pid, type, timr->it_signal_seq); /* If we failed to send the signal the timer stops. */ return ret > 0; } @@ -663,7 +666,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) * is a SIGEV_NONE timer move the expiry time forward by intervals, * so expiry is > now. */ - if (iv && (timr->it_signal_seq & REQUEUE_PENDING || sig_none)) + if (iv && timr->it_status != POSIX_TIMER_ARMED) timr->it_overrun += kc->timer_forward(timr, now); remaining = kc->timer_remaining(timr, now); @@ -863,8 +866,6 @@ void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_set else timer->it_interval = 0; - /* Prevent reloading in case there is a signal pending */ - timer->it_signal_seq = (timer->it_signal_seq + 2) & ~REQUEUE_PENDING; /* Reset overrun accounting */ timer->it_overrun_last = 0; timer->it_overrun = -1LL; @@ -882,8 +883,6 @@ int common_timer_set(struct k_itimer *timr, int flags, if (old_setting) common_timer_get(timr, old_setting); - /* Prevent rearming by clearing the interval */ - timr->it_interval = 0; /* * Careful here. On SMP systems the timer expiry function could be * active and spinning on timr->it_lock. @@ -933,6 +932,9 @@ retry: if (old_spec64) old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); + /* Prevent signal delivery and rearming. */ + timr->it_signal_seq++; + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -1001,7 +1003,6 @@ int common_timer_del(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; - timer->it_interval = 0; if (kc->timer_try_to_cancel(timer) < 0) return TIMER_RETRY; timer->it_status = POSIX_TIMER_DISARMED; @@ -1012,6 +1013,9 @@ static inline int timer_delete_hook(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; + /* Prevent signal delivery and rearming. */ + timer->it_signal_seq++; + if (WARN_ON_ONCE(!kc || !kc->timer_del)) return -EINVAL; return kc->timer_del(timer); -- cgit v1.2.3 From bf635681c906ad056d1fda325de8d1c12c9f8201 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:33 +0100 Subject: posix-cpu-timers: Cleanup the firing logic The firing flag of a posix CPU timer is tristate: 0: when the timer is not about to deliver a signal 1: when the timer has expired, but the signal has not been delivered yet -1: when the timer was queued for signal delivery and a rearm operation raced against it and supressed the signal delivery. This is a pointless exercise as this can be simply expressed with a boolean. Only if set, the signal is delivered. This makes delete and rearm consistent with the rest of the posix timers. Convert firing to bool and fixup the usage sites accordingly and add comments why the timer cannot be dequeued right away. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241105064213.172848618@linutronix.de --- include/linux/posix-timers.h | 2 +- kernel/time/posix-cpu-timers.c | 34 ++++++++++++++++++++++++---------- 2 files changed, 25 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 8c6d97412526..b1de21731a08 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -49,7 +49,7 @@ struct cpu_timer { struct timerqueue_head *head; struct pid *pid; struct list_head elist; - int firing; + bool firing; struct task_struct __rcu *handling; }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 4305c003c8d4..a282a3c00605 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -493,10 +493,18 @@ static int posix_cpu_timer_del(struct k_itimer *timer) */ WARN_ON_ONCE(ctmr->head || timerqueue_node_queued(&ctmr->node)); } else { - if (timer->it.cpu.firing) + if (timer->it.cpu.firing) { + /* + * Prevent signal delivery. The timer cannot be dequeued + * because it is on the firing list which is not protected + * by sighand->lock. The delivery path is waiting for + * the timer lock. So go back, unlock and retry. + */ + timer->it.cpu.firing = false; ret = TIMER_RETRY; - else + } else { disarm_timer(timer, p); + } unlock_task_sighand(p, &flags); } @@ -668,7 +676,13 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { - timer->it.cpu.firing = -1; + /* + * Prevent signal delivery. The timer cannot be dequeued + * because it is on the firing list which is not protected + * by sighand->lock. The delivery path is waiting for + * the timer lock. So go back, unlock and retry. + */ + timer->it.cpu.firing = false; ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); @@ -809,7 +823,7 @@ static u64 collect_timerqueue(struct timerqueue_head *head, if (++i == MAX_COLLECTED || now < expires) return expires; - ctmr->firing = 1; + ctmr->firing = true; /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(ctmr->handling, current); cpu_timer_dequeue(ctmr); @@ -1364,7 +1378,7 @@ static void handle_posix_cpu_timers(struct task_struct *tsk) * timer call will interfere. */ list_for_each_entry_safe(timer, next, &firing, it.cpu.elist) { - int cpu_firing; + bool cpu_firing; /* * spin_lock() is sufficient here even independent of the @@ -1376,13 +1390,13 @@ static void handle_posix_cpu_timers(struct task_struct *tsk) spin_lock(&timer->it_lock); list_del_init(&timer->it.cpu.elist); cpu_firing = timer->it.cpu.firing; - timer->it.cpu.firing = 0; + timer->it.cpu.firing = false; /* - * The firing flag is -1 if we collided with a reset - * of the timer, which already reported this - * almost-firing as an overrun. So don't generate an event. + * If the firing flag is cleared then this raced with a + * timer rearm/delete operation. So don't generate an + * event. */ - if (likely(cpu_firing >= 0)) + if (likely(cpu_firing)) cpu_timer_fire(timer); /* See posix_cpu_timer_wait_running() */ rcu_assign_pointer(timer->it.cpu.handling, NULL); -- cgit v1.2.3 From 4cf7bf2a2f1a8ace4a49a1138c8123fdb5990093 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:35 +0100 Subject: posix-cpu-timers: Use dedicated flag for CPU timer nanosleep POSIX CPU timer nanosleep creates a k_itimer on stack and uses the sigq pointer to detect the nanosleep case in the expiry function. Prepare for embedding sigqueue into struct k_itimer by using a dedicated flag for nanosleep. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.238550394@linutronix.de --- include/linux/posix-timers.h | 2 ++ kernel/time/posix-cpu-timers.c | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index b1de21731a08..bcd01208d795 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -42,6 +42,7 @@ static inline int clockid_to_fd(const clockid_t clk) * @pid: Pointer to target task PID * @elist: List head for the expiry list * @firing: Timer is currently firing + * @nanosleep: Timer is used for nanosleep and is not a regular posix-timer * @handling: Pointer to the task which handles expiry */ struct cpu_timer { @@ -50,6 +51,7 @@ struct cpu_timer { struct pid *pid; struct list_head elist; bool firing; + bool nanosleep; struct task_struct __rcu *handling; }; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index a282a3c00605..0c441d8c2604 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -596,7 +596,7 @@ static void cpu_timer_fire(struct k_itimer *timer) timer->it_status = POSIX_TIMER_DISARMED; - if (unlikely(timer->sigq == NULL)) { + if (unlikely(ctmr->nanosleep)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. @@ -1493,6 +1493,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, timer.it_overrun = -1; error = posix_cpu_timer_create(&timer); timer.it_process = current; + timer.it.cpu.nanosleep = true; if (!error) { static struct itimerspec64 zero_it; -- cgit v1.2.3 From 5d916a0988eed5217c103932ff4887c9ae83c89c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:36 +0100 Subject: posix-timers: Add a refcount to struct k_itimer To cure the SIG_IGN handling for posix interval timers, the preallocated sigqueue needs to be embedded into struct k_itimer to prevent life time races of all sorts. To make that work correctly it needs reference counting so that timer deletion does not free the timer prematuraly when there is a signal queued or delivered concurrently. Add a rcuref to the posix timer part. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.304756440@linutronix.de --- include/linux/posix-timers.h | 14 ++++++++++++++ kernel/time/posix-timers.c | 7 ++++--- 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index bcd01208d795..9740fd0c2933 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -6,11 +6,13 @@ #include #include #include +#include #include #include struct kernel_siginfo; struct task_struct; +struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, const clockid_t clock) @@ -105,6 +107,7 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_deliver_signal(struct kernel_siginfo *info); +void posixtimer_free_timer(struct k_itimer *timer); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ @@ -129,6 +132,7 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info) { return false; } +static inline void posixtimer_free_timer(struct k_itimer *timer) { } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -156,6 +160,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_signal: Pointer to the creators signal struct * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) + * @rcuref: Reference count for life time management * @sigq: Pointer to preallocated sigqueue * @it: Union representing the various posix timer type * internals. @@ -180,6 +185,7 @@ struct k_itimer { struct task_struct *it_process; }; struct sigqueue *sigq; + rcuref_t rcuref; union { struct { struct hrtimer timer; @@ -200,4 +206,12 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new); +#ifdef CONFIG_POSIX_TIMERS +static inline void posixtimer_putref(struct k_itimer *tmr) +{ + if (rcuref_put(&tmr->rcuref)) + posixtimer_free_timer(tmr); +} +#endif /* !CONFIG_POSIX_TIMERS */ + #endif diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 66ed49efc02f..53bd3c4de92c 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -417,10 +417,11 @@ static struct k_itimer * alloc_posix_timer(void) return NULL; } clear_siginfo(&tmr->sigq->info); + rcuref_init(&tmr->rcuref, 1); return tmr; } -static void posix_timer_free(struct k_itimer *tmr) +void posixtimer_free_timer(struct k_itimer *tmr) { put_pid(tmr->it_pid); sigqueue_free(tmr->sigq); @@ -432,7 +433,7 @@ static void posix_timer_unhash_and_free(struct k_itimer *tmr) spin_lock(&hash_lock); hlist_del_rcu(&tmr->t_hash); spin_unlock(&hash_lock); - posix_timer_free(tmr); + posixtimer_putref(tmr); } static int common_timer_create(struct k_itimer *new_timer) @@ -467,7 +468,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, */ new_timer_id = posix_timer_add(new_timer); if (new_timer_id < 0) { - posix_timer_free(new_timer); + posixtimer_free_timer(new_timer); return new_timer_id; } -- cgit v1.2.3 From 54f1dd642fd088ba969206f09e7afffad7d9db2c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:39 +0100 Subject: signal: Provide posixtimer_sigqueue_init() To cure the SIG_IGN handling for posix interval timers, the preallocated sigqueue needs to be embedded into struct k_itimer to prevent life time races of all sorts. Provide a new function to initialize the embedded sigqueue to prepare for that. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.450427515@linutronix.de --- include/linux/posix-timers.h | 2 ++ kernel/signal.c | 11 +++++++++++ 2 files changed, 13 insertions(+) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 9740fd0c2933..200098d27cc0 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -12,6 +12,7 @@ struct kernel_siginfo; struct task_struct; +struct sigqueue; struct k_itimer; static inline clockid_t make_process_cpuclock(const unsigned int pid, @@ -106,6 +107,7 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, } void posixtimer_rearm_itimer(struct task_struct *p); +bool posixtimer_init_sigqueue(struct sigqueue *q); bool posixtimer_deliver_signal(struct kernel_siginfo *info); void posixtimer_free_timer(struct k_itimer *timer); diff --git a/kernel/signal.c b/kernel/signal.c index dbd42471cf03..911ed3ab479e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1905,6 +1905,17 @@ void flush_itimer_signals(void) __flush_itimer_signals(&tsk->signal->shared_pending); } +bool posixtimer_init_sigqueue(struct sigqueue *q) +{ + struct ucounts *ucounts = sig_get_ucounts(current, -1, 0); + + if (!ucounts) + return false; + clear_siginfo(&q->info); + __sigqueue_init(q, ucounts, SIGQUEUE_PREALLOC); + return true; +} + struct sigqueue *sigqueue_alloc(void) { return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); -- cgit v1.2.3 From ef1c5bcd6daa674392bdf89b8ae889aafd73f956 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:41 +0100 Subject: posix-timers: Store PID type in the timer instead of re-evaluating the signal delivery mode everywhere. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.519086500@linutronix.de --- include/linux/posix-timers.h | 2 ++ kernel/time/posix-timers.c | 9 ++++++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 200098d27cc0..947176582de9 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -180,6 +181,7 @@ struct k_itimer { s64 it_overrun_last; unsigned int it_signal_seq; int it_sigev_notify; + enum pid_type it_pid_type; ktime_t it_interval; struct signal_struct *it_signal; union { diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 53bd3c4de92c..f18d64c7cd3b 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -298,7 +298,6 @@ out: int posix_timer_queue_signal(struct k_itimer *timr) { enum posix_timer_state state = POSIX_TIMER_DISARMED; - enum pid_type type; int ret; lockdep_assert_held(&timr->it_lock); @@ -308,8 +307,7 @@ int posix_timer_queue_signal(struct k_itimer *timr) timr->it_status = state; - type = !(timr->it_sigev_notify & SIGEV_THREAD_ID) ? PIDTYPE_TGID : PIDTYPE_PID; - ret = send_sigqueue(timr->sigq, timr->it_pid, type, timr->it_signal_seq); + ret = send_sigqueue(timr->sigq, timr->it_pid, timr->it_pid_type, timr->it_signal_seq); /* If we failed to send the signal the timer stops. */ return ret > 0; } @@ -496,6 +494,11 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, new_timer->it_pid = get_pid(task_tgid(current)); } + if (new_timer->it_sigev_notify & SIGEV_THREAD_ID) + new_timer->it_pid_type = PIDTYPE_PID; + else + new_timer->it_pid_type = PIDTYPE_TGID; + new_timer->sigq->info.si_tid = new_timer->it_id; new_timer->sigq->info.si_code = SI_TIMER; -- cgit v1.2.3 From 0360ed14d9826678a50fa2b873e522a24cd3c018 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:42 +0100 Subject: signal: Refactor send_sigqueue() To handle posix timers which have their signal ignored via SIG_IGN properly it is required to requeue a ignored signal for delivery when SIG_IGN is lifted so the timer gets rearmed. Split the required code out of send_sigqueue() so it can be reused in context of sigaction(). While at it rename send_sigqueue() to posixtimer_send_sigqueue() so its clear what this is about. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.586453412@linutronix.de --- include/linux/posix-timers.h | 1 + include/linux/sched/signal.h | 1 - kernel/signal.c | 82 ++++++++++++++++++++++++-------------------- kernel/time/posix-timers.c | 2 +- 4 files changed, 47 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 947176582de9..52611ea923b2 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -109,6 +109,7 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); +int posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info); void posixtimer_free_timer(struct k_itimer *timer); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index bd9f569231d9..36283c1c55e9 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -340,7 +340,6 @@ extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); -extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type, int si_private); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) diff --git a/kernel/signal.c b/kernel/signal.c index 911ed3ab479e..5b71e26abb0e 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1947,40 +1947,54 @@ void sigqueue_free(struct sigqueue *q) __sigqueue_free(q); } -int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type, int si_private) +static void posixtimer_queue_sigqueue(struct sigqueue *q, struct task_struct *t, enum pid_type type) { - int sig = q->info.si_signo; struct sigpending *pending; + int sig = q->info.si_signo; + + signalfd_notify(t, sig); + pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; + list_add_tail(&q->list, &pending->list); + sigaddset(&pending->signal, sig); + complete_signal(sig, t, type); +} + +/* + * This function is used by POSIX timers to deliver a timer signal. + * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID + * set), the signal must be delivered to the specific thread (queues + * into t->pending). + * + * Where type is not PIDTYPE_PID, signals must be delivered to the + * process. In this case, prefer to deliver to current if it is in + * the same thread group as the target process, which avoids + * unnecessarily waking up a potentially idle task. + */ +static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr) +{ + struct task_struct *t = pid_task(tmr->it_pid, tmr->it_pid_type); + + if (t && tmr->it_pid_type != PIDTYPE_PID && same_thread_group(t, current)) + t = current; + return t; +} + +int posixtimer_send_sigqueue(struct k_itimer *tmr) +{ + struct sigqueue *q = tmr->sigq; + int sig = q->info.si_signo; struct task_struct *t; unsigned long flags; int ret, result; - if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) - return 0; - if (WARN_ON_ONCE(q->info.si_code != SI_TIMER)) - return 0; - - ret = -1; - rcu_read_lock(); + guard(rcu)(); - /* - * This function is used by POSIX timers to deliver a timer signal. - * Where type is PIDTYPE_PID (such as for timers with SIGEV_THREAD_ID - * set), the signal must be delivered to the specific thread (queues - * into t->pending). - * - * Where type is not PIDTYPE_PID, signals must be delivered to the - * process. In this case, prefer to deliver to current if it is in - * the same thread group as the target process, which avoids - * unnecessarily waking up a potentially idle task. - */ - t = pid_task(pid, type); + t = posixtimer_get_target(tmr); if (!t) - goto ret; - if (type != PIDTYPE_PID && same_thread_group(t, current)) - t = current; + return -1; + if (!likely(lock_task_sighand(t, &flags))) - goto ret; + return -1; /* * Update @q::info::si_sys_private for posix timer signals with @@ -1988,30 +2002,24 @@ int send_sigqueue(struct sigqueue *q, struct pid *pid, enum pid_type type, int s * decides based on si_sys_private whether to invoke * posixtimer_rearm() or not. */ - q->info.si_sys_private = si_private; + q->info.si_sys_private = tmr->it_signal_seq; ret = 1; /* the signal is ignored */ - result = TRACE_SIGNAL_IGNORED; - if (!prepare_signal(sig, t, false)) + if (!prepare_signal(sig, t, false)) { + result = TRACE_SIGNAL_IGNORED; goto out; + } ret = 0; if (unlikely(!list_empty(&q->list))) { result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } - - signalfd_notify(t, sig); - pending = (type != PIDTYPE_PID) ? &t->signal->shared_pending : &t->pending; - list_add_tail(&q->list, &pending->list); - sigaddset(&pending->signal, sig); - complete_signal(sig, t, type); + posixtimer_queue_sigqueue(q, t, tmr->it_pid_type); result = TRACE_SIGNAL_DELIVERED; out: - trace_signal_generate(sig, &q->info, t, type != PIDTYPE_PID, result); + trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); -ret: - rcu_read_unlock(); return ret; } #endif /* CONFIG_POSIX_TIMERS */ diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index f18d64c7cd3b..0901ed9ca183 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -307,7 +307,7 @@ int posix_timer_queue_signal(struct k_itimer *timr) timr->it_status = state; - ret = send_sigqueue(timr->sigq, timr->it_pid, timr->it_pid_type, timr->it_signal_seq); + ret = posixtimer_send_sigqueue(timr); /* If we failed to send the signal the timer stops. */ return ret > 0; } -- cgit v1.2.3 From 11629b9808e5900d675fd469d19932ea48060de3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:43 +0100 Subject: signal: Replace resched_timer logic In preparation for handling ignored posix timer signals correctly and embedding the sigqueue struct into struct k_itimer, hand down a pointer to the sigqueue struct into posix_timer_deliver_signal() instead of just having a boolean flag. No functional change. Suggested-by: Eric W. Biederman Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: "Eric W. Biederman" Link: https://lore.kernel.org/all/20241105064213.652658158@linutronix.de --- include/linux/posix-timers.h | 5 +++-- kernel/signal.c | 32 ++++++++++++++++++++------------ kernel/time/posix-timers.c | 2 +- 3 files changed, 24 insertions(+), 15 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 52611ea923b2..39f1db76833a 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -110,7 +110,7 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); int posixtimer_send_sigqueue(struct k_itimer *tmr); -bool posixtimer_deliver_signal(struct kernel_siginfo *info); +bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); /* Init task static initializer */ @@ -135,7 +135,8 @@ static inline void posix_cputimers_init(struct posix_cputimers *pct) { } static inline void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit) { } static inline void posixtimer_rearm_itimer(struct task_struct *p) { } -static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info) { return false; } +static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, + struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } #endif diff --git a/kernel/signal.c b/kernel/signal.c index 5b71e26abb0e..0ddb5dd284aa 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -545,7 +545,7 @@ bool unhandled_signal(struct task_struct *tsk, int sig) } static void collect_signal(int sig, struct sigpending *list, kernel_siginfo_t *info, - bool *resched_timer) + struct sigqueue **timer_sigq) { struct sigqueue *q, *first = NULL; @@ -568,10 +568,17 @@ still_pending: list_del_init(&first->list); copy_siginfo(info, &first->info); - *resched_timer = (first->flags & SIGQUEUE_PREALLOC) && - (info->si_code == SI_TIMER); - - __sigqueue_free(first); + /* + * posix-timer signals are preallocated and freed when the + * timer goes away. Either directly or by clearing + * SIGQUEUE_PREALLOC so that the next delivery will free + * them. Spare the extra round through __sigqueue_free() + * which is ignoring preallocated signals. + */ + if (unlikely((first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER))) + *timer_sigq = first; + else + __sigqueue_free(first); } else { /* * Ok, it wasn't in the queue. This must be @@ -588,12 +595,12 @@ still_pending: } static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, - kernel_siginfo_t *info, bool *resched_timer) + kernel_siginfo_t *info, struct sigqueue **timer_sigq) { int sig = next_signal(pending, mask); if (sig) - collect_signal(sig, pending, info, resched_timer); + collect_signal(sig, pending, info, timer_sigq); return sig; } @@ -605,18 +612,19 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, int dequeue_signal(sigset_t *mask, kernel_siginfo_t *info, enum pid_type *type) { struct task_struct *tsk = current; - bool resched_timer = false; + struct sigqueue *timer_sigq; int signr; lockdep_assert_held(&tsk->sighand->siglock); again: *type = PIDTYPE_PID; - signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); + timer_sigq = NULL; + signr = __dequeue_signal(&tsk->pending, mask, info, &timer_sigq); if (!signr) { *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, - mask, info, &resched_timer); + mask, info, &timer_sigq); if (unlikely(signr == SIGALRM)) posixtimer_rearm_itimer(tsk); @@ -642,8 +650,8 @@ again: current->jobctl |= JOBCTL_STOP_DEQUEUED; } - if (IS_ENABLED(CONFIG_POSIX_TIMERS) && unlikely(resched_timer)) { - if (!posixtimer_deliver_signal(info)) + if (IS_ENABLED(CONFIG_POSIX_TIMERS) && unlikely(timer_sigq)) { + if (!posixtimer_deliver_signal(info, timer_sigq)) goto again; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0901ed9ca183..d6fef064b357 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -254,7 +254,7 @@ static void common_hrtimer_rearm(struct k_itimer *timr) * This function is called from the signal delivery code. It decides * whether the signal should be dropped and rearms interval timers. */ -bool posixtimer_deliver_signal(struct kernel_siginfo *info) +bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { struct k_itimer *timr; unsigned long flags; -- cgit v1.2.3 From 6017a158beb13b412e55a451379798aae5876514 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:45 +0100 Subject: posix-timers: Embed sigqueue in struct k_itimer To cure the SIG_IGN handling for posix interval timers, the preallocated sigqueue needs to be embedded into struct k_itimer to prevent life time races of all sorts. Now that the prerequisites are in place, embed the sigqueue into struct k_itimer and fixup the relevant usage sites. Aside of preparing for proper SIG_IGN handling, this spares an extra allocation. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.719695194@linutronix.de --- fs/proc/base.c | 4 +- include/linux/posix-timers.h | 23 +++++++++++- kernel/signal.c | 19 ++++++---- kernel/time/posix-timers.c | 88 ++++++++++++++++++++++++++------------------ 4 files changed, 87 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/fs/proc/base.c b/fs/proc/base.c index b31283d81c52..6a37a43241e4 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2553,8 +2553,8 @@ static int show_timer(struct seq_file *m, void *v) seq_printf(m, "ID: %d\n", timer->it_id); seq_printf(m, "signal: %d/%px\n", - timer->sigq->info.si_signo, - timer->sigq->info.si_value.sival_ptr); + timer->sigq.info.si_signo, + timer->sigq.info.si_value.sival_ptr); seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 39f1db76833a..28c0a30e0853 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -39,6 +39,8 @@ static inline int clockid_to_fd(const clockid_t clk) #ifdef CONFIG_POSIX_TIMERS +#include + /** * cpu_timer - Posix CPU timer representation for k_itimer * @node: timerqueue node to queue in the task/sig @@ -166,7 +168,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_pid: The pid of the process/task targeted by the signal * @it_process: The task to wakeup on clock_nanosleep (CPU timers) * @rcuref: Reference count for life time management - * @sigq: Pointer to preallocated sigqueue + * @sigq: Embedded sigqueue * @it: Union representing the various posix timer type * internals. * @rcu: RCU head for freeing the timer. @@ -190,7 +192,7 @@ struct k_itimer { struct pid *it_pid; struct task_struct *it_process; }; - struct sigqueue *sigq; + struct sigqueue sigq; rcuref_t rcuref; union { struct { @@ -218,6 +220,23 @@ static inline void posixtimer_putref(struct k_itimer *tmr) if (rcuref_put(&tmr->rcuref)) posixtimer_free_timer(tmr); } + +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + WARN_ON_ONCE(!rcuref_get(&tmr->rcuref)); +} + +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + posixtimer_putref(tmr); +} +#else /* CONFIG_POSIX_TIMERS */ +static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } +static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } #endif /* !CONFIG_POSIX_TIMERS */ #endif diff --git a/kernel/signal.c b/kernel/signal.c index 0ddb5dd284aa..2d74cd5841ae 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -460,8 +460,10 @@ static struct sigqueue *__sigqueue_alloc(int sig, struct task_struct *t, gfp_t g static void __sigqueue_free(struct sigqueue *q) { - if (q->flags & SIGQUEUE_PREALLOC) + if (q->flags & SIGQUEUE_PREALLOC) { + posixtimer_sigqueue_putref(q); return; + } if (q->ucounts) { dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING); q->ucounts = NULL; @@ -569,11 +571,11 @@ still_pending: copy_siginfo(info, &first->info); /* - * posix-timer signals are preallocated and freed when the - * timer goes away. Either directly or by clearing - * SIGQUEUE_PREALLOC so that the next delivery will free - * them. Spare the extra round through __sigqueue_free() - * which is ignoring preallocated signals. + * posix-timer signals are preallocated and freed when the last + * reference count is dropped in posixtimer_deliver_signal() or + * immediately on timer deletion when the signal is not pending. + * Spare the extra round through __sigqueue_free() which is + * ignoring preallocated signals. */ if (unlikely((first->flags & SIGQUEUE_PREALLOC) && (info->si_code == SI_TIMER))) *timer_sigq = first; @@ -1989,7 +1991,7 @@ static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr) int posixtimer_send_sigqueue(struct k_itimer *tmr) { - struct sigqueue *q = tmr->sigq; + struct sigqueue *q = &tmr->sigq; int sig = q->info.si_signo; struct task_struct *t; unsigned long flags; @@ -2020,9 +2022,12 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) ret = 0; if (unlikely(!list_empty(&q->list))) { + /* This holds a reference count already */ result = TRACE_SIGNAL_ALREADY_PENDING; goto out; } + + posixtimer_sigqueue_getref(q); posixtimer_queue_sigqueue(q, t, tmr->it_pid_type); result = TRACE_SIGNAL_DELIVERED; out: diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index d6fef064b357..2e2c0edcfa97 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -250,15 +250,40 @@ static void common_hrtimer_rearm(struct k_itimer *timr) hrtimer_restart(timer); } +static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_itimer *timr) +{ + guard(spinlock)(&timr->it_lock); + + /* + * Check if the timer is still alive or whether it got modified + * since the signal was queued. In either case, don't rearm and + * drop the signal. + */ + if (timr->it_signal_seq != info->si_sys_private || WARN_ON_ONCE(!timr->it_signal)) + return false; + + if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) + return true; + + timr->kclock->timer_rearm(timr); + timr->it_status = POSIX_TIMER_ARMED; + timr->it_overrun_last = timr->it_overrun; + timr->it_overrun = -1LL; + ++timr->it_signal_seq; + info->si_overrun = timer_overrun_to_int(timr); + return true; +} + /* * This function is called from the signal delivery code. It decides - * whether the signal should be dropped and rearms interval timers. + * whether the signal should be dropped and rearms interval timers. The + * timer can be unconditionally accessed as there is a reference held on + * it. */ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { - struct k_itimer *timr; - unsigned long flags; - bool ret = false; + struct k_itimer *timr = container_of(timer_sigq, struct k_itimer, sigq); + bool ret; /* * Release siglock to ensure proper locking order versus @@ -266,28 +291,11 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *tim */ spin_unlock(¤t->sighand->siglock); - timr = lock_timer(info->si_tid, &flags); - if (!timr) - goto out; - - if (timr->it_signal_seq != info->si_sys_private) - goto out_unlock; - - if (timr->it_interval && !WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) { - timr->kclock->timer_rearm(timr); + ret = __posixtimer_deliver_signal(info, timr); - timr->it_status = POSIX_TIMER_ARMED; - timr->it_overrun_last = timr->it_overrun; - timr->it_overrun = -1LL; - ++timr->it_signal_seq; - - info->si_overrun = timer_overrun_to_int(timr); - } - ret = true; + /* Drop the reference which was acquired when the signal was queued */ + posixtimer_putref(timr); -out_unlock: - unlock_timer(timr, flags); -out: spin_lock(¤t->sighand->siglock); /* Don't expose the si_sys_private value to userspace */ @@ -404,17 +412,17 @@ static struct pid *good_sigevent(sigevent_t * event) } } -static struct k_itimer * alloc_posix_timer(void) +static struct k_itimer *alloc_posix_timer(void) { struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); if (!tmr) return tmr; - if (unlikely(!(tmr->sigq = sigqueue_alloc()))) { + + if (unlikely(!posixtimer_init_sigqueue(&tmr->sigq))) { kmem_cache_free(posix_timers_cache, tmr); return NULL; } - clear_siginfo(&tmr->sigq->info); rcuref_init(&tmr->rcuref, 1); return tmr; } @@ -422,7 +430,8 @@ static struct k_itimer * alloc_posix_timer(void) void posixtimer_free_timer(struct k_itimer *tmr) { put_pid(tmr->it_pid); - sigqueue_free(tmr->sigq); + if (tmr->sigq.ucounts) + dec_rlimit_put_ucounts(tmr->sigq.ucounts, UCOUNT_RLIMIT_SIGPENDING); kfree_rcu(tmr, rcu); } @@ -484,13 +493,13 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, goto out; } new_timer->it_sigev_notify = event->sigev_notify; - new_timer->sigq->info.si_signo = event->sigev_signo; - new_timer->sigq->info.si_value = event->sigev_value; + new_timer->sigq.info.si_signo = event->sigev_signo; + new_timer->sigq.info.si_value = event->sigev_value; } else { new_timer->it_sigev_notify = SIGEV_SIGNAL; - new_timer->sigq->info.si_signo = SIGALRM; - memset(&new_timer->sigq->info.si_value, 0, sizeof(sigval_t)); - new_timer->sigq->info.si_value.sival_int = new_timer->it_id; + new_timer->sigq.info.si_signo = SIGALRM; + memset(&new_timer->sigq.info.si_value, 0, sizeof(sigval_t)); + new_timer->sigq.info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } @@ -499,8 +508,8 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, else new_timer->it_pid_type = PIDTYPE_TGID; - new_timer->sigq->info.si_tid = new_timer->it_id; - new_timer->sigq->info.si_code = SI_TIMER; + new_timer->sigq.info.si_tid = new_timer->it_id; + new_timer->sigq.info.si_code = SI_TIMER; if (copy_to_user(created_timer_id, &new_timer_id, sizeof (new_timer_id))) { error = -EFAULT; @@ -584,7 +593,14 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * 1) Set timr::it_signal to NULL with timr::it_lock held * 2) Release timr::it_lock * 3) Remove from the hash under hash_lock - * 4) Call RCU for removal after the grace period + * 4) Put the reference count. + * + * The reference count might not drop to zero if timr::sigq is + * queued. In that case the signal delivery or flush will put the + * last reference count. + * + * When the reference count reaches zero, the timer is scheduled + * for RCU removal after the grace period. * * Holding rcu_read_lock() accross the lookup ensures that * the timer cannot be freed. -- cgit v1.2.3 From c2a4796a154bb952be1106911841aab2c8c17c4d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:46 +0100 Subject: signal: Cleanup unused posix-timer leftovers Remove the leftovers of sigqueue preallocation as it's not longer used. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.786506636@linutronix.de --- include/linux/sched/signal.h | 2 -- kernel/signal.c | 39 ++++----------------------------------- 2 files changed, 4 insertions(+), 37 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 36283c1c55e9..02972fd41931 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -338,8 +338,6 @@ extern void force_fatal_sig(int); extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); -extern struct sigqueue *sigqueue_alloc(void); -extern void sigqueue_free(struct sigqueue *); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline void clear_notify_signal(void) diff --git a/kernel/signal.c b/kernel/signal.c index 2d74cd5841ae..d267a2c5e977 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -439,8 +439,8 @@ static void __sigqueue_init(struct sigqueue *q, struct ucounts *ucounts, * - this may be called without locks if and only if t == current, otherwise an * appropriate lock must be held to stop the target task from exiting */ -static struct sigqueue *__sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, - int override_rlimit, const unsigned int sigqueue_flags) +static struct sigqueue *sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags, + int override_rlimit) { struct ucounts *ucounts = sig_get_ucounts(t, sig, override_rlimit); struct sigqueue *q; @@ -454,7 +454,7 @@ static struct sigqueue *__sigqueue_alloc(int sig, struct task_struct *t, gfp_t g return NULL; } - __sigqueue_init(q, ucounts, sigqueue_flags); + __sigqueue_init(q, ucounts, 0); return q; } @@ -1070,7 +1070,7 @@ static int __send_signal_locked(int sig, struct kernel_siginfo *info, else override_rlimit = 0; - q = __sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit, 0); + q = sigqueue_alloc(sig, t, GFP_ATOMIC, override_rlimit); if (q) { list_add_tail(&q->list, &pending->list); @@ -1926,37 +1926,6 @@ bool posixtimer_init_sigqueue(struct sigqueue *q) return true; } -struct sigqueue *sigqueue_alloc(void) -{ - return __sigqueue_alloc(-1, current, GFP_KERNEL, 0, SIGQUEUE_PREALLOC); -} - -void sigqueue_free(struct sigqueue *q) -{ - spinlock_t *lock = ¤t->sighand->siglock; - unsigned long flags; - - if (WARN_ON_ONCE(!(q->flags & SIGQUEUE_PREALLOC))) - return; - /* - * We must hold ->siglock while testing q->list - * to serialize with collect_signal() or with - * __exit_signal()->flush_sigqueue(). - */ - spin_lock_irqsave(lock, flags); - q->flags &= ~SIGQUEUE_PREALLOC; - /* - * If it is queued it will be freed when dequeued, - * like the "regular" sigqueue. - */ - if (!list_empty(&q->list)) - q = NULL; - spin_unlock_irqrestore(lock, flags); - - if (q) - __sigqueue_free(q); -} - static void posixtimer_queue_sigqueue(struct sigqueue *q, struct task_struct *t, enum pid_type type) { struct sigpending *pending; -- cgit v1.2.3 From 647da5f709f112319c0d51e06f330d8afecb1940 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:48 +0100 Subject: posix-timers: Move sequence logic into struct k_itimer The posix timer signal handling uses siginfo::si_sys_private for handling the sequence counter check. That indirection is not longer required and the sequence count value at signal queueing time can be stored in struct k_itimer itself. This removes the requirement of treating siginfo::si_sys_private special as it's now always zero as the kernel does not touch it anymore. Suggested-by: Eric W. Biederman Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: "Eric W. Biederman" Link: https://lore.kernel.org/all/20241105064213.852619866@linutronix.de --- include/linux/posix-timers.h | 2 ++ include/uapi/asm-generic/siginfo.h | 2 +- kernel/signal.c | 8 +++----- kernel/time/posix-timers.c | 5 +---- 4 files changed, 7 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 28c0a30e0853..49a89614d900 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -162,6 +162,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery + * @it_sigqueue_seq: The sequence count at the point where the signal was queued * @it_sigev_notify: The notify word of sigevent struct for signal delivery * @it_interval: The interval for periodic timers * @it_signal: Pointer to the creators signal struct @@ -184,6 +185,7 @@ struct k_itimer { s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; + unsigned int it_sigqueue_seq; int it_sigev_notify; enum pid_type it_pid_type; ktime_t it_interval; diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index b7bc545ec3b2..5a1ca43b5fc6 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -46,7 +46,7 @@ union __sifields { __kernel_timer_t _tid; /* timer id */ int _overrun; /* overrun count */ sigval_t _sigval; /* same as below */ - int _sys_private; /* not to be passed to user */ + int _sys_private; /* Not used by the kernel. Historic leftover. Always 0. */ } _timer; /* POSIX.1b signals */ diff --git a/kernel/signal.c b/kernel/signal.c index d267a2c5e977..d2734dc4d74f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1976,12 +1976,10 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) return -1; /* - * Update @q::info::si_sys_private for posix timer signals with - * sighand locked to prevent a race against dequeue_signal() which - * decides based on si_sys_private whether to invoke - * posixtimer_rearm() or not. + * Update @tmr::sigqueue_seq for posix timer signals with sighand + * locked to prevent a race against dequeue_signal(). */ - q->info.si_sys_private = tmr->it_signal_seq; + tmr->it_sigqueue_seq = tmr->it_signal_seq; ret = 1; /* the signal is ignored */ if (!prepare_signal(sig, t, false)) { diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 2e2c0edcfa97..f20c06d0cf09 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -259,7 +259,7 @@ static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_it * since the signal was queued. In either case, don't rearm and * drop the signal. */ - if (timr->it_signal_seq != info->si_sys_private || WARN_ON_ONCE(!timr->it_signal)) + if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!timr->it_signal)) return false; if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) @@ -297,9 +297,6 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *tim posixtimer_putref(timr); spin_lock(¤t->sighand->siglock); - - /* Don't expose the si_sys_private value to userspace */ - info->si_sys_private = 0; return ret; } -- cgit v1.2.3 From 69f032c92cf883ea74a4b69ba3d91317aa6f174e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:49 +0100 Subject: signal: Provide ignored_posix_timers list To prepare for handling posix timer signals on sigaction(SIG_IGN) properly, add a list to task::signal. This list will be used to queue posix timers so their signal can be requeued when SIG_IGN is lifted later. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.920101900@linutronix.de --- include/linux/sched/signal.h | 1 + init/init_task.c | 5 +++-- kernel/fork.c | 1 + 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 02972fd41931..d5d03d919df8 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -138,6 +138,7 @@ struct signal_struct { /* POSIX.1b Interval Timers */ unsigned int next_posix_timer_id; struct hlist_head posix_timers; + struct hlist_head ignored_posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; diff --git a/init/init_task.c b/init/init_task.c index 136a8231355a..e557f622bd90 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -30,8 +30,9 @@ static struct signal_struct init_signals = { .cred_guard_mutex = __MUTEX_INITIALIZER(init_signals.cred_guard_mutex), .exec_update_lock = __RWSEM_INITIALIZER(init_signals.exec_update_lock), #ifdef CONFIG_POSIX_TIMERS - .posix_timers = HLIST_HEAD_INIT, - .cputimer = { + .posix_timers = HLIST_HEAD_INIT, + .ignored_posix_timers = HLIST_HEAD_INIT, + .cputimer = { .cputime_atomic = INIT_CPUTIME_ATOMIC, }, #endif diff --git a/kernel/fork.c b/kernel/fork.c index 60c0b4868fd4..c2bd8367a850 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1864,6 +1864,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); + INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); sig->real_timer.function = it_real_fn; #endif -- cgit v1.2.3 From 0e20cd33acc7a173b23900550331ee82a23e9f00 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:51 +0100 Subject: posix-timers: Handle ignored list on delete and exit To handle posix timer signals on sigaction(SIG_IGN) properly, the timers will be queued on a separate ignored list. Add the necessary cleanup code for timer_delete() and exit_itimers(). Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064213.987530588@linutronix.de --- include/linux/posix-timers.h | 4 +++- kernel/time/posix-timers.c | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 49a89614d900..1608b52a44d5 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -152,7 +152,8 @@ static inline void posix_cputimers_init_work(void) { } /** * struct k_itimer - POSIX.1b interval timer structure. - * @list: List head for binding the timer to signals->posix_timers + * @list: List node for binding the timer to tsk::signal::posix_timers + * @ignored_list: List node for tracking ignored timers in tsk::signal::ignored_posix_timers * @t_hash: Entry in the posix timer hash table * @it_lock: Lock protecting the timer * @kclock: Pointer to the k_clock struct handling this timer @@ -176,6 +177,7 @@ static inline void posix_cputimers_init_work(void) { } */ struct k_itimer { struct hlist_node list; + struct hlist_node ignored_list; struct hlist_node t_hash; spinlock_t it_lock; const struct k_clock *kclock; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index f20c06d0cf09..2b88fb4e937e 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1027,6 +1027,18 @@ int common_timer_del(struct k_itimer *timer) return 0; } +/* + * If the deleted timer is on the ignored list, remove it and + * drop the associated reference. + */ +static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr) +{ + if (!hlist_unhashed(&tmr->ignored_list)) { + hlist_del_init(&tmr->ignored_list); + posixtimer_putref(tmr); + } +} + static inline int timer_delete_hook(struct k_itimer *timer) { const struct k_clock *kc = timer->kclock; @@ -1059,6 +1071,7 @@ retry_delete: spin_lock(¤t->sighand->siglock); hlist_del(&timer->list); + posix_timer_cleanup_ignored(timer); spin_unlock(¤t->sighand->siglock); /* * A concurrent lookup could check timer::it_signal lockless. It @@ -1110,6 +1123,8 @@ retry_delete: } hlist_del(&timer->list); + posix_timer_cleanup_ignored(timer); + /* * Setting timer::it_signal to NULL is technically not required * here as nothing can access the timer anymore legitimately via @@ -1142,6 +1157,19 @@ void exit_itimers(struct task_struct *tsk) /* The timers are not longer accessible via tsk::signal */ while (!hlist_empty(&timers)) itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); + + /* + * There should be no timers on the ignored list. itimer_delete() has + * mopped them up. + */ + if (!WARN_ON_ONCE(!hlist_empty(&tsk->signal->ignored_posix_timers))) + return; + + hlist_move_list(&tsk->signal->ignored_posix_timers, &timers); + while (!hlist_empty(&timers)) { + posix_timer_cleanup_ignored(hlist_entry(timers.first, struct k_itimer, + ignored_list)); + } } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, -- cgit v1.2.3 From df7a996b4dab03c889fa86d849447b716f07b069 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:54 +0100 Subject: signal: Queue ignored posixtimers on ignore list Queue posixtimers which have their signal ignored on the ignored list: 1) When the timer fires and the signal has SIG_IGN set 2) When SIG_IGN is installed via sigaction() and a timer signal is already queued This only happens when the signal is for a valid timer, which delivered the signal in periodic mode. One-shot timer signals are correctly dropped. Due to the lock order constraints (sighand::siglock nests inside timer::lock) the signal code cannot access any of the timer fields which are relevant to make this decision, e.g. timer::it_status. This is addressed by establishing a protection scheme which requires to lock both locks on the timer side for modifying decision fields in the timer struct and therefore makes it possible for the signal delivery to evaluate with only sighand:siglock being held: 1) Move the NULLification of timer->it_signal into the sighand::siglock protected section of timer_delete() and check timer::it_signal in the code path which determines whether the signal is dropped or queued on the ignore list. This ensures that a deleted timer cannot be moved onto the ignore list, which would prevent it from being freed on exit() as it is not longer in the process' posix timer list. If the timer got moved to the ignored list before deletion then it is removed from the ignored list under sighand lock in timer_delete(). 2) Provide a new timer::it_sig_periodic flag, which gets set in the signal queue path with both timer and sighand locks held if the timer is actually in periodic mode at expiry time. The ignore list code checks this flag under sighand::siglock and drops the signal when it is not set. If it is set, then the signal is moved to the ignored list independent of the actual state of the timer. When the signal is un-ignored later then the signal is moved back to the signal queue. On signal delivery the posix timer side decides about dropping the signal if the timer was re-armed, dis-armed or deleted based on the signal sequence counter check. If the thread/process exits then not yet delivered signals are discarded which means the reference of the timer containing the sigqueue is dropped and frees the timer. This is way cheaper than requiring all code paths to lock sighand::siglock of the target thread/process on any modification of timer::it_status or going all the way and removing pending signals from the signal queues on every rearm, disarm or delete operation. So the protection scheme here is that on the timer side both timer::lock and sighand::siglock have to be held for modifying timer::it_signal timer::it_sig_periodic which means that on the signal side holding sighand::siglock is enough to evaluate these fields. In posixtimer_deliver_signal() holding timer::lock is sufficient to do the sequence validation against timer::it_signal_seq because a concurrent expiry is waiting on timer::lock to be released. This completes the SIG_IGN handling and such timers are not longer self rearmed which avoids pointless wakeups. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064214.120756416@linutronix.de --- include/linux/posix-timers.h | 2 ++ kernel/signal.c | 80 +++++++++++++++++++++++++++++++++++++++++--- kernel/time/posix-timers.c | 7 +++- 3 files changed, 83 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 1608b52a44d5..43ea6e784a25 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -160,6 +160,7 @@ static inline void posix_cputimers_init_work(void) { } * @it_clock: The posix timer clock id * @it_id: The posix timer id for identifying the timer * @it_status: The status of the timer + * @it_sig_periodic: The periodic status at signal delivery * @it_overrun: The overrun counter for pending signals * @it_overrun_last: The overrun at the time of the last delivered signal * @it_signal_seq: Sequence count to control signal delivery @@ -184,6 +185,7 @@ struct k_itimer { clockid_t it_clock; timer_t it_id; int it_status; + bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; diff --git a/kernel/signal.c b/kernel/signal.c index 908b49c594e4..9b098a7a206f 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -59,6 +59,8 @@ #include #include /* for syscall_get_* */ +#include "time/posix-timers.h" + /* * SLAB caches for signal bits. */ @@ -731,6 +733,16 @@ void signal_wake_up_state(struct task_struct *t, unsigned int state) kick_process(t); } +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q); + +static void sigqueue_free_ignored(struct task_struct *tsk, struct sigqueue *q) +{ + if (likely(!(q->flags & SIGQUEUE_PREALLOC) || q->info.si_code != SI_TIMER)) + __sigqueue_free(q); + else + posixtimer_sig_ignore(tsk, q); +} + /* Remove signals in mask from the pending set and queue. */ static void flush_sigqueue_mask(struct task_struct *p, sigset_t *mask, struct sigpending *s) { @@ -747,7 +759,7 @@ static void flush_sigqueue_mask(struct task_struct *p, sigset_t *mask, struct si list_for_each_entry_safe(q, n, &s->list, list) { if (sigismember(mask, q->info.si_signo)) { list_del_init(&q->list); - __sigqueue_free(q); + sigqueue_free_ignored(p, q); } } } @@ -1964,7 +1976,7 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) int sig = q->info.si_signo; struct task_struct *t; unsigned long flags; - int ret, result; + int result; guard(rcu)(); @@ -1981,13 +1993,55 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) */ tmr->it_sigqueue_seq = tmr->it_signal_seq; - ret = 1; /* the signal is ignored */ + /* + * Set the signal delivery status under sighand lock, so that the + * ignored signal handling can distinguish between a periodic and a + * non-periodic timer. + */ + tmr->it_sig_periodic = tmr->it_status == POSIX_TIMER_REQUEUE_PENDING; + if (!prepare_signal(sig, t, false)) { result = TRACE_SIGNAL_IGNORED; + + /* Paranoia check. Try to survive. */ + if (WARN_ON_ONCE(!list_empty(&q->list))) + goto out; + + /* Periodic timers with SIG_IGN are queued on the ignored list */ + if (tmr->it_sig_periodic) { + /* + * Already queued means the timer was rearmed after + * the previous expiry got it on the ignore list. + * Nothing to do for that case. + */ + if (hlist_unhashed(&tmr->ignored_list)) { + /* + * Take a signal reference and queue it on + * the ignored list. + */ + posixtimer_sigqueue_getref(q); + posixtimer_sig_ignore(t, q); + } + } else if (!hlist_unhashed(&tmr->ignored_list)) { + /* + * Covers the case where a timer was periodic and + * then the signal was ignored. Later it was rearmed + * as oneshot timer. The previous signal is invalid + * now, and this oneshot signal has to be dropped. + * Remove it from the ignored list and drop the + * reference count as the signal is not longer + * queued. + */ + hlist_del_init(&tmr->ignored_list); + posixtimer_putref(tmr); + } goto out; } - ret = 0; + /* This should never happen and leaks a reference count */ + if (WARN_ON_ONCE(!hlist_unhashed(&tmr->ignored_list))) + hlist_del_init(&tmr->ignored_list); + if (unlikely(!list_empty(&q->list))) { /* This holds a reference count already */ result = TRACE_SIGNAL_ALREADY_PENDING; @@ -2000,7 +2054,22 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) out: trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); - return ret; + return 0; +} + +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) +{ + struct k_itimer *tmr = container_of(q, struct k_itimer, sigq); + + /* + * If the timer is marked deleted already or the signal originates + * from a non-periodic timer, then just drop the reference + * count. Otherwise queue it on the ignored list. + */ + if (tmr->it_signal && tmr->it_sig_periodic) + hlist_add_head(&tmr->ignored_list, &tsk->signal->ignored_posix_timers); + else + posixtimer_putref(tmr); } static void posixtimer_sig_unignore(struct task_struct *tsk, int sig) @@ -2048,6 +2117,7 @@ static void posixtimer_sig_unignore(struct task_struct *tsk, int sig) } } #else /* CONFIG_POSIX_TIMERS */ +static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) { } static inline void posixtimer_sig_unignore(struct task_struct *tsk, int sig) { } #endif /* !CONFIG_POSIX_TIMERS */ diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 2b88fb4e937e..ea72db3c9365 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -1072,12 +1072,17 @@ retry_delete: spin_lock(¤t->sighand->siglock); hlist_del(&timer->list); posix_timer_cleanup_ignored(timer); - spin_unlock(¤t->sighand->siglock); /* * A concurrent lookup could check timer::it_signal lockless. It * will reevaluate with timer::it_lock held and observe the NULL. + * + * It must be written with siglock held so that the signal code + * observes timer->it_signal == NULL in do_sigaction(SIG_IGN), + * which prevents it from moving a pending signal of a deleted + * timer to the ignore list. */ WRITE_ONCE(timer->it_signal, NULL); + spin_unlock(¤t->sighand->siglock); unlock_timer(timer, flags); posix_timer_unhash_and_free(timer); -- cgit v1.2.3 From 7a66f72b09bb0762360274b1fb677b3433dbaa06 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:55 +0100 Subject: posix-timers: Cleanup SIG_IGN workaround leftovers Now that ignored posix timer signals are requeued and the timers are rearmed on signal delivery the workaround to keep such timers alive and self rearm them is not longer required. Remove the relevant hacks and the not longer required return values from the related functions. The alarm timer workarounds will be cleaned up in a separate step. Signed-off-by: Thomas Gleixner Reviewed-by: Frederic Weisbecker Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/all/20241105064214.187239060@linutronix.de --- include/linux/posix-timers.h | 2 +- kernel/signal.c | 7 ++-- kernel/time/alarmtimer.c | 47 ++++++--------------------- kernel/time/posix-cpu-timers.c | 18 +++-------- kernel/time/posix-timers.c | 73 ++++-------------------------------------- kernel/time/posix-timers.h | 2 +- 6 files changed, 24 insertions(+), 125 deletions(-) (limited to 'include') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 43ea6e784a25..f11f10c97bd9 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -111,7 +111,7 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct, void posixtimer_rearm_itimer(struct task_struct *p); bool posixtimer_init_sigqueue(struct sigqueue *q); -int posixtimer_send_sigqueue(struct k_itimer *tmr); +void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); diff --git a/kernel/signal.c b/kernel/signal.c index 9b098a7a206f..cbf70c808969 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1970,7 +1970,7 @@ static inline struct task_struct *posixtimer_get_target(struct k_itimer *tmr) return t; } -int posixtimer_send_sigqueue(struct k_itimer *tmr) +void posixtimer_send_sigqueue(struct k_itimer *tmr) { struct sigqueue *q = &tmr->sigq; int sig = q->info.si_signo; @@ -1982,10 +1982,10 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) t = posixtimer_get_target(tmr); if (!t) - return -1; + return; if (!likely(lock_task_sighand(t, &flags))) - return -1; + return; /* * Update @tmr::sigqueue_seq for posix timer signals with sighand @@ -2054,7 +2054,6 @@ int posixtimer_send_sigqueue(struct k_itimer *tmr) out: trace_signal_generate(sig, &q->info, t, tmr->it_pid_type != PIDTYPE_PID, result); unlock_task_sighand(t, &flags); - return 0; } static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueue *q) diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 452d8aa2f6e0..8543d7f1cdb4 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -197,28 +197,15 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) { struct alarm *alarm = container_of(timer, struct alarm, timer); struct alarm_base *base = &alarm_bases[alarm->type]; - unsigned long flags; - int ret = HRTIMER_NORESTART; - int restart = ALARMTIMER_NORESTART; - spin_lock_irqsave(&base->lock, flags); - alarmtimer_dequeue(base, alarm); - spin_unlock_irqrestore(&base->lock, flags); + scoped_guard (spinlock_irqsave, &base->lock) + alarmtimer_dequeue(base, alarm); if (alarm->function) - restart = alarm->function(alarm, base->get_ktime()); - - spin_lock_irqsave(&base->lock, flags); - if (restart != ALARMTIMER_NORESTART) { - hrtimer_set_expires(&alarm->timer, alarm->node.expires); - alarmtimer_enqueue(base, alarm); - ret = HRTIMER_RESTART; - } - spin_unlock_irqrestore(&base->lock, flags); + alarm->function(alarm, base->get_ktime()); trace_alarmtimer_fired(alarm, base->get_ktime()); - return ret; - + return HRTIMER_NORESTART; } ktime_t alarm_expires_remaining(const struct alarm *alarm) @@ -567,30 +554,14 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * * Return: whether the timer is to be restarted */ -static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, - ktime_t now) +static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) { - struct k_itimer *ptr = container_of(alarm, struct k_itimer, - it.alarm.alarmtimer); - enum alarmtimer_restart result = ALARMTIMER_NORESTART; - unsigned long flags; - - spin_lock_irqsave(&ptr->it_lock, flags); + struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); - if (posix_timer_queue_signal(ptr) && ptr->it_interval) { - /* - * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. Ensure that - * small intervals cannot starve the system. - */ - ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); - ++ptr->it_signal_seq; - ptr->it_status = POSIX_TIMER_ARMED; - result = ALARMTIMER_RESTART; - } - spin_unlock_irqrestore(&ptr->it_lock, flags); + guard(spinlock_irqsave)(&ptr->it_lock); + posix_timer_queue_signal(ptr); - return result; + return ALARMTIMER_NORESTART; } /** diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 0c441d8c2604..50e8d04ab661 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -603,21 +603,11 @@ static void cpu_timer_fire(struct k_itimer *timer) */ wake_up_process(timer->it_process); cpu_timer_setexpires(ctmr, 0); - } else if (!timer->it_interval) { - /* - * One-shot timer. Clear it as soon as it's fired. - */ + } else { posix_timer_queue_signal(timer); - cpu_timer_setexpires(ctmr, 0); - } else if (posix_timer_queue_signal(timer)) { - /* - * The signal did not get queued because the signal - * was ignored, so we won't get any callback to - * reload the timer. But we need to keep it - * ticking in case the signal is deliverable next time. - */ - posix_cpu_timer_rearm(timer); - ++timer->it_signal_seq; + /* Disable oneshot timers */ + if (!timer->it_interval) + cpu_timer_setexpires(ctmr, 0); } } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index ea72db3c9365..881a9ce96af7 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -300,21 +300,12 @@ bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *tim return ret; } -int posix_timer_queue_signal(struct k_itimer *timr) +void posix_timer_queue_signal(struct k_itimer *timr) { - enum posix_timer_state state = POSIX_TIMER_DISARMED; - int ret; - lockdep_assert_held(&timr->it_lock); - if (timr->it_interval) - state = POSIX_TIMER_REQUEUE_PENDING; - - timr->it_status = state; - - ret = posixtimer_send_sigqueue(timr); - /* If we failed to send the signal the timer stops. */ - return ret > 0; + timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED; + posixtimer_send_sigqueue(timr); } /* @@ -327,62 +318,10 @@ int posix_timer_queue_signal(struct k_itimer *timr) static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); - enum hrtimer_restart ret = HRTIMER_NORESTART; - unsigned long flags; - - spin_lock_irqsave(&timr->it_lock, flags); - - if (posix_timer_queue_signal(timr)) { - /* - * The signal was not queued due to SIG_IGN. As a - * consequence the timer is not going to be rearmed from - * the signal delivery path. But as a real signal handler - * can be installed later the timer must be rearmed here. - */ - if (timr->it_interval != 0) { - ktime_t now = hrtimer_cb_get_time(timer); - - /* - * FIXME: What we really want, is to stop this - * timer completely and restart it in case the - * SIG_IGN is removed. This is a non trivial - * change to the signal handling code. - * - * For now let timers with an interval less than a - * jiffy expire every jiffy and recheck for a - * valid signal handler. - * - * This avoids interrupt starvation in case of a - * very small interval, which would expire the - * timer immediately again. - * - * Moving now ahead of time by one jiffy tricks - * hrtimer_forward() to expire the timer later, - * while it still maintains the overrun accuracy - * for the price of a slight inconsistency in the - * timer_gettime() case. This is at least better - * than a timer storm. - * - * Only required when high resolution timers are - * enabled as the periodic tick based timers are - * automatically aligned to the next tick. - */ - if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS)) { - ktime_t kj = TICK_NSEC; - - if (timr->it_interval < kj) - now = ktime_add(now, kj); - } - - timr->it_overrun += hrtimer_forward(timer, now, timr->it_interval); - ret = HRTIMER_RESTART; - ++timr->it_signal_seq; - timr->it_status = POSIX_TIMER_ARMED; - } - } - unlock_timer(timr, flags); - return ret; + guard(spinlock_irqsave)(&timr->it_lock); + posix_timer_queue_signal(timr); + return HRTIMER_NORESTART; } static struct pid *good_sigevent(sigevent_t * event) diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index 4d09677e584e..61906f0688c1 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -42,7 +42,7 @@ extern const struct k_clock clock_process; extern const struct k_clock clock_thread; extern const struct k_clock alarm_clock; -int posix_timer_queue_signal(struct k_itimer *timr); +void posix_timer_queue_signal(struct k_itimer *timr); void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); int common_timer_set(struct k_itimer *timr, int flags, -- cgit v1.2.3 From 2634303f8773b0c602069887565cd412440be15d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 5 Nov 2024 09:14:58 +0100 Subject: alarmtimers: Remove return value from alarm functions Now that the SIG_IGN problem is solved in the core code, the alarmtimer callbacks do not require a return value anymore. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Acked-by: Frederic Weisbecker Link: https://lore.kernel.org/all/20241105064214.318837272@linutronix.de --- drivers/power/supply/charger-manager.c | 3 +-- fs/timerfd.c | 4 +--- include/linux/alarmtimer.h | 10 ++-------- kernel/time/alarmtimer.c | 16 +++++----------- net/netfilter/xt_IDLETIMER.c | 4 +--- 5 files changed, 10 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/power/supply/charger-manager.c b/drivers/power/supply/charger-manager.c index 96f0a7fbf105..09ec0ecf1486 100644 --- a/drivers/power/supply/charger-manager.c +++ b/drivers/power/supply/charger-manager.c @@ -1412,10 +1412,9 @@ static inline struct charger_desc *cm_get_drv_data(struct platform_device *pdev) return dev_get_platdata(&pdev->dev); } -static enum alarmtimer_restart cm_timer_func(struct alarm *alarm, ktime_t now) +static void cm_timer_func(struct alarm *alarm, ktime_t now) { cm_timer_set = false; - return ALARMTIMER_NORESTART; } static int charger_manager_probe(struct platform_device *pdev) diff --git a/fs/timerfd.c b/fs/timerfd.c index 137523e0bb21..f10c99ad5c60 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -79,13 +79,11 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) return HRTIMER_NORESTART; } -static enum alarmtimer_restart timerfd_alarmproc(struct alarm *alarm, - ktime_t now) +static void timerfd_alarmproc(struct alarm *alarm, ktime_t now) { struct timerfd_ctx *ctx = container_of(alarm, struct timerfd_ctx, t.alarm); timerfd_triggered(ctx); - return ALARMTIMER_NORESTART; } /* diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h index 05e758b8b894..3ffa5341dce2 100644 --- a/include/linux/alarmtimer.h +++ b/include/linux/alarmtimer.h @@ -20,12 +20,6 @@ enum alarmtimer_type { ALARM_BOOTTIME_FREEZER, }; -enum alarmtimer_restart { - ALARMTIMER_NORESTART, - ALARMTIMER_RESTART, -}; - - #define ALARMTIMER_STATE_INACTIVE 0x00 #define ALARMTIMER_STATE_ENQUEUED 0x01 @@ -42,14 +36,14 @@ enum alarmtimer_restart { struct alarm { struct timerqueue_node node; struct hrtimer timer; - enum alarmtimer_restart (*function)(struct alarm *, ktime_t now); + void (*function)(struct alarm *, ktime_t now); enum alarmtimer_type type; int state; void *data; }; void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)); + void (*function)(struct alarm *, ktime_t)); void alarm_start(struct alarm *alarm, ktime_t start); void alarm_start_relative(struct alarm *alarm, ktime_t start); void alarm_restart(struct alarm *alarm); diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 593e7d561fa8..37d2d79daea4 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -321,7 +321,7 @@ static int alarmtimer_resume(struct device *dev) static void __alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); alarm->timer.function = alarmtimer_fired; @@ -337,7 +337,7 @@ __alarm_init(struct alarm *alarm, enum alarmtimer_type type, * @function: callback that is run when the alarm fires */ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); @@ -530,14 +530,12 @@ static enum alarmtimer_type clock2alarm(clockid_t clockid) * * Return: whether the timer is to be restarted */ -static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, ktime_t now) +static void alarm_handle_timer(struct alarm *alarm, ktime_t now) { struct k_itimer *ptr = container_of(alarm, struct k_itimer, it.alarm.alarmtimer); guard(spinlock_irqsave)(&ptr->it_lock); posix_timer_queue_signal(ptr); - - return ALARMTIMER_NORESTART; } /** @@ -698,18 +696,14 @@ static int alarm_timer_create(struct k_itimer *new_timer) * @now: time at the timer expiration * * Wakes up the task that set the alarmtimer - * - * Return: ALARMTIMER_NORESTART */ -static enum alarmtimer_restart alarmtimer_nsleep_wakeup(struct alarm *alarm, - ktime_t now) +static void alarmtimer_nsleep_wakeup(struct alarm *alarm, ktime_t now) { struct task_struct *task = alarm->data; alarm->data = NULL; if (task) wake_up_process(task); - return ALARMTIMER_NORESTART; } /** @@ -761,7 +755,7 @@ static int alarmtimer_do_nsleep(struct alarm *alarm, ktime_t absexp, static void alarm_init_on_stack(struct alarm *alarm, enum alarmtimer_type type, - enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) + void (*function)(struct alarm *, ktime_t)) { hrtimer_init_on_stack(&alarm->timer, alarm_bases[type].base_clockid, HRTIMER_MODE_ABS); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index db720efa811d..5514600586a9 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -107,14 +107,12 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } -static enum alarmtimer_restart idletimer_tg_alarmproc(struct alarm *alarm, - ktime_t now) +static void idletimer_tg_alarmproc(struct alarm *alarm, ktime_t now) { struct idletimer_tg *timer = alarm->data; pr_debug("alarm %s expired\n", timer->attr.attr.name); schedule_work(&timer->work); - return ALARMTIMER_NORESTART; } static int idletimer_check_sysfs_name(const char *name, unsigned int size) -- cgit v1.2.3 From fbf920f255315974808ce91d934fe50198294d51 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:15 +0100 Subject: hrtimers: Add missing hrtimer_init() trace points hrtimer_init*_on_stack() is not covered by tracing when CONFIG_DEBUG_OBJECTS_TIMERS=y. Rework the functions similar to hrtimer_init() and hrtimer_init_sleeper() so that the hrtimer_init() tracepoint is unconditionally available. The rework makes hrtimer_init_sleeper() unused. Delete it. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/74528e8abf2bb96e8bee85ffacbf14e15cf89f0d.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 19 +-------------- kernel/time/hrtimer.c | 65 +++++++++++++++++++++++++++---------------------- 2 files changed, 37 insertions(+), 47 deletions(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index aa1e65ccb615..5aa9d57528c4 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -228,32 +228,15 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); -extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, - enum hrtimer_mode mode); - -#ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); +#ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_hrtimer_on_stack(struct hrtimer *timer); #else -static inline void hrtimer_init_on_stack(struct hrtimer *timer, - clockid_t which_clock, - enum hrtimer_mode mode) -{ - hrtimer_init(timer, which_clock, mode); -} - -static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode) -{ - hrtimer_init_sleeper(sl, clock_id, mode); -} - static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } #endif diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 04f7d8a392c3..4b0507cf38ea 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -417,6 +417,11 @@ static inline void debug_hrtimer_init(struct hrtimer *timer) debug_object_init(timer, &hrtimer_debug_descr); } +static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) +{ + debug_object_init_on_stack(timer, &hrtimer_debug_descr); +} + static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { @@ -428,28 +433,6 @@ static inline void debug_hrtimer_deactivate(struct hrtimer *timer) debug_object_deactivate(timer, &hrtimer_debug_descr); } -static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, - enum hrtimer_mode mode); - -void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, - enum hrtimer_mode mode) -{ - debug_object_init_on_stack(timer, &hrtimer_debug_descr); - __hrtimer_init(timer, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); - -static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, - clockid_t clock_id, enum hrtimer_mode mode); - -void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, enum hrtimer_mode mode) -{ - debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); - __hrtimer_init_sleeper(sl, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); - void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); @@ -459,6 +442,7 @@ EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } +static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } @@ -472,6 +456,13 @@ debug_init(struct hrtimer *timer, clockid_t clockid, trace_hrtimer_init(timer, clockid, mode); } +static inline void debug_init_on_stack(struct hrtimer *timer, clockid_t clockid, + enum hrtimer_mode mode) +{ + debug_hrtimer_init_on_stack(timer); + trace_hrtimer_init(timer, clockid, mode); +} + static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { @@ -1600,6 +1591,23 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init); +/** + * hrtimer_init_on_stack - initialize a timer in stack memory + * @timer: The timer to be initialized + * @clock_id: The clock to be used + * @mode: The timer mode + * + * Similar to hrtimer_init(), except that this one must be used if struct hrtimer is in stack + * memory. + */ +void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) +{ + debug_init_on_stack(timer, clock_id, mode); + __hrtimer_init(timer, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); + /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated @@ -1944,7 +1952,7 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because - * hrtimer_init_sleeper() determines the delivery mode on RT so the + * __hrtimer_init_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) @@ -1987,19 +1995,18 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, } /** - * hrtimer_init_sleeper - initialize sleeper to the given clock + * hrtimer_init_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ -void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, - enum hrtimer_mode mode) +void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode) { - debug_init(&sl->timer, clock_id, mode); + debug_init_on_stack(&sl->timer, clock_id, mode); __hrtimer_init_sleeper(sl, clock_id, mode); - } -EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); +EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { -- cgit v1.2.3 From 908a1d775422ba2e27a5e33d0c130b522419e121 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:20 +0100 Subject: hrtimers: Introduce hrtimer_setup() to replace hrtimer_init() To initialize hrtimer, hrtimer_init() needs to be called and also hrtimer::function must be set. This is error-prone and awkward to use. Introduce hrtimer_setup() which does both of these things, so that users of hrtimer can be simplified. The new setup function also has a sanity check for the provided function pointer. If NULL, a warning is emitted and a dummy callback installed. hrtimer_init() will be removed as soon as all of its users have been converted to the new function. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/5057c1ddbfd4b92033cd93d37fe38e6b069d5ba6.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 2 ++ kernel/time/hrtimer.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 5aa9d57528c4..bcc0715c59a8 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -228,6 +228,8 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer) /* Initialize timers: */ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); +extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 4b0507cf38ea..a5ef67edcda9 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1535,6 +1535,11 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) return HRTIMER_BASE_MONOTONIC; } +static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) +{ + return HRTIMER_NORESTART; +} + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, enum hrtimer_mode mode) { @@ -1571,6 +1576,18 @@ static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, timerqueue_init(&timer->node); } +static void __hrtimer_setup(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + __hrtimer_init(timer, clock_id, mode); + + if (WARN_ON_ONCE(!function)) + timer->function = hrtimer_dummy_timeout; + else + timer->function = function; +} + /** * hrtimer_init - initialize a timer to the given clock * @timer: the timer to be initialized @@ -1591,6 +1608,27 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init); +/** + * hrtimer_setup - initialize a timer to the given clock + * @timer: the timer to be initialized + * @function: the callback function + * @clock_id: the clock to be used + * @mode: The modes which are relevant for initialization: + * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, + * HRTIMER_MODE_REL_SOFT + * + * The PINNED variants of the above can be handed in, + * but the PINNED bit is ignored as pinning happens + * when the hrtimer is started + */ +void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_init(timer, clock_id, mode); + __hrtimer_setup(timer, function, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_setup); + /** * hrtimer_init_on_stack - initialize a timer in stack memory * @timer: The timer to be initialized -- cgit v1.2.3 From 444cb7db4c9f9b5d96be17c38b3e989df7bfabd5 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:21 +0100 Subject: hrtimers: Introduce hrtimer_setup_on_stack() To initialize hrtimer on stack, hrtimer_init_on_stack() needs to be called and also hrtimer::function must be set. This is error-prone and awkward to use. Introduce hrtimer_setup_on_stack() which does both of these things, so that users of hrtimer can be simplified. The new setup function also has a sanity check for the provided function pointer. If NULL, a warning is emitted and a dummy callback installed. hrtimer_init_on_stack() will be removed as soon as all of its users have been converted to the new function. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/4b05e2ab3a82c517adf67fabc0f0cd8fe118b97c.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 3 +++ kernel/time/hrtimer.c | 19 +++++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index bcc0715c59a8..2da513f8d66a 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -232,6 +232,9 @@ extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); +extern void hrtimer_setup_on_stack(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode); extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index a5ef67edcda9..daee4e27f839 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1646,6 +1646,25 @@ void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); +/** + * hrtimer_setup_on_stack - initialize a timer on stack memory + * @timer: The timer to be initialized + * @function: the callback function + * @clock_id: The clock to be used + * @mode: The timer mode + * + * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack + * memory. + */ +void hrtimer_setup_on_stack(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *), + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_init_on_stack(timer, clock_id, mode); + __hrtimer_setup(timer, function, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); + /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated -- cgit v1.2.3 From c9bd83abfeb9a9b103e689b251ccff7a01be8366 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:22 +0100 Subject: hrtimers: Introduce hrtimer_setup_sleeper_on_stack() The hrtimer_init*() API is replaced by hrtimer_setup*() variants to initialize the timer including the callback function at once. hrtimer_init_sleeper_on_stack() does not need user to setup the callback function separately, so a new variant would not be strictly necessary. Nonetheless, to keep the naming convention consistent, introduce hrtimer_setup_sleeper_on_stack(). hrtimer_init_on_stack() will be removed once all users are converted. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/7b5e18e6dd0ace9eaa211201528cb9dc23752454.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 2 ++ kernel/time/hrtimer.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2da513f8d66a..48872a2b4071 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -238,6 +238,8 @@ extern void hrtimer_setup_on_stack(struct hrtimer *timer, extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); +extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, + enum hrtimer_mode mode); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS extern void destroy_hrtimer_on_stack(struct hrtimer *timer); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index daee4e27f839..1d1f5c03673c 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2065,6 +2065,20 @@ void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, } EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); +/** + * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory + * @sl: sleeper to be initialized + * @clock_id: the clock to be used + * @mode: timer mode abs/rel + */ +void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, + clockid_t clock_id, enum hrtimer_mode mode) +{ + debug_init_on_stack(&sl->timer, clock_id, mode); + __hrtimer_init_sleeper(sl, clock_id, mode); +} +EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); + int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { -- cgit v1.2.3 From 8f02e3563bb5824eb01c94f2c75f1dcee2d05625 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:23 +0100 Subject: hrtimers: Introduce hrtimer_update_function() Some users of hrtimer need to change the callback function after the initial setup. They write to hrtimer::function directly. That's not safe under all circumstances as the write is lockless and a concurrent timer expiry might end up using the wrong function pointer. Introduce hrtimer_update_function(), which also performs runtime checks whether it is safe to modify the callback. This allows to make hrtimer::function private once all users are converted. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/20a937b0ae09ad54b5b6d86eabead7c570f1b72e.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 48872a2b4071..6e026730e803 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -327,6 +327,28 @@ static inline int hrtimer_callback_running(struct hrtimer *timer) return timer->base->running == timer; } +/** + * hrtimer_update_function - Update the timer's callback function + * @timer: Timer to update + * @function: New callback function + * + * Only safe to call if the timer is not enqueued. Can be called in the callback function if the + * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED). + */ +static inline void hrtimer_update_function(struct hrtimer *timer, + enum hrtimer_restart (*function)(struct hrtimer *)) +{ + guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); + + if (WARN_ON_ONCE(hrtimer_is_queued(timer))) + return; + + if (WARN_ON_ONCE(!function)) + return; + + timer->function = function; +} + /* Forward a hrtimer so it expires after now: */ extern u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval); -- cgit v1.2.3 From 211647e5121e0e0da974bf69a8eb7c9fe57fa3bd Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:28 +0100 Subject: wait: Switch to use hrtimer_setup_sleeper_on_stack() hrtimer_setup_sleeper_on_stack() replaces hrtimer_init_sleeper_on_stack() to keep the naming convention consistent. Convert the usage site over to it. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/fc91182375df81120a88dbe0263267e24d1bf19e.1730386209.git.namcao@linutronix.de --- include/linux/wait.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/wait.h b/include/linux/wait.h index 8aa3372f21a0..643b7c7bf376 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -541,8 +541,8 @@ do { \ int __ret = 0; \ struct hrtimer_sleeper __t; \ \ - hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ - HRTIMER_MODE_REL); \ + hrtimer_setup_sleeper_on_stack(&__t, CLOCK_MONOTONIC, \ + HRTIMER_MODE_REL); \ if ((timeout) != KTIME_MAX) { \ hrtimer_set_expires_range_ns(&__t.timer, timeout, \ current->timer_slack_ns); \ -- cgit v1.2.3 From f3bef7aaa6c807b78e8fc6929c3226d3038fe505 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:29 +0100 Subject: hrtimers: Delete hrtimer_init_sleeper_on_stack() hrtimer_init_sleeper_on_stack() is now unused. Delete it. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/52549846635c0b3a2abf82101f539efdabcd9778.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 3 --- kernel/time/hrtimer.c | 14 -------------- 2 files changed, 17 deletions(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 6e026730e803..4e4f04b3c0c2 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -235,9 +235,6 @@ extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, extern void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); -extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, - enum hrtimer_mode mode); extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 69430467a17d..376b8182b72e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2051,20 +2051,6 @@ static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, sl->task = current; } -/** - * hrtimer_init_sleeper_on_stack - initialize a sleeper in stack memory - * @sl: sleeper to be initialized - * @clock_id: the clock to be used - * @mode: timer mode abs/rel - */ -void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, - clockid_t clock_id, enum hrtimer_mode mode) -{ - debug_init_on_stack(&sl->timer, clock_id, mode); - __hrtimer_init_sleeper(sl, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); - /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized -- cgit v1.2.3 From 3c2fb0152175f9f596b40763cdc1378297da60af Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 31 Oct 2024 16:14:33 +0100 Subject: hrtimers: Delete hrtimer_init_on_stack() hrtimer_init_on_stack() is now unused. Delete it. Signed-off-by: Nam Cao Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/all/510ce0d2944c4a382ea51e51d03dcfb73ba0f4f7.1730386209.git.namcao@linutronix.de --- include/linux/hrtimer.h | 2 -- kernel/time/hrtimer.c | 17 ----------------- 2 files changed, 19 deletions(-) (limited to 'include') diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 4e4f04b3c0c2..7ef5f7ef31a9 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -230,8 +230,6 @@ extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, enum hrtimer_mode mode); extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); -extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, - enum hrtimer_mode mode); extern void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 376b8182b72e..55e9ffbcd49a 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1629,23 +1629,6 @@ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struc } EXPORT_SYMBOL_GPL(hrtimer_setup); -/** - * hrtimer_init_on_stack - initialize a timer in stack memory - * @timer: The timer to be initialized - * @clock_id: The clock to be used - * @mode: The timer mode - * - * Similar to hrtimer_init(), except that this one must be used if struct hrtimer is in stack - * memory. - */ -void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t clock_id, - enum hrtimer_mode mode) -{ - debug_init_on_stack(timer, clock_id, mode); - __hrtimer_init(timer, clock_id, mode); -} -EXPORT_SYMBOL_GPL(hrtimer_init_on_stack); - /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized -- cgit v1.2.3 From 1d58f7f3a1373734b2e86a246edcf1cd39359f3e Mon Sep 17 00:00:00 2001 From: "Dr. David Alan Gilbert" Date: Fri, 25 Oct 2024 21:31:01 +0100 Subject: clocksource/drivers/dw_apb: Remove unused dw_apb_clockevent functions dw_apb_clockevent_pause(), dw_apb_clockevent_resume() and dw_apb_clockevent_stop() have been unused since 2021's commit 1b79fc4f2bfd ("x86/apb_timer: Remove driver for deprecated platform") Remove them. (Some of the other clockevent functions are still called by dw_apb_timer_of.c so I guess it is still in use?) Signed-off-by: Dr. David Alan Gilbert Link: https://lore.kernel.org/r/20241025203101.241709-1-linux@treblig.org Signed-off-by: Daniel Lezcano --- drivers/clocksource/dw_apb_timer.c | 39 -------------------------------------- include/linux/dw_apb_timer.h | 3 --- 2 files changed, 42 deletions(-) (limited to 'include') diff --git a/drivers/clocksource/dw_apb_timer.c b/drivers/clocksource/dw_apb_timer.c index f5f24a95ee82..3a55ae5fe225 100644 --- a/drivers/clocksource/dw_apb_timer.c +++ b/drivers/clocksource/dw_apb_timer.c @@ -68,25 +68,6 @@ static inline void apbt_writel_relaxed(struct dw_apb_timer *timer, u32 val, writel_relaxed(val, timer->base + offs); } -static void apbt_disable_int(struct dw_apb_timer *timer) -{ - u32 ctrl = apbt_readl(timer, APBTMR_N_CONTROL); - - ctrl |= APBTMR_CONTROL_INT; - apbt_writel(timer, ctrl, APBTMR_N_CONTROL); -} - -/** - * dw_apb_clockevent_pause() - stop the clock_event_device from running - * - * @dw_ced: The APB clock to stop generating events. - */ -void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced) -{ - disable_irq(dw_ced->timer.irq); - apbt_disable_int(&dw_ced->timer); -} - static void apbt_eoi(struct dw_apb_timer *timer) { apbt_readl_relaxed(timer, APBTMR_N_EOI); @@ -284,26 +265,6 @@ dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, return dw_ced; } -/** - * dw_apb_clockevent_resume() - resume a clock that has been paused. - * - * @dw_ced: The APB clock to resume. - */ -void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced) -{ - enable_irq(dw_ced->timer.irq); -} - -/** - * dw_apb_clockevent_stop() - stop the clock_event_device and release the IRQ. - * - * @dw_ced: The APB clock to stop generating the events. - */ -void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced) -{ - free_irq(dw_ced->timer.irq, &dw_ced->ced); -} - /** * dw_apb_clockevent_register() - register the clock with the generic layer * diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h index 82ebf9223948..f8811c46b89e 100644 --- a/include/linux/dw_apb_timer.h +++ b/include/linux/dw_apb_timer.h @@ -34,9 +34,6 @@ struct dw_apb_clocksource { }; void dw_apb_clockevent_register(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced); -void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced); struct dw_apb_clock_event_device * dw_apb_clockevent_init(int cpu, const char *name, unsigned rating, -- cgit v1.2.3