Merge branch 'master' into x86/memblock

Conflicts & resolutions: * arch/x86/xen/setup.c dc91c728fd "xen: allow extra memory to be in multiple regions" 24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..." conflicted on xen_add_extra_mem() updates. The resolution is trivial as the latter just want to replace memblock_x86_reserve_range() with memblock_reserve(). * drivers/pci/intel-iommu.c 166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/" 5dfe8660a3d "bootmem: Replace work_with_active_regions() with..." conflicted as the former moved the file under drivers/iommu/. Resolved by applying the chnages from the latter on the moved file. * mm/Kconfig 6661672053a "memblock: add NO_BOOTMEM config symbol" c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option" conflicted trivially. Both added config options. Just letting both add their own options resolves the conflict. * mm/memblock.c d1f0ece6cdc "mm/memblock.c: small function definition fixes" ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()" confliected. The former updates function removed by the latter. Resolution is trivial. Signed-off-by: Tejun Heo <tj@kernel.org>
author: Tejun Heo <tj@kernel.org> 2011-11-28 09:46:22 -0800
committer: Tejun Heo <tj@kernel.org> 2011-11-28 09:46:22 -0800
commit: d4bbf7e7759afc172e2bfbc5c416324590049cdd (patch)
tree: 7eab5ee5481cd3dcf1162329fec827177640018a /kernel/trace
parent: a150439c4a97db379f0ed6faa46fbbb6e7bf3cb2 (diff)
parent: 401d0069cb344f401bc9d264c31db55876ff78c0 (diff)
24 files changed, 1749 insertions, 917 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2ad39e556cb4..cd3134510f3d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -82,7 +82,7 @@ config EVENT_POWER_TRACING_DEPRECATED
 	  power:power_frequency
 	  This is for userspace compatibility
 	  and will vanish after 5 kernel iterations,
-	  namely 2.6.41.
+	  namely 3.1.
 
 config CONTEXT_SWITCH_TRACER
 	bool
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 761c510a06c5..5f39a07fe5ea 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -15,6 +15,8 @@ ifdef CONFIG_TRACING_BRANCHES
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 endif
 
+CFLAGS_trace_events_filter.o := -I$(src)
+
 #
 # Make the trace clocks available generally: it's infrastructure
 # relied on by ptrace for example:
@@ -53,6 +55,9 @@ endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
+ifeq ($(CONFIG_PM_RUNTIME),y)
+obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
+endif
 ifeq ($(CONFIG_TRACING),y)
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 6957aa298dfa..16fc34a0806f 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -23,6 +23,7 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/debugfs.h>
+#include <linux/export.h>
 #include <linux/time.h>
 #include <linux/uaccess.h>
 
@@ -206,6 +207,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);
 	what |= MASK_TC_BIT(rw, DISCARD);
+	what |= MASK_TC_BIT(rw, FLUSH);
+	what |= MASK_TC_BIT(rw, FUA);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -1054,6 +1057,9 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 		goto out;
 	}
 
+	if (tc & BLK_TC_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
 	else if (tc & BLK_TC_WRITE)
@@ -1063,10 +1069,10 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 	else
 		rwbs[i++] = 'N';
 
+	if (tc & BLK_TC_FUA)
+		rwbs[i++] = 'F';
 	if (tc & BLK_TC_AHEAD)
 		rwbs[i++] = 'A';
-	if (tc & BLK_TC_BARRIER)
-		rwbs[i++] = 'B';
 	if (tc & BLK_TC_SYNC)
 		rwbs[i++] = 'S';
 	if (tc & BLK_TC_META)
@@ -1132,7 +1138,7 @@ typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
 
 static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	unsigned long long ts  = iter->ts;
 	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
@@ -1148,7 +1154,7 @@ static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 
 static int blk_log_action(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
@@ -1561,7 +1567,7 @@ static const struct {
 } mask_maps[] = {
 	{ BLK_TC_READ,		"read"		},
 	{ BLK_TC_WRITE,		"write"		},
-	{ BLK_TC_BARRIER,	"barrier"	},
+	{ BLK_TC_FLUSH,		"flush"		},
 	{ BLK_TC_SYNC,		"sync"		},
 	{ BLK_TC_QUEUE,		"queue"		},
 	{ BLK_TC_REQUEUE,	"requeue"	},
@@ -1573,6 +1579,7 @@ static const struct {
 	{ BLK_TC_META,		"meta"		},
 	{ BLK_TC_DISCARD,	"discard"	},
 	{ BLK_TC_DRV_DATA,	"drv_data"	},
+	{ BLK_TC_FUA,		"fua"		},
 };
 
 static int blk_trace_str2mask(const char *str)
@@ -1788,6 +1795,9 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 {
 	int i = 0;
 
+	if (rw & REQ_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (rw & WRITE)
 		rwbs[i++] = 'W';
 	else if (rw & REQ_DISCARD)
@@ -1797,6 +1807,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 	else
 		rwbs[i++] = 'N';
 
+	if (rw & REQ_FUA)
+		rwbs[i++] = 'F';
 	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
 	if (rw & REQ_SYNC)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 908038f57440..900b409543db 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -22,6 +22,7 @@
 #include <linux/hardirq.h>
 #include <linux/kthread.h>
 #include <linux/uaccess.h>
+#include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/sysctl.h>
 #include <linux/slab.h>
@@ -32,7 +33,6 @@
 
 #include <trace/events/sched.h>
 
-#include <asm/ftrace.h>
 #include <asm/setup.h>
 
 #include "trace_output.h"
@@ -82,14 +82,14 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops ftrace_list_end __read_mostly =
-{
+static struct ftrace_ops ftrace_list_end __read_mostly = {
 	.func		= ftrace_stub,
 };
 
 static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
 ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
@@ -148,9 +148,11 @@ void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
 	__ftrace_trace_function = ftrace_stub;
+	__ftrace_trace_function_delay = ftrace_stub;
 	ftrace_pid_function = ftrace_stub;
 }
 
+#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -210,7 +212,12 @@ static void update_ftrace_function(void)
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
 #else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* do not update till all functions have been modified */
+	__ftrace_trace_function_delay = func;
+#else
 	__ftrace_trace_function = func;
+#endif
 	ftrace_trace_function = ftrace_test_stop_func;
 #endif
 }
@@ -785,8 +792,7 @@ static void unregister_ftrace_profiler(void)
 	unregister_ftrace_graph();
 }
 #else
-static struct ftrace_ops ftrace_profile_ops __read_mostly =
-{
+static struct ftrace_ops ftrace_profile_ops __read_mostly = {
 	.func		= function_profile_call,
 };
 
@@ -806,19 +812,10 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 		     size_t cnt, loff_t *ppos)
 {
 	unsigned long val;
-	char buf[64];		/* big enough to hold a number */
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	val = !!val;
@@ -1182,8 +1179,14 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
 	return NULL;
 }
 
+static void
+ftrace_hash_rec_disable(struct ftrace_ops *ops, int filter_hash);
+static void
+ftrace_hash_rec_enable(struct ftrace_ops *ops, int filter_hash);
+
 static int
-ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
+ftrace_hash_move(struct ftrace_ops *ops, int enable,
+		 struct ftrace_hash **dst, struct ftrace_hash *src)
 {
 	struct ftrace_func_entry *entry;
 	struct hlist_node *tp, *tn;
@@ -1193,9 +1196,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	unsigned long key;
 	int size = src->count;
 	int bits = 0;
+	int ret;
 	int i;
 
 	/*
+	 * Remove the current set, update the hash and add
+	 * them back.
+	 */
+	ftrace_hash_rec_disable(ops, enable);
+
+	/*
 	 * If the new source is empty, just free dst and assign it
 	 * the empty_hash.
 	 */
@@ -1215,9 +1225,10 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	if (bits > FTRACE_HASH_MAX_BITS)
 		bits = FTRACE_HASH_MAX_BITS;
 
+	ret = -ENOMEM;
 	new_hash = alloc_ftrace_hash(bits);
 	if (!new_hash)
-		return -ENOMEM;
+		goto out;
 
 	size = 1 << src->size_bits;
 	for (i = 0; i < size; i++) {
@@ -1236,7 +1247,16 @@ ftrace_hash_move(struct ftrace_hash **dst, struct ftrace_hash *src)
 	rcu_assign_pointer(*dst, new_hash);
 	free_ftrace_hash_rcu(old_hash);
 
-	return 0;
+	ret = 0;
+ out:
+	/*
+	 * Enable regardless of ret:
+	 *  On success, we enable the new hash.
+	 *  On failure, we re-enable the original hash.
+	 */
+	ftrace_hash_rec_enable(ops, enable);
+
+	return ret;
 }
 
 /*
@@ -1596,6 +1616,12 @@ static int __ftrace_modify_code(void *data)
 {
 	int *command = data;
 
+	/*
+	 * Do not call function tracer while we update the code.
+	 * We are in stop machine, no worrying about races.
+	 */
+	function_trace_stop++;
+
 	if (*command & FTRACE_ENABLE_CALLS)
 		ftrace_replace_code(1);
 	else if (*command & FTRACE_DISABLE_CALLS)
@@ -1609,6 +1635,18 @@ static int __ftrace_modify_code(void *data)
 	else if (*command & FTRACE_STOP_FUNC_RET)
 		ftrace_disable_ftrace_graph_caller();
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	/*
+	 * For archs that call ftrace_test_stop_func(), we must
+	 * wait till after we update all the function callers
+	 * before we update the callback. This keeps different
+	 * ops that record different functions from corrupting
+	 * each other.
+	 */
+	__ftrace_trace_function = __ftrace_trace_function_delay;
+#endif
+	function_trace_stop--;
+
 	return 0;
 }
 
@@ -1744,10 +1782,36 @@ static cycle_t		ftrace_update_time;
 static unsigned long	ftrace_update_cnt;
 unsigned long		ftrace_update_tot_cnt;
 
+static int ops_traces_mod(struct ftrace_ops *ops)
+{
+	struct ftrace_hash *hash;
+
+	hash = ops->filter_hash;
+	return !!(!hash || !hash->count);
+}
+
 static int ftrace_update_code(struct module *mod)
 {
 	struct dyn_ftrace *p;
 	cycle_t start, stop;
+	unsigned long ref = 0;
+
+	/*
+	 * When adding a module, we need to check if tracers are
+	 * currently enabled and if they are set to trace all functions.
+	 * If they are, we need to enable the module functions as well
+	 * as update the reference counts for those function records.
+	 */
+	if (mod) {
+		struct ftrace_ops *ops;
+
+		for (ops = ftrace_ops_list;
+		     ops != &ftrace_list_end; ops = ops->next) {
+			if (ops->flags & FTRACE_OPS_FL_ENABLED &&
+			    ops_traces_mod(ops))
+				ref++;
+		}
+	}
 
 	start = ftrace_now(raw_smp_processor_id());
 	ftrace_update_cnt = 0;
@@ -1760,7 +1824,7 @@ static int ftrace_update_code(struct module *mod)
 
 		p = ftrace_new_addrs;
 		ftrace_new_addrs = p->newlist;
-		p->flags = 0L;
+		p->flags = ref;
 
 		/*
 		 * Do the initial record conversion from mcount jump
@@ -1783,7 +1847,7 @@ static int ftrace_update_code(struct module *mod)
 		 * conversion puts the module to the correct state, thus
 		 * passing the ftrace_make_call check.
 		 */
-		if (ftrace_start_up) {
+		if (ftrace_start_up && ref) {
 			int failed = __ftrace_replace_code(p, 1);
 			if (failed) {
 				ftrace_bug(failed, p->ip);
@@ -2407,10 +2471,9 @@ ftrace_match_module_records(struct ftrace_hash *hash, char *buff, char *mod)
  */
 
 static int
-ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
+ftrace_mod_callback(struct ftrace_hash *hash,
+		    char *func, char *cmd, char *param, int enable)
 {
-	struct ftrace_ops *ops = &global_ops;
-	struct ftrace_hash *hash;
 	char *mod;
 	int ret = -EINVAL;
 
@@ -2430,11 +2493,6 @@ ftrace_mod_callback(char *func, char *cmd, char *param, int enable)
 	if (!strlen(mod))
 		return ret;
 
-	if (enable)
-		hash = ops->filter_hash;
-	else
-		hash = ops->notrace_hash;
-
 	ret = ftrace_match_module_records(hash, func, mod);
 	if (!ret)
 		ret = -EINVAL;
@@ -2760,7 +2818,7 @@ static int ftrace_process_regex(struct ftrace_hash *hash,
 	mutex_lock(&ftrace_cmd_mutex);
 	list_for_each_entry(p, &ftrace_commands, list) {
 		if (strcmp(p->name, command) == 0) {
-			ret = p->func(func, command, next, enable);
+			ret = p->func(hash, func, command, next, enable);
 			goto out_unlock;
 		}
 	}
@@ -2857,7 +2915,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		ftrace_match_records(hash, buf, len);
 
 	mutex_lock(&ftrace_lock);
-	ret = ftrace_hash_move(orig_hash, hash);
+	ret = ftrace_hash_move(ops, enable, orig_hash, hash);
+	if (!ret && ops->flags & FTRACE_OPS_FL_ENABLED
+	    && ftrace_enabled)
+		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 	mutex_unlock(&ftrace_lock);
 
 	mutex_unlock(&ftrace_regex_lock);
@@ -3040,18 +3102,12 @@ ftrace_regex_release(struct inode *inode, struct file *file)
 			orig_hash = &iter->ops->notrace_hash;
 
 		mutex_lock(&ftrace_lock);
-		/*
-		 * Remove the current set, update the hash and add
-		 * them back.
-		 */
-		ftrace_hash_rec_disable(iter->ops, filter_hash);
-		ret = ftrace_hash_move(orig_hash, iter->hash);
-		if (!ret) {
-			ftrace_hash_rec_enable(iter->ops, filter_hash);
-			if (iter->ops->flags & FTRACE_OPS_FL_ENABLED
-			    && ftrace_enabled)
-				ftrace_run_update_code(FTRACE_ENABLE_CALLS);
-		}
+		ret = ftrace_hash_move(iter->ops, filter_hash,
+				       orig_hash, iter->hash);
+		if (!ret && (iter->ops->flags & FTRACE_OPS_FL_ENABLED)
+		    && ftrace_enabled)
+			ftrace_run_update_code(FTRACE_ENABLE_CALLS);
+
 		mutex_unlock(&ftrace_lock);
 	}
 	free_ftrace_hash(iter->hash);
@@ -3330,7 +3386,7 @@ static int ftrace_process_locs(struct module *mod,
 {
 	unsigned long *p;
 	unsigned long addr;
-	unsigned long flags;
+	unsigned long flags = 0; /* Shut up gcc */
 
 	mutex_lock(&ftrace_lock);
 	p = start;
@@ -3348,12 +3404,18 @@ static int ftrace_process_locs(struct module *mod,
 	}
 
 	/*
-	 * Disable interrupts to prevent interrupts from executing
-	 * code that is being modified.
+	 * We only need to disable interrupts on start up
+	 * because we are modifying code that an interrupt
+	 * may execute, and the modification is not atomic.
+	 * But for modules, nothing runs the code we modify
+	 * until we are finished with it, and there's no
+	 * reason to cause large interrupt latencies while we do it.
 	 */
-	local_irq_save(flags);
+	if (!mod)
+		local_irq_save(flags);
 	ftrace_update_code(mod);
-	local_irq_restore(flags);
+	if (!mod)
+		local_irq_restore(flags);
 	mutex_unlock(&ftrace_lock);
 
 	return 0;
@@ -3802,6 +3864,14 @@ void ftrace_kill(void)
 }
 
 /**
+ * Test if ftrace is dead or not.
+ */
+int ftrace_is_dead(void)
+{
+	return ftrace_disabled;
+}
+
+/**
  * register_ftrace_function - register a function for profiling
  * @ops - ops structure that holds the function for profiling.
  *
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b0c7aa407943..f5b7b5c1195b 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -478,7 +478,7 @@ struct ring_buffer_per_cpu {
 	int				cpu;
 	atomic_t			record_disabled;
 	struct ring_buffer		*buffer;
-	spinlock_t			reader_lock;	/* serialize readers */
+	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct list_head		*pages;
@@ -488,12 +488,14 @@ struct ring_buffer_per_cpu {
 	struct buffer_page		*reader_page;
 	unsigned long			lost_events;
 	unsigned long			last_overrun;
+	local_t				entries_bytes;
 	local_t				commit_overrun;
 	local_t				overrun;
 	local_t				entries;
 	local_t				committing;
 	local_t				commits;
 	unsigned long			read;
+	unsigned long			read_bytes;
 	u64				write_stamp;
 	u64				read_stamp;
 };
@@ -997,15 +999,21 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 			     unsigned nr_pages)
 {
 	struct buffer_page *bpage, *tmp;
-	unsigned long addr;
 	LIST_HEAD(pages);
 	unsigned i;
 
 	WARN_ON(!nr_pages);
 
 	for (i = 0; i < nr_pages; i++) {
+		struct page *page;
+		/*
+		 * __GFP_NORETRY flag makes sure that the allocation fails
+		 * gracefully without invoking oom-killer and the system is
+		 * not destabilized.
+		 */
 		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
-				    GFP_KERNEL, cpu_to_node(cpu_buffer->cpu));
+				    GFP_KERNEL | __GFP_NORETRY,
+				    cpu_to_node(cpu_buffer->cpu));
 		if (!bpage)
 			goto free_pages;
 
@@ -1013,10 +1021,11 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 		list_add(&bpage->list, &pages);
 
-		addr = __get_free_page(GFP_KERNEL);
-		if (!addr)
+		page = alloc_pages_node(cpu_to_node(cpu_buffer->cpu),
+					GFP_KERNEL | __GFP_NORETRY, 0);
+		if (!page)
 			goto free_pages;
-		bpage->page = (void *)addr;
+		bpage->page = page_address(page);
 		rb_init_page(bpage->page);
 	}
 
@@ -1045,7 +1054,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
-	unsigned long addr;
+	struct page *page;
 	int ret;
 
 	cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
@@ -1055,7 +1064,7 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
-	spin_lock_init(&cpu_buffer->reader_lock);
+	raw_spin_lock_init(&cpu_buffer->reader_lock);
 	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
@@ -1067,10 +1076,10 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	rb_check_bpage(cpu_buffer, bpage);
 
 	cpu_buffer->reader_page = bpage;
-	addr = __get_free_page(GFP_KERNEL);
-	if (!addr)
+	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
+	if (!page)
 		goto fail_free_reader;
-	bpage->page = (void *)addr;
+	bpage->page = page_address(page);
 	rb_init_page(bpage->page);
 
 	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
@@ -1252,7 +1261,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	struct list_head *p;
 	unsigned i;
 
-	spin_lock_irq(&cpu_buffer->reader_lock);
+	raw_spin_lock_irq(&cpu_buffer->reader_lock);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1270,7 +1279,7 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	rb_check_pages(cpu_buffer);
 
 out:
-	spin_unlock_irq(&cpu_buffer->reader_lock);
+	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 static void
@@ -1281,7 +1290,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	struct list_head *p;
 	unsigned i;
 
-	spin_lock_irq(&cpu_buffer->reader_lock);
+	raw_spin_lock_irq(&cpu_buffer->reader_lock);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1296,7 +1305,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_check_pages(cpu_buffer);
 
 out:
-	spin_unlock_irq(&cpu_buffer->reader_lock);
+	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
 /**
@@ -1314,7 +1323,6 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	unsigned nr_pages, rm_pages, new_pages;
 	struct buffer_page *bpage, *tmp;
 	unsigned long buffer_size;
-	unsigned long addr;
 	LIST_HEAD(pages);
 	int i, cpu;
 
@@ -1375,16 +1383,24 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
 	for_each_buffer_cpu(buffer, cpu) {
 		for (i = 0; i < new_pages; i++) {
+			struct page *page;
+			/*
+			 * __GFP_NORETRY flag makes sure that the allocation
+			 * fails gracefully without invoking oom-killer and
+			 * the system is not destabilized.
+			 */
 			bpage = kzalloc_node(ALIGN(sizeof(*bpage),
 						  cache_line_size()),
-					    GFP_KERNEL, cpu_to_node(cpu));
+					    GFP_KERNEL | __GFP_NORETRY,
+					    cpu_to_node(cpu));
 			if (!bpage)
 				goto free_pages;
 			list_add(&bpage->list, &pages);
-			addr = __get_free_page(GFP_KERNEL);
-			if (!addr)
+			page = alloc_pages_node(cpu_to_node(cpu),
+						GFP_KERNEL | __GFP_NORETRY, 0);
+			if (!page)
 				goto free_pages;
-			bpage->page = (void *)addr;
+			bpage->page = page_address(page);
 			rb_init_page(bpage->page);
 		}
 	}
@@ -1694,6 +1710,7 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 		 * the counters.
 		 */
 		local_add(entries, &cpu_buffer->overrun);
+		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
 
 		/*
 		 * The entries will be zeroed out when we move the
@@ -1849,6 +1866,9 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	event = __rb_page_index(tail_page, tail);
 	kmemcheck_annotate_bitfield(event, bitfield);
 
+	/* account for padding bytes */
+	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);
+
 	/*
 	 * Save the original length to the meta data.
 	 * This will be used by the reader to add lost event
@@ -2040,6 +2060,9 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (!tail)
 		tail_page->page->time_stamp = ts;
 
+	/* account for these added bytes */
+	local_add(length, &cpu_buffer->entries_bytes);
+
 	return event;
 }
 
@@ -2062,6 +2085,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
 			local_read(&bpage->write) & ~RB_WRITE_MASK;
+		unsigned long event_length = rb_event_length(event);
 		/*
 		 * This is on the tail page. It is possible that
 		 * a write could come in and move the tail page
@@ -2071,8 +2095,11 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 		old_index += write_mask;
 		new_index += write_mask;
 		index = local_cmpxchg(&bpage->write, old_index, new_index);
-		if (index == old_index)
+		if (index == old_index) {
+			/* update counters */
+			local_sub(event_length, &cpu_buffer->entries_bytes);
 			return 1;
+		}
 	}
 
 	/* could not discard */
@@ -2647,6 +2674,58 @@ rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
 }
 
 /**
+ * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to read from.
+ */
+unsigned long ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
+{
+	unsigned long flags;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct buffer_page *bpage;
+	unsigned long ret;
+
+	if (!cpumask_test_cpu(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	/*
+	 * if the tail is on reader_page, oldest time stamp is on the reader
+	 * page
+	 */
+	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
+		bpage = cpu_buffer->reader_page;
+	else
+		bpage = rb_set_head_page(cpu_buffer);
+	ret = bpage->page->time_stamp;
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);
+
+/**
+ * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to read from.
+ */
+unsigned long ring_buffer_bytes_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 = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu);
+
+/**
  * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
  * @buffer: The ring buffer
  * @cpu: The per CPU buffer to get the entries from.
@@ -2790,9 +2869,9 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 
 	cpu_buffer = iter->cpu_buffer;
 
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	rb_iter_reset(iter);
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 
@@ -3251,12 +3330,12 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
  again:
 	local_irq_save(flags);
 	if (dolock)
-		spin_lock(&cpu_buffer->reader_lock);
+		raw_spin_lock(&cpu_buffer->reader_lock);
 	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
 	if (dolock)
-		spin_unlock(&cpu_buffer->reader_lock);
+		raw_spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);
 
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
@@ -3281,9 +3360,9 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	unsigned long flags;
 
  again:
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	event = rb_iter_peek(iter, ts);
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
@@ -3323,7 +3402,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	if (dolock)
-		spin_lock(&cpu_buffer->reader_lock);
+		raw_spin_lock(&cpu_buffer->reader_lock);
 
 	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event) {
@@ -3332,7 +3411,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
 	}
 
 	if (dolock)
-		spin_unlock(&cpu_buffer->reader_lock);
+		raw_spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);
 
  out:
@@ -3424,11 +3503,11 @@ ring_buffer_read_start(struct ring_buffer_iter *iter)
 
 	cpu_buffer = iter->cpu_buffer;
 
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	arch_spin_lock(&cpu_buffer->lock);
 	rb_iter_reset(iter);
 	arch_spin_unlock(&cpu_buffer->lock);
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
@@ -3463,7 +3542,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
 
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
  again:
 	event = rb_iter_peek(iter, ts);
 	if (!event)
@@ -3474,7 +3553,7 @@ ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 
 	rb_advance_iter(iter);
  out:
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return event;
 }
@@ -3513,11 +3592,13 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 	cpu_buffer->reader_page->read = 0;
 
 	local_set(&cpu_buffer->commit_overrun, 0);
+	local_set(&cpu_buffer->entries_bytes, 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->read_bytes = 0;
 
 	cpu_buffer->write_stamp = 0;
 	cpu_buffer->read_stamp = 0;
@@ -3543,7 +3624,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 
 	atomic_inc(&cpu_buffer->record_disabled);
 
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
 		goto out;
@@ -3555,7 +3636,7 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	arch_spin_unlock(&cpu_buffer->lock);
 
  out:
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	atomic_dec(&cpu_buffer->record_disabled);
 }
@@ -3593,10 +3674,10 @@ int ring_buffer_empty(struct ring_buffer *buffer)
 		cpu_buffer = buffer->buffers[cpu];
 		local_irq_save(flags);
 		if (dolock)
-			spin_lock(&cpu_buffer->reader_lock);
+			raw_spin_lock(&cpu_buffer->reader_lock);
 		ret = rb_per_cpu_empty(cpu_buffer);
 		if (dolock)
-			spin_unlock(&cpu_buffer->reader_lock);
+			raw_spin_unlock(&cpu_buffer->reader_lock);
 		local_irq_restore(flags);
 
 		if (!ret)
@@ -3627,10 +3708,10 @@ int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
 	cpu_buffer = buffer->buffers[cpu];
 	local_irq_save(flags);
 	if (dolock)
-		spin_lock(&cpu_buffer->reader_lock);
+		raw_spin_lock(&cpu_buffer->reader_lock);
 	ret = rb_per_cpu_empty(cpu_buffer);
 	if (dolock)
-		spin_unlock(&cpu_buffer->reader_lock);
+		raw_spin_unlock(&cpu_buffer->reader_lock);
 	local_irq_restore(flags);
 
 	return ret;
@@ -3730,16 +3811,17 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
  * Returns:
  *  The page allocated, or NULL on error.
  */
-void *ring_buffer_alloc_read_page(struct ring_buffer *buffer)
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
 {
 	struct buffer_data_page *bpage;
-	unsigned long addr;
+	struct page *page;
 
-	addr = __get_free_page(GFP_KERNEL);
-	if (!addr)
+	page = alloc_pages_node(cpu_to_node(cpu),
+				GFP_KERNEL | __GFP_NORETRY, 0);
+	if (!page)
 		return NULL;
 
-	bpage = (void *)addr;
+	bpage = page_address(page);
 
 	rb_init_page(bpage);
 
@@ -3826,7 +3908,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	if (!bpage)
 		goto out;
 
-	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
@@ -3903,6 +3985,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 	} else {
 		/* update the entry counter */
 		cpu_buffer->read += rb_page_entries(reader);
+		cpu_buffer->read_bytes += BUF_PAGE_SIZE;
 
 		/* swap the pages */
 		rb_init_page(bpage);
@@ -3949,7 +4032,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
 		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
 
  out_unlock:
-	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
  out:
 	return ret;
@@ -3978,20 +4061,11 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
 	unsigned long *p = filp->private_data;
-	char buf[64];
 	unsigned long val;
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	if (val)
diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c
index 302f8a614635..a5457d577b98 100644
--- a/kernel/trace/ring_buffer_benchmark.c
+++ b/kernel/trace/ring_buffer_benchmark.c
@@ -106,7 +106,7 @@ static enum event_status read_page(int cpu)
 	int inc;
 	int i;
 
-	bpage = ring_buffer_alloc_read_page(buffer);
+	bpage = ring_buffer_alloc_read_page(buffer, cpu);
 	if (!bpage)
 		return EVENT_DROPPED;
 
diff --git a/kernel/trace/rpm-traces.c b/kernel/trace/rpm-traces.c
new file mode 100644
index 000000000000..4b3b5eaf94d1
--- /dev/null
+++ b/kernel/trace/rpm-traces.c
@@ -0,0 +1,20 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Ming Lei <ming.lei@canonical.com>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/rpm.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_return_int);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_suspend);
+EXPORT_TRACEPOINT_SYMBOL_GPL(rpm_resume);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ee9c921d7f21..f2bd275bb60f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -341,28 +341,29 @@ unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
 	TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE;
 
 static int trace_stop_count;
-static DEFINE_SPINLOCK(tracing_start_lock);
+static DEFINE_RAW_SPINLOCK(tracing_start_lock);
+
+static void wakeup_work_handler(struct work_struct *work)
+{
+	wake_up(&trace_wait);
+}
+
+static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
  *
- * Simply wakes up any task that is blocked on the trace_wait
- * queue. These is used with trace_poll for tasks polling the trace.
+ * Schedules a delayed work to wake up any task that is blocked on the
+ * trace_wait queue. These is used with trace_poll for tasks polling the
+ * trace.
  */
 void trace_wake_up(void)
 {
-	int cpu;
+	const unsigned long delay = msecs_to_jiffies(2);
 
 	if (trace_flags & TRACE_ITER_BLOCK)
 		return;
-	/*
-	 * The runqueue_is_locked() can fail, but this is the best we
-	 * have for now:
-	 */
-	cpu = get_cpu();
-	if (!runqueue_is_locked(cpu))
-		wake_up(&trace_wait);
-	put_cpu();
+	schedule_delayed_work(&wakeup_work, delay);
 }
 
 static int __init set_buf_size(char *str)
@@ -424,6 +425,7 @@ static const char *trace_options[] = {
 	"graph-time",
 	"record-cmd",
 	"overwrite",
+	"disable_on_free",
 	NULL
 };
 
@@ -433,6 +435,7 @@ static struct {
 } trace_clocks[] = {
 	{ trace_clock_local,	"local" },
 	{ trace_clock_global,	"global" },
+	{ trace_clock_counter,	"counter" },
 };
 
 int trace_clock_id;
@@ -958,7 +961,7 @@ void tracing_start(void)
 	if (tracing_disabled)
 		return;
 
-	spin_lock_irqsave(&tracing_start_lock, flags);
+	raw_spin_lock_irqsave(&tracing_start_lock, flags);
 	if (--trace_stop_count) {
 		if (trace_stop_count < 0) {
 			/* Someone screwed up their debugging */
@@ -983,7 +986,7 @@ void tracing_start(void)
 
 	ftrace_start();
  out:
-	spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
 
 /**
@@ -998,7 +1001,7 @@ void tracing_stop(void)
 	unsigned long flags;
 
 	ftrace_stop();
-	spin_lock_irqsave(&tracing_start_lock, flags);
+	raw_spin_lock_irqsave(&tracing_start_lock, flags);
 	if (trace_stop_count++)
 		goto out;
 
@@ -1016,7 +1019,7 @@ void tracing_stop(void)
 	arch_spin_unlock(&ftrace_max_lock);
 
  out:
-	spin_unlock_irqrestore(&tracing_start_lock, flags);
+	raw_spin_unlock_irqrestore(&tracing_start_lock, flags);
 }
 
 void trace_stop_cmdline_recording(void);
@@ -1191,6 +1194,18 @@ void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
 }
 EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
 
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+					    struct ring_buffer_event *event,
+					    unsigned long flags, int pc,
+					    struct pt_regs *regs)
+{
+	ring_buffer_unlock_commit(buffer, event);
+
+	ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
+	ftrace_trace_userstack(buffer, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs);
+
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
 					 struct ring_buffer_event *event)
 {
@@ -1234,30 +1249,103 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
 }
 
 #ifdef CONFIG_STACKTRACE
+
+#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+struct ftrace_stack {
+	unsigned long		calls[FTRACE_STACK_MAX_ENTRIES];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+static DEFINE_PER_CPU(int, ftrace_stack_reserve);
+
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
 				 unsigned long flags,
-				 int skip, int pc)
+				 int skip, int pc, struct pt_regs *regs)
 {
 	struct ftrace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
 	struct stack_entry *entry;
 	struct stack_trace trace;
+	int use_stack;
+	int size = FTRACE_STACK_ENTRIES;
+
+	trace.nr_entries	= 0;
+	trace.skip		= skip;
+
+	/*
+	 * Since events can happen in NMIs there's no safe way to
+	 * use the per cpu ftrace_stacks. We reserve it and if an interrupt
+	 * or NMI comes in, it will just have to use the default
+	 * FTRACE_STACK_SIZE.
+	 */
+	preempt_disable_notrace();
+
+	use_stack = ++__get_cpu_var(ftrace_stack_reserve);
+	/*
+	 * We don't need any atomic variables, just a barrier.
+	 * If an interrupt comes in, we don't care, because it would
+	 * have exited and put the counter back to what we want.
+	 * We just need a barrier to keep gcc from moving things
+	 * around.
+	 */
+	barrier();
+	if (use_stack == 1) {
+		trace.entries		= &__get_cpu_var(ftrace_stack).calls[0];
+		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
+
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+
+		if (trace.nr_entries > size)
+			size = trace.nr_entries;
+	} else
+		/* From now on, use_stack is a boolean */
+		use_stack = 0;
+
+	size *= sizeof(unsigned long);
 
 	event = trace_buffer_lock_reserve(buffer, TRACE_STACK,
-					  sizeof(*entry), flags, pc);
+					  sizeof(*entry) + size, flags, pc);
 	if (!event)
-		return;
-	entry	= ring_buffer_event_data(event);
-	memset(&entry->caller, 0, sizeof(entry->caller));
+		goto out;
+	entry = ring_buffer_event_data(event);
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= FTRACE_STACK_ENTRIES;
-	trace.skip		= skip;
-	trace.entries		= entry->caller;
+	memset(&entry->caller, 0, size);
+
+	if (use_stack)
+		memcpy(&entry->caller, trace.entries,
+		       trace.nr_entries * sizeof(unsigned long));
+	else {
+		trace.max_entries	= FTRACE_STACK_ENTRIES;
+		trace.entries		= entry->caller;
+		if (regs)
+			save_stack_trace_regs(regs, &trace);
+		else
+			save_stack_trace(&trace);
+	}
+
+	entry->size = trace.nr_entries;
 
-	save_stack_trace(&trace);
 	if (!filter_check_discard(call, entry, buffer, event))
 		ring_buffer_unlock_commit(buffer, event);
+
+ out:
+	/* Again, don't let gcc optimize things here */
+	barrier();
+	__get_cpu_var(ftrace_stack_reserve)--;
+	preempt_enable_notrace();
+
+}
+
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+			     int skip, int pc, struct pt_regs *regs)
+{
+	if (!(trace_flags & TRACE_ITER_STACKTRACE))
+		return;
+
+	__ftrace_trace_stack(buffer, flags, skip, pc, regs);
 }
 
 void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
@@ -1266,13 +1354,13 @@ void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
 	if (!(trace_flags & TRACE_ITER_STACKTRACE))
 		return;
 
-	__ftrace_trace_stack(buffer, flags, skip, pc);
+	__ftrace_trace_stack(buffer, flags, skip, pc, NULL);
 }
 
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc)
 {
-	__ftrace_trace_stack(tr->buffer, flags, skip, pc);
+	__ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
 }
 
 /**
@@ -1288,7 +1376,7 @@ void trace_dump_stack(void)
 	local_save_flags(flags);
 
 	/* skipping 3 traces, seems to get us at the caller of this function */
-	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
+	__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(), NULL);
 }
 
 static DEFINE_PER_CPU(int, user_stack_count);
@@ -1536,7 +1624,12 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts,
 
 	ftrace_enable_cpu();
 
-	return event ? ring_buffer_event_data(event) : NULL;
+	if (event) {
+		iter->ent_size = ring_buffer_event_length(event);
+		return ring_buffer_event_data(event);
+	}
+	iter->ent_size = 0;
+	return NULL;
 }
 
 static struct trace_entry *
@@ -2051,6 +2144,9 @@ void trace_default_header(struct seq_file *m)
 {
 	struct trace_iterator *iter = m->private;
 
+	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+		return;
+
 	if (iter->iter_flags & TRACE_FILE_LAT_FMT) {
 		/* print nothing if the buffers are empty */
 		if (trace_empty(iter))
@@ -2064,6 +2160,14 @@ void trace_default_header(struct seq_file *m)
 	}
 }
 
+static void test_ftrace_alive(struct seq_file *m)
+{
+	if (!ftrace_is_dead())
+		return;
+	seq_printf(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+	seq_printf(m, "#          MAY BE MISSING FUNCTION EVENTS\n");
+}
+
 static int s_show(struct seq_file *m, void *v)
 {
 	struct trace_iterator *iter = v;
@@ -2073,6 +2177,7 @@ static int s_show(struct seq_file *m, void *v)
 		if (iter->tr) {
 			seq_printf(m, "# tracer: %s\n", iter->trace->name);
 			seq_puts(m, "#\n");
+			test_ftrace_alive(m);
 		}
 		if (iter->trace && iter->trace->print_header)
 			iter->trace->print_header(m);
@@ -2615,9 +2720,9 @@ static const char readme_msg[] =
 	"# cat /sys/kernel/debug/tracing/trace_options\n"
 	"noprint-parent nosym-offset nosym-addr noverbose\n"
 	"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
-	"# echo 1 > /sys/kernel/debug/tracing/tracing_enabled\n"
+	"# echo 1 > /sys/kernel/debug/tracing/tracing_on\n"
 	"# cat /sys/kernel/debug/tracing/trace > /tmp/trace.txt\n"
-	"# echo 0 > /sys/kernel/debug/tracing/tracing_enabled\n"
+	"# echo 0 > /sys/kernel/debug/tracing/tracing_on\n"
 ;
 
 static ssize_t
@@ -2701,20 +2806,11 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	char buf[64];
 	unsigned long val;
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	val = !!val;
@@ -2767,7 +2863,7 @@ int tracer_init(struct tracer *t, struct trace_array *tr)
 	return t->init(tr);
 }
 
-static int tracing_resize_ring_buffer(unsigned long size)
+static int __tracing_resize_ring_buffer(unsigned long size)
 {
 	int ret;
 
@@ -2819,6 +2915,41 @@ static int tracing_resize_ring_buffer(unsigned long size)
 	return ret;
 }
 
+static ssize_t tracing_resize_ring_buffer(unsigned long size)
+{
+	int cpu, ret = size;
+
+	mutex_lock(&trace_types_lock);
+
+	tracing_stop();
+
+	/* disable all cpu buffers */
+	for_each_tracing_cpu(cpu) {
+		if (global_trace.data[cpu])
+			atomic_inc(&global_trace.data[cpu]->disabled);
+		if (max_tr.data[cpu])
+			atomic_inc(&max_tr.data[cpu]->disabled);
+	}
+
+	if (size != global_trace.entries)
+		ret = __tracing_resize_ring_buffer(size);
+
+	if (ret < 0)
+		ret = -ENOMEM;
+
+	for_each_tracing_cpu(cpu) {
+		if (global_trace.data[cpu])
+			atomic_dec(&global_trace.data[cpu]->disabled);
+		if (max_tr.data[cpu])
+			atomic_dec(&max_tr.data[cpu]->disabled);
+	}
+
+	tracing_start();
+	mutex_unlock(&trace_types_lock);
+
+	return ret;
+}
+
 
 /**
  * tracing_update_buffers - used by tracing facility to expand ring buffers
@@ -2836,7 +2967,7 @@ int tracing_update_buffers(void)
 
 	mutex_lock(&trace_types_lock);
 	if (!ring_buffer_expanded)
-		ret = tracing_resize_ring_buffer(trace_buf_size);
+		ret = __tracing_resize_ring_buffer(trace_buf_size);
 	mutex_unlock(&trace_types_lock);
 
 	return ret;
@@ -2860,7 +2991,7 @@ static int tracing_set_tracer(const char *buf)
 	mutex_lock(&trace_types_lock);
 
 	if (!ring_buffer_expanded) {
-		ret = tracing_resize_ring_buffer(trace_buf_size);
+		ret = __tracing_resize_ring_buffer(trace_buf_size);
 		if (ret < 0)
 			goto out;
 		ret = 0;
@@ -2966,20 +3097,11 @@ tracing_max_lat_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
 	unsigned long *ptr = filp->private_data;
-	char buf[64];
 	unsigned long val;
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	*ptr = val * 1000;
@@ -3434,83 +3556,96 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 		      size_t cnt, loff_t *ppos)
 {
 	unsigned long val;
-	char buf[64];
-	int ret, cpu;
-
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
+	int ret;
 
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	/* must have at least 1 entry */
 	if (!val)
 		return -EINVAL;
 
-	mutex_lock(&trace_types_lock);
-
-	tracing_stop();
-
-	/* disable all cpu buffers */
-	for_each_tracing_cpu(cpu) {
-		if (global_trace.data[cpu])
-			atomic_inc(&global_trace.data[cpu]->disabled);
-		if (max_tr.data[cpu])
-			atomic_inc(&max_tr.data[cpu]->disabled);
-	}
-
 	/* value is in KB */
 	val <<= 10;
 
-	if (val != global_trace.entries) {
-		ret = tracing_resize_ring_buffer(val);
-		if (ret < 0) {
-			cnt = ret;
-			goto out;
-		}
-	}
+	ret = tracing_resize_ring_buffer(val);
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
-	/* If check pages failed, return ENOMEM */
-	if (tracing_disabled)
-		cnt = -ENOMEM;
- out:
+	return cnt;
+}
+
+static ssize_t
+tracing_total_entries_read(struct file *filp, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	struct trace_array *tr = filp->private_data;
+	char buf[64];
+	int r, cpu;
+	unsigned long size = 0, expanded_size = 0;
+
+	mutex_lock(&trace_types_lock);
 	for_each_tracing_cpu(cpu) {
-		if (global_trace.data[cpu])
-			atomic_dec(&global_trace.data[cpu]->disabled);
-		if (max_tr.data[cpu])
-			atomic_dec(&max_tr.data[cpu]->disabled);
+		size += tr->entries >> 10;
+		if (!ring_buffer_expanded)
+			expanded_size += trace_buf_size >> 10;
 	}
-
-	tracing_start();
+	if (ring_buffer_expanded)
+		r = sprintf(buf, "%lu\n", size);
+	else
+		r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size);
 	mutex_unlock(&trace_types_lock);
 
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+tracing_free_buffer_write(struct file *filp, const char __user *ubuf,
+			  size_t cnt, loff_t *ppos)
+{
+	/*
+	 * There is no need to read what the user has written, this function
+	 * is just to make sure that there is no error when "echo" is used
+	 */
+
+	*ppos += cnt;
+
 	return cnt;
 }
 
-static int mark_printk(const char *fmt, ...)
+static int
+tracing_free_buffer_release(struct inode *inode, struct file *filp)
 {
-	int ret;
-	va_list args;
-	va_start(args, fmt);
-	ret = trace_vprintk(0, fmt, args);
-	va_end(args);
-	return ret;
+	/* disable tracing ? */
+	if (trace_flags & TRACE_ITER_STOP_ON_FREE)
+		tracing_off();
+	/* resize the ring buffer to 0 */
+	tracing_resize_ring_buffer(0);
+
+	return 0;
 }
 
 static ssize_t
 tracing_mark_write(struct file *filp, const char __user *ubuf,
 					size_t cnt, loff_t *fpos)
 {
-	char *buf;
-	size_t written;
+	unsigned long addr = (unsigned long)ubuf;
+	struct ring_buffer_event *event;
+	struct ring_buffer *buffer;
+	struct print_entry *entry;
+	unsigned long irq_flags;
+	struct page *pages[2];
+	int nr_pages = 1;
+	ssize_t written;
+	void *page1;
+	void *page2;
+	int offset;
+	int size;
+	int len;
+	int ret;
 
 	if (tracing_disabled)
 		return -EINVAL;
@@ -3518,28 +3653,81 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 	if (cnt > TRACE_BUF_SIZE)
 		cnt = TRACE_BUF_SIZE;
 
-	buf = kmalloc(cnt + 2, GFP_KERNEL);
-	if (buf == NULL)
-		return -ENOMEM;
+	/*
+	 * Userspace is injecting traces into the kernel trace buffer.
+	 * We want to be as non intrusive as possible.
+	 * To do so, we do not want to allocate any special buffers
+	 * or take any locks, but instead write the userspace data
+	 * straight into the ring buffer.
+	 *
+	 * First we need to pin the userspace buffer into memory,
+	 * which, most likely it is, because it just referenced it.
+	 * But there's no guarantee that it is. By using get_user_pages_fast()
+	 * and kmap_atomic/kunmap_atomic() we can get access to the
+	 * pages directly. We then write the data directly into the
+	 * ring buffer.
+	 */
+	BUILD_BUG_ON(TRACE_BUF_SIZE >= PAGE_SIZE);
 
-	if (copy_from_user(buf, ubuf, cnt)) {
-		kfree(buf);
-		return -EFAULT;
+	/* check if we cross pages */
+	if ((addr & PAGE_MASK) != ((addr + cnt) & PAGE_MASK))
+		nr_pages = 2;
+
+	offset = addr & (PAGE_SIZE - 1);
+	addr &= PAGE_MASK;
+
+	ret = get_user_pages_fast(addr, nr_pages, 0, pages);
+	if (ret < nr_pages) {
+		while (--ret >= 0)
+			put_page(pages[ret]);
+		written = -EFAULT;
+		goto out;
+	}
+
+	page1 = kmap_atomic(pages[0]);
+	if (nr_pages == 2)
+		page2 = kmap_atomic(pages[1]);
+
+	local_save_flags(irq_flags);
+	size = sizeof(*entry) + cnt + 2; /* possible \n added */
+	buffer = global_trace.buffer;
+	event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+					  irq_flags, preempt_count());
+	if (!event) {
+		/* Ring buffer disabled, return as if not open for write */
+		written = -EBADF;
+		goto out_unlock;
 	}
-	if (buf[cnt-1] != '\n') {
-		buf[cnt] = '\n';
-		buf[cnt+1] = '\0';
+
+	entry = ring_buffer_event_data(event);
+	entry->ip = _THIS_IP_;
+
+	if (nr_pages == 2) {
+		len = PAGE_SIZE - offset;
+		memcpy(&entry->buf, page1 + offset, len);
+		memcpy(&entry->buf[len], page2, cnt - len);
 	} else
-		buf[cnt] = '\0';
+		memcpy(&entry->buf, page1 + offset, cnt);
 
-	written = mark_printk("%s", buf);
-	kfree(buf);
-	*fpos += written;
+	if (entry->buf[cnt - 1] != '\n') {
+		entry->buf[cnt] = '\n';
+		entry->buf[cnt + 1] = '\0';
+	} else
+		entry->buf[cnt] = '\0';
+
+	ring_buffer_unlock_commit(buffer, event);
+
+	written = cnt;
 
-	/* don't tell userspace we wrote more - it might confuse them */
-	if (written > cnt)
-		written = cnt;
+	*fpos += written;
 
+ out_unlock:
+	if (nr_pages == 2)
+		kunmap_atomic(page2);
+	kunmap_atomic(page1);
+	while (nr_pages > 0)
+		put_page(pages[--nr_pages]);
+ out:
 	return written;
 }
 
@@ -3640,6 +3828,17 @@ static const struct file_operations tracing_entries_fops = {
 	.llseek		= generic_file_llseek,
 };
 
+static const struct file_operations tracing_total_entries_fops = {
+	.open		= tracing_open_generic,
+	.read		= tracing_total_entries_read,
+	.llseek		= generic_file_llseek,
+};
+
+static const struct file_operations tracing_free_buffer_fops = {
+	.write		= tracing_free_buffer_write,
+	.release	= tracing_free_buffer_release,
+};
+
 static const struct file_operations tracing_mark_fops = {
 	.open		= tracing_open_generic,
 	.write		= tracing_mark_write,
@@ -3696,7 +3895,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 		return 0;
 
 	if (!info->spare)
-		info->spare = ring_buffer_alloc_read_page(info->tr->buffer);
+		info->spare = ring_buffer_alloc_read_page(info->tr->buffer, info->cpu);
 	if (!info->spare)
 		return -ENOMEM;
 
@@ -3704,8 +3903,6 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (info->read < PAGE_SIZE)
 		goto read;
 
-	info->read = 0;
-
 	trace_access_lock(info->cpu);
 	ret = ring_buffer_read_page(info->tr->buffer,
 				    &info->spare,
@@ -3715,6 +3912,8 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
 	if (ret < 0)
 		return 0;
 
+	info->read = 0;
+
 read:
 	size = PAGE_SIZE - info->read;
 	if (size > count)
@@ -3853,7 +4052,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 
 		ref->ref = 1;
 		ref->buffer = info->tr->buffer;
-		ref->page = ring_buffer_alloc_read_page(ref->buffer);
+		ref->page = ring_buffer_alloc_read_page(ref->buffer, info->cpu);
 		if (!ref->page) {
 			kfree(ref);
 			break;
@@ -3862,8 +4061,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		r = ring_buffer_read_page(ref->buffer, &ref->page,
 					  len, info->cpu, 1);
 		if (r < 0) {
-			ring_buffer_free_read_page(ref->buffer,
-						   ref->page);
+			ring_buffer_free_read_page(ref->buffer, ref->page);
 			kfree(ref);
 			break;
 		}
@@ -3923,6 +4121,8 @@ tracing_stats_read(struct file *filp, char __user *ubuf,
 	struct trace_array *tr = &global_trace;
 	struct trace_seq *s;
 	unsigned long cnt;
+	unsigned long long t;
+	unsigned long usec_rem;
 
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
 	if (!s)
@@ -3939,6 +4139,17 @@ 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_bytes_cpu(tr->buffer, cpu);
+	trace_seq_printf(s, "bytes: %ld\n", cnt);
+
+	t = ns2usecs(ring_buffer_oldest_event_ts(tr->buffer, cpu));
+	usec_rem = do_div(t, USEC_PER_SEC);
+	trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem);
+
+	t = ns2usecs(ring_buffer_time_stamp(tr->buffer, cpu));
+	usec_rem = do_div(t, USEC_PER_SEC);
+	trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem);
+
 	count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, s->len);
 
 	kfree(s);
@@ -4099,19 +4310,10 @@ trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt,
 {
 	struct trace_option_dentry *topt = filp->private_data;
 	unsigned long val;
-	char buf[64];
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	if (val != 0 && val != 1)
@@ -4159,20 +4361,11 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			 loff_t *ppos)
 {
 	long index = (long)filp->private_data;
-	char buf[64];
 	unsigned long val;
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	if (val != 0 && val != 1)
@@ -4365,6 +4558,12 @@ static __init int tracer_init_debugfs(void)
 	trace_create_file("buffer_size_kb", 0644, d_tracer,
 			&global_trace, &tracing_entries_fops);
 
+	trace_create_file("buffer_total_size_kb", 0444, d_tracer,
+			&global_trace, &tracing_total_entries_fops);
+
+	trace_create_file("free_buffer", 0644, d_tracer,
+			&global_trace, &tracing_free_buffer_fops);
+
 	trace_create_file("trace_marker", 0220, d_tracer,
 			NULL, &tracing_mark_fops);
 
@@ -4478,6 +4677,12 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
 
 	tracing_off();
 
+	/* Did function tracer already get disabled? */
+	if (ftrace_is_dead()) {
+		printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n");
+		printk("#          MAY BE MISSING FUNCTION EVENTS\n");
+	}
+
 	if (disable_tracing)
 		ftrace_kill();
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 229f8591f61d..092e1f8d18dc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -2,7 +2,7 @@
 #define _LINUX_KERNEL_TRACE_H
 
 #include <linux/fs.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/sched.h>
 #include <linux/clocksource.h>
 #include <linux/ring_buffer.h>
@@ -278,6 +278,29 @@ struct tracer {
 };
 
 
+/* Only current can touch trace_recursion */
+#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
+#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
+
+/* Ring buffer has the 10 LSB bits to count */
+#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
+
+/* for function tracing recursion */
+#define TRACE_INTERNAL_BIT		(1<<11)
+#define TRACE_GLOBAL_BIT		(1<<12)
+/*
+ * Abuse of the trace_recursion.
+ * As we need a way to maintain state if we are tracing the function
+ * graph in irq because we want to trace a particular function that
+ * was called in irq context but we have irq tracing off. Since this
+ * can only be modified by current, we can reuse trace_recursion.
+ */
+#define TRACE_IRQ_BIT			(1<<13)
+
+#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
+#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
+#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
+
 #define TRACE_PIPE_ALL_CPU	-1
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
@@ -389,6 +412,9 @@ void update_max_tr_single(struct trace_array *tr,
 void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
 			int skip, int pc);
 
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+			     int skip, int pc, struct pt_regs *regs);
+
 void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
 			    int pc);
 
@@ -400,6 +426,12 @@ static inline void ftrace_trace_stack(struct ring_buffer *buffer,
 {
 }
 
+static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
+					   unsigned long flags, int skip,
+					   int pc, struct pt_regs *regs)
+{
+}
+
 static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
 					  unsigned long flags, int pc)
 {
@@ -507,8 +539,18 @@ static inline int ftrace_graph_addr(unsigned long addr)
 		return 1;
 
 	for (i = 0; i < ftrace_graph_count; i++) {
-		if (addr == ftrace_graph_funcs[i])
+		if (addr == ftrace_graph_funcs[i]) {
+			/*
+			 * If no irqs are to be traced, but a set_graph_function
+			 * is set, and called by an interrupt handler, we still
+			 * want to trace it.
+			 */
+			if (in_irq())
+				trace_recursion_set(TRACE_IRQ_BIT);
+			else
+				trace_recursion_clear(TRACE_IRQ_BIT);
 			return 1;
+		}
 	}
 
 	return 0;
@@ -537,11 +579,13 @@ static inline int ftrace_trace_task(struct task_struct *task)
 
 	return test_tsk_trace_trace(task);
 }
+extern int ftrace_is_dead(void);
 #else
 static inline int ftrace_trace_task(struct task_struct *task)
 {
 	return 1;
 }
+static inline int ftrace_is_dead(void) { return 0; }
 #endif
 
 /*
@@ -609,6 +653,7 @@ enum trace_iterator_flags {
 	TRACE_ITER_GRAPH_TIME		= 0x80000,
 	TRACE_ITER_RECORD_CMD		= 0x100000,
 	TRACE_ITER_OVERWRITE		= 0x200000,
+	TRACE_ITER_STOP_ON_FREE		= 0x400000,
 };
 
 /*
@@ -677,6 +722,7 @@ struct event_subsystem {
 	struct dentry		*entry;
 	struct event_filter	*filter;
 	int			nr_events;
+	int			ref_count;
 };
 
 #define FILTER_PRED_INVALID	((unsigned short)-1)
@@ -717,16 +763,10 @@ struct filter_pred {
 	filter_pred_fn_t 	fn;
 	u64 			val;
 	struct regex		regex;
-	/*
-	 * Leaf nodes use field_name, ops is used by AND and OR
-	 * nodes. The field_name is always freed when freeing a pred.
-	 * We can overload field_name for ops and have it freed
-	 * as well.
-	 */
-	union {
-		char		*field_name;
-		unsigned short	*ops;
-	};
+	unsigned short		*ops;
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+	struct ftrace_event_field *field;
+#endif
 	int 			offset;
 	int 			not;
 	int 			op;
@@ -784,19 +824,4 @@ extern const char *__stop___trace_bprintk_fmt[];
 	FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
 #include "trace_entries.h"
 
-/* Only current can touch trace_recursion */
-#define trace_recursion_inc() do { (current)->trace_recursion++; } while (0)
-#define trace_recursion_dec() do { (current)->trace_recursion--; } while (0)
-
-/* Ring buffer has the 10 LSB bits to count */
-#define trace_recursion_buffer() ((current)->trace_recursion & 0x3ff)
-
-/* for function tracing recursion */
-#define TRACE_INTERNAL_BIT		(1<<11)
-#define TRACE_GLOBAL_BIT		(1<<12)
-
-#define trace_recursion_set(bit)	do { (current)->trace_recursion |= (bit); } while (0)
-#define trace_recursion_clear(bit)	do { (current)->trace_recursion &= ~(bit); } while (0)
-#define trace_recursion_test(bit)	((current)->trace_recursion & (bit))
-
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 6302747a1398..394783531cbb 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -113,3 +113,15 @@ u64 notrace trace_clock_global(void)
 
 	return now;
 }
+
+static atomic64_t trace_counter;
+
+/*
+ * trace_clock_counter(): simply an atomic counter.
+ * Use the trace_counter "counter" for cases where you do not care
+ * about timings, but are interested in strict ordering.
+ */
+u64 notrace trace_clock_counter(void)
+{
+	return atomic64_add_return(1, &trace_counter);
+}
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e32744c84d94..93365907f219 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -161,7 +161,8 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
 	TRACE_STACK,
 
 	F_STRUCT(
-		__array(	unsigned long,	caller, FTRACE_STACK_ENTRIES	)
+		__field(	int,		size	)
+		__dynamic_array(unsigned long,	caller	)
 	),
 
 	F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 686ec399f2a8..581876f9f387 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -244,6 +244,35 @@ static void ftrace_clear_events(void)
 	mutex_unlock(&event_mutex);
 }
 
+static void __put_system(struct event_subsystem *system)
+{
+	struct event_filter *filter = system->filter;
+
+	WARN_ON_ONCE(system->ref_count == 0);
+	if (--system->ref_count)
+		return;
+
+	if (filter) {
+		kfree(filter->filter_string);
+		kfree(filter);
+	}
+	kfree(system->name);
+	kfree(system);
+}
+
+static void __get_system(struct event_subsystem *system)
+{
+	WARN_ON_ONCE(system->ref_count == 0);
+	system->ref_count++;
+}
+
+static void put_system(struct event_subsystem *system)
+{
+	mutex_lock(&event_mutex);
+	__put_system(system);
+	mutex_unlock(&event_mutex);
+}
+
 /*
  * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
  */
@@ -486,20 +515,11 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
 	struct ftrace_event_call *call = filp->private_data;
-	char buf[64];
 	unsigned long val;
 	int ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	ret = tracing_update_buffers();
@@ -528,7 +548,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		   loff_t *ppos)
 {
 	const char set_to_char[4] = { '?', '0', '1', 'X' };
-	const char *system = filp->private_data;
+	struct event_subsystem *system = filp->private_data;
 	struct ftrace_event_call *call;
 	char buf[2];
 	int set = 0;
@@ -539,7 +559,7 @@ system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 		if (!call->name || !call->class || !call->class->reg)
 			continue;
 
-		if (system && strcmp(call->class->system, system) != 0)
+		if (system && strcmp(call->class->system, system->name) != 0)
 			continue;
 
 		/*
@@ -569,21 +589,13 @@ static ssize_t
 system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 		    loff_t *ppos)
 {
-	const char *system = filp->private_data;
+	struct event_subsystem *system = filp->private_data;
+	const char *name = NULL;
 	unsigned long val;
-	char buf[64];
 	ssize_t ret;
 
-	if (cnt >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+	if (ret)
 		return ret;
 
 	ret = tracing_update_buffers();
@@ -593,7 +605,14 @@ system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	if (val != 0 && val != 1)
 		return -EINVAL;
 
-	ret = __ftrace_set_clr_event(NULL, system, NULL, val);
+	/*
+	 * Opening of "enable" adds a ref count to system,
+	 * so the name is safe to use.
+	 */
+	if (system)
+		name = system->name;
+
+	ret = __ftrace_set_clr_event(NULL, name, NULL, val);
 	if (ret)
 		goto out;
 
@@ -826,6 +845,52 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
 	return cnt;
 }
 
+static LIST_HEAD(event_subsystems);
+
+static int subsystem_open(struct inode *inode, struct file *filp)
+{
+	struct event_subsystem *system = NULL;
+	int ret;
+
+	if (!inode->i_private)
+		goto skip_search;
+
+	/* Make sure the system still exists */
+	mutex_lock(&event_mutex);
+	list_for_each_entry(system, &event_subsystems, list) {
+		if (system == inode->i_private) {
+			/* Don't open systems with no events */
+			if (!system->nr_events) {
+				system = NULL;
+				break;
+			}
+			__get_system(system);
+			break;
+		}
+	}
+	mutex_unlock(&event_mutex);
+
+	if (system != inode->i_private)
+		return -ENODEV;
+
+ skip_search:
+	ret = tracing_open_generic(inode, filp);
+	if (ret < 0 && system)
+		put_system(system);
+
+	return ret;
+}
+
+static int subsystem_release(struct inode *inode, struct file *file)
+{
+	struct event_subsystem *system = inode->i_private;
+
+	if (system)
+		put_system(system);
+
+	return 0;
+}
+
 static ssize_t
 subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
 		      loff_t *ppos)
@@ -963,17 +1028,19 @@ static const struct file_operations ftrace_event_filter_fops = {
 };
 
 static const struct file_operations ftrace_subsystem_filter_fops = {
-	.open = tracing_open_generic,
+	.open = subsystem_open,
 	.read = subsystem_filter_read,
 	.write = subsystem_filter_write,
 	.llseek = default_llseek,
+	.release = subsystem_release,
 };
 
 static const struct file_operations ftrace_system_enable_fops = {
-	.open = tracing_open_generic,
+	.open = subsystem_open,
 	.read = system_enable_read,
 	.write = system_enable_write,
 	.llseek = default_llseek,
+	.release = subsystem_release,
 };
 
 static const struct file_operations ftrace_show_header_fops = {
@@ -1002,8 +1069,6 @@ static struct dentry *event_trace_events_dir(void)
 	return d_events;
 }
 
-static LIST_HEAD(event_subsystems);
-
 static struct dentry *
 event_subsystem_dir(const char *name, struct dentry *d_events)
 {
@@ -1013,6 +1078,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
+			__get_system(system);
 			system->nr_events++;
 			return system->entry;
 		}
@@ -1035,6 +1101,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	}
 
 	system->nr_events = 1;
+	system->ref_count = 1;
 	system->name = kstrdup(name, GFP_KERNEL);
 	if (!system->name) {
 		debugfs_remove(system->entry);
@@ -1062,8 +1129,7 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 			   "'%s/filter' entry\n", name);
 	}
 
-	trace_create_file("enable", 0644, system->entry,
-			  (void *)system->name,
+	trace_create_file("enable", 0644, system->entry, system,
 			  &ftrace_system_enable_fops);
 
 	return system->entry;
@@ -1184,16 +1250,9 @@ static void remove_subsystem_dir(const char *name)
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
 			if (!--system->nr_events) {
-				struct event_filter *filter = system->filter;
-
 				debugfs_remove_recursive(system->entry);
 				list_del(&system->list);
-				if (filter) {
-					kfree(filter->filter_string);
-					kfree(filter);
-				}
-				kfree(system->name);
-				kfree(system);
+				__put_system(system);
 			}
 			break;
 		}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 8008ddcfbf20..816d3d074979 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -381,6 +381,63 @@ get_pred_parent(struct filter_pred *pred, struct filter_pred *preds,
 	return pred;
 }
 
+enum walk_return {
+	WALK_PRED_ABORT,
+	WALK_PRED_PARENT,
+	WALK_PRED_DEFAULT,
+};
+
+typedef int (*filter_pred_walkcb_t) (enum move_type move,
+				     struct filter_pred *pred,
+				     int *err, void *data);
+
+static int walk_pred_tree(struct filter_pred *preds,
+			  struct filter_pred *root,
+			  filter_pred_walkcb_t cb, void *data)
+{
+	struct filter_pred *pred = root;
+	enum move_type move = MOVE_DOWN;
+	int done = 0;
+
+	if  (!preds)
+		return -EINVAL;
+
+	do {
+		int err = 0, ret;
+
+		ret = cb(move, pred, &err, data);
+		if (ret == WALK_PRED_ABORT)
+			return err;
+		if (ret == WALK_PRED_PARENT)
+			goto get_parent;
+
+		switch (move) {
+		case MOVE_DOWN:
+			if (pred->left != FILTER_PRED_INVALID) {
+				pred = &preds[pred->left];
+				continue;
+			}
+			goto get_parent;
+		case MOVE_UP_FROM_LEFT:
+			pred = &preds[pred->right];
+			move = MOVE_DOWN;
+			continue;
+		case MOVE_UP_FROM_RIGHT:
+ get_parent:
+			if (pred == root)
+				break;
+			pred = get_pred_parent(pred, preds,
+					       pred->parent,
+					       &move);
+			continue;
+		}
+		done = 1;
+	} while (!done);
+
+	/* We are fine. */
+	return 0;
+}
+
 /*
  * A series of AND or ORs where found together. Instead of
  * climbing up and down the tree branches, an array of the
@@ -410,99 +467,91 @@ static int process_ops(struct filter_pred *preds,
 
 	for (i = 0; i < op->val; i++) {
 		pred = &preds[op->ops[i]];
-		match = pred->fn(pred, rec);
+		if (!WARN_ON_ONCE(!pred->fn))
+			match = pred->fn(pred, rec);
 		if (!!match == type)
 			return match;
 	}
 	return match;
 }
 
+struct filter_match_preds_data {
+	struct filter_pred *preds;
+	int match;
+	void *rec;
+};
+
+static int filter_match_preds_cb(enum move_type move, struct filter_pred *pred,
+				 int *err, void *data)
+{
+	struct filter_match_preds_data *d = data;
+
+	*err = 0;
+	switch (move) {
+	case MOVE_DOWN:
+		/* only AND and OR have children */
+		if (pred->left != FILTER_PRED_INVALID) {
+			/* If ops is set, then it was folded. */
+			if (!pred->ops)
+				return WALK_PRED_DEFAULT;
+			/* We can treat folded ops as a leaf node */
+			d->match = process_ops(d->preds, pred, d->rec);
+		} else {
+			if (!WARN_ON_ONCE(!pred->fn))
+				d->match = pred->fn(pred, d->rec);
+		}
+
+		return WALK_PRED_PARENT;
+	case MOVE_UP_FROM_LEFT:
+		/*
+		 * Check for short circuits.
+		 *
+		 * Optimization: !!match == (pred->op == OP_OR)
+		 *   is the same as:
+		 * if ((match && pred->op == OP_OR) ||
+		 *     (!match && pred->op == OP_AND))
+		 */
+		if (!!d->match == (pred->op == OP_OR))
+			return WALK_PRED_PARENT;
+		break;
+	case MOVE_UP_FROM_RIGHT:
+		break;
+	}
+
+	return WALK_PRED_DEFAULT;
+}
+
 /* return 1 if event matches, 0 otherwise (discard) */
 int filter_match_preds(struct event_filter *filter, void *rec)
 {
-	int match = -1;
-	enum move_type move = MOVE_DOWN;
 	struct filter_pred *preds;
-	struct filter_pred *pred;
 	struct filter_pred *root;
-	int n_preds;
-	int done = 0;
+	struct filter_match_preds_data data = {
+		/* match is currently meaningless */
+		.match = -1,
+		.rec   = rec,
+	};
+	int n_preds, ret;
 
 	/* no filter is considered a match */
 	if (!filter)
 		return 1;
 
 	n_preds = filter->n_preds;
-
 	if (!n_preds)
 		return 1;
 
 	/*
 	 * n_preds, root and filter->preds are protect with preemption disabled.
 	 */
-	preds = rcu_dereference_sched(filter->preds);
 	root = rcu_dereference_sched(filter->root);
 	if (!root)
 		return 1;
 
-	pred = root;
-
-	/* match is currently meaningless */
-	match = -1;
-
-	do {
-		switch (move) {
-		case MOVE_DOWN:
-			/* only AND and OR have children */
-			if (pred->left != FILTER_PRED_INVALID) {
-				/* If ops is set, then it was folded. */
-				if (!pred->ops) {
-					/* keep going to down the left side */
-					pred = &preds[pred->left];
-					continue;
-				}
-				/* We can treat folded ops as a leaf node */
-				match = process_ops(preds, pred, rec);
-			} else
-				match = pred->fn(pred, rec);
-			/* If this pred is the only pred */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			/*
-			 * Check for short circuits.
-			 *
-			 * Optimization: !!match == (pred->op == OP_OR)
-			 *   is the same as:
-			 * if ((match && pred->op == OP_OR) ||
-			 *     (!match && pred->op == OP_AND))
-			 */
-			if (!!match == (pred->op == OP_OR)) {
-				if (pred == root)
-					break;
-				pred = get_pred_parent(pred, preds,
-						       pred->parent, &move);
-				continue;
-			}
-			/* now go down the right side of the tree. */
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			/* We finished this equation. */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
-
-	return match;
+	data.preds = preds = rcu_dereference_sched(filter->preds);
+	ret = walk_pred_tree(preds, root, filter_match_preds_cb, &data);
+	WARN_ON(ret);
+	return data.match;
 }
 EXPORT_SYMBOL_GPL(filter_match_preds);
 
@@ -628,22 +677,6 @@ find_event_field(struct ftrace_event_call *call, char *name)
 	return __find_event_field(head, name);
 }
 
-static void filter_free_pred(struct filter_pred *pred)
-{
-	if (!pred)
-		return;
-
-	kfree(pred->field_name);
-	kfree(pred);
-}
-
-static void filter_clear_pred(struct filter_pred *pred)
-{
-	kfree(pred->field_name);
-	pred->field_name = NULL;
-	pred->regex.len = 0;
-}
-
 static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
 {
 	stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
@@ -689,20 +722,13 @@ __pop_pred_stack(struct pred_stack *stack)
 static int filter_set_pred(struct event_filter *filter,
 			   int idx,
 			   struct pred_stack *stack,
-			   struct filter_pred *src,
-			   filter_pred_fn_t fn)
+			   struct filter_pred *src)
 {
 	struct filter_pred *dest = &filter->preds[idx];
 	struct filter_pred *left;
 	struct filter_pred *right;
 
 	*dest = *src;
-	if (src->field_name) {
-		dest->field_name = kstrdup(src->field_name, GFP_KERNEL);
-		if (!dest->field_name)
-			return -ENOMEM;
-	}
-	dest->fn = fn;
 	dest->index = idx;
 
 	if (dest->op == OP_OR || dest->op == OP_AND) {
@@ -743,11 +769,7 @@ static int filter_set_pred(struct event_filter *filter,
 
 static void __free_preds(struct event_filter *filter)
 {
-	int i;
-
 	if (filter->preds) {
-		for (i = 0; i < filter->a_preds; i++)
-			kfree(filter->preds[i].field_name);
 		kfree(filter->preds);
 		filter->preds = NULL;
 	}
@@ -840,23 +862,19 @@ static void filter_free_subsystem_filters(struct event_subsystem *system)
 	}
 }
 
-static int filter_add_pred_fn(struct filter_parse_state *ps,
-			      struct ftrace_event_call *call,
-			      struct event_filter *filter,
-			      struct filter_pred *pred,
-			      struct pred_stack *stack,
-			      filter_pred_fn_t fn)
+static int filter_add_pred(struct filter_parse_state *ps,
+			   struct event_filter *filter,
+			   struct filter_pred *pred,
+			   struct pred_stack *stack)
 {
-	int idx, err;
+	int err;
 
 	if (WARN_ON(filter->n_preds == filter->a_preds)) {
 		parse_error(ps, FILT_ERR_TOO_MANY_PREDS, 0);
 		return -ENOSPC;
 	}
 
-	idx = filter->n_preds;
-	filter_clear_pred(&filter->preds[idx]);
-	err = filter_set_pred(filter, idx, stack, pred, fn);
+	err = filter_set_pred(filter, filter->n_preds, stack, pred);
 	if (err)
 		return err;
 
@@ -937,31 +955,15 @@ static filter_pred_fn_t select_comparison_fn(int op, int field_size,
 	return fn;
 }
 
-static int filter_add_pred(struct filter_parse_state *ps,
-			   struct ftrace_event_call *call,
-			   struct event_filter *filter,
-			   struct filter_pred *pred,
-			   struct pred_stack *stack,
-			   bool dry_run)
+static int init_pred(struct filter_parse_state *ps,
+		     struct ftrace_event_field *field,
+		     struct filter_pred *pred)
+
 {
-	struct ftrace_event_field *field;
-	filter_pred_fn_t fn;
+	filter_pred_fn_t fn = filter_pred_none;
 	unsigned long long val;
 	int ret;
 
-	fn = pred->fn = filter_pred_none;
-
-	if (pred->op == OP_AND)
-		goto add_pred_fn;
-	else if (pred->op == OP_OR)
-		goto add_pred_fn;
-
-	field = find_event_field(call, pred->field_name);
-	if (!field) {
-		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
-		return -EINVAL;
-	}
-
 	pred->offset = field->offset;
 
 	if (!is_legal_op(field, pred->op)) {
@@ -1001,9 +1003,7 @@ static int filter_add_pred(struct filter_parse_state *ps,
 	if (pred->op == OP_NE)
 		pred->not = 1;
 
-add_pred_fn:
-	if (!dry_run)
-		return filter_add_pred_fn(ps, call, filter, pred, stack, fn);
+	pred->fn = fn;
 	return 0;
 }
 
@@ -1302,39 +1302,37 @@ parse_operand:
 	return 0;
 }
 
-static struct filter_pred *create_pred(int op, char *operand1, char *operand2)
+static struct filter_pred *create_pred(struct filter_parse_state *ps,
+				       struct ftrace_event_call *call,
+				       int op, char *operand1, char *operand2)
 {
-	struct filter_pred *pred;
+	struct ftrace_event_field *field;
+	static struct filter_pred pred;
 
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
-		return NULL;
+	memset(&pred, 0, sizeof(pred));
+	pred.op = op;
+
+	if (op == OP_AND || op == OP_OR)
+		return &pred;
 
-	pred->field_name = kstrdup(operand1, GFP_KERNEL);
-	if (!pred->field_name) {
-		kfree(pred);
+	if (!operand1 || !operand2) {
+		parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
 		return NULL;
 	}
 
-	strcpy(pred->regex.pattern, operand2);
-	pred->regex.len = strlen(pred->regex.pattern);
-
-	pred->op = op;
-
-	return pred;
-}
-
-static struct filter_pred *create_logical_pred(int op)
-{
-	struct filter_pred *pred;
-
-	pred = kzalloc(sizeof(*pred), GFP_KERNEL);
-	if (!pred)
+	field = find_event_field(call, operand1);
+	if (!field) {
+		parse_error(ps, FILT_ERR_FIELD_NOT_FOUND, 0);
 		return NULL;
+	}
 
-	pred->op = op;
+	strcpy(pred.regex.pattern, operand2);
+	pred.regex.len = strlen(pred.regex.pattern);
 
-	return pred;
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+	pred.field = field;
+#endif
+	return init_pred(ps, field, &pred) ? NULL : &pred;
 }
 
 static int check_preds(struct filter_parse_state *ps)
@@ -1375,6 +1373,23 @@ static int count_preds(struct filter_parse_state *ps)
 	return n_preds;
 }
 
+struct check_pred_data {
+	int count;
+	int max;
+};
+
+static int check_pred_tree_cb(enum move_type move, struct filter_pred *pred,
+			      int *err, void *data)
+{
+	struct check_pred_data *d = data;
+
+	if (WARN_ON(d->count++ > d->max)) {
+		*err = -EINVAL;
+		return WALK_PRED_ABORT;
+	}
+	return WALK_PRED_DEFAULT;
+}
+
 /*
  * The tree is walked at filtering of an event. If the tree is not correctly
  * built, it may cause an infinite loop. Check here that the tree does
@@ -1383,107 +1398,76 @@ static int count_preds(struct filter_parse_state *ps)
 static int check_pred_tree(struct event_filter *filter,
 			   struct filter_pred *root)
 {
-	struct filter_pred *preds;
-	struct filter_pred *pred;
-	enum move_type move = MOVE_DOWN;
-	int count = 0;
-	int done = 0;
-	int max;
-
-	/*
-	 * The max that we can hit a node is three times.
-	 * Once going down, once coming up from left, and
-	 * once coming up from right. This is more than enough
-	 * since leafs are only hit a single time.
-	 */
-	max = 3 * filter->n_preds;
+	struct check_pred_data data = {
+		/*
+		 * The max that we can hit a node is three times.
+		 * Once going down, once coming up from left, and
+		 * once coming up from right. This is more than enough
+		 * since leafs are only hit a single time.
+		 */
+		.max   = 3 * filter->n_preds,
+		.count = 0,
+	};
 
-	preds = filter->preds;
-	if  (!preds)
-		return -EINVAL;
-	pred = root;
+	return walk_pred_tree(filter->preds, root,
+			      check_pred_tree_cb, &data);
+}
 
-	do {
-		if (WARN_ON(count++ > max))
-			return -EINVAL;
+static int count_leafs_cb(enum move_type move, struct filter_pred *pred,
+			  int *err, void *data)
+{
+	int *count = data;
 
-		switch (move) {
-		case MOVE_DOWN:
-			if (pred->left != FILTER_PRED_INVALID) {
-				pred = &preds[pred->left];
-				continue;
-			}
-			/* A leaf at the root is just a leaf in the tree */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
+	if ((move == MOVE_DOWN) &&
+	    (pred->left == FILTER_PRED_INVALID))
+		(*count)++;
 
-	/* We are fine. */
-	return 0;
+	return WALK_PRED_DEFAULT;
 }
 
 static int count_leafs(struct filter_pred *preds, struct filter_pred *root)
 {
-	struct filter_pred *pred;
-	enum move_type move = MOVE_DOWN;
-	int count = 0;
-	int done = 0;
+	int count = 0, ret;
 
-	pred = root;
+	ret = walk_pred_tree(preds, root, count_leafs_cb, &count);
+	WARN_ON(ret);
+	return count;
+}
 
-	do {
-		switch (move) {
-		case MOVE_DOWN:
-			if (pred->left != FILTER_PRED_INVALID) {
-				pred = &preds[pred->left];
-				continue;
-			}
-			/* A leaf at the root is just a leaf in the tree */
-			if (pred == root)
-				return 1;
-			count++;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
+struct fold_pred_data {
+	struct filter_pred *root;
+	int count;
+	int children;
+};
 
-	return count;
+static int fold_pred_cb(enum move_type move, struct filter_pred *pred,
+			int *err, void *data)
+{
+	struct fold_pred_data *d = data;
+	struct filter_pred *root = d->root;
+
+	if (move != MOVE_DOWN)
+		return WALK_PRED_DEFAULT;
+	if (pred->left != FILTER_PRED_INVALID)
+		return WALK_PRED_DEFAULT;
+
+	if (WARN_ON(d->count == d->children)) {
+		*err = -EINVAL;
+		return WALK_PRED_ABORT;
+	}
+
+	pred->index &= ~FILTER_PRED_FOLD;
+	root->ops[d->count++] = pred->index;
+	return WALK_PRED_DEFAULT;
 }
 
 static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
 {
-	struct filter_pred *pred;
-	enum move_type move = MOVE_DOWN;
-	int count = 0;
+	struct fold_pred_data data = {
+		.root  = root,
+		.count = 0,
+	};
 	int children;
-	int done = 0;
 
 	/* No need to keep the fold flag */
 	root->index &= ~FILTER_PRED_FOLD;
@@ -1501,37 +1485,26 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
 		return -ENOMEM;
 
 	root->val = children;
+	data.children = children;
+	return walk_pred_tree(preds, root, fold_pred_cb, &data);
+}
 
-	pred = root;
-	do {
-		switch (move) {
-		case MOVE_DOWN:
-			if (pred->left != FILTER_PRED_INVALID) {
-				pred = &preds[pred->left];
-				continue;
-			}
-			if (WARN_ON(count == children))
-				return -EINVAL;
-			pred->index &= ~FILTER_PRED_FOLD;
-			root->ops[count++] = pred->index;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
+static int fold_pred_tree_cb(enum move_type move, struct filter_pred *pred,
+			     int *err, void *data)
+{
+	struct filter_pred *preds = data;
 
-	return 0;
+	if (move != MOVE_DOWN)
+		return WALK_PRED_DEFAULT;
+	if (!(pred->index & FILTER_PRED_FOLD))
+		return WALK_PRED_DEFAULT;
+
+	*err = fold_pred(preds, pred);
+	if (*err)
+		return WALK_PRED_ABORT;
+
+	/* eveyrhing below is folded, continue with parent */
+	return WALK_PRED_PARENT;
 }
 
 /*
@@ -1542,51 +1515,8 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
 static int fold_pred_tree(struct event_filter *filter,
 			   struct filter_pred *root)
 {
-	struct filter_pred *preds;
-	struct filter_pred *pred;
-	enum move_type move = MOVE_DOWN;
-	int done = 0;
-	int err;
-
-	preds = filter->preds;
-	if  (!preds)
-		return -EINVAL;
-	pred = root;
-
-	do {
-		switch (move) {
-		case MOVE_DOWN:
-			if (pred->index & FILTER_PRED_FOLD) {
-				err = fold_pred(preds, pred);
-				if (err)
-					return err;
-				/* Folded nodes are like leafs */
-			} else if (pred->left != FILTER_PRED_INVALID) {
-				pred = &preds[pred->left];
-				continue;
-			}
-
-			/* A leaf at the root is just a leaf in the tree */
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		case MOVE_UP_FROM_LEFT:
-			pred = &preds[pred->right];
-			move = MOVE_DOWN;
-			continue;
-		case MOVE_UP_FROM_RIGHT:
-			if (pred == root)
-				break;
-			pred = get_pred_parent(pred, preds,
-					       pred->parent, &move);
-			continue;
-		}
-		done = 1;
-	} while (!done);
-
-	return 0;
+	return walk_pred_tree(filter->preds, root, fold_pred_tree_cb,
+			      filter->preds);
 }
 
 static int replace_preds(struct ftrace_event_call *call,
@@ -1643,27 +1573,17 @@ static int replace_preds(struct ftrace_event_call *call,
 			goto fail;
 		}
 
-		if (elt->op == OP_AND || elt->op == OP_OR) {
-			pred = create_logical_pred(elt->op);
-			goto add_pred;
-		}
-
-		if (!operand1 || !operand2) {
-			parse_error(ps, FILT_ERR_MISSING_FIELD, 0);
+		pred = create_pred(ps, call, elt->op, operand1, operand2);
+		if (!pred) {
 			err = -EINVAL;
 			goto fail;
 		}
 
-		pred = create_pred(elt->op, operand1, operand2);
-add_pred:
-		if (!pred) {
-			err = -ENOMEM;
-			goto fail;
+		if (!dry_run) {
+			err = filter_add_pred(ps, filter, pred, &stack);
+			if (err)
+				goto fail;
 		}
-		err = filter_add_pred(ps, call, filter, pred, &stack, dry_run);
-		filter_free_pred(pred);
-		if (err)
-			goto fail;
 
 		operand1 = operand2 = NULL;
 	}
@@ -1886,6 +1806,12 @@ int apply_subsystem_event_filter(struct event_subsystem *system,
 
 	mutex_lock(&event_mutex);
 
+	/* Make sure the system still has events */
+	if (!system->nr_events) {
+		err = -ENODEV;
+		goto out_unlock;
+	}
+
 	if (!strcmp(strstrip(filter_string), "0")) {
 		filter_free_subsystem_preds(system);
 		remove_filter_string(system->filter);
@@ -1952,17 +1878,14 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 	int err;
 	struct event_filter *filter;
 	struct filter_parse_state *ps;
-	struct ftrace_event_call *call = NULL;
+	struct ftrace_event_call *call;
 
 	mutex_lock(&event_mutex);
 
-	list_for_each_entry(call, &ftrace_events, list) {
-		if (call->event.type == event_id)
-			break;
-	}
+	call = event->tp_event;
 
 	err = -EINVAL;
-	if (&call->list == &ftrace_events)
+	if (!call)
 		goto out_unlock;
 
 	err = -EEXIST;
@@ -2006,3 +1929,215 @@ out_unlock:
 
 #endif /* CONFIG_PERF_EVENTS */
 
+#ifdef CONFIG_FTRACE_STARTUP_TEST
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#define CREATE_TRACE_POINTS
+#include "trace_events_filter_test.h"
+
+static int test_get_filter(char *filter_str, struct ftrace_event_call *call,
+			   struct event_filter **pfilter)
+{
+	struct event_filter *filter;
+	struct filter_parse_state *ps;
+	int err = -ENOMEM;
+
+	filter = __alloc_filter();
+	if (!filter)
+		goto out;
+
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
+	if (!ps)
+		goto free_filter;
+
+	parse_init(ps, filter_ops, filter_str);
+	err = filter_parse(ps);
+	if (err)
+		goto free_ps;
+
+	err = replace_preds(call, filter, ps, filter_str, false);
+	if (!err)
+		*pfilter = filter;
+
+ free_ps:
+	filter_opstack_clear(ps);
+	postfix_clear(ps);
+	kfree(ps);
+
+ free_filter:
+	if (err)
+		__free_filter(filter);
+
+ out:
+	return err;
+}
+
+#define DATA_REC(m, va, vb, vc, vd, ve, vf, vg, vh, nvisit) \
+{ \
+	.filter = FILTER, \
+	.rec    = { .a = va, .b = vb, .c = vc, .d = vd, \
+		    .e = ve, .f = vf, .g = vg, .h = vh }, \
+	.match  = m, \
+	.not_visited = nvisit, \
+}
+#define YES 1
+#define NO  0
+
+static struct test_filter_data_t {
+	char *filter;
+	struct ftrace_raw_ftrace_test_filter rec;
+	int match;
+	char *not_visited;
+} test_filter_data[] = {
+#define FILTER "a == 1 && b == 1 && c == 1 && d == 1 && " \
+	       "e == 1 && f == 1 && g == 1 && h == 1"
+	DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, ""),
+	DATA_REC(NO,  0, 1, 1, 1, 1, 1, 1, 1, "bcdefgh"),
+	DATA_REC(NO,  1, 1, 1, 1, 1, 1, 1, 0, ""),
+#undef FILTER
+#define FILTER "a == 1 || b == 1 || c == 1 || d == 1 || " \
+	       "e == 1 || f == 1 || g == 1 || h == 1"
+	DATA_REC(NO,  0, 0, 0, 0, 0, 0, 0, 0, ""),
+	DATA_REC(YES, 0, 0, 0, 0, 0, 0, 0, 1, ""),
+	DATA_REC(YES, 1, 0, 0, 0, 0, 0, 0, 0, "bcdefgh"),
+#undef FILTER
+#define FILTER "(a == 1 || b == 1) && (c == 1 || d == 1) && " \
+	       "(e == 1 || f == 1) && (g == 1 || h == 1)"
+	DATA_REC(NO,  0, 0, 1, 1, 1, 1, 1, 1, "dfh"),
+	DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""),
+	DATA_REC(YES, 1, 0, 1, 0, 0, 1, 0, 1, "bd"),
+	DATA_REC(NO,  1, 0, 1, 0, 0, 1, 0, 0, "bd"),
+#undef FILTER
+#define FILTER "(a == 1 && b == 1) || (c == 1 && d == 1) || " \
+	       "(e == 1 && f == 1) || (g == 1 && h == 1)"
+	DATA_REC(YES, 1, 0, 1, 1, 1, 1, 1, 1, "efgh"),
+	DATA_REC(YES, 0, 0, 0, 0, 0, 0, 1, 1, ""),
+	DATA_REC(NO,  0, 0, 0, 0, 0, 0, 0, 1, ""),
+#undef FILTER
+#define FILTER "(a == 1 && b == 1) && (c == 1 && d == 1) && " \
+	       "(e == 1 && f == 1) || (g == 1 && h == 1)"
+	DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 0, "gh"),
+	DATA_REC(NO,  0, 0, 0, 0, 0, 0, 0, 1, ""),
+	DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, ""),
+#undef FILTER
+#define FILTER "((a == 1 || b == 1) || (c == 1 || d == 1) || " \
+	       "(e == 1 || f == 1)) && (g == 1 || h == 1)"
+	DATA_REC(YES, 1, 1, 1, 1, 1, 1, 0, 1, "bcdef"),
+	DATA_REC(NO,  0, 0, 0, 0, 0, 0, 0, 0, ""),
+	DATA_REC(YES, 1, 1, 1, 1, 1, 0, 1, 1, "h"),
+#undef FILTER
+#define FILTER "((((((((a == 1) && (b == 1)) || (c == 1)) && (d == 1)) || " \
+	       "(e == 1)) && (f == 1)) || (g == 1)) && (h == 1))"
+	DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "ceg"),
+	DATA_REC(NO,  0, 1, 0, 1, 0, 1, 0, 1, ""),
+	DATA_REC(NO,  1, 0, 1, 0, 1, 0, 1, 0, ""),
+#undef FILTER
+#define FILTER "((((((((a == 1) || (b == 1)) && (c == 1)) || (d == 1)) && " \
+	       "(e == 1)) || (f == 1)) && (g == 1)) || (h == 1))"
+	DATA_REC(YES, 1, 1, 1, 1, 1, 1, 1, 1, "bdfh"),
+	DATA_REC(YES, 0, 1, 0, 1, 0, 1, 0, 1, ""),
+	DATA_REC(YES, 1, 0, 1, 0, 1, 0, 1, 0, "bdfh"),
+};
+
+#undef DATA_REC
+#undef FILTER
+#undef YES
+#undef NO
+
+#define DATA_CNT (sizeof(test_filter_data)/sizeof(struct test_filter_data_t))
+
+static int test_pred_visited;
+
+static int test_pred_visited_fn(struct filter_pred *pred, void *event)
+{
+	struct ftrace_event_field *field = pred->field;
+
+	test_pred_visited = 1;
+	printk(KERN_INFO "\npred visited %s\n", field->name);
+	return 1;
+}
+
+static int test_walk_pred_cb(enum move_type move, struct filter_pred *pred,
+			     int *err, void *data)
+{
+	char *fields = data;
+
+	if ((move == MOVE_DOWN) &&
+	    (pred->left == FILTER_PRED_INVALID)) {
+		struct ftrace_event_field *field = pred->field;
+
+		if (!field) {
+			WARN(1, "all leafs should have field defined");
+			return WALK_PRED_DEFAULT;
+		}
+		if (!strchr(fields, *field->name))
+			return WALK_PRED_DEFAULT;
+
+		WARN_ON(!pred->fn);
+		pred->fn = test_pred_visited_fn;
+	}
+	return WALK_PRED_DEFAULT;
+}
+
+static __init int ftrace_test_event_filter(void)
+{
+	int i;
+
+	printk(KERN_INFO "Testing ftrace filter: ");
+
+	for (i = 0; i < DATA_CNT; i++) {
+		struct event_filter *filter = NULL;
+		struct test_filter_data_t *d = &test_filter_data[i];
+		int err;
+
+		err = test_get_filter(d->filter, &event_ftrace_test_filter,
+				      &filter);
+		if (err) {
+			printk(KERN_INFO
+			       "Failed to get filter for '%s', err %d\n",
+			       d->filter, err);
+			break;
+		}
+
+		/*
+		 * The preemption disabling is not really needed for self
+		 * tests, but the rcu dereference will complain without it.
+		 */
+		preempt_disable();
+		if (*d->not_visited)
+			walk_pred_tree(filter->preds, filter->root,
+				       test_walk_pred_cb,
+				       d->not_visited);
+
+		test_pred_visited = 0;
+		err = filter_match_preds(filter, &d->rec);
+		preempt_enable();
+
+		__free_filter(filter);
+
+		if (test_pred_visited) {
+			printk(KERN_INFO
+			       "Failed, unwanted pred visited for filter %s\n",
+			       d->filter);
+			break;
+		}
+
+		if (err != d->match) {
+			printk(KERN_INFO
+			       "Failed to match filter '%s', expected %d\n",
+			       d->filter, d->match);
+			break;
+		}
+	}
+
+	if (i == DATA_CNT)
+		printk(KERN_CONT "OK\n");
+
+	return 0;
+}
+
+late_initcall(ftrace_test_event_filter);
+
+#endif /* CONFIG_FTRACE_STARTUP_TEST */
diff --git a/kernel/trace/trace_events_filter_test.h b/kernel/trace/trace_events_filter_test.h
new file mode 100644
index 000000000000..bfd4dba0d603
--- /dev/null
+++ b/kernel/trace/trace_events_filter_test.h
@@ -0,0 +1,50 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM test
+
+#if !defined(_TRACE_TEST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TEST_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(ftrace_test_filter,
+
+	TP_PROTO(int a, int b, int c, int d, int e, int f, int g, int h),
+
+	TP_ARGS(a, b, c, d, e, f, g, h),
+
+	TP_STRUCT__entry(
+		__field(int, a)
+		__field(int, b)
+		__field(int, c)
+		__field(int, d)
+		__field(int, e)
+		__field(int, f)
+		__field(int, g)
+		__field(int, h)
+	),
+
+	TP_fast_assign(
+		__entry->a = a;
+		__entry->b = b;
+		__entry->c = c;
+		__entry->d = d;
+		__entry->e = e;
+		__entry->f = f;
+		__entry->g = g;
+		__entry->h = h;
+	),
+
+	TP_printk("a %d, b %d, c %d, d %d, e %d, f %d, g %d, h %d",
+		  __entry->a, __entry->b, __entry->c, __entry->d,
+		  __entry->e, __entry->f, __entry->g, __entry->h)
+);
+
+#endif /* _TRACE_TEST_H || TRACE_HEADER_MULTI_READ */
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE trace_events_filter_test
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 8d0e1cc4e974..c7b0c6a7db09 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -324,7 +324,8 @@ ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
 }
 
 static int
-ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
+ftrace_trace_onoff_callback(struct ftrace_hash *hash,
+			    char *glob, char *cmd, char *param, int enable)
 {
 	struct ftrace_probe_ops *ops;
 	void *count = (void *)-1;
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 962cdb24ed81..a7d2a4c653d8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -74,6 +74,20 @@ static struct tracer_flags tracer_flags = {
 
 static struct trace_array *graph_array;
 
+/*
+ * DURATION column is being also used to display IRQ signs,
+ * following values are used by print_graph_irq and others
+ * to fill in space into DURATION column.
+ */
+enum {
+	DURATION_FILL_FULL  = -1,
+	DURATION_FILL_START = -2,
+	DURATION_FILL_END   = -3,
+};
+
+static enum print_line_t
+print_graph_duration(unsigned long long duration, struct trace_seq *s,
+		     u32 flags);
 
 /* Add a function return address to the trace stack on thread info.*/
 int
@@ -213,7 +227,7 @@ int __trace_graph_entry(struct trace_array *tr,
 
 static inline int ftrace_graph_ignore_irqs(void)
 {
-	if (!ftrace_graph_skip_irqs)
+	if (!ftrace_graph_skip_irqs || trace_recursion_test(TRACE_IRQ_BIT))
 		return 0;
 
 	return in_irq();
@@ -577,32 +591,6 @@ get_return_for_leaf(struct trace_iterator *iter,
 	return next;
 }
 
-/* Signal a overhead of time execution to the output */
-static int
-print_graph_overhead(unsigned long long duration, struct trace_seq *s,
-		     u32 flags)
-{
-	/* If duration disappear, we don't need anything */
-	if (!(flags & TRACE_GRAPH_PRINT_DURATION))
-		return 1;
-
-	/* Non nested entry or return */
-	if (duration == -1)
-		return trace_seq_printf(s, "  ");
-
-	if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
-		/* Duration exceeded 100 msecs */
-		if (duration > 100000ULL)
-			return trace_seq_printf(s, "! ");
-
-		/* Duration exceeded 10 msecs */
-		if (duration > 10000ULL)
-			return trace_seq_printf(s, "+ ");
-	}
-
-	return trace_seq_printf(s, "  ");
-}
-
 static int print_graph_abs_time(u64 t, struct trace_seq *s)
 {
 	unsigned long usecs_rem;
@@ -625,34 +613,36 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 		addr >= (unsigned long)__irqentry_text_end)
 		return TRACE_TYPE_UNHANDLED;
 
-	/* Absolute time */
-	if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
-		ret = print_graph_abs_time(iter->ts, s);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	if (trace_flags & TRACE_ITER_CONTEXT_INFO) {
+		/* Absolute time */
+		if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
+			ret = print_graph_abs_time(iter->ts, s);
+			if (!ret)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
 
-	/* Cpu */
-	if (flags & TRACE_GRAPH_PRINT_CPU) {
-		ret = print_graph_cpu(s, cpu);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+		/* Cpu */
+		if (flags & TRACE_GRAPH_PRINT_CPU) {
+			ret = print_graph_cpu(s, cpu);
+			if (ret == TRACE_TYPE_PARTIAL_LINE)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
 
-	/* Proc */
-	if (flags & TRACE_GRAPH_PRINT_PROC) {
-		ret = print_graph_proc(s, pid);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-		ret = trace_seq_printf(s, " | ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
+		/* Proc */
+		if (flags & TRACE_GRAPH_PRINT_PROC) {
+			ret = print_graph_proc(s, pid);
+			if (ret == TRACE_TYPE_PARTIAL_LINE)
+				return TRACE_TYPE_PARTIAL_LINE;
+			ret = trace_seq_printf(s, " | ");
+			if (!ret)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
 	}
 
 	/* No overhead */
-	ret = print_graph_overhead(-1, s, flags);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
+	ret = print_graph_duration(DURATION_FILL_START, s, flags);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
 
 	if (type == TRACE_GRAPH_ENT)
 		ret = trace_seq_printf(s, "==========>");
@@ -662,9 +652,10 @@ print_graph_irq(struct trace_iterator *iter, unsigned long addr,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Don't close the duration column if haven't one */
-	if (flags & TRACE_GRAPH_PRINT_DURATION)
-		trace_seq_printf(s, " |");
+	ret = print_graph_duration(DURATION_FILL_END, s, flags);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
+
 	ret = trace_seq_printf(s, "\n");
 
 	if (!ret)
@@ -716,9 +707,49 @@ trace_print_graph_duration(unsigned long long duration, struct trace_seq *s)
 }
 
 static enum print_line_t
-print_graph_duration(unsigned long long duration, struct trace_seq *s)
+print_graph_duration(unsigned long long duration, struct trace_seq *s,
+		     u32 flags)
 {
-	int ret;
+	int ret = -1;
+
+	if (!(flags & TRACE_GRAPH_PRINT_DURATION) ||
+	    !(trace_flags & TRACE_ITER_CONTEXT_INFO))
+			return TRACE_TYPE_HANDLED;
+
+	/* No real adata, just filling the column with spaces */
+	switch (duration) {
+	case DURATION_FILL_FULL:
+		ret = trace_seq_printf(s, "              |  ");
+		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+	case DURATION_FILL_START:
+		ret = trace_seq_printf(s, "  ");
+		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+	case DURATION_FILL_END:
+		ret = trace_seq_printf(s, " |");
+		return ret ? TRACE_TYPE_HANDLED : TRACE_TYPE_PARTIAL_LINE;
+	}
+
+	/* Signal a overhead of time execution to the output */
+	if (flags & TRACE_GRAPH_PRINT_OVERHEAD) {
+		/* Duration exceeded 100 msecs */
+		if (duration > 100000ULL)
+			ret = trace_seq_printf(s, "! ");
+		/* Duration exceeded 10 msecs */
+		else if (duration > 10000ULL)
+			ret = trace_seq_printf(s, "+ ");
+	}
+
+	/*
+	 * The -1 means we either did not exceed the duration tresholds
+	 * or we dont want to print out the overhead. Either way we need
+	 * to fill out the space.
+	 */
+	if (ret == -1)
+		ret = trace_seq_printf(s, "  ");
+
+	/* Catching here any failure happenned above */
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
 
 	ret = trace_print_graph_duration(duration, s);
 	if (ret != TRACE_TYPE_HANDLED)
@@ -767,18 +798,11 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 			cpu_data->enter_funcs[call->depth] = 0;
 	}
 
-	/* Overhead */
-	ret = print_graph_overhead(duration, s, flags);
-	if (!ret)
+	/* Overhead and duration */
+	ret = print_graph_duration(duration, s, flags);
+	if (ret == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Duration */
-	if (flags & TRACE_GRAPH_PRINT_DURATION) {
-		ret = print_graph_duration(duration, s);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
-
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
 		ret = trace_seq_printf(s, " ");
@@ -815,17 +839,10 @@ print_graph_entry_nested(struct trace_iterator *iter,
 			cpu_data->enter_funcs[call->depth] = call->func;
 	}
 
-	/* No overhead */
-	ret = print_graph_overhead(-1, s, flags);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	/* No time */
-	if (flags & TRACE_GRAPH_PRINT_DURATION) {
-		ret = trace_seq_printf(s, "            |  ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
 
 	/* Function */
 	for (i = 0; i < call->depth * TRACE_GRAPH_INDENT; i++) {
@@ -865,6 +882,9 @@ print_graph_prologue(struct trace_iterator *iter, struct trace_seq *s,
 			return TRACE_TYPE_PARTIAL_LINE;
 	}
 
+	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+		return 0;
+
 	/* Absolute time */
 	if (flags & TRACE_GRAPH_PRINT_ABS_TIME) {
 		ret = print_graph_abs_time(iter->ts, s);
@@ -1078,18 +1098,11 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
 	if (print_graph_prologue(iter, s, 0, 0, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Overhead */
-	ret = print_graph_overhead(duration, s, flags);
-	if (!ret)
+	/* Overhead and duration */
+	ret = print_graph_duration(duration, s, flags);
+	if (ret == TRACE_TYPE_PARTIAL_LINE)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Duration */
-	if (flags & TRACE_GRAPH_PRINT_DURATION) {
-		ret = print_graph_duration(duration, s);
-		if (ret == TRACE_TYPE_PARTIAL_LINE)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
-
 	/* Closing brace */
 	for (i = 0; i < trace->depth * TRACE_GRAPH_INDENT; i++) {
 		ret = trace_seq_printf(s, " ");
@@ -1146,17 +1159,10 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 	if (print_graph_prologue(iter, s, 0, 0, flags))
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* No overhead */
-	ret = print_graph_overhead(-1, s, flags);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	/* No time */
-	if (flags & TRACE_GRAPH_PRINT_DURATION) {
-		ret = trace_seq_printf(s, "            |  ");
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-	}
+	ret = print_graph_duration(DURATION_FILL_FULL, s, flags);
+	if (ret != TRACE_TYPE_HANDLED)
+		return ret;
 
 	/* Indentation */
 	if (depth > 0)
@@ -1207,7 +1213,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
 
 
 enum print_line_t
-__print_graph_function_flags(struct trace_iterator *iter, u32 flags)
+print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 {
 	struct ftrace_graph_ent_entry *field;
 	struct fgraph_data *data = iter->private;
@@ -1270,18 +1276,7 @@ __print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 static enum print_line_t
 print_graph_function(struct trace_iterator *iter)
 {
-	return __print_graph_function_flags(iter, tracer_flags.val);
-}
-
-enum print_line_t print_graph_function_flags(struct trace_iterator *iter,
-					     u32 flags)
-{
-	if (trace_flags & TRACE_ITER_LATENCY_FMT)
-		flags |= TRACE_GRAPH_PRINT_DURATION;
-	else
-		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
-
-	return __print_graph_function_flags(iter, flags);
+	return print_graph_function_flags(iter, tracer_flags.val);
 }
 
 static enum print_line_t
@@ -1309,8 +1304,7 @@ static void print_lat_header(struct seq_file *s, u32 flags)
 	seq_printf(s, "#%.*s / _----=> need-resched    \n", size, spaces);
 	seq_printf(s, "#%.*s| / _---=> hardirq/softirq \n", size, spaces);
 	seq_printf(s, "#%.*s|| / _--=> preempt-depth   \n", size, spaces);
-	seq_printf(s, "#%.*s||| / _-=> lock-depth      \n", size, spaces);
-	seq_printf(s, "#%.*s|||| /                     \n", size, spaces);
+	seq_printf(s, "#%.*s||| /                      \n", size, spaces);
 }
 
 static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
@@ -1329,7 +1323,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_printf(s, "  TASK/PID       ");
 	if (lat)
-		seq_printf(s, "|||||");
+		seq_printf(s, "||||");
 	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "  DURATION   ");
 	seq_printf(s, "               FUNCTION CALLS\n");
@@ -1343,7 +1337,7 @@ static void __print_graph_headers_flags(struct seq_file *s, u32 flags)
 	if (flags & TRACE_GRAPH_PRINT_PROC)
 		seq_printf(s, "   |    |        ");
 	if (lat)
-		seq_printf(s, "|||||");
+		seq_printf(s, "||||");
 	if (flags & TRACE_GRAPH_PRINT_DURATION)
 		seq_printf(s, "   |   |      ");
 	seq_printf(s, "               |   |   |   |\n");
@@ -1358,15 +1352,16 @@ void print_graph_headers_flags(struct seq_file *s, u32 flags)
 {
 	struct trace_iterator *iter = s->private;
 
+	if (!(trace_flags & TRACE_ITER_CONTEXT_INFO))
+		return;
+
 	if (trace_flags & TRACE_ITER_LATENCY_FMT) {
 		/* print nothing if the buffers are empty */
 		if (trace_empty(iter))
 			return;
 
 		print_trace_header(s, iter);
-		flags |= TRACE_GRAPH_PRINT_DURATION;
-	} else
-		flags |= TRACE_GRAPH_PRINT_ABS_TIME;
+	}
 
 	__print_graph_headers_flags(s, flags);
 }
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index c77424be284d..20dad0d7a163 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -23,7 +23,7 @@ static int				tracer_enabled __read_mostly;
 
 static DEFINE_PER_CPU(int, tracing_cpu);
 
-static DEFINE_SPINLOCK(max_trace_lock);
+static DEFINE_RAW_SPINLOCK(max_trace_lock);
 
 enum {
 	TRACER_IRQS_OFF		= (1 << 1),
@@ -226,7 +226,9 @@ static void irqsoff_trace_close(struct trace_iterator *iter)
 }
 
 #define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_CPU | \
-			    TRACE_GRAPH_PRINT_PROC)
+			    TRACE_GRAPH_PRINT_PROC | \
+			    TRACE_GRAPH_PRINT_ABS_TIME | \
+			    TRACE_GRAPH_PRINT_DURATION)
 
 static enum print_line_t irqsoff_print_line(struct trace_iterator *iter)
 {
@@ -319,7 +321,7 @@ check_critical_timing(struct trace_array *tr,
 	if (!report_latency(delta))
 		goto out;
 
-	spin_lock_irqsave(&max_trace_lock, flags);
+	raw_spin_lock_irqsave(&max_trace_lock, flags);
 
 	/* check if we are still the max latency */
 	if (!report_latency(delta))
@@ -342,7 +344,7 @@ check_critical_timing(struct trace_array *tr,
 	max_sequence++;
 
 out_unlock:
-	spin_unlock_irqrestore(&max_trace_lock, flags);
+	raw_spin_unlock_irqrestore(&max_trace_lock, flags);
 
 out:
 	data->critical_sequence = max_sequence;
@@ -503,13 +505,13 @@ EXPORT_SYMBOL(trace_hardirqs_off_caller);
 #ifdef CONFIG_PREEMPT_TRACER
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
-	if (preempt_trace())
+	if (preempt_trace() && !irq_trace())
 		stop_critical_timing(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
-	if (preempt_trace())
+	if (preempt_trace() && !irq_trace())
 		start_critical_timing(a0, a1);
 }
 #endif /* CONFIG_PREEMPT_TRACER */
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 27d13b36b8be..00d527c945a4 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -343,6 +343,14 @@ DEFINE_BASIC_FETCH_FUNCS(deref)
 DEFINE_FETCH_deref(string)
 DEFINE_FETCH_deref(string_size)
 
+static __kprobes void update_deref_fetch_param(struct deref_fetch_param *data)
+{
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
 static __kprobes void free_deref_fetch_param(struct deref_fetch_param *data)
 {
 	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
@@ -377,6 +385,19 @@ DEFINE_BASIC_FETCH_FUNCS(bitfield)
 #define fetch_bitfield_string_size NULL
 
 static __kprobes void
+update_bitfield_fetch_param(struct bitfield_fetch_param *data)
+{
+	/*
+	 * Don't check the bitfield itself, because this must be the
+	 * last fetch function.
+	 */
+	if (CHECK_FETCH_FUNCS(deref, data->orig.fn))
+		update_deref_fetch_param(data->orig.data);
+	else if (CHECK_FETCH_FUNCS(symbol, data->orig.fn))
+		update_symbol_cache(data->orig.data);
+}
+
+static __kprobes void
 free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 {
 	/*
@@ -389,6 +410,7 @@ free_bitfield_fetch_param(struct bitfield_fetch_param *data)
 		free_symbol_cache(data->orig.data);
 	kfree(data);
 }
+
 /* Default (unsigned long) fetch type */
 #define __DEFAULT_FETCH_TYPE(t) u##t
 #define _DEFAULT_FETCH_TYPE(t) __DEFAULT_FETCH_TYPE(t)
@@ -536,6 +558,7 @@ struct probe_arg {
 /* Flags for trace_probe */
 #define TP_FLAG_TRACE	1
 #define TP_FLAG_PROFILE	2
+#define TP_FLAG_REGISTERED 4
 
 struct trace_probe {
 	struct list_head	list;
@@ -555,16 +578,49 @@ struct trace_probe {
 	(sizeof(struct probe_arg) * (n)))
 
 
-static __kprobes int probe_is_return(struct trace_probe *tp)
+static __kprobes int trace_probe_is_return(struct trace_probe *tp)
 {
 	return tp->rp.handler != NULL;
 }
 
-static __kprobes const char *probe_symbol(struct trace_probe *tp)
+static __kprobes const char *trace_probe_symbol(struct trace_probe *tp)
 {
 	return tp->symbol ? tp->symbol : "unknown";
 }
 
+static __kprobes unsigned long trace_probe_offset(struct trace_probe *tp)
+{
+	return tp->rp.kp.offset;
+}
+
+static __kprobes bool trace_probe_is_enabled(struct trace_probe *tp)
+{
+	return !!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE));
+}
+
+static __kprobes bool trace_probe_is_registered(struct trace_probe *tp)
+{
+	return !!(tp->flags & TP_FLAG_REGISTERED);
+}
+
+static __kprobes bool trace_probe_has_gone(struct trace_probe *tp)
+{
+	return !!(kprobe_gone(&tp->rp.kp));
+}
+
+static __kprobes bool trace_probe_within_module(struct trace_probe *tp,
+						struct module *mod)
+{
+	int len = strlen(mod->name);
+	const char *name = trace_probe_symbol(tp);
+	return strncmp(mod->name, name, len) == 0 && name[len] == ':';
+}
+
+static __kprobes bool trace_probe_is_on_module(struct trace_probe *tp)
+{
+	return !!strchr(trace_probe_symbol(tp), ':');
+}
+
 static int register_probe_event(struct trace_probe *tp);
 static void unregister_probe_event(struct trace_probe *tp);
 
@@ -646,6 +702,16 @@ error:
 	return ERR_PTR(ret);
 }
 
+static void update_probe_arg(struct probe_arg *arg)
+{
+	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
+		update_bitfield_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(deref, arg->fetch.fn))
+		update_deref_fetch_param(arg->fetch.data);
+	else if (CHECK_FETCH_FUNCS(symbol, arg->fetch.fn))
+		update_symbol_cache(arg->fetch.data);
+}
+
 static void free_probe_arg(struct probe_arg *arg)
 {
 	if (CHECK_FETCH_FUNCS(bitfield, arg->fetch.fn))
@@ -671,7 +737,7 @@ static void free_trace_probe(struct trace_probe *tp)
 	kfree(tp);
 }
 
-static struct trace_probe *find_probe_event(const char *event,
+static struct trace_probe *find_trace_probe(const char *event,
 					    const char *group)
 {
 	struct trace_probe *tp;
@@ -683,15 +749,104 @@ static struct trace_probe *find_probe_event(const char *event,
 	return NULL;
 }
 
-/* Unregister a trace_probe and probe_event: call with locking probe_lock */
-static void unregister_trace_probe(struct trace_probe *tp)
+/* Enable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static int enable_trace_probe(struct trace_probe *tp, int flag)
 {
-	if (probe_is_return(tp))
-		unregister_kretprobe(&tp->rp);
+	int ret = 0;
+
+	tp->flags |= flag;
+	if (trace_probe_is_enabled(tp) && trace_probe_is_registered(tp) &&
+	    !trace_probe_has_gone(tp)) {
+		if (trace_probe_is_return(tp))
+			ret = enable_kretprobe(&tp->rp);
+		else
+			ret = enable_kprobe(&tp->rp.kp);
+	}
+
+	return ret;
+}
+
+/* Disable trace_probe - @flag must be TP_FLAG_TRACE or TP_FLAG_PROFILE */
+static void disable_trace_probe(struct trace_probe *tp, int flag)
+{
+	tp->flags &= ~flag;
+	if (!trace_probe_is_enabled(tp) && trace_probe_is_registered(tp)) {
+		if (trace_probe_is_return(tp))
+			disable_kretprobe(&tp->rp);
+		else
+			disable_kprobe(&tp->rp.kp);
+	}
+}
+
+/* Internal register function - just handle k*probes and flags */
+static int __register_trace_probe(struct trace_probe *tp)
+{
+	int i, ret;
+
+	if (trace_probe_is_registered(tp))
+		return -EINVAL;
+
+	for (i = 0; i < tp->nr_args; i++)
+		update_probe_arg(&tp->args[i]);
+
+	/* Set/clear disabled flag according to tp->flag */
+	if (trace_probe_is_enabled(tp))
+		tp->rp.kp.flags &= ~KPROBE_FLAG_DISABLED;
+	else
+		tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
+
+	if (trace_probe_is_return(tp))
+		ret = register_kretprobe(&tp->rp);
 	else
-		unregister_kprobe(&tp->rp.kp);
+		ret = register_kprobe(&tp->rp.kp);
+
+	if (ret == 0)
+		tp->flags |= TP_FLAG_REGISTERED;
+	else {
+		pr_warning("Could not insert probe at %s+%lu: %d\n",
+			   trace_probe_symbol(tp), trace_probe_offset(tp), ret);
+		if (ret == -ENOENT && trace_probe_is_on_module(tp)) {
+			pr_warning("This probe might be able to register after"
+				   "target module is loaded. Continue.\n");
+			ret = 0;
+		} else if (ret == -EILSEQ) {
+			pr_warning("Probing address(0x%p) is not an "
+				   "instruction boundary.\n",
+				   tp->rp.kp.addr);
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}
+
+/* Internal unregister function - just handle k*probes and flags */
+static void __unregister_trace_probe(struct trace_probe *tp)
+{
+	if (trace_probe_is_registered(tp)) {
+		if (trace_probe_is_return(tp))
+			unregister_kretprobe(&tp->rp);
+		else
+			unregister_kprobe(&tp->rp.kp);
+		tp->flags &= ~TP_FLAG_REGISTERED;
+		/* Cleanup kprobe for reuse */
+		if (tp->rp.kp.symbol_name)
+			tp->rp.kp.addr = NULL;
+	}
+}
+
+/* Unregister a trace_probe and probe_event: call with locking probe_lock */
+static int unregister_trace_probe(struct trace_probe *tp)
+{
+	/* Enabled event can not be unregistered */
+	if (trace_probe_is_enabled(tp))
+		return -EBUSY;
+
+	__unregister_trace_probe(tp);
 	list_del(&tp->list);
 	unregister_probe_event(tp);
+
+	return 0;
 }
 
 /* Register a trace_probe and probe_event */
@@ -702,41 +857,68 @@ static int register_trace_probe(struct trace_probe *tp)
 
 	mutex_lock(&probe_lock);
 
-	/* register as an event */
-	old_tp = find_probe_event(tp->call.name, tp->call.class->system);
+	/* Delete old (same name) event if exist */
+	old_tp = find_trace_probe(tp->call.name, tp->call.class->system);
 	if (old_tp) {
-		/* delete old event */
-		unregister_trace_probe(old_tp);
+		ret = unregister_trace_probe(old_tp);
+		if (ret < 0)
+			goto end;
 		free_trace_probe(old_tp);
 	}
+
+	/* Register new event */
 	ret = register_probe_event(tp);
 	if (ret) {
 		pr_warning("Failed to register probe event(%d)\n", ret);
 		goto end;
 	}
 
-	tp->rp.kp.flags |= KPROBE_FLAG_DISABLED;
-	if (probe_is_return(tp))
-		ret = register_kretprobe(&tp->rp);
-	else
-		ret = register_kprobe(&tp->rp.kp);
-
-	if (ret) {
-		pr_warning("Could not insert probe(%d)\n", ret);
-		if (ret == -EILSEQ) {
-			pr_warning("Probing address(0x%p) is not an "
-				   "instruction boundary.\n",
-				   tp->rp.kp.addr);
-			ret = -EINVAL;
-		}
+	/* Register k*probe */
+	ret = __register_trace_probe(tp);
+	if (ret < 0)
 		unregister_probe_event(tp);
-	} else
+	else
 		list_add_tail(&tp->list, &probe_list);
+
 end:
 	mutex_unlock(&probe_lock);
 	return ret;
 }
 
+/* Module notifier call back, checking event on the module */
+static int trace_probe_module_callback(struct notifier_block *nb,
+				       unsigned long val, void *data)
+{
+	struct module *mod = data;
+	struct trace_probe *tp;
+	int ret;
+
+	if (val != MODULE_STATE_COMING)
+		return NOTIFY_DONE;
+
+	/* Update probes on coming module */
+	mutex_lock(&probe_lock);
+	list_for_each_entry(tp, &probe_list, list) {
+		if (trace_probe_within_module(tp, mod)) {
+			/* Don't need to check busy - this should have gone. */
+			__unregister_trace_probe(tp);
+			ret = __register_trace_probe(tp);
+			if (ret)
+				pr_warning("Failed to re-register probe %s on"
+					   "%s: %d\n",
+					   tp->call.name, mod->name, ret);
+		}
+	}
+	mutex_unlock(&probe_lock);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block trace_probe_module_nb = {
+	.notifier_call = trace_probe_module_callback,
+	.priority = 1	/* Invoked after kprobe module callback */
+};
+
 /* Split symbol and offset. */
 static int split_symbol_offset(char *symbol, unsigned long *offset)
 {
@@ -962,8 +1144,8 @@ static int create_trace_probe(int argc, char **argv)
 {
 	/*
 	 * Argument syntax:
-	 *  - Add kprobe: p[:[GRP/]EVENT] KSYM[+OFFS]|KADDR [FETCHARGS]
-	 *  - Add kretprobe: r[:[GRP/]EVENT] KSYM[+0] [FETCHARGS]
+	 *  - Add kprobe: p[:[GRP/]EVENT] [MOD:]KSYM[+OFFS]|KADDR [FETCHARGS]
+	 *  - Add kretprobe: r[:[GRP/]EVENT] [MOD:]KSYM[+0] [FETCHARGS]
 	 * Fetch args:
 	 *  $retval	: fetch return value
 	 *  $stack	: fetch stack address
@@ -1025,17 +1207,18 @@ static int create_trace_probe(int argc, char **argv)
 			return -EINVAL;
 		}
 		mutex_lock(&probe_lock);
-		tp = find_probe_event(event, group);
+		tp = find_trace_probe(event, group);
 		if (!tp) {
 			mutex_unlock(&probe_lock);
 			pr_info("Event %s/%s doesn't exist.\n", group, event);
 			return -ENOENT;
 		}
 		/* delete an event */
-		unregister_trace_probe(tp);
-		free_trace_probe(tp);
+		ret = unregister_trace_probe(tp);
+		if (ret == 0)
+			free_trace_probe(tp);
 		mutex_unlock(&probe_lock);
-		return 0;
+		return ret;
 	}
 
 	if (argc < 2) {
@@ -1144,20 +1327,30 @@ error:
 	return ret;
 }
 
-static void cleanup_all_probes(void)
+static int release_all_trace_probes(void)
 {
 	struct trace_probe *tp;
+	int ret = 0;
 
 	mutex_lock(&probe_lock);
+	/* Ensure no probe is in use. */
+	list_for_each_entry(tp, &probe_list, list)
+		if (trace_probe_is_enabled(tp)) {
+			ret = -EBUSY;
+			goto end;
+		}
 	/* TODO: Use batch unregistration */
 	while (!list_empty(&probe_list)) {
 		tp = list_entry(probe_list.next, struct trace_probe, list);
 		unregister_trace_probe(tp);
 		free_trace_probe(tp);
 	}
+
+end:
 	mutex_unlock(&probe_lock);
-}
 
+	return ret;
+}
 
 /* Probes listing interfaces */
 static void *probes_seq_start(struct seq_file *m, loff_t *pos)
@@ -1181,15 +1374,16 @@ static int probes_seq_show(struct seq_file *m, void *v)
 	struct trace_probe *tp = v;
 	int i;
 
-	seq_printf(m, "%c", probe_is_return(tp) ? 'r' : 'p');
+	seq_printf(m, "%c", trace_probe_is_return(tp) ? 'r' : 'p');
 	seq_printf(m, ":%s/%s", tp->call.class->system, tp->call.name);
 
 	if (!tp->symbol)
 		seq_printf(m, " 0x%p", tp->rp.kp.addr);
 	else if (tp->rp.kp.offset)
-		seq_printf(m, " %s+%u", probe_symbol(tp), tp->rp.kp.offset);
+		seq_printf(m, " %s+%u", trace_probe_symbol(tp),
+			   tp->rp.kp.offset);
 	else
-		seq_printf(m, " %s", probe_symbol(tp));
+		seq_printf(m, " %s", trace_probe_symbol(tp));
 
 	for (i = 0; i < tp->nr_args; i++)
 		seq_printf(m, " %s=%s", tp->args[i].name, tp->args[i].comm);
@@ -1207,9 +1401,13 @@ static const struct seq_operations probes_seq_op = {
 
 static int probes_open(struct inode *inode, struct file *file)
 {
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (file->f_flags & O_TRUNC))
-		cleanup_all_probes();
+	int ret;
+
+	if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) {
+		ret = release_all_trace_probes();
+		if (ret < 0)
+			return ret;
+	}
 
 	return seq_open(file, &probes_seq_op);
 }
@@ -1397,7 +1595,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
-		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+		trace_nowake_buffer_unlock_commit_regs(buffer, event,
+						       irq_flags, pc, regs);
 }
 
 /* Kretprobe handler */
@@ -1429,7 +1628,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
 	store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
 
 	if (!filter_current_check_discard(buffer, call, entry, event))
-		trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+		trace_nowake_buffer_unlock_commit_regs(buffer, event,
+						       irq_flags, pc, regs);
 }
 
 /* Event entry printers */
@@ -1511,30 +1711,6 @@ partial:
 	return TRACE_TYPE_PARTIAL_LINE;
 }
 
-static int probe_event_enable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags |= TP_FLAG_TRACE;
-	if (probe_is_return(tp))
-		return enable_kretprobe(&tp->rp);
-	else
-		return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_event_disable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags &= ~TP_FLAG_TRACE;
-	if (!(tp->flags & (TP_FLAG_TRACE | TP_FLAG_PROFILE))) {
-		if (probe_is_return(tp))
-			disable_kretprobe(&tp->rp);
-		else
-			disable_kprobe(&tp->rp.kp);
-	}
-}
-
 #undef DEFINE_FIELD
 #define DEFINE_FIELD(type, item, name, is_signed)			\
 	do {								\
@@ -1596,7 +1772,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len)
 
 	const char *fmt, *arg;
 
-	if (!probe_is_return(tp)) {
+	if (!trace_probe_is_return(tp)) {
 		fmt = "(%lx)";
 		arg = "REC->" FIELD_STRING_IP;
 	} else {
@@ -1713,49 +1889,25 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
 	head = this_cpu_ptr(call->perf_events);
 	perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
-
-static int probe_perf_enable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags |= TP_FLAG_PROFILE;
-
-	if (probe_is_return(tp))
-		return enable_kretprobe(&tp->rp);
-	else
-		return enable_kprobe(&tp->rp.kp);
-}
-
-static void probe_perf_disable(struct ftrace_event_call *call)
-{
-	struct trace_probe *tp = (struct trace_probe *)call->data;
-
-	tp->flags &= ~TP_FLAG_PROFILE;
-
-	if (!(tp->flags & TP_FLAG_TRACE)) {
-		if (probe_is_return(tp))
-			disable_kretprobe(&tp->rp);
-		else
-			disable_kprobe(&tp->rp.kp);
-	}
-}
 #endif	/* CONFIG_PERF_EVENTS */
 
 static __kprobes
 int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
 {
+	struct trace_probe *tp = (struct trace_probe *)event->data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return probe_event_enable(event);
+		return enable_trace_probe(tp, TP_FLAG_TRACE);
 	case TRACE_REG_UNREGISTER:
-		probe_event_disable(event);
+		disable_trace_probe(tp, TP_FLAG_TRACE);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
 	case TRACE_REG_PERF_REGISTER:
-		return probe_perf_enable(event);
+		return enable_trace_probe(tp, TP_FLAG_PROFILE);
 	case TRACE_REG_PERF_UNREGISTER:
-		probe_perf_disable(event);
+		disable_trace_probe(tp, TP_FLAG_PROFILE);
 		return 0;
 #endif
 	}
@@ -1805,7 +1957,7 @@ static int register_probe_event(struct trace_probe *tp)
 
 	/* Initialize ftrace_event_call */
 	INIT_LIST_HEAD(&call->class->fields);
-	if (probe_is_return(tp)) {
+	if (trace_probe_is_return(tp)) {
 		call->event.funcs = &kretprobe_funcs;
 		call->class->define_fields = kretprobe_event_define_fields;
 	} else {
@@ -1844,6 +1996,9 @@ static __init int init_kprobe_trace(void)
 	struct dentry *d_tracer;
 	struct dentry *entry;
 
+	if (register_module_notifier(&trace_probe_module_nb))
+		return -EINVAL;
+
 	d_tracer = tracing_init_dentry();
 	if (!d_tracer)
 		return 0;
@@ -1897,12 +2052,12 @@ static __init int kprobe_trace_self_tests_init(void)
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_probe_event("testprobe", KPROBE_EVENT_SYSTEM);
+		tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
 		if (WARN_ON_ONCE(tp == NULL)) {
 			pr_warning("error on getting new probe.\n");
 			warn++;
 		} else
-			probe_event_enable(&tp->call);
+			enable_trace_probe(tp, TP_FLAG_TRACE);
 	}
 
 	ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
@@ -1912,12 +2067,12 @@ static __init int kprobe_trace_self_tests_init(void)
 		warn++;
 	} else {
 		/* Enable trace point */
-		tp = find_probe_event("testprobe2", KPROBE_EVENT_SYSTEM);
+		tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
 		if (WARN_ON_ONCE(tp == NULL)) {
 			pr_warning("error on getting new probe.\n");
 			warn++;
 		} else
-			probe_event_enable(&tp->call);
+			enable_trace_probe(tp, TP_FLAG_TRACE);
 	}
 
 	if (warn)
@@ -1925,6 +2080,21 @@ static __init int kprobe_trace_self_tests_init(void)
 
 	ret = target(1, 2, 3, 4, 5, 6);
 
+	/* Disable trace points before removing it */
+	tp = find_trace_probe("testprobe", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
+	tp = find_trace_probe("testprobe2", KPROBE_EVENT_SYSTEM);
+	if (WARN_ON_ONCE(tp == NULL)) {
+		pr_warning("error on getting 2nd test probe.\n");
+		warn++;
+	} else
+		disable_trace_probe(tp, TP_FLAG_TRACE);
+
 	ret = command_trace_probe("-:testprobe");
 	if (WARN_ON_ONCE(ret)) {
 		pr_warning("error on deleting a probe.\n");
@@ -1938,7 +2108,7 @@ static __init int kprobe_trace_self_tests_init(void)
 	}
 
 end:
-	cleanup_all_probes();
+	release_all_trace_probes();
 	if (warn)
 		pr_cont("NG: Some tests are failed. Please check them.\n");
 	else
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index 017fa376505d..fd3c8aae55e5 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -12,7 +12,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include "trace.h"
 #include "trace_output.h"
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index e37de492a9e1..51999309a6cf 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -1107,19 +1107,20 @@ static enum print_line_t trace_stack_print(struct trace_iterator *iter,
 {
 	struct stack_entry *field;
 	struct trace_seq *s = &iter->seq;
-	int i;
+	unsigned long *p;
+	unsigned long *end;
 
 	trace_assign_type(field, iter->ent);
+	end = (unsigned long *)((long)iter->ent + iter->ent_size);
 
 	if (!trace_seq_puts(s, "<stack trace>\n"))
 		goto partial;
-	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
-		if (!field->caller[i] || (field->caller[i] == ULONG_MAX))
-			break;
+
+	for (p = field->caller; p && *p != ULONG_MAX && p < end; p++) {
 		if (!trace_seq_puts(s, " => "))
 			goto partial;
 
-		if (!seq_print_ip_sym(s, field->caller[i], flags))
+		if (!seq_print_ip_sym(s, *p, flags))
 			goto partial;
 		if (!trace_seq_puts(s, "\n"))
 			goto partial;
diff --git a/kernel/trace/trace_printk.c b/kernel/trace/trace_printk.c
index 1f06468a10d7..6fd4ffd042f9 100644
--- a/kernel/trace/trace_printk.c
+++ b/kernel/trace/trace_printk.c
@@ -59,18 +59,19 @@ void hold_module_trace_bprintk_format(const char **start, const char **end)
 			continue;
 		}
 
+		fmt = NULL;
 		tb_fmt = kmalloc(sizeof(*tb_fmt), GFP_KERNEL);
-		if (tb_fmt)
+		if (tb_fmt) {
 			fmt = kmalloc(strlen(*iter) + 1, GFP_KERNEL);
-		if (tb_fmt && fmt) {
-			list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list);
-			strcpy(fmt, *iter);
-			tb_fmt->fmt = fmt;
-			*iter = tb_fmt->fmt;
-		} else {
-			kfree(tb_fmt);
-			*iter = NULL;
+			if (fmt) {
+				list_add_tail(&tb_fmt->list, &trace_bprintk_fmt_list);
+				strcpy(fmt, *iter);
+				tb_fmt->fmt = fmt;
+			} else
+				kfree(tb_fmt);
 		}
+		*iter = fmt;
+
 	}
 	mutex_unlock(&btrace_mutex);
 }
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index f029dd4fd2ca..e4a70c0c71b6 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -227,7 +227,9 @@ static void wakeup_trace_close(struct trace_iterator *iter)
 		graph_trace_close(iter);
 }
 
-#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC)
+#define GRAPH_TRACER_FLAGS (TRACE_GRAPH_PRINT_PROC | \
+			    TRACE_GRAPH_PRINT_ABS_TIME | \
+			    TRACE_GRAPH_PRINT_DURATION)
 
 static enum print_line_t wakeup_print_line(struct trace_iterator *iter)
 {
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index b0b53b8e4c25..77575b386d97 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -156,20 +156,11 @@ stack_max_size_write(struct file *filp, const char __user *ubuf,
 {
 	long *ptr = filp->private_data;
 	unsigned long val, flags;
-	char buf[64];
 	int ret;
 	int cpu;
 
-	if (count >= sizeof(buf))
-		return -EINVAL;
-
-	if (copy_from_user(&buf, ubuf, count))
-		return -EFAULT;
-
-	buf[count] = 0;
-
-	ret = strict_strtoul(buf, 10, &val);
-	if (ret < 0)
+	ret = kstrtoul_from_user(ubuf, count, 10, &val);
+	if (ret)
 		return ret;
 
 	local_irq_save(flags);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index ee7b5a0bb9f8..cb654542c1a1 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -2,6 +2,7 @@
 #include <trace/events/syscalls.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/module.h>	/* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
 #include <linux/ftrace.h>
 #include <linux/perf_event.h>
 #include <asm/syscall.h>
author	Tejun Heo <tj@kernel.org>	2011-11-28 09:46:22 -0800
committer	Tejun Heo <tj@kernel.org>	2011-11-28 09:46:22 -0800
commit	d4bbf7e7759afc172e2bfbc5c416324590049cdd (patch)
tree	7eab5ee5481cd3dcf1162329fec827177640018a /kernel/trace
parent	a150439c4a97db379f0ed6faa46fbbb6e7bf3cb2 (diff)
parent	401d0069cb344f401bc9d264c31db55876ff78c0 (diff)