1 files changed, 42 insertions, 31 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a1ca4956ab5e..8c1b2d290718 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -423,7 +423,7 @@ struct ring_buffer_per_cpu {
         int                             cpu;
         struct ring_buffer              *buffer;
         spinlock_t                      reader_lock;    /* serialize readers */
-        raw_spinlock_t                  lock;
+        arch_spinlock_t                 lock;
         struct lock_class_key           lock_key;
         struct list_head                *pages;
         struct buffer_page              *head_page;     /* read from head */
@@ -464,6 +464,8 @@ struct ring_buffer_iter {
         struct ring_buffer_per_cpu      *cpu_buffer;
         unsigned long                   head;
         struct buffer_page              *head_page;
+        struct buffer_page              *cache_reader_page;
+        unsigned long                   cache_read;
         u64                             read_stamp;
 };
 
@@ -998,7 +1000,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
         cpu_buffer->buffer = buffer;
         spin_lock_init(&cpu_buffer->reader_lock);
         lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
-        cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+        cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
         bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
                             GFP_KERNEL, cpu_to_node(cpu));
@@ -1193,9 +1195,6 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
         struct list_head *p;
         unsigned i;
 
-        atomic_inc(&cpu_buffer->record_disabled);
-        synchronize_sched();
-
         spin_lock_irq(&cpu_buffer->reader_lock);
         rb_head_page_deactivate(cpu_buffer);
 
@@ -1211,12 +1210,9 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
                 return;
 
         rb_reset_cpu(cpu_buffer);
-        spin_unlock_irq(&cpu_buffer->reader_lock);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
-
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 static void
@@ -1227,9 +1223,6 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
         struct list_head *p;
         unsigned i;
 
-        atomic_inc(&cpu_buffer->record_disabled);
-        synchronize_sched();
-
         spin_lock_irq(&cpu_buffer->reader_lock);
         rb_head_page_deactivate(cpu_buffer);
 
@@ -1242,11 +1235,9 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
                 list_add_tail(&bpage->list, cpu_buffer->pages);
         }
         rb_reset_cpu(cpu_buffer);
-        spin_unlock_irq(&cpu_buffer->reader_lock);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 /**
@@ -1254,11 +1245,6 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
  * @buffer: the buffer to resize.
  * @size: the new size.
  *
- * The tracer is responsible for making sure that the buffer is
- * not being used while changing the size.
- * Note: We may be able to change the above requirement by using
- *  RCU synchronizations.
- *
  * Minimum size is 2 * BUF_PAGE_SIZE.
  *
  * Returns -1 on failure.
@@ -1290,6 +1276,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         if (size == buffer_size)
                 return size;
 
+        atomic_inc(&buffer->record_disabled);
+
+        /* Make sure all writers are done with this buffer. */
+        synchronize_sched();
+
         mutex_lock(&buffer->mutex);
         get_online_cpus();
 
@@ -1352,6 +1343,8 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
 
+        atomic_dec(&buffer->record_disabled);
+
         return size;
 
  free_pages:
@@ -1361,6 +1354,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
         }
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
+        atomic_dec(&buffer->record_disabled);
         return -ENOMEM;
 
         /*
@@ -1370,6 +1364,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
  out_fail:
         put_online_cpus();
         mutex_unlock(&buffer->mutex);
+        atomic_dec(&buffer->record_disabled);
         return -1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
@@ -2723,6 +2718,8 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
                 iter->read_stamp = cpu_buffer->read_stamp;
         else
                 iter->read_stamp = iter->head_page->page->time_stamp;
+        iter->cache_reader_page = cpu_buffer->reader_page;
+        iter->cache_read = cpu_buffer->read;
 }
 
 /**
@@ -2834,7 +2831,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         int ret;
 
         local_irq_save(flags);
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
 
  again:
         /*
@@ -2876,7 +2873,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
          * Splice the empty reader page into the list around the head.
          */
         reader = rb_set_head_page(cpu_buffer);
-        cpu_buffer->reader_page->list.next = reader->list.next;
+        cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
         cpu_buffer->reader_page->list.prev = reader->list.prev;
 
         /*
@@ -2913,7 +2910,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
          *
          * Now make the new head point back to the reader page.
          */
-        reader->list.next->prev = &cpu_buffer->reader_page->list;
+        rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
         rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
         /* Finally update the reader page to the new head */
@@ -2923,7 +2920,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
         goto again;
 
  out:
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
         local_irq_restore(flags);
 
         return reader;
@@ -3067,13 +3064,22 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         struct ring_buffer_event *event;
         int nr_loops = 0;
 
-        if (ring_buffer_iter_empty(iter))
-                return NULL;
-
         cpu_buffer = iter->cpu_buffer;
         buffer = cpu_buffer->buffer;
 
+        /*
+         * Check if someone performed a consuming read to
+         * the buffer. A consuming read invalidates the iterator
+         * and we need to reset the iterator in this case.
+         */
+        if (unlikely(iter->cache_read != cpu_buffer->read ||
+                     iter->cache_reader_page != cpu_buffer->reader_page))
+                rb_iter_reset(iter);
+
  again:
+        if (ring_buffer_iter_empty(iter))
+                return NULL;
+
         /*
          * We repeat when a timestamp is encountered.
          * We can get multiple timestamps by nested interrupts or also
@@ -3088,6 +3094,11 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
         if (rb_per_cpu_empty(cpu_buffer))
                 return NULL;
 
+        if (iter->head >= local_read(&iter->head_page->page->commit)) {
+                rb_inc_iter(iter);
+                goto again;
+        }
+
         event = rb_iter_head_event(iter);
 
         switch (event->type_len) {
@@ -3286,9 +3297,9 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
         synchronize_sched();
 
         spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
         rb_iter_reset(iter);
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
         return iter;
@@ -3408,11 +3419,11 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
         if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
                 goto out;
 
-        __raw_spin_lock(&cpu_buffer->lock);
+        arch_spin_lock(&cpu_buffer->lock);
 
         rb_reset_cpu(cpu_buffer);
 
-        __raw_spin_unlock(&cpu_buffer->lock);
+        arch_spin_unlock(&cpu_buffer->lock);
 
  out:
         spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);