diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-14 18:27:40 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-14 18:27:40 +0200 |
commit | 2d9db778ddca079228ef10e60bceea06b34b0eaa (patch) | |
tree | 141de3fcc8b32a0d495b36f461b5875681f5011e /kernel/time/clocksource.c | |
parent | Merge tag 'x86_apic_for_6.10' of git://git.kernel.org/pub/scm/linux/kernel/gi... (diff) | |
parent | Merge tag 'timers-v6.10-rc1' of https://git.linaro.org/people/daniel.lezcano/... (diff) | |
download | linux-2d9db778ddca079228ef10e60bceea06b34b0eaa.tar.xz linux-2d9db778ddca079228ef10e60bceea06b34b0eaa.zip |
Merge tag 'timers-core-2024-05-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timers and timekeeping updates from Thomas Gleixner:
"Core code:
- Make timekeeping and VDSO time readouts resilent against math
overflow:
In guest context the kernel is prone to math overflow when the host
defers the timer interrupt due to overload, malfunction or malice.
This can be mitigated by checking the clocksource delta for the
maximum deferrement which is readily available. If that value is
exceeded then the code uses a slowpath function which can handle
the multiplication overflow.
This functionality is enabled unconditionally in the kernel, but
made conditional in the VDSO code. The latter is conditional
because it allows architectures to optimize the check so it is not
causing performance regressions.
On X86 this is achieved by reworking the existing check for
negative TSC deltas as a negative delta obviously exceeds the
maximum deferrement when it is evaluated as an unsigned value. That
avoids two conditionals in the hotpath and allows to hide both the
negative delta and the large delta handling in the same slow path.
- Add an initial minimal ktime_t abstraction for Rust
- The usual boring cleanups and enhancements
Drivers:
- Boring updates to device trees and trivial enhancements in various
drivers"
* tag 'timers-core-2024-05-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
clocksource/drivers/arm_arch_timer: Mark hisi_161010101_oem_info const
clocksource/drivers/timer-ti-dm: Remove an unused field in struct dmtimer
clocksource/drivers/renesas-ostm: Avoid reprobe after successful early probe
clocksource/drivers/renesas-ostm: Allow OSTM driver to reprobe for RZ/V2H(P) SoC
dt-bindings: timer: renesas: ostm: Document Renesas RZ/V2H(P) SoC
rust: time: doc: Add missing C header links
clocksource: Make the int help prompt unit readable in ncurses
hrtimer: Rename __hrtimer_hres_active() to hrtimer_hres_active()
timerqueue: Remove never used function timerqueue_node_expires()
rust: time: Add Ktime
vdso: Fix powerpc build U64_MAX undeclared error
clockevents: Convert s[n]printf() to sysfs_emit()
clocksource: Convert s[n]printf() to sysfs_emit()
clocksource: Make watchdog and suspend-timing multiplication overflow safe
timekeeping: Let timekeeping_cycles_to_ns() handle both under and overflow
timekeeping: Make delta calculation overflow safe
timekeeping: Prepare timekeeping_cycles_to_ns() for overflow safety
timekeeping: Fold in timekeeping_delta_to_ns()
timekeeping: Consolidate timekeeping helpers
timekeeping: Refactor timekeeping helpers
...
Diffstat (limited to 'kernel/time/clocksource.c')
-rw-r--r-- | kernel/time/clocksource.c | 44 |
1 files changed, 21 insertions, 23 deletions
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index e5b260aa0e02..d25ba49e313c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -20,6 +20,16 @@ #include "tick-internal.h" #include "timekeeping_internal.h" +static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) +{ + u64 delta = clocksource_delta(end, start, cs->mask); + + if (likely(delta < cs->max_cycles)) + return clocksource_cyc2ns(delta, cs->mult, cs->shift); + + return mul_u64_u32_shr(delta, cs->mult, cs->shift); +} + /** * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks * @mult: pointer to mult variable @@ -222,8 +232,8 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { unsigned int nretries, max_retries; - u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; + u64 wd_end, wd_end2; max_retries = clocksource_get_max_watchdog_retry(); for (nretries = 0; nretries <= max_retries; nretries++) { @@ -234,9 +244,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_end2 = watchdog->read(watchdog); local_irq_enable(); - wd_delta = clocksource_delta(wd_end, *wdnow, watchdog->mask); - wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, - watchdog->shift); + wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end); if (wd_delay <= WATCHDOG_MAX_SKEW) { if (nretries > 1 || nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", @@ -254,8 +262,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, * report system busy, reinit the watchdog and skip the current * watchdog test. */ - wd_delta = clocksource_delta(wd_end2, wd_end, watchdog->mask); - wd_seq_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); + wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2); if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) goto skip_test; } @@ -366,8 +373,7 @@ void clocksource_verify_percpu(struct clocksource *cs) delta = (csnow_end - csnow_mid) & cs->mask; if (delta < 0) cpumask_set_cpu(cpu, &cpus_ahead); - delta = clocksource_delta(csnow_end, csnow_begin, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + cs_nsec = cycles_to_nsec_safe(cs, csnow_begin, csnow_end); if (cs_nsec > cs_nsec_max) cs_nsec_max = cs_nsec; if (cs_nsec < cs_nsec_min) @@ -398,8 +404,8 @@ static inline void clocksource_reset_watchdog(void) static void clocksource_watchdog(struct timer_list *unused) { - u64 csnow, wdnow, cslast, wdlast, delta; int64_t wd_nsec, cs_nsec, interval; + u64 csnow, wdnow, cslast, wdlast; int next_cpu, reset_pending; struct clocksource *cs; enum wd_read_status read_ret; @@ -456,12 +462,8 @@ static void clocksource_watchdog(struct timer_list *unused) continue; } - delta = clocksource_delta(wdnow, cs->wd_last, watchdog->mask); - wd_nsec = clocksource_cyc2ns(delta, watchdog->mult, - watchdog->shift); - - delta = clocksource_delta(csnow, cs->cs_last, cs->mask); - cs_nsec = clocksource_cyc2ns(delta, cs->mult, cs->shift); + wd_nsec = cycles_to_nsec_safe(watchdog, cs->wd_last, wdnow); + cs_nsec = cycles_to_nsec_safe(cs, cs->cs_last, csnow); wdlast = cs->wd_last; /* save these in case we print them */ cslast = cs->cs_last; cs->cs_last = csnow; @@ -832,7 +834,7 @@ void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles) */ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) { - u64 now, delta, nsec = 0; + u64 now, nsec = 0; if (!suspend_clocksource) return 0; @@ -847,12 +849,8 @@ u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now) else now = suspend_clocksource->read(suspend_clocksource); - if (now > suspend_start) { - delta = clocksource_delta(now, suspend_start, - suspend_clocksource->mask); - nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult, - suspend_clocksource->shift); - } + if (now > suspend_start) + nsec = cycles_to_nsec_safe(suspend_clocksource, suspend_start, now); /* * Disable the suspend timer to save power if current clocksource is @@ -1336,7 +1334,7 @@ static ssize_t current_clocksource_show(struct device *dev, ssize_t count = 0; mutex_lock(&clocksource_mutex); - count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); + count = sysfs_emit(buf, "%s\n", curr_clocksource->name); mutex_unlock(&clocksource_mutex); return count; |