Merge branch 'main' into zstd-linus

13 files changed, 297 insertions, 101 deletions

diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 04bfd62f5e5c..a41753be1a2b 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -73,6 +73,15 @@ config TIME_KUNIT_TEST
 
 	  If unsure, say N.
 
+config CONTEXT_TRACKING
+	bool
+
+config CONTEXT_TRACKING_IDLE
+	bool
+	select CONTEXT_TRACKING
+	help
+	  Tracks idle state on behalf of RCU.
+
 if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
@@ -111,7 +120,7 @@ config NO_HZ_FULL
 	# NO_HZ_COMMON dependency
 	# We need at least one periodic CPU for timekeeping
 	depends on SMP
-	depends on HAVE_CONTEXT_TRACKING
+	depends on HAVE_CONTEXT_TRACKING_USER
 	# VIRT_CPU_ACCOUNTING_GEN dependency
 	depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
 	select NO_HZ_COMMON
@@ -137,31 +146,37 @@ config NO_HZ_FULL
 
 endchoice
 
-config CONTEXT_TRACKING
-       bool
+config CONTEXT_TRACKING_USER
+	bool
+	depends on HAVE_CONTEXT_TRACKING_USER
+	select CONTEXT_TRACKING
+	help
+	  Track transitions between kernel and user on behalf of RCU and
+	  tickless cputime accounting. The former case relies on context
+	  tracking to enter/exit RCU extended quiescent states.
 
-config CONTEXT_TRACKING_FORCE
-	bool "Force context tracking"
-	depends on CONTEXT_TRACKING
+config CONTEXT_TRACKING_USER_FORCE
+	bool "Force user context tracking"
+	depends on CONTEXT_TRACKING_USER
 	default y if !NO_HZ_FULL
 	help
 	  The major pre-requirement for full dynticks to work is to
-	  support the context tracking subsystem. But there are also
+	  support the user context tracking subsystem. But there are also
 	  other dependencies to provide in order to make the full
 	  dynticks working.
 
 	  This option stands for testing when an arch implements the
-	  context tracking backend but doesn't yet fulfill all the
+	  user context tracking backend but doesn't yet fulfill all the
 	  requirements to make the full dynticks feature working.
 	  Without the full dynticks, there is no way to test the support
-	  for context tracking and the subsystems that rely on it: RCU
+	  for user context tracking and the subsystems that rely on it: RCU
 	  userspace extended quiescent state and tickless cputime
 	  accounting. This option copes with the absence of the full
-	  dynticks subsystem by forcing the context tracking on all
+	  dynticks subsystem by forcing the user context tracking on all
 	  CPUs in the system.
 
 	  Say Y only if you're working on the development of an
-	  architecture backend for the context tracking.
+	  architecture backend for the user context tracking.
 
 	  Say N otherwise, this option brings an overhead that you
 	  don't want in production.
@@ -181,5 +196,14 @@ config HIGH_RES_TIMERS
 	  hardware is not capable then this option only increases
 	  the size of the kernel image.
 
+config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+	int "Clocksource watchdog maximum allowable skew (in μs)"
+	depends on CLOCKSOURCE_WATCHDOG
+	range 50 1000
+	default 100
+	help
+	  Specify the maximum amount of allowable watchdog skew in
+	  microseconds before reporting the clocksource to be unstable.
+
 endmenu
 endif
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 003ccf338d20..5d85014d59b5 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -690,7 +690,7 @@ static ssize_t unbind_device_store(struct device *dev,
 {
 	char name[CS_NAME_LEN];
 	ssize_t ret = sysfs_get_uname(buf, name, count);
-	struct clock_event_device *ce;
+	struct clock_event_device *ce = NULL, *iter;
 
 	if (ret < 0)
 		return ret;
@@ -698,9 +698,10 @@ static ssize_t unbind_device_store(struct device *dev,
 	ret = -ENODEV;
 	mutex_lock(&clockevents_mutex);
 	raw_spin_lock_irq(&clockevents_lock);
-	list_for_each_entry(ce, &clockevent_devices, list) {
-		if (!strcmp(ce->name, name)) {
-			ret = __clockevents_try_unbind(ce, dev->id);
+	list_for_each_entry(iter, &clockevent_devices, list) {
+		if (!strcmp(iter->name, name)) {
+			ret = __clockevents_try_unbind(iter, dev->id);
+			ce = iter;
 			break;
 		}
 	}
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1cf73807b450..8058bec87ace 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -107,7 +107,13 @@ static u64 suspend_start;
  * This delay could be due to SMIs, NMIs, or to VCPU preemptions.  Used as
  * a lower bound for cs->uncertainty_margin values when registering clocks.
  */
-#define WATCHDOG_MAX_SKEW (100 * NSEC_PER_USEC)
+#ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#define MAX_SKEW_USEC	CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
+#else
+#define MAX_SKEW_USEC	100
+#endif
+
+#define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC)
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
@@ -304,7 +310,7 @@ static void clocksource_verify_choose_cpus(void)
 	 * CPUs that are currently online.
 	 */
 	for (i = 1; i < n; i++) {
-		cpu = prandom_u32() % nr_cpu_ids;
+		cpu = prandom_u32_max(nr_cpu_ids);
 		cpu = cpumask_next(cpu - 1, cpu_online_mask);
 		if (cpu >= nr_cpu_ids)
 			cpu = cpumask_first(cpu_online_mask);
@@ -337,7 +343,7 @@ void clocksource_verify_percpu(struct clocksource *cs)
 	cpus_read_lock();
 	preempt_disable();
 	clocksource_verify_choose_cpus();
-	if (cpumask_weight(&cpus_chosen) == 0) {
+	if (cpumask_empty(&cpus_chosen)) {
 		preempt_enable();
 		cpus_read_unlock();
 		pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 0ea8702eb516..3ae661ab6260 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2037,11 +2037,11 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 	struct restart_block *restart;
 
 	do {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
 		hrtimer_sleeper_start_expires(t, mode);
 
 		if (likely(t->task))
-			freezable_schedule();
+			schedule();
 
 		hrtimer_cancel(&t->timer);
 		mode = HRTIMER_MODE_ABS;
@@ -2311,6 +2311,7 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta,
 
 	return !t.task ? 0 : -EINTR;
 }
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock);
 
 /**
  * schedule_hrtimeout_range - sleep until timeout
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 96b4e7810426..cb925e8ef9a8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -15,6 +15,7 @@
 #include <linux/workqueue.h>
 #include <linux/compat.h>
 #include <linux/sched/deadline.h>
+#include <linux/task_work.h>
 
 #include "posix-timers.h"
 
@@ -34,14 +35,20 @@ void posix_cputimers_group_init(struct posix_cputimers *pct, u64 cpu_limit)
  * tsk->signal->posix_cputimers.bases[clock].nextevt expiration cache if
  * necessary. Needs siglock protection since other code may update the
  * expiration cache as well.
+ *
+ * Returns 0 on success, -ESRCH on failure.  Can fail if the task is exiting and
+ * we cannot lock_task_sighand.  Cannot fail if task is current.
  */
-void update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
+int update_rlimit_cpu(struct task_struct *task, unsigned long rlim_new)
 {
 	u64 nsecs = rlim_new * NSEC_PER_SEC;
+	unsigned long irq_fl;
 
-	spin_lock_irq(&task->sighand->siglock);
+	if (!lock_task_sighand(task, &irq_fl))
+		return -ESRCH;
 	set_process_cpu_timer(task, CPUCLOCK_PROF, &nsecs, NULL);
-	spin_unlock_irq(&task->sighand->siglock);
+	unlock_task_sighand(task, &irq_fl);
+	return 0;
 }
 
 /*
@@ -863,7 +870,7 @@ static inline void check_dl_overrun(struct task_struct *tsk)
 {
 	if (tsk->dl.dl_overrun) {
 		tsk->dl.dl_overrun = 0;
-		__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
+		send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
 	}
 }
 
@@ -877,7 +884,7 @@ static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
 			rt ? "RT" : "CPU", hard ? "hard" : "soft",
 			current->comm, task_pid_nr(current));
 	}
-	__group_send_sig_info(signo, SEND_SIG_PRIV, current);
+	send_signal_locked(signo, SEND_SIG_PRIV, current, PIDTYPE_TGID);
 	return true;
 }
 
@@ -951,7 +958,7 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it,
 		trace_itimer_expire(signo == SIGPROF ?
 				    ITIMER_PROF : ITIMER_VIRTUAL,
 				    task_tgid(tsk), cur_time);
-		__group_send_sig_info(signo, SEND_SIG_PRIV, tsk);
+		send_signal_locked(signo, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
 	}
 
 	if (it->expires && it->expires < *expires)
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index fcb3b21d8bdc..90ea5f373e50 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -70,7 +70,7 @@ SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock,
 	return do_sys_settimeofday64(&new_tp, NULL);
 }
 
-int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
+static int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 {
 	switch (which_clock) {
 	case CLOCK_REALTIME:
@@ -90,6 +90,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 
 	return 0;
 }
+
 SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock,
 		struct __kernel_timespec __user *, tp)
 {
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 1cd10b102c51..5dead89308b7 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -1051,15 +1051,24 @@ retry_delete:
 }
 
 /*
- * This is called by do_exit or de_thread, only when there are no more
- * references to the shared signal_struct.
+ * This is called by do_exit or de_thread, only when nobody else can
+ * modify the signal->posix_timers list. Yet we need sighand->siglock
+ * to prevent the race with /proc/pid/timers.
  */
-void exit_itimers(struct signal_struct *sig)
+void exit_itimers(struct task_struct *tsk)
 {
+	struct list_head timers;
 	struct k_itimer *tmr;
 
-	while (!list_empty(&sig->posix_timers)) {
-		tmr = list_entry(sig->posix_timers.next, struct k_itimer, list);
+	if (list_empty(&tsk->signal->posix_timers))
+		return;
+
+	spin_lock_irq(&tsk->sighand->siglock);
+	list_replace_init(&tsk->signal->posix_timers, &timers);
+	spin_unlock_irq(&tsk->sighand->siglock);
+
+	while (!list_empty(&timers)) {
+		tmr = list_first_entry(&timers, struct k_itimer, list);
 		itimer_delete(tmr);
 	}
 }
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index b1b9b12899f5..8464c5acc913 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -8,6 +8,7 @@
 #include <linux/jiffies.h>
 #include <linux/ktime.h>
 #include <linux/kernel.h>
+#include <linux/math.h>
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
@@ -199,15 +200,13 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 
 	r = rate;
 	if (r >= 4000000) {
-		r /= 1000000;
+		r = DIV_ROUND_CLOSEST(r, 1000000);
 		r_unit = 'M';
+	} else if (r >= 4000) {
+		r = DIV_ROUND_CLOSEST(r, 1000);
+		r_unit = 'k';
 	} else {
-		if (r >= 1000) {
-			r /= 1000;
-			r_unit = 'k';
-		} else {
-			r_unit = ' ';
-		}
+		r_unit = ' ';
 	}
 
 	/* Calculate the ns resolution of this counter */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 17a283ce2b20..b0e3c9205946 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -169,6 +169,8 @@ static ktime_t tick_init_jiffy_update(void)
 	return period;
 }
 
+#define MAX_STALLED_JIFFIES 5
+
 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 {
 	int cpu = smp_processor_id();
@@ -186,7 +188,7 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 */
 	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
 #ifdef CONFIG_NO_HZ_FULL
-		WARN_ON(tick_nohz_full_running);
+		WARN_ON_ONCE(tick_nohz_full_running);
 #endif
 		tick_do_timer_cpu = cpu;
 	}
@@ -196,6 +198,21 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	if (tick_do_timer_cpu == cpu)
 		tick_do_update_jiffies64(now);
 
+	/*
+	 * If jiffies update stalled for too long (timekeeper in stop_machine()
+	 * or VMEXIT'ed for several msecs), force an update.
+	 */
+	if (ts->last_tick_jiffies != jiffies) {
+		ts->stalled_jiffies = 0;
+		ts->last_tick_jiffies = READ_ONCE(jiffies);
+	} else {
+		if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
+			tick_do_update_jiffies64(now);
+			ts->stalled_jiffies = 0;
+			ts->last_tick_jiffies = READ_ONCE(jiffies);
+		}
+	}
+
 	if (ts->inidle)
 		ts->got_idle_tick = 1;
 }
@@ -509,7 +526,6 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 	cpumask_copy(tick_nohz_full_mask, cpumask);
 	tick_nohz_full_running = true;
 }
-EXPORT_SYMBOL_GPL(tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
@@ -554,7 +570,7 @@ void __init tick_nohz_init(void)
 	}
 
 	for_each_cpu(cpu, tick_nohz_full_mask)
-		context_tracking_cpu_set(cpu);
+		ct_cpu_track_user(cpu);
 
 	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
 					"kernel/nohz:predown", NULL,
@@ -768,7 +784,7 @@ static inline bool local_timer_softirq_pending(void)
 
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
-	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
+	u64 basemono, next_tick, delta, expires;
 	unsigned long basejiff;
 	unsigned int seq;
 
@@ -791,7 +807,7 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 	 * minimal delta which brings us back to this place
 	 * immediately. Lather, rinse and repeat...
 	 */
-	if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+	if (rcu_needs_cpu() || arch_needs_cpu() ||
 	    irq_work_needs_cpu() || local_timer_softirq_pending()) {
 		next_tick = basemono + TICK_NSEC;
 	} else {
@@ -802,10 +818,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 		 * disabled this also looks at the next expiring
 		 * hrtimer.
 		 */
-		next_tmr = get_next_timer_interrupt(basejiff, basemono);
-		ts->next_timer = next_tmr;
-		/* Take the next rcu event into account */
-		next_tick = next_rcu < next_tmr ? next_rcu : next_tmr;
+		next_tick = get_next_timer_interrupt(basejiff, basemono);
+		ts->next_timer = next_tick;
 	}
 
 	/*
@@ -913,6 +927,8 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	if (unlikely(expires == KTIME_MAX)) {
 		if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
 			hrtimer_cancel(&ts->sched_timer);
+		else
+			tick_program_event(KTIME_MAX, 1);
 		return;
 	}
 
@@ -984,6 +1000,45 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
 	__tick_nohz_full_update_tick(ts, ktime_get());
 }
 
+/*
+ * A pending softirq outside an IRQ (or softirq disabled section) context
+ * should be waiting for ksoftirqd to handle it. Therefore we shouldn't
+ * reach here due to the need_resched() early check in can_stop_idle_tick().
+ *
+ * However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the
+ * cpu_down() process, softirqs can still be raised while ksoftirqd is parked,
+ * triggering the below since wakep_softirqd() is ignored.
+ *
+ */
+static bool report_idle_softirq(void)
+{
+	static int ratelimit;
+	unsigned int pending = local_softirq_pending();
+
+	if (likely(!pending))
+		return false;
+
+	/* Some softirqs claim to be safe against hotplug and ksoftirqd parking */
+	if (!cpu_active(smp_processor_id())) {
+		pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK;
+		if (!pending)
+			return false;
+	}
+
+	if (ratelimit < 10)
+		return false;
+
+	/* On RT, softirqs handling may be waiting on some lock */
+	if (!local_bh_blocked())
+		return false;
+
+	pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
+		pending);
+	ratelimit++;
+
+	return true;
+}
+
 static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 {
 	/*
@@ -1010,17 +1065,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 	if (need_resched())
 		return false;
 
-	if (unlikely(local_softirq_pending())) {
-		static int ratelimit;
-
-		if (ratelimit < 10 && !local_bh_blocked() &&
-		    (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
-			pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
-				(unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
+	if (unlikely(report_idle_softirq()))
 		return false;
-	}
 
 	if (tick_nohz_full_enabled()) {
 		/*
@@ -1319,9 +1365,15 @@ static void tick_nohz_handler(struct clock_event_device *dev)
 	tick_sched_do_timer(ts, now);
 	tick_sched_handle(ts, regs);
 
-	/* No need to reprogram if we are running tickless  */
-	if (unlikely(ts->tick_stopped))
+	if (unlikely(ts->tick_stopped)) {
+		/*
+		 * The clockevent device is not reprogrammed, so change the
+		 * clock event device to ONESHOT_STOPPED to avoid spurious
+		 * interrupts on devices which might not be truly one shot.
+		 */
+		tick_program_event(KTIME_MAX, 1);
 		return;
+	}
 
 	hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
 	tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
@@ -1493,7 +1545,7 @@ void tick_cancel_sched_timer(int cpu)
 }
 #endif
 
-/**
+/*
  * Async notification about clocksource changes
  */
 void tick_clock_notify(void)
@@ -1514,7 +1566,7 @@ void tick_oneshot_notify(void)
 	set_bit(0, &ts->check_clocks);
 }
 
-/**
+/*
  * Check, if a change happened, which makes oneshot possible.
  *
  * Called cyclic from the hrtimer softirq (driven by the timer
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index d952ae393423..504649513399 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -49,6 +49,8 @@ enum tick_nohz_mode {
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
  * @next_timer:		Expiry time of next expiring timer for debugging purpose only
  * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
+ * @last_tick_jiffies:	Value of jiffies seen on last tick
+ * @stalled_jiffies:	Number of stalled jiffies detected across ticks
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;
@@ -77,6 +79,8 @@ struct tick_sched {
 	u64				next_timer;
 	ktime_t				idle_expires;
 	atomic_t			tick_dep_mask;
+	unsigned long			last_tick_jiffies;
+	unsigned int			stalled_jiffies;
 };
 
 extern struct tick_sched *tick_get_tick_sched(int cpu);
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 29923b20e0e4..526257b3727c 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -449,7 +449,7 @@ time64_t mktime64(const unsigned int year0, const unsigned int mon0,
 }
 EXPORT_SYMBOL(mktime64);
 
-struct __kernel_old_timeval ns_to_kernel_old_timeval(const s64 nsec)
+struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec)
 {
 	struct timespec64 ts = ns_to_timespec64(nsec);
 	struct __kernel_old_timeval tv;
@@ -503,7 +503,7 @@ EXPORT_SYMBOL(set_normalized_timespec64);
  *
  * Returns the timespec64 representation of the nsec parameter.
  */
-struct timespec64 ns_to_timespec64(const s64 nsec)
+struct timespec64 ns_to_timespec64(s64 nsec)
 {
 	struct timespec64 ts = { 0, 0 };
 	s32 rem;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index dcdcb85121e4..f72b9f1de178 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,11 +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"
@@ -429,6 +431,14 @@ 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;
@@ -439,12 +449,7 @@ 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 += timekeeping_delta_to_ns(tkr,
-				clocksource_delta(
-					tk_clock_read(tkr),
-					tkr->cycle_last,
-					tkr->mask));
+		now += fast_tk_get_delta_ns(tkr);
 	} while (read_seqcount_latch_retry(&tkf->seq, seq));
 
 	return now;
@@ -482,7 +487,7 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf)
  * of the following timestamps. Callers need to be aware of that and
  * deal with it.
  */
-u64 ktime_get_mono_fast_ns(void)
+u64 notrace ktime_get_mono_fast_ns(void)
 {
 	return __ktime_get_fast_ns(&tk_fast_mono);
 }
@@ -494,7 +499,7 @@ EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns);
  * Contrary to ktime_get_mono_fast_ns() this is always correct because the
  * conversion factor is not affected by NTP/PTP correction.
  */
-u64 ktime_get_raw_fast_ns(void)
+u64 notrace ktime_get_raw_fast_ns(void)
 {
 	return __ktime_get_fast_ns(&tk_fast_raw);
 }
@@ -528,10 +533,27 @@ 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));
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot)));
 }
 EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns);
 
+/**
+ * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock.
+ *
+ * The same limitations as described for ktime_get_boot_fast_ns() apply. The
+ * mono time and the TAI offset are not read atomically which may yield wrong
+ * readouts. However, an update of the TAI offset is an rare event e.g., caused
+ * by settime or adjtimex with an offset. The user of this function has to deal
+ * with the possibility of wrong timestamps in post processing.
+ */
+u64 notrace ktime_get_tai_fast_ns(void)
+{
+	struct timekeeper *tk = &tk_core.timekeeper;
+
+	return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai)));
+}
+EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns);
+
 static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
 {
 	struct tk_read_base *tkr;
@@ -543,10 +565,7 @@ 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 = timekeeping_delta_to_ns(tkr,
-				clocksource_delta(tk_clock_read(tkr),
-				tkr->cycle_last, tkr->mask));
+		delta = fast_tk_get_delta_ns(tkr);
 	} while (read_seqcount_latch_retry(&tkf->seq, seq));
 
 	if (mono)
@@ -1325,8 +1344,10 @@ out:
 	/* Signal hrtimers about time change */
 	clock_was_set(CLOCK_SET_WALL);
 
-	if (!ret)
+	if (!ret) {
 		audit_tk_injoffset(ts_delta);
+		add_device_randomness(ts, sizeof(*ts));
+	}
 
 	return ret;
 }
@@ -2380,6 +2401,20 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc)
 	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
@@ -2398,6 +2433,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 	ret = timekeeping_validate_timex(txc);
 	if (ret)
 		return ret;
+	add_device_randomness(txc, sizeof(*txc));
 
 	if (txc->modes & ADJ_SETOFFSET) {
 		struct timespec64 delta;
@@ -2415,6 +2451,7 @@ int do_adjtimex(struct __kernel_timex *txc)
 	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);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 85f1021ad459..717fcb9fb14a 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -44,6 +44,7 @@
 #include <linux/slab.h>
 #include <linux/compat.h>
 #include <linux/random.h>
+#include <linux/sysctl.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -223,7 +224,7 @@ static void timer_update_keys(struct work_struct *work);
 static DECLARE_WORK(timer_update_work, timer_update_keys);
 
 #ifdef CONFIG_SMP
-unsigned int sysctl_timer_migration = 1;
+static unsigned int sysctl_timer_migration = 1;
 
 DEFINE_STATIC_KEY_FALSE(timers_migration_enabled);
 
@@ -234,7 +235,42 @@ static void timers_update_migration(void)
 	else
 		static_branch_disable(&timers_migration_enabled);
 }
-#else
+
+#ifdef CONFIG_SYSCTL
+static int timer_migration_handler(struct ctl_table *table, int write,
+			    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	mutex_lock(&timer_keys_mutex);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (!ret && write)
+		timers_update_migration();
+	mutex_unlock(&timer_keys_mutex);
+	return ret;
+}
+
+static struct ctl_table timer_sysctl[] = {
+	{
+		.procname	= "timer_migration",
+		.data		= &sysctl_timer_migration,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= timer_migration_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{}
+};
+
+static int __init timer_sysctl_init(void)
+{
+	register_sysctl("kernel", timer_sysctl);
+	return 0;
+}
+device_initcall(timer_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+#else /* CONFIG_SMP */
 static inline void timers_update_migration(void) { }
 #endif /* !CONFIG_SMP */
 
@@ -251,19 +287,6 @@ void timers_update_nohz(void)
 	schedule_work(&timer_update_work);
 }
 
-int timer_migration_handler(struct ctl_table *table, int write,
-			    void *buffer, size_t *lenp, loff_t *ppos)
-{
-	int ret;
-
-	mutex_lock(&timer_keys_mutex);
-	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-	if (!ret && write)
-		timers_update_migration();
-	mutex_unlock(&timer_keys_mutex);
-	return ret;
-}
-
 static inline bool is_timers_nohz_active(void)
 {
 	return static_branch_unlikely(&timers_nohz_active);
@@ -502,7 +525,7 @@ static inline unsigned calc_index(unsigned long expires, unsigned lvl,
 	 *
 	 * Round up with level granularity to prevent this.
 	 */
-	expires = (expires + LVL_GRAN(lvl)) >> LVL_SHIFT(lvl);
+	expires = (expires >> LVL_SHIFT(lvl)) + 1;
 	*bucket_expiry = expires << LVL_SHIFT(lvl);
 	return LVL_OFFS(lvl) + (expires & LVL_MASK);
 }
@@ -615,9 +638,39 @@ static void internal_add_timer(struct timer_base *base, struct timer_list *timer
 
 static const struct debug_obj_descr timer_debug_descr;
 
+struct timer_hint {
+	void	(*function)(struct timer_list *t);
+	long	offset;
+};
+
+#define TIMER_HINT(fn, container, timr, hintfn)			\
+	{							\
+		.function = fn,					\
+		.offset	  = offsetof(container, hintfn) -	\
+			    offsetof(container, timr)		\
+	}
+
+static const struct timer_hint timer_hints[] = {
+	TIMER_HINT(delayed_work_timer_fn,
+		   struct delayed_work, timer, work.func),
+	TIMER_HINT(kthread_delayed_work_timer_fn,
+		   struct kthread_delayed_work, timer, work.func),
+};
+
 static void *timer_debug_hint(void *addr)
 {
-	return ((struct timer_list *) addr)->function;
+	struct timer_list *timer = addr;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(timer_hints); i++) {
+		if (timer_hints[i].function == timer->function) {
+			void (**fn)(void) = addr + timer_hints[i].offset;
+
+			return *fn;
+		}
+	}
+
+	return timer->function;
 }
 
 static bool timer_is_static_object(void *addr)
@@ -1722,11 +1775,14 @@ static inline void __run_timers(struct timer_base *base)
 	       time_after_eq(jiffies, base->next_expiry)) {
 		levels = collect_expired_timers(base, heads);
 		/*
-		 * The only possible reason for not finding any expired
-		 * timer at this clk is that all matching timers have been
-		 * dequeued.
+		 * The two possible reasons for not finding any expired
+		 * timer at this clk are that all matching timers have been
+		 * dequeued or no timer has been queued since
+		 * base::next_expiry was set to base::clk +
+		 * NEXT_TIMER_MAX_DELTA.
 		 */
-		WARN_ON_ONCE(!levels && !base->next_expiry_recalc);
+		WARN_ON_ONCE(!levels && !base->next_expiry_recalc
+			     && base->timers_pending);
 		base->clk++;
 		base->next_expiry = __next_timer_interrupt(base);
 
@@ -1777,8 +1833,6 @@ void update_process_times(int user_tick)
 {
 	struct task_struct *p = current;
 
-	PRANDOM_ADD_NOISE(jiffies, user_tick, p, 0);
-
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
 	run_local_timers();
@@ -1950,6 +2004,7 @@ int timers_prepare_cpu(unsigned int cpu)
 		base = per_cpu_ptr(&timer_bases[b], cpu);
 		base->clk = jiffies;
 		base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+		base->next_expiry_recalc = false;
 		base->timers_pending = false;
 		base->is_idle = false;
 	}