Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf changes from Ingo Molnar:
 "Lots of changes:

   - (much) improved assembly annotation support in perf report, with
     jump visualization, searching, navigation, visual output
     improvements and more.

    - kernel support for AMD IBS PMU hardware features.  Notably 'perf
      record -e cycles:p' and 'perf top -e cycles:p' should work without
      skid now, like PEBS does on the Intel side, because it takes
      advantage of IBS transparently.

    - the libtracevents library: it is the first step towards unifying
      tracing tooling and perf, and it also gives a tracing library for
      external tools like powertop to rely on.

    - infrastructure: various improvements and refactoring of the UI
      modules and related code

    - infrastructure: cleanup and simplification of the profiling
      targets code (--uid, --pid, --tid, --cpu, --all-cpus, etc.)

    - tons of robustness fixes all around

    - various ftrace updates: speedups, cleanups, robustness
      improvements.

    - typing 'make' in tools/ will now give you a menu of projects to
      build and a short help text to explain what each does.

    - ... and lots of other changes I forgot to list.

  The perf record make bzImage + perf report regression you reported
  should be fixed."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (166 commits)
  tracing: Remove kernel_lock annotations
  tracing: Fix initial buffer_size_kb state
  ring-buffer: Merge separate resize loops
  perf evsel: Create events initially disabled -- again
  perf tools: Split term type into value type and term type
  perf hists: Fix callchain ip printf format
  perf target: Add uses_mmap field
  ftrace: Remove selecting FRAME_POINTER with FUNCTION_TRACER
  ftrace/x86: Have x86 ftrace use the ftrace_modify_all_code()
  ftrace: Make ftrace_modify_all_code() global for archs to use
  ftrace: Return record ip addr for ftrace_location()
  ftrace: Consolidate ftrace_location() and ftrace_text_reserved()
  ftrace: Speed up search by skipping pages by address
  ftrace: Remove extra helper functions
  ftrace: Sort all function addresses, not just per page
  tracing: change CPU ring buffer state from tracing_cpumask
  tracing: Check return value of tracing_dentry_percpu()
  ring-buffer: Reset head page before running self test
  ring-buffer: Add integrity check at end of iter read
  ring-buffer: Make addition of pages in ring buffer atomic
  ...

6 files changed, 858 insertions, 481 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index a1d2849..d81a1a5 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,6 @@ if FTRACE
 config FUNCTION_TRACER
 	bool "Kernel Function Tracer"
 	depends on HAVE_FUNCTION_TRACER
-	select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE
 	select KALLSYMS
 	select GENERIC_TRACER
 	select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0fa92f6..a008663 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1383,44 +1383,73 @@ 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 unsigned long 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 (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),
 			      ftrace_cmp_recs);
 		if (rec)
-			return 1;
+			return rec->ip;
 	}
 
 	return 0;
 }
 
+/**
+ * ftrace_location - return true if the ip giving is a traced location
+ * @ip: the instruction pointer to check
+ *
+ * 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.
+ */
+unsigned long 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)
+{
+	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,
 				     int filter_hash,
 				     bool inc)
@@ -1520,35 +1549,6 @@ 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;
@@ -1598,21 +1598,6 @@ 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)
-{
-	struct dyn_ftrace *rec;
-	struct ftrace_page *pg;
-
-	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();
-	return 0;
-}
-
 static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 {
 	unsigned long flag = 0UL;
@@ -1698,7 +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;
@@ -1708,7 +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 */
@@ -1826,22 +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;
 }
@@ -2469,57 +2459,35 @@ static int
 ftrace_avail_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
-	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return -ENOMEM;
-
-	iter->pg = ftrace_pages_start;
-	iter->ops = &global_ops;
-
-	ret = seq_open(file, &show_ftrace_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = iter;
-	} else {
-		kfree(iter);
+	iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+	if (iter) {
+		iter->pg = ftrace_pages_start;
+		iter->ops = &global_ops;
 	}
 
-	return ret;
+	return iter ? 0 : -ENOMEM;
 }
 
 static int
 ftrace_enabled_open(struct inode *inode, struct file *file)
 {
 	struct ftrace_iterator *iter;
-	int ret;
 
 	if (unlikely(ftrace_disabled))
 		return -ENODEV;
 
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
-	if (!iter)
-		return -ENOMEM;
-
-	iter->pg = ftrace_pages_start;
-	iter->flags = FTRACE_ITER_ENABLED;
-	iter->ops = &global_ops;
-
-	ret = seq_open(file, &show_ftrace_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-
-		m->private = iter;
-	} else {
-		kfree(iter);
+	iter = __seq_open_private(file, &show_ftrace_seq_ops, sizeof(*iter));
+	if (iter) {
+		iter->pg = ftrace_pages_start;
+		iter->flags = FTRACE_ITER_ENABLED;
+		iter->ops = &global_ops;
 	}
 
-	return ret;
+	return iter ? 0 : -ENOMEM;
 }
 
 static void ftrace_filter_reset(struct ftrace_hash *hash)
@@ -3688,22 +3656,36 @@ 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)
+{
+	const unsigned long *ipa = a;
+	const unsigned long *ipb = b;
+
+	if (*ipa > *ipb)
+		return 1;
+	if (*ipa < *ipb)
+		return -1;
+	return 0;
+}
+
+static void ftrace_swap_ips(void *a, void *b, int size)
 {
-	struct dyn_ftrace *reca = a;
-	struct dyn_ftrace *recb = b;
-	struct dyn_ftrace t;
+	unsigned long *ipa = a;
+	unsigned long *ipb = b;
+	unsigned long t;
 
-	t = *reca;
-	*reca = *recb;
-	*recb = t;
+	t = *ipa;
+	*ipa = *ipb;
+	*ipb = t;
 }
 
 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;
@@ -3715,8 +3697,11 @@ static int ftrace_process_locs(struct module *mod,
 	if (!count)
 		return 0;
 
-	pg = ftrace_allocate_pages(count);
-	if (!pg)
+	sort(start, count, sizeof(*start),
+	     ftrace_cmp_ips, ftrace_swap_ips);
+
+	start_pg = ftrace_allocate_pages(count);
+	if (!start_pg)
 		return -ENOMEM;
 
 	mutex_lock(&ftrace_lock);
@@ -3729,7 +3714,7 @@ 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;
@@ -3740,11 +3725,11 @@ 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++);
 		/*
@@ -3755,17 +3740,26 @@ 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;
 	}
 
-	/* These new locations need to be initialized */
-	ftrace_new_pgs = pg;
+	/* We should have used all pages */
+	WARN_ON(pg->next);
+
+	/* Assign the last page to ftrace_pages */
+	ftrace_pages = 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);
+	/* These new locations need to be initialized */
+	ftrace_new_pgs = start_pg;
 
 	/*
 	 * We only need to disable interrupts on start up
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cf8d11e..6420cda 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -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.
  */
@@ -449,6 +451,7 @@ struct ring_buffer_per_cpu {
 	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
+	unsigned int			nr_pages;
 	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
 	struct buffer_page		*tail_page;	/* write to tail */
@@ -466,13 +469,18 @@ struct ring_buffer_per_cpu {
 	unsigned long			read_bytes;
 	u64				write_stamp;
 	u64				read_stamp;
+	/* 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_done;
 };
 
 struct ring_buffer {
-	unsigned			pages;
 	unsigned			flags;
 	int				cpus;
 	atomic_t			record_disabled;
+	atomic_t			resize_disabled;
 	cpumask_var_t			cpumask;
 
 	struct lock_class_key		*reader_lock_key;
@@ -937,6 +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))
@@ -963,14 +975,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	return 0;
 }
 
-static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
-			     unsigned nr_pages)
+static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu)
 {
+	int i;
 	struct buffer_page *bpage, *tmp;
-	LIST_HEAD(pages);
-	unsigned i;
-
-	WARN_ON(!nr_pages);
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
@@ -981,15 +989,13 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 				    GFP_KERNEL | __GFP_NORETRY,
-				    cpu_to_node(cpu_buffer->cpu));
+				    cpu_to_node(cpu));
 		if (!bpage)
 			goto free_pages;
 
-		rb_check_bpage(cpu_buffer, bpage);
+		list_add(&bpage->list, pages);
 
-		list_add(&bpage->list, &pages);
-
-		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+		page = alloc_pages_node(cpu_to_node(cpu),
 					GFP_KERNEL | __GFP_NORETRY, 0);
 		if (!page)
 			goto free_pages;
@@ -997,6 +1003,27 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_init_page(bpage->page);
 	}
 
+	return 0;
+
+free_pages:
+	list_for_each_entry_safe(bpage, tmp, pages, list) {
+		list_del_init(&bpage->list);
+		free_buffer_page(bpage);
+	}
+
+	return -ENOMEM;
+}
+
+static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
+			     unsigned nr_pages)
+{
+	LIST_HEAD(pages);
+
+	WARN_ON(!nr_pages);
+
+	if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu))
+		return -ENOMEM;
+
 	/*
 	 * The ring buffer page list is a circular list that does not
 	 * start and end with a list head. All page list items point to
@@ -1005,20 +1032,15 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	cpu_buffer->pages = pages.next;
 	list_del(&pages);
 
+	cpu_buffer->nr_pages = nr_pages;
+
 	rb_check_pages(cpu_buffer);
 
 	return 0;
-
- free_pages:
-	list_for_each_entry_safe(bpage, tmp, &pages, list) {
-		list_del_init(&bpage->list);
-		free_buffer_page(bpage);
-	}
-	return -ENOMEM;
 }
 
 static struct ring_buffer_per_cpu *
-rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
@@ -1035,6 +1057,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, 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_done);
 
 	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
 			    GFP_KERNEL, cpu_to_node(cpu));
@@ -1052,7 +1076,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
 
-	ret = rb_allocate_pages(cpu_buffer, buffer->pages);
+	ret = rb_allocate_pages(cpu_buffer, nr_pages);
 	if (ret < 0)
 		goto fail_free_reader;
 
@@ -1113,7 +1137,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 {
 	struct ring_buffer *buffer;
 	int bsize;
-	int cpu;
+	int cpu, nr_pages;
 
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1124,14 +1148,14 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 	if (!alloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
 		goto fail_free_buffer;
 
-	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	buffer->flags = flags;
 	buffer->clock = trace_clock_local;
 	buffer->reader_lock_key = key;
 
 	/* need at least two pages */
-	if (buffer->pages < 2)
-		buffer->pages = 2;
+	if (nr_pages < 2)
+		nr_pages = 2;
 
 	/*
 	 * In case of non-hotplug cpu, if the ring-buffer is allocated
@@ -1154,7 +1178,7 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 
 	for_each_buffer_cpu(buffer, cpu) {
 		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, cpu);
+			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
 		if (!buffer->buffers[cpu])
 			goto fail_free_buffers;
 	}
@@ -1222,58 +1246,222 @@ void ring_buffer_set_clock(struct ring_buffer *buffer,
 
 static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
 
-static void
-rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
+static inline unsigned long rb_page_entries(struct buffer_page *bpage)
 {
-	struct buffer_page *bpage;
-	struct list_head *p;
-	unsigned i;
+	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 int
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
+{
+	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);
+
+	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);
-	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:
+	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)
+		success = rb_insert_pages(cpu_buffer);
+	else
+		success = rb_remove_pages(cpu_buffer,
+					-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)
+{
+	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_done);
 }
 
 /**
@@ -1283,16 +1471,14 @@ out:
  *
  * 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 ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
+			int cpu_id)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned nr_pages, rm_pages, new_pages;
-	struct buffer_page *bpage, *tmp;
-	unsigned long buffer_size;
-	LIST_HEAD(pages);
-	int i, cpu;
+	unsigned nr_pages;
+	int cpu, err = 0;
 
 	/*
 	 * Always succeed at resizing a non-existent buffer:
@@ -1302,113 +1488,154 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
 	size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 	size *= BUF_PAGE_SIZE;
-	buffer_size = buffer->pages * BUF_PAGE_SIZE;
 
 	/* we need a minimum of two pages */
 	if (size < BUF_PAGE_SIZE * 2)
 		size = BUF_PAGE_SIZE * 2;
 
-	if (size == buffer_size)
-		return size;
-
-	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 (size < buffer_size) {
+	if (cpu_id == RING_BUFFER_ALL_CPUS) {
+		/* calculate the pages to update */
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
 
-		/* easy case, just free pages */
-		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
-			goto out_fail;
+			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)) {
+				/* not enough memory for new pages */
+				err = -ENOMEM;
+				goto out_err;
+			}
+		}
 
-		rm_pages = buffer->pages - nr_pages;
+		get_online_cpus();
+		/*
+		 * Fire off all the required work handlers
+		 * We can't schedule on offline CPUs, 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)
+				continue;
+
+			if (cpu_online(cpu))
+				schedule_work_on(cpu,
+						&cpu_buffer->update_pages_work);
+			else
+				rb_update_pages(cpu_buffer);
+		}
 
+		/* wait for all the updates to complete */
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
-			rb_remove_pages(cpu_buffer, rm_pages);
+			if (!cpu_buffer->nr_pages_to_update)
+				continue;
+
+			if (cpu_online(cpu))
+				wait_for_completion(&cpu_buffer->update_done);
+			cpu_buffer->nr_pages_to_update = 0;
 		}
-		goto out;
-	}
 
-	/*
-	 * This is a bit more difficult. We only want to add pages
-	 * when we can allocate enough for all CPUs. We do this
-	 * by allocating all the pages and storing them on a local
-	 * link list. If we succeed in our allocation, then we
-	 * add these pages to the cpu_buffers. Otherwise we just free
-	 * them all and return -ENOMEM;
-	 */
-	if (RB_WARN_ON(buffer, nr_pages <= buffer->pages))
-		goto out_fail;
+		put_online_cpus();
+	} else {
+		cpu_buffer = buffer->buffers[cpu_id];
 
-	new_pages = nr_pages - buffer->pages;
+		if (nr_pages == cpu_buffer->nr_pages)
+			goto out;
 
-	for_each_buffer_cpu(buffer, cpu) {
-		for (i = 0; i < new_pages; i++) {
-			struct page *page;
-			/*
-			 * __GFP_NORETRY flag makes sure that the allocation
-			 * fails gracefully without invoking oom-killer and
-			 * the system is not destabilized.
-			 */
-			bpage = kzalloc_node(ALIGN(sizeof(*bpage),
-						  cache_line_size()),
-					    GFP_KERNEL | __GFP_NORETRY,
-					    cpu_to_node(cpu));
-			if (!bpage)
-				goto free_pages;
-			list_add(&bpage->list, &pages);
-			page = alloc_pages_node(cpu_to_node(cpu),
-						GFP_KERNEL | __GFP_NORETRY, 0);
-			if (!page)
-				goto free_pages;
-			bpage->page = page_address(page);
-			rb_init_page(bpage->page);
+		cpu_buffer->nr_pages_to_update = nr_pages -
+						cpu_buffer->nr_pages;
+
+		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)) {
+			err = -ENOMEM;
+			goto out_err;
 		}
-	}
 
-	for_each_buffer_cpu(buffer, cpu) {
-		cpu_buffer = buffer->buffers[cpu];
-		rb_insert_pages(cpu_buffer, &pages, new_pages);
-	}
+		get_online_cpus();
 
-	if (RB_WARN_ON(buffer, !list_empty(&pages)))
-		goto out_fail;
+		if (cpu_online(cpu_id)) {
+			schedule_work_on(cpu_id,
+					 &cpu_buffer->update_pages_work);
+			wait_for_completion(&cpu_buffer->update_done);
+		} else
+			rb_update_pages(cpu_buffer);
+
+		cpu_buffer->nr_pages_to_update = 0;
+		put_online_cpus();
+	}
 
  out:
-	buffer->pages = nr_pages;
-	put_online_cpus();
+	/*
+	 * 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;
 
-	atomic_dec(&buffer->record_disabled);
+ out_err:
+	for_each_buffer_cpu(buffer, cpu) {
+		struct buffer_page *bpage, *tmp;
 
-	return size;
+		cpu_buffer = buffer->buffers[cpu];
+		cpu_buffer->nr_pages_to_update = 0;
 
- free_pages:
-	list_for_each_entry_safe(bpage, tmp, &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;
+		if (list_empty(&cpu_buffer->new_pages))
+			continue;
 
-	/*
-	 * Something went totally wrong, and we are too paranoid
-	 * to even clean up the mess.
-	 */
- out_fail:
-	put_online_cpus();
+		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
+					list) {
+			list_del_init(&bpage->list);
+			free_buffer_page(bpage);
+		}
+	}
 	mutex_unlock(&buffer->mutex);
-	atomic_dec(&buffer->record_disabled);
-	return -1;
+	return err;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
@@ -1447,21 +1674,11 @@ 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)
 {
@@ -1510,7 +1727,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	 * assign the commit to the tail.
 	 */
  again:
-	max_count = cpu_buffer->buffer->pages * 100;
+	max_count = cpu_buffer->nr_pages * 100;
 
 	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
 		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
@@ -3486,6 +3703,7 @@ 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;
@@ -3548,7 +3766,14 @@ 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);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_finish);
@@ -3588,9 +3813,18 @@ EXPORT_SYMBOL_GPL(ring_buffer_read);
  * ring_buffer_size - return the size of the ring buffer (in bytes)
  * @buffer: The ring buffer.
  */
-unsigned long ring_buffer_size(struct ring_buffer *buffer)
+unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu)
 {
-	return BUF_PAGE_SIZE * buffer->pages;
+	/*
+	 * Earlier, this method returned
+	 *	BUF_PAGE_SIZE * buffer->nr_pages
+	 * Since the nr_pages field is now removed, we have converted this to
+	 * return the per cpu buffer value.
+	 */
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_size);
 
@@ -3611,6 +3845,7 @@ 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);
@@ -3647,8 +3882,12 @@ 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)))
@@ -3664,6 +3903,7 @@ 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);
 
@@ -3765,8 +4005,11 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
 		goto out;
 
+	cpu_buffer_a = buffer_a->buffers[cpu];
+	cpu_buffer_b = buffer_b->buffers[cpu];
+
 	/* At least make sure the two buffers are somewhat the same */
-	if (buffer_a->pages != buffer_b->pages)
+	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
 		goto out;
 
 	ret = -EAGAIN;
@@ -3780,9 +4023,6 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	if (atomic_read(&buffer_b->record_disabled))
 		goto out;
 
-	cpu_buffer_a = buffer_a->buffers[cpu];
-	cpu_buffer_b = buffer_b->buffers[cpu];
-
 	if (atomic_read(&cpu_buffer_a->record_disabled))
 		goto out;
 
@@ -4071,6 +4311,8 @@ static int rb_cpu_notify(struct notifier_block *self,
 	struct ring_buffer *buffer =
 		container_of(self, struct ring_buffer, cpu_notify);
 	long cpu = (long)hcpu;
+	int cpu_i, nr_pages_same;
+	unsigned int nr_pages;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
@@ -4078,8 +4320,23 @@ static int rb_cpu_notify(struct notifier_block *self,
 		if (cpumask_test_cpu(cpu, buffer->cpumask))
 			return NOTIFY_OK;
 
+		nr_pages = 0;
+		nr_pages_same = 1;
+		/* check if all cpu sizes are same */
+		for_each_buffer_cpu(buffer, cpu_i) {
+			/* fill in the size from first enabled cpu */
+			if (nr_pages == 0)
+				nr_pages = buffer->buffers[cpu_i]->nr_pages;
+			if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
+				nr_pages_same = 0;
+				break;
+			}
+		}
+		/* allocate minimum pages, user can later expand it */
+		if (!nr_pages_same)
+			nr_pages = 2;
 		buffer->buffers[cpu] =
-			rb_allocate_cpu_buffer(buffer, cpu);
+			rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
 		if (!buffer->buffers[cpu]) {
 			WARN(1, "failed to allocate ring buffer on CPU %ld\n",
 			     cpu);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2a22255..68032c6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -87,18 +87,6 @@ static int tracing_disabled = 1;
 
 DEFINE_PER_CPU(int, ftrace_cpu_disabled);
 
-static inline void ftrace_disable_cpu(void)
-{
-	preempt_disable();
-	__this_cpu_inc(ftrace_cpu_disabled);
-}
-
-static inline void ftrace_enable_cpu(void)
-{
-	__this_cpu_dec(ftrace_cpu_disabled);
-	preempt_enable();
-}
-
 cpumask_var_t __read_mostly	tracing_buffer_mask;
 
 /*
@@ -629,7 +617,6 @@ ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 {
 	int len;
-	void *ret;
 
 	if (s->len <= s->readpos)
 		return -EBUSY;
@@ -637,9 +624,7 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	len = s->len - s->readpos;
 	if (cnt > len)
 		cnt = len;
-	ret = memcpy(buf, s->buffer + s->readpos, cnt);
-	if (!ret)
-		return -EFAULT;
+	memcpy(buf, s->buffer + s->readpos, cnt);
 
 	s->readpos += cnt;
 	return cnt;
@@ -751,8 +736,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&ftrace_max_lock);
 
-	ftrace_disable_cpu();
-
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
 	if (ret == -EBUSY) {
@@ -766,8 +749,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 			"Failed to swap buffers due to commit in progress\n");
 	}
 
-	ftrace_enable_cpu();
-
 	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
@@ -782,8 +763,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
  * Register a new plugin tracer.
  */
 int register_tracer(struct tracer *type)
-__releases(kernel_lock)
-__acquires(kernel_lock)
 {
 	struct tracer *t;
 	int ret = 0;
@@ -841,7 +820,8 @@ __acquires(kernel_lock)
 
 		/* If we expanded the buffers, make sure the max is expanded too */
 		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, trace_buf_size);
+			ring_buffer_resize(max_tr.buffer, trace_buf_size,
+						RING_BUFFER_ALL_CPUS);
 
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
@@ -857,7 +837,8 @@ __acquires(kernel_lock)
 
 		/* Shrink the max buffer again */
 		if (ring_buffer_expanded && type->use_max_tr)
-			ring_buffer_resize(max_tr.buffer, 1);
+			ring_buffer_resize(max_tr.buffer, 1,
+						RING_BUFFER_ALL_CPUS);
 
 		printk(KERN_CONT "PASSED\n");
 	}
@@ -917,13 +898,6 @@ out:
 	mutex_unlock(&trace_types_lock);
 }
 
-static void __tracing_reset(struct ring_buffer *buffer, int cpu)
-{
-	ftrace_disable_cpu();
-	ring_buffer_reset_cpu(buffer, cpu);
-	ftrace_enable_cpu();
-}
-
 void tracing_reset(struct trace_array *tr, int cpu)
 {
 	struct ring_buffer *buffer = tr->buffer;
@@ -932,7 +906,7 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
 	/* Make sure all commits have finished */
 	synchronize_sched();
-	__tracing_reset(buffer, cpu);
+	ring_buffer_reset_cpu(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -950,7 +924,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		__tracing_reset(buffer, cpu);
+		ring_buffer_reset_cpu(buffer, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
@@ -1498,25 +1472,119 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 
 #endif /* CONFIG_STACKTRACE */
 
+/* created for use with alloc_percpu */
+struct trace_buffer_struct {
+	char buffer[TRACE_BUF_SIZE];
+};
+
+static struct trace_buffer_struct *trace_percpu_buffer;
+static struct trace_buffer_struct *trace_percpu_sirq_buffer;
+static struct trace_buffer_struct *trace_percpu_irq_buffer;
+static struct trace_buffer_struct *trace_percpu_nmi_buffer;
+
+/*
+ * The buffer used is dependent on the context. There is a per cpu
+ * buffer for normal context, softirq contex, hard irq context and
+ * for NMI context. Thise allows for lockless recording.
+ *
+ * Note, if the buffers failed to be allocated, then this returns NULL
+ */
+static char *get_trace_buf(void)
+{
+	struct trace_buffer_struct *percpu_buffer;
+	struct trace_buffer_struct *buffer;
+
+	/*
+	 * If we have allocated per cpu buffers, then we do not
+	 * need to do any locking.
+	 */
+	if (in_nmi())
+		percpu_buffer = trace_percpu_nmi_buffer;
+	else if (in_irq())
+		percpu_buffer = trace_percpu_irq_buffer;
+	else if (in_softirq())
+		percpu_buffer = trace_percpu_sirq_buffer;
+	else
+		percpu_buffer = trace_percpu_buffer;
+
+	if (!percpu_buffer)
+		return NULL;
+
+	buffer = per_cpu_ptr(percpu_buffer, smp_processor_id());
+
+	return buffer->buffer;
+}
+
+static int alloc_percpu_trace_buffer(void)
+{
+	struct trace_buffer_struct *buffers;
+	struct trace_buffer_struct *sirq_buffers;
+	struct trace_buffer_struct *irq_buffers;
+	struct trace_buffer_struct *nmi_buffers;
+
+	buffers = alloc_percpu(struct trace_buffer_struct);
+	if (!buffers)
+		goto err_warn;
+
+	sirq_buffers = alloc_percpu(struct trace_buffer_struct);
+	if (!sirq_buffers)
+		goto err_sirq;
+
+	irq_buffers = alloc_percpu(struct trace_buffer_struct);
+	if (!irq_buffers)
+		goto err_irq;
+
+	nmi_buffers = alloc_percpu(struct trace_buffer_struct);
+	if (!nmi_buffers)
+		goto err_nmi;
+
+	trace_percpu_buffer = buffers;
+	trace_percpu_sirq_buffer = sirq_buffers;
+	trace_percpu_irq_buffer = irq_buffers;
+	trace_percpu_nmi_buffer = nmi_buffers;
+
+	return 0;
+
+ err_nmi:
+	free_percpu(irq_buffers);
+ err_irq:
+	free_percpu(sirq_buffers);
+ err_sirq:
+	free_percpu(buffers);
+ err_warn:
+	WARN(1, "Could not allocate percpu trace_printk buffer");
+	return -ENOMEM;
+}
+
+void trace_printk_init_buffers(void)
+{
+	static int buffers_allocated;
+
+	if (buffers_allocated)
+		return;
+
+	if (alloc_percpu_trace_buffer())
+		return;
+
+	pr_info("ftrace: Allocated trace_printk buffers\n");
+
+	buffers_allocated = 1;
+}
+
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
  */
 int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 {
-	static arch_spinlock_t trace_buf_lock =
-		(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
-	static u32 trace_buf[TRACE_BUF_SIZE];
-
 	struct ftrace_event_call *call = &event_bprint;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
 	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
 	struct bprint_entry *entry;
 	unsigned long flags;
-	int disable;
-	int cpu, len = 0, size, pc;
+	char *tbuffer;
+	int len = 0, size, pc;
 
 	if (unlikely(tracing_selftest_running || tracing_disabled))
 		return 0;
@@ -1526,43 +1594,36 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	pc = preempt_count();
 	preempt_disable_notrace();
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
 
-	disable = atomic_inc_return(&data->disabled);
-	if (unlikely(disable != 1))
+	tbuffer = get_trace_buf();
+	if (!tbuffer) {
+		len = 0;
 		goto out;
+	}
 
-	/* Lockdep uses trace_printk for lock tracing */
-	local_irq_save(flags);
-	arch_spin_lock(&trace_buf_lock);
-	len = vbin_printf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+	len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args);
 
-	if (len > TRACE_BUF_SIZE || len < 0)
-		goto out_unlock;
+	if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0)
+		goto out;
 
+	local_save_flags(flags);
 	size = sizeof(*entry) + sizeof(u32) * len;
 	buffer = tr->buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
 					  flags, pc);
 	if (!event)
-		goto out_unlock;
+		goto out;
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
 	entry->fmt			= fmt;
 
-	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
+	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
 	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
 		ftrace_trace_stack(buffer, flags, 6, pc);
 	}
 
-out_unlock:
-	arch_spin_unlock(&trace_buf_lock);
-	local_irq_restore(flags);
-
 out:
-	atomic_dec_return(&data->disabled);
 	preempt_enable_notrace();
 	unpause_graph_tracing();
 
@@ -1588,58 +1649,53 @@ int trace_array_printk(struct trace_array *tr,
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
-	static arch_spinlock_t trace_buf_lock = __ARCH_SPIN_LOCK_UNLOCKED;
-	static char trace_buf[TRACE_BUF_SIZE];
-
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	struct trace_array_cpu *data;
-	int cpu, len = 0, size, pc;
+	int len = 0, size, pc;
 	struct print_entry *entry;
-	unsigned long irq_flags;
-	int disable;
+	unsigned long flags;
+	char *tbuffer;
 
 	if (tracing_disabled || tracing_selftest_running)
 		return 0;
 
+	/* Don't pollute graph traces with trace_vprintk internals */
+	pause_graph_tracing();
+
 	pc = preempt_count();
 	preempt_disable_notrace();
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
 
-	disable = atomic_inc_return(&data->disabled);
-	if (unlikely(disable != 1))
+
+	tbuffer = get_trace_buf();
+	if (!tbuffer) {
+		len = 0;
 		goto out;
+	}
 
-	pause_graph_tracing();
-	raw_local_irq_save(irq_flags);
-	arch_spin_lock(&trace_buf_lock);
-	len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+	len = vsnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
+	if (len > TRACE_BUF_SIZE)
+		goto out;
 
+	local_save_flags(flags);
 	size = sizeof(*entry) + len + 1;
 	buffer = tr->buffer;
 	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-					  irq_flags, pc);
+					  flags, pc);
 	if (!event)
-		goto out_unlock;
+		goto out;
 	entry = ring_buffer_event_data(event);
 	entry->ip = ip;
 
-	memcpy(&entry->buf, trace_buf, len);
+	memcpy(&entry->buf, tbuffer, len);
 	entry->buf[len] = '\0';
 	if (!filter_check_discard(call, entry, buffer, event)) {
 		ring_buffer_unlock_commit(buffer, event);
-		ftrace_trace_stack(buffer, irq_flags, 6, pc);
+		ftrace_trace_stack(buffer, flags, 6, pc);
 	}
-
- out_unlock:
-	arch_spin_unlock(&trace_buf_lock);
-	raw_local_irq_restore(irq_flags);
-	unpause_graph_tracing();
  out:
-	atomic_dec_return(&data->disabled);
 	preempt_enable_notrace();
+	unpause_graph_tracing();
 
 	return len;
 }
@@ -1652,14 +1708,9 @@ EXPORT_SYMBOL_GPL(trace_vprintk);
 
 static void trace_iterator_increment(struct trace_iterator *iter)
 {
-	/* Don't allow ftrace to trace into the ring buffers */
-	ftrace_disable_cpu();
-
 	iter->idx++;
 	if (iter->buffer_iter[iter->cpu])
 		ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
-
-	ftrace_enable_cpu();
 }
 
 static struct trace_entry *
@@ -1669,17 +1720,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
 
-	/* Don't allow ftrace to trace into the ring buffers */
-	ftrace_disable_cpu();
-
 	if (buf_iter)
 		event = ring_buffer_iter_peek(buf_iter, ts);
 	else
 		event = ring_buffer_peek(iter->tr->buffer, cpu, ts,
 					 lost_events);
 
-	ftrace_enable_cpu();
-
 	if (event) {
 		iter->ent_size = ring_buffer_event_length(event);
 		return ring_buffer_event_data(event);
@@ -1769,11 +1815,8 @@ void *trace_find_next_entry_inc(struct trace_iterator *iter)
 
 static void trace_consume(struct trace_iterator *iter)
 {
-	/* Don't allow ftrace to trace into the ring buffers */
-	ftrace_disable_cpu();
 	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts,
 			    &iter->lost_events);
-	ftrace_enable_cpu();
 }
 
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
@@ -1862,16 +1905,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		iter->cpu = 0;
 		iter->idx = -1;
 
-		ftrace_disable_cpu();
-
 		if (cpu_file == TRACE_PIPE_ALL_CPU) {
 			for_each_tracing_cpu(cpu)
 				tracing_iter_reset(iter, cpu);
 		} else
 			tracing_iter_reset(iter, cpu_file);
 
-		ftrace_enable_cpu();
-
 		iter->leftover = 0;
 		for (p = iter; p && l < *pos; p = s_next(m, p, &l))
 			;
@@ -2332,15 +2371,13 @@ static struct trace_iterator *
 __tracing_open(struct inode *inode, struct file *file)
 {
 	long cpu_file = (long) inode->i_private;
-	void *fail_ret = ERR_PTR(-ENOMEM);
 	struct trace_iterator *iter;
-	struct seq_file *m;
-	int cpu, ret;
+	int cpu;
 
 	if (tracing_disabled)
 		return ERR_PTR(-ENODEV);
 
-	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
+	iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter));
 	if (!iter)
 		return ERR_PTR(-ENOMEM);
 
@@ -2397,32 +2434,15 @@ __tracing_open(struct inode *inode, struct file *file)
 		tracing_iter_reset(iter, cpu);
 	}
 
-	ret = seq_open(file, &tracer_seq_ops);
-	if (ret < 0) {
-		fail_ret = ERR_PTR(ret);
-		goto fail_buffer;
-	}
-
-	m = file->private_data;
-	m->private = iter;
-
 	mutex_unlock(&trace_types_lock);
 
 	return iter;
 
- fail_buffer:
-	for_each_tracing_cpu(cpu) {
-		if (iter->buffer_iter[cpu])
-			ring_buffer_read_finish(iter->buffer_iter[cpu]);
-	}
-	free_cpumask_var(iter->started);
-	tracing_start();
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
-	kfree(iter);
-
-	return fail_ret;
+	seq_release_private(inode, file);
+	return ERR_PTR(-ENOMEM);
 }
 
 int tracing_open_generic(struct inode *inode, struct file *filp)
@@ -2458,11 +2478,10 @@ static int tracing_release(struct inode *inode, struct file *file)
 	tracing_start();
 	mutex_unlock(&trace_types_lock);
 
-	seq_release(inode, file);
 	mutex_destroy(&iter->mutex);
 	free_cpumask_var(iter->started);
 	kfree(iter->trace);
-	kfree(iter);
+	seq_release_private(inode, file);
 	return 0;
 }
 
@@ -2648,10 +2667,12 @@ 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);
@@ -2974,7 +2995,14 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
 	return t->init(tr);
 }
 
-static int __tracing_resize_ring_buffer(unsigned long size)
+static void set_buffer_entries(struct trace_array *tr, unsigned long val)
+{
+	int cpu;
+	for_each_tracing_cpu(cpu)
+		tr->data[cpu]->entries = val;
+}
+
+static int __tracing_resize_ring_buffer(unsigned long size, int cpu)
 {
 	int ret;
 
@@ -2985,19 +3013,32 @@ static int __tracing_resize_ring_buffer(unsigned long size)
 	 */
 	ring_buffer_expanded = 1;
 
-	ret = ring_buffer_resize(global_trace.buffer, size);
+	ret = ring_buffer_resize(global_trace.buffer, size, cpu);
 	if (ret < 0)
 		return ret;
 
 	if (!current_trace->use_max_tr)
 		goto out;
 
-	ret = ring_buffer_resize(max_tr.buffer, size);
+	ret = ring_buffer_resize(max_tr.buffer, size, cpu);
 	if (ret < 0) {
-		int r;
+		int r = 0;
+
+		if (cpu == RING_BUFFER_ALL_CPUS) {
+			int i;
+			for_each_tracing_cpu(i) {
+				r = ring_buffer_resize(global_trace.buffer,
+						global_trace.data[i]->entries,
+						i);
+				if (r < 0)
+					break;
+			}
+		} else {
+			r = ring_buffer_resize(global_trace.buffer,
+						global_trace.data[cpu]->entries,
+						cpu);
+		}
 
-		r = ring_buffer_resize(global_trace.buffer,
-				       global_trace.entries);
 		if (r < 0) {
 			/*
 			 * AARGH! We are left with different
@@ -3019,43 +3060,39 @@ static int __tracing_resize_ring_buffer(unsigned long size)
 		return ret;
 	}
 
-	max_tr.entries = size;
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		set_buffer_entries(&max_tr, size);
+	else
+		max_tr.data[cpu]->entries = size;
+
  out:
-	global_trace.entries = size;
+	if (cpu == RING_BUFFER_ALL_CPUS)
+		set_buffer_entries(&global_trace, size);
+	else
+		global_trace.data[cpu]->entries = size;
 
 	return ret;
 }
 
-static ssize_t tracing_resize_ring_buffer(unsigned long size)
+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)) {
+			ret = -EINVAL;
+			goto out;
+		}
 	}
 
-	if (size != global_trace.entries)
-		ret = __tracing_resize_ring_buffer(size);
-
+	ret = __tracing_resize_ring_buffer(size, cpu_id);
 	if (ret < 0)
 		ret = -ENOMEM;
 
-	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();
+out:
 	mutex_unlock(&trace_types_lock);
 
 	return ret;
@@ -3078,7 +3115,8 @@ int tracing_update_buffers(void)
 
 	mutex_lock(&trace_types_lock);
 	if (!ring_buffer_expanded)
-		ret = __tracing_resize_ring_buffer(trace_buf_size);
+		ret = __tracing_resize_ring_buffer(trace_buf_size,
+						RING_BUFFER_ALL_CPUS);
 	mutex_unlock(&trace_types_lock);
 
 	return ret;
@@ -3102,7 +3140,8 @@ static int tracing_set_tracer(const char *buf)
 	mutex_lock(&trace_types_lock);
 
 	if (!ring_buffer_expanded) {
-		ret = __tracing_resize_ring_buffer(trace_buf_size);
+		ret = __tracing_resize_ring_buffer(trace_buf_size,
+						RING_BUFFER_ALL_CPUS);
 		if (ret < 0)
 			goto out;
 		ret = 0;
@@ -3128,8 +3167,8 @@ static int tracing_set_tracer(const char *buf)
 		 * The max_tr ring buffer has some state (e.g. ring->clock) and
 		 * we want preserve it.
 		 */
-		ring_buffer_resize(max_tr.buffer, 1);
-		max_tr.entries = 1;
+		ring_buffer_resize(max_tr.buffer, 1, RING_BUFFER_ALL_CPUS);
+		set_buffer_entries(&max_tr, 1);
 	}
 	destroy_trace_option_files(topts);
 
@@ -3137,10 +3176,17 @@ static int tracing_set_tracer(const char *buf)
 
 	topts = create_trace_option_files(current_trace);
 	if (current_trace->use_max_tr) {
-		ret = ring_buffer_resize(max_tr.buffer, global_trace.entries);
-		if (ret < 0)
-			goto out;
-		max_tr.entries = global_trace.entries;
+		int cpu;
+		/* we need to make per cpu buffer sizes equivalent */
+		for_each_tracing_cpu(cpu) {
+			ret = ring_buffer_resize(max_tr.buffer,
+						global_trace.data[cpu]->entries,
+						cpu);
+			if (ret < 0)
+				goto out;
+			max_tr.data[cpu]->entries =
+					global_trace.data[cpu]->entries;
+		}
 	}
 
 	if (t->init) {
@@ -3642,30 +3688,82 @@ out_err:
 	goto out;
 }
 
+struct ftrace_entries_info {
+	struct trace_array	*tr;
+	int			cpu;
+};
+
+static int tracing_entries_open(struct inode *inode, struct file *filp)
+{
+	struct ftrace_entries_info *info;
+
+	if (tracing_disabled)
+		return -ENODEV;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->tr = &global_trace;
+	info->cpu = (unsigned long)inode->i_private;
+
+	filp->private_data = info;
+
+	return 0;
+}
+
 static ssize_t
 tracing_entries_read(struct file *filp, char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
-	struct trace_array *tr = filp->private_data;
-	char buf[96];
-	int r;
+	struct ftrace_entries_info *info = filp->private_data;
+	struct trace_array *tr = info->tr;
+	char buf[64];
+	int r = 0;
+	ssize_t ret;
 
 	mutex_lock(&trace_types_lock);
-	if (!ring_buffer_expanded)
-		r = sprintf(buf, "%lu (expanded: %lu)\n",
-			    tr->entries >> 10,
-			    trace_buf_size >> 10);
-	else
-		r = sprintf(buf, "%lu\n", tr->entries >> 10);
+
+	if (info->cpu == RING_BUFFER_ALL_CPUS) {
+		int cpu, buf_size_same;
+		unsigned long size;
+
+		size = 0;
+		buf_size_same = 1;
+		/* check if all cpu sizes are same */
+		for_each_tracing_cpu(cpu) {
+			/* fill in the size from first enabled cpu */
+			if (size == 0)
+				size = tr->data[cpu]->entries;
+			if (size != tr->data[cpu]->entries) {
+				buf_size_same = 0;
+				break;
+			}
+		}
+
+		if (buf_size_same) {
+			if (!ring_buffer_expanded)
+				r = sprintf(buf, "%lu (expanded: %lu)\n",
+					    size >> 10,
+					    trace_buf_size >> 10);
+			else
+				r = sprintf(buf, "%lu\n", size >> 10);
+		} else
+			r = sprintf(buf, "X\n");
+	} else
+		r = sprintf(buf, "%lu\n", tr->data[info->cpu]->entries >> 10);
+
 	mutex_unlock(&trace_types_lock);
 
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	return ret;
 }
 
 static ssize_t
 tracing_entries_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
+	struct ftrace_entries_info *info = filp->private_data;
 	unsigned long val;
 	int ret;
 
@@ -3680,7 +3778,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	/* value is in KB */
 	val <<= 10;
 
-	ret = tracing_resize_ring_buffer(val);
+	ret = tracing_resize_ring_buffer(val, info->cpu);
 	if (ret < 0)
 		return ret;
 
@@ -3689,6 +3787,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static int
+tracing_entries_release(struct inode *inode, struct file *filp)
+{
+	struct ftrace_entries_info *info = filp->private_data;
+
+	kfree(info);
+
+	return 0;
+}
+
 static ssize_t
 tracing_total_entries_read(struct file *filp, char __user *ubuf,
 				size_t cnt, loff_t *ppos)
@@ -3700,7 +3808,7 @@ tracing_total_entries_read(struct file *filp, char __user *ubuf,
 
 	mutex_lock(&trace_types_lock);
 	for_each_tracing_cpu(cpu) {
-		size += tr->entries >> 10;
+		size += tr->data[cpu]->entries >> 10;
 		if (!ring_buffer_expanded)
 			expanded_size += trace_buf_size >> 10;
 	}
@@ -3734,7 +3842,7 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp)
 	if (trace_flags & TRACE_ITER_STOP_ON_FREE)
 		tracing_off();
 	/* resize the ring buffer to 0 */
-	tracing_resize_ring_buffer(0);
+	tracing_resize_ring_buffer(0, RING_BUFFER_ALL_CPUS);
 
 	return 0;
 }
@@ -3749,14 +3857,14 @@ 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;
@@ -3795,9 +3903,8 @@ 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 */
@@ -3815,10 +3922,10 @@ 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';
@@ -3833,11 +3940,10 @@ 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;
 }
@@ -3933,9 +4039,10 @@ static const struct file_operations tracing_pipe_fops = {
 };
 
 static const struct file_operations tracing_entries_fops = {
-	.open		= tracing_open_generic,
+	.open		= tracing_entries_open,
 	.read		= tracing_entries_read,
 	.write		= tracing_entries_write,
+	.release	= tracing_entries_release,
 	.llseek		= generic_file_llseek,
 };
 
@@ -4367,6 +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) {
@@ -4387,6 +4497,9 @@ static void tracing_init_debugfs_percpu(long cpu)
 
 	trace_create_file("stats", 0444, d_cpu,
 			(void *) cpu, &tracing_stats_fops);
+
+	trace_create_file("buffer_size_kb", 0444, d_cpu,
+			(void *) cpu, &tracing_entries_fops);
 }
 
 #ifdef CONFIG_FTRACE_SELFTEST
@@ -4718,7 +4831,7 @@ static __init int tracer_init_debugfs(void)
 			(void *) TRACE_PIPE_ALL_CPU, &tracing_pipe_fops);
 
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
-			&global_trace, &tracing_entries_fops);
+			(void *) RING_BUFFER_ALL_CPUS, &tracing_entries_fops);
 
 	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
 			&global_trace, &tracing_total_entries_fops);
@@ -4957,6 +5070,10 @@ __init static int tracer_alloc_buffers(void)
 	if (!alloc_cpumask_var(&tracing_cpumask, GFP_KERNEL))
 		goto out_free_buffer_mask;
 
+	/* Only allocate trace_printk buffers if a trace_printk exists */
+	if (__stop___trace_bprintk_fmt != __start___trace_bprintk_fmt)
+		trace_printk_init_buffers();
+
 	/* To save memory, keep the ring buffer size to its minimum */
 	if (ring_buffer_expanded)
 		ring_buf_size = trace_buf_size;
@@ -4975,7 +5092,6 @@ __init static int tracer_alloc_buffers(void)
 		WARN_ON(1);
 		goto out_free_cpumask;
 	}
-	global_trace.entries = ring_buffer_size(global_trace.buffer);
 	if (global_trace.buffer_disabled)
 		tracing_off();
 
@@ -4988,7 +5104,6 @@ __init static int tracer_alloc_buffers(void)
 		ring_buffer_free(global_trace.buffer);
 		goto out_free_cpumask;
 	}
-	max_tr.entries = 1;
 #endif
 
 	/* Allocate the first page for all buffers */
@@ -4997,6 +5112,12 @@ __init static int tracer_alloc_buffers(void)
 		max_tr.data[i] = &per_cpu(max_tr_data, i);
 	}
 
+	set_buffer_entries(&global_trace,
+			   ring_buffer_size(global_trace.buffer, 0));
+#ifdef CONFIG_TRACER_MAX_TRACE
+	set_buffer_entries(&max_tr, 1);
+#endif
+
 	trace_init_cmdlines();
 
 	register_tracer(&nop_trace);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f95d65d..6c6f793 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -131,6 +131,7 @@ struct trace_array_cpu {
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
+	unsigned long		entries;
 	unsigned long		saved_latency;
 	unsigned long		critical_start;
 	unsigned long		critical_end;
@@ -152,7 +153,6 @@ struct trace_array_cpu {
  */
 struct trace_array {
 	struct ring_buffer	*buffer;
-	unsigned long		entries;
 	int			cpu;
 	int			buffer_disabled;
 	cycle_t			time_start;
@@ -826,6 +826,8 @@ extern struct list_head ftrace_events;
 extern const char *__start___trace_bprintk_fmt[];
 extern const char *__stop___trace_bprintk_fmt[];
 
+void trace_printk_init_buffers(void);
+
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter)	\
 	extern struct ftrace_event_call					\
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 6fd4ffd..a9077c1 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -51,6 +51,10 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 	const char **iter;
 	char *fmt;
 
+	/* allocate the trace_printk per cpu buffers */
+	if (start != end)
+		trace_printk_init_buffers();
+
 	mutex_lock(&btrace_mutex);
 	for (iter = start; iter < end; iter++) {
 		struct trace_bprintk_fmt *tb_fmt = lookup_format(*iter);