From ceea5e3771ed2378668455fa21861bead7504df5 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 8 Jun 2017 16:44:20 -0700 Subject: time: Fix clock->read(clock) race around clocksource changes In tests, which excercise switching of clocksources, a NULL pointer dereference can be observed on AMR64 platforms in the clocksource read() function: u64 clocksource_mmio_readl_down(struct clocksource *c) { return ~(u64)readl_relaxed(to_mmio_clksrc(c)->reg) & c->mask; } This is called from the core timekeeping code via: cycle_now = tkr->read(tkr->clock); tkr->read is the cached tkr->clock->read() function pointer. When the clocksource is changed then tkr->clock and tkr->read are updated sequentially. The code above results in a sequential load operation of tkr->read and tkr->clock as well. If the store to tkr->clock hits between the loads of tkr->read and tkr->clock, then the old read() function is called with the new clock pointer. As a consequence the read() function dereferences a different data structure and the resulting 'reg' pointer can point anywhere including NULL. This problem was introduced when the timekeeping code was switched over to use struct tk_read_base. Before that, it was theoretically possible as well when the compiler decided to reload clock in the code sequence: now = tk->clock->read(tk->clock); Add a helper function which avoids the issue by reading tk_read_base->clock once into a local variable clk and then issue the read function via clk->read(clk). This guarantees that the read() function always gets the proper clocksource pointer handed in. Since there is now no use for the tkr.read pointer, this patch also removes it, and to address stopping the fast timekeeper during suspend/resume, it introduces a dummy clocksource to use rather then just a dummy read function. Signed-off-by: John Stultz Acked-by: Ingo Molnar Cc: Prarit Bhargava Cc: Richard Cochran Cc: Stephen Boyd Cc: stable Cc: Miroslav Lichvar Cc: Daniel Mentz Link: http://lkml.kernel.org/r/1496965462-20003-2-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 52 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 36 insertions(+), 16 deletions(-) (limited to 'kernel/time/timekeeping.c') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 9652bc57fd09..eff94cb8e89e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -118,6 +118,26 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) tk->offs_boot = ktime_add(tk->offs_boot, delta); } +/* + * tk_clock_read - atomic clocksource read() helper + * + * This helper is necessary to use in the read paths because, while the + * seqlock ensures we don't return a bad value while structures are updated, + * it doesn't protect from potential crashes. There is the possibility that + * the tkr's clocksource may change between the read reference, and the + * clock reference passed to the read function. This can cause crashes if + * the wrong clocksource is passed to the wrong read function. + * This isn't necessary to use when holding the timekeeper_lock or doing + * a read of the fast-timekeeper tkrs (which is protected by its own locking + * and update logic). + */ +static inline u64 tk_clock_read(struct tk_read_base *tkr) +{ + struct clocksource *clock = READ_ONCE(tkr->clock); + + return clock->read(clock); +} + #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ @@ -175,7 +195,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) */ do { seq = read_seqcount_begin(&tk_core.seq); - now = tkr->read(tkr->clock); + now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; @@ -209,7 +229,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr) u64 cycle_now, delta; /* read clocksource */ - cycle_now = tkr->read(tkr->clock); + cycle_now = tk_clock_read(tkr); /* calculate the delta since the last update_wall_time */ delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask); @@ -238,12 +258,10 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; - tk->tkr_mono.read = clock->read; tk->tkr_mono.mask = clock->mask; - tk->tkr_mono.cycle_last = tk->tkr_mono.read(clock); + tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; - tk->tkr_raw.read = clock->read; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; @@ -404,7 +422,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) now += timekeeping_delta_to_ns(tkr, clocksource_delta( - tkr->read(tkr->clock), + tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); } while (read_seqcount_retry(&tkf->seq, seq)); @@ -461,6 +479,10 @@ static u64 dummy_clock_read(struct clocksource *cs) return cycles_at_suspend; } +static struct clocksource dummy_clock = { + .read = dummy_clock_read, +}; + /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. @@ -477,13 +499,13 @@ static void halt_fast_timekeeper(struct timekeeper *tk) struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - cycles_at_suspend = tkr->read(tkr->clock); - tkr_dummy.read = dummy_clock_read; + cycles_at_suspend = tk_clock_read(tkr); + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); - tkr_dummy.read = dummy_clock_read; + tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } @@ -649,11 +671,10 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) */ static void timekeeping_forward_now(struct timekeeper *tk) { - struct clocksource *clock = tk->tkr_mono.clock; u64 cycle_now, delta; u64 nsec; - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -929,8 +950,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) do { seq = read_seqcount_begin(&tk_core.seq); - - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, @@ -1108,7 +1128,7 @@ int get_device_system_crosststamp(int (*get_time_fn) * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ - now = tk->tkr_mono.read(tk->tkr_mono.clock); + now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!cycle_between(interval_start, cycles, now)) { clock_was_set_seq = tk->clock_was_set_seq; @@ -1629,7 +1649,7 @@ void timekeeping_resume(void) * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ - cycle_now = tk->tkr_mono.read(clock); + cycle_now = tk_clock_read(&tk->tkr_mono); if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) && cycle_now > tk->tkr_mono.cycle_last) { u64 nsec, cyc_delta; @@ -2030,7 +2050,7 @@ void update_wall_time(void) #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET offset = real_tk->cycle_interval; #else - offset = clocksource_delta(tk->tkr_mono.read(tk->tkr_mono.clock), + offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); #endif -- cgit v1.2.3 From 3d88d56c5873f6eebe23e05c3da701960146b801 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Thu, 8 Jun 2017 16:44:21 -0700 Subject: time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting Due to how the MONOTONIC_RAW accumulation logic was handled, there is the potential for a 1ns discontinuity when we do accumulations. This small discontinuity has for the most part gone un-noticed, but since ARM64 enabled CLOCK_MONOTONIC_RAW in their vDSO clock_gettime implementation, we've seen failures with the inconsistency-check test in kselftest. This patch addresses the issue by using the same sub-ns accumulation handling that CLOCK_MONOTONIC uses, which avoids the issue for in-kernel users. Since the ARM64 vDSO implementation has its own clock_gettime calculation logic, this patch reduces the frequency of errors, but failures are still seen. The ARM64 vDSO will need to be updated to include the sub-nanosecond xtime_nsec values in its calculation for this issue to be completely fixed. Signed-off-by: John Stultz Tested-by: Daniel Mentz Cc: Prarit Bhargava Cc: Kevin Brodsky Cc: Richard Cochran Cc: Stephen Boyd Cc: Will Deacon Cc: "stable #4 . 8+" Cc: Miroslav Lichvar Link: http://lkml.kernel.org/r/1496965462-20003-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/timekeeper_internal.h | 4 ++-- kernel/time/timekeeping.c | 19 ++++++++++--------- 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'kernel/time/timekeeping.c') diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e9834ada4d0c..f7043ccca81c 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -57,7 +57,7 @@ struct tk_read_base { * interval. * @xtime_remainder: Shifted nano seconds left over when rounding * @cycle_interval - * @raw_interval: Raw nano seconds accumulated per NTP 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 @@ -99,7 +99,7 @@ struct timekeeper { u64 cycle_interval; u64 xtime_interval; s64 xtime_remainder; - u32 raw_interval; + 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 diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index eff94cb8e89e..b602c48cb841 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -280,7 +280,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; - tk->raw_interval = (interval * clock->mult) >> clock->shift; + tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { @@ -1996,7 +1996,7 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; - u64 raw_nsecs; + u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) @@ -2011,14 +2011,15 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = (u64)tk->raw_interval << shift; - raw_nsecs += tk->raw_time.tv_nsec; - if (raw_nsecs >= NSEC_PER_SEC) { - u64 raw_secs = raw_nsecs; - raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); - tk->raw_time.tv_sec += raw_secs; + tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; + snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; + while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { + tk->tkr_raw.xtime_nsec -= snsec_per_sec; + tk->raw_time.tv_sec++; } - tk->raw_time.tv_nsec = raw_nsecs; + tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift; + tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift; /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; -- cgit v1.2.3