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

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

9 files changed, 136 insertions, 104 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 192e43a87407..407a2568f35e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -31,6 +31,7 @@
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
+#include <linux/scs.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/cpuset.h>
 
@@ -588,6 +589,12 @@ static int bringup_cpu(unsigned int cpu)
 	int ret;
 
 	/*
+	 * Reset stale stack state from the last time this CPU was online.
+	 */
+	scs_task_reset(idle);
+	kasan_unpoison_task_stack(idle);
+
+	/*
 	 * Some architectures have to walk the irq descriptors to
 	 * setup the vector space for the cpu which comes online.
 	 * Prevent irq alloc/free across the bringup.
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 523106a506ee..30d94f68c5bd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9759,6 +9759,9 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
 				continue;
 			if (event->attr.config != entry->type)
 				continue;
+			/* Cannot deliver synchronous signal to other task. */
+			if (event->attr.sigtrap)
+				continue;
 			if (perf_tp_event_match(event, &data, regs))
 				perf_swevent_event(event, count, &data, regs);
 		}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index e9db0c810554..21eccc961bba 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp)
 		}
 	}
 
+	if (rp->data_size > KRETPROBE_MAX_DATA_SIZE)
+		return -E2BIG;
+
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c51387a43265..04a74d040a6d 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -105,9 +105,9 @@
  * atomic_long_cmpxchg() will be used to obtain writer lock.
  *
  * There are three places where the lock handoff bit may be set or cleared.
- * 1) rwsem_mark_wake() for readers.
- * 2) rwsem_try_write_lock() for writers.
- * 3) Error path of rwsem_down_write_slowpath().
+ * 1) rwsem_mark_wake() for readers		-- set, clear
+ * 2) rwsem_try_write_lock() for writers	-- set, clear
+ * 3) rwsem_del_waiter()			-- clear
  *
  * For all the above cases, wait_lock will be held. A writer must also
  * be the first one in the wait_list to be eligible for setting the handoff
@@ -334,6 +334,9 @@ struct rwsem_waiter {
 	struct task_struct *task;
 	enum rwsem_waiter_type type;
 	unsigned long timeout;
+
+	/* Writer only, not initialized in reader */
+	bool handoff_set;
 };
 #define rwsem_first_waiter(sem) \
 	list_first_entry(&sem->wait_list, struct rwsem_waiter, list)
@@ -344,12 +347,6 @@ enum rwsem_wake_type {
 	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
 };
 
-enum writer_wait_state {
-	WRITER_NOT_FIRST,	/* Writer is not first in wait list */
-	WRITER_FIRST,		/* Writer is first in wait list     */
-	WRITER_HANDOFF		/* Writer is first & handoff needed */
-};
-
 /*
  * The typical HZ value is either 250 or 1000. So set the minimum waiting
  * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
@@ -365,6 +362,31 @@ enum writer_wait_state {
  */
 #define MAX_READERS_WAKEUP	0x100
 
+static inline void
+rwsem_add_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+	lockdep_assert_held(&sem->wait_lock);
+	list_add_tail(&waiter->list, &sem->wait_list);
+	/* caller will set RWSEM_FLAG_WAITERS */
+}
+
+/*
+ * Remove a waiter from the wait_list and clear flags.
+ *
+ * Both rwsem_mark_wake() and rwsem_try_write_lock() contain a full 'copy' of
+ * this function. Modify with care.
+ */
+static inline void
+rwsem_del_waiter(struct rw_semaphore *sem, struct rwsem_waiter *waiter)
+{
+	lockdep_assert_held(&sem->wait_lock);
+	list_del(&waiter->list);
+	if (likely(!list_empty(&sem->wait_list)))
+		return;
+
+	atomic_long_andnot(RWSEM_FLAG_HANDOFF | RWSEM_FLAG_WAITERS, &sem->count);
+}
+
 /*
  * handle the lock release when processes blocked on it that can now run
  * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
@@ -376,6 +398,8 @@ enum writer_wait_state {
  *   preferably when the wait_lock is released
  * - woken process blocks are discarded from the list after having task zeroed
  * - writers are only marked woken if downgrading is false
+ *
+ * Implies rwsem_del_waiter() for all woken readers.
  */
 static void rwsem_mark_wake(struct rw_semaphore *sem,
 			    enum rwsem_wake_type wake_type,
@@ -490,18 +514,25 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 
 	adjustment = woken * RWSEM_READER_BIAS - adjustment;
 	lockevent_cond_inc(rwsem_wake_reader, woken);
+
+	oldcount = atomic_long_read(&sem->count);
 	if (list_empty(&sem->wait_list)) {
-		/* hit end of list above */
+		/*
+		 * Combined with list_move_tail() above, this implies
+		 * rwsem_del_waiter().
+		 */
 		adjustment -= RWSEM_FLAG_WAITERS;
+		if (oldcount & RWSEM_FLAG_HANDOFF)
+			adjustment -= RWSEM_FLAG_HANDOFF;
+	} else if (woken) {
+		/*
+		 * When we've woken a reader, we no longer need to force
+		 * writers to give up the lock and we can clear HANDOFF.
+		 */
+		if (oldcount & RWSEM_FLAG_HANDOFF)
+			adjustment -= RWSEM_FLAG_HANDOFF;
 	}
 
-	/*
-	 * When we've woken a reader, we no longer need to force writers
-	 * to give up the lock and we can clear HANDOFF.
-	 */
-	if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
-		adjustment -= RWSEM_FLAG_HANDOFF;
-
 	if (adjustment)
 		atomic_long_add(adjustment, &sem->count);
 
@@ -532,12 +563,12 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
  * race conditions between checking the rwsem wait list and setting the
  * sem->count accordingly.
  *
- * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
- * bit is set or the lock is acquired with handoff bit cleared.
+ * Implies rwsem_del_waiter() on success.
  */
 static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
-					enum writer_wait_state wstate)
+					struct rwsem_waiter *waiter)
 {
+	bool first = rwsem_first_waiter(sem) == waiter;
 	long count, new;
 
 	lockdep_assert_held(&sem->wait_lock);
@@ -546,13 +577,19 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	do {
 		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
 
-		if (has_handoff && wstate == WRITER_NOT_FIRST)
-			return false;
+		if (has_handoff) {
+			if (!first)
+				return false;
+
+			/* First waiter inherits a previously set handoff bit */
+			waiter->handoff_set = true;
+		}
 
 		new = count;
 
 		if (count & RWSEM_LOCK_MASK) {
-			if (has_handoff || (wstate != WRITER_HANDOFF))
+			if (has_handoff || (!rt_task(waiter->task) &&
+					    !time_after(jiffies, waiter->timeout)))
 				return false;
 
 			new |= RWSEM_FLAG_HANDOFF;
@@ -569,9 +606,17 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	 * We have either acquired the lock with handoff bit cleared or
 	 * set the handoff bit.
 	 */
-	if (new & RWSEM_FLAG_HANDOFF)
+	if (new & RWSEM_FLAG_HANDOFF) {
+		waiter->handoff_set = true;
+		lockevent_inc(rwsem_wlock_handoff);
 		return false;
+	}
 
+	/*
+	 * Have rwsem_try_write_lock() fully imply rwsem_del_waiter() on
+	 * success.
+	 */
+	list_del(&waiter->list);
 	rwsem_set_owner(sem);
 	return true;
 }
@@ -956,7 +1001,7 @@ queue:
 		}
 		adjustment += RWSEM_FLAG_WAITERS;
 	}
-	list_add_tail(&waiter.list, &sem->wait_list);
+	rwsem_add_waiter(sem, &waiter);
 
 	/* we're now waiting on the lock, but no longer actively locking */
 	count = atomic_long_add_return(adjustment, &sem->count);
@@ -1002,11 +1047,7 @@ queue:
 	return sem;
 
 out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list)) {
-		atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
-				   &sem->count);
-	}
+	rwsem_del_waiter(sem, &waiter);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock_fail);
@@ -1020,9 +1061,7 @@ static struct rw_semaphore *
 rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 {
 	long count;
-	enum writer_wait_state wstate;
 	struct rwsem_waiter waiter;
-	struct rw_semaphore *ret = sem;
 	DEFINE_WAKE_Q(wake_q);
 
 	/* do optimistic spinning and steal lock if possible */
@@ -1038,16 +1077,13 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 	waiter.task = current;
 	waiter.type = RWSEM_WAITING_FOR_WRITE;
 	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+	waiter.handoff_set = false;
 
 	raw_spin_lock_irq(&sem->wait_lock);
-
-	/* account for this before adding a new element to the list */
-	wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;
-
-	list_add_tail(&waiter.list, &sem->wait_list);
+	rwsem_add_waiter(sem, &waiter);
 
 	/* we're now waiting on the lock */
-	if (wstate == WRITER_NOT_FIRST) {
+	if (rwsem_first_waiter(sem) != &waiter) {
 		count = atomic_long_read(&sem->count);
 
 		/*
@@ -1083,13 +1119,16 @@ wait:
 	/* wait until we successfully acquire the lock */
 	set_current_state(state);
 	for (;;) {
-		if (rwsem_try_write_lock(sem, wstate)) {
+		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
 			break;
 		}
 
 		raw_spin_unlock_irq(&sem->wait_lock);
 
+		if (signal_pending_state(state, current))
+			goto out_nolock;
+
 		/*
 		 * After setting the handoff bit and failing to acquire
 		 * the lock, attempt to spin on owner to accelerate lock
@@ -1098,7 +1137,7 @@ wait:
 		 * In this case, we attempt to acquire the lock again
 		 * without sleeping.
 		 */
-		if (wstate == WRITER_HANDOFF) {
+		if (waiter.handoff_set) {
 			enum owner_state owner_state;
 
 			preempt_disable();
@@ -1109,66 +1148,26 @@ wait:
 				goto trylock_again;
 		}
 
-		/* Block until there are no active lockers. */
-		for (;;) {
-			if (signal_pending_state(state, current))
-				goto out_nolock;
-
-			schedule();
-			lockevent_inc(rwsem_sleep_writer);
-			set_current_state(state);
-			/*
-			 * If HANDOFF bit is set, unconditionally do
-			 * a trylock.
-			 */
-			if (wstate == WRITER_HANDOFF)
-				break;
-
-			if ((wstate == WRITER_NOT_FIRST) &&
-			    (rwsem_first_waiter(sem) == &waiter))
-				wstate = WRITER_FIRST;
-
-			count = atomic_long_read(&sem->count);
-			if (!(count & RWSEM_LOCK_MASK))
-				break;
-
-			/*
-			 * The setting of the handoff bit is deferred
-			 * until rwsem_try_write_lock() is called.
-			 */
-			if ((wstate == WRITER_FIRST) && (rt_task(current) ||
-			    time_after(jiffies, waiter.timeout))) {
-				wstate = WRITER_HANDOFF;
-				lockevent_inc(rwsem_wlock_handoff);
-				break;
-			}
-		}
+		schedule();
+		lockevent_inc(rwsem_sleep_writer);
+		set_current_state(state);
 trylock_again:
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
 	__set_current_state(TASK_RUNNING);
-	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
-
-	return ret;
+	return sem;
 
 out_nolock:
 	__set_current_state(TASK_RUNNING);
 	raw_spin_lock_irq(&sem->wait_lock);
-	list_del(&waiter.list);
-
-	if (unlikely(wstate == WRITER_HANDOFF))
-		atomic_long_add(-RWSEM_FLAG_HANDOFF,  &sem->count);
-
-	if (list_empty(&sem->wait_list))
-		atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
-	else
+	rwsem_del_waiter(sem, &waiter);
+	if (!list_empty(&sem->wait_list))
 		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	wake_up_q(&wake_q);
 	lockevent_inc(rwsem_wlock_fail);
-
 	return ERR_PTR(-EINTR);
 }
 
@@ -1249,17 +1248,14 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 
 	DEBUG_RWSEMS_WARN_ON(sem->magic != sem, sem);
 
-	/*
-	 * Optimize for the case when the rwsem is not locked at all.
-	 */
-	tmp = RWSEM_UNLOCKED_VALUE;
-	do {
+	tmp = atomic_long_read(&sem->count);
+	while (!(tmp & RWSEM_READ_FAILED_MASK)) {
 		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
-					tmp + RWSEM_READER_BIAS)) {
+						    tmp + RWSEM_READER_BIAS)) {
 			rwsem_set_reader_owned(sem);
 			return 1;
 		}
-	} while (!(tmp & RWSEM_READ_FAILED_MASK));
+	}
 	return 0;
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3c9b0fda64ac..76f9deeaa942 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8619,9 +8619,6 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY;
 	kthread_set_per_cpu(idle, cpu);
 
-	scs_task_reset(idle);
-	kasan_unpoison_task_stack(idle);
-
 #ifdef CONFIG_SMP
 	/*
 	 * It's possible that init_idle() gets called multiple times on a task,
@@ -8777,7 +8774,6 @@ void idle_task_exit(void)
 		finish_arch_post_lock_switch();
 	}
 
-	scs_task_reset(current);
 	/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6b60ab9475ed..38715aa6cfdf 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1366,14 +1366,26 @@ __event_trigger_test_discard(struct trace_event_file *file,
 	if (eflags & EVENT_FILE_FL_TRIGGER_COND)
 		*tt = event_triggers_call(file, buffer, entry, event);
 
-	if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) ||
-	    (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
-	     !filter_match_preds(file->filter, entry))) {
-		__trace_event_discard_commit(buffer, event);
-		return true;
-	}
+	if (likely(!(file->flags & (EVENT_FILE_FL_SOFT_DISABLED |
+				    EVENT_FILE_FL_FILTERED |
+				    EVENT_FILE_FL_PID_FILTER))))
+		return false;
+
+	if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
+		goto discard;
+
+	if (file->flags & EVENT_FILE_FL_FILTERED &&
+	    !filter_match_preds(file->filter, entry))
+		goto discard;
+
+	if ((file->flags & EVENT_FILE_FL_PID_FILTER) &&
+	    trace_event_ignore_this_pid(file))
+		goto discard;
 
 	return false;
+ discard:
+	__trace_event_discard_commit(buffer, event);
+	return true;
 }
 
 /**
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4021b9a79f93..92be9cb1d7d4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -2678,12 +2678,24 @@ static struct trace_event_file *
 trace_create_new_event(struct trace_event_call *call,
 		       struct trace_array *tr)
 {
+	struct trace_pid_list *no_pid_list;
+	struct trace_pid_list *pid_list;
 	struct trace_event_file *file;
+	unsigned int first;
 
 	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
 	if (!file)
 		return NULL;
 
+	pid_list = rcu_dereference_protected(tr->filtered_pids,
+					     lockdep_is_held(&event_mutex));
+	no_pid_list = rcu_dereference_protected(tr->filtered_no_pids,
+					     lockdep_is_held(&event_mutex));
+
+	if (!trace_pid_list_first(pid_list, &first) ||
+	    !trace_pid_list_first(no_pid_list, &first))
+		file->flags |= EVENT_FILE_FL_PID_FILTER;
+
 	file->event_call = call;
 	file->tr = tr;
 	atomic_set(&file->sm_ref, 0);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 9555b8e1d1e3..319f9c8ca7e7 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3757,7 +3757,7 @@ static int check_synth_field(struct synth_event *event,
 
 	if (strcmp(field->type, hist_field->type) != 0) {
 		if (field->size != hist_field->size ||
-		    field->is_signed != hist_field->is_signed)
+		    (!field->is_string && field->is_signed != hist_field->is_signed))
 			return -EINVAL;
 	}
 
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 39bb56d2dcbe..9628b5571846 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -15,6 +15,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/sort.h>
+#include <linux/kmemleak.h>
 
 #include "tracing_map.h"
 #include "trace.h"
@@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a)
 	for (i = 0; i < a->n_pages; i++) {
 		if (!a->pages[i])
 			break;
+		kmemleak_free(a->pages[i]);
 		free_page((unsigned long)a->pages[i]);
 	}
 
@@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts,
 		a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL);
 		if (!a->pages[i])
 			goto free;
+		kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL);
 	}
  out:
 	return a;