Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index fa49cd7..4820823 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
/*
- * linux/kernel/timer.c
- *
* Kernel internal timers
*
* Copyright (C) 1991, 1992 Linus Torvalds
@@ -197,6 +196,10 @@
struct timer_base {
raw_spinlock_t lock;
struct timer_list *running_timer;
+#ifdef CONFIG_PREEMPT_RT
+ spinlock_t expiry_lock;
+ atomic_t timer_waiters;
+#endif
unsigned long clk;
unsigned long next_expiry;
unsigned int cpu;
@@ -537,6 +540,8 @@
hlist_add_head(&timer->entry, base->vectors + idx);
__set_bit(idx, base->pending_map);
timer_set_idx(timer, idx);
+
+ trace_timer_start(timer, timer->expires, timer->flags);
}
static void
@@ -648,7 +653,7 @@
case ODEBUG_STATE_ACTIVE:
WARN_ON(1);
-
+ /* fall through */
default:
return false;
}
@@ -758,13 +763,6 @@
trace_timer_init(timer);
}
-static inline void
-debug_activate(struct timer_list *timer, unsigned long expires)
-{
- debug_timer_activate(timer);
- trace_timer_start(timer, expires, timer->flags);
-}
-
static inline void debug_deactivate(struct timer_list *timer)
{
debug_timer_deactivate(timer);
@@ -1038,7 +1036,7 @@
}
}
- debug_activate(timer, expires);
+ debug_timer_activate(timer);
timer->expires = expires;
/*
@@ -1172,7 +1170,7 @@
}
forward_timer_base(base);
- debug_activate(timer, timer->expires);
+ debug_timer_activate(timer);
internal_add_timer(base, timer);
raw_spin_unlock_irqrestore(&base->lock, flags);
}
@@ -1233,7 +1231,78 @@
}
EXPORT_SYMBOL(try_to_del_timer_sync);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_PREEMPT_RT
+static __init void timer_base_init_expiry_lock(struct timer_base *base)
+{
+ spin_lock_init(&base->expiry_lock);
+}
+
+static inline void timer_base_lock_expiry(struct timer_base *base)
+{
+ spin_lock(&base->expiry_lock);
+}
+
+static inline void timer_base_unlock_expiry(struct timer_base *base)
+{
+ spin_unlock(&base->expiry_lock);
+}
+
+/*
+ * The counterpart to del_timer_wait_running().
+ *
+ * If there is a waiter for base->expiry_lock, then it was waiting for the
+ * timer callback to finish. Drop expiry_lock and reaquire it. That allows
+ * the waiter to acquire the lock and make progress.
+ */
+static void timer_sync_wait_running(struct timer_base *base)
+{
+ if (atomic_read(&base->timer_waiters)) {
+ spin_unlock(&base->expiry_lock);
+ spin_lock(&base->expiry_lock);
+ }
+}
+
+/*
+ * This function is called on PREEMPT_RT kernels when the fast path
+ * deletion of a timer failed because the timer callback function was
+ * running.
+ *
+ * This prevents priority inversion, if the softirq thread on a remote CPU
+ * got preempted, and it prevents a life lock when the task which tries to
+ * delete a timer preempted the softirq thread running the timer callback
+ * function.
+ */
+static void del_timer_wait_running(struct timer_list *timer)
+{
+ u32 tf;
+
+ tf = READ_ONCE(timer->flags);
+ if (!(tf & TIMER_MIGRATING)) {
+ struct timer_base *base = get_timer_base(tf);
+
+ /*
+ * Mark the base as contended and grab the expiry lock,
+ * which is held by the softirq across the timer
+ * callback. Drop the lock immediately so the softirq can
+ * expire the next timer. In theory the timer could already
+ * be running again, but that's more than unlikely and just
+ * causes another wait loop.
+ */
+ atomic_inc(&base->timer_waiters);
+ spin_lock_bh(&base->expiry_lock);
+ atomic_dec(&base->timer_waiters);
+ spin_unlock_bh(&base->expiry_lock);
+ }
+}
+#else
+static inline void timer_base_init_expiry_lock(struct timer_base *base) { }
+static inline void timer_base_lock_expiry(struct timer_base *base) { }
+static inline void timer_base_unlock_expiry(struct timer_base *base) { }
+static inline void timer_sync_wait_running(struct timer_base *base) { }
+static inline void del_timer_wait_running(struct timer_list *timer) { }
+#endif
+
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
/**
* del_timer_sync - deactivate a timer and wait for the handler to finish.
* @timer: the timer to be deactivated
@@ -1272,6 +1341,8 @@
*/
int del_timer_sync(struct timer_list *timer)
{
+ int ret;
+
#ifdef CONFIG_LOCKDEP
unsigned long flags;
@@ -1289,17 +1360,24 @@
* could lead to deadlock.
*/
WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE));
- for (;;) {
- int ret = try_to_del_timer_sync(timer);
- if (ret >= 0)
- return ret;
- cpu_relax();
- }
+
+ do {
+ ret = try_to_del_timer_sync(timer);
+
+ if (unlikely(ret < 0)) {
+ del_timer_wait_running(timer);
+ cpu_relax();
+ }
+ } while (ret < 0);
+
+ return ret;
}
EXPORT_SYMBOL(del_timer_sync);
#endif
-static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *))
+static void call_timer_fn(struct timer_list *timer,
+ void (*fn)(struct timer_list *),
+ unsigned long baseclk)
{
int count = preempt_count();
@@ -1322,14 +1400,14 @@
*/
lock_map_acquire(&lockdep_map);
- trace_timer_expire_entry(timer);
+ trace_timer_expire_entry(timer, baseclk);
fn(timer);
trace_timer_expire_exit(timer);
lock_map_release(&lockdep_map);
if (count != preempt_count()) {
- WARN_ONCE(1, "timer: %pF preempt leak: %08x -> %08x\n",
+ WARN_ONCE(1, "timer: %pS preempt leak: %08x -> %08x\n",
fn, count, preempt_count());
/*
* Restore the preempt count. That gives us a decent
@@ -1343,6 +1421,13 @@
static void expire_timers(struct timer_base *base, struct hlist_head *head)
{
+ /*
+ * This value is required only for tracing. base->clk was
+ * incremented directly before expire_timers was called. But expiry
+ * is related to the old base->clk value.
+ */
+ unsigned long baseclk = base->clk - 1;
+
while (!hlist_empty(head)) {
struct timer_list *timer;
void (*fn)(struct timer_list *);
@@ -1356,11 +1441,14 @@
if (timer->flags & TIMER_IRQSAFE) {
raw_spin_unlock(&base->lock);
- call_timer_fn(timer, fn);
+ call_timer_fn(timer, fn, baseclk);
+ base->running_timer = NULL;
raw_spin_lock(&base->lock);
} else {
raw_spin_unlock_irq(&base->lock);
- call_timer_fn(timer, fn);
+ call_timer_fn(timer, fn, baseclk);
+ base->running_timer = NULL;
+ timer_sync_wait_running(base);
raw_spin_lock_irq(&base->lock);
}
}
@@ -1590,24 +1678,26 @@
static int collect_expired_timers(struct timer_base *base,
struct hlist_head *heads)
{
+ unsigned long now = READ_ONCE(jiffies);
+
/*
* NOHZ optimization. After a long idle sleep we need to forward the
* base to current jiffies. Avoid a loop by searching the bitfield for
* the next expiring timer.
*/
- if ((long)(jiffies - base->clk) > 2) {
+ if ((long)(now - base->clk) > 2) {
unsigned long next = __next_timer_interrupt(base);
/*
* If the next timer is ahead of time forward to current
* jiffies, otherwise forward to the next expiry time:
*/
- if (time_after(next, jiffies)) {
+ if (time_after(next, now)) {
/*
* The call site will increment base->clk and then
* terminate the expiry loop immediately.
*/
- base->clk = jiffies;
+ base->clk = now;
return 0;
}
base->clk = next;
@@ -1633,14 +1723,14 @@
/* Note: this timer irq context must be accounted for as well. */
account_process_tick(p, user_tick);
run_local_timers();
- rcu_check_callbacks(user_tick);
+ rcu_sched_clock_irq(user_tick);
#ifdef CONFIG_IRQ_WORK
if (in_irq())
irq_work_tick();
#endif
scheduler_tick();
if (IS_ENABLED(CONFIG_POSIX_TIMERS))
- run_posix_cpu_timers(p);
+ run_posix_cpu_timers();
}
/**
@@ -1655,6 +1745,7 @@
if (!time_after_eq(jiffies, base->clk))
return;
+ timer_base_lock_expiry(base);
raw_spin_lock_irq(&base->lock);
/*
@@ -1681,8 +1772,8 @@
while (levels--)
expire_timers(base, heads + levels);
}
- base->running_timer = NULL;
raw_spin_unlock_irq(&base->lock);
+ timer_base_unlock_expiry(base);
}
/*
@@ -1927,6 +2018,7 @@
base->cpu = cpu;
raw_spin_lock_init(&base->lock);
base->clk = jiffies;
+ timer_base_init_expiry_lock(base);
}
}