From b22da3d8526a935aa31e086e63f60ff3246cb61c Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Sat, 09 Dec 2023 07:24:11 +0000 Subject: [PATCH] add stmac read mac form eeprom --- kernel/kernel/time/timekeeping.c | 216 ++++++++++++++++++++++++++++++++++++++--------------- 1 files changed, 154 insertions(+), 62 deletions(-) diff --git a/kernel/kernel/time/timekeeping.c b/kernel/kernel/time/timekeeping.c index 0343c5d..d9b48f7 100644 --- a/kernel/kernel/time/timekeeping.c +++ b/kernel/kernel/time/timekeeping.c @@ -1,13 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * linux/kernel/time/timekeeping.c - * - * Kernel timekeeping code and accessor functions - * - * This code was moved from linux/kernel/timer.c. - * Please see that file for copyright and history logs. - * + * Kernel timekeeping code and accessor functions. Based on code from + * timer.c, moved in commit 8524070b7982. */ - #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> @@ -22,10 +17,13 @@ #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> +#include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> +#include <linux/audit.h> +#include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" @@ -43,19 +41,23 @@ TK_ADV_FREQ }; +DEFINE_RAW_SPINLOCK(timekeeper_lock); + /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { - seqcount_t seq; + seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { - .seq = SEQCNT_ZERO(tk_core.seq), + .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; -static DEFINE_RAW_SPINLOCK(timekeeper_lock); static struct timekeeper shadow_timekeeper; + +/* flag for if timekeeping is suspended */ +int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper @@ -67,7 +69,7 @@ * See @update_fast_timekeeper() below. */ struct tk_fast { - seqcount_t seq; + seqcount_latch_t seq; struct tk_read_base base[2]; }; @@ -76,25 +78,41 @@ static u64 dummy_clock_read(struct clocksource *cs) { - return cycles_at_suspend; + if (timekeeping_suspended) + return cycles_at_suspend; + return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; +/* + * Boot time initialization which allows local_clock() to be utilized + * during early boot when clocksources are not available. local_clock() + * returns nanoseconds already so no conversion is required, hence mult=1 + * and shift=0. When the first proper clocksource is installed then + * the fast time keepers are updated with the correct values. + */ +#define FAST_TK_INIT \ + { \ + .clock = &dummy_clock, \ + .mask = CLOCKSOURCE_MASK(64), \ + .mult = 1, \ + .shift = 0, \ + } + static struct tk_fast tk_fast_mono ____cacheline_aligned = { - .base[0] = { .clock = &dummy_clock, }, - .base[1] = { .clock = &dummy_clock, }, + .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), + .base[0] = FAST_TK_INIT, + .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { - .base[0] = { .clock = &dummy_clock, }, - .base[1] = { .clock = &dummy_clock, }, + .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), + .base[0] = FAST_TK_INIT, + .base[1] = FAST_TK_INIT, }; - -/* flag for if timekeeping is suspended */ -int __read_mostly timekeeping_suspended; static inline void tk_normalize_xtime(struct timekeeper *tk) { @@ -161,7 +179,7 @@ * 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, + * seqcount 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 @@ -226,10 +244,10 @@ unsigned int seq; /* - * Since we're called holding a seqlock, the data may shift + * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the - * results away. So nest another seqlock here to atomically + * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { @@ -468,7 +486,7 @@ tk_clock_read(tkr), tkr->cycle_last, tkr->mask)); - } while (read_seqcount_retry(&tkf->seq, seq)); + } while (read_seqcount_latch_retry(&tkf->seq, seq)); return now; } @@ -490,7 +508,7 @@ * * 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: + * protected with seqcounts. 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 @@ -514,29 +532,29 @@ } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); - /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ -static __always_inline u64 __ktime_get_real_fast_ns(struct tk_fast *tkf) +static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; + u64 basem, baser, delta; unsigned int seq; - u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); - now = ktime_to_ns(tkr->base_real); + basem = ktime_to_ns(tkr->base); + baser = ktime_to_ns(tkr->base_real); - now += timekeeping_delta_to_ns(tkr, - clocksource_delta( - tk_clock_read(tkr), - tkr->cycle_last, - tkr->mask)); - } while (read_seqcount_retry(&tkf->seq, seq)); + delta = timekeeping_delta_to_ns(tkr, + clocksource_delta(tk_clock_read(tkr), + tkr->cycle_last, tkr->mask)); + } while (read_seqcount_latch_retry(&tkf->seq, seq)); - return now; + if (mono) + *mono = basem + delta; + return baser + delta; } /** @@ -544,9 +562,63 @@ */ u64 ktime_get_real_fast_ns(void) { - return __ktime_get_real_fast_ns(&tk_fast_mono); + return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); + +/** + * ktime_get_fast_timestamps: - NMI safe timestamps + * @snapshot: Pointer to timestamp storage + * + * Stores clock monotonic, boottime and realtime timestamps. + * + * Boot time is a racy access on 32bit systems if the sleep time injection + * happens late during resume and not in timekeeping_resume(). That could + * be avoided by expanding struct tk_read_base with boot offset for 32bit + * and adding more overhead to the update. As this is a hard to observe + * once per resume event which can be filtered with reasonable effort using + * the accurate mono/real timestamps, it's probably not worth the trouble. + * + * Aside of that it might be possible on 32 and 64 bit to observe the + * following when the sleep time injection happens late: + * + * CPU 0 CPU 1 + * timekeeping_resume() + * ktime_get_fast_timestamps() + * mono, real = __ktime_get_real_fast() + * inject_sleep_time() + * update boot offset + * boot = mono + bootoffset; + * + * That means that boot time already has the sleep time adjustment, but + * real time does not. On the next readout both are in sync again. + * + * Preventing this for 64bit is not really feasible without destroying the + * careful cache layout of the timekeeper because the sequence count and + * struct tk_read_base would then need two cache lines instead of one. + * + * Access to the time keeper clock source is disabled accross the innermost + * steps of suspend/resume. The accessors still work, but the timestamps + * are frozen until time keeping is resumed which happens very early. + * + * For regular suspend/resume there is no observable difference vs. sched + * clock, but it might affect some of the nasty low level debug printks. + * + * OTOH, access to sched clock is not guaranteed accross suspend/resume on + * all systems either so it depends on the hardware in use. + * + * If that turns out to be a real problem then this could be mitigated by + * using sched clock in a similar way as during early boot. But it's not as + * trivial as on early boot because it needs some careful protection + * against the clock monotonic timestamp jumping backwards on resume. + */ +void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); + snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); +} /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. @@ -730,7 +802,7 @@ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); @@ -840,7 +912,7 @@ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; - unsigned long seq; + unsigned int seq; ktime_t tconv; do { @@ -957,7 +1029,7 @@ * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ -time64_t __ktime_get_real_seconds(void) +noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; @@ -971,7 +1043,7 @@ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; @@ -1132,7 +1204,7 @@ ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; - unsigned long seq; + unsigned int seq; bool do_interp; int ret; @@ -1258,6 +1330,11 @@ /* signal hrtimers about time change */ clock_was_set(); + + if (!ret) { + audit_tk_injoffset(ts_delta); + add_device_randomness(ts, sizeof(*ts)); + } return ret; } @@ -1418,7 +1495,7 @@ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; do { @@ -1440,7 +1517,7 @@ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; int ret; do { @@ -1459,7 +1536,7 @@ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 ret; do { @@ -1473,7 +1550,7 @@ } /** - * read_persistent_clock - Return time from the persistent clock. + * read_persistent_clock64 - Return time from the persistent clock. * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. @@ -1481,18 +1558,10 @@ * * XXX - Do be sure to remove it once all arches implement it. */ -void __weak read_persistent_clock(struct timespec *ts) +void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; -} - -void __weak read_persistent_clock64(struct timespec64 *ts64) -{ - struct timespec ts; - - read_persistent_clock(&ts); - *ts64 = timespec_to_timespec64(ts); } /** @@ -2009,7 +2078,7 @@ * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into - * into a shifted interval nanoseconds. Allows for O(log) accumulation + * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. @@ -2167,7 +2236,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2181,7 +2250,7 @@ { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2201,7 +2270,7 @@ void do_timer(unsigned long ticks) { jiffies_64 += ticks; - calc_global_load(ticks); + calc_global_load(); } /** @@ -2251,7 +2320,7 @@ /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(const struct timex *txc) +static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2313,13 +2382,28 @@ return 0; } +/** + * random_get_entropy_fallback - Returns the raw clock source value, + * used by random.c for platforms with no valid random_get_entropy(). + */ +unsigned long random_get_entropy_fallback(void) +{ + struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; + struct clocksource *clock = READ_ONCE(tkr->clock); + + if (unlikely(timekeeping_suspended || !clock)) + return 0; + return clock->read(clock); +} +EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ -int do_adjtimex(struct timex *txc) +int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; + struct audit_ntp_data ad; unsigned long flags; struct timespec64 ts; s32 orig_tai, tai; @@ -2329,6 +2413,7 @@ ret = timekeeping_validate_timex(txc); if (ret) return ret; + add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; @@ -2339,15 +2424,20 @@ ret = timekeeping_inject_offset(&delta); if (ret) return ret; + + audit_tk_injoffset(delta); } + audit_ntp_init(&ad); + ktime_get_real_ts64(&ts); + add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; - ret = __do_adjtimex(txc, &ts, &tai); + ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); @@ -2358,6 +2448,8 @@ write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + audit_ntp_log(&ad); + /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) timekeeping_advance(TK_ADV_FREQ); -- Gitblit v1.6.2