Merge branch 'sched/urgent' into sched/core, to pick up pending v6.7 fixes for the v6.8 merge window

This fix didn't make it upstream in time, pick it up
for the v6.8 merge window.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

6 files changed, 103 insertions, 102 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9cc20855dc2b..b803030c3a03 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4100,6 +4100,10 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 	if (cfs_rq->tg == &root_task_group)
 		return;
 
+	/* rq has been offline and doesn't contribute to the share anymore: */
+	if (!cpu_active(cpu_of(rq_of(cfs_rq))))
+		return;
+
 	/*
 	 * For migration heavy workloads, access to tg->load_avg can be
 	 * unbound. Limit the update rate to at most once per ms.
@@ -4116,6 +4120,49 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq)
 	}
 }
 
+static inline void clear_tg_load_avg(struct cfs_rq *cfs_rq)
+{
+	long delta;
+	u64 now;
+
+	/*
+	 * No need to update load_avg for root_task_group, as it is not used.
+	 */
+	if (cfs_rq->tg == &root_task_group)
+		return;
+
+	now = sched_clock_cpu(cpu_of(rq_of(cfs_rq)));
+	delta = 0 - cfs_rq->tg_load_avg_contrib;
+	atomic_long_add(delta, &cfs_rq->tg->load_avg);
+	cfs_rq->tg_load_avg_contrib = 0;
+	cfs_rq->last_update_tg_load_avg = now;
+}
+
+/* CPU offline callback: */
+static void __maybe_unused clear_tg_offline_cfs_rqs(struct rq *rq)
+{
+	struct task_group *tg;
+
+	lockdep_assert_rq_held(rq);
+
+	/*
+	 * The rq clock has already been updated in
+	 * set_rq_offline(), so we should skip updating
+	 * the rq clock again in unthrottle_cfs_rq().
+	 */
+	rq_clock_start_loop_update(rq);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
+
+		clear_tg_load_avg(cfs_rq);
+	}
+	rcu_read_unlock();
+
+	rq_clock_stop_loop_update(rq);
+}
+
 /*
  * Called within set_task_rq() right before setting a task's CPU. The
  * caller only guarantees p->pi_lock is held; no other assumptions,
@@ -4412,6 +4459,8 @@ static inline bool skip_blocked_update(struct sched_entity *se)
 
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {}
 
+static inline void clear_tg_offline_cfs_rqs(struct rq *rq) {}
+
 static inline int propagate_entity_load_avg(struct sched_entity *se)
 {
 	return 0;
@@ -12422,6 +12471,9 @@ static void rq_offline_fair(struct rq *rq)
 
 	/* Ensure any throttled groups are reachable by pick_next_task */
 	unthrottle_offline_cfs_rqs(rq);
+
+	/* Ensure that we remove rq contribution to group share: */
+	clear_tg_offline_cfs_rqs(rq);
 }
 
 #endif /* CONFIG_SMP */
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index e1a6e3c675c0..9a846439b36a 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -201,6 +201,20 @@ COND_SYSCALL(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time32);
 COND_SYSCALL_COMPAT(recvmmsg_time64);
 
+/* Posix timer syscalls may be configured out */
+COND_SYSCALL(timer_create);
+COND_SYSCALL(timer_gettime);
+COND_SYSCALL(timer_getoverrun);
+COND_SYSCALL(timer_settime);
+COND_SYSCALL(timer_delete);
+COND_SYSCALL(clock_adjtime);
+COND_SYSCALL(getitimer);
+COND_SYSCALL(setitimer);
+COND_SYSCALL(alarm);
+COND_SYSCALL_COMPAT(timer_create);
+COND_SYSCALL_COMPAT(getitimer);
+COND_SYSCALL_COMPAT(setitimer);
+
 /*
  * Architecture specific syscalls: see further below
  */
diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 828aeecbd1e8..9b6fcb8d85e7 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -17,40 +17,6 @@
 #include <linux/time_namespace.h>
 #include <linux/compat.h>
 
-#ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
-/* Architectures may override SYS_NI and COMPAT_SYS_NI */
-#include <asm/syscall_wrapper.h>
-#endif
-
-asmlinkage long sys_ni_posix_timers(void)
-{
-	pr_err_once("process %d (%s) attempted a POSIX timer syscall "
-		    "while CONFIG_POSIX_TIMERS is not set\n",
-		    current->pid, current->comm);
-	return -ENOSYS;
-}
-
-#ifndef SYS_NI
-#define SYS_NI(name)  SYSCALL_ALIAS(sys_##name, sys_ni_posix_timers)
-#endif
-
-#ifndef COMPAT_SYS_NI
-#define COMPAT_SYS_NI(name)  SYSCALL_ALIAS(compat_sys_##name, sys_ni_posix_timers)
-#endif
-
-SYS_NI(timer_create);
-SYS_NI(timer_gettime);
-SYS_NI(timer_getoverrun);
-SYS_NI(timer_settime);
-SYS_NI(timer_delete);
-SYS_NI(clock_adjtime);
-SYS_NI(getitimer);
-SYS_NI(setitimer);
-SYS_NI(clock_adjtime32);
-#ifdef __ARCH_WANT_SYS_ALARM
-SYS_NI(alarm);
-#endif
-
 /*
  * We preserve minimal support for CLOCK_REALTIME and CLOCK_MONOTONIC
  * as it is easy to remain compatible with little code. CLOCK_BOOTTIME
@@ -158,18 +124,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 				 which_clock);
 }
 
-#ifdef CONFIG_COMPAT
-COMPAT_SYS_NI(timer_create);
-#endif
-
-#if defined(CONFIG_COMPAT) || defined(CONFIG_ALPHA)
-COMPAT_SYS_NI(getitimer);
-COMPAT_SYS_NI(setitimer);
-#endif
-
 #ifdef CONFIG_COMPAT_32BIT_TIME
-SYS_NI(timer_settime32);
-SYS_NI(timer_gettime32);
 
 SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock,
 		struct old_timespec32 __user *, tp)
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5a114e752f11..83eab547f1d1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -700,48 +700,6 @@ rb_time_read_cmpxchg(local_t *l, unsigned long expect, unsigned long set)
 	return local_try_cmpxchg(l, &expect, set);
 }
 
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	unsigned long cnt, top, bottom, msb;
-	unsigned long cnt2, top2, bottom2, msb2;
-	u64 val;
-
-	/* Any interruptions in this function should cause a failure */
-	cnt = local_read(&t->cnt);
-
-	/* The cmpxchg always fails if it interrupted an update */
-	 if (!__rb_time_read(t, &val, &cnt2))
-		 return false;
-
-	 if (val != expect)
-		 return false;
-
-	 if ((cnt & 3) != cnt2)
-		 return false;
-
-	 cnt2 = cnt + 1;
-
-	 rb_time_split(val, &top, &bottom, &msb);
-	 msb = rb_time_val_cnt(msb, cnt);
-	 top = rb_time_val_cnt(top, cnt);
-	 bottom = rb_time_val_cnt(bottom, cnt);
-
-	 rb_time_split(set, &top2, &bottom2, &msb2);
-	 msb2 = rb_time_val_cnt(msb2, cnt);
-	 top2 = rb_time_val_cnt(top2, cnt2);
-	 bottom2 = rb_time_val_cnt(bottom2, cnt2);
-
-	if (!rb_time_read_cmpxchg(&t->cnt, cnt, cnt2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->msb, msb, msb2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->top, top, top2))
-		return false;
-	if (!rb_time_read_cmpxchg(&t->bottom, bottom, bottom2))
-		return false;
-	return true;
-}
-
 #else /* 64 bits */
 
 /* local64_t always succeeds */
@@ -755,11 +713,6 @@ static void rb_time_set(rb_time_t *t, u64 val)
 {
 	local64_set(&t->time, val);
 }
-
-static bool rb_time_cmpxchg(rb_time_t *t, u64 expect, u64 set)
-{
-	return local64_try_cmpxchg(&t->time, &expect, set);
-}
 #endif
 
 /*
@@ -3610,20 +3563,36 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	} else {
 		u64 ts;
 		/* SLOW PATH - Interrupted between A and C */
-		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
-		/* Was interrupted before here, write_stamp must be valid */
+
+		/* Save the old before_stamp */
+		a_ok = rb_time_read(&cpu_buffer->before_stamp, &info->before);
 		RB_WARN_ON(cpu_buffer, !a_ok);
+
+		/*
+		 * Read a new timestamp and update the before_stamp to make
+		 * the next event after this one force using an absolute
+		 * timestamp. This is in case an interrupt were to come in
+		 * between E and F.
+		 */
 		ts = rb_time_stamp(cpu_buffer->buffer);
+		rb_time_set(&cpu_buffer->before_stamp, ts);
+
+		barrier();
+ /*E*/		a_ok = rb_time_read(&cpu_buffer->write_stamp, &info->after);
+		/* Was interrupted before here, write_stamp must be valid */
+		RB_WARN_ON(cpu_buffer, !a_ok);
 		barrier();
- /*E*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
-		    info->after < ts &&
-		    rb_time_cmpxchg(&cpu_buffer->write_stamp,
-				    info->after, ts)) {
-			/* Nothing came after this event between C and E */
+ /*F*/		if (write == (local_read(&tail_page->write) & RB_WRITE_MASK) &&
+		    info->after == info->before && info->after < ts) {
+			/*
+			 * Nothing came after this event between C and F, it is
+			 * safe to use info->after for the delta as it
+			 * matched info->before and is still valid.
+			 */
 			info->delta = ts - info->after;
 		} else {
 			/*
-			 * Interrupted between C and E:
+			 * Interrupted between C and F:
 			 * Lost the previous events time stamp. Just set the
 			 * delta to zero, and this will be the same time as
 			 * the event this event interrupted. And the events that
diff --git a/kernel/trace/synth_event_gen_test.c b/kernel/trace/synth_event_gen_test.c
index 8dfe85499d4a..354c2117be43 100644
--- a/kernel/trace/synth_event_gen_test.c
+++ b/kernel/trace/synth_event_gen_test.c
@@ -477,6 +477,17 @@ static int __init synth_event_gen_test_init(void)
 
 	ret = test_trace_synth_event();
 	WARN_ON(ret);
+
+	/* Disable when done */
+	trace_array_set_clr_event(gen_synth_test->tr,
+				  "synthetic",
+				  "gen_synth_test", false);
+	trace_array_set_clr_event(empty_synth_test->tr,
+				  "synthetic",
+				  "empty_synth_test", false);
+	trace_array_set_clr_event(create_synth_test->tr,
+				  "synthetic",
+				  "create_synth_test", false);
  out:
 	return ret;
 }
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 846e02c0fb59..e7af286af4f1 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -1137,7 +1137,7 @@ EXPORT_SYMBOL_GPL(synth_event_add_fields);
  * @cmd: A pointer to the dynevent_cmd struct representing the new event
  * @name: The name of the synthetic event
  * @mod: The module creating the event, NULL if not created from a module
- * @args: Variable number of arg (pairs), one pair for each field
+ * @...: Variable number of arg (pairs), one pair for each field
  *
  * NOTE: Users normally won't want to call this function directly, but
  * rather use the synth_event_gen_cmd_start() wrapper, which
@@ -1695,7 +1695,7 @@ __synth_event_trace_end(struct synth_event_trace_state *trace_state)
  * synth_event_trace - Trace a synthetic event
  * @file: The trace_event_file representing the synthetic event
  * @n_vals: The number of values in vals
- * @args: Variable number of args containing the event values
+ * @...: Variable number of args containing the event values
  *
  * Trace a synthetic event using the values passed in the variable
  * argument list.