From 38bf985b05625df3fbbc1dbf543bdd2da447c2af Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 27 May 2015 16:44:48 -0700 Subject: [PATCH 1/7] timer_list: Add the base offset so remaining nsecs are accurate for non monotonic timers I noticed for non-monotonic timers in timer_list, some of the output looked a little confusing. For example: #1: <0000000000000000>, posix_timer_fn, S:01, hrtimer_start_range_ns, leap-a-day/2360 # expires at 1434412800000000000-1434412800000000000 nsecs [in 1434410725062375469 to 1434410725062375469 nsecs] You'll note the relative time till the expiration "[in xxx to yyy nsecs]" is incorrect. This is because its printing the delta between CLOCK_MONOTONIC time to the CLOCK_REALTIME expiration. This patch fixes this issue by adding the clock offset to the "now" time which we use to calculate the delta. Cc: Prarit Bhargava Cc: Daniel Bristot de Oliveira Cc: Richard Cochran Cc: Jan Kara Cc: Jiri Bohac Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Shuah Khan Signed-off-by: John Stultz --- kernel/time/timer_list.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index a4536e1e3e2a..129c96033e46 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -137,7 +137,7 @@ print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) (unsigned long long) ktime_to_ns(base->offset)); #endif SEQ_printf(m, "active timers:\n"); - print_active_timers(m, base, now); + print_active_timers(m, base, now + ktime_to_ns(base->offset)); } static void print_cpu(struct seq_file *m, int cpu, u64 now) From de4a95faf173be1e798c37ca486dfcb234a0941b Mon Sep 17 00:00:00 2001 From: Karsten Blees Date: Thu, 25 Jun 2015 14:13:55 +0200 Subject: [PATCH 2/7] time: Fix nanosecond file time rounding in timespec_trunc() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit timespec_trunc() avoids rounding if granularity <= nanoseconds-per-jiffie (or TICK_NSEC). This optimization assumes that: 1. current_kernel_time().tv_nsec is already rounded to TICK_NSEC (i.e. with HZ=1000 you'd get 1000000, 2000000, 3000000... but never 1000001). This is no longer true (probably since hrtimers introduced in 2.6.16). 2. TICK_NSEC is evenly divisible by all possible granularities. This may be true for HZ=100, 250, 1000, but obviously not for HZ=300 / TICK_NSEC=3333333 (introduced in 2.6.20). Thus, sub-second portions of in-core file times are not rounded to on-disk granularity. I.e. file times may change when the inode is re-read from disk or when the file system is remounted. This affects all file systems with file time granularities > 1 ns and < 1s, e.g. CEPH (1000 ns), UDF (1000 ns), CIFS (100 ns), NTFS (100 ns) and FUSE (configurable from user mode via struct fuse_init_out.time_gran). Steps to reproduce with e.g. UDF: $ dd if=/dev/zero of=udfdisk count=10000 && mkudffs udfdisk $ mkdir udf && mount udfdisk udf $ touch udf/test && stat -c %y udf/test 2015-06-09 10:22:56.130006767 +0200 $ umount udf && mount udfdisk udf $ stat -c %y udf/test 2015-06-09 10:22:56.130006000 +0200 Remounting truncates the mtime to 1 µs. Fix the rounding in timespec_trunc() and update the documentation. timespec_trunc() is exclusively used to calculate inode's [acm]time (mostly via current_fs_time()), and always with super_block.s_time_gran as second argument. So this can safely be changed without side effects. Note: This does _not_ fix the issue for FAT's 2 second mtime resolution, as super_block.s_time_gran isn't prepared to handle different ctime / mtime / atime resolutions nor resolutions > 1 second. Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Karsten Blees Signed-off-by: John Stultz --- kernel/time/time.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/kernel/time/time.c b/kernel/time/time.c index 85d5bb1d67eb..34dbd4209e4a 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -287,26 +287,20 @@ EXPORT_SYMBOL(jiffies_to_usecs); * @t: Timespec * @gran: Granularity in ns. * - * Truncate a timespec to a granularity. gran must be smaller than a second. - * Always rounds down. - * - * This function should be only used for timestamps returned by - * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because - * it doesn't handle the better resolution of the latter. + * Truncate a timespec to a granularity. Always rounds down. gran must + * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec timespec_trunc(struct timespec t, unsigned gran) { - /* - * Division is pretty slow so avoid it for common cases. - * Currently current_kernel_time() never returns better than - * jiffies resolution. Exploit that. - */ - if (gran <= jiffies_to_usecs(1) * 1000) { + /* Avoid division in the common cases 1 ns and 1 s. */ + if (gran == 1) { /* nothing */ - } else if (gran == 1000000000) { + } else if (gran == NSEC_PER_SEC) { t.tv_nsec = 0; - } else { + } else if (gran > 1 && gran < NSEC_PER_SEC) { t.tv_nsec -= t.tv_nsec % gran; + } else { + WARN(1, "illegal file time granularity: %u", gran); } return t; } From e1d7ba8735551ed79c7a0463a042353574b96da3 Mon Sep 17 00:00:00 2001 From: Wang YanQing Date: Tue, 23 Jun 2015 18:38:54 +0800 Subject: [PATCH 3/7] time: Always make sure wall_to_monotonic isn't positive Two issues were found on an IMX6 development board without an enabled RTC device(resulting in the boot time and monotonic time being initialized to 0). Issue 1:exportfs -a generate: "exportfs: /opt/nfs/arm does not support NFS export" Issue 2:cat /proc/stat: "btime 4294967236" The same issues can be reproduced on x86 after running the following code: int main(void) { struct timeval val; int ret; val.tv_sec = 0; val.tv_usec = 0; ret = settimeofday(&val, NULL); return 0; } Two issues are different symptoms of same problem: The reason is a positive wall_to_monotonic pushes boot time back to the time before Epoch, and getboottime will return negative value. In symptom 1: negative boot time cause get_expiry() to overflow time_t when input expire time is 2147483647, then cache_flush() always clears entries just added in ip_map_parse. In symptom 2: show_stat() uses "unsigned long" to print negative btime value returned by getboottime. This patch fix the problem by prohibiting time from being set to a value which would cause a negative boot time. As a result one can't set the CLOCK_REALTIME time prior to (1970 + system uptime). Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Wang YanQing [jstultz: reworded commit message] Signed-off-by: John Stultz --- kernel/time/timekeeping.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index bca3667a2de1..4cdb771913c8 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -911,6 +911,7 @@ int do_settimeofday64(const struct timespec64 *ts) struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; + int ret = 0; if (!timespec64_valid_strict(ts)) return -EINVAL; @@ -924,10 +925,15 @@ int do_settimeofday64(const struct timespec64 *ts) ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { + ret = -EINVAL; + goto out; + } + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); - +out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); @@ -936,7 +942,7 @@ int do_settimeofday64(const struct timespec64 *ts) /* signal hrtimers about time change */ clock_was_set(); - return 0; + return ret; } EXPORT_SYMBOL(do_settimeofday64); @@ -965,7 +971,8 @@ int timekeeping_inject_offset(struct timespec *ts) /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), ts64); - if (!timespec64_valid_strict(&tmp)) { + if (timespec64_compare(&tk->wall_to_monotonic, &ts64) > 0 || + !timespec64_valid_strict(&tmp)) { ret = -EINVAL; goto error; } From 7494e9eedee2121305a48af4fbbcedb69a2c2b93 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Sun, 26 Jul 2015 18:45:39 +0800 Subject: [PATCH 4/7] time: Add the common weak version of update_persistent_clock() The weak update_persistent_clock64() calls update_persistent_clock(), if the architecture defines an update_persistent_clock64() to replace and remove its update_persistent_clock() version, when building the kernel the linker will throw an undefined symbol error, that is, any arch that switches to update_persistent_clock64() will have this issue. To solve the issue, we add the common weak update_persistent_clock(). Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Arnd Bergmann Signed-off-by: Xunlei Pang Signed-off-by: John Stultz --- kernel/time/ntp.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index fb4d98c7fd43..df68cb875248 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -487,6 +487,11 @@ int second_overflow(unsigned long secs) } #ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock(struct timespec now) +{ + return -ENODEV; +} + int __weak update_persistent_clock64(struct timespec64 now64) { struct timespec now; From 19a46fe57a005a884ccb38419071f772ac2fca2b Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 29 Jul 2015 19:58:15 +0800 Subject: [PATCH 5/7] time: Introduce struct itimerspec64 The struct itimerspec is not year 2038 safe on 32bit systems due to the limitation of the struct timespec members. Introduce itimerspec64 which uses struct timespec64 instead and provide conversion functions. Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Baolin Wang Signed-off-by: John Stultz --- include/linux/time64.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) diff --git a/include/linux/time64.h b/include/linux/time64.h index 77b5df2acd2a..367d5af899e8 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -12,11 +12,18 @@ typedef __s64 time64_t; */ #if __BITS_PER_LONG == 64 # define timespec64 timespec +#define itimerspec64 itimerspec #else struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; + +struct itimerspec64 { + struct timespec64 it_interval; + struct timespec64 it_value; +}; + #endif /* Parameters used to convert the timespec values: */ @@ -45,6 +52,16 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ts; } +static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) +{ + return *its64; +} + +static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) +{ + return *its; +} + # define timespec64_equal timespec_equal # define timespec64_compare timespec_compare # define set_normalized_timespec64 set_normalized_timespec @@ -77,6 +94,24 @@ static inline struct timespec64 timespec_to_timespec64(const struct timespec ts) return ret; } +static inline struct itimerspec itimerspec64_to_itimerspec(struct itimerspec64 *its64) +{ + struct itimerspec ret; + + ret.it_interval = timespec64_to_timespec(its64->it_interval); + ret.it_value = timespec64_to_timespec(its64->it_value); + return ret; +} + +static inline struct itimerspec64 itimerspec_to_itimerspec64(struct itimerspec *its) +{ + struct itimerspec64 ret; + + ret.it_interval = timespec_to_timespec64(its->it_interval); + ret.it_value = timespec_to_timespec64(its->it_value); + return ret; +} + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { From 8758a240e2d74c5932ab51a73377e6507b7fd441 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 29 Jul 2015 20:09:43 +0800 Subject: [PATCH 6/7] time: Introduce current_kernel_time64() The current_kernel_time() is not year 2038 safe on 32bit systems since it returns a timespec value. Introduce current_kernel_time64() which returns a timespec64 value. Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Baolin Wang Signed-off-by: John Stultz --- include/linux/timekeeping.h | 9 ++++++++- kernel/time/timekeeping.c | 6 +++--- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 3aa72e648650..657ea03fff40 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -18,10 +18,17 @@ extern int do_sys_settimeofday(const struct timespec *tv, * Kernel time accessors */ unsigned long get_seconds(void); -struct timespec current_kernel_time(void); +struct timespec64 current_kernel_time64(void); /* does not take xtime_lock */ struct timespec __current_kernel_time(void); +static inline struct timespec current_kernel_time(void) +{ + struct timespec64 now = current_kernel_time64(); + + return timespec64_to_timespec(now); +} + /* * timespec based interfaces */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 4cdb771913c8..f6ee2e6b6f5d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1881,7 +1881,7 @@ struct timespec __current_kernel_time(void) return timespec64_to_timespec(tk_xtime(tk)); } -struct timespec current_kernel_time(void) +struct timespec64 current_kernel_time64(void) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now; @@ -1893,9 +1893,9 @@ struct timespec current_kernel_time(void) now = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); - return timespec64_to_timespec(now); + return now; } -EXPORT_SYMBOL(current_kernel_time); +EXPORT_SYMBOL(current_kernel_time64); struct timespec64 get_monotonic_coarse64(void) { From 9ca308506062fc4a4ee8ca7ad2f71033c831c2fb Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Wed, 29 Jul 2015 20:18:31 +0800 Subject: [PATCH 7/7] time: Introduce timespec64_to_jiffies()/jiffies_to_timespec64() The conversion between struct timespec and jiffies is not year 2038 safe on 32bit systems. Introduce timespec64_to_jiffies() and jiffies_to_timespec64() functions which use struct timespec64 to make it ready for 2038 issue. Cc: Prarit Bhargava Cc: Richard Cochran Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Baolin Wang Signed-off-by: John Stultz --- include/linux/jiffies.h | 22 +++++++++++++++++++--- kernel/time/time.c | 21 +++++++++++++-------- 2 files changed, 32 insertions(+), 11 deletions(-) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 535fd3bb1ba8..bf96d9f27bd0 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -416,9 +416,25 @@ static inline unsigned long usecs_to_jiffies(const unsigned int u) } } -extern unsigned long timespec_to_jiffies(const struct timespec *value); -extern void jiffies_to_timespec(const unsigned long jiffies, - struct timespec *value); +extern unsigned long timespec64_to_jiffies(const struct timespec64 *value); +extern void jiffies_to_timespec64(const unsigned long jiffies, + struct timespec64 *value); +static inline unsigned long timespec_to_jiffies(const struct timespec *value) +{ + struct timespec64 ts = timespec_to_timespec64(*value); + + return timespec64_to_jiffies(&ts); +} + +static inline void jiffies_to_timespec(const unsigned long jiffies, + struct timespec *value) +{ + struct timespec64 ts; + + jiffies_to_timespec64(jiffies, &ts); + *value = timespec64_to_timespec(ts); +} + extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); diff --git a/kernel/time/time.c b/kernel/time/time.c index 34dbd4209e4a..f18ab105ed87 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -540,7 +540,7 @@ EXPORT_SYMBOL(__usecs_to_jiffies); * value to a scaled second value. */ static unsigned long -__timespec_to_jiffies(unsigned long sec, long nsec) +__timespec64_to_jiffies(u64 sec, long nsec) { nsec = nsec + TICK_NSEC - 1; @@ -548,22 +548,27 @@ __timespec_to_jiffies(unsigned long sec, long nsec) sec = MAX_SEC_IN_JIFFIES; nsec = 0; } - return (((u64)sec * SEC_CONVERSION) + + return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); + return __timespec64_to_jiffies((u64)sec, nsec); } -EXPORT_SYMBOL(timespec_to_jiffies); +unsigned long +timespec64_to_jiffies(const struct timespec64 *value) +{ + return __timespec64_to_jiffies(value->tv_sec, value->tv_nsec); +} +EXPORT_SYMBOL(timespec64_to_jiffies); void -jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) +jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with @@ -574,7 +579,7 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) NSEC_PER_SEC, &rem); value->tv_nsec = rem; } -EXPORT_SYMBOL(jiffies_to_timespec); +EXPORT_SYMBOL(jiffies_to_timespec64); /* * We could use a similar algorithm to timespec_to_jiffies (with a