26 files changed, 2873 insertions, 1204 deletions

diff --git a/kernel/relay.c b/kernel/relay.c
index 09ac2008f77..d06450670c8 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -675,9 +675,7 @@ int relay_late_setup_files(struct rchan *chan,
 	 */
 	for_each_online_cpu(i) {
 		if (unlikely(!chan->buf[i])) {
-			printk(KERN_ERR "relay_late_setup_files: CPU %u "
-					"has no buffer, it must have!\n", i);
-			BUG();
+			WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n");
 			err = -EINVAL;
 			break;
 		}
diff --git a/kernel/sched.c b/kernel/sched.c
index 52bbf1c842a..c154825ae75 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4399,10 +4399,7 @@ void scheduler_tick(void)
 #endif
 }
 
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
-
-static inline unsigned long get_parent_ip(unsigned long addr)
+unsigned long get_parent_ip(unsigned long addr)
 {
 	if (in_lock_functions(addr)) {
 		addr = CALLER_ADDR2;
@@ -4412,6 +4409,9 @@ static inline unsigned long get_parent_ip(unsigned long addr)
 	return addr;
 }
 
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+
 void __kprobes add_preempt_count(int val)
 {
 #ifdef CONFIG_DEBUG_PREEMPT
diff --git a/kernel/softirq.c b/kernel/softirq.c
index bdbe9de9cd8..6edfc2c11d9 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -21,6 +21,7 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/rcupdate.h>
+#include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
 
@@ -79,13 +80,23 @@ static void __local_bh_disable(unsigned long ip)
 	WARN_ON_ONCE(in_irq());
 
 	raw_local_irq_save(flags);
-	add_preempt_count(SOFTIRQ_OFFSET);
+	/*
+	 * The preempt tracer hooks into add_preempt_count and will break
+	 * lockdep because it calls back into lockdep after SOFTIRQ_OFFSET
+	 * is set and before current->softirq_enabled is cleared.
+	 * We must manually increment preempt_count here and manually
+	 * call the trace_preempt_off later.
+	 */
+	preempt_count() += SOFTIRQ_OFFSET;
 	/*
 	 * Were softirqs turned off above:
 	 */
 	if (softirq_count() == SOFTIRQ_OFFSET)
 		trace_softirqs_off(ip);
 	raw_local_irq_restore(flags);
+
+	if (preempt_count() == SOFTIRQ_OFFSET)
+		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
 }
 #else /* !CONFIG_TRACE_IRQFLAGS */
 static inline void __local_bh_disable(unsigned long ip)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e2a4ff6fc3a..dde1d46f77e 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -264,6 +264,38 @@ config HW_BRANCH_TRACER
 	  This tracer records all branches on the system in a circular
 	  buffer giving access to the last N branches for each cpu.
 
+config KMEMTRACE
+	bool "Trace SLAB allocations"
+	select TRACING
+	help
+	  kmemtrace provides tracing for slab allocator functions, such as
+	  kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected
+	  data is then fed to the userspace application in order to analyse
+	  allocation hotspots, internal fragmentation and so on, making it
+	  possible to see how well an allocator performs, as well as debug
+	  and profile kernel code.
+
+	  This requires an userspace application to use. See
+	  Documentation/vm/kmemtrace.txt for more information.
+
+	  Saying Y will make the kernel somewhat larger and slower. However,
+	  if you disable kmemtrace at run-time or boot-time, the performance
+	  impact is minimal (depending on the arch the kernel is built for).
+
+	  If unsure, say N.
+
+config WORKQUEUE_TRACER
+	bool "Trace workqueues"
+	select TRACING
+	help
+	  The workqueue tracer provides some statistical informations
+          about each cpu workqueue thread such as the number of the
+          works inserted and executed since their creation. It can help
+          to evaluate the amount of work each of them have to perform.
+          For example it can help a developer to decide whether he should
+          choose a per cpu workqueue instead of a singlethreaded one.
+
+
 config DYNAMIC_FTRACE
 	bool "enable/disable ftrace tracepoints dynamically"
 	depends on FUNCTION_TRACER
@@ -302,4 +334,27 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config MMIOTRACE
+	bool "Memory mapped IO tracing"
+	depends on HAVE_MMIOTRACE_SUPPORT && DEBUG_KERNEL && PCI
+	select TRACING
+	help
+	  Mmiotrace traces Memory Mapped I/O access and is meant for
+	  debugging and reverse engineering. It is called from the ioremap
+	  implementation and works via page faults. Tracing is disabled by
+	  default and can be enabled at run-time.
+
+	  See Documentation/tracers/mmiotrace.txt.
+	  If you are not helping to develop drivers, say N.
+
+config MMIOTRACE_TEST
+	tristate "Test module for mmiotrace"
+	depends on MMIOTRACE && m
+	help
+	  This is a dumb module for testing mmiotrace. It is very dangerous
+	  as it will write garbage to IO memory starting at a given address.
+	  However, it should be safe to use on e.g. unused portion of VRAM.
+
+	  Say N, unless you absolutely know what you are doing.
+
 endmenu
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 349d5a93653..f76d48f3527 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -19,6 +19,8 @@ obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
+obj-$(CONFIG_TRACING) += trace_output.o
+obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
@@ -33,5 +35,7 @@ obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
 obj-$(CONFIG_POWER_TRACER) += trace_power.o
+obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
+obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7dcf6e9f2b0..7e9a20b6993 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -264,14 +264,6 @@ static void ftrace_update_pid_func(void)
 # error Dynamic ftrace depends on MCOUNT_RECORD
 #endif
 
-/*
- * Since MCOUNT_ADDR may point to mcount itself, we do not want
- * to get it confused by reading a reference in the code as we
- * are parsing on objcopy output of text. Use a variable for
- * it instead.
- */
-static unsigned long mcount_addr = MCOUNT_ADDR;
-
 enum {
 	FTRACE_ENABLE_CALLS		= (1 << 0),
 	FTRACE_DISABLE_CALLS		= (1 << 1),
@@ -290,7 +282,7 @@ static DEFINE_MUTEX(ftrace_regex_lock);
 
 struct ftrace_page {
 	struct ftrace_page	*next;
-	unsigned long		index;
+	int			index;
 	struct dyn_ftrace	records[];
 };
 
@@ -464,7 +456,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 	unsigned long ip, fl;
 	unsigned long ftrace_addr;
 
-	ftrace_addr = (unsigned long)ftrace_caller;
+	ftrace_addr = (unsigned long)FTRACE_ADDR;
 
 	ip = rec->ip;
 
@@ -576,7 +568,7 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 
 	ip = rec->ip;
 
-	ret = ftrace_make_nop(mod, rec, mcount_addr);
+	ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
 	if (ret) {
 		ftrace_bug(ret, ip);
 		rec->flags |= FTRACE_FL_FAILED;
@@ -787,7 +779,7 @@ enum {
 
 struct ftrace_iterator {
 	struct ftrace_page	*pg;
-	unsigned		idx;
+	int			idx;
 	unsigned		flags;
 	unsigned char		buffer[FTRACE_BUFF_MAX+1];
 	unsigned		buffer_idx;
@@ -1903,7 +1895,7 @@ int register_ftrace_function(struct ftrace_ops *ops)
 }
 
 /**
- * unregister_ftrace_function - unresgister a function for profiling.
+ * unregister_ftrace_function - unregister a function for profiling.
  * @ops - ops structure that holds the function to unregister
  *
  * Unregister a function that was added to be called by ftrace profiling.
diff --git a/kernel/trace/kmemtrace.c b/kernel/trace/kmemtrace.c
new file mode 100644
index 00000000000..72b326bba00
--- /dev/null
+++ b/kernel/trace/kmemtrace.c
@@ -0,0 +1,350 @@
+/*
+ * Memory allocator tracing
+ *
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ * Copyright (C) 2008 Pekka Enberg <penberg@cs.helsinki.fi>
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ */
+
+#include <linux/dcache.h>
+#include <linux/debugfs.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <trace/kmemtrace.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+/* Select an alternative, minimalistic output than the original one */
+#define TRACE_KMEM_OPT_MINIMAL	0x1
+
+static struct tracer_opt kmem_opts[] = {
+	/* Default disable the minimalistic output */
+	{ TRACER_OPT(kmem_minimalistic, TRACE_KMEM_OPT_MINIMAL) },
+	{ }
+};
+
+static struct tracer_flags kmem_tracer_flags = {
+	.val = 0,
+	.opts = kmem_opts
+};
+
+
+static bool kmem_tracing_enabled __read_mostly;
+static struct trace_array *kmemtrace_array;
+
+static int kmem_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	kmemtrace_array = tr;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		tracing_reset(tr, cpu);
+
+	kmem_tracing_enabled = true;
+
+	return 0;
+}
+
+static void kmem_trace_reset(struct trace_array *tr)
+{
+	kmem_tracing_enabled = false;
+}
+
+static void kmemtrace_headers(struct seq_file *s)
+{
+	/* Don't need headers for the original kmemtrace output */
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return;
+
+	seq_printf(s, "#\n");
+	seq_printf(s, "# ALLOC  TYPE  REQ   GIVEN  FLAGS     "
+			"      POINTER         NODE    CALLER\n");
+	seq_printf(s, "# FREE   |      |     |       |       "
+			"       |   |            |        |\n");
+	seq_printf(s, "# |\n\n");
+}
+
+/*
+ * The two following functions give the original output from kmemtrace,
+ * or something close to....perhaps they need some missing things
+ */
+static enum print_line_t
+kmemtrace_print_alloc_original(struct trace_iterator *iter,
+				struct kmemtrace_alloc_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Taken from the old linux/kmemtrace.h */
+	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu "
+	  "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	   entry->type_id, entry->call_site, (unsigned long) entry->ptr,
+	   (unsigned long) entry->bytes_req, (unsigned long) entry->bytes_alloc,
+	   (unsigned long) entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_original(struct trace_iterator *iter,
+				struct kmemtrace_free_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Taken from the old linux/kmemtrace.h */
+	ret = trace_seq_printf(s, "type_id %d call_site %lu ptr %lu\n",
+	   entry->type_id, entry->call_site, (unsigned long) entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+
+/* The two other following provide a more minimalistic output */
+static enum print_line_t
+kmemtrace_print_alloc_compress(struct trace_iterator *iter,
+					struct kmemtrace_alloc_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Alloc entry */
+	ret = trace_seq_printf(s, "  +      ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Type */
+	switch (entry->type_id) {
+	case KMEMTRACE_TYPE_KMALLOC:
+		ret = trace_seq_printf(s, "K   ");
+		break;
+	case KMEMTRACE_TYPE_CACHE:
+		ret = trace_seq_printf(s, "C   ");
+		break;
+	case KMEMTRACE_TYPE_PAGES:
+		ret = trace_seq_printf(s, "P   ");
+		break;
+	default:
+		ret = trace_seq_printf(s, "?   ");
+	}
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Requested */
+	ret = trace_seq_printf(s, "%4zd   ", entry->bytes_req);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Allocated */
+	ret = trace_seq_printf(s, "%4zd   ", entry->bytes_alloc);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Flags
+	 * TODO: would be better to see the name of the GFP flag names
+	 */
+	ret = trace_seq_printf(s, "%08x   ", entry->gfp_flags);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Pointer to allocated */
+	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Node */
+	ret = trace_seq_printf(s, "%4d   ", entry->node);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Call site */
+	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_printf(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free_compress(struct trace_iterator *iter,
+				struct kmemtrace_free_entry *entry)
+{
+	struct trace_seq *s = &iter->seq;
+	int ret;
+
+	/* Free entry */
+	ret = trace_seq_printf(s, "  -      ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Type */
+	switch (entry->type_id) {
+	case KMEMTRACE_TYPE_KMALLOC:
+		ret = trace_seq_printf(s, "K     ");
+		break;
+	case KMEMTRACE_TYPE_CACHE:
+		ret = trace_seq_printf(s, "C     ");
+		break;
+	case KMEMTRACE_TYPE_PAGES:
+		ret = trace_seq_printf(s, "P     ");
+		break;
+	default:
+		ret = trace_seq_printf(s, "?     ");
+	}
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Skip requested/allocated/flags */
+	ret = trace_seq_printf(s, "                       ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Pointer to allocated */
+	ret = trace_seq_printf(s, "0x%tx   ", (ptrdiff_t)entry->ptr);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Skip node */
+	ret = trace_seq_printf(s, "       ");
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	/* Call site */
+	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	if (!trace_seq_printf(s, "\n"))
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC: {
+		struct kmemtrace_alloc_entry *field;
+		trace_assign_type(field, entry);
+		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
+			return kmemtrace_print_alloc_compress(iter, field);
+		else
+			return kmemtrace_print_alloc_original(iter, field);
+	}
+
+	case TRACE_KMEM_FREE: {
+		struct kmemtrace_free_entry *field;
+		trace_assign_type(field, entry);
+		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
+			return kmemtrace_print_free_compress(iter, field);
+		else
+			return kmemtrace_print_free_original(iter, field);
+	}
+
+	default:
+		return TRACE_TYPE_UNHANDLED;
+	}
+}
+
+/* Trace allocations */
+void kmemtrace_mark_alloc_node(enum kmemtrace_type_id type_id,
+			     unsigned long call_site,
+			     const void *ptr,
+			     size_t bytes_req,
+			     size_t bytes_alloc,
+			     gfp_t gfp_flags,
+			     int node)
+{
+	struct ring_buffer_event *event;
+	struct kmemtrace_alloc_entry *entry;
+	struct trace_array *tr = kmemtrace_array;
+	unsigned long irq_flags;
+
+	if (!kmem_tracing_enabled)
+		return;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type = TRACE_KMEM_ALLOC;
+	entry->call_site = call_site;
+	entry->ptr = ptr;
+	entry->bytes_req = bytes_req;
+	entry->bytes_alloc = bytes_alloc;
+	entry->gfp_flags = gfp_flags;
+	entry->node	=	node;
+
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+}
+EXPORT_SYMBOL(kmemtrace_mark_alloc_node);
+
+void kmemtrace_mark_free(enum kmemtrace_type_id type_id,
+		       unsigned long call_site,
+		       const void *ptr)
+{
+	struct ring_buffer_event *event;
+	struct kmemtrace_free_entry *entry;
+	struct trace_array *tr = kmemtrace_array;
+	unsigned long irq_flags;
+
+	if (!kmem_tracing_enabled)
+		return;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+
+	entry->ent.type = TRACE_KMEM_FREE;
+	entry->type_id	= type_id;
+	entry->call_site = call_site;
+	entry->ptr = ptr;
+
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+}
+EXPORT_SYMBOL(kmemtrace_mark_free);
+
+static struct tracer kmem_tracer __read_mostly = {
+	.name		= "kmemtrace",
+	.init		= kmem_trace_init,
+	.reset		= kmem_trace_reset,
+	.print_line	= kmemtrace_print_line,
+	.print_header = kmemtrace_headers,
+	.flags		= &kmem_tracer_flags
+};
+
+void kmemtrace_init(void)
+{
+	/* earliest opportunity to start kmem tracing */
+}
+
+static int __init init_kmem_tracer(void)
+{
+	return register_tracer(&kmem_tracer);
+}
+
+device_initcall(init_kmem_tracer);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index bd38c5cfd8a..b36d7374cee 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -123,8 +123,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
 EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);
 
 #define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
-#define RB_ALIGNMENT_SHIFT	2
-#define RB_ALIGNMENT		(1 << RB_ALIGNMENT_SHIFT)
+#define RB_ALIGNMENT		4U
 #define RB_MAX_SMALL_DATA	28
 
 enum {
@@ -133,7 +132,7 @@ enum {
 };
 
 /* inline for ring buffer fast paths */
-static inline unsigned
+static unsigned
 rb_event_length(struct ring_buffer_event *event)
 {
 	unsigned length;
@@ -151,7 +150,7 @@ rb_event_length(struct ring_buffer_event *event)
 
 	case RINGBUF_TYPE_DATA:
 		if (event->len)
-			length = event->len << RB_ALIGNMENT_SHIFT;
+			length = event->len * RB_ALIGNMENT;
 		else
 			length = event->array[0];
 		return length + RB_EVNT_HDR_SIZE;
@@ -179,7 +178,7 @@ unsigned ring_buffer_event_length(struct ring_buffer_event *event)
 EXPORT_SYMBOL_GPL(ring_buffer_event_length);
 
 /* inline for ring buffer fast paths */
-static inline void *
+static void *
 rb_event_data(struct ring_buffer_event *event)
 {
 	BUG_ON(event->type != RINGBUF_TYPE_DATA);
@@ -229,10 +228,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
  * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
  * this issue out.
  */
-static inline void free_buffer_page(struct buffer_page *bpage)
+static void free_buffer_page(struct buffer_page *bpage)
 {
-	if (bpage->page)
-		free_page((unsigned long)bpage->page);
+	free_page((unsigned long)bpage->page);
 	kfree(bpage);
 }
 
@@ -811,7 +809,7 @@ rb_event_index(struct ring_buffer_event *event)
 	return (addr & ~PAGE_MASK) - (PAGE_SIZE - BUF_PAGE_SIZE);
 }
 
-static inline int
+static int
 rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 	     struct ring_buffer_event *event)
 {
@@ -825,7 +823,7 @@ rb_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
 		rb_commit_index(cpu_buffer) == index;
 }
 
-static inline void
+static void
 rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
 		    struct ring_buffer_event *event)
 {
@@ -850,7 +848,7 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
 	local_set(&cpu_buffer->commit_page->page->commit, index);
 }
 
-static inline void
+static void
 rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	/*
@@ -896,7 +894,7 @@ static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page->read = 0;
 }
 
-static inline void rb_inc_iter(struct ring_buffer_iter *iter)
+static void rb_inc_iter(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
@@ -926,7 +924,7 @@ static inline void rb_inc_iter(struct ring_buffer_iter *iter)
  * and with this, we can determine what to place into the
  * data field.
  */
-static inline void
+static void
 rb_update_event(struct ring_buffer_event *event,
 			 unsigned type, unsigned length)
 {
@@ -938,15 +936,11 @@ rb_update_event(struct ring_buffer_event *event,
 		break;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
-		event->len =
-			(RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1))
-			>> RB_ALIGNMENT_SHIFT;
+		event->len = DIV_ROUND_UP(RB_LEN_TIME_EXTEND, RB_ALIGNMENT);
 		break;
 
 	case RINGBUF_TYPE_TIME_STAMP:
-		event->len =
-			(RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1))
-			>> RB_ALIGNMENT_SHIFT;
+		event->len = DIV_ROUND_UP(RB_LEN_TIME_STAMP, RB_ALIGNMENT);
 		break;
 
 	case RINGBUF_TYPE_DATA:
@@ -955,16 +949,14 @@ rb_update_event(struct ring_buffer_event *event,
 			event->len = 0;
 			event->array[0] = length;
 		} else
-			event->len =
-				(length + (RB_ALIGNMENT-1))
-				>> RB_ALIGNMENT_SHIFT;
+			event->len = DIV_ROUND_UP(length, RB_ALIGNMENT);
 		break;
 	default:
 		BUG();
 	}
 }
 
-static inline unsigned rb_calculate_event_length(unsigned length)
+static unsigned rb_calculate_event_length(unsigned length)
 {
 	struct ring_buffer_event event; /* Used only for sizeof array */
 
@@ -1438,7 +1430,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(ring_buffer_write);
 
-static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+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;
@@ -2277,9 +2269,24 @@ int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 	if (buffer_a->pages != buffer_b->pages)
 		return -EINVAL;
 
+	if (ring_buffer_flags != RB_BUFFERS_ON)
+		return -EAGAIN;
+
+	if (atomic_read(&buffer_a->record_disabled))
+		return -EAGAIN;
+
+	if (atomic_read(&buffer_b->record_disabled))
+		return -EAGAIN;
+
 	cpu_buffer_a = buffer_a->buffers[cpu];
 	cpu_buffer_b = buffer_b->buffers[cpu];
 
+	if (atomic_read(&cpu_buffer_a->record_disabled))
+		return -EAGAIN;
+
+	if (atomic_read(&cpu_buffer_b->record_disabled))
+		return -EAGAIN;
+
 	/*
 	 * We can't do a synchronize_sched here because this
 	 * function can be called in atomic context.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 17bb88d86ac..2f8ac1f008f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -37,6 +37,7 @@
 #include <linux/irqflags.h>
 
 #include "trace.h"
+#include "trace_output.h"
 
 #define TRACE_BUFFER_FLAGS	(RB_FL_OVERWRITE)
 
@@ -186,9 +187,6 @@ int tracing_is_enabled(void)
 	return tracer_enabled;
 }
 
-/* function tracing enabled */
-int				ftrace_function_enabled;
-
 /*
  * trace_buf_size is the size in bytes that is allocated
  * for a buffer. Note, the number of bytes is always rounded
@@ -329,132 +327,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	tracing_record_cmdline(current);
 }
 
-/**
- * trace_seq_printf - sequence printing of trace information
- * @s: trace sequence descriptor
- * @fmt: printf format string
- *
- * The tracer may use either sequence operations or its own
- * copy to user routines. To simplify formating of a trace
- * trace_seq_printf is used to store strings into a special
- * buffer (@s). Then the output may be either used by
- * the sequencer or pulled into another buffer.
- */
-int
-trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
-{
-	int len = (PAGE_SIZE - 1) - s->len;
-	va_list ap;
-	int ret;
-
-	if (!len)
-		return 0;
-
-	va_start(ap, fmt);
-	ret = vsnprintf(s->buffer + s->len, len, fmt, ap);
-	va_end(ap);
-
-	/* If we can't write it all, don't bother writing anything */
-	if (ret >= len)
-		return 0;
-
-	s->len += ret;
-
-	return len;
-}
-
-/**
- * trace_seq_puts - trace sequence printing of simple string
- * @s: trace sequence descriptor
- * @str: simple string to record
- *
- * The tracer may use either the sequence operations or its own
- * copy to user routines. This function records a simple string
- * into a special buffer (@s) for later retrieval by a sequencer
- * or other mechanism.
- */
-static int
-trace_seq_puts(struct trace_seq *s, const char *str)
-{
-	int len = strlen(str);
-
-	if (len > ((PAGE_SIZE - 1) - s->len))
-		return 0;
-
-	memcpy(s->buffer + s->len, str, len);
-	s->len += len;
-
-	return len;
-}
-
-static int
-trace_seq_putc(struct trace_seq *s, unsigned char c)
-{
-	if (s->len >= (PAGE_SIZE - 1))
-		return 0;
-
-	s->buffer[s->len++] = c;
-
-	return 1;
-}
-
-static int
-trace_seq_putmem(struct trace_seq *s, void *mem, size_t len)
-{
-	if (len > ((PAGE_SIZE - 1) - s->len))
-		return 0;
-
-	memcpy(s->buffer + s->len, mem, len);
-	s->len += len;
-
-	return len;
-}
-
-#define MAX_MEMHEX_BYTES	8
-#define HEX_CHARS		(MAX_MEMHEX_BYTES*2 + 1)
-
-static int
-trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
-{
-	unsigned char hex[HEX_CHARS];
-	unsigned char *data = mem;
-	int i, j;
-
-#ifdef __BIG_ENDIAN
-	for (i = 0, j = 0; i < len; i++) {
-#else
-	for (i = len-1, j = 0; i >= 0; i--) {
-#endif
-		hex[j++] = hex_asc_hi(data[i]);
-		hex[j++] = hex_asc_lo(data[i]);
-	}
-	hex[j++] = ' ';
-
-	return trace_seq_putmem(s, hex, j);
-}
-
-static int
-trace_seq_path(struct trace_seq *s, struct path *path)
-{
-	unsigned char *p;
-
-	if (s->len >= (PAGE_SIZE - 1))
-		return 0;
-	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
-	if (!IS_ERR(p)) {
-		p = mangle_path(s->buffer + s->len, p, "\n");
-		if (p) {
-			s->len = p - s->buffer;
-			return 1;
-		}
-	} else {
-		s->buffer[s->len++] = '?';
-		return 1;
-	}
-
-	return 0;
-}
-
 static void
 trace_seq_reset(struct trace_seq *s)
 {
@@ -543,7 +415,7 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	ftrace_enable_cpu();
 
-	WARN_ON_ONCE(ret);
+	WARN_ON_ONCE(ret && ret != -EAGAIN);
 
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
@@ -738,13 +610,12 @@ void tracing_start(void)
 		return;
 
 	spin_lock_irqsave(&tracing_start_lock, flags);
-	if (--trace_stop_count)
-		goto out;
-
-	if (trace_stop_count < 0) {
-		/* Someone screwed up their debugging */
-		WARN_ON_ONCE(1);
-		trace_stop_count = 0;
+	if (--trace_stop_c