Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 55 insertions, 11 deletions

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 485bb0389b48..929e98c62965 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -537,7 +537,7 @@ retry:
 		}
 	}
 
-	ret = __replace_page(vma, vaddr, old_page, new_page);
+	ret = __replace_page(vma, vaddr & PAGE_MASK, old_page, new_page);
 	if (new_page)
 		put_page(new_page);
 put_old:
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index e0e853412c15..1e78ef24321e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -627,12 +627,21 @@ retry:
 }
 
 /*
- * PI futexes can not be requeued and must remove themselves from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
+ * PI futexes can not be requeued and must remove themselves from the hash
+ * bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 void futex_unqueue_pi(struct futex_q *q)
 {
-	__futex_unqueue(q);
+	/*
+	 * If the lock was not acquired (due to timeout or signal) then the
+	 * rt_waiter is removed before futex_q is. If this is observed by
+	 * an unlocker after dropping the rtmutex wait lock and before
+	 * acquiring the hash bucket lock, then the unlocker dequeues the
+	 * futex_q from the hash bucket list to guarantee consistent state
+	 * vs. userspace. Therefore the dequeue here must be conditional.
+	 */
+	if (!plist_node_empty(&q->list))
+		__futex_unqueue(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);
diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c
index 90e5197f4e56..5722467f2737 100644
--- a/kernel/futex/pi.c
+++ b/kernel/futex/pi.c
@@ -1135,6 +1135,7 @@ retry:
 
 	hb = futex_hash(&key);
 	spin_lock(&hb->lock);
+retry_hb:
 
 	/*
 	 * Check waiters first. We do not trust user space values at
@@ -1177,12 +1178,17 @@ retry:
 		/*
 		 * Futex vs rt_mutex waiter state -- if there are no rt_mutex
 		 * waiters even though futex thinks there are, then the waiter
-		 * is leaving and the uncontended path is safe to take.
+		 * is leaving. The entry needs to be removed from the list so a
+		 * new futex_lock_pi() is not using this stale PI-state while
+		 * the futex is available in user space again.
+		 * There can be more than one task on its way out so it needs
+		 * to retry.
 		 */
 		rt_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
 		if (!rt_waiter) {
+			__futex_unqueue(top_waiter);
 			raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-			goto do_uncontended;
+			goto retry_hb;
 		}
 
 		get_pi_state(pi_state);
@@ -1217,7 +1223,6 @@ retry:
 		return ret;
 	}
 
-do_uncontended:
 	/*
 	 * We have no kernel internal state, i.e. no waiters in the
 	 * kernel. Waiters which are about to queue themselves are stuck
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 27ca1c866f29..371eb1711d34 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -600,7 +600,7 @@ int __init early_irq_init(void)
 		mutex_init(&desc[i].request_mutex);
 		init_waitqueue_head(&desc[i].wait_for_threads);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
-		irq_resend_init(desc);
+		irq_resend_init(&desc[i]);
 	}
 	return arch_early_irq_init();
 }
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index c108ed8a9804..3052b1f1168e 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -99,6 +99,7 @@ static u64 suspend_start;
  * Interval: 0.5sec.
  */
 #define WATCHDOG_INTERVAL (HZ >> 1)
+#define WATCHDOG_INTERVAL_MAX_NS ((2 * WATCHDOG_INTERVAL) * (NSEC_PER_SEC / HZ))
 
 /*
  * Threshold: 0.0312s, when doubled: 0.0625s.
@@ -134,6 +135,7 @@ static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
 static int watchdog_running;
 static atomic_t watchdog_reset_pending;
+static int64_t watchdog_max_interval;
 
 static inline void clocksource_watchdog_lock(unsigned long *flags)
 {
@@ -399,8 +401,8 @@ 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;
 	int next_cpu, reset_pending;
-	int64_t wd_nsec, cs_nsec;
 	struct clocksource *cs;
 	enum wd_read_status read_ret;
 	unsigned long extra_wait = 0;
@@ -470,6 +472,27 @@ static void clocksource_watchdog(struct timer_list *unused)
 		if (atomic_read(&watchdog_reset_pending))
 			continue;
 
+		/*
+		 * The processing of timer softirqs can get delayed (usually
+		 * on account of ksoftirqd not getting to run in a timely
+		 * manner), which causes the watchdog interval to stretch.
+		 * Skew detection may fail for longer watchdog intervals
+		 * on account of fixed margins being used.
+		 * Some clocksources, e.g. acpi_pm, cannot tolerate
+		 * watchdog intervals longer than a few seconds.
+		 */
+		interval = max(cs_nsec, wd_nsec);
+		if (unlikely(interval > WATCHDOG_INTERVAL_MAX_NS)) {
+			if (system_state > SYSTEM_SCHEDULING &&
+			    interval > 2 * watchdog_max_interval) {
+				watchdog_max_interval = interval;
+				pr_warn("Long readout interval, skipping watchdog check: cs_nsec: %lld wd_nsec: %lld\n",
+					cs_nsec, wd_nsec);
+			}
+			watchdog_timer.expires = jiffies;
+			continue;
+		}
+
 		/* Check the deviation from the watchdog clocksource. */
 		md = cs->uncertainty_margin + watchdog->uncertainty_margin;
 		if (abs(cs_nsec - wd_nsec) > md) {
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index d2501673028d..01fb50c1b17e 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -1577,6 +1577,7 @@ void tick_cancel_sched_timer(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 	ktime_t idle_sleeptime, iowait_sleeptime;
+	unsigned long idle_calls, idle_sleeps;
 
 # ifdef CONFIG_HIGH_RES_TIMERS
 	if (ts->sched_timer.base)
@@ -1585,9 +1586,13 @@ void tick_cancel_sched_timer(int cpu)
 
 	idle_sleeptime = ts->idle_sleeptime;
 	iowait_sleeptime = ts->iowait_sleeptime;
+	idle_calls = ts->idle_calls;
+	idle_sleeps = ts->idle_sleeps;
 	memset(ts, 0, sizeof(*ts));
 	ts->idle_sleeptime = idle_sleeptime;
 	ts->iowait_sleeptime = iowait_sleeptime;
+	ts->idle_calls = idle_calls;
+	ts->idle_sleeps = idle_sleeps;
 }
 #endif
 
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 46439e3bcec4..b33c3861fbbb 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -1470,8 +1470,10 @@ register_snapshot_trigger(char *glob,
 			  struct event_trigger_data *data,
 			  struct trace_event_file *file)
 {
-	if (tracing_alloc_snapshot_instance(file->tr) != 0)
-		return 0;
+	int ret = tracing_alloc_snapshot_instance(file->tr);
+
+	if (ret < 0)
+		return ret;
 
 	return register_trigger(glob, data, file);
 }