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 ++++ 1 file changed, 4 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); /* -- 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