4 files changed, 159 insertions, 124 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 041b91c2b..2df8e13a2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -415,7 +415,6 @@ struct rb_irq_work {
 	struct irq_work			work;
 	wait_queue_head_t		waiters;
 	wait_queue_head_t		full_waiters;
-	long				wait_index;
 	bool				waiters_pending;
 	bool				full_waiters_pending;
 	bool				wakeup_full;
@@ -832,8 +831,19 @@ static void rb_wake_up_waiters(struct irq_work *work)
 
 	wake_up_all(&rbwork->waiters);
 	if (rbwork->full_waiters_pending || rbwork->wakeup_full) {
+		/* Only cpu_buffer sets the above flags */
+		struct ring_buffer_per_cpu *cpu_buffer =
+			container_of(rbwork, struct ring_buffer_per_cpu, irq_work);
+
+		/* Called from interrupt context */
+		raw_spin_lock(&cpu_buffer->reader_lock);
 		rbwork->wakeup_full = false;
 		rbwork->full_waiters_pending = false;
+
+		/* Waking up all waiters, they will reset the shortest full */
+		cpu_buffer->shortest_full = 0;
+		raw_spin_unlock(&cpu_buffer->reader_lock);
+
 		wake_up_all(&rbwork->full_waiters);
 	}
 }
@@ -862,14 +872,41 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
 		rbwork = &cpu_buffer->irq_work;
 	}
 
-	rbwork->wait_index++;
-	/* make sure the waiters see the new index */
-	smp_wmb();
-
 	/* This can be called in any context */
 	irq_work_queue(&rbwork->work);
 }
 
+static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	bool ret = false;
+
+	/* Reads of all CPUs always waits for any data */
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		return !ring_buffer_empty(buffer);
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	if (!ring_buffer_empty_cpu(buffer, cpu)) {
+		unsigned long flags;
+		bool pagebusy;
+
+		if (!full)
+			return true;
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+		pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
+		ret = !pagebusy && full_hit(buffer, cpu, full);
+
+		if (!ret && (!cpu_buffer->shortest_full ||
+			     cpu_buffer->shortest_full > full)) {
+		    cpu_buffer->shortest_full = full;
+		}
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	}
+	return ret;
+}
+
 /**
  * ring_buffer_wait - wait for input to the ring buffer
  * @buffer: buffer to wait on
@@ -885,7 +922,6 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 	struct ring_buffer_per_cpu *cpu_buffer;
 	DEFINE_WAIT(wait);
 	struct rb_irq_work *work;
-	long wait_index;
 	int ret = 0;
 
 	/*
@@ -904,81 +940,54 @@ int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full)
 		work = &cpu_buffer->irq_work;
 	}
 
-	wait_index = READ_ONCE(work->wait_index);
-
-	while (true) {
-		if (full)
-			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
-		else
-			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
-
-		/*
-		 * The events can happen in critical sections where
-		 * checking a work queue can cause deadlocks.
-		 * After adding a task to the queue, this flag is set
-		 * only to notify events to try to wake up the queue
-		 * using irq_work.
-		 *
-		 * We don't clear it even if the buffer is no longer
-		 * empty. The flag only causes the next event to run
-		 * irq_work to do the work queue wake up. The worse
-		 * that can happen if we race with !trace_empty() is that
-		 * an event will cause an irq_work to try to wake up
-		 * an empty queue.
-		 *
-		 * There's no reason to protect this flag either, as
-		 * the work queue and irq_work logic will do the necessary
-		 * synchronization for the wake ups. The only thing
-		 * that is necessary is that the wake up happens after
-		 * a task has been queued. It's OK for spurious wake ups.
-		 */
-		if (full)
-			work->full_waiters_pending = true;
-		else
-			work->waiters_pending = true;
-
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-
-		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
-			break;
-
-		if (cpu != RING_BUFFER_ALL_CPUS &&
-		    !ring_buffer_empty_cpu(buffer, cpu)) {
-			unsigned long flags;
-			bool pagebusy;
-			bool done;
-
-			if (!full)
-				break;
-
-			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
-			done = !pagebusy && full_hit(buffer, cpu, full);
+	if (full)
+		prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
+	else
+		prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);
 
-			if (!cpu_buffer->shortest_full ||
-			    cpu_buffer->shortest_full > full)
-				cpu_buffer->shortest_full = full;
-			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
-			if (done)
-				break;
-		}
+	/*
+	 * The events can happen in critical sections where
+	 * checking a work queue can cause deadlocks.
+	 * After adding a task to the queue, this flag is set
+	 * only to notify events to try to wake up the queue
+	 * using irq_work.
+	 *
+	 * We don't clear it even if the buffer is no longer
+	 * empty. The flag only causes the next event to run
+	 * irq_work to do the work queue wake up. The worse
+	 * that can happen if we race with !trace_empty() is that
+	 * an event will cause an irq_work to try to wake up
+	 * an empty queue.
+	 *
+	 * There's no reason to protect this flag either, as
+	 * the work queue and irq_work logic will do the necessary
+	 * synchronization for the wake ups. The only thing
+	 * that is necessary is that the wake up happens after
+	 * a task has been queued. It's OK for spurious wake ups.
+	 */
+	if (full)
+		work->full_waiters_pending = true;
+	else
+		work->waiters_pending = true;
 
-		schedule();
+	if (rb_watermark_hit(buffer, cpu, full))
+		goto out;
 
-		/* Make sure to see the new wait index */
-		smp_rmb();
-		if (wait_index != work->wait_index)
-			break;
+	if (signal_pending(current)) {
+		ret = -EINTR;
+		goto out;
 	}
 
+	schedule();
+ out:
 	if (full)
 		finish_wait(&work->full_waiters, &wait);
 	else
 		finish_wait(&work->waiters, &wait);
 
+	if (!ret && !rb_watermark_hit(buffer, cpu, full) && signal_pending(current))
+		ret = -EINTR;
+
 	return ret;
 }
 
@@ -1001,30 +1010,51 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 			  struct file *filp, poll_table *poll_table, int full)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	struct rb_irq_work *work;
+	struct rb_irq_work *rbwork;
 
 	if (cpu == RING_BUFFER_ALL_CPUS) {
-		work = &buffer->irq_work;
+		rbwork = &buffer->irq_work;
 		full = 0;
 	} else {
 		if (!cpumask_test_cpu(cpu, buffer->cpumask))
-			return -EINVAL;
+			return EPOLLERR;
 
 		cpu_buffer = buffer->buffers[cpu];
-		work = &cpu_buffer->irq_work;
+		rbwork = &cpu_buffer->irq_work;
 	}
 
 	if (full) {
-		poll_wait(filp, &work->full_waiters, poll_table);
-		work->full_waiters_pending = true;
+		unsigned long flags;
+
+		poll_wait(filp, &rbwork->full_waiters, poll_table);
+
+		raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 		if (!cpu_buffer->shortest_full ||
 		    cpu_buffer->shortest_full > full)
 			cpu_buffer->shortest_full = full;
-	} else {
-		poll_wait(filp, &work->waiters, poll_table);
-		work->waiters_pending = true;
+		raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+		if (full_hit(buffer, cpu, full))
+			return EPOLLIN | EPOLLRDNORM;
+		/*
+		 * Only allow full_waiters_pending update to be seen after
+		 * the shortest_full is set. If the writer sees the
+		 * full_waiters_pending flag set, it will compare the
+		 * amount in the ring buffer to shortest_full. If the amount
+		 * in the ring buffer is greater than the shortest_full
+		 * percent, it will call the irq_work handler to wake up
+		 * this list. The irq_handler will reset shortest_full
+		 * back to zero. That's done under the reader_lock, but
+		 * the below smp_mb() makes sure that the update to
+		 * full_waiters_pending doesn't leak up into the above.
+		 */
+		smp_mb();
+		rbwork->full_waiters_pending = true;
+		return 0;
 	}
 
+	poll_wait(filp, &rbwork->waiters, poll_table);
+	rbwork->waiters_pending = true;
+
 	/*
 	 * There's a tight race between setting the waiters_pending and
 	 * checking if the ring buffer is empty.  Once the waiters_pending bit
@@ -1040,9 +1070,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu,
 	 */
 	smp_mb();
 
-	if (full)
-		return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0;
-
 	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
 	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
 		return EPOLLIN | EPOLLRDNORM;
@@ -4184,7 +4211,7 @@ int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
 	cpu_buffer = iter->cpu_buffer;
 	reader = cpu_buffer->reader_page;
 	head_page = cpu_buffer->head_page;
-	commit_page = cpu_buffer->commit_page;
+	commit_page = READ_ONCE(cpu_buffer->commit_page);
 	commit_ts = commit_page->page->time_stamp;
 
 	/*
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 548f694fc..22e1e5711 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
+#include <linux/kmemleak.h>
 #include <linux/poll.h>
 #include <linux/nmi.h>
 #include <linux/fs.h>
@@ -2239,7 +2240,7 @@ struct saved_cmdlines_buffer {
 	unsigned *map_cmdline_to_pid;
 	unsigned cmdline_num;
 	int cmdline_idx;
-	char *saved_cmdlines;
+	char saved_cmdlines[];
 };
 static struct saved_cmdlines_buffer *savedcmd;
 
@@ -2253,47 +2254,60 @@ static inline void set_cmdline(int idx, const char *cmdline)
 	strncpy(get_saved_cmdlines(idx), cmdline, TASK_COMM_LEN);
 }
 
-static int allocate_cmdlines_buffer(unsigned int val,
-				    struct saved_cmdlines_buffer *s)
+static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
 {
+	int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN);
+
+	kfree(s->map_cmdline_to_pid);
+	kmemleak_free(s);
+	free_pages((unsigned long)s, order);
+}
+
+static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val)
+{
+	struct saved_cmdlines_buffer *s;
+	struct page *page;
+	int orig_size, size;
+	int order;
+
+	/* Figure out how much is needed to hold the given number of cmdlines */
+	orig_size = sizeof(*s) + val * TASK_COMM_LEN;
+	order = get_order(orig_size);
+	size = 1 << (order + PAGE_SHIFT);
+	page = alloc_pages(GFP_KERNEL, order);
+	if (!page)
+		return NULL;
+
+	s = page_address(page);
+	kmemleak_alloc(s, size, 1, GFP_KERNEL);
+	memset(s, 0, sizeof(*s));
+
+	/* Round up to actual allocation */
+	val = (size - sizeof(*s)) / TASK_COMM_LEN;
+	s->cmdline_num = val;
+
 	s->map_cmdline_to_pid = kmalloc_array(val,
 					      sizeof(*s->map_cmdline_to_pid),
 					      GFP_KERNEL);
-	if (!s->map_cmdline_to_pid)
-		return -ENOMEM;
-
-	s->saved_cmdlines = kmalloc_array(TASK_COMM_LEN, val, GFP_KERNEL);
-	if (!s->saved_cmdlines) {
-		kfree(s->map_cmdline_to_pid);
-		return -ENOMEM;
+	if (!s->map_cmdline_to_pid) {
+		free_saved_cmdlines_buffer(s);
+		return NULL;
 	}
 
 	s->cmdline_idx = 0;
-	s->cmdline_num = val;
 	memset(&s->map_pid_to_cmdline, NO_CMDLINE_MAP,
 	       sizeof(s->map_pid_to_cmdline));
 	memset(s->map_cmdline_to_pid, NO_CMDLINE_MAP,
 	       val * sizeof(*s->map_cmdline_to_pid));
 
-	return 0;
+	return s;
 }
 
 static int trace_create_savedcmd(void)
 {
-	int ret;
-
-	savedcmd = kmalloc(sizeof(*savedcmd), GFP_KERNEL);
-	if (!savedcmd)
-		return -ENOMEM;
+	savedcmd = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT);
 
-	ret = allocate_cmdlines_buffer(SAVED_CMDLINES_DEFAULT, savedcmd);
-	if (ret < 0) {
-		kfree(savedcmd);
-		savedcmd = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
+	return savedcmd ? 0 : -ENOMEM;
 }
 
 int is_tracing_stopped(void)
@@ -5603,26 +5617,14 @@ tracing_saved_cmdlines_size_read(struct file *filp, char __user *ubuf,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
-static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s)
-{
-	kfree(s->saved_cmdlines);
-	kfree(s->map_cmdline_to_pid);
-	kfree(s);
-}
-
 static int tracing_resize_saved_cmdlines(unsigned int val)
 {
 	struct saved_cmdlines_buffer *s, *savedcmd_temp;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = allocate_cmdlines_buffer(val);
 	if (!s)
 		return -ENOMEM;
 
-	if (allocate_cmdlines_buffer(val, s) < 0) {
-		kfree(s);
-		return -ENOMEM;
-	}
-
 	preempt_disable();
 	arch_spin_lock(&trace_cmdline_lock);
 	savedcmd_temp = savedcmd;
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 643e0b199..eb81ad523 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -400,7 +400,8 @@ void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
 	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 
 	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		      "perf buffer not large enough"))
+		      "perf buffer not large enough, wanted %d, have %d",
+		      size, PERF_MAX_TRACE_SIZE))
 		return NULL;
 
 	*rctxp = rctx = perf_swevent_get_recursion_context();
diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
index 51a9d1185..d47641f97 100644
--- a/kernel/trace/tracing_map.c
+++ b/kernel/trace/tracing_map.c
@@ -574,7 +574,12 @@ __tracing_map_insert(struct tracing_map *map, void *key, bool lookup_only)
 				}
 
 				memcpy(elt->key, key, map->key_size);
-				entry->val = elt;
+				/*
+				 * Ensure the initialization is visible and
+				 * publish the elt.
+				 */
+				smp_wmb();
+				WRITE_ONCE(entry->val, elt);
 				atomic64_inc(&map->hits);
 
 				return entry->val;