[PATCH 0/5] [GIT PULL] tracing: updates for 3.5

[PATCH 0/5] [GIT PULL] tracing: updates for 3.5

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 1259 bytes --]


Ingo,

Please pull the latest tip/perf/core tree, which can be found at:

  git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace.git
tip/perf/core

Head SHA1: 61463fad01fe416ab55d56a970a707b33d081436


Dan Carpenter (1):
      tracing: Remove an unneeded check in trace_seq_buffer()

Steven Rostedt (3):
      tracing: Add percpu buffers for trace_printk()
      ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine
      ftrace/x86: Remove the complex ftrace NMI handling code

Vaibhav Nagarnaik (1):
      ring-buffer: Add per_cpu ring buffer control files

----
 arch/x86/Kconfig              |    1 -
 arch/x86/include/asm/ftrace.h |    4 +
 arch/x86/kernel/ftrace.c      |  512 +++++++++++++++++++++++++++--------------
 arch/x86/kernel/nmi.c         |   10 +-
 arch/x86/kernel/traps.c       |    9 +-
 include/linux/ftrace.h        |    6 +
 include/linux/kernel.h        |   13 +-
 include/linux/ring_buffer.h   |    6 +-
 kernel/trace/ring_buffer.c    |  248 +++++++++++---------
 kernel/trace/trace.c          |  379 ++++++++++++++++++++++--------
 kernel/trace/trace.h          |    4 +-
 kernel/trace/trace_printk.c   |    4 +
 12 files changed, 813 insertions(+), 383 deletions(-)

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 1/5] tracing: Add percpu buffers for trace_printk()

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 11523 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.

Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().

Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.

A buffer is made for each type of context:

  normal
  softirq
  irq
  nmi

The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.

Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/kernel.h      |   13 +--
 kernel/trace/trace.c        |  184 +++++++++++++++++++++++++++++++------------
 kernel/trace/trace.h        |    2 +
 kernel/trace/trace_printk.c |    4 +
 4 files changed, 148 insertions(+), 55 deletions(-)

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 645231c..c0d3442 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -480,15 +480,16 @@ do {									\
 
 #define trace_printk(fmt, args...)					\
 do {									\
+	static const char *trace_printk_fmt				\
+		__attribute__((section("__trace_printk_fmt"))) =	\
+		__builtin_constant_p(fmt) ? fmt : NULL;			\
+									\
 	__trace_printk_check_format(fmt, ##args);			\
-	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
-		  __attribute__((section("__trace_printk_fmt"))) =	\
-			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\
+	if (__builtin_constant_p(fmt))					\
 		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
-	} else								\
-		__trace_printk(_THIS_IP_, fmt, ##args);		\
+	else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);			\
 } while (0)
 
 extern __printf(2, 3)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ed7b5d1..1ab8e35 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1498,25 +1498,119 @@ 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 +1620,36 @@ 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 +1675,53 @@ 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;
 }
@@ -4955,6 +5037,10 @@ __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;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 95059f0..f9d8550 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -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);
-- 
1.7.9.5



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 2/5] tracing: Remove an unneeded check in trace_seq_buffer()

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 1292 bytes --]

From: Dan Carpenter <dan.carpenter@oracle.com>

memcpy() returns a pointer to "bug".  Hopefully, it's not NULL here or
we would already have Oopsed.

Link: http://lkml.kernel.org/r/20120420063145.GA22649@elgon.mountain

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c |    5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1ab8e35..bbcde54 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -629,7 +629,6 @@ 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 +636,7 @@ 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;
-- 
1.7.9.5



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 3/5] ring-buffer: Add per_cpu ring buffer control files

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 27323 bytes --]

From: Vaibhav Nagarnaik <vnagarnaik@google.com>

Add a debugfs entry under per_cpu/ folder for each cpu called
buffer_size_kb to control the ring buffer size for each CPU
independently.

If the global file buffer_size_kb is used to set size, the individual
ring buffers will be adjusted to the given size. The buffer_size_kb will
report the common size to maintain backward compatibility.

If the buffer_size_kb file under the per_cpu/ directory is used to
change buffer size for a specific CPU, only the size of the respective
ring buffer is updated. When tracing/buffer_size_kb is read, it reports
'X' to indicate that sizes of per_cpu ring buffers are not equivalent.

Link: http://lkml.kernel.org/r/1328212844-11889-1-git-send-email-vnagarnaik@google.com

Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Michael Rubin <mrubin@google.com>
Cc: David Sharp <dhsharp@google.com>
Cc: Justin Teravest <teravest@google.com>
Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |    6 +-
 kernel/trace/ring_buffer.c  |  248 ++++++++++++++++++++++++-------------------
 kernel/trace/trace.c        |  190 ++++++++++++++++++++++++++-------
 kernel/trace/trace.h        |    2 +-
 4 files changed, 297 insertions(+), 149 deletions(-)

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 7be2e88..6c8835f 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -96,9 +96,11 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k
 	__ring_buffer_alloc((size), (flags), &__key);	\
 })
 
+#define RING_BUFFER_ALL_CPUS -1
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
-int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, int cpu);
 
 void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
 
@@ -129,7 +131,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts);
 void ring_buffer_iter_reset(struct ring_buffer_iter *iter);
 int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
 
-unsigned long ring_buffer_size(struct ring_buffer *buffer);
+unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu);
 
 void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_reset(struct ring_buffer *buffer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index cf8d11e..2d5eb33 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -449,6 +449,7 @@ 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 */
@@ -466,10 +467,12 @@ 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 ring_buffer {
-	unsigned			pages;
 	unsigned			flags;
 	int				cpus;
 	atomic_t			record_disabled;
@@ -963,14 +966,10 @@ 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 +980,13 @@ 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 +994,27 @@ 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 +1023,15 @@ 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;
@@ -1052,7 +1065,7 @@ 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 +1126,7 @@ 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 +1137,14 @@ 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 +1167,7 @@ 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;
 	}
@@ -1276,6 +1289,18 @@ out:
 	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
+static void update_pages_handler(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;
+}
+
 /**
  * ring_buffer_resize - resize the ring buffer
  * @buffer: the buffer to resize.
@@ -1285,14 +1310,12 @@ out:
  *
  * Returns -1 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;
 
 	/*
 	 * Always succeed at resizing a non-existent buffer:
@@ -1302,15 +1325,11 @@ 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);
 
 	/* Make sure all writers are done with this buffer. */
@@ -1321,68 +1340,56 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
 	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
-	if (size < buffer_size) {
-
-		/* easy case, just free pages */
-		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages))
-			goto out_fail;
-
-		rm_pages = buffer->pages - nr_pages;
-
+	if (cpu_id == RING_BUFFER_ALL_CPUS) {
+		/* calculate the pages to update */
 		for_each_buffer_cpu(buffer, cpu) {
 			cpu_buffer = buffer->buffers[cpu];
-			rb_remove_pages(cpu_buffer, rm_pages);
-		}
-		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;
+			cpu_buffer->nr_pages_to_update = nr_pages -
+							cpu_buffer->nr_pages;
 
-	new_pages = nr_pages - buffer->pages;
+			/*
+			 * nothing more to do for removing pages or no update
+			 */
+			if (cpu_buffer->nr_pages_to_update <= 0)
+				continue;
 
-	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.
+			 * to add pages, make sure all new pages can be
+			 * allocated without receiving ENOMEM
 			 */
-			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);
+			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 */
+				goto no_mem;
 		}
-	}
 
-	for_each_buffer_cpu(buffer, cpu) {
-		cpu_buffer = buffer->buffers[cpu];
-		rb_insert_pages(cpu_buffer, &pages, new_pages);
-	}
+		/* 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);
+			}
+		}
+	} else {
+		cpu_buffer = buffer->buffers[cpu_id];
+		if (nr_pages == cpu_buffer->nr_pages)
+			goto out;
 
-	if (RB_WARN_ON(buffer, !list_empty(&pages)))
-		goto out_fail;
+		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))
+			goto no_mem;
+
+		update_pages_handler(cpu_buffer);
+	}
 
  out:
-	buffer->pages = nr_pages;
 	put_online_cpus();
 	mutex_unlock(&buffer->mutex);
 
@@ -1390,25 +1397,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
 	return size;
 
- free_pages:
-	list_for_each_entry_safe(bpage, tmp, &pages, list) {
-		list_del_init(&bpage->list);
-		free_buffer_page(bpage);
+ no_mem:
+	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;
-
-	/*
-	 * Something went totally wrong, and we are too paranoid
-	 * to even clean up the mess.
-	 */
- out_fail:
-	put_online_cpus();
-	mutex_unlock(&buffer->mutex);
-	atomic_dec(&buffer->record_disabled);
-	return -1;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_resize);
 
@@ -1510,7 +1516,7 @@ 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)))
@@ -3588,9 +3594,18 @@ 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);
 
@@ -3765,8 +3780,11 @@ 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 +3798,6 @@ 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 +4086,8 @@ 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 +4095,23 @@ 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 bbcde54..f11a285 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -838,7 +838,8 @@ __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);
@@ -854,7 +855,8 @@ __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");
 	}
@@ -3053,7 +3055,14 @@ 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;
 
@@ -3064,19 +3073,32 @@ 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
@@ -3098,14 +3120,21 @@ 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;
 
@@ -3121,12 +3150,19 @@ static ssize_t tracing_resize_ring_buffer(unsigned long size)
 			atomic_inc(&max_tr.data[cpu]->disabled);
 	}
 
-	if (size != global_trace.entries)
-		ret = __tracing_resize_ring_buffer(size);
+	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;
+		}
+	}
 
+	ret = __tracing_resize_ring_buffer(size, cpu_id);
 	if (ret < 0)
 		ret = -ENOMEM;
 
+out:
 	for_each_tracing_cpu(cpu) {
 		if (global_trace.data[cpu])
 			atomic_dec(&global_trace.data[cpu]->disabled);
@@ -3157,7 +3193,8 @@ 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;
@@ -3181,7 +3218,8 @@ 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;
@@ -3207,8 +3245,8 @@ 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);
 
@@ -3216,10 +3254,17 @@ 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) {
@@ -3721,30 +3766,82 @@ 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;
 
@@ -3759,7 +3856,7 @@ 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;
 
@@ -3768,6 +3865,16 @@ 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)
@@ -3779,7 +3886,7 @@ 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;
 	}
@@ -3813,7 +3920,7 @@ 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;
 }
@@ -4012,9 +4119,10 @@ 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,
 };
 
@@ -4466,6 +4574,9 @@ 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
@@ -4795,7 +4906,7 @@ 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);
@@ -5056,7 +5167,6 @@ __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();
 
@@ -5069,7 +5179,6 @@ __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 */
@@ -5078,6 +5187,11 @@ __init static int tracer_alloc_buffers(void)
 		max_tr.data[i] = &per_cpu(max_tr_data, i);
 	}
 
+	set_buffer_entries(&global_trace, ring_buf_size);
+#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 f9d8550..1c8b7c6 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;
-- 
1.7.9.5



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 4/5] ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 12160 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

This method changes x86 to add a breakpoint to the mcount locations
instead of calling stop machine.

Now that iret can be handled by NMIs, we perform the following to
update code:

1) Add a breakpoint to all locations that will be modified

2) Sync all cores

3) Update all locations to be either a nop or call (except breakpoint
   op)

4) Sync all cores

5) Remove the breakpoint with the new code.

6) Sync all cores

[
  Added updates that Masami suggested:
   Use unlikely(modifying_ftrace_code) in int3 trap to keep kprobes efficient.
   Don't use NOTIFY_* in ftrace handler in int3 as it is not a notifier.
]

Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/include/asm/ftrace.h |    4 +
 arch/x86/kernel/ftrace.c      |  343 +++++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/traps.c       |    9 +-
 include/linux/ftrace.h        |    6 +
 4 files changed, 361 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 268c783..f866c10 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -34,6 +34,7 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
+extern int modifying_ftrace_code;
 
 static inline unsigned long ftrace_call_adjust(unsigned long addr)
 {
@@ -50,6 +51,9 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
+int ftrace_int3_handler(int cmd, const char *str,
+		struct pt_regs *regs, long err, int trap, int sig);
+
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c9a281f..24108af 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
+#include <linux/kprobes.h>
 
 #include <trace/syscall.h>
 
@@ -334,6 +335,348 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
+int modifying_ftrace_code __read_mostly;
+
+/*
+ * A breakpoint was added to the code address we are about to
+ * modify, and this is the handle that will just skip over it.
+ * We are either changing a nop into a trace call, or a trace
+ * call to a nop. While the change is taking place, we treat
+ * it just like it was a nop.
+ */
+int ftrace_int3_handler(int cmd, const char *str,
+		 struct pt_regs *regs, long err, int trap, int sig)
+{
+	if (!modifying_ftrace_code || cmd != DIE_INT3 || !regs)
+		return 0;
+
+	if (!ftrace_location(regs->ip - 1))
+		return 0;
+
+	regs->ip += MCOUNT_INSN_SIZE - 1;
+
+	return 1;
+}
+
+static int ftrace_write(unsigned long ip, const char *val, int size)
+{
+	/*
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
+	 */
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa(ip));
+
+	return probe_kernel_write((void *)ip, val, size);
+}
+
+static int add_break(unsigned long ip, const char *old)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	if (ftrace_write(ip, &brk, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned const char *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+
+	return add_break(rec->ip, old);
+}
+
+
+static int add_brk_on_nop(struct dyn_ftrace *rec)
+{
+	unsigned const char *old;
+
+	old = ftrace_nop_replace();
+
+	return add_break(rec->ip, old);
+}
+
+static int add_breakpoints(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_brk_on_nop(rec);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_brk_on_call(rec, ftrace_addr);
+	}
+	return 0;
+}
+
+/*
+ * On error, we need to remove breakpoints. This needs to
+ * be done caefully. If the address does not currently have a
+ * breakpoint, we know we are done. Otherwise, we look at the
+ * remaining 4 bytes of the instruction. If it matches a nop
+ * we replace the breakpoint with the nop. Otherwise we replace
+ * it with the call instruction.
+ */
+static int remove_breakpoint(struct dyn_ftrace *rec)
+{
+	unsigned char ins[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+	const unsigned char *nop;
+	unsigned long ftrace_addr;
+	unsigned long ip = rec->ip;
+
+	/* If we fail the read, just give up */
+	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* If this does not have a breakpoint, we are done */
+	if (ins[0] != brk)
+		return -1;
+
+	nop = ftrace_nop_replace();
+
+	/*
+	 * If the last 4 bytes of the instruction do not match
+	 * a nop, then we assume that this is a call to ftrace_addr.
+	 */
+	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
+		/*
+		 * For extra paranoidism, we check if the breakpoint is on
+		 * a call that would actually jump to the ftrace_addr.
+		 * If not, don't touch the breakpoint, we make just create
+		 * a disaster.
+		 */
+		ftrace_addr = (unsigned long)FTRACE_ADDR;
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
+			return -EINVAL;
+	}
+
+	return probe_kernel_write((void *)ip, &nop[0], 1);
+}
+
+static int add_update_code(unsigned long ip, unsigned const char *new)
+{
+	/* skip breakpoint */
+	ip++;
+	new++;
+	if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
+		return -EPERM;
+	return 0;
+}
+
+static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+	return add_update_code(ip, new);
+}
+
+static int add_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+	return add_update_code(ip, new);
+}
+
+static int add_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_test_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+
+	return 0;
+}
+
+static int finish_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+
+	if (ftrace_write(ip, new, 1))
+		return -EPERM;
+	return 0;
+}
+
+static int finish_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return finish_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return finish_update_nop(rec);
+	}
+
+	return 0;
+}
+
+static void do_sync_core(void *data)
+{
+	sync_core();
+}
+
+static void run_sync(void)
+{
+	int enable_irqs = irqs_disabled();
+
+	/* We may be called with interrupts disbled (on bootup). */
+	if (enable_irqs)
+		local_irq_enable();
+	on_each_cpu(do_sync_core, NULL, 1);
+	if (enable_irqs)
+		local_irq_disable();
+}
+
+static void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	const char *report = "adding breakpoints";
+	int count = 0;
+	int ret;
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_breakpoints(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+		count++;
+	}
+
+	run_sync();
+
+	report = "updating code";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	report = "removing breakpoints";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = finish_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	return;
+
+ remove_breakpoints:
+	ftrace_bug(ret, rec ? rec->ip : 0);
+	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+		remove_breakpoint(rec);
+	}
+}
+
+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();
+
+	modifying_ftrace_code--;
+}
+
 int __init ftrace_dyn_arch_init(void *data)
 {
 	/* The return code is retured via data */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ff9281f1..1712485 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -50,6 +50,7 @@
 #include <asm/processor.h>
 #include <asm/debugreg.h>
 #include <linux/atomic.h>
+#include <asm/ftrace.h>
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/i387.h>
@@ -303,8 +304,14 @@ gp_in_kernel:
 }
 
 /* May run on IST stack. */
-dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
+dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
+#ifdef CONFIG_FUNCTION_TRACER
+	/* ftrace must be first, everything else may cause a recursive crash */
+	if (unlikely(modifying_ftrace_code) &&
+	    ftrace_int3_handler(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP))
+		return;
+#endif
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
 	if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
 				SIGTRAP) == NOTIFY_STOP)
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 72a6cab..0b55903 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -286,6 +286,12 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void);
 struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter);
 struct dyn_ftrace *ftrace_rec_iter_record(struct ftrace_rec_iter *iter);
 
+#define for_ftrace_rec_iter(iter)		\
+	for (iter = ftrace_rec_iter_start();	\
+	     iter;				\
+	     iter = ftrace_rec_iter_next(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);
-- 
1.7.9.5



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

[PATCH 5/5] ftrace/x86: Remove the complex ftrace NMI handling code

[Steven Rostedt]

[-- Attachment #1: Type: text/plain, Size: 9407 bytes --]

From: Steven Rostedt <srostedt@redhat.com>

As ftrace function tracing would require modifying code that could
be executed in NMI context, which is not stopped with stop_machine(),
ftrace had to do a complex algorithm with various stages of setup
and memory barriers to make it work.

With the new breakpoint method, this is no longer required. The changes
to the code can be done without any problem in NMI context, as well as
without stop machine altogether. Remove the complex code as it is
no longer needed.

Also, a lot of the notrace annotations could be removed from the
NMI code as it is now safe to trace them. With the exception of
do_nmi itself, which does some special work to handle running in
the debug stack. The breakpoint method can cause NMIs to double
nest the debug stack if it's not setup properly, and that is done
in do_nmi(), thus that function must not be traced.

(Note the arch sh may want to do the same)

Cc: Paul Mundt <lethal@linux-sh.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 arch/x86/Kconfig         |    1 -
 arch/x86/kernel/ftrace.c |  169 +---------------------------------------------
 arch/x86/kernel/nmi.c    |   10 +--
 3 files changed, 6 insertions(+), 174 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d14cc6..1324139 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -40,7 +40,6 @@ config X86
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
-	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KVM
 	select HAVE_ARCH_KGDB
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 24108af..db97bd1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -27,38 +27,18 @@
 #include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <asm/nops.h>
-#include <asm/nmi.h>
-
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
-/*
- * modifying_code is set to notify NMIs that they need to use
- * memory barriers when entering or exiting. But we don't want
- * to burden NMIs with unnecessary memory barriers when code
- * modification is not being done (which is most of the time).
- *
- * A mutex is already held when ftrace_arch_code_modify_prepare
- * and post_process are called. No locks need to be taken here.
- *
- * Stop machine will make sure currently running NMIs are done
- * and new NMIs will see the updated variable before we need
- * to worry about NMIs doing memory barriers.
- */
-static int modifying_code __read_mostly;
-static DEFINE_PER_CPU(int, save_modifying_code);
-
 int ftrace_arch_code_modify_prepare(void)
 {
 	set_kernel_text_rw();
 	set_all_modules_text_rw();
-	modifying_code = 1;
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
 {
-	modifying_code = 0;
 	set_all_modules_text_ro();
 	set_kernel_text_ro();
 	return 0;
@@ -91,134 +71,6 @@ static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-/*
- * Modifying code must take extra care. On an SMP machine, if
- * the code being modified is also being executed on another CPU
- * that CPU will have undefined results and possibly take a GPF.
- * We use kstop_machine to stop other CPUS from exectuing code.
- * But this does not stop NMIs from happening. We still need
- * to protect against that. We separate out the modification of
- * the code to take care of this.
- *
- * Two buffers are added: An IP buffer and a "code" buffer.
- *
- * 1) Put the instruction pointer into the IP buffer
- *    and the new code into the "code" buffer.
- * 2) Wait for any running NMIs to finish and set a flag that says
- *    we are modifying code, it is done in an atomic operation.
- * 3) Write the code
- * 4) clear the flag.
- * 5) Wait for any running NMIs to finish.
- *
- * If an NMI is executed, the first thing it does is to call
- * "ftrace_nmi_enter". This will check if the flag is set to write
- * and if it is, it will write what is in the IP and "code" buffers.
- *
- * The trick is, it does not matter if everyone is writing the same
- * content to the code location. Also, if a CPU is executing code
- * it is OK to write to that code location if the contents being written
- * are the same as what exists.
- */
-
-#define MOD_CODE_WRITE_FLAG (1 << 31)	/* set when NMI should do the write */
-static atomic_t nmi_running = ATOMIC_INIT(0);
-static int mod_code_status;		/* holds return value of text write */
-static void *mod_code_ip;		/* holds the IP to write to */
-static const void *mod_code_newcode;	/* holds the text to write to the IP */
-
-static unsigned nmi_wait_count;
-static atomic_t nmi_update_count = ATOMIC_INIT(0);
-
-int ftrace_arch_read_dyn_info(char *buf, int size)
-{
-	int r;
-
-	r = snprintf(buf, size, "%u %u",
-		     nmi_wait_count,
-		     atomic_read(&nmi_update_count));
-	return r;
-}
-
-static void clear_mod_flag(void)
-{
-	int old = atomic_read(&nmi_running);
-
-	for (;;) {
-		int new = old & ~MOD_CODE_WRITE_FLAG;
-
-		if (old == new)
-			break;
-
-		old = atomic_cmpxchg(&nmi_running, old, new);
-	}
-}
-
-static void ftrace_mod_code(void)
-{
-	/*
-	 * Yes, more than one CPU process can be writing to mod_code_status.
-	 *    (and the code itself)
-	 * But if one were to fail, then they all should, and if one were
-	 * to succeed, then they all should.
-	 */
-	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
-					     MCOUNT_INSN_SIZE);
-
-	/* if we fail, then kill any new writers */
-	if (mod_code_status)
-		clear_mod_flag();
-}
-
-void ftrace_nmi_enter(void)
-{
-	__this_cpu_write(save_modifying_code, modifying_code);
-
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	if (atomic_inc_return(&nmi_running) & MOD_CODE_WRITE_FLAG) {
-		smp_rmb();
-		ftrace_mod_code();
-		atomic_inc(&nmi_update_count);
-	}
-	/* Must have previous changes seen before executions */
-	smp_mb();
-}
-
-void ftrace_nmi_exit(void)
-{
-	if (!__this_cpu_read(save_modifying_code))
-		return;
-
-	/* Finish all executions before clearing nmi_running */
-	smp_mb();
-	atomic_dec(&nmi_running);
-}
-
-static void wait_for_nmi_and_set_mod_flag(void)
-{
-	if (!atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_cmpxchg(&nmi_running, 0, MOD_CODE_WRITE_FLAG));
-
-	nmi_wait_count++;
-}
-
-static void wait_for_nmi(void)
-{
-	if (!atomic_read(&nmi_running))
-		return;
-
-	do {
-		cpu_relax();
-	} while (atomic_read(&nmi_running));
-
-	nmi_wait_count++;
-}
-
 static inline int
 within(unsigned long addr, unsigned long start, unsigned long end)
 {
@@ -239,26 +91,7 @@ do_ftrace_mod_code(unsigned long ip, const void *new_code)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa(ip));
 
-	mod_code_ip = (void *)ip;
-	mod_code_newcode = new_code;
-
-	/* The buffers need to be visible before we let NMIs write them */
-	smp_mb();
-
-	wait_for_nmi_and_set_mod_flag();
-
-	/* Make sure all running NMIs have finished before we write the code */
-	smp_mb();
-
-	ftrace_mod_code();
-
-	/* Make sure the write happens before clearing the bit */
-	smp_mb();
-
-	clear_mod_flag();
-	wait_for_nmi();
-
-	return mod_code_status;
+	return probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE);
 }
 
 static const unsigned char *ftrace_nop_replace(void)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 47acaf3..eb1539e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -84,7 +84,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 
 #define nmi_to_desc(type) (&nmi_desc[type])
 
-static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
+static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
 	struct nmi_desc *desc = nmi_to_desc(type);
 	struct nmiaction *a;
@@ -209,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name)
 
 EXPORT_SYMBOL_GPL(unregister_nmi_handler);
 
-static notrace __kprobes void
+static __kprobes void
 pci_serr_error(unsigned char reason, struct pt_regs *regs)
 {
 	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
@@ -236,7 +236,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 io_check_error(unsigned char reason, struct pt_regs *regs)
 {
 	unsigned long i;
@@ -263,7 +263,7 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	outb(reason, NMI_REASON_PORT);
 }
 
-static notrace __kprobes void
+static __kprobes void
 unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 {
 	int handled;
@@ -305,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 static DEFINE_PER_CPU(bool, swallow_nmi);
 static DEFINE_PER_CPU(unsigned long, last_nmi_rip);
 
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+static __kprobes void default_do_nmi(struct pt_regs *regs)
 {
 	unsigned char reason = 0;
 	int handled;
-- 
1.7.9.5



[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 836 bytes --]

Re: [PATCH 4/5] ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine

[Masami Hiramatsu]

(2012/04/26 3:48), Steven Rostedt wrote:
> From: Steven Rostedt <srostedt@redhat.com>
> 
> This method changes x86 to add a breakpoint to the mcount locations
> instead of calling stop machine.
> 
> Now that iret can be handled by NMIs, we perform the following to
> update code:
> 
> 1) Add a breakpoint to all locations that will be modified
> 
> 2) Sync all cores
> 
> 3) Update all locations to be either a nop or call (except breakpoint
>    op)
> 
> 4) Sync all cores
> 
> 5) Remove the breakpoint with the new code.
> 
> 6) Sync all cores
> 
> [
>   Added updates that Masami suggested:
>    Use unlikely(modifying_ftrace_code) in int3 trap to keep kprobes efficient.
>    Don't use NOTIFY_* in ftrace handler in int3 as it is not a notifier.
> ]

I just have a few comments :)

[...]
> +int modifying_ftrace_code __read_mostly;
> +
> +/*
> + * A breakpoint was added to the code address we are about to
> + * modify, and this is the handle that will just skip over it.
> + * We are either changing a nop into a trace call, or a trace
> + * call to a nop. While the change is taking place, we treat
> + * it just like it was a nop.
> + */
> +int ftrace_int3_handler(int cmd, const char *str,
> +		 struct pt_regs *regs, long err, int trap, int sig)
> +{
> +	if (!modifying_ftrace_code || cmd != DIE_INT3 || !regs)
> +		return 0;
> +

At this moment, all of these checks are meaningless, because
this is not a handler but just a fixup code in int3 isr. :)
So, I think you can just define "int ftrace_int3_fixup(regs)"
for this purpose.

> +	if (!ftrace_location(regs->ip - 1))
> +		return 0;
> +
> +	regs->ip += MCOUNT_INSN_SIZE - 1;
> +
> +	return 1;
> +}

[...]

> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index ff9281f1..1712485 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -50,6 +50,7 @@
>  #include <asm/processor.h>
>  #include <asm/debugreg.h>
>  #include <linux/atomic.h>
> +#include <asm/ftrace.h>
>  #include <asm/traps.h>
>  #include <asm/desc.h>
>  #include <asm/i387.h>
> @@ -303,8 +304,14 @@ gp_in_kernel:
>  }
>  
>  /* May run on IST stack. */
> -dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
> +dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
>  {
> +#ifdef CONFIG_FUNCTION_TRACER

I guess CONFIG_DYNAMIC_FTRACE ?

> +	/* ftrace must be first, everything else may cause a recursive crash */
> +	if (unlikely(modifying_ftrace_code) &&
> +	    ftrace_int3_handler(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP))
> +		return;
> +#endif

Thank you!

-- 
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: masami.hiramatsu.pt@hitachi.com

Re: [PATCH 4/5] ftrace/x86: Have arch x86_64 use breakpoints instead of stop machine

[Steven Rostedt]

On Thu, 2012-04-26 at 19:43 +0900, Masami Hiramatsu wrote:
> (2012/04/26 3:48), Steven Rostedt wrote:
> > From: Steven Rostedt <srostedt@redhat.com>
> > 
> > This method changes x86 to add a breakpoint to the mcount locations
> > instead of calling stop machine.
> > 
> > Now that iret can be handled by NMIs, we perform the following to
> > update code:
> > 
> > 1) Add a breakpoint to all locations that will be modified
> > 
> > 2) Sync all cores
> > 
> > 3) Update all locations to be either a nop or call (except breakpoint
> >    op)
> > 
> > 4) Sync all cores
> > 
> > 5) Remove the breakpoint with the new code.
> > 
> > 6) Sync all cores
> > 
> > [
> >   Added updates that Masami suggested:
> >    Use unlikely(modifying_ftrace_code) in int3 trap to keep kprobes efficient.
> >    Don't use NOTIFY_* in ftrace handler in int3 as it is not a notifier.
> > ]
> 
> I just have a few comments :)
> 

Thanks Masami,

below is the changes I made. I'll post a v2.

-- Steve

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index f866c10..18d9005 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -51,8 +51,7 @@ struct dyn_arch_ftrace {
 	/* No extra data needed for x86 */
 };
 
-int ftrace_int3_handler(int cmd, const char *str,
-		struct pt_regs *regs, long err, int trap, int sig);
+int ftrace_int3_handler(struct pt_regs *regs);
 
 #endif /*  CONFIG_DYNAMIC_FTRACE */
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 24108af..80af347 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -344,10 +344,9 @@ int modifying_ftrace_code __read_mostly;
  * call to a nop. While the change is taking place, we treat
  * it just like it was a nop.
  */
-int ftrace_int3_handler(int cmd, const char *str,
-		 struct pt_regs *regs, long err, int trap, int sig)
+int ftrace_int3_handler(struct pt_regs *regs)
 {
-	if (!modifying_ftrace_code || cmd != DIE_INT3 || !regs)
+	if (WARN_ON_ONCE(!regs))
 		return 0;
 
 	if (!ftrace_location(regs->ip - 1))
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1712485..92d5756 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -306,10 +306,9 @@ gp_in_kernel:
 /* May run on IST stack. */
 dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code)
 {
-#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
 	/* ftrace must be first, everything else may cause a recursive crash */
-	if (unlikely(modifying_ftrace_code) &&
-	    ftrace_int3_handler(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP))
+	if (unlikely(modifying_ftrace_code) && ftrace_int3_handler(regs))
 		return;
 #endif
 #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP