From 4450dc0ae2c18a0ac6dce560215c7a1fa12122b5 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 5 Apr 2018 17:26:58 +0200 Subject: clockevents: Fix kernel messages split across multiple lines Convert the clockevents driver from old-style printk() to pr_info() and pr_cont(), to fix split kernel messages like below: Clockevents: could not switch to one-shot mode: dummy_timer is not functional. Signed-off-by: Geert Uytterhoeven Signed-off-by: Thomas Gleixner Cc: Frederic Weisbecker Link: https://lkml.kernel.org/r/1522942018-14471-1-git-send-email-geert%2Brenesas@glider.be --- kernel/time/tick-oneshot.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index c1f518e7aa80..6fe615d57ebb 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -82,16 +82,15 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT) || !tick_device_is_functional(dev)) { - printk(KERN_INFO "Clockevents: " - "could not switch to one-shot mode:"); + pr_info("Clockevents: could not switch to one-shot mode:"); if (!dev) { - printk(" no tick device\n"); + pr_cont(" no tick device\n"); } else { if (!tick_device_is_functional(dev)) - printk(" %s is not functional.\n", dev->name); + pr_cont(" %s is not functional.\n", dev->name); else - printk(" %s does not support one-shot mode.\n", - dev->name); + pr_cont(" %s does not support one-shot mode.\n", + dev->name); } return -EINVAL; } -- cgit v1.2.1 From e142aa09ed88be98395dde7acb96fb2263566b68 Mon Sep 17 00:00:00 2001 From: Baolin Wang Date: Fri, 13 Apr 2018 13:27:58 +0800 Subject: timekeeping: Remove __current_kernel_time() The __current_kernel_time() function based on 'struct timespec' is no longer recommended for new code, and the only user of this function has been replaced by commit 6909e29fdefb ("kdb: use __ktime_get_real_seconds instead of __current_kernel_time"). Remove the obsolete interface. Signed-off-by: Baolin Wang Signed-off-by: Thomas Gleixner Cc: arnd@arndb.de Cc: sboyd@kernel.org Cc: broonie@kernel.org Cc: john.stultz@linaro.org Link: https://lkml.kernel.org/r/1a9dbea7ee2cda7efe9ed330874075cf17fdbff6.1523596316.git.baolin.wang@linaro.org --- kernel/time/timekeeping.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ca90219a1e73..dcf7f20fcd12 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2139,13 +2139,6 @@ unsigned long get_seconds(void) } EXPORT_SYMBOL(get_seconds); -struct timespec __current_kernel_time(void) -{ - struct timekeeper *tk = &tk_core.timekeeper; - - return timespec64_to_timespec(tk_xtime(tk)); -} - struct timespec64 current_kernel_time64(void) { struct timekeeper *tk = &tk_core.timekeeper; -- cgit v1.2.1 From c3bca5d450b620dd3d36e14b5e1f43639fd47d6b Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Tue, 17 Apr 2018 14:57:42 -0700 Subject: posix-cpu-timers: Ensure set_process_cpu_timer is always evaluated Commit a9445e47d897 ("posix-cpu-timers: Make set_process_cpu_timer() more robust") moved the check into the 'if' statement. Unfortunately, it did so on the right side of an && which means that it may get short circuited and never evaluated. This is easily reproduced with: $ cat loop.c void main() { struct rlimit res; /* set the CPU time limit */ getrlimit(RLIMIT_CPU,&res); res.rlim_cur = 2; res.rlim_max = 2; setrlimit(RLIMIT_CPU,&res); while (1); } Which will hang forever instead of being killed. Fix this by pulling the evaluation out of the if statement but checking the return value instead. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1568337 Fixes: a9445e47d897 ("posix-cpu-timers: Make set_process_cpu_timer() more robust") Signed-off-by: Laura Abbott Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Cc: "Max R . P . Grossmann" Cc: John Stultz Link: https://lkml.kernel.org/r/20180417215742.2521-1-labbott@redhat.com --- kernel/time/posix-cpu-timers.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/time') diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 2541bd89f20e..5a6251ac6f7a 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1205,10 +1205,12 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, u64 *newval, u64 *oldval) { u64 now; + int ret; WARN_ON_ONCE(clock_idx == CPUCLOCK_SCHED); + ret = cpu_timer_sample_group(clock_idx, tsk, &now); - if (oldval && cpu_timer_sample_group(clock_idx, tsk, &now) != -EINVAL) { + if (oldval && ret != -EINVAL) { /* * We are setting itimer. The *oldval is absolute and we update * it to be relative, *newval argument is relative and we update -- cgit v1.2.1 From 1f71addd34f4c442bec7d7c749acc1beb58126f2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 24 Apr 2018 21:22:18 +0200 Subject: tick/sched: Do not mess with an enqueued hrtimer Kaike reported that in tests rdma hrtimers occasionaly stopped working. He did great debugging, which provided enough context to decode the problem. CPU 3 CPU 2 idle start sched_timer expires = 712171000000 queue->next = sched_timer start rdmavt timer. expires = 712172915662 lock(baseof(CPU3)) tick_nohz_stop_tick() tick = 716767000000 timerqueue_add(tmr) hrtimer_set_expires(sched_timer, tick); sched_timer->expires = 716767000000 <---- FAIL if (tmr->expires < queue->next->expires) hrtimer_start(sched_timer) queue->next = tmr; lock(baseof(CPU3)) unlock(baseof(CPU3)) timerqueue_remove() timerqueue_add() ts->sched_timer is queued and queue->next is pointing to it, but then ts->sched_timer.expires is modified. This not only corrupts the ordering of the timerqueue RB tree, it also makes CPU2 see the new expiry time of timerqueue->next->expires when checking whether timerqueue->next needs to be updated. So CPU2 sees that the rdma timer is earlier than timerqueue->next and sets the rdma timer as new next. Depending on whether it had also seen the new time at RB tree enqueue, it might have queued the rdma timer at the wrong place and then after removing the sched_timer the RB tree is completely hosed. The problem was introduced with a commit which tried to solve inconsistency between the hrtimer in the tick_sched data and the underlying hardware clockevent. It split out hrtimer_set_expires() to store the new tick time in both the NOHZ and the NOHZ + HIGHRES case, but missed the fact that in the NOHZ + HIGHRES case the hrtimer might still be queued. Use hrtimer_start(timer, tick...) for the NOHZ + HIGHRES case which sets timer->expires after canceling the timer and move the hrtimer_set_expires() invocation into the NOHZ only code path which is not affected as it merily uses the hrtimer as next event storage so code pathes can be shared with the NOHZ + HIGHRES case. Fixes: d4af6d933ccf ("nohz: Fix spurious warning when hrtimer and clockevent get out of sync") Reported-by: "Wan Kaike" Signed-off-by: Thomas Gleixner Acked-by: Frederic Weisbecker Cc: "Marciniszyn Mike" Cc: Anna-Maria Gleixner Cc: linux-rdma@vger.kernel.org Cc: "Dalessandro Dennis" Cc: "Fleck John" Cc: stable@vger.kernel.org Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: "Weiny Ira" Cc: "linux-rdma@vger.kernel.org" Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804241637390.1679@nanos.tec.linutronix.de Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1804242119210.1597@nanos.tec.linutronix.de --- kernel/time/tick-sched.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 646645e981f9..d31bec177fa5 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -804,12 +804,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) return; } - hrtimer_set_expires(&ts->sched_timer, tick); - - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); - else + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + } else { + hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); + } } static void tick_nohz_retain_tick(struct tick_sched *ts) -- cgit v1.2.1 From a3ed0e4393d6885b4af7ce84b437dc696490a530 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 25 Apr 2018 15:33:38 +0200 Subject: Revert: Unify CLOCK_MONOTONIC and CLOCK_BOOTTIME Revert commits 92af4dcb4e1c ("tracing: Unify the "boot" and "mono" tracing clocks") 127bfa5f4342 ("hrtimer: Unify MONOTONIC and BOOTTIME clock behavior") 7250a4047aa6 ("posix-timers: Unify MONOTONIC and BOOTTIME clock behavior") d6c7270e913d ("timekeeping: Remove boot time specific code") f2d6fdbfd238 ("Input: Evdev - unify MONOTONIC and BOOTTIME clock behavior") d6ed449afdb3 ("timekeeping: Make the MONOTONIC clock behave like the BOOTTIME clock") 72199320d49d ("timekeeping: Add the new CLOCK_MONOTONIC_ACTIVE clock") As stated in the pull request for the unification of CLOCK_MONOTONIC and CLOCK_BOOTTIME, it was clear that we might have to revert the change. As reported by several folks systemd and other applications rely on the documented behaviour of CLOCK_MONOTONIC on Linux and break with the above changes. After resume daemons time out and other timeout related issues are observed. Rafael compiled this list: * systemd kills daemons on resume, after >WatchdogSec seconds of suspending (Genki Sky). [Verified that that's because systemd uses CLOCK_MONOTONIC and expects it to not include the suspend time.] * systemd-journald misbehaves after resume: systemd-journald[7266]: File /var/log/journal/016627c3c4784cd4812d4b7e96a34226/system.journal corrupted or uncleanly shut down, renaming and replacing. (Mike Galbraith). * NetworkManager reports "networking disabled" and networking is broken after resume 50% of the time (Pavel). [May be because of systemd.] * MATE desktop dims the display and starts the screensaver right after system resume (Pavel). * Full system hang during resume (me). [May be due to systemd or NM or both.] That happens on debian and open suse systems. It's sad, that these problems were neither catched in -next nor by those folks who expressed interest in this change. Reported-by: Rafael J. Wysocki Reported-by: Genki Sky , Reported-by: Pavel Machek Signed-off-by: Thomas Gleixner Cc: Dmitry Torokhov Cc: John Stultz Cc: Jonathan Corbet Cc: Kevin Easton Cc: Linus Torvalds Cc: Mark Salyzyn Cc: Michael Kerrisk Cc: Peter Zijlstra Cc: Petr Mladek Cc: Prarit Bhargava Cc: Sergey Senozhatsky Cc: Steven Rostedt --- kernel/time/hrtimer.c | 16 ++++++++-- kernel/time/posix-stubs.c | 2 -- kernel/time/posix-timers.c | 26 +++++++++------ kernel/time/tick-common.c | 15 --------- kernel/time/tick-internal.h | 6 ---- kernel/time/tick-sched.c | 9 ------ kernel/time/timekeeping.c | 78 +++++++++++++++++++++------------------------ kernel/time/timekeeping.h | 1 + 8 files changed, 69 insertions(+), 84 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index eda1210ce50f..14e858753d76 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -90,6 +90,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, @@ -105,6 +110,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME_SOFT, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, @@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, - [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; @@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, - offs_real, offs_tai); + offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; + base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index e0dbae98db9d..69a937c3cd81 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) case CLOCK_BOOTTIME: get_monotonic_boottime64(tp); break; - case CLOCK_MONOTONIC_ACTIVE: - ktime_get_active_ts64(tp); default: return -EINVAL; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b6899b5060bd..10b7186d0638 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + get_monotonic_boottime64(tp); return 0; } -static int posix_get_monotonic_active(clockid_t which_clock, - struct timespec64 *tp) +static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - ktime_get_active_ts64(tp); + timekeeping_clocktai64(tp); return 0; } @@ -1317,9 +1316,19 @@ static const struct k_clock clock_tai = { .timer_arm = common_hrtimer_arm, }; -static const struct k_clock clock_monotonic_active = { +static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_active, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { @@ -1330,11 +1339,10 @@ static const struct k_clock * const posix_clocks[] = { [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, - [CLOCK_BOOTTIME] = &clock_monotonic, + [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, - [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active, }; static const struct k_clock *clockid_to_kclock(const clockid_t id) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 099572ca4a8f..49edc1c4f3e6 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -419,19 +419,6 @@ void tick_suspend_local(void) clockevents_shutdown(td->evtdev); } -static void tick_forward_next_period(void) -{ - ktime_t delta, now = ktime_get(); - u64 n; - - delta = ktime_sub(now, tick_next_period); - n = ktime_divns(delta, tick_period); - tick_next_period += n * tick_period; - if (tick_next_period < now) - tick_next_period += tick_period; - tick_sched_forward_next_period(); -} - /** * tick_resume_local - Resume the local tick device * @@ -444,8 +431,6 @@ void tick_resume_local(void) struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool broadcast = tick_resume_check_broadcast(); - tick_forward_next_period(); - clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 21efab7485ca..e277284c2831 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) -extern void tick_sched_forward_next_period(void); -#else -static inline void tick_sched_forward_next_period(void) { } -#endif - /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index d31bec177fa5..da9455a6b42b 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -51,15 +51,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) */ static ktime_t last_jiffies_update; -/* - * Called after resume. Make sure that jiffies are not fast forwarded due to - * clock monotonic being forwarded by the suspended time. - */ -void tick_sched_forward_next_period(void) -{ - last_jiffies_update = tick_next_period; -} - /* * Must be called with interrupts disabled ! */ diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcf7f20fcd12..49cbceef5deb 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Update both bases so mono and raw stay coupled. */ - tk->tkr_mono.base += delta; - tk->tkr_raw.base += delta; - - /* Accumulate time spent in suspend */ - tk->time_suspended += delta; + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /* @@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); +/** + * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. + * + * To keep it NMI safe since we're accessing from tracing, we're not using a + * separate timekeeper with updates to monotonic clock and boot offset + * protected with seqlocks. This has the following minor side effects: + * + * (1) Its possible that a timestamp be taken after the boot offset is updated + * but before the timekeeper is updated. If this happens, the new boot offset + * is added to the old timekeeping making the clock appear to update slightly + * earlier: + * CPU 0 CPU 1 + * timekeeping_inject_sleeptime64() + * __timekeeping_inject_sleeptime(tk, delta); + * timestamp(); + * timekeeping_update(tk, TK_CLEAR_NTP...); + * + * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be + * partially updated. Since the tk->offs_boot update is a rare event, this + * should be a rare occurrence which postprocessing should be able to handle. + */ +u64 notrace ktime_get_boot_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); +} +EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); + + /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ @@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; @@ -860,39 +886,6 @@ void ktime_get_ts64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts64); -/** - * ktime_get_active_ts64 - Get the active non-suspended monotonic clock - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime clock and - * the wall_to_monotonic offset, subtracts the accumulated suspend time and - * stores the result in normalized timespec64 format in the variable - * pointed to by @ts. - */ -void ktime_get_active_ts64(struct timespec64 *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 tomono, tsusp; - u64 nsec, nssusp; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr_mono); - tomono = tk->wall_to_monotonic; - nssusp = tk->time_suspended; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec64_add_ns(ts, nsec + tomono.tv_nsec); - tsusp = ns_to_timespec64(nssusp); - *ts = timespec64_sub(*ts, tsusp); -} - /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * @@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, return; } tk_xtime_add(tk, delta); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -2125,7 +2119,7 @@ out: void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended); + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } @@ -2188,6 +2182,7 @@ void do_timer(unsigned long ticks) * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the @@ -2197,7 +2192,7 @@ void do_timer(unsigned long ticks) * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, - ktime_t *offs_tai) + ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; @@ -2214,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 79b67f5e0343..7a9b4eb7a1d5 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -6,6 +6,7 @@ */ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, + ktime_t *offs_boot, ktime_t *offs_tai); extern int timekeeping_valid_for_hres(void); -- cgit v1.2.1 From 2aae7bcfa4104b770e6f612356adb8d66c6144d6 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 23 Apr 2018 17:28:55 +0200 Subject: clocksource: Allow clocksource_mark_unstable() on unregistered clocksources Because of how the code flips between tsc-early and tsc clocksources it might need to mark one or both unstable. The current code in mark_tsc_unstable() only worked because previously it registered the tsc clocksource once and then never touched it. Since it now unregisters the tsc-early clocksource, it needs to know if a clocksource got unregistered and the current cs->mult test doesn't work for that. Instead use list_empty(&cs->list) to test for registration. Furthermore, since clocksource_mark_unstable() needs to place the cs on the wd_list, it links the cs->list and cs->wd_list serialization. It must not see a clocsource registered (!empty cs->list) but already past dequeue_watchdog(). So place {en,de}queue{,_watchdog}() under the same lock. Provided cs->list is initialized to empty, this then allows us to unconditionally use clocksource_mark_unstable(), regardless of the registration state. Fixes: aa83c45762a2 ("x86/tsc: Introduce early tsc clocksource") Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Rafael J. Wysocki Tested-by: Diego Viola Cc: len.brown@intel.com Cc: rjw@rjwysocki.net Cc: diego.viola@gmail.com Cc: rui.zhang@intel.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180502135312.GS12217@hirez.programming.kicks-ass.net --- kernel/time/clocksource.c | 50 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 34 insertions(+), 16 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 0e974cface0b..c3d2b94723dc 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -119,6 +119,16 @@ static DEFINE_SPINLOCK(watchdog_lock); static int watchdog_running; static atomic_t watchdog_reset_pending; +static void inline clocksource_watchdog_lock(unsigned long *flags) +{ + spin_lock_irqsave(&watchdog_lock, *flags); +} + +static void inline clocksource_watchdog_unlock(unsigned long *flags) +{ + spin_unlock_irqrestore(&watchdog_lock, *flags); +} + static int clocksource_watchdog_kthread(void *data); static void __clocksource_change_rating(struct clocksource *cs, int rating); @@ -142,6 +152,9 @@ static void __clocksource_unstable(struct clocksource *cs) cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; + if (list_empty(&cs->list)) + return; + if (cs->mark_unstable) cs->mark_unstable(cs); @@ -164,7 +177,7 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_lock_irqsave(&watchdog_lock, flags); if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { - if (list_empty(&cs->wd_list)) + if (!list_empty(&cs->list) && list_empty(&cs->wd_list)) list_add(&cs->wd_list, &watchdog_list); __clocksource_unstable(cs); } @@ -319,9 +332,6 @@ static void clocksource_resume_watchdog(void) static void clocksource_enqueue_watchdog(struct clocksource *cs) { - unsigned long flags; - - spin_lock_irqsave(&watchdog_lock, flags); if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a clocksource to be watched. */ list_add(&cs->wd_list, &watchdog_list); @@ -331,7 +341,6 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; } - spin_unlock_irqrestore(&watchdog_lock, flags); } static void clocksource_select_watchdog(bool fallback) @@ -373,9 +382,6 @@ static void clocksource_select_watchdog(bool fallback) static void clocksource_dequeue_watchdog(struct clocksource *cs) { - unsigned long flags; - - spin_lock_irqsave(&watchdog_lock, flags); if (cs != watchdog) { if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a watched clocksource. */ @@ -384,21 +390,19 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs) clocksource_stop_watchdog(); } } - spin_unlock_irqrestore(&watchdog_lock, flags); } static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; - LIST_HEAD(unstable); int select = 0; spin_lock_irqsave(&watchdog_lock, flags); list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); - list_add(&cs->wd_list, &unstable); + __clocksource_change_rating(cs, 0); select = 1; } if (cs->flags & CLOCK_SOURCE_RESELECT) { @@ -410,11 +414,6 @@ static int __clocksource_watchdog_kthread(void) clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); - /* Needs to be done outside of watchdog lock */ - list_for_each_entry_safe(cs, tmp, &unstable, wd_list) { - list_del_init(&cs->wd_list); - __clocksource_change_rating(cs, 0); - } return select; } @@ -447,6 +446,9 @@ static inline int __clocksource_watchdog_kthread(void) { return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } void clocksource_mark_unstable(struct clocksource *cs) { } +static void inline clocksource_watchdog_lock(unsigned long *flags) { } +static void inline clocksource_watchdog_unlock(unsigned long *flags) { } + #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ /** @@ -779,14 +781,19 @@ EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); */ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) { + unsigned long flags; /* Initialize mult/shift and max_idle_ns */ __clocksource_update_freq_scale(cs, scale, freq); /* Add clocksource to the clocksource list */ mutex_lock(&clocksource_mutex); + + clocksource_watchdog_lock(&flags); clocksource_enqueue(cs); clocksource_enqueue_watchdog(cs); + clocksource_watchdog_unlock(&flags); + clocksource_select(); clocksource_select_watchdog(false); mutex_unlock(&clocksource_mutex); @@ -808,8 +815,13 @@ static void __clocksource_change_rating(struct clocksource *cs, int 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); mutex_unlock(&clocksource_mutex); @@ -821,6 +833,8 @@ EXPORT_SYMBOL(clocksource_change_rating); */ static int clocksource_unbind(struct clocksource *cs) { + unsigned long flags; + if (clocksource_is_watchdog(cs)) { /* Select and try to install a replacement watchdog. */ clocksource_select_watchdog(true); @@ -834,8 +848,12 @@ static int clocksource_unbind(struct clocksource *cs) if (curr_clocksource == cs) return -EBUSY; } + + clocksource_watchdog_lock(&flags); clocksource_dequeue_watchdog(cs); list_del_init(&cs->list); + clocksource_watchdog_unlock(&flags); + return 0; } -- cgit v1.2.1 From 5b9e886a4af97574ca3ce1147f35545da0e7afc7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Apr 2018 12:00:11 +0200 Subject: clocksource: Initialize cs->wd_list A number of places relies on list_empty(&cs->wd_list), however the list_head does not get initialized. Do so upon registration, such that thereafter it is possible to rely on list_empty() correctly reflecting the list membership status. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Tested-by: Diego Viola Reviewed-by: Rafael J. Wysocki Cc: stable@vger.kernel.org Cc: len.brown@intel.com Cc: rjw@rjwysocki.net Cc: rui.zhang@intel.com Link: https://lkml.kernel.org/r/20180430100344.472662715@infradead.org --- kernel/time/clocksource.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/time') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c3d2b94723dc..935f39eb8aac 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -332,6 +332,8 @@ static void clocksource_resume_watchdog(void) static void clocksource_enqueue_watchdog(struct clocksource *cs) { + INIT_LIST_HEAD(&cs->wd_list); + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { /* cs is a clocksource to be watched. */ list_add(&cs->wd_list, &watchdog_list); -- cgit v1.2.1 From cd2af07d823e5287cd6c91d54337348c2a873462 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Apr 2018 12:00:13 +0200 Subject: clocksource: Consistent de-rate when marking unstable When a registered clocksource gets marked unstable the watchdog_kthread will de-rate and re-select the clocksource. Ensure it also de-rates when getting called on an unregistered clocksource. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Rafael J. Wysocki Cc: len.brown@intel.com Cc: rjw@rjwysocki.net Cc: diego.viola@gmail.com Cc: rui.zhang@intel.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180430100344.594904898@infradead.org --- kernel/time/clocksource.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'kernel/time') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 935f39eb8aac..605656df16c4 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -152,12 +152,19 @@ static void __clocksource_unstable(struct clocksource *cs) cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; - if (list_empty(&cs->list)) + /* + * If the clocksource is registered clocksource_watchdog_kthread() will + * re-rate and re-select. + */ + if (list_empty(&cs->list)) { + cs->rating = 0; return; + } if (cs->mark_unstable) cs->mark_unstable(cs); + /* kick clocksource_watchdog_kthread() */ if (finished_booting) schedule_work(&watchdog_work); } -- cgit v1.2.1 From 7dba33c6346c337aac3f7cd188137d4a6d3d1f3a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 30 Apr 2018 12:00:14 +0200 Subject: clocksource: Rework stale comment AFAICS the hotplug code no longer uses this function. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Reviewed-by: Rafael J. Wysocki Cc: len.brown@intel.com Cc: rjw@rjwysocki.net Cc: diego.viola@gmail.com Cc: rui.zhang@intel.com Link: https://lkml.kernel.org/r/20180430100344.656525644@infradead.org --- kernel/time/clocksource.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 605656df16c4..84f37420fcf5 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -173,10 +173,8 @@ static void __clocksource_unstable(struct clocksource *cs) * clocksource_mark_unstable - mark clocksource unstable via watchdog * @cs: clocksource to be marked unstable * - * This function is called instead of clocksource_change_rating from - * cpu hotplug code to avoid a deadlock between the clocksource mutex - * and the cpu hotplug mutex. It defers the update of the clocksource - * to the watchdog thread. + * This function is called by the x86 TSC code to mark clocksources as unstable; + * it defers demotion and re-selection to a kthread. */ void clocksource_mark_unstable(struct clocksource *cs) { -- cgit v1.2.1