1 files changed, 80 insertions, 57 deletions

diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 5dd017fea6f5..41ca394feb22 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -14,12 +14,14 @@
 #include <linux/module.h>
 #include <linux/percpu.h>
 #include <linux/mutex.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/list.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 
+#include <asm/local.h>
 #include "trace.h"
 
 /*
@@ -206,6 +208,14 @@ EXPORT_SYMBOL_GPL(tracing_is_on);
 #define RB_MAX_SMALL_DATA       (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
 #define RB_EVNT_MIN_SIZE        8U      /* two 32bit words */
 
+#if !defined(CONFIG_64BIT) || defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+# define RB_FORCE_8BYTE_ALIGNMENT       0
+# define RB_ARCH_ALIGNMENT              RB_ALIGNMENT
+#else
+# define RB_FORCE_8BYTE_ALIGNMENT       1
+# define RB_ARCH_ALIGNMENT              8U
+#endif
+
 /* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
 #define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX
 
@@ -397,18 +407,21 @@ int ring_buffer_print_page_header(struct trace_seq *s)
         int ret;
 
         ret = trace_seq_printf(s, "\tfield: u64 timestamp;\t"
-                               "offset:0;\tsize:%u;\n",
-                               (unsigned int)sizeof(field.time_stamp));
+                               "offset:0;\tsize:%u;\tsigned:%u;\n",
+                               (unsigned int)sizeof(field.time_stamp),
+                               (unsigned int)is_signed_type(u64));
 
         ret = trace_seq_printf(s, "\tfield: local_t commit;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), commit),
-                               (unsigned int)sizeof(field.commit));
+                               (unsigned int)sizeof(field.commit),
+                               (unsigned int)is_signed_type(long));
 
         ret = trace_seq_printf(s, "\tfield: char data;\t"
-                               "offset:%u;\tsize:%u;\n",
+                               "offset:%u;\tsize:%u;\tsigned:%u;\n",
                                (unsigned int)offsetof(typeof(field), data),
-                               (unsigned int)BUF_PAGE_SIZE);
+                               (unsigned int)BUF_PAGE_SIZE,
+                               (unsigned int)is_signed_type(char));
 
         return ret;
 }
@@ -420,7 +433,7 @@ 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 */
@@ -461,6 +474,8 @@ 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;
 };
 
@@ -995,7 +1010,7 @@ 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));
@@ -1190,30 +1205,25 @@ 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);
 
         for (i = 0; i < nr_pages; i++) {
                 if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-                        return;
+                        goto out;
                 p = cpu_buffer->pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
                 free_buffer_page(bpage);
         }
         if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-                return;
+                goto out;
 
         rb_reset_cpu(cpu_buffer);
-        spin_unlock_irq(&cpu_buffer->reader_lock);
-
         rb_check_pages(cpu_buffer);
 
-        atomic_dec(&cpu_buffer->record_disabled);
-
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 static void
@@ -1224,26 +1234,22 @@ 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);
 
         for (i = 0; i < nr_pages; i++) {
                 if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-                        return;
+                        goto out;
                 p = pages->next;
                 bpage = list_entry(p, struct buffer_page, list);
                 list_del_init(&bpage->list);
                 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);
+out:
+        spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 /**
@@ -1251,11 +1257,6 @@ 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.
@@ -1287,6 +1288,11 @@ 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();
 
@@ -1349,6 +1355,8 @@ 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:
@@ -1358,6 +1366,7 @@ 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;
 
         /*
@@ -1367,6 +1376,7 @@ 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);
@@ -1548,7 +1558,7 @@ rb_update_event(struct ring_buffer_event *event,
 
         case 0:
                 length -= RB_EVNT_HDR_SIZE;
-                if (length > RB_MAX_SMALL_DATA)
+                if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
                         event->array[0] = length;
                 else
                         event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
@@ -1723,11 +1733,11 @@ static unsigned rb_calculate_event_length(unsigned length)
         if (!length)
                 length = 1;
 
-        if (length > RB_MAX_SMALL_DATA)
+        if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
                 length += sizeof(event.array[0]);
 
         length += RB_EVNT_HDR_SIZE;
-        length = ALIGN(length, RB_ALIGNMENT);
+        length = ALIGN(length, RB_ARCH_ALIGNMENT);
 
         return length;
 }
@@ -1787,9 +1797,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 static struct ring_buffer_event *
 rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
              unsigned long length, unsigned long tail,
-             struct buffer_page *commit_page,
              struct buffer_page *tail_page, u64 *ts)
 {
+        struct buffer_page *commit_page = cpu_buffer->commit_page;
         struct ring_buffer *buffer = cpu_buffer->buffer;
         struct buffer_page *next_page;
         int ret;
@@ -1892,13 +1902,10 @@ static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
                   unsigned type, unsigned long length, u64 *ts)
 {
-        struct buffer_page *tail_page, *commit_page;
+        struct buffer_page *tail_page;
         struct ring_buffer_event *event;
         unsigned long tail, write;
 
-        commit_page = cpu_buffer->commit_page;
-        /* we just need to protect against interrupts */
-        barrier();
         tail_page = cpu_buffer->tail_page;
         write = local_add_return(length, &tail_page->write);
 
@@ -1909,7 +1916,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
         /* See if we shot pass the end of this buffer page */
         if (write > BUF_PAGE_SIZE)
                 return rb_move_tail(cpu_buffer, length, tail,
-                                    commit_page, tail_page, ts);
+                                    tail_page, ts);
 
         /* We reserved something on the buffer */
 
@@ -2237,12 +2244,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return NULL;
 
-        if (atomic_read(&buffer->record_disabled))
-                return NULL;
-
         /* If we are tracing schedule, we don't want to recurse */
         resched = ftrace_preempt_disable();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out_nocheck;
+
         if (trace_recursive_lock())
                 goto out_nocheck;
 
@@ -2474,11 +2481,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
         if (ring_buffer_flags != RB_BUFFERS_ON)
                 return -EBUSY;
 
-        if (atomic_read(&buffer->record_disabled))
-                return -EBUSY;
-
         resched = ftrace_preempt_disable();
 
+        if (atomic_read(&buffer->record_disabled))
+                goto out;
+
         cpu = raw_smp_processor_id();
 
         if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -2546,7 +2553,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable);
  * @buffer: The ring buffer to enable writes
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable(struct ring_buffer *buffer)
 {
@@ -2582,7 +2589,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);
  * @cpu: The CPU to enable.
  *
  * Note, multiple disables will need the same number of enables
- * to truely enable the writing (much like preempt_disable).
+ * to truly enable the writing (much like preempt_disable).
  */
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
 {
@@ -2723,6 +2730,8 @@ 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 +2843,7 @@ 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 +2885,7 @@ 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 +2922,7 @@ 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 +2932,7 @@ 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 +3076,22 @@ 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 +3106,11 @@ 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 +3309,9 @@ 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 +3431,11 @@ 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);