tracing: Updates for 3.5

index 48ef496..d1b3469 100644
@@ -3875,14 +3875,14 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	struct print_entry *entry;
 	unsigned long irq_flags;
 	struct page *pages[2];
+	void *map_page[2];
 	int nr_pages = 1;
 	ssize_t written;
-	void *page1;
-	void *page2;
 	int offset;
 	int size;
 	int len;
 	int ret;
+	int i;
 
 	if (tracing_disabled)
 		return -EINVAL;

@@ -3921,9 +3921,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 		goto out;
 	}
 
-	page1 = kmap_atomic(pages[0]);
-	if (nr_pages == 2)
-		page2 = kmap_atomic(pages[1]);
+	for (i = 0; i < nr_pages; i++)
+		map_page[i] = kmap_atomic(pages[i]);
 
 	local_save_flags(irq_flags);
 	size = sizeof(*entry) + cnt + 2; /* possible \n added */

@@ -3941,10 +3940,10 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 
 	if (nr_pages == 2) {
 		len = PAGE_SIZE - offset;
-		memcpy(&entry->buf, page1 + offset, len);
-		memcpy(&entry->buf[len], page2, cnt - len);
+		memcpy(&entry->buf, map_page[0] + offset, len);
+		memcpy(&entry->buf[len], map_page[1], cnt - len);
 	} else
-		memcpy(&entry->buf, page1 + offset, cnt);
+		memcpy(&entry->buf, map_page[0] + offset, cnt);
 
 	if (entry->buf[cnt - 1] != '\n') {
 		entry->buf[cnt] = '\n';

@@ -3959,11 +3958,10 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	*fpos += written;
 
  out_unlock:
-	if (nr_pages == 2)
-		kunmap_atomic(page2);
-	kunmap_atomic(page1);
-	while (nr_pages > 0)
-		put_page(pages[--nr_pages]);
+	for (i = 0; i < nr_pages; i++){
+		kunmap_atomic(map_page[i]);
+		put_page(pages[i]);
+	}
  out:
 	return written;
 }

index 2d5eb33..27ac37e 100644
@@ -23,6 +23,8 @@
 #include <asm/local.h>
 #include "trace.h"
 
+static void update_pages_handler(struct work_struct *work);
+
 /*
  * The ring buffer header is special. We must manually up keep it.
  */

@@ -470,12 +472,15 @@ struct ring_buffer_per_cpu {
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
 	int				nr_pages_to_update;
 	struct list_head		new_pages; /* new pages to add */
+	struct work_struct		update_pages_work;
+	struct completion		update_completion;
 };
 
 struct ring_buffer {
 	unsigned			flags;
 	int				cpus;
 	atomic_t			record_disabled;
+	atomic_t			resize_disabled;
 	cpumask_var_t			cpumask;
 
 	struct lock_class_key		*reader_lock_key;

@@ -1048,6 +1053,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 	raw_spin_lock_init(&cpu_buffer->reader_lock);
 	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
+	INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler);
+	init_completion(&cpu_buffer->update_completion);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));

@@ -1235,32 +1242,123 @@ void ring_buffer_set_clock(struct ring_buffer *buffer,
 
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
+{
+	return local_read(&bpage->entries) & RB_WRITE_MASK;
+}
+
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
+{
+	return local_read(&bpage->write) & RB_WRITE_MASK;
+}
+
 static void
-rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
 {
-	struct buffer_page *bpage;
-	struct list_head *p;
-	unsigned i;
+	struct list_head *tail_page, *to_remove, *next_page;
+	struct buffer_page *to_remove_page, *tmp_iter_page;
+	struct buffer_page *last_page, *first_page;
+	unsigned int nr_removed;
+	unsigned long head_bit;
+	int page_entries;
+
+	head_bit = 0;
 
 	raw_spin_lock_irq(&cpu_buffer->reader_lock);
-	rb_head_page_deactivate(cpu_buffer);
+	atomic_inc(&cpu_buffer->record_disabled);
+	/*
+	 * We don't race with the readers since we have acquired the reader
+	 * lock. We also don't race with writers after disabling recording.
+	 * This makes it easy to figure out the first and the last page to be
+	 * removed from the list. We unlink all the pages in between including
+	 * the first and last pages. This is done in a busy loop so that we
+	 * lose the least number of traces.
+	 * The pages are freed after we restart recording and unlock readers.
+	 */
+	tail_page = &cpu_buffer->tail_page->list;
 
-	for (i = 0; i < nr_pages; i++) {
-		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-			goto out;
-		p = cpu_buffer->pages->next;
-		bpage = list_entry(p, struct buffer_page, list);
-		list_del_init(&bpage->list);
-		free_buffer_page(bpage);
+	/*
+	 * tail page might be on reader page, we remove the next page
+	 * from the ring buffer
+	 */
+	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
+		tail_page = rb_list_head(tail_page->next);
+	to_remove = tail_page;
+
+	/* start of pages to remove */
+	first_page = list_entry(rb_list_head(to_remove->next),
+				struct buffer_page, list);
+
+	for (nr_removed = 0; nr_removed < nr_pages; nr_removed++) {
+		to_remove = rb_list_head(to_remove)->next;
+		head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD;
 	}
-	if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-		goto out;
 
-	rb_reset_cpu(cpu_buffer);
-	rb_check_pages(cpu_buffer);
+	next_page = rb_list_head(to_remove)->next;
 
-out:
+	/*
+	 * Now we remove all pages between tail_page and next_page.
+	 * Make sure that we have head_bit value preserved for the
+	 * next page
+	 */
+	tail_page->next = (struct list_head *)((unsigned long)next_page |
+						head_bit);
+	next_page = rb_list_head(next_page);
+	next_page->prev = tail_page;
+
+	/* make sure pages points to a valid page in the ring buffer */
+	cpu_buffer->pages = next_page;
+
+	/* update head page */
+	if (head_bit)
+		cpu_buffer->head_page = list_entry(next_page,
+						struct buffer_page, list);
+
+	/*
+	 * change read pointer to make sure any read iterators reset
+	 * themselves
+	 */
+	cpu_buffer->read = 0;
+
+	/* pages are removed, resume tracing and then free the pages */
+	atomic_dec(&cpu_buffer->record_disabled);
 	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+
+	RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages));
+
+	/* last buffer page to remove */
+	last_page = list_entry(rb_list_head(to_remove), struct buffer_page,
+				list);
+	tmp_iter_page = first_page;
+
+	do {
+		to_remove_page = tmp_iter_page;
+		rb_inc_page(cpu_buffer, &tmp_iter_page);
+
+		/* update the counters */
+		page_entries = rb_page_entries(to_remove_page);
+		if (page_entries) {
+			/*
+			 * If something was added to this page, it was full
+			 * since it is not the tail page. So we deduct the
+			 * bytes consumed in ring buffer from here.
+			 * No need to update overruns, since this page is
+			 * deleted from ring buffer and its entries are
+			 * already accounted for.
+			 */
+			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
+		}
+
+		/*
+		 * We have already removed references to this list item, just
+		 * free up the buffer_page and its page
+		 */
+		free_buffer_page(to_remove_page);
+		nr_removed--;
+
+	} while (to_remove_page != last_page);
+
+	RB_WARN_ON(cpu_buffer, nr_removed);
 }
 
 static void

@@ -1272,6 +1370,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	unsigned i;
 
 	raw_spin_lock_irq(&cpu_buffer->reader_lock);
+	/* stop the writers while inserting pages */
+	atomic_inc(&cpu_buffer->record_disabled);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {

@@ -1286,19 +1386,27 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_check_pages(cpu_buffer);
 
 out:
+	atomic_dec(&cpu_buffer->record_disabled);
 	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
-static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer)
+static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	if (cpu_buffer->nr_pages_to_update > 0)
 		rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages,
 				cpu_buffer->nr_pages_to_update);
 	else
 		rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update);
+
 	cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update;
-	/* reset this value */
-	cpu_buffer->nr_pages_to_update = 0;
+}
+
+static void update_pages_handler(struct work_struct *work)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = container_of(work,
+			struct ring_buffer_per_cpu, update_pages_work);
+	rb_update_pages(cpu_buffer);
+	complete(&cpu_buffer->update_completion);
 }
 
 /**

@@ -1308,14 +1416,14 @@ static void update_pages_handler(struct ring_buffer_per_cpu *cpu_buffer)
  *
  * Minimum size is 2 * BUF_PAGE_SIZE.
  *
- * Returns -1 on failure.
+ * Returns 0 on success and < 0 on failure.
  */
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			int cpu_id)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned nr_pages;
-	int cpu;
+	int cpu, err = 0;
 
 	/*
 	 * Always succeed at resizing a non-existent buffer:

@@ -1330,15 +1438,18 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	if (size < BUF_PAGE_SIZE * 2)
 		size = BUF_PAGE_SIZE * 2;
 
-	atomic_inc(&buffer->record_disabled);
+	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
-	/* Make sure all writers are done with this buffer. */
-	synchronize_sched();
+	/*
+	 * Don't succeed if resizing is disabled, as a reader might be
+	 * manipulating the ring buffer and is expecting a sane state while
+	 * this is true.
+	 */
+	if (atomic_read(&buffer->resize_disabled))
+		return -EBUSY;
 
+	/* prevent another thread from changing buffer sizes */
 	mutex_lock(&buffer->mutex);
-	get_online_cpus();
-
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
 	if (cpu_id == RING_BUFFER_ALL_CPUS) {
 		/* calculate the pages to update */

@@ -1347,33 +1458,67 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 
 			cpu_buffer->nr_pages_to_update = nr_pages -
 							cpu_buffer->nr_pages;
-
 			/*
 			 * nothing more to do for removing pages or no update
 			 */
 			if (cpu_buffer->nr_pages_to_update <= 0)
 				continue;
-
 			/*
 			 * to add pages, make sure all new pages can be
 			 * allocated without receiving ENOMEM
 			 */
 			INIT_LIST_HEAD(&cpu_buffer->new_pages);
 			if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
-						&cpu_buffer->new_pages, cpu))
+						&cpu_buffer->new_pages, cpu)) {
 				/* not enough memory for new pages */
-				goto no_mem;
+				err = -ENOMEM;
+				goto out_err;
+			}
+		}
+
+		get_online_cpus();
+		/*
+		 * Fire off all the required work handlers
+		 * Look out for offline CPUs
+		 */
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
+			if (!cpu_buffer->nr_pages_to_update ||
+			    !cpu_online(cpu))
+				continue;
+
+			schedule_work_on(cpu, &cpu_buffer->update_pages_work);
+		}
+		/*
+		 * This loop is for the CPUs that are not online.
+		 * We can't schedule anything on them, but it's not necessary
+		 * since we can change their buffer sizes without any race.
+		 */
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
+			if (!cpu_buffer->nr_pages_to_update ||
+			    cpu_online(cpu))
+				continue;
+
+			rb_update_pages(cpu_buffer);
 		}
 
 		/* wait for all the updates to complete */
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
-			if (cpu_buffer->nr_pages_to_update) {
-				update_pages_handler(cpu_buffer);
-			}
+			if (!cpu_buffer->nr_pages_to_update ||
+			    !cpu_online(cpu))
+				continue;
+
+			wait_for_completion(&cpu_buffer->update_completion);
+			/* reset this value */
+			cpu_buffer->nr_pages_to_update = 0;
 		}
+
+		put_online_cpus();
 	} else {
 		cpu_buffer = buffer->buffers[cpu_id];
+
 		if (nr_pages == cpu_buffer->nr_pages)
 			goto out;
 

@@ -1383,38 +1528,47 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 		INIT_LIST_HEAD(&cpu_buffer->new_pages);
 		if (cpu_buffer->nr_pages_to_update > 0 &&
 			__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
-						&cpu_buffer->new_pages, cpu_id))
-			goto no_mem;
+					    &cpu_buffer->new_pages, cpu_id)) {
+			err = -ENOMEM;
+			goto out_err;
+		}
 
-		update_pages_handler(cpu_buffer);
+		get_online_cpus();
+
+		if (cpu_online(cpu_id)) {
+			schedule_work_on(cpu_id,
+					 &cpu_buffer->update_pages_work);
+			wait_for_completion(&cpu_buffer->update_completion);
+		} else
+			rb_update_pages(cpu_buffer);
+
+		put_online_cpus();
+		/* reset this value */
+		cpu_buffer->nr_pages_to_update = 0;
 	}
 
  out:
-	put_online_cpus();
 	mutex_unlock(&buffer->mutex);
-
-	atomic_dec(&buffer->record_disabled);
-
 	return size;
 
- no_mem:
+ out_err:
 	for_each_buffer_cpu(buffer, cpu) {
 		struct buffer_page *bpage, *tmp;
+
 		cpu_buffer = buffer->buffers[cpu];
-		/* reset this number regardless */
 		cpu_buffer->nr_pages_to_update = 0;
+
 		if (list_empty(&cpu_buffer->new_pages))
 			continue;
+
 		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
 					list) {
 			list_del_init(&bpage->list);
 			free_buffer_page(bpage);
 		}
 	}
-	put_online_cpus();
 	mutex_unlock(&buffer->mutex);
-	atomic_dec(&buffer->record_disabled);
-	return -ENOMEM;
+	return err;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 

@@ -1453,21 +1607,11 @@ rb_iter_head_event(struct ring_buffer_iter *iter)
 	return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned long rb_page_write(struct buffer_page *bpage)
-{
-	return local_read(&bpage->write) & RB_WRITE_MASK;
-}
-
 static inline unsigned rb_page_commit(struct buffer_page *bpage)
 {
 	return local_read(&bpage->page->commit);
 }
 
-static inline unsigned long rb_page_entries(struct buffer_page *bpage)
-{
-	return local_read(&bpage->entries) & RB_WRITE_MASK;
-}
-
 /* Size is determined by what has been committed */
 static inline unsigned rb_page_size(struct buffer_page *bpage)
 {

@@ -3492,6 +3636,7 @@ ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
 
 	iter->cpu_buffer = cpu_buffer;
 
+	atomic_inc(&buffer->resize_disabled);
 	atomic_inc(&cpu_buffer->record_disabled);
 
 	return iter;

@@ -3555,6 +3700,7 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
 	atomic_dec(&cpu_buffer->record_disabled);
+	atomic_dec(&cpu_buffer->buffer->resize_disabled);
 	kfree(iter);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_finish);

@@ -3662,8 +3808,12 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
+	atomic_inc(&buffer->resize_disabled);
 	atomic_inc(&cpu_buffer->record_disabled);
 
+	/* Make sure all commits have finished */
+	synchronize_sched();
+
 	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))

@@ -3679,6 +3829,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->record_disabled);
+	atomic_dec(&buffer->resize_disabled);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);
 

index d1b3469..dfbd86c 100644
@@ -3076,20 +3076,10 @@ static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
 
 static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
 {
-	int cpu, ret = size;
+	int ret = size;
 
 	mutex_lock(&trace_types_lock);
 
-	tracing_stop();
-
-	/* disable all cpu buffers */
-	for_each_tracing_cpu(cpu) {
-		if (global_trace.data[cpu])
-			atomic_inc(&global_trace.data[cpu]->disabled);
-		if (max_tr.data[cpu])
-			atomic_inc(&max_tr.data[cpu]->disabled);
-	}
-
 	if (cpu_id != RING_BUFFER_ALL_CPUS) {
 		/* make sure, this cpu is enabled in the mask */
 		if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) {

@@ -3103,14 +3093,6 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size, int cpu_id)
 		ret = -ENOMEM;
 
 out:
-	for_each_tracing_cpu(cpu) {
-		if (global_trace.data[cpu])
-			atomic_dec(&global_trace.data[cpu]->disabled);
-		if (max_tr.data[cpu])
-			atomic_dec(&max_tr.data[cpu]->disabled);
-	}
-
-	tracing_start();
 	mutex_unlock(&trace_types_lock);
 
 	return ret;

index 27ac37e..d673ef0 100644
@@ -1252,7 +1252,7 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
 	return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
-static void
+static int
 rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
 {
 	struct list_head *tail_page, *to_remove, *next_page;

@@ -1359,46 +1359,97 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
 	} while (to_remove_page != last_page);
 
 	RB_WARN_ON(cpu_buffer, nr_removed);
+
+	return nr_removed == 0;
 }
 
-static void
-rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
-		struct list_head *pages, unsigned nr_pages)
+static int
+rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct buffer_page *bpage;
-	struct list_head *p;
-	unsigned i;
+	struct list_head *pages = &cpu_buffer->new_pages;
+	int retries, success;
 
 	raw_spin_lock_irq(&cpu_buffer->reader_lock);
-	/* stop the writers while inserting pages */
-	atomic_inc(&cpu_buffer->record_disabled);
-	rb_head_page_deactivate(cpu_buffer);
+	/*
+	 * We are holding the reader lock, so the reader page won't be swapped
+	 * in the ring buffer. Now we are racing with the writer trying to
+	 * move head page and the tail page.
+	 * We are going to adapt the reader page update process where:
+	 * 1. We first splice the start and end of list of new pages between
+	 *    the head page and its previous page.
+	 * 2. We cmpxchg the prev_page->next to point from head page to the
+	 *    start of new pages list.
+	 * 3. Finally, we update the head->prev to the end of new list.
+	 *
+	 * We will try this process 10 times, to make sure that we don't keep
+	 * spinning.
+	 */
+	retries = 10;
+	success = 0;
+	while (retries--) {
+		struct list_head *head_page, *prev_page, *r;
+		struct list_head *last_page, *first_page;
+		struct list_head *head_page_with_bit;
 
-	for (i = 0; i < nr_pages; i++) {
-		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-			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);
+		head_page = &rb_set_head_page(cpu_buffer)->list;
+		prev_page = head_page->prev;
+
+		first_page = pages->next;
+		last_page  = pages->prev;
+
+		head_page_with_bit = (struct list_head *)
+				     ((unsigned long)head_page | RB_PAGE_HEAD);
+
+		last_page->next = head_page_with_bit;
+		first_page->prev = prev_page;
+
+		r = cmpxchg(&prev_page->next, head_page_with_bit, first_page);
+
+		if (r == head_page_with_bit) {
+			/*
+			 * yay, we replaced the page pointer to our new list,
+			 * now, we just have to update to head page's prev
+			 * pointer to point to end of list
+			 */
+			head_page->prev = last_page;
+			success = 1;
+			break;
+		}
 	}
-	rb_reset_cpu(cpu_buffer);
-	rb_check_pages(cpu_buffer);
 
-out:
-	atomic_dec(&cpu_buffer->record_disabled);
+	if (success)
+		INIT_LIST_HEAD(pages);
+	/*
+	 * If we weren't successful in adding in new pages, warn and stop
+	 * tracing
+	 */
+	RB_WARN_ON(cpu_buffer, !success);
 	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+
+	/* free pages if they weren't inserted */
+	if (!success) {
+		struct buffer_page *bpage, *tmp;
+		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
+					 list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+	}
+	return success;
 }
 
 static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	int success;
+
 	if (cpu_buffer->nr_pages_to_update > 0)
-		rb_insert_pages(cpu_buffer, &cpu_buffer->new_pages,
-				cpu_buffer->nr_pages_to_update);
+		success = rb_insert_pages(cpu_buffer);
 	else
-		rb_remove_pages(cpu_buffer, -cpu_buffer->nr_pages_to_update);
+		success = rb_remove_pages(cpu_buffer,
+					-cpu_buffer->nr_pages_to_update);
 
-	cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update;
+	if (success)
+		cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update;
 }
 
 static void update_pages_handler(struct work_struct *work)

@@ -3772,6 +3823,7 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->commit_page = cpu_buffer->head_page;
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	INIT_LIST_HEAD(&cpu_buffer->new_pages);
 	local_set(&cpu_buffer->reader_page->write, 0);
 	local_set(&cpu_buffer->reader_page->entries, 0);
 	local_set(&cpu_buffer->reader_page->page->commit, 0);

index d673ef0..e0573c5 100644
@@ -1599,6 +1599,29 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	}
 
  out:
+	/*
+	 * The ring buffer resize can happen with the ring buffer
+	 * enabled, so that the update disturbs the tracing as little
+	 * as possible. But if the buffer is disabled, we do not need
+	 * to worry about that, and we can take the time to verify
+	 * that the buffer is not corrupt.
+	 */
+	if (atomic_read(&buffer->record_disabled)) {
+		atomic_inc(&buffer->record_disabled);
+		/*
+		 * Even though the buffer was disabled, we must make sure
+		 * that it is truly disabled before calling rb_check_pages.
+		 * There could have been a race between checking
+		 * record_disable and incrementing it.
+		 */
+		synchronize_sched();
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
+			rb_check_pages(cpu_buffer);
+		}
+		atomic_dec(&buffer->record_disabled);
+	}
+
 	mutex_unlock(&buffer->mutex);
 	return size;
 

@@ -3750,6 +3773,12 @@ ring_buffer_read_finish(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
+	/*
+	 * Ring buffer is disabled from recording, here's a good place
+	 * to check the integrity of the ring buffer. 
+	 */
+	rb_check_pages(cpu_buffer);
+
 	atomic_dec(&cpu_buffer->record_disabled);
 	atomic_dec(&cpu_buffer->buffer->resize_disabled);
 	kfree(iter);

index e0573c5..68388f8 100644
@@ -945,6 +945,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	/* Reset the head page if it exists */
+	if (cpu_buffer->head_page)
+		rb_set_head_page(cpu_buffer);
+
 	rb_head_page_deactivate(cpu_buffer);
 
 	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))

index dfbd86c..0ed4df0 100644
@@ -4474,6 +4474,9 @@ static void tracing_init_debugfs_percpu(long cpu)
 	struct dentry *d_cpu;
 	char cpu_dir[30]; /* 30 characters should be more than enough */
 
+	if (!d_percpu)
+		return;
+
 	snprintf(cpu_dir, 30, "cpu%ld", cpu);
 	d_cpu = debugfs_create_dir(cpu_dir, d_percpu);
 	if (!d_cpu) {

index 0ed4df0..08a08ba 100644
@@ -2669,10 +2669,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 		if (cpumask_test_cpu(cpu, tracing_cpumask) &&
 				!cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_inc(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_disable_cpu(global_trace.buffer, cpu);
 		}
 		if (!cpumask_test_cpu(cpu, tracing_cpumask) &&
 				cpumask_test_cpu(cpu, tracing_cpumask_new)) {
 			atomic_dec(&global_trace.data[cpu]->disabled);
+			ring_buffer_record_enable_cpu(global_trace.buffer, cpu);
 		}
 	}
 	arch_spin_unlock(&ftrace_max_lock);

index 8aeadf6..4e2e1cc 100644
@@ -486,8 +486,8 @@
 	CPU_DISCARD(init.data)						\
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
-	*(.init.rodata)							\
 	MCOUNT_REC()							\
+	*(.init.rodata)							\
 	FTRACE_EVENTS()							\
 	TRACE_SYSCALLS()						\
 	DEV_DISCARD(init.rodata)					\

index cf81f27..53ed01e 100644
@@ -3666,15 +3666,27 @@ static __init int ftrace_init_dyn_debugfs(struct dentry *d_tracer)
 	return 0;
 }
 
-static void ftrace_swap_recs(void *a, void *b, int size)
+static int ftrace_cmp_ips(const void *a, const void *b)
 {
-	struct dyn_ftrace *reca = a;
-	struct dyn_ftrace *recb = b;
-	struct dyn_ftrace t;
+	const unsigned long *ipa = a;
+	const unsigned long *ipb = b;
 
-	t = *reca;
-	*reca = *recb;
-	*recb = t;
+	if (*ipa > *ipb)
+		return 1;
+	if (*ipa < *ipb)
+		return -1;
+	return 0;
+}
+
+static void ftrace_swap_ips(void *a, void *b, int size)
+{
+	unsigned long *ipa = a;
+	unsigned long *ipb = b;
+	unsigned long t;
+
+	t = *ipa;
+	*ipa = *ipb;
+	*ipb = t;
 }
 
 static int ftrace_process_locs(struct module *mod,

@@ -3693,6 +3705,9 @@ static int ftrace_process_locs(struct module *mod,
 	if (!count)
 		return 0;
 
+	sort(start, count, sizeof(*start),
+	     ftrace_cmp_ips, ftrace_swap_ips);
+
 	pg = ftrace_allocate_pages(count);
 	if (!pg)
 		return -ENOMEM;

@@ -3740,11 +3755,6 @@ static int ftrace_process_locs(struct module *mod,
 	/* These new locations need to be initialized */
 	ftrace_new_pgs = pg;
 
-	/* Make each individual set of pages sorted by ips */
-	for (; pg; pg = pg->next)
-		sort(pg->records, pg->index, sizeof(struct dyn_ftrace),
-		     ftrace_cmp_recs, ftrace_swap_recs);
-
 	/*
 	 * We only need to disable interrupts on start up
 	 * because we are modifying code that an interrupt

index 53ed01e..e10f9e5 100644
@@ -1520,35 +1520,6 @@ static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
 	__ftrace_hash_rec_update(ops, filter_hash, 1);
 }
 
-static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
-{
-	if (ftrace_pages->index == ftrace_pages->size) {
-		/* We should have allocated enough */
-		if (WARN_ON(!ftrace_pages->next))
-			return NULL;
-		ftrace_pages = ftrace_pages->next;
-	}
-
-	return &ftrace_pages->records[ftrace_pages->index++];
-}
-
-static struct dyn_ftrace *
-ftrace_record_ip(unsigned long ip)
-{
-	struct dyn_ftrace *rec;
-
-	if (ftrace_disabled)
-		return NULL;
-
-	rec = ftrace_alloc_dyn_node(ip);
-	if (!rec)
-		return NULL;
-
-	rec->ip = ip;
-
-	return rec;
-}
-
 static void print_ip_ins(const char *fmt, unsigned char *p)
 {
 	int i;

@@ -3693,7 +3664,9 @@ static int ftrace_process_locs(struct module *mod,
 			       unsigned long *start,
 			       unsigned long *end)
 {
+	struct ftrace_page *start_pg;
 	struct ftrace_page *pg;
+	struct dyn_ftrace *rec;
 	unsigned long count;
 	unsigned long *p;
 	unsigned long addr;

@@ -3708,8 +3681,8 @@ static int ftrace_process_locs(struct module *mod,
 	sort(start, count, sizeof(*start),
 	     ftrace_cmp_ips, ftrace_swap_ips);
 
-	pg = ftrace_allocate_pages(count);
-	if (!pg)
+	start_pg = ftrace_allocate_pages(count);
+	if (!start_pg)
 		return -ENOMEM;
 
 	mutex_lock(&ftrace_lock);

@@ -3722,7 +3695,7 @@ static int ftrace_process_locs(struct module *mod,
 	if (!mod) {
 		WARN_ON(ftrace_pages || ftrace_pages_start);
 		/* First initialization */
-		ftrace_pages = ftrace_pages_start = pg;
+		ftrace_pages = ftrace_pages_start = start_pg;
 	} else {
 		if (!ftrace_pages)
 			goto out;

@@ -3733,11 +3706,11 @@ static int ftrace_process_locs(struct module *mod,
 				ftrace_pages = ftrace_pages->next;
 		}
 
-		ftrace_pages->next = pg;
-		ftrace_pages = pg;
+		ftrace_pages->next = start_pg;
 	}
 
 	p = start;
+	pg = start_pg;
 	while (p < end) {
 		addr = ftrace_call_adjust(*p++);
 		/*

@@ -3748,12 +3721,26 @@ static int ftrace_process_locs(struct module *mod,
 		 */
 		if (!addr)
 			continue;
-		if (!ftrace_record_ip(addr))
-			break;
+
+		if (pg->index == pg->size) {
+			/* We should have allocated enough */
+			if (WARN_ON(!pg->next))
+				break;
+			pg = pg->next;
+		}
+
+		rec = &pg->records[pg->index++];
+		rec->ip = addr;
 	}
 
+	/* We should have used all pages */
+	WARN_ON(pg->next);
+
+	/* Assign the last page to ftrace_pages */
+	ftrace_pages = pg;
+
 	/* These new locations need to be initialized */
-	ftrace_new_pgs = pg;
+	ftrace_new_pgs = start_pg;
 
 	/*
 	 * We only need to disable interrupts on start up

index e10f9e5..fc93562 100644
@@ -1411,6 +1411,8 @@ int ftrace_location(unsigned long ip)
 	key.ip = ip;
 
 	for (pg = ftrace_pages_start; pg; pg = pg->next) {
+		if (ip < pg->records[0].ip || ip > pg->records[pg->index - 1].ip)
+			continue;
 		rec = bsearch(&key, pg->records, pg->index,
 			      sizeof(struct dyn_ftrace),
 			      ftrace_cmp_recs);

@@ -1571,16 +1573,24 @@ void ftrace_bug(int failed, unsigned long ip)
 
 
 /* Return 1 if the address range is reserved for ftrace */
-int ftrace_text_reserved(void *start, void *end)
+int ftrace_text_reserved(void *s, void *e)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
+	unsigned long start = (unsigned long)s;
+	unsigned long end = (unsigned long)e;
+	int i;
 
-	do_for_each_ftrace_rec(pg, rec) {
-		if (rec->ip <= (unsigned long)end &&
-		    rec->ip + MCOUNT_INSN_SIZE > (unsigned long)start)
-			return 1;
-	} while_for_each_ftrace_rec();
+	for (pg = ftrace_pages_start; pg; pg = pg->next) {
+		if (end < pg->records[0].ip ||
+		    start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
+			continue;
+		for (i = 0; i < pg->index; i++) {
+			rec = &pg->records[i];
+			if (rec->ip <= end && rec->ip + MCOUNT_INSN_SIZE > start)
+				return 1;
+		}
+	}
 	return 0;
 }
 

index fc93562..dd091c8 100644
@@ -1383,35 +1383,28 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
 
 static int ftrace_cmp_recs(const void *a, const void *b)
 {
-	const struct dyn_ftrace *reca = a;
-	const struct dyn_ftrace *recb = b;
+	const struct dyn_ftrace *key = a;
+	const struct dyn_ftrace *rec = b;
 
-	if (reca->ip > recb->ip)
-		return 1;
-	if (reca->ip < recb->ip)
+	if (key->flags < rec->ip)
 		return -1;
+	if (key->ip >= rec->ip + MCOUNT_INSN_SIZE)
+		return 1;
 	return 0;
 }
 
-/**
- * ftrace_location - return true if the ip giving is a traced location
- * @ip: the instruction pointer to check
- *
- * Returns 1 if @ip given is a pointer to a ftrace location.
- * That is, the instruction that is either a NOP or call to
- * the function tracer. It checks the ftrace internal tables to
- * determine if the address belongs or not.
- */
-int ftrace_location(unsigned long ip)
+static int ftrace_location_range(unsigned long start, unsigned long end)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
 	struct dyn_ftrace key;
 
-	key.ip = ip;
+	key.ip = start;
+	key.flags = end;	/* overload flags, as it is unsigned long */
 
 	for (pg = ftrace_pages_start; pg; pg = pg->next) {
-		if (ip < pg->records[0].ip || ip > pg->records[pg->index - 1].ip)
+		if (end < pg->records[0].ip ||
+		    start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
 			continue;
 		rec = bsearch(&key, pg->records, pg->index,
 			      sizeof(struct dyn_ftrace),

@@ -1423,6 +1416,36 @@ int ftrace_location(unsigned long ip)
 	return 0;
 }
 
+/**
+ * ftrace_location - return true if the ip giving is a traced location
+ * @ip: the instruction pointer to check
+ *
+ * Returns 1 if @ip given is a pointer to a ftrace location.
+ * That is, the instruction that is either a NOP or call to
+ * the function tracer. It checks the ftrace internal tables to
+ * determine if the address belongs or not.
+ */
+int ftrace_location(unsigned long ip)
+{
+	return ftrace_location_range(ip, ip);
+}
+
+/**
+ * ftrace_text_reserved - return true if range contains an ftrace location
+ * @start: start of range to search
+ * @end: end of range to search (inclusive). @end points to the last byte to check.
+ *
+ * Returns 1 if @start and @end contains a ftrace location.
+ * That is, the instruction that is either a NOP or call to
+ * the function tracer. It checks the ftrace internal tables to
+ * determine if the address belongs or not.
+ */
+int ftrace_text_reserved(void *start, void *end)
+{
+	return ftrace_location_range((unsigned long)start,
+				     (unsigned long)end);
+}
+
 static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)

@@ -1571,29 +1594,6 @@ void ftrace_bug(int failed, unsigned long ip)
 	}
 }
 
-
-/* Return 1 if the address range is reserved for ftrace */
-int ftrace_text_reserved(void *s, void *e)
-{
-	struct dyn_ftrace *rec;
-	struct ftrace_page *pg;
-	unsigned long start = (unsigned long)s;
-	unsigned long end = (unsigned long)e;
-	int i;
-
-	for (pg = ftrace_pages_start; pg; pg = pg->next) {
-		if (end < pg->records[0].ip ||
-		    start >= (pg->records[pg->index - 1].ip + MCOUNT_INSN_SIZE))
-			continue;
-		for (i = 0; i < pg->index; i++) {
-			rec = &pg->records[i];
-			if (rec->ip <= end && rec->ip + MCOUNT_INSN_SIZE > start)
-				return 1;
-		}
-	}
-	return 0;
-}
-
 static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 {
 	unsigned long flag = 0UL;

index d32cc5e..609948e 100644
@@ -295,7 +295,7 @@ struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter);
 int ftrace_update_record(struct dyn_ftrace *rec, int enable);
 int ftrace_test_record(struct dyn_ftrace *rec, int enable);
 void ftrace_run_stop_machine(int command);
-int ftrace_location(unsigned long ip);
+unsigned long ftrace_location(unsigned long ip);
 
 extern ftrace_func_t ftrace_trace_function;
 

index dd091c8..ef08262 100644
@@ -1393,7 +1393,7 @@ static int ftrace_cmp_recs(const void *a, const void *b)
 	return 0;
 }
 
-static int ftrace_location_range(unsigned long start, unsigned long end)
+static unsigned long ftrace_location_range(unsigned long start, unsigned long end)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;

@@ -1410,7 +1410,7 @@ static int ftrace_location_range(unsigned long start, unsigned long end)
 			      sizeof(struct dyn_ftrace),
 			      ftrace_cmp_recs);
 		if (rec)
-			return 1;
+			return rec->ip;
 	}
 
 	return 0;

@@ -1420,12 +1420,12 @@ static int ftrace_location_range(unsigned long start, unsigned long end)
  * ftrace_location - return true if the ip giving is a traced location
  * @ip: the instruction pointer to check
  *
- * Returns 1 if @ip given is a pointer to a ftrace location.
+ * Returns rec->ip if @ip given is a pointer to a ftrace location.
  * That is, the instruction that is either a NOP or call to
  * the function tracer. It checks the ftrace internal tables to
  * determine if the address belongs or not.
  */
-int ftrace_location(unsigned long ip)
+unsigned long ftrace_location(unsigned long ip)
 {
 	return ftrace_location_range(ip, ip);
 }

@@ -1442,8 +1442,12 @@ int ftrace_location(unsigned long ip)
  */
 int ftrace_text_reserved(void *start, void *end)
 {
-	return ftrace_location_range((unsigned long)start,
-				     (unsigned long)end);
+	unsigned long ret;
+
+	ret = ftrace_location_range((unsigned long)start,
+				    (unsigned long)end);
+
+	return (int)!!ret;
 }
 
 static void __ftrace_hash_rec_update(struct ftrace_ops *ops,

index 609948e..cd72ace 100644
@@ -319,6 +319,8 @@ extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
 
+void ftrace_modify_all_code(int command);
+
 #ifndef FTRACE_ADDR
 #define FTRACE_ADDR ((unsigned long)ftrace_caller)
 #endif

index ef08262..3c34582 100644
@@ -1811,22 +1811,27 @@ int __weak ftrace_arch_code_modify_post_process(void)
 	return 0;
 }
 
-static int __ftrace_modify_code(void *data)
+void ftrace_modify_all_code(int command)
 {
-	int *command = data;
-
-	if (*command & FTRACE_UPDATE_CALLS)
+	if (command & FTRACE_UPDATE_CALLS)
 		ftrace_replace_code(1);
-	else if (*command & FTRACE_DISABLE_CALLS)
+	else if (command & FTRACE_DISABLE_CALLS)
 		ftrace_replace_code(0);
 
-	if (*command & FTRACE_UPDATE_TRACE_FUNC)
+	if (command & FTRACE_UPDATE_TRACE_FUNC)
 		ftrace_update_ftrace_func(ftrace_trace_function);
 
-	if (*command & FTRACE_START_FUNC_RET)
+	if (command & FTRACE_START_FUNC_RET)
 		ftrace_enable_ftrace_graph_caller();
-	else if (*command & FTRACE_STOP_FUNC_RET)
+	else if (command & FTRACE_STOP_FUNC_RET)
 		ftrace_disable_ftrace_graph_caller();
+}
+
+static int __ftrace_modify_code(void *data)
+{
+	int *command = data;
+
+	ftrace_modify_all_code(*command);
 
 	return 0;
 }

index 4243e8b..32ff365 100644
@@ -435,7 +435,7 @@ static void run_sync(void)
 		local_irq_disable();
 }
 
-static void ftrace_replace_code(int enable)
+void ftrace_replace_code(int enable)
 {
 	struct ftrace_rec_iter *iter;
 	struct dyn_ftrace *rec;

@@ -493,18 +493,7 @@ void arch_ftrace_update_code(int command)
 {
 	modifying_ftrace_code++;
 
-	if (command & FTRACE_UPDATE_CALLS)
-		ftrace_replace_code(1);
-	else if (command & FTRACE_DISABLE_CALLS)
-		ftrace_replace_code(0);
-
-	if (command & FTRACE_UPDATE_TRACE_FUNC)
-		ftrace_update_ftrace_func(ftrace_trace_function);
-
-	if (command & FTRACE_START_FUNC_RET)
-		ftrace_enable_ftrace_graph_caller();
-	else if (command & FTRACE_STOP_FUNC_RET)
-		ftrace_disable_ftrace_graph_caller();
+	ftrace_modify_all_code(command);
 
 	modifying_ftrace_code--;
 }

index cd72ace..55e6d63 100644
@@ -314,6 +314,7 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void *data);
+extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);

index 3c34582..a008663 100644
@@ -1683,7 +1683,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	return -1; /* unknow ftrace bug */
 }
 
-static void ftrace_replace_code(int update)
+void __weak ftrace_replace_code(int enable)
 {
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;

@@ -1693,7 +1693,7 @@ static void ftrace_replace_code(int update)
 		return;
 
 	do_for_each_ftrace_rec(pg, rec) {
-		failed = __ftrace_replace_code(rec, update);
+		failed = __ftrace_replace_code(rec, enable);
 		if (failed) {
 			ftrace_bug(failed, rec->ip);
 			/* Stop processing */