From 215368e8e59023d6a0abdda896923018d74fdf7f Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Mon, 15 Jun 2009 10:56:42 +0800
Subject: tracing: fix a typo in tracing_cpumask_write()

It's tracing_cpumask_new that should be kfree()ed.

This causes tracing_cpumask to be freed due to the typo:

 # echo z > tracing_cpumask
 bash: echo: write error: Invalid argument

And subsequent reads/writes to tracing_cpuamsk will access this
already-freed tracing_cpumask, thus may lead to crash.

[ Impact: fix leak and crash when writing invalid val to tracing_cpumask ]

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A35B86A.7070608@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8acd9b81a5d7..7355a38e18be 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2191,11 +2191,12 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
 		return -ENOMEM;
 
-	mutex_lock(&tracing_cpumask_update_lock);
 	err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
 	if (err)
 		goto err_unlock;
 
+	mutex_lock(&tracing_cpumask_update_lock);
+
 	local_irq_disable();
 	__raw_spin_lock(&ftrace_max_lock);
 	for_each_tracing_cpu(cpu) {
@@ -2223,8 +2224,7 @@ tracing_cpumask_write(struct file *filp, const char __user *ubuf,
 	return count;
 
 err_unlock:
-	mutex_unlock(&tracing_cpumask_update_lock);
-	free_cpumask_var(tracing_cpumask);
+	free_cpumask_var(tracing_cpumask_new);
 
 	return err;
 }
-- 
cgit v1.2.3


From e4f2d10f479d18198ebafcb5e124cc3dd8b8817a Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Mon, 15 Jun 2009 10:57:28 +0800
Subject: tracing: replace a GFP_ATOMIC with GFP_KERNEL allocation

Atomic allocation is not needed here.

[ Impact: clean up of memory alloction type ]

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <4A35B898.2050607@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7355a38e18be..0f57f1b443b6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3627,7 +3627,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	struct trace_seq *s;
 	unsigned long cnt;
 
-	s = kmalloc(sizeof(*s), GFP_ATOMIC);
+	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
 		return ENOMEM;
 
-- 
cgit v1.2.3


From f129e965bef40c6153e4fe505f1e408286213424 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Wed, 24 Jun 2009 09:53:44 +0800
Subject: tracing: Reset iterator in t_start()

The iterator is m->private, but it's not reset to trace_types in
t_start(). If the output is larger than PAGE_SIZE and t_start()
is called the 2nd time, things will go wrong.

Reviewed-by: Liming Wang <liming.wang@windriver.com>
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A418728.5020506@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/trace.c | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 076fa6f0ee48..3bb31006b5cc 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2053,25 +2053,23 @@ static int tracing_open(struct inode *inode, struct file *file)
 static void *
 t_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t = v;
 
 	(*pos)++;
 
 	if (t)
 		t = t->next;
 
-	m->private = t;
-
 	return t;
 }
 
 static void *t_start(struct seq_file *m, loff_t *pos)
 {
-	struct tracer *t = m->private;
+	struct tracer *t;
 	loff_t l = 0;
 
 	mutex_lock(&trace_types_lock);
-	for (; t && l < *pos; t = t_next(m, t, &l))
+	for (t = trace_types; t && l < *pos; t = t_next(m, t, &l))
 		;
 
 	return t;
@@ -2107,18 +2105,10 @@ static struct seq_operations show_traces_seq_ops = {
 
 static int show_traces_open(struct inode *inode, struct file *file)
 {
-	int ret;
-
 	if (tracing_disabled)
 		return -ENODEV;
 
-	ret = seq_open(file, &show_traces_seq_ops);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = trace_types;
-	}
-
-	return ret;
+	return seq_open(file, &show_traces_seq_ops);
 }
 
 static ssize_t
-- 
cgit v1.2.3


From 9d612beff5089b89a295a2331883a8ce3fff08c1 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Wed, 24 Jun 2009 17:33:15 +0800
Subject: tracing: Fix trace_buf_size boot option

We should be able to specify [KMG] when setting trace_buf_size
boot option, as documented in kernel-parameters.txt

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A41F2DB.4020102@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/kernel-parameters.txt | 3 ++-
 kernel/trace/trace.c                | 5 ++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 92e1ab8178a8..d3f41db3ed49 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2475,7 +2475,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	tp720=		[HW,PS2]
 
-	trace_buf_size=nn[KMG] [ftrace] will set tracing buffer size.
+	trace_buf_size=nn[KMG]
+			[FTRACE] will set tracing buffer size.
 
 	trix=		[HW,OSS] MediaTrix AudioTrix Pro
 			Format:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3bb31006b5cc..3aa0a0dfdfa8 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -284,13 +284,12 @@ void trace_wake_up(void)
 static int __init set_buf_size(char *str)
 {
 	unsigned long buf_size;
-	int ret;
 
 	if (!str)
 		return 0;
-	ret = strict_strtoul(str, 0, &buf_size);
+	buf_size = memparse(str, &str);
 	/* nr_entries can not be zero */
-	if (ret < 0 || buf_size == 0)
+	if (buf_size == 0)
 		return 0;
 	trace_buf_size = buf_size;
 	return 1;
-- 
cgit v1.2.3


From 020e5f85cb087a40572c8b8b2dd06292a14fa212 Mon Sep 17 00:00:00 2001
From: Li Zefan <lizf@cn.fujitsu.com>
Date: Wed, 1 Jul 2009 10:47:05 +0800
Subject: tracing/events: Add trace_event boot option

We already have ftrace= boot option, and this adds a similar
boot option for trace events, so allow trace events to be
enabled at boot, for boot debugging purpose.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <4A4ACE29.3010407@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/kernel-parameters.txt |  5 +++++
 Documentation/trace/events.txt      |  9 +++++++++
 kernel/trace/trace.c                |  4 ++--
 kernel/trace/trace.h                |  3 +++
 kernel/trace/trace_events.c         | 37 +++++++++++++++++++++++++++++++++----
 5 files changed, 52 insertions(+), 6 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index d3f41db3ed49..2582e7aea29f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2478,6 +2478,11 @@ and is between 256 and 4096 characters. It is defined in the file
 	trace_buf_size=nn[KMG]
 			[FTRACE] will set tracing buffer size.
 
+	trace_event=[event-list]
+			[FTRACE] Set and start specified trace events in order
+			to facilitate early boot debugging.
+			See also Documentation/trace/events.txt
+
 	trix=		[HW,OSS] MediaTrix AudioTrix Pro
 			Format:
 			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index f157d7594ea7..2bcc8d4dea29 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -83,6 +83,15 @@ When reading one of these enable files, there are four results:
  X - there is a mixture of events enabled and disabled
  ? - this file does not affect any event
 
+2.3 Boot option
+---------------
+
+In order to facilitate early boot debugging, use boot option:
+
+	trace_event=[event-list]
+
+The format of this boot option is the same as described in section 2.1.
+
 3. Defining an event-enabled tracepoint
 =======================================
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3aa0a0dfdfa8..bdb3afc8b306 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -49,7 +49,7 @@ unsigned long __read_mostly	tracing_thresh;
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
  */
-static int ring_buffer_expanded;
+int ring_buffer_expanded;
 
 /*
  * We need to change this state when a selftest is running.
@@ -63,7 +63,7 @@ static bool __read_mostly tracing_selftest_running;
 /*
  * If a tracer is running, we do not want to run SELFTEST.
  */
-static bool __read_mostly tracing_selftest_disabled;
+bool __read_mostly tracing_selftest_disabled;
 
 /* For tracers that don't implement custom flags */
 static struct tracer_opt dummy_tracer_opt[] = {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3548ae5cc780..52eb0d8dcd75 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -517,6 +517,9 @@ extern unsigned long ftrace_update_tot_cnt;
 extern int DYN_FTRACE_TEST_NAME(void);
 #endif
 
+extern int ring_buffer_expanded;
+extern bool tracing_selftest_disabled;
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
 					   struct trace_array *tr);
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 53c8fd376a88..fecac1314cbe 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -17,6 +17,8 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 
+#include <asm/setup.h>
+
 #include "trace_output.h"
 
 #define TRACE_SYSTEM "TRACE_SYSTEM"
@@ -1133,6 +1135,18 @@ struct notifier_block trace_module_nb = {
 extern struct ftrace_event_call __start_ftrace_events[];
 extern struct ftrace_event_call __stop_ftrace_events[];
 
+static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
+
+static __init int setup_trace_event(char *str)
+{
+	strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
+	ring_buffer_expanded = 1;
+	tracing_selftest_disabled = 1;
+
+	return 1;
+}
+__setup("trace_event=", setup_trace_event);
+
 static __init int event_trace_init(void)
 {
 	struct ftrace_event_call *call;
@@ -1140,6 +1154,8 @@ static __init int event_trace_init(void)
 	struct dentry *entry;
 	struct dentry *d_events;
 	int ret;
+	char *buf = bootup_event_buf;
+	char *token;
 
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
@@ -1185,6 +1201,19 @@ static __init int event_trace_init(void)
 				 &ftrace_event_format_fops);
 	}
 
+	while (true) {
+		token = strsep(&buf, ",");
+
+		if (!token)
+			break;
+		if (!*token)
+			continue;
+
+		ret = ftrace_set_clr_event(token, 1);
+		if (ret)
+			pr_warning("Failed to enable trace event: %s\n", token);
+	}
+
 	ret = register_module_notifier(&trace_module_nb);
 	if (ret)
 		pr_warning("Failed to register trace events module notifier\n");
@@ -1392,10 +1421,10 @@ static __init void event_trace_self_test_with_function(void)
 
 static __init int event_trace_self_tests_init(void)
 {
-
-	event_trace_self_tests();
-
-	event_trace_self_test_with_function();
+	if (!tracing_selftest_disabled) {
+		event_trace_self_tests();
+		event_trace_self_test_with_function();
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 77ae365eca895061c8bf2b2e3ae1d9ea62869739 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 27 Mar 2009 11:00:29 -0400
Subject: ring-buffer: make lockless

This patch converts the ring buffers into a completely lockless
buffer recording system. The read side still takes locks since
we still serialize readers. But the writers are the ones that
must be lockless (those can happen in NMIs).

The main change is to the "head_page" pointer. We write to the
tail, and read from the head. The "head_page" pointer in the cpu
buffer is now just a reference to where to look. The real head
page is now kept in the head_page->list->prev->next pointer.
That is, in the list head of the previous page we set flags.

The list pages are allocated to be aligned such that the lowest
significant bits are always zero pointing to the list. This gives
us play to put in flags to their pointers.

bit 0: set when the page is a head page
bit 1: set when the writer is moving the page (for overwrite mode)

cmpxchg is used to update the pointer.

When the writer wraps the buffer and the tail meets the head,
in overwrite mode, the writer must move the head page forward.
It first uses cmpxchg to change the pointer flag from 1 to 2.
Once this is done, the reader on another CPU will not take the
page from the buffer.

The writers need to protect against interrupts (we don't bother with
disabling interrupts because NMIs are allowed to write too).

After the writer sets the pointer flag to 2, it takes care to
manage interrupts coming in. This is discribed in detail within the
comments of the code.

 Changes in version 2:
  - Let reader reset entries value of header page.
  - Fix tail page passing commit page on reader page test.
  - Always increment entries and write counter in rb_tail_page_update
  - Add safety check in rb_set_commit_to_write to break out of infinite loop
  - add mask in rb_is_reader_page

[ Impact: lock free writing to the ring buffer ]

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
---
 include/linux/ring_buffer.h |   1 -
 kernel/trace/ring_buffer.c  | 886 ++++++++++++++++++++++++++++++++++++--------
 kernel/trace/trace.c        |   3 -
 3 files changed, 738 insertions(+), 152 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 29f8599e6bea..7fca71693ae7 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -170,7 +170,6 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 7c0168ad6d51..e648ba4f70e0 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -322,6 +322,14 @@ struct buffer_data_page {
 	unsigned char	 data[];	/* data of buffer page */
 };
 
+/*
+ * Note, the buffer_page list must be first. The buffer pages
+ * are allocated in cache lines, which means that each buffer
+ * page will be at the beginning of a cache line, and thus
+ * the least significant bits will be zero. We use this to
+ * add flags in the list struct pointers, to make the ring buffer
+ * lockless.
+ */
 struct buffer_page {
 	struct list_head list;		/* list of buffer pages */
 	local_t		 write;		/* index for next write */
@@ -330,6 +338,21 @@ struct buffer_page {
 	struct buffer_data_page *page;	/* Actual data page */
 };
 
+/*
+ * The buffer page counters, write and entries, must be reset
+ * atomically when crossing page boundaries. To synchronize this
+ * update, two counters are inserted into the number. One is
+ * the actual counter for the write position or count on the page.
+ *
+ * The other is a counter of updaters. Before an update happens
+ * the update partition of the counter is incremented. This will
+ * allow the updater to update the counter atomically.
+ *
+ * The counter is 20 bits, and the state data is 12.
+ */
+#define RB_WRITE_MASK		0xfffff
+#define RB_WRITE_INTCNT		(1 << 20)
+
 static void rb_init_page(struct buffer_data_page *bpage)
 {
 	local_set(&bpage->commit, 0);
@@ -403,7 +426,7 @@ int ring_buffer_print_page_header(struct trace_seq *s)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			reader_lock; /* serialize readers */
+	spinlock_t			reader_lock;	/* serialize readers */
 	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct list_head		*pages;
@@ -411,13 +434,12 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*tail_page;	/* write to tail */
 	struct buffer_page		*commit_page;	/* committed pages */
 	struct buffer_page		*reader_page;
-	unsigned long			nmi_dropped;
-	unsigned long			commit_overrun;
-	unsigned long			overrun;
-	unsigned long			read;
+	local_t				commit_overrun;
+	local_t				overrun;
 	local_t				entries;
 	local_t				committing;
 	local_t				commits;
+	unsigned long			read;
 	u64				write_stamp;
 	u64				read_stamp;
 	atomic_t			record_disabled;
@@ -489,6 +511,385 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
+/*
+ * Making the ring buffer lockless makes things tricky.
+ * Although writes only happen on the CPU that they are on,
+ * and they only need to worry about interrupts. Reads can
+ * happen on any CPU.
+ *
+ * The reader page is always off the ring buffer, but when the
+ * reader finishes with a page, it needs to swap its page with
+ * a new one from the buffer. The reader needs to take from
+ * the head (writes go to the tail). But if a writer is in overwrite
+ * mode and wraps, it must push the head page forward.
+ *
+ * Here lies the problem.
+ *
+ * The reader must be careful to replace only the head page, and
+ * not another one. As described at the top of the file in the
+ * ASCII art, the reader sets its old page to point to the next
+ * page after head. It then sets the page after head to point to
+ * the old reader page. But if the writer moves the head page
+ * during this operation, the reader could end up with the tail.
+ *
+ * We use cmpxchg to help prevent this race. We also do something
+ * special with the page before head. We set the LSB to 1.
+ *
+ * When the writer must push the page forward, it will clear the
+ * bit that points to the head page, move the head, and then set
+ * the bit that points to the new head page.
+ *
+ * We also don't want an interrupt coming in and moving the head
+ * page on another writer. Thus we use the second LSB to catch
+ * that too. Thus:
+ *
+ * head->list->prev->next        bit 1          bit 0
+ *                              -------        -------
+ * Normal page                     0              0
+ * Points to head page             0              1
+ * New head page                   1              0
+ *
+ * Note we can not trust the prev pointer of the head page, because:
+ *
+ * +----+       +-----+        +-----+
+ * |    |------>|  T  |---X--->|  N  |
+ * |    |<------|     |        |     |
+ * +----+       +-----+        +-----+
+ *   ^                           ^ |
+ *   |          +-----+          | |
+ *   +----------|  R  |----------+ |
+ *              |     |<-----------+
+ *              +-----+
+ *
+ * Key:  ---X-->  HEAD flag set in pointer
+ *         T      Tail page
+ *         R      Reader page
+ *         N      Next page
+ *
+ * (see __rb_reserve_next() to see where this happens)
+ *
+ *  What the above shows is that the reader just swapped out
+ *  the reader page with a page in the buffer, but before it
+ *  could make the new header point back to the new page added
+ *  it was preempted by a writer. The writer moved forward onto
+ *  the new page added by the reader and is about to move forward
+ *  again.
+ *
+ *  You can see, it is legitimate for the previous pointer of
+ *  the head (or any page) not to point back to itself. But only
+ *  temporarially.
+ */
+
+#define RB_PAGE_NORMAL		0UL
+#define RB_PAGE_HEAD		1UL
+#define RB_PAGE_UPDATE		2UL
+
+
+#define RB_FLAG_MASK		3UL
+
+/* PAGE_MOVED is not part of the mask */
+#define RB_PAGE_MOVED		4UL
+
+/*
+ * rb_list_head - remove any bit
+ */
+static struct list_head *rb_list_head(struct list_head *list)
+{
+	unsigned long val = (unsigned long)list;
+
+	return (struct list_head *)(val & ~RB_FLAG_MASK);
+}
+
+/*
+ * rb_is_head_page - test if the give page is the head page
+ *
+ * Because the reader may move the head_page pointer, we can
+ * not trust what the head page is (it may be pointing to
+ * the reader page). But if the next page is a header page,
+ * its flags will be non zero.
+ */
+static int inline
+rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		struct buffer_page *page, struct list_head *list)
+{
+	unsigned long val;
+
+	val = (unsigned long)list->next;
+
+	if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
+		return RB_PAGE_MOVED;
+
+	return val & RB_FLAG_MASK;
+}
+
+/*
+ * rb_is_reader_page
+ *
+ * The unique thing about the reader page, is that, if the
+ * writer is ever on it, the previous pointer never points
+ * back to the reader page.
+ */
+static int rb_is_reader_page(struct buffer_page *page)
+{
+	struct list_head *list = page->list.prev;
+
+	return rb_list_head(list->next) != &page->list;
+}
+
+/*
+ * rb_set_list_to_head - set a list_head to be pointing to head.
+ */
+static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
+				struct list_head *list)
+{
+	unsigned long *ptr;
+
+	ptr = (unsigned long *)&list->next;
+	*ptr |= RB_PAGE_HEAD;
+	*ptr &= ~RB_PAGE_UPDATE;
+}
+
+/*
+ * rb_head_page_activate - sets up head page
+ */
+static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+
+	head = cpu_buffer->head_page;
+	if (!head)
+		return;
+
+	/*
+	 * Set the previous list pointer to have the HEAD flag.
+	 */
+	rb_set_list_to_head(cpu_buffer, head->list.prev);
+}
+
+static void rb_list_head_clear(struct list_head *list)
+{
+	unsigned long *ptr = (unsigned long *)&list->next;
+
+	*ptr &= ~RB_FLAG_MASK;
+}
+
+/*
+ * rb_head_page_dactivate - clears head page ptr (for free list)
+ */
+static void
+rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *hd;
+
+	/* Go through the whole list and clear any pointers found. */
+	rb_list_head_clear(cpu_buffer->pages);
+
+	list_for_each(hd, cpu_buffer->pages)
+		rb_list_head_clear(hd);
+}
+
+static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
+			    struct buffer_page *head,
+			    struct buffer_page *prev,
+			    int old_flag, int new_flag)
+{
+	struct list_head *list;
+	unsigned long val = (unsigned long)&head->list;
+	unsigned long ret;
+
+	list = &prev->list;
+
+	val &= ~RB_FLAG_MASK;
+
+	ret = (unsigned long)cmpxchg(&list->next,
+				     val | old_flag, val | new_flag);
+
+	/* check if the reader took the page */
+	if ((ret & ~RB_FLAG_MASK) != val)
+		return RB_PAGE_MOVED;
+
+	return ret & RB_FLAG_MASK;
+}
+
+static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_UPDATE);
+}
+
+static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
+				 struct buffer_page *head,
+				 struct buffer_page *prev,
+				 int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_HEAD);
+}
+
+static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
+				   struct buffer_page *head,
+				   struct buffer_page *prev,
+				   int old_flag)
+{
+	return rb_head_page_set(cpu_buffer, head, prev,
+				old_flag, RB_PAGE_NORMAL);
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page **bpage)
+{
+	struct list_head *p = rb_list_head((*bpage)->list.next);
+
+	*bpage = list_entry(p, struct buffer_page, list);
+}
+
+static struct buffer_page *
+rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct buffer_page *head;
+	struct buffer_page *page;
+	struct list_head *list;
+	int i;
+
+	if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
+		return NULL;
+
+	/* sanity check */
+	list = cpu_buffer->pages;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
+		return NULL;
+
+	page = head = cpu_buffer->head_page;
+	/*
+	 * It is possible that the writer moves the header behind
+	 * where we started, and we miss in one loop.
+	 * A second loop should grab the header, but we'll do
+	 * three loops just because I'm paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		do {
+			if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
+				cpu_buffer->head_page = page;
+				return page;
+			}
+			rb_inc_page(cpu_buffer, &page);
+		} while (page != head);
+	}
+
+	RB_WARN_ON(cpu_buffer, 1);
+
+	return NULL;
+}
+
+static int rb_head_page_replace(struct buffer_page *old,
+				struct buffer_page *new)
+{
+	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
+	unsigned long val;
+	unsigned long ret;
+
+	val = *ptr & ~RB_FLAG_MASK;
+	val |= RB_PAGE_HEAD;
+
+	ret = cmpxchg(ptr, val, &new->list);
+
+	return ret == val;
+}
+
+/*
+ * rb_tail_page_update - move the tail page forward
+ *
+ * Returns 1 if moved tail page, 0 if someone else did.
+ */
+static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page *tail_page,
+			       struct buffer_page *next_page)
+{
+	struct buffer_page *old_tail;
+	unsigned long old_entries;
+	unsigned long old_write;
+	int ret = 0;
+
+	/*
+	 * The tail page now needs to be moved forward.
+	 *
+	 * We need to reset the tail page, but without messing
+	 * with possible erasing of data brought in by interrupts
+	 * that have moved the tail page and are currently on it.
+	 *
+	 * We add a counter to the write field to denote this.
+	 */
+	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
+	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);
+
+	/*
+	 * Just make sure we have seen our old_write and synchronize
+	 * with any interrupts that come in.
+	 */
+	barrier();
+
+	/*
+	 * If the tail page is still the same as what we think
+	 * it is, then it is up to us to update the tail
+	 * pointer.
+	 */
+	if (tail_page == cpu_buffer->tail_page) {
+		/* Zero the write counter */
+		unsigned long val = old_write & ~RB_WRITE_MASK;
+		unsigned long eval = old_entries & ~RB_WRITE_MASK;
+
+		/*
+		 * This will only succeed if an interrupt did
+		 * not come in and change it. In which case, we
+		 * do not want to modify it.
+		 */
+		local_cmpxchg(&next_page->write, old_write, val);
+		local_cmpxchg(&next_page->entries, old_entries, eval);
+
+		/*
+		 * No need to worry about races with clearing out the commit.
+		 * it only can increment when a commit takes place. But that
+		 * only happens in the outer most nested commit.
+		 */
+		local_set(&next_page->page->commit, 0);
+
+		old_tail = cmpxchg(&cpu_buffer->tail_page,
+				   tail_page, next_page);
+
+		if (old_tail == tail_page)
+			ret = 1;
+	}
+
+	return ret;
+}
+
+static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
+			  struct buffer_page *bpage)
+{
+	unsigned long val = (unsigned long)bpage;
+
+	if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
+		return 1;
+
+	return 0;
+}
+
+/**
+ * rb_check_list - make sure a pointer to a list has the last bits zero
+ */
+static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
+			 struct list_head *list)
+{
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
+		return 1;
+	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
+		return 1;
+	return 0;
+}
+
 /**
  * check_pages - integrity check of buffer pages
  * @cpu_buffer: CPU buffer with pages to test
@@ -501,11 +902,16 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = cpu_buffer->pages;
 	struct buffer_page *bpage, *tmp;
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
 		return -1;
 	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
 		return -1;
 
+	if (rb_check_list(cpu_buffer, head))
+		return -1;
+
 	list_for_each_entry_safe(bpage, tmp, head, list) {
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.next->prev != &bpage->list))
@@ -513,8 +919,12 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 		if (RB_WARN_ON(cpu_buffer,
 			       bpage->list.prev->next != &bpage->list))
 			return -1;
+		if (rb_check_list(cpu_buffer, &bpage->list))
+			return -1;
 	}
 
+	rb_head_page_activate(cpu_buffer);
+
 	return 0;
 }
 
@@ -533,6 +943,9 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 				    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
 		if (!bpage)
 			goto free_pages;
+
+		rb_check_bpage(cpu_buffer, bpage);
+
 		list_add(&bpage->list, &pages);
 
 		addr = __get_free_page(GFP_KERNEL);
@@ -586,6 +999,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	if (!bpage)
 		goto fail_free_buffer;
 
+	rb_check_bpage(cpu_buffer, bpage);
+
 	cpu_buffer->reader_page = bpage;
 	addr = __get_free_page(GFP_KERNEL);
 	if (!addr)
@@ -603,6 +1018,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;
 
+	rb_head_page_activate(cpu_buffer);
+
 	return cpu_buffer;
 
  fail_free_reader:
@@ -620,6 +1037,8 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 
 	free_buffer_page(cpu_buffer->reader_page);
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	if (head) {
 		list_for_each_entry_safe(bpage, tmp, head, list) {
 			list_del_init(&bpage->list);
@@ -770,6 +1189,8 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
 			return;
@@ -800,6 +1221,9 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
+	spin_lock_irq(&cpu_buffer->reader_lock);
+	rb_head_page_deactivate(cpu_buffer);
+
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
 			return;
@@ -809,6 +1233,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 		list_add_tail(&bpage->list, cpu_buffer->pages);
 	}
 	rb_reset_cpu(cpu_buffer);
+	spin_unlock_irq(&cpu_buffer->reader_lock);
 
 	rb_check_pages(cpu_buffer);
 
@@ -958,22 +1383,15 @@ rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 			       cpu_buffer->reader_page->read);
 }
 
-static inline struct ring_buffer_event *
-rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return __rb_page_index(cpu_buffer->head_page,
-			       cpu_buffer->head_page->read);
-}
-
 static inline struct ring_buffer_event *
 rb_iter_head_event(struct ring_buffer_iter *iter)
 {
 	return __rb_page_index(iter->head_page, iter->head);
 }
 
-static inline unsigned rb_page_write(struct buffer_page *bpage)
+static inline unsigned long rb_page_write(struct buffer_page *bpage)
 {
-	return local_read(&bpage->write);
+	return local_read(&bpage->write) & RB_WRITE_MASK;
 }
 
 static inline unsigned rb_page_commit(struct buffer_page *bpage)
@@ -981,6 +1399,11 @@ 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 commited */
 static inline unsigned rb_page_size(struct buffer_page *bpage)
 {
@@ -993,19 +1416,6 @@ rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
 	return rb_page_commit(cpu_buffer->commit_page);
 }
 
-static inline unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
-{
-	return rb_page_commit(cpu_buffer->head_page);
-}
-
-static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
-			       struct buffer_page **bpage)
-{
-	struct list_head *p = (*bpage)->list.next;
-
-	*bpage = list_entry(p, struct buffer_page, list);
-}
-
 static inline unsigned
 rb_event_index(struct ring_buffer_event *event)
 {
@@ -1031,6 +1441,8 @@ rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 static void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	unsigned long max_count;
+
 	/*
 	 * We only race with interrupts and NMIs on this CPU.
 	 * If we own the commit event, then we can commit
@@ -1040,9 +1452,16 @@ 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;
+
 	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
+			return;
+		if (RB_WARN_ON(cpu_buffer,
+			       rb_is_reader_page(cpu_buffer->tail_page)))
+			return;
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
 		cpu_buffer->write_stamp =
 			cpu_buffer->commit_page->page->time_stamp;
@@ -1051,8 +1470,12 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	}
 	while (rb_commit_index(cpu_buffer) !=
 	       rb_page_write(cpu_buffer->commit_page)) {
-		cpu_buffer->commit_page->page->commit =
-			cpu_buffer->commit_page->write;
+
+		local_set(&cpu_buffer->commit_page->page->commit,
+			  rb_page_write(cpu_buffer->commit_page));
+		RB_WARN_ON(cpu_buffer,
+			   local_read(&cpu_buffer->commit_page->page->commit) &
+			   ~RB_WRITE_MASK);
 		barrier();
 	}
 
@@ -1085,7 +1508,7 @@ static void rb_inc_iter(struct ring_buffer_iter *iter)
 	 * to the head page instead of next.
 	 */
 	if (iter->head_page == cpu_buffer->reader_page)
-		iter->head_page = cpu_buffer->head_page;
+		iter->head_page = rb_set_head_page(cpu_buffer);
 	else
 		rb_inc_page(cpu_buffer, &iter->head_page);
 
@@ -1129,6 +1552,163 @@ rb_update_event(struct ring_buffer_event *event,
 	}
 }
 
+/*
+ * rb_handle_head_page - writer hit the head page
+ *
+ * Returns: +1 to retry page
+ *           0 to continue
+ *          -1 on error
+ */
+static int
+rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
+		    struct buffer_page *tail_page,
+		    struct buffer_page *next_page)
+{
+	struct buffer_page *new_head;
+	int entries;
+	int type;
+	int ret;
+
+	entries = rb_page_entries(next_page);
+
+	/*
+	 * The hard part is here. We need to move the head
+	 * forward, and protect against both readers on
+	 * other CPUs and writers coming in via interrupts.
+	 */
+	type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
+				       RB_PAGE_HEAD);
+
+	/*
+	 * type can be one of four:
+	 *  NORMAL - an interrupt already moved it for us
+	 *  HEAD   - we are the first to get here.
+	 *  UPDATE - we are the interrupt interrupting
+	 *           a current move.
+	 *  MOVED  - a reader on another CPU moved the next
+	 *           pointer to its reader page. Give up
+	 *           and try again.
+	 */
+
+	switch (type) {
+	case RB_PAGE_HEAD:
+		/*
+		 * We changed the head to UPDATE, thus
+		 * it is our responsibility to update
+		 * the counters.
+		 */
+		local_add(entries, &cpu_buffer->overrun);
+
+		/*
+		 * The entries will be zeroed out when we move the
+		 * tail page.
+		 */
+
+		/* still more to do */
+		break;
+
+	case RB_PAGE_UPDATE:
+		/*
+		 * This is an interrupt that interrupt the
+		 * previous update. Still more to do.
+		 */
+		break;
+	case RB_PAGE_NORMAL:
+		/*
+		 * An interrupt came in before the update
+		 * and processed this for us.
+		 * Nothing left to do.
+		 */
+		return 1;
+	case RB_PAGE_MOVED:
+		/*
+		 * The reader is on another CPU and just did
+		 * a swap with our next_page.
+		 * Try again.
+		 */
+		return 1;
+	default:
+		RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
+		return -1;
+	}
+
+	/*
+	 * Now that we are here, the old head pointer is
+	 * set to UPDATE. This will keep the reader from
+	 * swapping the head page with the reader page.
+	 * The reader (on another CPU) will spin till
+	 * we are finished.
+	 *
+	 * We just need to protect against interrupts
+	 * doing the job. We will set the next pointer
+	 * to HEAD. After that, we set the old pointer
+	 * to NORMAL, but only if it was HEAD before.
+	 * otherwise we are an interrupt, and only
+	 * want the outer most commit to reset it.
+	 */
+	new_head = next_page;
+	rb_inc_page(cpu_buffer, &new_head);
+
+	ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
+				    RB_PAGE_NORMAL);
+
+	/*
+	 * Valid returns are:
+	 *  HEAD   - an interrupt came in and already set it.
+	 *  NORMAL - One of two things:
+	 *            1) We really set it.
+	 *            2) A bunch of interrupts came in and moved
+	 *               the page forward again.
+	 */
+	switch (ret) {
+	case RB_PAGE_HEAD:
+	case RB_PAGE_NORMAL:
+		/* OK */
+		break;
+	default:
+		RB_WARN_ON(cpu_buffer, 1);
+		return -1;
+	}
+
+	/*
+	 * It is possible that an interrupt came in,
+	 * set the head up, then more interrupts came in
+	 * and moved it again. When we get back here,
+	 * the page would have been set to NORMAL but we
+	 * just set it back to HEAD.
+	 *
+	 * How do you detect this? Well, if that happened
+	 * the tail page would have moved.
+	 */
+	if (ret == RB_PAGE_NORMAL) {
+		/*
+		 * If the tail had moved passed next, then we need
+		 * to reset the pointer.
+		 */
+		if (cpu_buffer->tail_page != tail_page &&
+		    cpu_buffer->tail_page != next_page)
+			rb_head_page_set_normal(cpu_buffer, new_head,
+						next_page,
+						RB_PAGE_HEAD);
+	}
+
+	/*
+	 * If this was the outer most commit (the one that
+	 * changed the original pointer from HEAD to UPDATE),
+	 * then it is up to us to reset it to NORMAL.
+	 */
+	if (type == RB_PAGE_HEAD) {
+		ret = rb_head_page_set_normal(cpu_buffer, next_page,
+					      tail_page,
+					      RB_PAGE_UPDATE);
+		if (RB_WARN_ON(cpu_buffer,
+			       ret != RB_PAGE_UPDATE))
+			return -1;
+	}
+
+	return 0;
+}
+
 static unsigned rb_calculate_event_length(unsigned length)
 {
 	struct ring_buffer_event event; /* Used only for sizeof array */
@@ -1207,96 +1787,93 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct buffer_page *commit_page,
 	     struct buffer_page *tail_page, u64 *ts)
 {
-	struct buffer_page *next_page, *head_page, *reader_page;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
-	bool lock_taken = false;
-	unsigned long flags;
+	struct buffer_page *next_page;
+	int ret;
 
 	next_page = tail_page;
 
-	local_irq_save(flags);
-	/*
-	 * Since the write to the buffer is still not
-	 * fully lockless, we must be careful with NMIs.
-	 * The locks in the writers are taken when a write
-	 * crosses to a new page. The locks protect against
-	 * races with the readers (this will soon be fixed
-	 * with a lockless solution).
-	 *
-	 * Because we can not protect against NMIs, and we
-	 * want to keep traces reentrant, we need to manage
-	 * what happens when we are in an NMI.
-	 *
-	 * NMIs can happen after we take the lock.
-	 * If we are in an NMI, only take the lock
-	 * if it is not already taken. Otherwise
-	 * simply fail.
-	 */
-	if (unlikely(in_nmi())) {
-		if (!__raw_spin_trylock(&cpu_buffer->lock)) {
-			cpu_buffer->nmi_dropped++;
-			goto out_reset;
-		}
-	} else
-		__raw_spin_lock(&cpu_buffer->lock);
-
-	lock_taken = true;
-
 	rb_inc_page(cpu_buffer, &next_page);
 
-	head_page = cpu_buffer->head_page;
-	reader_page = cpu_buffer->reader_page;
-
-	/* we grabbed the lock before incrementing */
-	if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
-		goto out_reset;
-
 	/*
 	 * If for some reason, we had an interrupt storm that made
 	 * it all the way around the buffer, bail, and warn
 	 * about it.
 	 */
 	if (unlikely(next_page == commit_page)) {
-		cpu_buffer->commit_overrun++;
+		local_inc(&cpu_buffer->commit_overrun);
 		goto out_reset;
 	}
 
-	if (next_page == head_page) {
-		if (!(buffer->flags & RB_FL_OVERWRITE))
-			goto out_reset;
-
-		/* tail_page has not moved yet? */
-		if (tail_page == cpu_buffer->tail_page) {
-			/* count overflows */
-			cpu_buffer->overrun +=
-				local_read(&head_page->entries);
+	/*
+	 * This is where the fun begins!
+	 *
+	 * We are fighting against races between a reader that
+	 * could be on another CPU trying to swap its reader
+	 * page with the buffer head.
+	 *
+	 * We are also fighting against interrupts coming in and
+	 * moving the head or tail on us as well.
+	 *
+	 * If the next page is the head page then we have filled
+	 * the buffer, unless the commit page is still on the
+	 * reader page.
+	 */
+	if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {
 
-			rb_inc_page(cpu_buffer, &head_page);
-			cpu_buffer->head_page = head_page;
-			cpu_buffer->head_page->read = 0;
+		/*
+		 * If the commit is not on the reader page, then
+		 * move the header page.
+		 */
+		if (!rb_is_reader_page(cpu_buffer->commit_page)) {
+			/*
+			 * If we are not in overwrite mode,
+			 * this is easy, just stop here.
+			 */
+			if (!(buffer->flags & RB_FL_OVERWRITE))
+				goto out_reset;
+
+			ret = rb_handle_head_page(cpu_buffer,
+						  tail_page,
+						  next_page);
+			if (ret < 0)
+				goto out_reset;
+			if (ret)
+				goto out_again;
+		} else {
+			/*
+			 * We need to be careful here too. The
+			 * commit page could still be on the reader
+			 * page. We could have a small buffer, and
+			 * have filled up the buffer with events
+			 * from interrupts and such, and wrapped.
+			 *
+			 * Note, if the tail page is also the on the
+			 * reader_page, we let it move out.
+			 */
+			if (unlikely((cpu_buffer->commit_page !=
+				      cpu_buffer->tail_page) &&
+				     (cpu_buffer->commit_page ==
+				      cpu_buffer->reader_page))) {
+				local_inc(&cpu_buffer->commit_overrun);
+				goto out_reset;
+			}
 		}
 	}
 
-	/*
-	 * If the tail page is still the same as what we think
-	 * it is, then it is up to us to update the tail
-	 * pointer.
-	 */
-	if (tail_page == cpu_buffer->tail_page) {
-		local_set(&next_page->write, 0);
-		local_set(&next_page->entries, 0);
-		local_set(&next_page->page->commit, 0);
-		cpu_buffer->tail_page = next_page;
-
-		/* reread the time stamp */
+	ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
+	if (ret) {
+		/*
+		 * Nested commits always have zero deltas, so
+		 * just reread the time stamp
+		 */
 		*ts = rb_time_stamp(buffer, cpu_buffer->cpu);
-		cpu_buffer->tail_page->page->time_stamp = *ts;
+		next_page->page->time_stamp = *ts;
 	}
 
-	rb_reset_tail(cpu_buffer, tail_page, tail, length);
+ out_again:
 
-	__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
+	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
 	/* fail and let the caller try again */
 	return ERR_PTR(-EAGAIN);
@@ -1305,9 +1882,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	/* reset write */
 	rb_reset_tail(cpu_buffer, tail_page, tail, length);
 
-	if (likely(lock_taken))
-		__raw_spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
 	return NULL;
 }
 
@@ -1324,6 +1898,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	barrier();
 	tail_page = cpu_buffer->tail_page;
 	write = local_add_return(length, &tail_page->write);
+
+	/* set write to only the index of the write */
+	write &= RB_WRITE_MASK;
 	tail = write - length;
 
 	/* See if we shot pass the end of this buffer page */
@@ -1368,12 +1945,16 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	bpage = cpu_buffer->tail_page;
 
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
+		unsigned long write_mask =
+			local_read(&bpage->write) & ~RB_WRITE_MASK;
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
 		 * and write to the next page. That is fine
 		 * because we just shorten what is on this page.
 		 */
+		old_index += write_mask;
+		new_index += write_mask;
 		index = local_cmpxchg(&bpage->write, old_index, new_index);
 		if (index == old_index)
 			return 1;
@@ -1882,9 +2463,13 @@ EXPORT_SYMBOL_GPL(ring_buffer_write);
 static int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	struct buffer_page *reader = cpu_buffer->reader_page;
-	struct buffer_page *head = cpu_buffer->head_page;
+	struct buffer_page *head = rb_set_head_page(cpu_buffer);
 	struct buffer_page *commit = cpu_buffer->commit_page;
 
+	/* In case of error, head will be NULL */
+	if (unlikely(!head))
+		return 1;
+
 	return reader->read == rb_page_commit(reader) &&
 		(commit == reader ||
 		 (commit == head &&
@@ -1975,7 +2560,7 @@ unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = (local_read(&cpu_buffer->entries) - cpu_buffer->overrun)
+	ret = (local_read(&cpu_buffer->entries) - local_read(&cpu_buffer->overrun))
 		- cpu_buffer->read;
 
 	return ret;
@@ -1996,32 +2581,12 @@ unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->overrun;
+	ret = local_read(&cpu_buffer->overrun);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);
 
-/**
- * ring_buffer_nmi_dropped_cpu - get the number of nmis that were dropped
- * @buffer: The ring buffer
- * @cpu: The per CPU buffer to get the number of overruns from
- */
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long ret;
-
-	if (!cpumask_test_cpu(cpu, buffer->cpumask))
-		return 0;
-
-	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->nmi_dropped;
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_nmi_dropped_cpu);
-
 /**
  * ring_buffer_commit_overrun_cpu - get the number of overruns caused by commits
  * @buffer: The ring buffer
@@ -2037,7 +2602,7 @@ ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	ret = cpu_buffer->commit_overrun;
+	ret = local_read(&cpu_buffer->commit_overrun);
 
 	return ret;
 }
@@ -2060,7 +2625,7 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer)
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
 		entries += (local_read(&cpu_buffer->entries) -
-			    cpu_buffer->overrun) - cpu_buffer->read;
+			    local_read(&cpu_buffer->overrun)) - cpu_buffer->read;
 	}
 
 	return entries;
@@ -2083,7 +2648,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 	/* if you care about this being correct, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		overruns += cpu_buffer->overrun;
+		overruns += local_read(&cpu_buffer->overrun);
 	}
 
 	return overruns;
@@ -2096,8 +2661,10 @@ static void rb_iter_reset(struct ring_buffer_iter *iter)
 
 	/* Iterator usage is expected to have record disabled */
 	if (list_empty(&cpu_buffer->reader_page->list)) {
-		iter->head_page = cpu_buffer->head_page;
-		iter->head = cpu_buffer->head_page->read;
+		iter->head_page = rb_set_head_page(cpu_buffer);
+		if (unlikely(!iter->head_page))
+			return;
+		iter->head = iter->head_page->read;
 	} else {
 		iter->head_page = cpu_buffer->reader_page;
 		iter->head = cpu_buffer->reader_page->read;
@@ -2214,6 +2781,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	struct buffer_page *reader = NULL;
 	unsigned long flags;
 	int nr_loops = 0;
+	int ret;
 
 	local_irq_save(flags);
 	__raw_spin_lock(&cpu_buffer->lock);
@@ -2247,11 +2815,17 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto out;
 
 	/*
-	 * Splice the empty reader page into the list around the head.
 	 * Reset the reader page to size zero.
 	 */
+	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);
 
-	reader = cpu_buffer->head_page;
+ spin:
+	/*
+	 * Splice the empty reader page into the list around the head.
+	 */
+	reader = rb_set_head_page(cpu_buffer);
 	cpu_buffer->reader_page->list.next = reader->list.next;
 	cpu_buffer->reader_page->list.prev = reader->list.prev;
 
@@ -2262,22 +2836,35 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	 */
 	cpu_buffer->pages = reader->list.prev;
 
-	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);
+	/* The reader page will be pointing to the new head */
+	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);
 
-	/* Make the reader page now replace the head */
-	reader->list.prev->next = &cpu_buffer->reader_page->list;
-	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	/*
+	 * Here's the tricky part.
+	 *
+	 * We need to move the pointer past the header page.
+	 * But we can only do that if a writer is not currently
+	 * moving it. The page before the header page has the
+	 * flag bit '1' set if it is pointing to the page we want.
+	 * but if the writer is in the process of moving it
+	 * than it will be '2' or already moved '0'.
+	 */
+
+	ret = rb_head_page_replace(reader, cpu_buffer->reader_page);
 
 	/*
-	 * If the tail is on the reader, then we must set the head
-	 * to the inserted page, otherwise we set it one before.
+	 * If we did not convert it, then we must try again.
 	 */
-	cpu_buffer->head_page = cpu_buffer->reader_page;
+	if (!ret)
+		goto spin;
 
-	if (cpu_buffer->commit_page != reader)
-		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+	/*
+	 * Yeah! We succeeded in replacing the page.
+	 *
+	 * Now make the new head point back to the reader page.
+	 */
+	reader->list.next->prev = &cpu_buffer->reader_page->list;
+	rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
 
 	/* Finally update the reader page to the new head */
 	cpu_buffer->reader_page = reader;
@@ -2733,6 +3320,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_size);
 static void
 rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	rb_head_page_deactivate(cpu_buffer);
+
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages, struct buffer_page, list);
 	local_set(&cpu_buffer->head_page->write, 0);
@@ -2750,16 +3339,17 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	local_set(&cpu_buffer->reader_page->page->commit, 0);
 	cpu_buffer->reader_page->read = 0;
 
-	cpu_buffer->nmi_dropped = 0;
-	cpu_buffer->commit_overrun = 0;
-	cpu_buffer->overrun = 0;
-	cpu_buffer->read = 0;
+	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->overrun, 0);
 	local_set(&cpu_buffer->entries, 0);
 	local_set(&cpu_buffer->committing, 0);
 	local_set(&cpu_buffer->commits, 0);
+	cpu_buffer->read = 0;
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
+
+	rb_head_page_activate(cpu_buffer);
 }
 
 /**
@@ -3107,7 +3697,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		read = 0;
 	} else {
 		/* update the entry counter */
-		cpu_buffer->read += local_read(&reader->entries);
+		cpu_buffer->read += rb_page_entries(reader);
 
 		/* swap the pages */
 		rb_init_page(bpage);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bdb3afc8b306..b591f7a1bd7b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3630,9 +3630,6 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	cnt = ring_buffer_commit_overrun_cpu(tr->buffer, cpu);
 	trace_seq_printf(s, "commit overrun: %ld\n", cnt);
 
-	cnt = ring_buffer_nmi_dropped_cpu(tr->buffer, cpu);
-	trace_seq_printf(s, "nmi dropped: %ld\n", cnt);
-
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
-- 
cgit v1.2.3


From 405f55712dfe464b3240d7816cc4fe4174831be2 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sat, 11 Jul 2009 22:08:37 +0400
Subject: headers: smp_lock.h redux

* Remove smp_lock.h from files which don't need it (including some headers!)
* Add smp_lock.h to files which do need it
* Make smp_lock.h include conditional in hardirq.h
  It's needed only for one kernel_locked() usage which is under CONFIG_PREEMPT

  This will make hardirq.h inclusion cheaper for every PREEMPT=n config
  (which includes allmodconfig/allyesconfig, BTW)

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/kernel/ptrace.c                      | 1 -
 arch/blackfin/kernel/ptrace.c                   | 1 -
 arch/blackfin/kernel/sys_bfin.c                 | 1 -
 arch/cris/kernel/sys_cris.c                     | 1 -
 arch/ia64/kernel/ptrace.c                       | 1 -
 arch/m32r/kernel/ptrace.c                       | 1 -
 arch/microblaze/kernel/ptrace.c                 | 1 -
 arch/microblaze/kernel/signal.c                 | 1 -
 arch/microblaze/kernel/sys_microblaze.c         | 1 -
 arch/mips/kernel/ptrace32.c                     | 1 -
 arch/mips/mm/hugetlbpage.c                      | 1 -
 arch/mn10300/kernel/ptrace.c                    | 1 -
 arch/mn10300/kernel/signal.c                    | 1 -
 arch/mn10300/kernel/sys_mn10300.c               | 1 -
 arch/mn10300/kernel/traps.c                     | 1 -
 arch/mn10300/mm/fault.c                         | 1 -
 arch/mn10300/mm/misalignment.c                  | 1 -
 arch/powerpc/kernel/ptrace32.c                  | 1 -
 arch/s390/kernel/dis.c                          | 1 -
 arch/s390/kernel/ptrace.c                       | 1 -
 arch/s390/mm/fault.c                            | 1 -
 arch/sh/mm/tlb-sh3.c                            | 1 -
 arch/sparc/kernel/ptrace_32.c                   | 1 -
 arch/sparc/kernel/ptrace_64.c                   | 1 -
 arch/sparc/kernel/time_64.c                     | 1 -
 arch/sparc/kernel/traps_32.c                    | 1 -
 drivers/block/DAC960.c                          | 1 +
 drivers/block/cciss.c                           | 1 +
 drivers/block/loop.c                            | 1 -
 drivers/bluetooth/hci_vhci.c                    | 1 -
 drivers/char/amiserial.c                        | 1 +
 drivers/char/cyclades.c                         | 1 +
 drivers/char/epca.c                             | 1 +
 drivers/char/isicom.c                           | 1 +
 drivers/char/istallion.c                        | 1 +
 drivers/char/moxa.c                             | 1 +
 drivers/char/mxser.c                            | 1 +
 drivers/char/n_hdlc.c                           | 1 +
 drivers/char/n_r3964.c                          | 1 +
 drivers/char/pty.c                              | 1 +
 drivers/char/rio/rio_linux.c                    | 1 +
 drivers/char/riscom8.c                          | 1 +
 drivers/char/rocket.c                           | 1 +
 drivers/char/serial167.c                        | 1 +
 drivers/char/specialix.c                        | 1 +
 drivers/char/sx.c                               | 1 +
 drivers/char/synclink.c                         | 1 +
 drivers/char/synclink_gt.c                      | 1 +
 drivers/char/synclinkmp.c                       | 1 +
 drivers/char/tpm/tpm.c                          | 1 -
 drivers/char/tty_ioctl.c                        | 1 -
 drivers/char/tty_ldisc.c                        | 1 -
 drivers/char/vt.c                               | 1 +
 drivers/char/vt_ioctl.c                         | 1 +
 drivers/gpio/vr41xx_giu.c                       | 1 -
 drivers/hid/usbhid/hid-core.c                   | 1 -
 drivers/isdn/hisax/hfc_usb.c                    | 1 -
 drivers/isdn/i4l/isdn_tty.c                     | 1 +
 drivers/isdn/mISDN/stack.c                      | 1 +
 drivers/media/dvb/bt8xx/dst_ca.c                | 1 +
 drivers/media/dvb/dvb-core/dvbdev.h             | 1 -
 drivers/media/dvb/ttpci/av7110.c                | 1 -
 drivers/media/radio/radio-mr800.c               | 1 +
 drivers/media/radio/radio-si470x.c              | 1 +
 drivers/media/video/bt8xx/bttv-driver.c         | 1 +
 drivers/media/video/cx23885/cx23885-417.c       | 1 +
 drivers/media/video/cx23885/cx23885-video.c     | 1 +
 drivers/media/video/cx88/cx88-blackbird.c       | 1 +
 drivers/media/video/cx88/cx88-video.c           | 1 +
 drivers/media/video/dabusb.c                    | 1 +
 drivers/media/video/pwc/pwc-if.c                | 1 +
 drivers/media/video/pwc/pwc.h                   | 1 -
 drivers/media/video/s2255drv.c                  | 1 +
 drivers/media/video/saa5246a.c                  | 1 -
 drivers/media/video/saa5249.c                   | 1 -
 drivers/media/video/saa7134/saa7134-empress.c   | 1 +
 drivers/media/video/se401.c                     | 1 +
 drivers/media/video/stk-webcam.c                | 1 +
 drivers/media/video/stradis.c                   | 1 +
 drivers/media/video/stv680.c                    | 1 +
 drivers/media/video/usbvideo/vicam.c            | 1 +
 drivers/media/video/usbvision/usbvision-video.c | 1 +
 drivers/media/video/v4l2-dev.c                  | 1 -
 drivers/media/video/zoran/zoran_driver.c        | 1 +
 drivers/misc/sgi-gru/grufile.c                  | 1 -
 drivers/misc/sgi-gru/grukservices.c             | 1 -
 drivers/net/irda/irtty-sir.c                    | 1 -
 drivers/pci/hotplug/cpci_hotplug_core.c         | 1 -
 drivers/pci/hotplug/cpqphp_ctrl.c               | 1 -
 drivers/pci/hotplug/cpqphp_sysfs.c              | 1 +
 drivers/pci/hotplug/pciehp_ctrl.c               | 1 -
 drivers/pci/syscall.c                           | 1 -
 drivers/s390/block/dasd_ioctl.c                 | 1 +
 drivers/scsi/qla2xxx/qla_mid.c                  | 1 -
 drivers/telephony/ixj.c                         | 1 +
 drivers/telephony/phonedev.c                    | 1 -
 drivers/usb/class/cdc-wdm.c                     | 1 -
 drivers/usb/gadget/amd5536udc.c                 | 1 -
 drivers/usb/gadget/langwell_udc.c               | 1 -
 drivers/usb/gadget/s3c2410_udc.c                | 1 -
 drivers/usb/host/r8a66597-hcd.c                 | 1 -
 drivers/usb/misc/iowarrior.c                    | 1 +
 drivers/usb/misc/rio500.c                       | 1 +
 drivers/usb/misc/usblcd.c                       | 1 +
 drivers/usb/musb/cppi_dma.h                     | 1 -
 drivers/usb/musb/musb_core.h                    | 1 -
 drivers/usb/serial/ftdi_sio.c                   | 1 +
 drivers/usb/serial/mos7840.c                    | 1 +
 drivers/usb/serial/usb-serial.c                 | 1 +
 drivers/video/fbmem.c                           | 1 -
 fs/adfs/super.c                                 | 1 +
 fs/afs/super.c                                  | 1 +
 fs/autofs4/dev-ioctl.c                          | 1 -
 fs/bfs/dir.c                                    | 1 -
 fs/bfs/file.c                                   | 1 -
 fs/btrfs/compression.c                          | 1 -
 fs/btrfs/file.c                                 | 1 -
 fs/btrfs/inode.c                                | 1 -
 fs/btrfs/ioctl.c                                | 1 -
 fs/btrfs/super.c                                | 1 -
 fs/char_dev.c                                   | 1 -
 fs/compat.c                                     | 1 -
 fs/compat_ioctl.c                               | 1 +
 fs/exofs/super.c                                | 1 +
 fs/ext2/ioctl.c                                 | 1 -
 fs/ext4/ioctl.c                                 | 1 -
 fs/fat/dir.c                                    | 1 -
 fs/fat/namei_msdos.c                            | 1 -
 fs/fat/namei_vfat.c                             | 1 -
 fs/fcntl.c                                      | 1 -
 fs/freevxfs/vxfs_super.c                        | 1 +
 fs/hfs/super.c                                  | 1 +
 fs/hfsplus/super.c                              | 1 +
 fs/hpfs/dir.c                                   | 1 +
 fs/hpfs/file.c                                  | 1 +
 fs/hpfs/hpfs_fn.h                               | 1 -
 fs/hpfs/inode.c                                 | 1 +
 fs/hpfs/namei.c                                 | 1 +
 fs/jffs2/super.c                                | 1 +
 fs/lockd/clntproc.c                             | 1 +
 fs/lockd/svc4proc.c                             | 1 +
 fs/lockd/svcproc.c                              | 1 +
 fs/nfs/delegation.c                             | 1 +
 fs/nfs/dir.c                                    | 1 -
 fs/nfs/file.c                                   | 1 -
 fs/nfs/inode.c                                  | 1 -
 fs/nfs/nfs4proc.c                               | 1 -
 fs/nfs/read.c                                   | 1 -
 fs/nfsd/nfsctl.c                                | 1 -
 fs/nfsd/nfssvc.c                                | 1 -
 fs/nilfs2/dir.c                                 | 1 -
 fs/ocfs2/ioctl.c                                | 1 -
 fs/reiserfs/xattr.c                             | 1 -
 fs/squashfs/super.c                             | 1 +
 fs/ubifs/ioctl.c                                | 1 -
 fs/xfs/linux-2.6/xfs_file.c                     | 1 -
 include/linux/crash_dump.h                      | 1 -
 include/linux/hardirq.h                         | 2 ++
 include/linux/quotaops.h                        | 1 -
 include/linux/sunrpc/xdr.h                      | 1 -
 kernel/power/user.c                             | 1 -
 kernel/trace/blktrace.c                         | 1 +
 kernel/trace/trace.c                            | 1 +
 net/appletalk/ddp.c                             | 1 +
 net/ipx/af_ipx.c                                | 1 +
 net/irda/af_irda.c                              | 1 +
 net/irda/irnet/irnet.h                          | 1 -
 net/irda/irnet/irnet_ppp.c                      | 1 +
 net/sunrpc/clnt.c                               | 1 -
 net/sunrpc/sched.c                              | 1 -
 net/sunrpc/svc_xprt.c                           | 1 +
 net/wanrouter/wanmain.c                         | 1 +
 net/x25/af_x25.c                                | 1 +
 173 files changed, 81 insertions(+), 93 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/arch/alpha/kernel/ptrace.c b/arch/alpha/kernel/ptrace.c
index 1e9ad52c460e..e072041d19f8 100644
--- a/arch/alpha/kernel/ptrace.c
+++ b/arch/alpha/kernel/ptrace.c
@@ -8,7 +8,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
diff --git a/arch/blackfin/kernel/ptrace.c b/arch/blackfin/kernel/ptrace.c
index d76618db50df..6a387eec6b65 100644
--- a/arch/blackfin/kernel/ptrace.c
+++ b/arch/blackfin/kernel/ptrace.c
@@ -31,7 +31,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
diff --git a/arch/blackfin/kernel/sys_bfin.c b/arch/blackfin/kernel/sys_bfin.c
index a8f1329c15a4..3da60fb13ce4 100644
--- a/arch/blackfin/kernel/sys_bfin.c
+++ b/arch/blackfin/kernel/sys_bfin.c
@@ -29,7 +29,6 @@
  * 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
diff --git a/arch/cris/kernel/sys_cris.c b/arch/cris/kernel/sys_cris.c
index a79fbd87021b..2ad962c7e88e 100644
--- a/arch/cris/kernel/sys_cris.c
+++ b/arch/cris/kernel/sys_cris.c
@@ -15,7 +15,6 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 92c9689b7d97..9daa87fdb018 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -15,7 +15,6 @@
 #include <linux/mm.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
-#include <linux/smp_lock.h>
 #include <linux/user.h>
 #include <linux/security.h>
 #include <linux/audit.h>
diff --git a/arch/m32r/kernel/ptrace.c b/arch/m32r/kernel/ptrace.c
index bf0abe9e1f73..98b8feb12ed8 100644
--- a/arch/m32r/kernel/ptrace.c
+++ b/arch/m32r/kernel/ptrace.c
@@ -19,7 +19,6 @@
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
diff --git a/arch/microblaze/kernel/ptrace.c b/arch/microblaze/kernel/ptrace.c
index b86aa623e36d..53ff39af6a5c 100644
--- a/arch/microblaze/kernel/ptrace.c
+++ b/arch/microblaze/kernel/ptrace.c
@@ -27,7 +27,6 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
 
diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c
index 493819c25fba..1c80e4fc40ce 100644
--- a/arch/microblaze/kernel/signal.c
+++ b/arch/microblaze/kernel/signal.c
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/microblaze/kernel/sys_microblaze.c b/arch/microblaze/kernel/sys_microblaze.c
index 8c9ebac5da10..e000bce09b2b 100644
--- a/arch/microblaze/kernel/sys_microblaze.c
+++ b/arch/microblaze/kernel/sys_microblaze.c
@@ -15,7 +15,6 @@
 #include <linux/errno.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index c4f9ac17474a..32644b4a0714 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -22,7 +22,6 @@
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/user.h>
 #include <linux/security.h>
 
diff --git a/arch/mips/mm/hugetlbpage.c b/arch/mips/mm/hugetlbpage.c
index 471c09aa1614..8c2834f5919d 100644
--- a/arch/mips/mm/hugetlbpage.c
+++ b/arch/mips/mm/hugetlbpage.c
@@ -16,7 +16,6 @@
 #include <linux/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/sysctl.h>
diff --git a/arch/mn10300/kernel/ptrace.c b/arch/mn10300/kernel/ptrace.c
index e143339ad28e..cf847dabc1bd 100644
--- a/arch/mn10300/kernel/ptrace.c
+++ b/arch/mn10300/kernel/ptrace.c
@@ -13,7 +13,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
diff --git a/arch/mn10300/kernel/signal.c b/arch/mn10300/kernel/signal.c
index 9f7572a0f578..feb2f2e810db 100644
--- a/arch/mn10300/kernel/signal.c
+++ b/arch/mn10300/kernel/signal.c
@@ -12,7 +12,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/errno.h>
diff --git a/arch/mn10300/kernel/sys_mn10300.c b/arch/mn10300/kernel/sys_mn10300.c
index bca5a84dc72c..29d196b83d25 100644
--- a/arch/mn10300/kernel/sys_mn10300.c
+++ b/arch/mn10300/kernel/sys_mn10300.c
@@ -13,7 +13,6 @@
 #include <linux/syscalls.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/sem.h>
 #include <linux/msg.h>
 #include <linux/shm.h>
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index 0dfdc5001124..91365adba4f5 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -17,7 +17,6 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index a62e1e138bc1..53bb17d0f068 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -20,7 +20,6 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/vt_kern.h>		/* For unblank_screen() */
diff --git a/arch/mn10300/mm/misalignment.c b/arch/mn10300/mm/misalignment.c
index 94c4a4358065..30016251f658 100644
--- a/arch/mn10300/mm/misalignment.c
+++ b/arch/mn10300/mm/misalignment.c
@@ -17,7 +17,6 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
diff --git a/arch/powerpc/kernel/ptrace32.c b/arch/powerpc/kernel/ptrace32.c
index 297632cba047..8a6daf4129f6 100644
--- a/arch/powerpc/kernel/ptrace32.c
+++ b/arch/powerpc/kernel/ptrace32.c
@@ -21,7 +21,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/regset.h>
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index d2f270c995d9..db943a7ec513 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -15,7 +15,6 @@
 #include <linux/timer.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 490b39934d65..43acd73105b7 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -26,7 +26,6 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/ptrace.h>
 #include <linux/user.h>
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 74eb26bf1970..e5e119fe03b2 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -22,7 +22,6 @@
 #include <linux/compat.h>
 #include <linux/smp.h>
 #include <linux/kdebug.h>
-#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/module.h>
diff --git a/arch/sh/mm/tlb-sh3.c b/arch/sh/mm/tlb-sh3.c
index 7fbfd5a11ffa..17cb7c3adf22 100644
--- a/arch/sh/mm/tlb-sh3.c
+++ b/arch/sh/mm/tlb-sh3.c
@@ -18,7 +18,6 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 
 #include <asm/system.h>
diff --git a/arch/sparc/kernel/ptrace_32.c b/arch/sparc/kernel/ptrace_32.c
index 8ce6285a06d5..7e3dfd9bb97e 100644
--- a/arch/sparc/kernel/ptrace_32.c
+++ b/arch/sparc/kernel/ptrace_32.c
@@ -16,7 +16,6 @@
 #include <linux/ptrace.h>
 #include <linux/user.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/security.h>
 #include <linux/signal.h>
 #include <linux/regset.h>
diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c
index a941c610e7ce..4ae91dc2feb9 100644
--- a/arch/sparc/kernel/ptrace_64.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -17,7 +17,6 @@
 #include <linux/ptrace.h>
 #include <linux/user.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/security.h>
 #include <linux/seccomp.h>
 #include <linux/audit.h>
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index 5c12e79b4bdf..da1218e8ee87 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -11,7 +11,6 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 358283341b47..c0490c7bbde0 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -13,7 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/kdebug.h>
 
 #include <asm/delay.h>
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index 668dc234b8e2..1e6b7c14f697 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -36,6 +36,7 @@
 #include <linux/ioport.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/proc_fs.h>
 #include <linux/reboot.h>
 #include <linux/spinlock.h>
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 65a0655e7fc8..a52cc7fe45ea 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -26,6 +26,7 @@
 #include <linux/pci.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <linux/major.h>
 #include <linux/fs.h>
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 801f4ab83302..5757188cd1fb 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -61,7 +61,6 @@
 #include <linux/blkdev.h>
 #include <linux/blkpg.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
 #include <linux/loop.h>
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 1df9dda2e377..d5cde6d86f89 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -28,7 +28,6 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
diff --git a/drivers/char/amiserial.c b/drivers/char/amiserial.c
index 72429b6b2fa8..6c32fbf07164 100644
--- a/drivers/char/amiserial.c
+++ b/drivers/char/amiserial.c
@@ -81,6 +81,7 @@ static char *serial_version = "4.30";
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
 
diff --git a/drivers/char/cyclades.c b/drivers/char/cyclades.c
index f3366d3f06cf..2dafc2da0648 100644
--- a/drivers/char/cyclades.c
+++ b/drivers/char/cyclades.c
@@ -633,6 +633,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/serial.h>
+#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
diff --git a/drivers/char/epca.c b/drivers/char/epca.c
index abef1f7d84fe..ff647ca1c489 100644
--- a/drivers/char/epca.c
+++ b/drivers/char/epca.c
@@ -36,6 +36,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/uaccess.h>
diff --git a/drivers/char/isicom.c b/drivers/char/isicom.c
index 621d1184673c..4f1f4cd670da 100644
--- a/drivers/char/isicom.c
+++ b/drivers/char/isicom.c
@@ -122,6 +122,7 @@
 #include <linux/fs.h>
 #include <linux/sched.h>
 #include <linux/serial.h>
+#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/timer.h>
diff --git a/drivers/char/istallion.c b/drivers/char/istallion.c
index 0c999f5bb3db..ab2f3349c5c4 100644
--- a/drivers/char/istallion.c
+++ b/drivers/char/istallion.c
@@ -20,6 +20,7 @@
 
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/char/moxa.c b/drivers/char/moxa.c
index 65b6ff2442c6..dd0083bbb64a 100644
--- a/drivers/char/moxa.c
+++ b/drivers/char/moxa.c
@@ -34,6 +34,7 @@
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
 #include <linux/major.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
diff --git a/drivers/char/mxser.c b/drivers/char/mxser.c
index 52d953eb30c3..dbf8d52f31d0 100644
--- a/drivers/char/mxser.c
+++ b/drivers/char/mxser.c
@@ -23,6 +23,7 @@
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/timer.h>
 #include <linux/interrupt.h>
 #include <linux/tty.h>
diff --git a/drivers/char/n_hdlc.c b/drivers/char/n_hdlc.c
index 1c43c8cdee25..c68118efad84 100644
--- a/drivers/char/n_hdlc.c
+++ b/drivers/char/n_hdlc.c
@@ -97,6 +97,7 @@
 #include <linux/slab.h>
 #include <linux/tty.h>
 #include <linux/errno.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>	/* used in new tty drivers */
 #include <linux/signal.h>	/* used in new tty drivers */
 #include <linux/if.h>
diff --git a/drivers/char/n_r3964.c b/drivers/char/n_r3964.c
index 2e99158ebb8a..6934025a1ac1 100644
--- a/drivers/char/n_r3964.c
+++ b/drivers/char/n_r3964.c
@@ -58,6 +58,7 @@
 #include <linux/ioport.h>
 #include <linux/in.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/tty.h>
 #include <linux/errno.h>
 #include <linux/string.h>	/* used in new tty drivers */
diff --git a/drivers/char/pty.c b/drivers/char/pty.c
index 9d1b4f548f67..6e6942c45f5b 100644
--- a/drivers/char/pty.c
+++ b/drivers/char/pty.c
@@ -22,6 +22,7 @@
 #include <linux/major.h>
 #include <linux/mm.h>
 #include <linux/init.h>
+#include <linux/smp_lock.h>
 #include <linux/sysctl.h>
 #include <linux/device.h>
 #include <linux/uaccess.h>
diff --git a/drivers/char/rio/rio_linux.c b/drivers/char/rio/rio_linux.c
index ce81da5b2da9..d58c2eb07f07 100644
--- a/drivers/char/rio/rio_linux.c
+++ b/drivers/char/rio/rio_linux.c
@@ -44,6 +44,7 @@
 #include <linux/delay.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/miscdevice.h>
 #include <linux/init.h>
 
diff --git a/drivers/char/riscom8.c b/drivers/char/riscom8.c
index 217660451237..171711acf5cd 100644
--- a/drivers/char/riscom8.c
+++ b/drivers/char/riscom8.c
@@ -47,6 +47,7 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/tty_flip.h>
+#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
 
diff --git a/drivers/char/rocket.c b/drivers/char/rocket.c
index 63d5b628477a..0e29a23ec4c5 100644
--- a/drivers/char/rocket.c
+++ b/drivers/char/rocket.c
@@ -73,6 +73,7 @@
 #include <linux/tty_driver.h>
 #include <linux/tty_flip.h>
 #include <linux/serial.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index f1f24f0ee26f..51e7a46787be 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -52,6 +52,7 @@
 #include <linux/interrupt.h>
 #include <linux/serial.h>
 #include <linux/serialP.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/fcntl.h>
 #include <linux/ptrace.h>
diff --git a/drivers/char/specialix.c b/drivers/char/specialix.c
index e72be4190a44..bfe4cdb2febb 100644
--- a/drivers/char/specialix.c
+++ b/drivers/char/specialix.c
@@ -87,6 +87,7 @@
 #include <linux/tty_flip.h>
 #include <linux/mm.h>
 #include <linux/serial.h>
+#include <linux/smp_lock.h>
 #include <linux/fcntl.h>
 #include <linux/major.h>
 #include <linux/delay.h>
diff --git a/drivers/char/sx.c b/drivers/char/sx.c
index 518f2a25d91e..a81ec4fcf6ff 100644
--- a/drivers/char/sx.c
+++ b/drivers/char/sx.c
@@ -216,6 +216,7 @@
 #include <linux/eisa.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/bitops.h>
diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c
index afded3a2379c..813552f14884 100644
--- a/drivers/char/synclink.c
+++ b/drivers/char/synclink.c
@@ -81,6 +81,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index a2e67e6df3a1..91f20a92fddf 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -62,6 +62,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c
index 6f727e3c53ad..8d4a2a8a0a70 100644
--- a/drivers/char/synclinkmp.c
+++ b/drivers/char/synclinkmp.c
@@ -52,6 +52,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <linux/init.h>
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index ccdd828adcef..b0603b2e5684 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -26,7 +26,6 @@
 #include <linux/poll.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
-#include <linux/smp_lock.h>
 
 #include "tpm.h"
 
diff --git a/drivers/char/tty_ioctl.c b/drivers/char/tty_ioctl.c
index b24f6c6a1ea3..ad6ba4ed2808 100644
--- a/drivers/char/tty_ioctl.c
+++ b/drivers/char/tty_ioctl.c
@@ -21,7 +21,6 @@
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
diff --git a/drivers/char/tty_ldisc.c b/drivers/char/tty_ldisc.c
index 913aa8d3f1c5..0ef0dc97ba20 100644
--- a/drivers/char/tty_ldisc.c
+++ b/drivers/char/tty_ldisc.c
@@ -21,7 +21,6 @@
 #include <linux/proc_fs.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/wait.h>
 #include <linux/bitops.h>
diff --git a/drivers/char/vt.c b/drivers/char/vt.c
index d9113b4c76e3..7947bd1b4cf7 100644
--- a/drivers/char/vt.c
+++ b/drivers/char/vt.c
@@ -89,6 +89,7 @@
 #include <linux/mutex.h>
 #include <linux/vt_kern.h>
 #include <linux/selection.h>
+#include <linux/smp_lock.h>
 #include <linux/tiocl.h>
 #include <linux/kbd_kern.h>
 #include <linux/consolemap.h>
diff --git a/drivers/char/vt_ioctl.c b/drivers/char/vt_ioctl.c
index 7539bed0f7e0..95189f288f8c 100644
--- a/drivers/char/vt_ioctl.c
+++ b/drivers/char/vt_ioctl.c
@@ -25,6 +25,7 @@
 #include <linux/console.h>
 #include <linux/consolemap.h>
 #include <linux/signal.h>
+#include <linux/smp_lock.h>
 #include <linux/timex.h>
 
 #include <asm/io.h>
diff --git a/drivers/gpio/vr41xx_giu.c b/drivers/gpio/vr41xx_giu.c
index b70e06133e78..b16c9a8c03f5 100644
--- a/drivers/gpio/vr41xx_giu.c
+++ b/drivers/gpio/vr41xx_giu.c
@@ -29,7 +29,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 76c4bbe9dccb..3c1fcb7640ab 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -22,7 +22,6 @@
 #include <linux/list.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <asm/unaligned.h>
 #include <asm/byteorder.h>
diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 8df889b0c1a9..9de54202c90c 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -37,7 +37,6 @@
 #include <linux/kernel_stat.h>
 #include <linux/usb.h>
 #include <linux/kernel.h>
-#include <linux/smp_lock.h>
 #include <linux/sched.h>
 #include <linux/moduleparam.h>
 #include "hisax.h"
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index b4d4522e5071..2881a66c1aa9 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -13,6 +13,7 @@
 
 #include <linux/isdn.h>
 #include <linux/delay.h>
+#include <linux/smp_lock.h>
 #include "isdn_common.h"
 #include "isdn_tty.h"
 #ifdef CONFIG_ISDN_AUDIO
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index e2f45019ebf0..3e1532a180ff 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -17,6 +17,7 @@
 
 #include <linux/mISDNif.h>
 #include <linux/kthread.h>
+#include <linux/smp_lock.h>
 #include "core.h"
 
 static u_int	*debug;
diff --git a/drivers/media/dvb/bt8xx/dst_ca.c b/drivers/media/dvb/bt8xx/dst_ca.c
index 4601b059b2b2..0e246eaad05a 100644
--- a/drivers/media/dvb/bt8xx/dst_ca.c
+++ b/drivers/media/dvb/bt8xx/dst_ca.c
@@ -21,6 +21,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/dvb/ca.h>
 #include "dvbdev.h"
diff --git a/drivers/media/dvb/dvb-core/dvbdev.h b/drivers/media/dvb/dvb-core/dvbdev.h
index 79927305e84d..487919bea7ae 100644
--- a/drivers/media/dvb/dvb-core/dvbdev.h
+++ b/drivers/media/dvb/dvb-core/dvbdev.h
@@ -27,7 +27,6 @@
 #include <linux/poll.h>
 #include <linux/fs.h>
 #include <linux/list.h>
-#include <linux/smp_lock.h>
 
 #define DVB_MAJOR 212
 
diff --git a/drivers/media/dvb/ttpci/av7110.c b/drivers/media/dvb/ttpci/av7110.c
index d1d959ed37b7..8d65c652ba50 100644
--- a/drivers/media/dvb/ttpci/av7110.c
+++ b/drivers/media/dvb/ttpci/av7110.c
@@ -36,7 +36,6 @@
 #include <linux/fs.h>
 #include <linux/timer.h>
 #include <linux/poll.h>
-#include <linux/smp_lock.h>
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
diff --git a/drivers/media/radio/radio-mr800.c b/drivers/media/radio/radio-mr800.c
index 837467f93805..575bf9d89419 100644
--- a/drivers/media/radio/radio-mr800.c
+++ b/drivers/media/radio/radio-mr800.c
@@ -58,6 +58,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/input.h>
 #include <linux/videodev2.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/radio/radio-si470x.c b/drivers/media/radio/radio-si470x.c
index 46d216329611..e85f318b4d2b 100644
--- a/drivers/media/radio/radio-si470x.c
+++ b/drivers/media/radio/radio-si470x.c
@@ -127,6 +127,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/input.h>
 #include <linux/usb.h>
 #include <linux/hid.h>
diff --git a/drivers/media/video/bt8xx/bttv-driver.c b/drivers/media/video/bt8xx/bttv-driver.c
index 5eb1464af670..d147d29bb0d3 100644
--- a/drivers/media/video/bt8xx/bttv-driver.c
+++ b/drivers/media/video/bt8xx/bttv-driver.c
@@ -41,6 +41,7 @@
 #include <linux/fs.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/kdev_t.h>
 #include "bttvp.h"
diff --git a/drivers/media/video/cx23885/cx23885-417.c b/drivers/media/video/cx23885/cx23885-417.c
index 2943bfd32a94..428f0c45e6b7 100644
--- a/drivers/media/video/cx23885/cx23885-417.c
+++ b/drivers/media/video/cx23885/cx23885-417.c
@@ -31,6 +31,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/firmware.h>
+#include <linux/smp_lock.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/cx2341x.h>
diff --git a/drivers/media/video/cx23885/cx23885-video.c b/drivers/media/video/cx23885/cx23885-video.c
index 70836af3ab48..5d6093336300 100644
--- a/drivers/media/video/cx23885/cx23885-video.c
+++ b/drivers/media/video/cx23885/cx23885-video.c
@@ -26,6 +26,7 @@
 #include <linux/kmod.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
diff --git a/drivers/media/video/cx88/cx88-blackbird.c b/drivers/media/video/cx88/cx88-blackbird.c
index 44eacfb0d0d6..356d6896da3f 100644
--- a/drivers/media/video/cx88/cx88-blackbird.c
+++ b/drivers/media/video/cx88/cx88-blackbird.c
@@ -32,6 +32,7 @@
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/firmware.h>
+#include <linux/smp_lock.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
 #include <media/cx2341x.h>
diff --git a/drivers/media/video/cx88/cx88-video.c b/drivers/media/video/cx88/cx88-video.c
index b12770848c00..2bb54c3ef5cd 100644
--- a/drivers/media/video/cx88/cx88-video.c
+++ b/drivers/media/video/cx88/cx88-video.c
@@ -31,6 +31,7 @@
 #include <linux/kmod.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/delay.h>
diff --git a/drivers/media/video/dabusb.c b/drivers/media/video/dabusb.c
index ec2f45dde164..0664d111085f 100644
--- a/drivers/media/video/dabusb.c
+++ b/drivers/media/video/dabusb.c
@@ -32,6 +32,7 @@
 #include <linux/list.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
diff --git a/drivers/media/video/pwc/pwc-if.c b/drivers/media/video/pwc/pwc-if.c
index db25c3034c11..8d17cf613306 100644
--- a/drivers/media/video/pwc/pwc-if.c
+++ b/drivers/media/video/pwc/pwc-if.c
@@ -62,6 +62,7 @@
 #include <linux/module.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #ifdef CONFIG_USB_PWC_INPUT_EVDEV
 #include <linux/usb/input.h>
 #endif
diff --git a/drivers/media/video/pwc/pwc.h b/drivers/media/video/pwc/pwc.h
index 0be6f814f539..0b658dee05a4 100644
--- a/drivers/media/video/pwc/pwc.h
+++ b/drivers/media/video/pwc/pwc.h
@@ -29,7 +29,6 @@
 #include <linux/usb.h>
 #include <linux/spinlock.h>
 #include <linux/wait.h>
-#include <linux/smp_lock.h>
 #include <linux/version.h>
 #include <linux/mutex.h>
 #include <linux/mm.h>
diff --git a/drivers/media/video/s2255drv.c b/drivers/media/video/s2255drv.c
index 6be845ccc7d7..9e3262c0ba37 100644
--- a/drivers/media/video/s2255drv.c
+++ b/drivers/media/video/s2255drv.c
@@ -48,6 +48,7 @@
 #include <linux/videodev2.h>
 #include <linux/version.h>
 #include <linux/mm.h>
+#include <linux/smp_lock.h>
 #include <media/videobuf-vmalloc.h>
 #include <media/v4l2-common.h>
 #include <media/v4l2-ioctl.h>
diff --git a/drivers/media/video/saa5246a.c b/drivers/media/video/saa5246a.c
index 155804b061e9..b624a4c01fdc 100644
--- a/drivers/media/video/saa5246a.c
+++ b/drivers/media/video/saa5246a.c
@@ -43,7 +43,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/i2c.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/videotext.h>
 #include <linux/videodev2.h>
diff --git a/drivers/media/video/saa5249.c b/drivers/media/video/saa5249.c
index 271d6e931b75..12835fb82c95 100644
--- a/drivers/media/video/saa5249.c
+++ b/drivers/media/video/saa5249.c
@@ -46,7 +46,6 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/i2c.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/videotext.h>
diff --git a/drivers/media/video/saa7134/saa7134-empress.c b/drivers/media/video/saa7134/saa7134-empress.c
index add1757f8930..296788c3bf0e 100644
--- a/drivers/media/video/saa7134/saa7134-empress.c
+++ b/drivers/media/video/saa7134/saa7134-empress.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/delay.h>
 
 #include "saa7134-reg.h"
diff --git a/drivers/media/video/se401.c b/drivers/media/video/se401.c
index c8f05297d0f0..85ffc2cba039 100644
--- a/drivers/media/video/se401.c
+++ b/drivers/media/video/se401.c
@@ -31,6 +31,7 @@ static const char version[] = "0.24";
 #include <linux/init.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/usb.h>
 #include "se401.h"
diff --git a/drivers/media/video/stk-webcam.c b/drivers/media/video/stk-webcam.c
index 2e5937047278..4d6785e63455 100644
--- a/drivers/media/video/stk-webcam.c
+++ b/drivers/media/video/stk-webcam.c
@@ -27,6 +27,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 
 #include <linux/usb.h>
 #include <linux/mm.h>
diff --git a/drivers/media/video/stradis.c b/drivers/media/video/stradis.c
index 0eb313082c97..eaada39c76fd 100644
--- a/drivers/media/video/stradis.c
+++ b/drivers/media/video/stradis.c
@@ -26,6 +26,7 @@
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/poll.h>
diff --git a/drivers/media/video/stv680.c b/drivers/media/video/stv680.c
index 75f286f7a2e9..8b4e7dafce7b 100644
--- a/drivers/media/video/stv680.c
+++ b/drivers/media/video/stv680.c
@@ -62,6 +62,7 @@
 #include <linux/init.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/pagemap.h>
 #include <linux/errno.h>
 #include <linux/videodev.h>
diff --git a/drivers/media/video/usbvideo/vicam.c b/drivers/media/video/usbvideo/vicam.c
index 8d73979596f9..45fce39ec9ad 100644
--- a/drivers/media/video/usbvideo/vicam.c
+++ b/drivers/media/video/usbvideo/vicam.c
@@ -43,6 +43,7 @@
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/firmware.h>
 #include <linux/ihex.h>
diff --git a/drivers/media/video/usbvision/usbvision-video.c b/drivers/media/video/usbvision/usbvision-video.c
index 90b58914f984..90d9b5c0e9a7 100644
--- a/drivers/media/video/usbvision/usbvision-video.c
+++ b/drivers/media/video/usbvision/usbvision-video.c
@@ -50,6 +50,7 @@
 #include <linux/list.h>
 #include <linux/timer.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/utsname.h>
 #include <linux/highmem.h>
diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c
index 31eac66411d7..a7f1b69a7dab 100644
--- a/drivers/media/video/v4l2-dev.c
+++ b/drivers/media/video/v4l2-dev.c
@@ -25,7 +25,6 @@
 #include <linux/init.h>
 #include <linux/kmod.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
diff --git a/drivers/media/video/zoran/zoran_driver.c b/drivers/media/video/zoran/zoran_driver.c
index 3d7df32a3d87..bcdefb1bcb3d 100644
--- a/drivers/media/video/zoran/zoran_driver.c
+++ b/drivers/media/video/zoran/zoran_driver.c
@@ -49,6 +49,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/pci.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index fa2d93a9fb8d..aed609832bc2 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -29,7 +29,6 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/io.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
 #include <linux/miscdevice.h>
diff --git a/drivers/misc/sgi-gru/grukservices.c b/drivers/misc/sgi-gru/grukservices.c
index eedbf9c32760..79689b10f937 100644
--- a/drivers/misc/sgi-gru/grukservices.c
+++ b/drivers/misc/sgi-gru/grukservices.c
@@ -24,7 +24,6 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/device.h>
 #include <linux/miscdevice.h>
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index d53aa9582137..20f9bc626688 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -31,7 +31,6 @@
 #include <linux/tty.h>
 #include <linux/init.h>
 #include <asm/uaccess.h>
-#include <linux/smp_lock.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
 
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index a5b9f6ae507b..d703e73fffa7 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -32,7 +32,6 @@
 #include <linux/pci_hotplug.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/smp_lock.h>
 #include <asm/atomic.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c
index 2fa47af992a8..0ff689afa757 100644
--- a/drivers/pci/hotplug/cpqphp_ctrl.c
+++ b/drivers/pci/hotplug/cpqphp_ctrl.c
@@ -34,7 +34,6 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/wait.h>
-#include <linux/smp_lock.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
 #include <linux/kthread.h>
diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c
index 8450f4a6568a..e6089bdb6e5b 100644
--- a/drivers/pci/hotplug/cpqphp_sysfs.c
+++ b/drivers/pci/hotplug/cpqphp_sysfs.c
@@ -33,6 +33,7 @@
 #include <linux/workqueue.h>
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
+#include <linux/smp_lock.h>
 #include <linux/debugfs.h>
 #include "cpqphp.h"
 
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index ff4034502d24..8aab8edf123e 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -30,7 +30,6 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
-#include <linux/smp_lock.h>
 #include <linux/pci.h>
 #include <linux/workqueue.h>
 #include "../pci.h"
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index ec22284eed30..e1c1ec540893 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -9,7 +9,6 @@
 
 #include <linux/errno.h>
 #include <linux/pci.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <asm/uaccess.h>
 #include "pci.h"
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 4ce3f72ee1c1..df918ef27965 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -16,6 +16,7 @@
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/blkpg.h>
+#include <linux/smp_lock.h>
 
 #include <asm/ccwdev.h>
 #include <asm/cmb.h>
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index 650bcef08f2a..cd78c501803a 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -9,7 +9,6 @@
 
 #include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
-#include <linux/smp_lock.h>
 #include <linux/list.h>
 
 #include <scsi/scsi_tcq.h>
diff --git a/drivers/telephony/ixj.c b/drivers/telephony/ixj.c
index a913efc69669..40de151f2789 100644
--- a/drivers/telephony/ixj.c
+++ b/drivers/telephony/ixj.c
@@ -257,6 +257,7 @@
 #include <linux/fs.h>		/* everything... */
 #include <linux/errno.h>	/* error codes */
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
diff --git a/drivers/telephony/phonedev.c b/drivers/telephony/phonedev.c
index b52cc830c0b4..f3873f650bb4 100644
--- a/drivers/telephony/phonedev.c
+++ b/drivers/telephony/phonedev.c
@@ -23,7 +23,6 @@
 #include <linux/errno.h>
 #include <linux/phonedev.h>
 #include <linux/init.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 0fe434505ac4..ba589d4ca8bc 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -15,7 +15,6 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/uaccess.h>
 #include <linux/bitops.h>
diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c
index 826f3adde5d8..77352ccc245e 100644
--- a/drivers/usb/gadget/amd5536udc.c
+++ b/drivers/usb/gadget/amd5536udc.c
@@ -48,7 +48,6 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/drivers/usb/gadget/langwell_udc.c b/drivers/usb/gadget/langwell_udc.c
index 6829d5961359..a3913519fd58 100644
--- a/drivers/usb/gadget/langwell_udc.c
+++ b/drivers/usb/gadget/langwell_udc.c
@@ -34,7 +34,6 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index 9a2b8920532d..a9b452fe6221 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -28,7 +28,6 @@
 #include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 56976cc0352a..e18f74946e68 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -26,7 +26,6 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/timer.h>
diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c
index 3c5fe5cee05a..90e1a8dedfa9 100644
--- a/drivers/usb/misc/iowarrior.c
+++ b/drivers/usb/misc/iowarrior.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/poll.h>
 #include <linux/usb/iowarrior.h>
 
diff --git a/drivers/usb/misc/rio500.c b/drivers/usb/misc/rio500.c
index deb95bb49fd1..d645f3899fe1 100644
--- a/drivers/usb/misc/rio500.c
+++ b/drivers/usb/misc/rio500.c
@@ -32,6 +32,7 @@
 #include <linux/kernel.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/random.h>
 #include <linux/poll.h>
diff --git a/drivers/usb/misc/usblcd.c b/drivers/usb/misc/usblcd.c
index e0ff9ccd866b..29092b8e59ce 100644
--- a/drivers/usb/misc/usblcd.c
+++ b/drivers/usb/misc/usblcd.c
@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/mutex.h>
 #include <asm/uaccess.h>
diff --git a/drivers/usb/musb/cppi_dma.h b/drivers/usb/musb/cppi_dma.h
index 8a39de3e6e47..59bf949e589b 100644
--- a/drivers/usb/musb/cppi_dma.h
+++ b/drivers/usb/musb/cppi_dma.h
@@ -5,7 +5,6 @@
 
 #include <linux/slab.h>
 #include <linux/list.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/dmapool.h>
 
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index f3772ca3b2cf..381d648a36b8 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -38,7 +38,6 @@
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
-#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/timer.h>
 #include <linux/clk.h>
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 5f08702f672f..5a8ae274d258 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -33,6 +33,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index c40f95c1951c..c31940a307f8 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -26,6 +26,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index a84216464ca0..0c39b55aeef4 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -21,6 +21,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/tty.h>
 #include <linux/tty_driver.h>
 #include <linux/tty_flip.h>
diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index 53ea05645ff8..a85c818be945 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -16,7 +16,6 @@
 #include <linux/compat.h>
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/smp_lock.h>
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/slab.h>
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index aad92f0a1048..6910a98bd73c 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -13,6 +13,7 @@
 #include <linux/parser.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/statfs.h>
 #include "adfs.h"
 #include "dir_f.h"
diff --git a/fs/afs/super.c b/fs/afs/super.c
index ad0514d0115f..e1ea1c240b6a 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/parser.h>
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index f3da2eb51f56..00bf8fcb245f 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -19,7 +19,6 @@
 #include <linux/sched.h>
 #include <linux/compat.h>
 #include <linux/syscalls.h>
-#include <linux/smp_lock.h>
 #include <linux/magic.h>
 #include <linux/dcache.h>
 #include <linux/uaccess.h>
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 54bd07d44e68..1e41aadb1068 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -8,7 +8,6 @@
 #include <linux/time.h>
 #include <linux/string.h>
 #include <linux/fs.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/sched.h>
 #include "bfs.h"
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index 6a021265f018..88b9a3ff44e4 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -11,7 +11,6 @@
 
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
 #include "bfs.h"
 
 #undef DEBUG
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index de1e2fd32080..9d8ba4d54a37 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -26,7 +26,6 @@
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
 #include <linux/swap.h>
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 7c3cd248d8d6..4b833972273a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -22,7 +22,6 @@
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
 #include <linux/swap.h>
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7ffa3d34ea19..791eab19e330 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -26,7 +26,6 @@
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/mpage.h>
 #include <linux/swap.h>
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 9f4db848db10..bd88f25889f7 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -27,7 +27,6 @@
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
 #include <linux/mpage.h>
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9f179d4832d5..6d6d06cb6dfc 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -26,7 +26,6 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
 #include <linux/mpage.h>
diff --git a/fs/char_dev.c b/fs/char_dev.c
index b7c9d5187a75..a173551e19d7 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -13,7 +13,6 @@
 #include <linux/major.h>
 #include <linux/errno.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 
 #include <linux/kobject.h>
diff --git a/fs/compat.c b/fs/compat.c
index fbadb947727b..94502dab972a 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -32,7 +32,6 @@
 #include <linux/smb_mount.h>
 #include <linux/ncp_mount.h>
 #include <linux/nfs4_mount.h>
-#include <linux/smp_lock.h>
 #include <linux/syscalls.h>
 #include <linux/ctype.h>
 #include <linux/module.h>
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 626c7483b4de..f28f070a60fc 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -19,6 +19,7 @@
 #include <linux/compiler.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/smp_lock.h>
 #include <linux/ioctl.h>
 #include <linux/if.h>
 #include <linux/if_bridge.h>
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index a343b4ea62f6..5ab10c3bbebe 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -31,6 +31,7 @@
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 
+#include <linux/smp_lock.h>
 #include <linux/string.h>
 #include <linux/parser.h>
 #include <linux/vfs.h>
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 7cb4badef927..e7431309bdca 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -13,7 +13,6 @@
 #include <linux/sched.h>
 #include <linux/compat.h>
 #include <linux/mount.h>
-#include <linux/smp_lock.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
 
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index bb415408fdb6..24a6abb2aef5 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -12,7 +12,6 @@
 #include <linux/capability.h>
 #include <linux/time.h>
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
 #include <linux/mount.h>
 #include <linux/file.h>
 #include <asm/uaccess.h>
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 38ff75a0fe22..530b4ca01510 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -16,7 +16,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/time.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/compat.h>
 #include <asm/uaccess.h>
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 82f88733b681..bbc94ae4fd77 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -9,7 +9,6 @@
 #include <linux/module.h>
 #include <linux/time.h>
 #include <linux/buffer_head.h>
-#include <linux/smp_lock.h>
 #include "fat.h"
 
 /* Characters that are undesirable in an MS-DOS file name */
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 73471b7ecc8c..cb6e83557112 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -19,7 +19,6 @@
 #include <linux/jiffies.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/namei.h>
 #include "fat.h"
diff --git a/fs/fcntl.c b/fs/fcntl.c
index a040b764f8e3..ae413086db97 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -19,7 +19,6 @@
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
-#include <linux/smp_lock.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
diff --git a/fs/freevxfs/vxfs_super.c b/fs/freevxfs/vxfs_super.c
index cdbd1654e4cd..1e8af939b3e4 100644
--- a/fs/freevxfs/vxfs_super.c
+++ b/fs/freevxfs/vxfs_super.c
@@ -38,6 +38,7 @@
 #include <linux/buffer_head.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/stat.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index 6f833dc8e910..f7fcbe49da72 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -19,6 +19,7 @@
 #include <linux/nls.h>
 #include <linux/parser.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 
 #include "hfs_fs.h"
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 9fc3af0c0dab..c0759fe0855b 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -12,6 +12,7 @@
 #include <linux/pagemap.h>
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/vfs.h>
 #include <linux/nls.h>
 
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 6916c41d7017..8865c94f55f6 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -6,6 +6,7 @@
  *  directory VFS functions
  */
 
+#include <linux/smp_lock.h>
 #include "hpfs_fn.h"
 
 static int hpfs_dir_release(struct inode *inode, struct file *filp)
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 64ab52259204..3efabff00367 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -6,6 +6,7 @@
  *  file VFS functions
  */
 
+#include <linux/smp_lock.h>
 #include "hpfs_fn.h"
 
 #define BLOCKS(size) (((size) + 511) >> 9)
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index c2ea31bae313..701ca54c0867 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -13,7 +13,6 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 
 #include "hpfs.h"
 
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 39a1bfbea312..fe703ae46bc7 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -6,6 +6,7 @@
  *  inode VFS functions
  */
 
+#include <linux/smp_lock.h>
 #include "hpfs_fn.h"
 
 void hpfs_init_inode(struct inode *i)
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index b649232dde97..82b9c4ba9ed0 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -6,6 +6,7 @@
  *  adding & removing files & directories
  */
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include "hpfs_fn.h"
 
 static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index 07a22caf2687..0035c021395a 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/fs.h>
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index f2fdcbce143e..4336adba952a 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/smp_lock.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 1725037374c5..bd173a6ca3b1 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/in.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index 3688e55901fc..e1d28ddd2169 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -10,6 +10,7 @@
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/in.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/clnt.h>
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index af05b918cb5b..6dd48a4405b4 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -10,6 +10,7 @@
 #include <linux/kthread.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 
 #include <linux/nfs4.h>
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 89f98e9a024b..38d42c29fb92 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -29,7 +29,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/pagevec.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0055b813ec2c..05062329b678 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -26,7 +26,6 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include <linux/aio.h>
 
 #include <asm/uaccess.h>
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 64f87194d390..bd7938eda6a8 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -30,7 +30,6 @@
 #include <linux/nfs_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/lockd/bind.h>
-#include <linux/smp_lock.h>
 #include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/nfs_idmap.h>
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 92ce43517814..ff0c080db59b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -45,7 +45,6 @@
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-#include <linux/smp_lock.h>
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 96c4ebfa46f4..73ea5e8d66ce 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -18,7 +18,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
-#include <linux/smp_lock.h>
 
 #include <asm/system.h>
 
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 1250fb978ac1..6d0847562d87 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -25,7 +25,6 @@
 #include <linux/init.h>
 #include <linux/inet.h>
 #include <linux/string.h>
-#include <linux/smp_lock.h>
 #include <linux/ctype.h>
 
 #include <linux/nfs.h>
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index d4c9884cd54b..492c79b7800b 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -18,7 +18,6 @@
 #include <linux/unistd.h>
 #include <linux/slab.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/freezer.h>
 #include <linux/fs_struct.h>
 #include <linux/kthread.h>
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 54100acc1102..1a4fa04cf071 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -43,7 +43,6 @@
  */
 
 #include <linux/pagemap.h>
-#include <linux/smp_lock.h>
 #include "nilfs.h"
 #include "page.h"
 
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 9fcd36dcc9a0..467b413bec21 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -7,7 +7,6 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
-#include <linux/smp_lock.h>
 
 #define MLOG_MASK_PREFIX ML_INODE
 #include <cluster/masklog.h>
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index f3d47d856848..6925b835a43b 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -46,7 +46,6 @@
 #include <linux/reiserfs_acl.h>
 #include <asm/uaccess.h>
 #include <net/checksum.h>
-#include <linux/smp_lock.h>
 #include <linux/stat.h>
 #include <linux/quotaops.h>
 
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 3b52770f46ff..cb5fc57e370b 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -30,6 +30,7 @@
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/slab.h>
+#include <linux/smp_lock.h>
 #include <linux/mutex.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 6db7a6be6c97..8aacd64957a2 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -25,7 +25,6 @@
 /* This file implements EXT2-compatible extended attribute ioctl() calls */
 
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
 #include <linux/mount.h>
 #include "ubifs.h"
 
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index f4e255441574..0542fd507649 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -41,7 +41,6 @@
 #include "xfs_ioctl.h"
 
 #include <linux/dcache.h>
-#include <linux/smp_lock.h>
 
 static struct vm_operations_struct xfs_file_vm_ops;
 
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 2dac064d8359..0026f267da20 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -3,7 +3,6 @@
 
 #ifdef CONFIG_CRASH_DUMP
 #include <linux/kexec.h>
-#include <linux/smp_lock.h>
 #include <linux/device.h>
 #include <linux/proc_fs.h>
 
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 45257475623c..8246c697863d 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -2,7 +2,9 @@
 #define LINUX_HARDIRQ_H
 
 #include <linux/preempt.h>
+#ifdef CONFIG_PREEMPT
 #include <linux/smp_lock.h>
+#endif
 #include <linux/lockdep.h>
 #include <linux/ftrace_irq.h>
 #include <asm/hardirq.h>
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 7bc457593684..26361c4c037a 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -7,7 +7,6 @@
 #ifndef _LINUX_QUOTAOPS_
 #define _LINUX_QUOTAOPS_
 
-#include <linux/smp_lock.h>
 #include <linux/fs.h>
 
 static inline struct quota_info *sb_dqopt(struct super_block *sb)
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index d8910b68e1bd..b99c625fddfe 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -12,7 +12,6 @@
 #include <linux/uio.h>
 #include <asm/byteorder.h>
 #include <linux/scatterlist.h>
-#include <linux/smp_lock.h>
 
 /*
  * Buffer adjustment
diff --git a/kernel/power/user.c b/kernel/power/user.c
index ed97375daae9..bf0014d6a5f0 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -23,7 +23,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/smp_lock.h>
 #include <scsi/scsi_scan.h>
 
 #include <asm/uaccess.h>
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 39af8af6fc30..1090b0aed9ba 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/mutex.h>
 #include <linux/debugfs.h>
+#include <linux/smp_lock.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 3aa0a0dfdfa8..8bc8d8afea6a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,6 +17,7 @@
 #include <linux/writeback.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/smp_lock.h>
 #include <linux/notifier.h>
 #include <linux/irqflags.h>
 #include <linux/debugfs.h>
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 590b83963622..bfbe13786bb4 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -54,6 +54,7 @@
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/if_arp.h>
+#include <linux/smp_lock.h>
 #include <linux/termios.h>	/* For TIOCOUTQ/INQ */
 #include <net/datalink.h>
 #include <net/psnap.h>
diff --git a/net/ipx/af_ipx.c b/net/ipx/af_ipx.c
index 417b0e309495..f1118d92a191 100644
--- a/net/ipx/af_ipx.c
+++ b/net/ipx/af_ipx.c
@@ -41,6 +41,7 @@
 #include <linux/netdevice.h>
 #include <linux/uio.h>
 #include <linux/skbuff.h>
+#include <linux/smp_lock.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/string.h>
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index cb762c8723ea..80cf29aae096 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -45,6 +45,7 @@
 #include <linux/capability.h>
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/smp_lock.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
 #include <linux/init.h>
diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h
index bccf4d0059f0..b001c361ad30 100644
--- a/net/irda/irnet/irnet.h
+++ b/net/irda/irnet/irnet.h
@@ -241,7 +241,6 @@
 #include <linux/module.h>
 
 #include <linux/kernel.h>
-#include <linux/smp_lock.h>
 #include <linux/skbuff.h>
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c
index 6d8ae03c14f5..68cbcb19cbd8 100644
--- a/net/irda/irnet/irnet_ppp.c
+++ b/net/irda/irnet/irnet_ppp.c
@@ -13,6 +13,7 @@
  *	2) as a control channel (write commands, read events)
  */
 
+#include <linux/smp_lock.h>
 #include "irnet_ppp.h"		/* Private header */
 /* Please put other headers in irnet.h - Thanks */
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 5bc2f45bddf0..ebfcf9b89909 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -28,7 +28,6 @@
 #include <linux/kallsyms.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
-#include <linux/smp_lock.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
 #include <linux/in6.h>
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 1102ce1251f7..8f459abe97cf 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -16,7 +16,6 @@
 #include <linux/slab.h>
 #include <linux/mempool.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/spinlock.h>
 #include <linux/mutex.h>
 
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 6f33d33cc064..27d44332f017 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -5,6 +5,7 @@
  */
 
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/errno.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c
index 466e2d22d256..258daa80ad92 100644
--- a/net/wanrouter/wanmain.c
+++ b/net/wanrouter/wanmain.c
@@ -48,6 +48,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>	/* support for loadable modules */
 #include <linux/slab.h>		/* kmalloc(), kfree() */
+#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/string.h>	/* inline mem*, str* functions */
 
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 21cdc872004e..5e6c072c64d3 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -40,6 +40,7 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/smp_lock.h>
 #include <linux/timer.h>
 #include <linux/string.h>
 #include <linux/net.h>
-- 
cgit v1.2.3


From 566b0aaf798a0dddfc455d1a5b05c424c6686c65 Mon Sep 17 00:00:00 2001
From: "jolsa@redhat.com" <jolsa@redhat.com>
Date: Thu, 16 Jul 2009 21:44:26 +0200
Subject: tracing: Remove unused fields/variables

Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Cc: rostedt@goodmis.org
LKML-Reference: <1247773468-11594-2-git-send-email-jolsa@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/trace/ftrace.c | 3 ---
 kernel/trace/trace.c  | 3 +--
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6227dc806377..24e3ff53b24b 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1339,7 +1339,6 @@ struct ftrace_iterator {
 	unsigned		flags;
 	unsigned char		buffer[FTRACE_BUFF_MAX+1];
 	unsigned		buffer_idx;
-	unsigned		filtered;
 };
 
 static void *
@@ -2268,7 +2267,6 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 	}
 
 	if (isspace(ch)) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ret = ftrace_process_regex(iter->buffer,
 					   iter->buffer_idx, enable);
@@ -2399,7 +2397,6 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 		iter = file->private_data;
 
 	if (iter->buffer_idx) {
-		iter->filtered++;
 		iter->buffer[iter->buffer_idx] = 0;
 		ftrace_match_records(iter->buffer, iter->buffer_idx, enable);
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 60a49488b791..e30e6b1dbd4e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4265,7 +4265,6 @@ void ftrace_dump(void)
 
 __init static int tracer_alloc_buffers(void)
 {
-	struct trace_array_cpu *data;
 	int ring_buf_size;
 	int i;
 	int ret = -ENOMEM;
@@ -4315,7 +4314,7 @@ __init static int tracer_alloc_buffers(void)
 
 	/* Allocate the first page for all buffers */
 	for_each_tracing_cpu(i) {
-		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
+		global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 	}
 
-- 
cgit v1.2.3


From ff4e9da2330beb8d64498a513d3f9694e941b01a Mon Sep 17 00:00:00 2001
From: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Date: Mon, 22 Jun 2009 10:33:07 +0800
Subject: tracing: cleanup for tracing_trace_options_read()

'\n' is already appended, and what we need is just an extra
space for the '\0'.

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
LKML-Reference: <4A3EED63.3090908@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e30e6b1dbd4e..38a4a3ee749d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2256,8 +2256,8 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 		len += 3; /* "no" and newline */
 	}
 
-	/* +2 for \n and \0 */
-	buf = kmalloc(len + 2, GFP_KERNEL);
+	/* +1 for \0 */
+	buf = kmalloc(len + 1, GFP_KERNEL);
 	if (!buf) {
 		mutex_unlock(&trace_types_lock);
 		return -ENOMEM;
@@ -2280,7 +2280,7 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 	}
 	mutex_unlock(&trace_types_lock);
 
-	WARN_ON(r >= len + 2);
+	WARN_ON(r >= len + 1);
 
 	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 
-- 
cgit v1.2.3


From 8650ae32ef7045e763825dee6256dde7f331bb85 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 22 Jul 2009 23:29:30 -0400
Subject: tracing: only truncate ftrace files when O_TRUNC is set

The current code will truncate the ftrace files contents if O_APPEND
is not set and the file is opened in write mode. This is incorrect.
It should only truncate the file if O_TRUNC is set. Otherwise
if one of these files is opened by a C program with fopen "r+",
it will incorrectly truncate the file.

Reported-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c       | 4 ++--
 kernel/trace/trace.c        | 2 +-
 kernel/trace/trace_events.c | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1f3ec2afa511..1e1d23c26308 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1662,7 +1662,7 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable)
 
 	mutex_lock(&ftrace_regex_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND))
+	    (file->f_flags & O_TRUNC))
 		ftrace_filter_reset(enable);
 
 	if (file->f_mode & FMODE_READ) {
@@ -2577,7 +2577,7 @@ ftrace_graph_open(struct inode *inode, struct file *file)
 
 	mutex_lock(&graph_lock);
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND)) {
+	    (file->f_flags & O_TRUNC)) {
 		ftrace_graph_count = 0;
 		memset(ftrace_graph_funcs, 0, sizeof(ftrace_graph_funcs));
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8bc8d8afea6a..d8ef28574aa1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2031,7 +2031,7 @@ static int tracing_open(struct inode *inode, struct file *file)
 
 	/* If this file was open for write, then erase contents */
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND)) {
+	    (file->f_flags & O_TRUNC)) {
 		long cpu = (long) inode->i_private;
 
 		if (cpu == TRACE_PIPE_ALL_CPU)
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 53c8fd376a88..23d2972b22d6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -376,7 +376,7 @@ ftrace_event_seq_open(struct inode *inode, struct file *file)
 	const struct seq_operations *seq_ops;
 
 	if ((file->f_mode & FMODE_WRITE) &&
-	    !(file->f_flags & O_APPEND))
+	    (file->f_flags & O_TRUNC))
 		ftrace_clear_events();
 
 	seq_ops = inode->i_private;
-- 
cgit v1.2.3


From 74e7ff8c50b6b022e6ffaa736b16a4dc161d3eaf Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Tue, 28 Jul 2009 20:17:22 +0800
Subject: tracing: Fix missing function_graph events when we splice_read from
 trace_pipe

About a half events are missing when we splice_read
from trace_pipe. They are unexpectedly consumed because we ignore
the TRACE_TYPE_NO_CONSUME return value used by the function graph
tracer when it needs to consume the events by itself to walk on
the ring buffer.

The same problem appears with ftrace_dump()

Example of an output before this patch:

1)               |      ktime_get_real() {
1)   2.846 us    |          read_hpet();
1)   4.558 us    |        }
1)   6.195 us    |      }

After this patch:

0)               |      ktime_get_real() {
0)               |        getnstimeofday() {
0)   1.960 us    |          read_hpet();
0)   3.597 us    |        }
0)   5.196 us    |      }

The fix also applies on 2.6.30

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: stable@kernel.org
LKML-Reference: <4A6EEC52.90704@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 kernel/trace/trace.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8bc8d8afea6a..da984ad065ab 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3085,7 +3085,8 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter)
 			break;
 		}
 
-		trace_consume(iter);
+		if (ret != TRACE_TYPE_NO_CONSUME)
+			trace_consume(iter);
 		rem -= count;
 		if (!find_next_entry_inc(iter))	{
 			rem = 0;
@@ -4233,8 +4234,11 @@ static void __ftrace_dump(bool disable_tracing)
 		iter.pos = -1;
 
 		if (find_next_entry_inc(&iter) != NULL) {
-			print_trace_line(&iter);
-			trace_consume(&iter);
+			int ret;
+
+			ret = print_trace_line(&iter);
+			if (ret != TRACE_TYPE_NO_CONSUME)
+				trace_consume(&iter);
 		}
 
 		trace_printk_seq(&iter.seq);
-- 
cgit v1.2.3


From 5e5bf483986ad86ad25f25eec5299c86eb2d1c57 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 29 Jul 2009 17:11:12 +0200
Subject: tracing/core: Turn ftrace_cpu_disabled into a global var

In order to prepare the moving of the function graph tracer insertion
helpers from trace.c to trace_functions_graph.c, we need to export the
ftrace_cpu_disabled variable.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 2 +-
 kernel/trace/trace.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 38a4a3ee749d..b6211d604131 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -89,7 +89,7 @@ static int dummy_set_flag(u32 old_flags, u32 bit, int set)
  */
 static int tracing_disabled = 1;
 
-static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
 {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 758b0dbed552..c7e92732982d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -519,6 +519,7 @@ extern int DYN_FTRACE_TEST_NAME(void);
 
 extern int ring_buffer_expanded;
 extern bool tracing_selftest_disabled;
+DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 extern int trace_selftest_startup_function(struct tracer *trace,
-- 
cgit v1.2.3


From c0a0d0d3f65284c71115a9bb1ed801ee33eeb552 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 29 Jul 2009 17:51:13 +0200
Subject: tracing/core: Make the stack entry helpers global

Make the stacktrace event insertion helpers globals.
This has two effects:

- Prepare for moving the sched events insertion helpers to
  the sched switch tracer file.
- Move some ifdef outside function definitions

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 24 ++++++++----------------
 kernel/trace/trace.h | 28 +++++++++++++++++++++++++---
 2 files changed, 33 insertions(+), 19 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index b6211d604131..d6059a493e7f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -866,10 +866,6 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 
 	return event;
 }
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags, int skip, int pc);
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   unsigned long flags, int pc);
 
 static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
 					struct ring_buffer_event *event,
@@ -1003,11 +999,11 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 		trace_function(tr, ip, parent_ip, flags, pc);
 }
 
+#ifdef CONFIG_STACKTRACE
 static void __ftrace_trace_stack(struct trace_array *tr,
 				 unsigned long flags,
 				 int skip, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
@@ -1028,12 +1024,10 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	save_stack_trace(&trace);
 	if (!filter_check_discard(call, entry, tr->buffer, event))
 		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
 }
 
-static void ftrace_trace_stack(struct trace_array *tr,
-			       unsigned long flags,
-			       int skip, int pc)
+void ftrace_trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+			int pc)
 {
 	if (!(trace_flags & TRACE_ITER_STACKTRACE))
 		return;
@@ -1041,17 +1035,14 @@ static void ftrace_trace_stack(struct trace_array *tr,
 	__ftrace_trace_stack(tr, flags, skip, pc);
 }
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc)
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc)
 {
 	__ftrace_trace_stack(tr, flags, skip, pc);
 }
 
-static void ftrace_trace_userstack(struct trace_array *tr,
-				   unsigned long flags, int pc)
+void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags, int pc)
 {
-#ifdef CONFIG_STACKTRACE
 	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
@@ -1076,7 +1067,6 @@ static void ftrace_trace_userstack(struct trace_array *tr,
 	save_stack_trace_user(&trace);
 	if (!filter_check_discard(call, entry, tr->buffer, event))
 		ring_buffer_unlock_commit(tr->buffer, event);
-#endif
 }
 
 #ifdef UNUSED
@@ -1086,6 +1076,8 @@ static void __trace_userstack(struct trace_array *tr, unsigned long flags)
 }
 #endif /* UNUSED */
 
+#endif /* CONFIG_STACKTRACE */
+
 static void
 ftrace_trace_special(void *__tr,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c7e92732982d..116524d62366 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -489,9 +489,31 @@ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
 
-void __trace_stack(struct trace_array *tr,
-		   unsigned long flags,
-		   int skip, int pc);
+#ifdef CONFIG_STACKTRACE
+void ftrace_trace_stack(struct trace_array *tr, unsigned long flags,
+			int skip, int pc);
+
+void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags,
+			    int pc);
+
+void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
+		   int pc);
+#else
+static inline void ftrace_trace_stack(struct trace_array *tr,
+				      unsigned long flags, int skip, int pc)
+{
+}
+
+static inline void ftrace_trace_userstack(struct trace_array *tr,
+					  unsigned long flags, int pc)
+{
+}
+
+static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
+				 int skip, int pc)
+{
+}
+#endif /* CONFIG_STACKTRACE */
 
 extern cycle_t ftrace_now(int cpu);
 
-- 
cgit v1.2.3


From 82e04af498a85ba425efe77580b7ba08234411df Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 29 Jul 2009 18:00:29 +0200
Subject: tracing: Move sched event insertion helpers in the sched switch
 tracer file

The sched events helpers which insert the sched switch and wakeup
events into the ring buffer currently reside in trace.c
But this file is quite overloaded and the right place for these helpers
is in the sched switch tracer file.

Then move them to trace_functions.c

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c              | 56 --------------------------------------
 kernel/trace/trace_sched_switch.c | 57 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+), 56 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d6059a493e7f..1b73acb40e56 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1105,62 +1105,6 @@ __trace_special(void *__tr, void *__data,
 	ftrace_trace_special(__tr, arg1, arg2, arg3, preempt_count());
 }
 
-void
-tracing_sched_switch_trace(struct trace_array *tr,
-			   struct task_struct *prev,
-			   struct task_struct *next,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_context_switch;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_CTX,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= prev->pid;
-	entry->prev_prio		= prev->prio;
-	entry->prev_state		= prev->state;
-	entry->next_pid			= next->pid;
-	entry->next_prio		= next->prio;
-	entry->next_state		= next->state;
-	entry->next_cpu	= task_cpu(next);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, flags, pc);
-}
-
-void
-tracing_sched_wakeup_trace(struct trace_array *tr,
-			   struct task_struct *wakee,
-			   struct task_struct *curr,
-			   unsigned long flags, int pc)
-{
-	struct ftrace_event_call *call = &event_wakeup;
-	struct ring_buffer_event *event;
-	struct ctx_switch_entry *entry;
-
-	event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->prev_pid			= curr->pid;
-	entry->prev_prio		= curr->prio;
-	entry->prev_state		= curr->state;
-	entry->next_pid			= wakee->pid;
-	entry->next_prio		= wakee->prio;
-	entry->next_state		= wakee->state;
-	entry->next_cpu			= task_cpu(wakee);
-
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
-}
-
 void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index a98106dd979c..e1285d7b5488 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -20,6 +20,34 @@ static int			sched_ref;
 static DEFINE_MUTEX(sched_register_mutex);
 static int			sched_stopped;
 
+
+void
+tracing_sched_switch_trace(struct trace_array *tr,
+			   struct task_struct *prev,
+			   struct task_struct *next,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_context_switch;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_CTX,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= prev->pid;
+	entry->prev_prio		= prev->prio;
+	entry->prev_state		= prev->state;
+	entry->next_pid			= next->pid;
+	entry->next_prio		= next->prio;
+	entry->next_state		= next->state;
+	entry->next_cpu	= task_cpu(next);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		trace_buffer_unlock_commit(tr, event, flags, pc);
+}
+
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 			struct task_struct *next)
@@ -49,6 +77,35 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	local_irq_restore(flags);
 }
 
+void
+tracing_sched_wakeup_trace(struct trace_array *tr,
+			   struct task_struct *wakee,
+			   struct task_struct *curr,
+			   unsigned long flags, int pc)
+{
+	struct ftrace_event_call *call = &event_wakeup;
+	struct ring_buffer_event *event;
+	struct ctx_switch_entry *entry;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->prev_pid			= curr->pid;
+	entry->prev_prio		= curr->prio;
+	entry->prev_state		= curr->state;
+	entry->next_pid			= wakee->pid;
+	entry->next_prio		= wakee->prio;
+	entry->next_state		= wakee->state;
+	entry->next_cpu			= task_cpu(wakee);
+
+	if (!filter_check_discard(call, entry, tr->buffer, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
+	ftrace_trace_stack(tr, flags, 6, pc);
+	ftrace_trace_userstack(tr, flags, pc);
+}
+
 static void
 probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success)
 {
-- 
cgit v1.2.3


From 1a0799a8fef5acc6503f9c5e79b2cd003317826c Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Wed, 29 Jul 2009 18:59:58 +0200
Subject: tracing/function-graph-tracer: Move graph event insertion helpers in
 the graph tracer file

The function graph events helpers which insert the function entry and
return events into the ring buffer currently reside in trace.c
But this file is quite overloaded and the right place for these helpers
is in the function graph tracer file.

Then move them to trace_functions_graph.c

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c                 | 110 -------------------------------
 kernel/trace/trace.h                 |   1 +
 kernel/trace/trace_functions_graph.c | 122 ++++++++++++++++++++++++++++++++++-
 kernel/trace/trace_selftest.c        |   1 +
 4 files changed, 121 insertions(+), 113 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1b73acb40e56..0cfd1a62def1 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -942,54 +942,6 @@ trace_function(struct trace_array *tr,
 		ring_buffer_unlock_commit(tr->buffer, event);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static int __trace_graph_entry(struct trace_array *tr,
-				struct ftrace_graph_ent *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_entry;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ent_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return 0;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_ENT,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return 0;
-	entry	= ring_buffer_event_data(event);
-	entry->graph_ent			= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
-
-	return 1;
-}
-
-static void __trace_graph_return(struct trace_array *tr,
-				struct ftrace_graph_ret *trace,
-				unsigned long flags,
-				int pc)
-{
-	struct ftrace_event_call *call = &event_funcgraph_exit;
-	struct ring_buffer_event *event;
-	struct ftrace_graph_ret_entry *entry;
-
-	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
-		return;
-
-	event = trace_buffer_lock_reserve(&global_trace, TRACE_GRAPH_RET,
-					  sizeof(*entry), flags, pc);
-	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	entry->ret				= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(global_trace.buffer, event);
-}
-#endif
-
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
        unsigned long ip, unsigned long parent_ip, unsigned long flags,
@@ -1129,68 +1081,6 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 	local_irq_restore(flags);
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-int trace_graph_entry(struct ftrace_graph_ent *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int ret;
-	int cpu;
-	int pc;
-
-	if (!ftrace_trace_task(current))
-		return 0;
-
-	if (!ftrace_graph_addr(trace->func))
-		return 0;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		ret = __trace_graph_entry(tr, trace, flags, pc);
-	} else {
-		ret = 0;
-	}
-	/* Only do the atomic if it is not already set */
-	if (!test_tsk_trace_graph(current))
-		set_tsk_trace_graph(current);
-
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-void trace_graph_return(struct ftrace_graph_ret *trace)
-{
-	struct trace_array *tr = &global_trace;
-	struct trace_array_cpu *data;
-	unsigned long flags;
-	long disabled;
-	int cpu;
-	int pc;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = tr->data[cpu];
-	disabled = atomic_inc_return(&data->disabled);
-	if (likely(disabled == 1)) {
-		pc = preempt_count();
-		__trace_graph_return(tr, trace, flags, pc);
-	}
-	if (!trace->depth)
-		clear_tsk_trace_graph(current);
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
-
 /**
  * trace_vbprintk - write binary msg to tracing buffer
  *
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 116524d62366..9301f1263c5c 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -471,6 +471,7 @@ void trace_function(struct trace_array *tr,
 
 void trace_graph_return(struct ftrace_graph_ret *trace);
 int trace_graph_entry(struct ftrace_graph_ent *trace);
+void set_graph_array(struct trace_array *tr);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index e30472da15d5..f97244a41a4f 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -52,7 +52,7 @@ static struct tracer_flags tracer_flags = {
 	.opts = trace_opts
 };
 
-/* pid on the last trace processed */
+static struct trace_array *graph_array;
 
 
 /* Add a function return address to the trace stack on thread info.*/
@@ -166,10 +166,121 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	return ret;
 }
 
+static int __trace_graph_entry(struct trace_array *tr,
+				struct ftrace_graph_ent *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_entry;
+	struct ring_buffer_event *event;
+	struct ftrace_graph_ent_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return 0;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_GRAPH_ENT,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return 0;
+	entry	= ring_buffer_event_data(event);
+	entry->graph_ent			= *trace;
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
+
+	return 1;
+}
+
+int trace_graph_entry(struct ftrace_graph_ent *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int ret;
+	int cpu;
+	int pc;
+
+	if (unlikely(!tr))
+		return 0;
+
+	if (!ftrace_trace_task(current))
+		return 0;
+
+	if (!ftrace_graph_addr(trace->func))
+		return 0;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		ret = __trace_graph_entry(tr, trace, flags, pc);
+	} else {
+		ret = 0;
+	}
+	/* Only do the atomic if it is not already set */
+	if (!test_tsk_trace_graph(current))
+		set_tsk_trace_graph(current);
+
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static void __trace_graph_return(struct trace_array *tr,
+				struct ftrace_graph_ret *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ftrace_event_call *call = &event_funcgraph_exit;
+	struct ring_buffer_event *event;
+	struct ftrace_graph_ret_entry *entry;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_GRAPH_RET,
+					  sizeof(*entry), flags, pc);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	entry->ret				= *trace;
+	if (!filter_current_check_discard(call, entry, event))
+		ring_buffer_unlock_commit(tr->buffer, event);
+}
+
+void trace_graph_return(struct ftrace_graph_ret *trace)
+{
+	struct trace_array *tr = graph_array;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_graph_return(tr, trace, flags, pc);
+	}
+	if (!trace->depth)
+		clear_tsk_trace_graph(current);
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+}
+
 static int graph_trace_init(struct trace_array *tr)
 {
-	int ret = register_ftrace_graph(&trace_graph_return,
-					&trace_graph_entry);
+	int ret;
+
+	graph_array = tr;
+	ret = register_ftrace_graph(&trace_graph_return,
+				    &trace_graph_entry);
 	if (ret)
 		return ret;
 	tracing_start_cmdline_record();
@@ -177,6 +288,11 @@ static int graph_trace_init(struct trace_array *tr)
 	return 0;
 }
 
+void set_graph_array(struct trace_array *tr)
+{
+	graph_array = tr;
+}
+
 static void graph_trace_reset(struct trace_array *tr)
 {
 	tracing_stop_cmdline_record();
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 00dd6485bdd7..d2cdbabb4ead 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -288,6 +288,7 @@ trace_selftest_startup_function_graph(struct tracer *trace,
 	 * to detect and recover from possible hangs
 	 */
 	tracing_reset_online_cpus(tr);
+	set_graph_array(tr);
 	ret = register_ftrace_graph(&trace_graph_return,
 				    &trace_graph_entry_watchdog);
 	if (ret) {
-- 
cgit v1.2.3


From f413cdb80ce00ec1a4d0ab949b5d96c81cae7f75 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 7 Aug 2009 01:25:54 +0200
Subject: perf_counter: Fix/complete ftrace event records sampling

This patch implements the kernel side support for ftrace event
record sampling.

A new counter sampling attribute is added:

   PERF_SAMPLE_TP_RECORD

which requests ftrace events record sampling. In this case
if a PERF_TYPE_TRACEPOINT counter is active and a tracepoint
fires, we emit the tracepoint binary record to the
perfcounter event buffer, as a sample.

Result, after setting PERF_SAMPLE_TP_RECORD attribute from perf
record:

 perf record -f -F 1 -a -e workqueue:workqueue_execution
 perf report -D

 0x21e18 [0x48]: event: 9
 .
 . ... raw event: size 72 bytes
 .  0000:  09 00 00 00 01 00 48 00 d0 c7 00 81 ff ff ff ff  ......H........
 .  0010:  0a 00 00 00 0a 00 00 00 21 00 00 00 00 00 00 00  ........!......
 .  0020:  2b 00 01 02 0a 00 00 00 0a 00 00 00 65 76 65 6e  +...........eve
 .  0030:  74 73 2f 31 00 00 00 00 00 00 00 00 0a 00 00 00  ts/1...........
 .  0040:  e0 b1 31 81 ff ff ff ff                          .......
.
0x21e18 [0x48]: PERF_EVENT_SAMPLE (IP, 1): 10: 0xffffffff8100c7d0 period: 33

The raw ftrace binary record starts at offset 0020.

Translation:

 struct trace_entry {
	type		= 0x2b = 43;
	flags		= 1;
	preempt_count	= 2;
	pid		= 0xa = 10;
	tgid		= 0xa = 10;
 }

 thread_comm = "events/1"
 thread_pid  = 0xa = 10;
 func	    = 0xffffffff8131b1e0 = flush_to_ldisc()

What will come next?

 - Userspace support ('perf trace'), 'flight data recorder' mode
   for perf trace, etc.

 - The unconditional copy from the profiling callback brings
   some costs however if someone wants no such sampling to
   occur, and needs to be fixed in the future. For that we need
   to have an instant access to the perf counter attribute.
   This is a matter of a flag to add in the struct ftrace_event.

 - Take care of the events recursivity! Don't ever try to record
   a lock event for example, it seems some locking is used in
   the profiling fast path and lead to a tracing recursivity.
   That will be fixed using raw spinlock or recursivity
   protection.

 - [...]

 - Profit! :-)

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Tom Zanussi <tzanussi@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace_event.h |   4 +-
 include/linux/perf_counter.h |   9 ++-
 include/trace/ftrace.h       | 130 ++++++++++++++++++++++++++++++++-----------
 kernel/perf_counter.c        |  18 +++++-
 kernel/trace/trace.c         |   1 +
 kernel/trace/trace.h         |   4 --
 tools/perf/builtin-record.c  |   1 +
 7 files changed, 126 insertions(+), 41 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index d7cd193c2277..a81170de7f6b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -89,7 +89,9 @@ enum print_line_t {
 	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
 };
 
-
+void tracing_generic_entry_update(struct trace_entry *entry,
+				  unsigned long flags,
+				  int pc);
 struct ring_buffer_event *
 trace_current_buffer_lock_reserve(int type, unsigned long len,
 				  unsigned long flags, int pc);
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index e604e6ef72dd..a67dd5c5b6d3 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -121,8 +121,9 @@ enum perf_counter_sample_format {
 	PERF_SAMPLE_CPU				= 1U << 7,
 	PERF_SAMPLE_PERIOD			= 1U << 8,
 	PERF_SAMPLE_STREAM_ID			= 1U << 9,
+	PERF_SAMPLE_TP_RECORD			= 1U << 10,
 
-	PERF_SAMPLE_MAX = 1U << 10,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 11,		/* non-ABI */
 };
 
 /*
@@ -413,6 +414,11 @@ struct perf_callchain_entry {
 	__u64				ip[PERF_MAX_STACK_DEPTH];
 };
 
+struct perf_tracepoint_record {
+	int				size;
+	char				*record;
+};
+
 struct task_struct;
 
 /**
@@ -681,6 +687,7 @@ struct perf_sample_data {
 	struct pt_regs			*regs;
 	u64				addr;
 	u64				period;
+	void				*private;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index fec71f8dbc48..7fb16d90e7b1 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -353,15 +353,7 @@ static inline int ftrace_get_offsets_##call(				\
 /*
  * Generate the functions needed for tracepoint perf_counter support.
  *
- * static void ftrace_profile_<call>(proto)
- * {
- * 	extern void perf_tpcounter_event(int, u64, u64);
- * 	u64 __addr = 0, __count = 1;
- *
- * 	<assign>   <-- here we expand the TP_perf_assign() macro
- *
- * 	perf_tpcounter_event(event_<call>.id, __addr, __count);
- * }
+ * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
  *
  * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call)
  * {
@@ -381,28 +373,10 @@ static inline int ftrace_get_offsets_##call(				\
  *
  */
 
-#undef TP_fast_assign
-#define TP_fast_assign(args...)
-
-#undef TP_perf_assign
-#define TP_perf_assign(args...) args
-
-#undef __perf_addr
-#define __perf_addr(a) __addr = (a)
-
-#undef __perf_count
-#define __perf_count(c) __count = (c)
-
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
 									\
-static void ftrace_profile_##call(proto)				\
-{									\
-	extern void perf_tpcounter_event(int, u64, u64);		\
-	u64 __addr = 0, __count = 1;					\
-	{ assign; }							\
-	perf_tpcounter_event(event_##call.id, __addr, __count);		\
-}									\
+static void ftrace_profile_##call(proto);				\
 									\
 static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
 {									\
@@ -422,12 +396,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef TP_fast_assign
-#define TP_fast_assign(args...) args
-
-#undef TP_perf_assign
-#define TP_perf_assign(args...)
-
 #endif
 
 /*
@@ -647,5 +615,99 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+/*
+ * Define the insertion callback to profile events
+ *
+ * The job is very similar to ftrace_raw_event_<call> except that we don't
+ * insert in the ring buffer but in a perf counter.
+ *
+ * static void ftrace_profile_<call>(proto)
+ * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ *	struct ftrace_event_call *event_call = &event_<call>;
+ *	extern void perf_tpcounter_event(int, u64, u64, void *, int);
+ *	struct ftrace_raw_##call *entry;
+ *	u64 __addr = 0, __count = 1;
+ *	unsigned long irq_flags;
+ *	int __entry_size;
+ *	int __data_size;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *	__entry_size = __data_size + sizeof(*entry);
+ *
+ *	do {
+ *		char raw_data[__entry_size]; <- allocate our sample in the stack
+ *		struct trace_entry *ent;
+ *
+ *		entry = (struct ftrace_raw_<call> *)raw_data;
+ *		ent = &entry->ent;
+ *		tracing_generic_entry_update(ent, irq_flags, pc);
+ *		ent->type = event_call->id;
+ *
+ *		<tstruct> <- do some jobs with dynamic arrays
+ *
+ *		<assign>  <- affect our values
+ *
+ *		perf_tpcounter_event(event_call->id, __addr, __count, entry,
+ *			     __entry_size);  <- submit them to perf counter
+ *	} while (0);
+ *
+ * }
+ */
+
+#ifdef CONFIG_EVENT_PROFILE
+
+#undef __perf_addr
+#define __perf_addr(a) __addr = (a)
+
+#undef __perf_count
+#define __perf_count(c) __count = (c)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static void ftrace_profile_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	extern void perf_tpcounter_event(int, u64, u64, void *, int);	\
+	struct ftrace_raw_##call *entry;				\
+	u64 __addr = 0, __count = 1;					\
+	unsigned long irq_flags;					\
+	int __entry_size;						\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+	__entry_size = ALIGN(__data_size + sizeof(*entry), sizeof(u64));\
+									\
+	do {								\
+		char raw_data[__entry_size];				\
+		struct trace_entry *ent;				\
+									\
+		entry = (struct ftrace_raw_##call *)raw_data;		\
+		ent = &entry->ent;					\
+		tracing_generic_entry_update(ent, irq_flags, pc);	\
+		ent->type = event_call->id;				\
+									\
+		tstruct							\
+									\
+		{ assign; }						\
+									\
+		perf_tpcounter_event(event_call->id, __addr, __count, entry,\
+			     __entry_size);				\
+	} while (0);							\
+									\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_EVENT_PROFILE */
+
 #undef _TRACE_PROFILE_INIT
 
diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 52eb4b68d34f..868102172aa4 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -2646,6 +2646,7 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		u64 counter;
 	} group_entry;
 	struct perf_callchain_entry *callchain = NULL;
+	struct perf_tracepoint_record *tp;
 	int callchain_size = 0;
 	u64 time;
 	struct {
@@ -2714,6 +2715,11 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 			header.size += sizeof(u64);
 	}
 
+	if (sample_type & PERF_SAMPLE_TP_RECORD) {
+		tp = data->private;
+		header.size += tp->size;
+	}
+
 	ret = perf_output_begin(&handle, counter, header.size, nmi, 1);
 	if (ret)
 		return;
@@ -2777,6 +2783,9 @@ static void perf_counter_output(struct perf_counter *counter, int nmi,
 		}
 	}
 
+	if (sample_type & PERF_SAMPLE_TP_RECORD)
+		perf_output_copy(&handle, tp->record, tp->size);
+
 	perf_output_end(&handle);
 }
 
@@ -3703,11 +3712,18 @@ static const struct pmu perf_ops_task_clock = {
 };
 
 #ifdef CONFIG_EVENT_PROFILE
-void perf_tpcounter_event(int event_id, u64 addr, u64 count)
+void perf_tpcounter_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size)
 {
+	struct perf_tracepoint_record tp = {
+		.size = entry_size,
+		.record = record,
+	};
+
 	struct perf_sample_data data = {
 		.regs = get_irq_regs(),
 		.addr = addr,
+		.private = &tp,
 	};
 
 	if (!data.regs)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8930e39b9d8c..c22b40f8f576 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -848,6 +848,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
 }
+EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
 struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 						    int type,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3548ae5cc780..8b9f4f6e9559 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -438,10 +438,6 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
 struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
 					  int *ent_cpu, u64 *ent_ts);
 
-void tracing_generic_entry_update(struct trace_entry *entry,
-				  unsigned long flags,
-				  int pc);
-
 void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6da09928130f..90c98082af10 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -412,6 +412,7 @@ static void create_counter(int counter, int cpu, pid_t pid)
 	if (call_graph)
 		attr->sample_type	|= PERF_SAMPLE_CALLCHAIN;
 
+
 	attr->mmap		= track;
 	attr->comm		= track;
 	attr->inherit		= (cpu < 0) && inherit;
-- 
cgit v1.2.3


From 7770841e63730d62928b0879498064e9614b2ce0 Mon Sep 17 00:00:00 2001
From: Zhaolei <zhaolei@cn.fujitsu.com>
Date: Fri, 7 Aug 2009 18:53:21 +0800
Subject: tracing: Rename set_tracer_flags()'s local variable trace_flags

set_tracer_flags() have a local variable named trace_flags which has
the same name than a global one in the same scope.
This leads to confusion, using tracer_flags should be better by its
meaning.

Changelog:
v1->v2: Simplified another patch in this patchset, no change in this
        patch.

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 kernel/trace/trace.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e793cda91dd3..8ac204360a39 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2118,23 +2118,23 @@ tracing_trace_options_read(struct file *filp, char __user *ubuf,
 /* Try to assign a tracer specific option */
 static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 {
-	struct tracer_flags *trace_flags = trace->flags;
+	struct tracer_flags *tracer_flags = trace->flags;
 	struct tracer_opt *opts = NULL;
 	int ret = 0, i = 0;
 	int len;
 
-	for (i = 0; trace_flags->opts[i].name; i++) {
-		opts = &trace_flags->opts[i];
+	for (i = 0; tracer_flags->opts[i].name; i++) {
+		opts = &tracer_flags->opts[i];
 		len = strlen(opts->name);
 
 		if (strncmp(cmp, opts->name, len) == 0) {
-			ret = trace->set_flag(trace_flags->val,
+			ret = trace->set_flag(tracer_flags->val,
 				opts->bit, !neg);
 			break;
 		}
 	}
 	/* Not found */
-	if (!trace_flags->opts[i].name)
+	if (!tracer_flags->opts[i].name)
 		return -EINVAL;
 
 	/* Refused to handle */
@@ -2142,9 +2142,9 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
 		return ret;
 
 	if (neg)
-		trace_flags->val &= ~opts->bit;
+		tracer_flags->val &= ~opts->bit;
 	else
-		trace_flags->val |= opts->bit;
+		tracer_flags->val |= opts->bit;
 
 	return 0;
 }
-- 
cgit v1.2.3


From f2d84b65b9778e8a35dd904f7d3993f0a60c9756 Mon Sep 17 00:00:00 2001
From: Zhaolei <zhaolei@cn.fujitsu.com>
Date: Fri, 7 Aug 2009 18:55:48 +0800
Subject: ftrace: Unify effect of writing to trace_options and option/*

"echo noglobal-clock > trace_options" can be used to change trace
clock but "echo 0 > options/global-clock" can't. The flag toggling
will be silently accepted without actually changing the clock callback.

We can fix it by using set_tracer_flags() in
trace_options_core_write().

Changelog:
v1->v2: Simplified switch() after Li Zefan <lizf@cn.fujitsu.com>'s
        suggestion

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
Cc: Steven Rostedt <srostedt@redhat.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
---
 kernel/trace/trace.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c22b40f8f576..8c358395d338 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3896,17 +3896,9 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (ret < 0)
 		return ret;
 
-	switch (val) {
-	case 0:
-		trace_flags &= ~(1 << index);
-		break;
-	case 1:
-		trace_flags |= 1 << index;
-		break;
-
-	default:
+	if (val != 0 && val != 1)
 		return -EINVAL;
-	}
+	set_tracer_flags(1 << index, val);
 
 	*ppos += cnt;
 
-- 
cgit v1.2.3


From 5079f3261ffd7fe4a537679af695f2328943a245 Mon Sep 17 00:00:00 2001
From: Zhaolei <zhaolei@cn.fujitsu.com>
Date: Tue, 25 Aug 2009 16:12:56 +0800
Subject: ftrace: Move setting of clock-source out of options

There are many clock sources for the tracing system but we can only
enable/disable one at a time with the trace/options file.
We can move the setting of clock-source out of options and add a separate
file for it:
 # cat trace_clock
 [local] global
 # echo global > trace_clock
 # cat trace_clock
 local [global]

Signed-off-by: Zhao Lei <zhaolei@cn.fujitsu.com>
LKML-Reference: <4A939D08.6050604@cn.fujitsu.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 92 ++++++++++++++++++++++++++++++++++++++++++----------
 kernel/trace/trace.h |  7 ++--
 2 files changed, 79 insertions(+), 20 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 8ac204360a39..63dbc7ff213f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -323,12 +323,21 @@ static const char *trace_options[] = {
 	"printk-msg-only",
 	"context-info",
 	"latency-format",
-	"global-clock",
 	"sleep-time",
 	"graph-time",
 	NULL
 };
 
+static struct {
+	u64 (*func)(void);
+	const char *name;
+} trace_clocks[] = {
+	{ trace_clock_local,	"local" },
+	{ trace_clock_global,	"global" },
+};
+
+int trace_clock_id;
+
 /*
  * ftrace_max_lock is used to protect the swapping of buffers
  * when taking a max snapshot. The buffers themselves are
@@ -2159,22 +2168,6 @@ static void set_tracer_flags(unsigned int mask, int enabled)
 		trace_flags |= mask;
 	else
 		trace_flags &= ~mask;
-
-	if (mask == TRACE_ITER_GLOBAL_CLK) {
-		u64 (*func)(void);
-
-		if (enabled)
-			func = trace_clock_global;
-		else
-			func = trace_clock_local;
-
-		mutex_lock(&trace_types_lock);
-		ring_buffer_set_clock(global_trace.buffer, func);
-
-		if (max_tr.buffer)
-			ring_buffer_set_clock(max_tr.buffer, func);
-		mutex_unlock(&trace_types_lock);
-	}
 }
 
 static ssize_t
@@ -3142,6 +3135,62 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static ssize_t tracing_clock_read(struct file *filp, char __user *ubuf,
+				  size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int bufiter = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++)
+		bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter,
+			"%s%s%s%s", i ? " " : "",
+			i == trace_clock_id ? "[" : "", trace_clocks[i].name,
+			i == trace_clock_id ? "]" : "");
+	bufiter += snprintf(buf + bufiter, sizeof(buf) - bufiter, "\n");
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, bufiter);
+}
+
+static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *fpos)
+{
+	char buf[64];
+	const char *clockstr;
+	int i;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	clockstr = strstrip(buf);
+
+	for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) {
+		if (strcmp(trace_clocks[i].name, clockstr) == 0)
+			break;
+	}
+	if (i == ARRAY_SIZE(trace_clocks))
+		return -EINVAL;
+
+	trace_clock_id = i;
+
+	mutex_lock(&trace_types_lock);
+
+	ring_buffer_set_clock(global_trace.buffer, trace_clocks[i].func);
+	if (max_tr.buffer)
+		ring_buffer_set_clock(max_tr.buffer, trace_clocks[i].func);
+
+	mutex_unlock(&trace_types_lock);
+
+	*fpos += cnt;
+
+	return cnt;
+}
+
 static const struct file_operations tracing_max_lat_fops = {
 	.open		= tracing_open_generic,
 	.read		= tracing_max_lat_read,
@@ -3179,6 +3228,12 @@ static const struct file_operations tracing_mark_fops = {
 	.write		= tracing_mark_write,
 };
 
+static const struct file_operations trace_clock_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_clock_read,
+	.write		= tracing_clock_write,
+};
+
 struct ftrace_buffer_info {
 	struct trace_array	*tr;
 	void			*spare;
@@ -3918,6 +3973,9 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("saved_cmdlines", 0444, d_tracer,
 			NULL, &tracing_saved_cmdlines_fops);
 
+	trace_create_file("trace_clock", 0644, d_tracer, NULL,
+			  &trace_clock_fops);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 	trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 			&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 64dda5709cb9..654fd657bd03 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -568,6 +568,8 @@ trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
+extern int trace_clock_id;
+
 /* Standard output formatting function used for function return traces */
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern enum print_line_t print_graph_function(struct trace_iterator *iter);
@@ -656,9 +658,8 @@ enum trace_iterator_flags {
 	TRACE_ITER_PRINTK_MSGONLY	= 0x10000,
 	TRACE_ITER_CONTEXT_INFO		= 0x20000, /* Print pid/cpu/time */
 	TRACE_ITER_LATENCY_FMT		= 0x40000,
-	TRACE_ITER_GLOBAL_CLK		= 0x80000,
-	TRACE_ITER_SLEEP_TIME		= 0x100000,
-	TRACE_ITER_GRAPH_TIME		= 0x200000,
+	TRACE_ITER_SLEEP_TIME		= 0x80000,
+	TRACE_ITER_GRAPH_TIME		= 0x100000,
 };
 
 /*
-- 
cgit v1.2.3


From 5d4a9dba2d7fbab69f00dedd430d1788834a055a Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 27 Aug 2009 16:52:21 -0400
Subject: tracing: only show tracing_max_latency when latency tracer configured

The tracing_max_latency file should only be present when one of the
latency tracers ({preempt|irqs}off, wakeup*) are enabled.

This patch also removes tracing_thresh when latency tracers are not
enabled, as well as compiles out code that is only used for latency
tracers.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 92 ++++++++++++++++++++++++++++------------------------
 kernel/trace/trace.h |  2 ++
 2 files changed, 52 insertions(+), 42 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 63dbc7ff213f..0f0881676dc9 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -43,9 +43,6 @@
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
-unsigned long __read_mostly	tracing_max_latency;
-unsigned long __read_mostly	tracing_thresh;
-
 /*
  * On boot up, the ring buffer is set to the minimum size, so that
  * we do not waste memory on systems that are not using tracing.
@@ -338,45 +335,6 @@ static struct {
 
 int trace_clock_id;
 
-/*
- * ftrace_max_lock is used to protect the swapping of buffers
- * when taking a max snapshot. The buffers themselves are
- * protected by per_cpu spinlocks. But the action of the swap
- * needs its own lock.
- *
- * This is defined as a raw_spinlock_t in order to help
- * with performance when lockdep debugging is enabled.
- */
-static raw_spinlock_t ftrace_max_lock =
-	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
-
-/*
- * Copy the new maximum trace into the separate maximum-trace
- * structure. (this way the maximum trace is permanently saved,
- * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
- */
-static void
-__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
-{
-	struct trace_array_cpu *data = tr->data[cpu];
-
-	max_tr.cpu = cpu;
-	max_tr.time_start = data->preempt_timestamp;
-
-	data = max_tr.data[cpu];
-	data->saved_latency = tracing_max_latency;
-
-	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
-	data->pid = tsk->pid;
-	data->uid = task_uid(tsk);
-	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
-	data->policy = tsk->policy;
-	data->rt_priority = tsk->rt_priority;
-
-	/* record this tasks comm */
-	tracing_record_cmdline(tsk);
-}
-
 ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
 {
 	int len;
@@ -420,6 +378,53 @@ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt)
 	return cnt;
 }
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ *
+ * It is also used in other places outside the update_max_tr
+ * so it needs to be defined outside of the
+ * CONFIG_TRACER_MAX_TRACE.
+ */
+static raw_spinlock_t ftrace_max_lock =
+	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+
+#ifdef CONFIG_TRACER_MAX_TRACE
+unsigned long __read_mostly	tracing_max_latency;
+unsigned long __read_mostly	tracing_thresh;
+
+/*
+ * Copy the new maximum trace into the separate maximum-trace
+ * structure. (this way the maximum trace is permanently saved,
+ * for later retrieval via /sys/kernel/debug/tracing/latency_trace)
+ */
+static void
+__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
+{
+	struct trace_array_cpu *data = tr->data[cpu];
+
+	max_tr.cpu = cpu;
+	max_tr.time_start = data->preempt_timestamp;
+
+	data = max_tr.data[cpu];
+	data->saved_latency = tracing_max_latency;
+
+	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
+	data->pid = tsk->pid;
+	data->uid = task_uid(tsk);
+	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+	data->policy = tsk->policy;
+	data->rt_priority = tsk->rt_priority;
+
+	/* record this tasks comm */
+	tracing_record_cmdline(tsk);
+}
+
 /**
  * update_max_tr - snapshot all trace buffers from global_trace to max_tr
  * @tr: tracer
@@ -476,6 +481,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 /**
  * register_tracer - register a tracer with the ftrace system.
@@ -3952,11 +3958,13 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("current_tracer", 0644, d_tracer,
 			&global_trace, &set_tracer_fops);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 	trace_create_file("tracing_max_latency", 0644, d_tracer,
 			&tracing_max_latency, &tracing_max_lat_fops);
 
 	trace_create_file("tracing_thresh", 0644, d_tracer,
 			&tracing_thresh, &tracing_max_lat_fops);
+#endif
 
 	trace_create_file("README", 0444, d_tracer,
 			NULL, &tracing_readme_fops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 654fd657bd03..e2c06b21dd82 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -473,12 +473,14 @@ void unregister_tracer(struct tracer *type);
 
 extern unsigned long nsecs_to_usecs(unsigned long nsecs);
 
+#ifdef CONFIG_TRACER_MAX_TRACE
 extern unsigned long tracing_max_latency;
 extern unsigned long tracing_thresh;
 
 void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
 void update_max_tr_single(struct trace_array *tr,
 			  struct task_struct *tsk, int cpu);
+#endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef CONFIG_STACKTRACE
 void ftrace_trace_stack(struct trace_array *tr, unsigned long flags,
-- 
cgit v1.2.3


From 8248ac052dfd1eb41819fbc0ca5c7a1667e7e70c Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 2 Sep 2009 12:27:41 -0400
Subject: tracing: print out start and stop in latency traces

During development of the tracer, we would copy information from
the live tracer to the max tracer with one memcpy. Since then we
added a generic ring buffer and we handle the copies differently now.
Unfortunately, we never copied the critical section information, and
we lost the output:

 #  => started at: kmem_cache_alloc
 #  => ended at:   kmem_cache_alloc

This patch adds back the critical start and end copying as well as
removes the unused "trace_idx" and "overrun" fields of the
trace_array_cpu structure.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 19 +++++++++++--------
 kernel/trace/trace.h |  3 ---
 2 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0f0881676dc9..df2c9f730ac6 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -407,19 +407,22 @@ static void
 __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct trace_array_cpu *data = tr->data[cpu];
+	struct trace_array_cpu *max_data = tr->data[cpu];
 
 	max_tr.cpu = cpu;
 	max_tr.time_start = data->preempt_timestamp;
 
-	data = max_tr.data[cpu];
-	data->saved_latency = tracing_max_latency;
+	max_data = max_tr.data[cpu];
+	max_data->saved_latency = tracing_max_latency;
+	max_data->critical_start = data->critical_start;
+	max_data->critical_end = data->critical_end;
 
 	memcpy(data->comm, tsk->comm, TASK_COMM_LEN);
-	data->pid = tsk->pid;
-	data->uid = task_uid(tsk);
-	data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
-	data->policy = tsk->policy;
-	data->rt_priority = tsk->rt_priority;
+	max_data->pid = tsk->pid;
+	max_data->uid = task_uid(tsk);
+	max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO;
+	max_data->policy = tsk->policy;
+	max_data->rt_priority = tsk->rt_priority;
 
 	/* record this tasks comm */
 	tracing_record_cmdline(tsk);
@@ -1501,7 +1504,7 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 		seq_puts(m, "\n#  => ended at:   ");
 		seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags);
 		trace_print_seq(m, &iter->seq);
-		seq_puts(m, "#\n");
+		seq_puts(m, "\n#\n");
 	}
 
 	seq_puts(m, "#\n");
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index e2c06b21dd82..f2af713a8bcc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -234,9 +234,6 @@ struct trace_array_cpu {
 	atomic_t		disabled;
 	void			*buffer_page;	/* ring buffer spare */
 
-	/* these fields get copied into max-trace: */
-	unsigned long		trace_idx;
-	unsigned long		overrun;
 	unsigned long		saved_latency;
 	unsigned long		critical_start;
 	unsigned long		critical_end;
-- 
cgit v1.2.3


From b8de7bd168fa54d059b16d3057b2f8a32cc5bdc3 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Mon, 31 Aug 2009 22:32:27 -0400
Subject: tracing: disable update max tracer while reading trace

When reading the tracer from the trace file, updating the max latency
may corrupt the output. This patch disables the tracing of the max
latency while reading the trace file.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index df2c9f730ac6..e521f1e8f2bb 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -263,6 +263,9 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME |
 	TRACE_ITER_GRAPH_TIME;
 
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
@@ -442,6 +445,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	struct ring_buffer *buf = tr->buffer;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
@@ -469,6 +475,9 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {
 	int ret;
 
+	if (trace_stop_count)
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
@@ -685,9 +694,6 @@ static void trace_init_cmdlines(void)
 	cmdline_idx = 0;
 }
 
-static int trace_stop_count;
-static DEFINE_SPINLOCK(tracing_start_lock);
-
 /**
  * ftrace_off_permanent - disable all ftrace code permanently
  *
-- 
cgit v1.2.3


From 621968cdb2563b667d6ecb484ba91ef4c3a797b3 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 4 Sep 2009 12:02:35 -0400
Subject: tracing: disable buffers and synchronize_sched before resetting

Resetting the ring buffers while traces are happening can corrupt
the ring buffer and disable it (no kernel crash to worry about).

The safest thing to do is disable the ring buffers, call synchronize_sched()
to wait for all current writers to finish and then reset the buffer.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e521f1e8f2bb..9110329ecf77 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -658,12 +658,20 @@ void tracing_reset(struct trace_array *tr, int cpu)
 
 void tracing_reset_online_cpus(struct trace_array *tr)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	int cpu;
 
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
 		tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
 }
 
 void tracing_reset_current(int cpu)
-- 
cgit v1.2.3


From 76f0d07376388f32698ba51b6090a26b90c1342f Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 4 Sep 2009 12:12:39 -0400
Subject: tracing: remove users of tracing_reset

The function tracing_reset is deprecated for outside use of trace.c.

The new function to reset the the buffers is tracing_reset_online_cpus.

The reason for this is that resetting the buffers while the event
trace points are active can corrupt the buffers, because they may
be writing at the time of reset. The tracing_reset_online_cpus disables
writes and waits for current writers to finish.

This patch replaces all users of tracing_reset except for the latency
tracers. Those changes require more work and will be removed in the
following patches.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/kmemtrace.c   | 4 +---
 kernel/trace/trace.c       | 7 ++-----
 kernel/trace/trace_boot.c  | 4 +---
 kernel/trace/trace_power.c | 4 +---
 4 files changed, 5 insertions(+), 14 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
index dda53ccf749b..81b1645c8549 100644
--- a/kernel/trace/kmemtrace.c
+++ b/kernel/trace/kmemtrace.c
@@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void)
 
 static int kmem_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	kmemtrace_start_probes();
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 9110329ecf77..54517a889791 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -550,7 +550,6 @@ __acquires(kernel_lock)
 	if (type->selftest && !tracing_selftest_disabled) {
 		struct tracer *saved_tracer = current_trace;
 		struct trace_array *tr = &global_trace;
-		int i;
 
 		/*
 		 * Run a selftest on this tracer.
@@ -559,8 +558,7 @@ __acquires(kernel_lock)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		current_trace = type;
 		/* the test is responsible for initializing and enabling */
@@ -573,8 +571,7 @@ __acquires(kernel_lock)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_tracing_cpu(i)
-			tracing_reset(tr, i);
+		tracing_reset_online_cpus(tr);
 
 		printk(KERN_CONT "PASSED\n");
 	}
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index a29ef23ffb47..863139327816 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -41,14 +41,12 @@ void disable_boot_trace(void)
 
 static int boot_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	boot_trace = tr;
 
 	if (!tr)
 		return 0;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	tracing_sched_switch_assign_trace(tr);
 	return 0;
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index 8a30d9874cd4..a5d5a4f7745b 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -144,14 +144,12 @@ static void power_trace_reset(struct trace_array *tr)
 
 static int power_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	power_trace = tr;
 
 	trace_power_enabled = 1;
 	tracing_power_register();
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2f26ebd549b9ab55ac756b836ec759c11fe93f81 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Tue, 1 Sep 2009 11:06:29 -0400
Subject: tracing: use timestamp to determine start of latency traces

Currently the latency tracers reset the ring buffer. Unfortunately
if a commit is in process (due to a trace event), this can corrupt
the ring buffer. When this happens, the ring buffer will detect
the corruption and then permanently disable the ring buffer.

The bug does not crash the system, but it does prevent further tracing
after the bug is hit.

Instead of reseting the trace buffers, the timestamp of the start of
the trace is used instead. The buffers will still contain the previous
data, but the output will not count any data that is before the
timestamp of the trace.

Note, this only affects the static trace output (trace) and not the
runtime trace output (trace_pipe). The runtime trace output does not
make sense for the latency tracers anyway.

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c              | 80 ++++++++++++++++++++++++++++++---------
 kernel/trace/trace.h              |  1 +
 kernel/trace/trace_irqsoff.c      |  3 +-
 kernel/trace/trace_sched_wakeup.c |  7 +---
 4 files changed, 67 insertions(+), 24 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 54517a889791..7daf372e319a 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -454,10 +454,6 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
-	ftrace_disable_cpu();
-	ring_buffer_reset(tr->buffer);
-	ftrace_enable_cpu();
-
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
 }
@@ -483,7 +479,6 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	ftrace_disable_cpu();
 
-	ring_buffer_reset(max_tr.buffer);
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
 	ftrace_enable_cpu();
@@ -1374,6 +1369,37 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
 	return ent;
 }
 
+static void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+{
+	struct trace_array *tr = iter->tr;
+	struct ring_buffer_event *event;
+	struct ring_buffer_iter *buf_iter;
+	unsigned long entries = 0;
+	u64 ts;
+
+	tr->data[cpu]->skipped_entries = 0;
+
+	if (!iter->buffer_iter[cpu])
+		return;
+
+	buf_iter = iter->buffer_iter[cpu];
+	ring_buffer_iter_reset(buf_iter);
+
+	/*
+	 * We could have the case with the max latency tracers
+	 * that a reset never took place on a cpu. This is evident
+	 * by the timestamp being before the start of the buffer.
+	 */
+	while ((event = ring_buffer_iter_peek(buf_iter, &ts))) {
+		if (ts >= iter->tr->time_start)
+			break;
+		entries++;
+		ring_buffer_read(buf_iter, NULL);
+	}
+
+	tr->data[cpu]->skipped_entries = entries;
+}
+
 /*
  * No necessary locking here. The worst thing which can
  * happen is loosing events consumed at the same time
@@ -1412,10 +1438,9 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 		if (cpu_file == TRACE_PIPE_ALL_CPU) {
 			for_each_tracing_cpu(cpu)
-				ring_buffer_iter_reset(iter->buffer_iter[cpu]);
+				tracing_iter_reset(iter, cpu);
 		} else
-			ring_buffer_iter_reset(iter->buffer_iter[cpu_file]);
-
+			tracing_iter_reset(iter, cpu_file);
 
 		ftrace_enable_cpu();
 
@@ -1464,16 +1489,32 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter)
 	struct trace_array *tr = iter->tr;
 	struct trace_array_cpu *data = tr->data[tr->cpu];
 	struct tracer *type = current_trace;
-	unsigned long total;
-	unsigned long entries;
+	unsigned long entries = 0;
+	unsigned long total = 0;
+	unsigned long count;
 	const char *name = "preemption";
+	int cpu;
 
 	if (type)
 		name = type->name;
 
-	entries = ring_buffer_entries(iter->tr->buffer);
-	total = entries +
-		ring_buffer_overruns(iter->tr->buffer);
+
+	for_each_tracing_cpu(cpu) {
+		count = ring_buffer_entries_cpu(tr->buffer, cpu);
+		/*
+		 * If this buffer has skipped entries, then we hold all
+		 * entries for the trace and we need to ignore the
+		 * ones before the time stamp.
+		 */
+		if (tr->data[cpu]->skipped_entries) {
+			count -= tr->data[cpu]->skipped_entries;
+			/* total is the same as the entries */
+			total += count;
+		} else
+			total += count +
+				ring_buffer_overrun_cpu(tr->buffer, cpu);
+		entries += count;
+	}
 
 	seq_printf(m, "# %s latency trace v1.1.5 on %s\n",
 		   name, UTS_RELEASE);
@@ -1534,6 +1575,9 @@ static void test_cpu_buff_start(struct trace_iterator *iter)
 	if (cpumask_test_cpu(iter->cpu, iter->started))
 		return;
 
+	if (iter->tr->data[iter->cpu]->skipped_entries)
+		return;
+
 	cpumask_set_cpu(iter->cpu, iter->started);
 
 	/* Don't print started cpu buffer for the first entry of the trace */
@@ -1796,19 +1840,23 @@ __tracing_open(struct inode *inode, struct file *file)
 	if (ring_buffer_overruns(iter->tr->buffer))
 		iter->iter_flags |= TRACE_FILE_ANNOTATE;
 
+	/* stop the trace while dumping */
+	tracing_stop();
+
 	if (iter->cpu_file == TRACE_PIPE_ALL_CPU) {
 		for_each_tracing_cpu(cpu) {
 
 			iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
 				ring_buffer_read_start(iter->tr->buffer, cpu);
+		tracing_iter_reset(iter, cpu);
 	}
 
-	/* TODO stop tracer */
 	ret = seq_open(file, &tracer_seq_ops);
 	if (ret < 0) {
 		fail_ret = ERR_PTR(ret);
@@ -1818,9 +1866,6 @@ __tracing_open(struct inode *inode, struct file *file)
 	m = file->private_data;
 	m->private = iter;
 
-	/* stop the trace while dumping */
-	tracing_stop();
-
 	mutex_unlock(&trace_types_lock);
 
 	return iter;
@@ -1831,6 +1876,7 @@ __tracing_open(struct inode *inode, struct file *file)
 			ring_buffer_read_finish(iter->buffer_iter[cpu]);
 	}
 	free_cpumask_var(iter->started);
+	tracing_start();
  fail:
 	mutex_unlock(&trace_types_lock);
 	kfree(iter->trace);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f2af713a8bcc..ca070de36227 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -241,6 +241,7 @@ struct trace_array_cpu {
 	unsigned long		nice;
 	unsigned long		policy;
 	unsigned long		rt_priority;
+	unsigned long		skipped_entries;
 	cycle_t			preempt_timestamp;
 	pid_t			pid;
 	uid_t			uid;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index b923d13e2fad..5555b75a0d12 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -178,7 +178,6 @@ out_unlock:
 out:
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
-	tracing_reset(tr, cpu);
 	trace_function(tr, CALLER_ADDR0, parent_ip, flags, pc);
 }
 
@@ -208,7 +207,6 @@ start_critical_timing(unsigned long ip, unsigned long parent_ip)
 	data->critical_sequence = max_sequence;
 	data->preempt_timestamp = ftrace_now(cpu);
 	data->critical_start = parent_ip ? : ip;
-	tracing_reset(tr, cpu);
 
 	local_save_flags(flags);
 
@@ -379,6 +377,7 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
+	tracing_reset_online_cpus(tr);
 	start_irqsoff_tracer(tr);
 }
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index eacb27225173..ad69f105a7c6 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -186,11 +186,6 @@ out:
 
 static void __wakeup_reset(struct trace_array *tr)
 {
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		tracing_reset(tr, cpu);
-
 	wakeup_cpu = -1;
 	wakeup_prio = -1;
 
@@ -204,6 +199,8 @@ static void wakeup_reset(struct trace_array *tr)
 {
 	unsigned long flags;
 
+	tracing_reset_online_cpus(tr);
+
 	local_irq_save(flags);
 	__raw_spin_lock(&wakeup_lock);
 	__wakeup_reset(tr);
-- 
cgit v1.2.3


From f633903af2ceb0cec07d45e499a072b6593d0ed1 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Fri, 4 Sep 2009 12:35:16 -0400
Subject: tracing: make tracing_reset safe for external use

Reseting the trace buffer without first disabling the buffer and
waiting for any writers to complete, can corrupt the ring buffer.

This patch makes the external version of tracing_reset safe from
corruption by disabling the ring buffer and calling synchronize_sched.

This version can no longer be called from interrupt context. But all those
callers have been removed.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 7daf372e319a..0418e2650d41 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -641,13 +641,26 @@ void unregister_tracer(struct tracer *type)
 	mutex_unlock(&trace_types_lock);
 }
 
-void tracing_reset(struct trace_array *tr, int cpu)
+static void __tracing_reset(struct trace_array *tr, int cpu)
 {
 	ftrace_disable_cpu();
 	ring_buffer_reset_cpu(tr->buffer, cpu);
 	ftrace_enable_cpu();
 }
 
+void tracing_reset(struct trace_array *tr, int cpu)
+{
+	struct ring_buffer *buffer = tr->buffer;
+
+	ring_buffer_record_disable(buffer);
+
+	/* Make sure all commits have finished */
+	synchronize_sched();
+	__tracing_reset(tr, cpu);
+
+	ring_buffer_record_enable(buffer);
+}
+
 void tracing_reset_online_cpus(struct trace_array *tr)
 {
 	struct ring_buffer *buffer = tr->buffer;
@@ -661,7 +674,7 @@ void tracing_reset_online_cpus(struct trace_array *tr)
 	tr->time_start = ftrace_now(tr->cpu);
 
 	for_each_online_cpu(cpu)
-		tracing_reset(tr, cpu);
+		__tracing_reset(tr, cpu);
 
 	ring_buffer_record_enable(buffer);
 }
-- 
cgit v1.2.3


From e77405ad80f53966524b5c31244e13fbbbecbd84 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Wed, 2 Sep 2009 14:17:06 -0400
Subject: tracing: pass around ring buffer instead of tracer

The latency tracers (irqsoff and wakeup) can swap trace buffers
on the fly. If an event is happening and has reserved data on one of
the buffers, and the latency tracer swaps the global buffer with the
max buffer, the result is that the event may commit the data to the
wrong buffer.

This patch changes the API to the trace recording to be recieve the
buffer that was used to reserve a commit. Then this buffer can be passed
in to the commit.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 include/linux/ftrace_event.h         |  15 +++--
 include/trace/ftrace.h               |  15 +++--
 kernel/trace/blktrace.c              |  12 ++--
 kernel/trace/trace.c                 | 117 ++++++++++++++++++++---------------
 kernel/trace/trace.h                 |  17 ++---
 kernel/trace/trace_boot.c            |  12 ++--
 kernel/trace/trace_events.c          |   6 +-
 kernel/trace/trace_functions_graph.c |  14 +++--
 kernel/trace/trace_mmiotrace.c       |  10 +--
 kernel/trace/trace_power.c           |  18 ++++--
 kernel/trace/trace_sched_switch.c    |  18 +++---
 kernel/trace/trace_syscalls.c        |  18 +++---
 12 files changed, 163 insertions(+), 109 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 755480484eb6..23f7179bf74e 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -93,13 +93,17 @@ void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event);
 
 void tracing_record_cmdline(struct task_struct *tsk);
 
@@ -135,7 +139,8 @@ struct ftrace_event_call {
 
 extern void destroy_preds(struct ftrace_event_call *call);
 extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern int filter_current_check_discard(struct ftrace_event_call *call,
+extern int filter_current_check_discard(struct ring_buffer *buffer,
+					struct ftrace_event_call *call,
 					void *rec,
 					struct ring_buffer_event *event);
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index bfbc842600a1..308bafd93325 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -460,13 +460,15 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
  * {
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
- *	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *	event = trace_current_buffer_lock_reserve(&buffer,
+ *				  event_<call>.id,
  *				  sizeof(struct ftrace_raw_<call>),
  *				  irq_flags, pc);
  *	if (!event)
@@ -476,7 +478,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
  *	<assign>;  <-- Here we assign the entries by the __field and
  *			__array macros.
  *
- *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(void)
@@ -568,6 +570,7 @@ static void ftrace_raw_event_##call(proto)				\
 	struct ftrace_event_call *event_call = &event_##call;		\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
+	struct ring_buffer *buffer;					\
 	unsigned long irq_flags;					\
 	int __data_size;						\
 	int pc;								\
@@ -577,7 +580,8 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+	event = trace_current_buffer_lock_reserve(&buffer,		\
+				 event_##call.id,			\
 				 sizeof(*entry) + __data_size,		\
 				 irq_flags, pc);			\
 	if (!event)							\
@@ -589,8 +593,9 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	{ assign; }							\
 									\
-	if (!filter_current_check_discard(event_call, entry, event))	\
-		trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+		trace_nowake_buffer_unlock_commit(buffer,		\
+						  event, irq_flags, pc); \
 }									\
 									\
 static int ftrace_raw_reg_event_##call(void *ptr)			\
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 1090b0aed9ba..243bafc2ec90 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -65,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
 						  0, pc);
 		if (!event)
@@ -96,7 +98,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 	}
 }
 
@@ -179,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
@@ -204,8 +207,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
 						  0, pc);
 		if (!event)
@@ -252,7 +256,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 			return;
 		}
 	}
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0418e2650d41..0c61836e30e7 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -169,10 +169,11 @@ static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
-int filter_current_check_discard(struct ftrace_event_call *call, void *rec,
+int filter_current_check_discard(struct ring_buffer *buffer,
+				 struct ftrace_event_call *call, void *rec,
 				 struct ring_buffer_event *event)
 {
-	return filter_check_discard(call, rec, global_trace.buffer, event);
+	return filter_check_discard(call, rec, buffer, event);
 }
 EXPORT_SYMBOL_GPL(filter_current_check_discard);
 
@@ -887,14 +888,15 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags, int pc)
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags, int pc)
 {
 	struct ring_buffer_event *event;
 
-	event = ring_buffer_lock_reserve(tr->buffer, len);
+	event = ring_buffer_lock_reserve(buffer, len);
 	if (event != NULL) {
 		struct trace_entry *ent = ring_buffer_event_data(event);
 
@@ -905,53 +907,59 @@ struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
 	return event;
 }
 
-static inline void __trace_buffer_unlock_commit(struct trace_array *tr,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc,
-					int wake)
+static inline void
+__trace_buffer_unlock_commit(struct ring_buffer *buffer,
+			     struct ring_buffer_event *event,
+			     unsigned long flags, int pc,
+			     int wake)
 {
-	ring_buffer_unlock_commit(tr->buffer, event);
+	ring_buffer_unlock_commit(buffer, event);
 
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
+	ftrace_trace_stack(buffer, flags, 6, pc);
+	ftrace_trace_userstack(buffer, flags, pc);
 
 	if (wake)
 		trace_wake_up();
 }
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-					struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event,
+				unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(tr, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc)
 {
-	return trace_buffer_lock_reserve(&global_trace,
+	*current_rb = global_trace.buffer;
+	return trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
 
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 1);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 1);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_unlock_commit);
 
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
-					unsigned long flags, int pc)
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
+				       unsigned long flags, int pc)
 {
-	__trace_buffer_unlock_commit(&global_trace, event, flags, pc, 0);
+	__trace_buffer_unlock_commit(buffer, event, flags, pc, 0);
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event)
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event)
 {
-	ring_buffer_discard_commit(global_trace.buffer, event);
+	ring_buffer_discard_commit(buffer, event);
 }
 EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
@@ -961,6 +969,7 @@ trace_function(struct trace_array *tr,
 	       int pc)
 {
 	struct ftrace_event_call *call = &event_function;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct ftrace_entry *entry;
 
@@ -968,7 +977,7 @@ trace_function(struct trace_array *tr,
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_FN, sizeof(*entry),
+	event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
 					  flags, pc);
 	if (!event)
 		return;
@@ -976,8 +985,8 @@ trace_function(struct trace_array *tr,
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
 void
@@ -990,7 +999,7 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
-static void __ftrace_trace_stack(struct trace_array *tr,
+static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
 				 int skip, int pc)
 {
@@ -999,7 +1008,7 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	struct stack_entry *entry;
 	struct stack_trace trace;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -1012,26 +1021,27 @@ static void __ftrace_trace_stack(struct trace_array *tr,
 	trace.entries		= entry->caller;
 
 	save_stack_trace(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
-void ftrace_trace_stack(struct trace_array *tr, unsigned long flags, int skip,
-			int pc)
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
+			int skip, int pc)
 {
 	if (!(trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(buffer, flags, skip, pc);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc)
 {
-	__ftrace_trace_stack(tr, flags, skip, pc);
+	__ftrace_trace_stack(tr->buffer, flags, skip, pc);
 }
 
-void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags, int pc)
+void
+ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
 	struct ftrace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
@@ -1041,7 +1051,7 @@ void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags, int pc)
 	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_USER_STACK,
+	event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -1055,8 +1065,8 @@ void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags, int pc)
 	trace.entries		= entry->caller;
 
 	save_stack_trace_user(&trace);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
 #ifdef UNUSED
@@ -1075,9 +1085,10 @@ ftrace_trace_special(void *__tr,
 {
 	struct ring_buffer_event *event;
 	struct trace_array *tr = __tr;
+	struct ring_buffer *buffer = tr->buffer;
 	struct special_entry *entry;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_SPECIAL,
+	event = trace_buffer_lock_reserve(buffer, TRACE_SPECIAL,
 					  sizeof(*entry), 0, pc);
 	if (!event)
 		return;
@@ -1085,7 +1096,7 @@ ftrace_trace_special(void *__tr,
 	entry->arg1			= arg1;
 	entry->arg2			= arg2;
 	entry->arg3			= arg3;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void
@@ -1131,6 +1142,7 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	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;
@@ -1163,7 +1175,9 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 		goto out_unlock;
 
 	size = sizeof(*entry) + sizeof(u32) * len;
-	event = trace_buffer_lock_reserve(tr, TRACE_BPRINT, size, flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+					  flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1171,8 +1185,8 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 	entry->fmt			= fmt;
 
 	memcpy(entry->buf, trace_buf, sizeof(u32) * len);
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
 out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
@@ -1194,6 +1208,7 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
@@ -1222,7 +1237,9 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	trace_buf[len] = 0;
 
 	size = sizeof(*entry) + len + 1;
-	event = trace_buffer_lock_reserve(tr, TRACE_PRINT, size, irq_flags, pc);
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					  irq_flags, pc);
 	if (!event)
 		goto out_unlock;
 	entry = ring_buffer_event_data(event);
@@ -1230,8 +1247,8 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	memcpy(&entry->buf, trace_buf, len);
 	entry->buf[len] = 0;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
 
  out_unlock:
 	__raw_spin_unlock(&trace_buf_lock);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index ca070de36227..4d30414fe19a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -415,12 +415,13 @@ void init_tracer_sysprof_debugfs(struct dentry *d_tracer);
 
 struct ring_buffer_event;
 
-struct ring_buffer_event *trace_buffer_lock_reserve(struct trace_array *tr,
-						    int type,
-						    unsigned long len,
-						    unsigned long flags,
-						    int pc);
-void trace_buffer_unlock_commit(struct trace_array *tr,
+struct ring_buffer_event *
+trace_buffer_lock_reserve(struct ring_buffer *buffer,
+			  int type,
+			  unsigned long len,
+			  unsigned long flags,
+			  int pc);
+void trace_buffer_unlock_commit(struct ring_buffer *buffer,
 				struct ring_buffer_event *event,
 				unsigned long flags, int pc);
 
@@ -481,10 +482,10 @@ void update_max_tr_single(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef CONFIG_STACKTRACE
-void ftrace_trace_stack(struct trace_array *tr, unsigned long flags,
+void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
 			int skip, int pc);
 
-void ftrace_trace_userstack(struct trace_array *tr, unsigned long flags,
+void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
 			    int pc);
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 863139327816..19bfc75d467e 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -130,6 +130,7 @@ struct tracer boot_tracer __read_mostly =
 void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_call *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -142,13 +143,14 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_CALL,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_CALL,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_call = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -156,6 +158,7 @@ void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_boot_ret *entry;
 	struct trace_array *tr = boot_trace;
 
@@ -165,13 +168,14 @@ void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
 	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_BOOT_RET,
+	buffer = tr->buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_BOOT_RET,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->boot_ret = *bt;
-	trace_buffer_unlock_commit(tr, event, 0, 0);
+	trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d33bcdeffe69..78b1ed230177 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1438,6 +1438,7 @@ static void
 function_test_events_call(unsigned long ip, unsigned long parent_ip)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct ftrace_entry *entry;
 	unsigned long flags;
 	long disabled;
@@ -1455,7 +1456,8 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 
 	local_save_flags(flags);
 
-	event = trace_current_buffer_lock_reserve(TRACE_FN, sizeof(*entry),
+	event = trace_current_buffer_lock_reserve(&buffer,
+						  TRACE_FN, sizeof(*entry),
 						  flags, pc);
 	if (!event)
 		goto out;
@@ -1463,7 +1465,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip)
 	entry->ip			= ip;
 	entry->parent_ip		= parent_ip;
 
-	trace_nowake_buffer_unlock_commit(event, flags, pc);
+	trace_nowake_buffer_unlock_commit(buffer, event, flags, pc);
 
  out:
 	atomic_dec(&per_cpu(test_event_disable, cpu));
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 3f4a251b7d16..b3749a2c3132 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -173,19 +173,20 @@ static int __trace_graph_entry(struct trace_array *tr,
 {
 	struct ftrace_event_call *call = &event_funcgraph_entry;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ent_entry *entry;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
 		return 0;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_GRAPH_ENT,
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return 0;
 	entry	= ring_buffer_event_data(event);
 	entry->graph_ent			= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
 
 	return 1;
 }
@@ -236,19 +237,20 @@ static void __trace_graph_return(struct trace_array *tr,
 {
 	struct ftrace_event_call *call = &event_funcgraph_exit;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ftrace_graph_ret_entry *entry;
 
 	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
 		return;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_GRAPH_RET,
+	event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
-	if (!filter_current_check_discard(call, entry, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
+	if (!filter_current_check_discard(buffer, call, entry, event))
+		ring_buffer_unlock_commit(buffer, event);
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace)
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index d53b45ed0806..c4c9bbda53d3 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -307,11 +307,12 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_rw *rw)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_rw *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_RW,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_RW,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -319,7 +320,7 @@ static void __trace_mmiotrace_rw(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->rw			= *rw;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_rw(struct mmiotrace_rw *rw)
@@ -333,11 +334,12 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 				struct trace_array_cpu *data,
 				struct mmiotrace_map *map)
 {
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct trace_mmiotrace_map *entry;
 	int pc = preempt_count();
 
-	event = trace_buffer_lock_reserve(tr, TRACE_MMIO_MAP,
+	event = trace_buffer_lock_reserve(buffer, TRACE_MMIO_MAP,
 					  sizeof(*entry), 0, pc);
 	if (!event) {
 		atomic_inc(&dropped_count);
@@ -345,7 +347,7 @@ static void __trace_mmiotrace_map(struct trace_array *tr,
 	}
 	entry	= ring_buffer_event_data(event);
 	entry->map			= *map;
-	trace_buffer_unlock_commit(tr, event, 0, pc);
+	trace_buffer_unlock_commit(buffer, event, 0, pc);
 }
 
 void mmio_trace_mapping(struct mmiotrace_map *map)
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
index a5d5a4f7745b..fe1a00f1445a 100644
--- a/kernel/trace/trace_power.c
+++ b/kernel/trace/trace_power.c
@@ -38,6 +38,7 @@ static void probe_power_end(struct power_trace *it)
 {
 	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
 	struct trace_array *tr = power_trace;
@@ -45,18 +46,20 @@ static void probe_power_end(struct power_trace *it)
 	if (!trace_power_enabled)
 		return;
 
+	buffer = tr->buffer;
+
 	preempt_disable();
 	it->end = ktime_get();
 	data = tr->data[smp_processor_id()];
 
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
+	event = trace_buffer_lock_reserve(buffer, TRACE_POWER,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
@@ -66,6 +69,7 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 {
 	struct ftrace_event_call *call = &event_power;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	struct trace_power *entry;
 	struct trace_array_cpu *data;
 	struct trace_array *tr = power_trace;
@@ -73,6 +77,8 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 	if (!trace_power_enabled)
 		return;
 
+	buffer = tr->buffer;
+
 	memset(it, 0, sizeof(struct power_trace));
 	it->state = level;
 	it->type = type;
@@ -81,14 +87,14 @@ static void probe_power_mark(struct power_trace *it, unsigned int type,
 	it->end = it->stamp;
 	data = tr->data[smp_processor_id()];
 
-	event = trace_buffer_lock_reserve(tr, TRACE_POWER,
+	event = trace_buffer_lock_reserve(buffer, TRACE_POWER,
 					  sizeof(*entry), 0, 0);
 	if (!event)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	entry->state_data = *it;
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, 0, 0);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, 0, 0);
  out:
 	preempt_enable();
 }
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index e1285d7b5488..5fca0f51fde4 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -28,10 +28,11 @@ tracing_sched_switch_trace(struct trace_array *tr,
 			   unsigned long flags, int pc)
 {
 	struct ftrace_event_call *call = &event_context_switch;
+	struct ring_buffer *buffer = tr->buffer;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_CTX,
+	event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -44,8 +45,8 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_state		= next->state;
 	entry->next_cpu	= task_cpu(next);
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		trace_buffer_unlock_commit(tr, event, flags, pc);
+	if (!filter_check_discard(call, entry, buffer, event))
+		trace_buffer_unlock_commit(buffer, event, flags, pc);
 }
 
 static void
@@ -86,8 +87,9 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	struct ftrace_event_call *call = &event_wakeup;
 	struct ring_buffer_event *event;
 	struct ctx_switch_entry *entry;
+	struct ring_buffer *buffer = tr->buffer;
 
-	event = trace_buffer_lock_reserve(tr, TRACE_WAKE,
+	event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
 					  sizeof(*entry), flags, pc);
 	if (!event)
 		return;
@@ -100,10 +102,10 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_state		= wakee->state;
 	entry->next_cpu			= task_cpu(wakee);
 
-	if (!filter_check_discard(call, entry, tr->buffer, event))
-		ring_buffer_unlock_commit(tr->buffer, event);
-	ftrace_trace_stack(tr, flags, 6, pc);
-	ftrace_trace_userstack(tr, flags, pc);
+	if (!filter_check_discard(call, entry, buffer, event))
+		ring_buffer_unlock_commit(buffer, event);
+	ftrace_trace_stack(tr->buffer, flags, 6, pc);
+	ftrace_trace_userstack(tr->buffer, flags, pc);
 }
 
 static void
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 4f5fae6fad90..8712ce3c6a0e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -223,6 +223,7 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int size;
 	int syscall_nr;
 
@@ -238,8 +239,8 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	event = trace_current_buffer_lock_reserve(sys_data->enter_id, size,
-							0, 0);
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->enter_id,
+						  size, 0, 0);
 	if (!event)
 		return;
 
@@ -247,8 +248,9 @@ void ftrace_syscall_enter(struct pt_regs *regs, long id)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	if (!filter_current_check_discard(sys_data->enter_event, entry, event))
-		trace_current_buffer_unlock_commit(event, 0, 0);
+	if (!filter_current_check_discard(buffer, sys_data->enter_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
 void ftrace_syscall_exit(struct pt_regs *regs, long ret)
@@ -256,6 +258,7 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
 	int syscall_nr;
 
 	syscall_nr = syscall_get_nr(current, regs);
@@ -268,7 +271,7 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
-	event = trace_current_buffer_lock_reserve(sys_data->exit_id,
+	event = trace_current_buffer_lock_reserve(&buffer, sys_data->exit_id,
 				sizeof(*entry), 0, 0);
 	if (!event)
 		return;
@@ -277,8 +280,9 @@ void ftrace_syscall_exit(struct pt_regs *regs, long ret)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	if (!filter_current_check_discard(sys_data->exit_event, entry, event))
-		trace_current_buffer_unlock_commit(event, 0, 0);
+	if (!filter_current_check_discard(buffer, sys_data->exit_event,
+					  entry, event))
+		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
 }
 
 int reg_event_syscall_enter(void *ptr)
-- 
cgit v1.2.3


From 659372d3e42a3e17a2e042d38a8bcdb94bfbe797 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 3 Sep 2009 19:11:07 -0400
Subject: tracing: add trace_array_printk for internal tracers to use

This patch adds a trace_array_printk to allow a tracer to use the
trace_printk on its own trace array.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 24 ++++++++++++++++++++++--
 kernel/trace/trace.h |  5 +++++
 2 files changed, 27 insertions(+), 2 deletions(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0c61836e30e7..ef08328eb28d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1201,7 +1201,23 @@ out:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
-int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...)
+{
+	int ret;
+	va_list ap;
+
+	if (!(trace_flags & TRACE_ITER_PRINTK))
+		return 0;
+
+	va_start(ap, fmt);
+	ret = trace_array_vprintk(tr, ip, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+
+int trace_array_vprintk(struct trace_array *tr,
+			unsigned long ip, const char *fmt, va_list args)
 {
 	static raw_spinlock_t trace_buf_lock = __RAW_SPIN_LOCK_UNLOCKED;
 	static char trace_buf[TRACE_BUF_SIZE];
@@ -1209,7 +1225,6 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	struct ftrace_event_call *call = &event_print;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
-	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
 	int cpu, len = 0, size, pc;
 	struct print_entry *entry;
@@ -1260,6 +1275,11 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 
 	return len;
 }
+
+int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
+{
+	return trace_array_printk(&global_trace, ip, fmt, args);
+}
 EXPORT_SYMBOL_GPL(trace_vprintk);
 
 enum trace_file_type {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 4d30414fe19a..fa1dccb579d5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -566,6 +566,11 @@ extern int
 trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
 extern int
 trace_vprintk(unsigned long ip, const char *fmt, va_list args);
+extern int
+trace_array_vprintk(struct trace_array *tr,
+		    unsigned long ip, const char *fmt, va_list args);
+int trace_array_printk(struct trace_array *tr,
+		       unsigned long ip, const char *fmt, ...);
 
 extern unsigned long trace_flags;
 
-- 
cgit v1.2.3


From e8165dbb03ed04d798163ee512074b9a9466a9c8 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <srostedt@redhat.com>
Date: Thu, 3 Sep 2009 19:13:05 -0400
Subject: tracing: report error in trace if we fail to swap latency buffer

The irqsoff tracer will fail to swap the cpu buffer with the max
buffer if it preempts a commit. Instead of ignoring this, this patch
makes the tracer report it if the last max latency failed due to preempting
a current commit.

The output of the latency tracer will look like this:

 # tracer: irqsoff
 #
 # irqsoff latency trace v1.1.5 on 2.6.31-rc5
 # --------------------------------------------------------------------
 # latency: 112 us, #1/1, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
 #    -----------------
 #    | task: -4281 (uid:0 nice:0 policy:0 rt_prio:0)
 #    -----------------
 #  => started at: save_args
 #  => ended at:   __do_softirq
 #
 #
 #                  _------=> CPU#
 #                 / _-----=> irqs-off
 #                | / _----=> need-resched
 #                || / _---=> hardirq/softirq
 #                ||| / _--=> preempt-depth
 #                |||| /
 #                |||||     delay
 #  cmd     pid   ||||| time  |   caller
 #     \   /      |||||   \   |   /
    bash-4281    1d.s6  265us : update_max_tr_single: Failed to swap buffers due to commit in progress

Note the latency time and the functions that disabled the irqs or preemption
will still be listed.

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
 kernel/trace/trace.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'kernel/trace/trace.c')

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ef08328eb28d..6df9861fde6b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -482,9 +482,20 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
+	if (ret == -EBUSY) {
+		/*
+		 * We failed to swap the buffer due to a commit taking
+		 * place on this CPU. We fail to record, but we reset
+		 * the max trace buffer (no one writes directly to it)
+		 * and flag that it failed.
+		 */
+		trace_array_printk(&max_tr, _THIS_IP_,
+			"Failed to swap buffers due to commit in progress\n");
+	}
+
 	ftrace_enable_cpu();
 
-	WARN_ON_ONCE(ret && ret != -EAGAIN);
+	WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY);
 
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
-- 
cgit v1.2.3