diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-14 09:27:40 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-14 09:27:40 -0700 |
commit | 2d9db778ddca079228ef10e60bceea06b34b0eaa (patch) | |
tree | 141de3fcc8b32a0d495b36f461b5875681f5011e /kernel/time/timekeeping.c | |
parent | 61deafa9ecf3f6d00c570774b0b38f439be543ac (diff) | |
parent | a3825a7691585485e960cec04ce6667d176b7c67 (diff) |
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/timekeeping.c')
-rw-r--r-- | kernel/time/timekeeping.c | 96 |
1 files changed, 49 insertions, 47 deletions
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index b58dffc58a8f..4e18db1819f8 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -237,7 +237,9 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) } } -static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); + +static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; @@ -264,34 +266,23 @@ static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ - if (unlikely((~delta & mask) < (mask >> 3))) { + if (unlikely((~delta & mask) < (mask >> 3))) tk->underflow_seen = 1; - delta = 0; - } - /* Cap delta value to the max_cycles values to avoid mult overflows */ - if (unlikely(delta > max)) { + /* Check for multiplication overflows */ + if (unlikely(delta > max)) tk->overflow_seen = 1; - delta = tkr->clock->max_cycles; - } - return delta; + /* timekeeping_cycles_to_ns() handles both under and overflow */ + return timekeeping_cycles_to_ns(tkr, now); } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } -static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr) +static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { - u64 cycle_now, delta; - - /* read clocksource */ - 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); - - return delta; + BUG(); } #endif @@ -370,32 +361,46 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) } /* Timekeeper helper functions. */ +static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) +{ + return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); +} -static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta) +static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { - u64 nsec; + /* Calculate the delta since the last update_wall_time() */ + u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; - nsec = delta * tkr->mult + tkr->xtime_nsec; - nsec >>= tkr->shift; + /* + * This detects both negative motion and the case where the delta + * overflows the multiplication with tkr->mult. + */ + if (unlikely(delta > tkr->clock->max_cycles)) { + /* + * Handle clocksource inconsistency between CPUs to prevent + * time from going backwards by checking for the MSB of the + * mask being set in the delta. + */ + if (delta & ~(mask >> 1)) + return tkr->xtime_nsec >> tkr->shift; + + return delta_to_ns_safe(tkr, delta); + } - return nsec; + return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } -static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) +static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) { - u64 delta; - - delta = timekeeping_get_delta(tkr); - return timekeeping_delta_to_ns(tkr, delta); + return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } -static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) +static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { - u64 delta; + if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) + return timekeeping_debug_get_ns(tkr); - /* calculate the delta since the last update_wall_time */ - delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); - return timekeeping_delta_to_ns(tkr, delta); + return __timekeeping_get_ns(tkr); } /** @@ -431,14 +436,6 @@ static void update_fast_timekeeper(const struct tk_read_base *tkr, memcpy(base + 1, base, sizeof(*base)); } -static __always_inline u64 fast_tk_get_delta_ns(struct tk_read_base *tkr) -{ - u64 delta, cycles = tk_clock_read(tkr); - - delta = clocksource_delta(cycles, tkr->cycle_last, tkr->mask); - return timekeeping_delta_to_ns(tkr, delta); -} - static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; @@ -449,7 +446,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); - now += fast_tk_get_delta_ns(tkr); + now += __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; @@ -565,7 +562,7 @@ static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); - delta = fast_tk_get_delta_ns(tkr); + delta = __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) @@ -800,10 +797,15 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; - tk->tkr_mono.xtime_nsec += delta * tk->tkr_mono.mult; - tk->tkr_raw.xtime_nsec += delta * tk->tkr_raw.mult; + while (delta > 0) { + u64 max = tk->tkr_mono.clock->max_cycles; + u64 incr = delta < max ? delta : max; - tk_normalize_xtime(tk); + tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; + tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; + tk_normalize_xtime(tk); + delta -= incr; + } } /** |