19 files changed, 4156 insertions, 342 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e45db6b0d878..fafeaf803bd0 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -528,6 +528,32 @@ config MMIOTRACE
 	  See Documentation/trace/mmiotrace.txt.
 	  If you are not helping to develop drivers, say N.
 
+config TRACING_MAP
+	bool
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	help
+	  tracing_map is a special-purpose lock-free map for tracing,
+	  separated out as a stand-alone facility in order to allow it
+	  to be shared between multiple tracers.  It isn't meant to be
+	  generally used outside of that context, and is normally
+	  selected by tracers that use it.
+
+config HIST_TRIGGERS
+	bool "Histogram triggers"
+	depends on ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select TRACING_MAP
+	default n
+	help
+	  Hist triggers allow one or more arbitrary trace event fields
+	  to be aggregated into hash tables and dumped to stdout by
+	  reading a debugfs/tracefs file.  They're useful for
+	  gathering quick and dirty (though precise) summaries of
+	  event activity as an initial guide for further investigation
+	  using more advanced tools.
+
+	  See Documentation/trace/events.txt.
+	  If in doubt, say N.
+
 config MMIOTRACE_TEST
 	tristate "Test module for mmiotrace"
 	depends on MMIOTRACE && m
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 9b1044e936a6..979e7bfbde7a 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_TRACING) += trace_output.o
 obj-$(CONFIG_TRACING) += trace_seq.o
 obj-$(CONFIG_TRACING) += trace_stat.o
 obj-$(CONFIG_TRACING) += trace_printk.o
+obj-$(CONFIG_TRACING_MAP) += tracing_map.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
@@ -53,6 +54,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
 endif
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
 obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index f94e7a21f52d..9aef8654e90d 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -1349,6 +1349,7 @@ static enum print_line_t print_one_line(struct trace_iterator *iter,
 	if (t->action == BLK_TN_MESSAGE) {
 		log_action(iter, long_act ? "message" : "m");
 		blk_log_msg(s, iter->ent);
+		return trace_handle_return(s);
 	}
 
 	if (unlikely(what == 0 || what >= ARRAY_SIZE(what2act)))
@@ -1551,6 +1552,7 @@ static const struct {
 	{ BLK_TC_COMPLETE,	"complete"	},
 	{ BLK_TC_FS,		"fs"		},
 	{ BLK_TC_PC,		"pc"		},
+	{ BLK_TC_NOTIFY,	"notify"	},
 	{ BLK_TC_AHEAD,		"ahead"		},
 	{ BLK_TC_META,		"meta"		},
 	{ BLK_TC_DISCARD,	"discard"	},
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3e4ffb3ace5f..780bcbe1d4de 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -62,17 +62,21 @@ EXPORT_SYMBOL_GPL(trace_call_bpf);
 static u64 bpf_probe_read(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 {
 	void *dst = (void *) (long) r1;
-	int size = (int) r2;
+	int ret, size = (int) r2;
 	void *unsafe_ptr = (void *) (long) r3;
 
-	return probe_kernel_read(dst, unsafe_ptr, size);
+	ret = probe_kernel_read(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_probe_read_proto = {
 	.func		= bpf_probe_read,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_STACK,
+	.arg1_type	= ARG_PTR_TO_RAW_STACK,
 	.arg2_type	= ARG_CONST_STACK_SIZE,
 	.arg3_type	= ARG_ANYTHING,
 };
@@ -221,11 +225,12 @@ static const struct bpf_func_proto bpf_perf_event_read_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
 {
 	struct pt_regs *regs = (struct pt_regs *) (long) r1;
 	struct bpf_map *map = (struct bpf_map *) (long) r2;
 	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 index = flags & BPF_F_INDEX_MASK;
 	void *data = (void *) (long) r4;
 	struct perf_sample_data sample_data;
 	struct perf_event *event;
@@ -235,6 +240,10 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
 		.data = data,
 	};
 
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
+		return -EINVAL;
+	if (index == BPF_F_CURRENT_CPU)
+		index = raw_smp_processor_id();
 	if (unlikely(index >= array->map.max_entries))
 		return -E2BIG;
 
@@ -268,7 +277,34 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = {
 	.arg5_type	= ARG_CONST_STACK_SIZE,
 };
 
-static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs);
+
+static u64 bpf_event_output(u64 r1, u64 r2, u64 flags, u64 r4, u64 size)
+{
+	struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs);
+
+	perf_fetch_caller_regs(regs);
+
+	return bpf_perf_event_output((long)regs, r2, flags, r4, size);
+}
+
+static const struct bpf_func_proto bpf_event_output_proto = {
+	.func		= bpf_event_output,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_STACK,
+	.arg5_type	= ARG_CONST_STACK_SIZE,
+};
+
+const struct bpf_func_proto *bpf_get_event_output_proto(void)
+{
+	return &bpf_event_output_proto;
+}
+
+static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
 	case BPF_FUNC_map_lookup_elem:
@@ -295,12 +331,20 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func
 		return &bpf_get_smp_processor_id_proto;
 	case BPF_FUNC_perf_event_read:
 		return &bpf_perf_event_read_proto;
+	default:
+		return NULL;
+	}
+}
+
+static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
 	case BPF_FUNC_perf_event_output:
 		return &bpf_perf_event_output_proto;
 	case BPF_FUNC_get_stackid:
 		return &bpf_get_stackid_proto;
 	default:
-		return NULL;
+		return tracing_func_proto(func_id);
 	}
 }
 
@@ -332,9 +376,82 @@ static struct bpf_prog_type_list kprobe_tl = {
 	.type	= BPF_PROG_TYPE_KPROBE,
 };
 
+static u64 bpf_perf_event_output_tp(u64 r1, u64 r2, u64 index, u64 r4, u64 size)
+{
+	/*
+	 * r1 points to perf tracepoint buffer where first 8 bytes are hidden
+	 * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it
+	 * from there and call the same bpf_perf_event_output() helper
+	 */
+	u64 ctx = *(long *)(uintptr_t)r1;
+
+	return bpf_perf_event_output(ctx, r2, index, r4, size);
+}
+
+static const struct bpf_func_proto bpf_perf_event_output_proto_tp = {
+	.func		= bpf_perf_event_output_tp,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_STACK,
+	.arg5_type	= ARG_CONST_STACK_SIZE,
+};
+
+static u64 bpf_get_stackid_tp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+	u64 ctx = *(long *)(uintptr_t)r1;
+
+	return bpf_get_stackid(ctx, r2, r3, r4, r5);
+}
+
+static const struct bpf_func_proto bpf_get_stackid_proto_tp = {
+	.func		= bpf_get_stackid_tp,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_CONST_MAP_PTR,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_perf_event_output:
+		return &bpf_perf_event_output_proto_tp;
+	case BPF_FUNC_get_stackid:
+		return &bpf_get_stackid_proto_tp;
+	default:
+		return tracing_func_proto(func_id);
+	}
+}
+
+static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+	if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE)
+		return false;
+	if (type != BPF_READ)
+		return false;
+	if (off % size != 0)
+		return false;
+	return true;
+}
+
+static const struct bpf_verifier_ops tracepoint_prog_ops = {
+	.get_func_proto  = tp_prog_func_proto,
+	.is_valid_access = tp_prog_is_valid_access,
+};
+
+static struct bpf_prog_type_list tracepoint_tl = {
+	.ops	= &tracepoint_prog_ops,
+	.type	= BPF_PROG_TYPE_TRACEPOINT,
+};
+
 static int __init register_kprobe_prog_ops(void)
 {
 	bpf_register_prog_type(&kprobe_tl);
+	bpf_register_prog_type(&tracepoint_tl);
 	return 0;
 }
 late_initcall(register_kprobe_prog_ops);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b1870fbd2b67..900dbb1efff2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1530,7 +1530,19 @@ static int ftrace_cmp_recs(const void *a, const void *b)
 	return 0;
 }
 
-static unsigned long ftrace_location_range(unsigned long start, unsigned long end)
+/**
+ * ftrace_location_range - return the first address of a traced location
+ *	if it touches the given ip range
+ * @start: start of range to search.
+ * @end: end of range to search (inclusive). @end points to the last byte
+ *	to check.
+ *
+ * Returns rec->ip if the related ftrace location is a least partly within
+ * the given address range. That is, the first address of the instruction
+ * that is either a NOP or call to the function tracer. It checks the ftrace
+ * internal tables to determine if the address belongs or not.
+ */
+unsigned long ftrace_location_range(unsigned long start, unsigned long end)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
@@ -3444,11 +3456,23 @@ struct ftrace_glob {
 	int type;
 };
 
+/*
+ * If symbols in an architecture don't correspond exactly to the user-visible
+ * name of what they represent, it is possible to define this function to
+ * perform the necessary adjustments.
+*/
+char * __weak arch_ftrace_match_adjust(char *str, const char *search)
+{
+	return str;
+}
+
 static int ftrace_match(char *str, struct ftrace_glob *g)
 {
 	int matched = 0;
 	int slen;
 
+	str = arch_ftrace_match_adjust(str, g->search);
+
 	switch (g->type) {
 	case MATCH_FULL:
 		if (strcmp(str, g->search) == 0)
@@ -5713,7 +5737,6 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 {
 	int i;
 	int ret = 0;
-	unsigned long flags;
 	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
 	struct task_struct *g, *t;
 
@@ -5729,7 +5752,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 		}
 	}
 
-	read_lock_irqsave(&tasklist_lock, flags);
+	read_lock(&tasklist_lock);
 	do_each_thread(g, t) {
 		if (start == end) {
 			ret = -EAGAIN;
@@ -5747,7 +5770,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
 	} while_each_thread(g, t);
 
 unlock:
-	read_unlock_irqrestore(&tasklist_lock, flags);
+	read_unlock(&tasklist_lock);
 free:
 	for (i = start; i < end; i++)
 		kfree(ret_stack_list[i]);
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index 81b87451c0ea..0c7dee221dca 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -15,5 +15,6 @@
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
 EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
 EXPORT_TRACEPOINT_SYMBOL_GPL(powernv_throttle);
 
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 95181e36891a..9c143739b8d7 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -437,7 +437,7 @@ struct ring_buffer_per_cpu {
 	raw_spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
-	unsigned int			nr_pages;
+	unsigned long			nr_pages;
 	unsigned int			current_context;
 	struct list_head		*pages;
 	struct buffer_page		*head_page;	/* read from head */
@@ -458,7 +458,7 @@ struct ring_buffer_per_cpu {
 	u64				write_stamp;
 	u64				read_stamp;
 	/* ring buffer pages to update, > 0 to add, < 0 to remove */
-	int				nr_pages_to_update;
+	long				nr_pages_to_update;
 	struct list_head		new_pages; /* new pages to add */
 	struct work_struct		update_pages_work;
 	struct completion		update_done;
@@ -1128,10 +1128,10 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	return 0;
 }
 
-static int __rb_allocate_pages(int nr_pages, struct list_head *pages, int cpu)
+static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
 {
-	int i;
 	struct buffer_page *bpage, *tmp;
+	long i;
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page;
@@ -1168,7 +1168,7 @@ free_pages:
 }
 
 static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
-			     unsigned nr_pages)
+			     unsigned long nr_pages)
 {
 	LIST_HEAD(pages);
 
@@ -1193,7 +1193,7 @@ static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
 }
 
 static struct ring_buffer_per_cpu *
-rb_allocate_cpu_buffer(struct ring_buffer *buffer, int nr_pages, int cpu)
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, long nr_pages, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct buffer_page *bpage;
@@ -1293,8 +1293,9 @@ struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
 					struct lock_class_key *key)
 {
 	struct ring_buffer *buffer;
+	long nr_pages;
 	int bsize;
-	int cpu, nr_pages;
+	int cpu;
 
 	/* keep it in its own cache line */
 	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
@@ -1420,12 +1421,12 @@ static inline unsigned long rb_page_write(struct buffer_page *bpage)
 }
 
 static int
-rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned int nr_pages)
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
 {
 	struct list_head *tail_page, *to_remove, *next_page;
 	struct buffer_page *to_remove_page, *tmp_iter_page;
 	struct buffer_page *last_page, *first_page;
-	unsigned int nr_removed;
+	unsigned long nr_removed;
 	unsigned long head_bit;
 	int page_entries;
 
@@ -1642,7 +1643,7 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 			int cpu_id)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned nr_pages;
+	unsigned long nr_pages;
 	int cpu, err = 0;
 
 	/*
@@ -1656,14 +1657,13 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
 	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
 		return size;
 
-	size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
-	size *= BUF_PAGE_SIZE;
+	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
 
 	/* we need a minimum of two pages */
-	if (size < BUF_PAGE_SIZE * 2)
-		size = BUF_PAGE_SIZE * 2;
+	if (nr_pages < 2)
+		nr_pages = 2;
 
-	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	size = nr_pages * BUF_PAGE_SIZE;
 
 	/*
 	 * Don't succeed if resizing is disabled, as a reader might be
@@ -4640,8 +4640,9 @@ static int rb_cpu_notify(struct notifier_block *self,
 	struct ring_buffer *buffer =
 		container_of(self, struct ring_buffer, cpu_notify);
 	long cpu = (long)hcpu;
-	int cpu_i, nr_pages_same;
-	unsigned int nr_pages;
+	long nr_pages_same;
+	int cpu_i;
+	unsigned long nr_pages;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a2f0b9f33e9b..8a4bd6b68a0b 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -253,6 +253,9 @@ unsigned long long ns2usecs(cycle_t nsec)
 #define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK |			\
 	       TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD)
 
+/* trace_flags that are default zero for instances */
+#define ZEROED_TRACE_FLAGS \
+	TRACE_ITER_EVENT_FORK
 
 /*
  * The global_trace is the descriptor that holds the tracing
@@ -303,33 +306,18 @@ void trace_array_put(struct trace_array *this_tr)
 	mutex_unlock(&trace_types_lock);
 }
 
-int filter_check_discard(struct trace_event_file *file, void *rec,
-			 struct ring_buffer *buffer,
-			 struct ring_buffer_event *event)
-{
-	if (unlikely(file->flags & EVENT_FILE_FL_FILTERED) &&
-	    !filter_match_preds(file->filter, rec)) {
-		ring_buffer_discard_commit(buffer, event);
-		return 1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(filter_check_discard);
-
 int call_filter_check_discard(struct trace_event_call *call, void *rec,
 			      struct ring_buffer *buffer,
 			      struct ring_buffer_event *event)
 {
 	if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
 	    !filter_match_preds(call->filter, rec)) {
-		ring_buffer_discard_commit(buffer, event);
+		__trace_event_discard_commit(buffer, event);
 		return 1;
 	}
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(call_filter_check_discard);
 
 static cycle_t buffer_ftrace_now(struct trace_buffer *buf, int cpu)
 {
@@ -1672,6 +1660,16 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
+static __always_inline void
+trace_event_setup(struct ring_buffer_event *event,
+		  int type, unsigned long flags, int pc)
+{
+	struct trace_entry *ent = ring_buffer_event_data(event);
+
+	tracing_generic_entry_update(ent, flags, pc);
+	ent->type = type;
+}
+
 struct ring_buffer_event *
 trace_buffer_lock_reserve(struct ring_buffer *buffer,
 			  int type,
@@ -1681,34 +1679,137 @@ trace_buffer_lock_reserve(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 
 	event = ring_buffer_lock_reserve(buffer, len);
-	if (event != NULL) {
-		struct trace_entry *ent = ring_buffer_event_data(event);
+	if (event != NULL)
+		trace_event_setup(event, type, flags, pc);
+
+	return event;
+}
+
+DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event);
+DEFINE_PER_CPU(int, trace_buffered_event_cnt);
+static int trace_buffered_event_ref;
+
+/**
+ * trace_buffered_event_enable - enable buffering events
+ *
+ * When events are being filtered, it is quicker to use a temporary
+ * buffer to write the event data into if there's a likely chance
+ * that it will not be committed. The discard of the ring buffer
+ * is not as fast as committing, and is much slower than copying
+ * a commit.
+ *
+ * When an event is to be filtered, allocate per cpu buffers to
+ * write the event data into, and if the event is filtered and discarded
+ * it is simply dropped, otherwise, the entire data is to be committed
+ * in one shot.
+ */
+void trace_buffered_event_enable(void)
+{
+	struct ring_buffer_event *event;
+	struct page *page;
+	int cpu;
 
-		tracing_generic_entry_update(ent, flags, pc);
-		ent->type = type;
+	WARN_ON_ONCE(!mutex_is_locked(&event_mutex));
+
+	if (trace_buffered_event_ref++)
+		return;
+
+	for_each_tracing_cpu(cpu) {
+		page = alloc_pages_node(cpu_to_node(cpu),
+					GFP_KERNEL | __GFP_NORETRY, 0);
+		if (!page)
+			goto failed;
+
+		event = page_address(page);
+		memset(event, 0, sizeof(*event));
+
+		per_cpu(trace_buffered_event, cpu) = event;
+
+		preempt_disable();
+		if (cpu == smp_processor_id() &&
+		    this_cpu_read(trace_buffered_event) !=
+		    per_cpu(trace_buffered_event, cpu))
+			WARN_ON_ONCE(1);
+		preempt_enable();
 	}
 
-	return event;
+	return;
+ failed:
+	trace_buffered_event_disable();
 }
 
-void
-__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
+static void enable_trace_buffered_event(void *data)
 {
-	__this_cpu_write(trace_cmdline_save, true);
-	ring_buffer_unlock_commit(buffer, event);
+	/* Probably not needed, but do it anyway */
+	smp_rmb();
+	this_cpu_dec(trace_buffered_event_cnt);
 }
 
-void trace_buffer_unlock_commit(struct trace_array *tr,
-				struct ring_buffer *buffer,
-				struct ring_buffer_event *event,
-				unsigned long flags, int pc)
+static void disable_trace_buffered_event(void *data)
 {
-	__buffer_unlock_commit(buffer, event);
+	this_cpu_inc(trace_buffered_event_cnt);
+}
 
-	ftrace_trace_stack(tr, buffer, flags, 6, pc, NULL);
-	ftrace_trace_userstack(buffer, flags, pc);
+/**
+ * trace_buffered_event_disable - disable buffering events
+ *
+ * When a filter is removed, it is faster to not use the buffered
+ * events, and to commit directly into the ring buffer. Free up
+ * the temp buffers when there are no more users. This requires
+ * special synchronization with current events.
+ */
+void trace_buffered_event_disable(void)
+{
+	int cpu;
+
+	WARN_ON_ONCE(!mutex_is_locked(&event_mutex));
+
+	if (WARN_ON_ONCE(!trace_buffered_event_ref))
+		return;
+
+	if (--trace_buffered_event_ref)
+		return;
+
+	preempt_disable();
+	/* For each CPU, set the buffer as used. */
+	smp_call_function_many(tracing_buffer_mask,
+			       disable_trace_buffered_event, NULL, 1);
+	preempt_enable();
+
+	/* Wait for all current users to finish */
+	synchronize_sched();
+
+	for_each_tracing_cpu(cpu) {
+		free_page((unsigned long)per_cpu(trace_buffered_event, cpu));
+		per_cpu(trace_buffered_event, cpu) = NULL;
+	}
+	/*
+	 * Make sure trace_buffered_event is NULL before clearing
+	 * trace_buffered_event_cnt.
+	 */
+	smp_wmb();
+
+	preempt_disable();
+	/* Do the work on each cpu */
+	smp_call_function_many(tracing_buffer_mask,
+			       enable_trace_buffered_event, NULL, 1);
+	preempt_enable();
+}
+
+void
+__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
+{
+	__this_cpu_write(trace_cmdline_save, true);
+
+	/* If this is the temp buffer, we need to commit fully */
+	if (this_cpu_read(trace_buffered_event) == event) {
+		/* Length is in event->array[0] */
+		ring_buffer_write(buffer, event->array[0], &event->array[1]);
+		/* Release the temp buffer */
+		this_cpu_dec(trace_buffered_event_cnt);
+	} else
+		ring_buffer_unlock_commit(buffer, event);
 }
-EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit);
 
 static struct ring_buffer *temp_buffer;
 
@@ -1719,8 +1820,23 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 			  unsigned long flags, int pc)
 {
 	struct ring_buffer_event *entry;
+	int val;
 
 	*current_rb = trace_file->tr->trace_buffer.buffer;
+
+	if ((trace_file->flags &
+	     (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED)) &&
+	    (entry = this_cpu_read(trace_buffered_event))) {
+		/* Try to use the per cpu buffer first */
+		val = this_cpu_inc_return(trace_buffered_event_cnt);
+		if (val == 1) {
+			trace_event_setup(entry, type, flags, pc);
+			entry->array[0] = len;
+			return entry;
+		}
+		this_cpu_dec(trace_buffered_event_cnt);
+	}
+
 	entry = trace_buffer_lock_reserve(*current_rb,
 					 type, len, flags, pc);
 	/*
@@ -1738,17 +1854,6 @@ trace_event_buffer_lock_reserve(struct ring_buffer **current_rb,
 }
 EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve);
 
-struct ring_buffer_event *
-trace_current_buffer_lock_reserve(struct ring_buffer **current_rb,
-				  int type, unsigned long len,
-				  unsigned long flags, int pc)
-{
-	*current_rb = global_trace.trace_buffer.buffer;
-	return trace_buffer_lock_reserve(*current_rb,
-					 type, len, flags, pc);
-}
-EXPORT_SYMBOL_GPL(trace_current_buffer_lock_reserve);
-
 void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 				     struct ring_buffer *buffer,
 				     struct ring_buffer_event *event,
@@ -1760,14 +1865,6 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr,
 	ftrace_trace_stack(tr, buffer, flags, 0, pc, regs);
 	ftrace_trace_userstack(buffer, flags, pc);
 }
-EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs);
-
-void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
-					 struct ring_buffer_event *event)
-{
-	ring_buffer_discard_commit(buffer, event);
-}
-EXPORT_SYMBOL_GPL(trace_current_buffer_discard_commit);
 
 void
 trace_function(struct trace_array *tr,
@@ -3571,6 +3668,9 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
 	if (mask == TRACE_ITER_RECORD_CMD)
 		trace_event_enable_cmd_record(enabled);
 
+	if (mask == TRACE_ITER_EVENT_FORK)
+		trace_event_follow_fork(tr, enabled);
+
 	if (mask == TRACE_ITER_OVERWRITE) {
 		ring_buffer_change_overwrite(tr->trace_buffer.buffer, enabled);
 #ifdef CONFIG_TRACER_MAX_TRACE
@@ -3658,7 +3758,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
+	if (copy_from_user(buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
@@ -3804,12 +3904,19 @@ static const char readme_msg[] =
 	"\t   trigger: traceon, traceoff\n"
 	"\t            enable_event:<system>:<event>\n"
 	"\t            disable_event:<system>:<event>\n"
+#ifdef CONFIG_HIST_TRIGGERS
+	"\t            enable_hist:<system>:<event>\n"
+	"\t            disable_hist:<system>:<event>\n"
+#endif
 #ifdef CONFIG_STACKTRACE
 	"\t\t    stacktrace\n"
 #endif
 #ifdef CONFIG_TRACER_SNAPSHOT
 	"\t\t    snapshot\n"
 #endif
+#ifdef CONFIG_HIST_TRIGGERS
+	"\t\t    hist (see below)\n"
+#endif
 	"\t   example: echo traceoff > events/block/block_unplug/trigger\n"
 	"\t            echo traceoff:3 > events/block/block_unplug/trigger\n"
 	"\t            echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n"
@@ -3825,6 +3932,56 @@ static const char readme_msg[] =
 	"\t   To remove a trigger with a count:\n"
 	"\t     echo '!<trigger>:0 > <system>/<event>/trigger\n"
 	"\t   Filters can be ignored when removing a trigger.\n"
+#ifdef CONFIG_HIST_TRIGGERS
+	"      hist trigger\t- If set, event hits are aggregated into a hash table\n"
+	"\t    Format: hist:keys=<field1[,field2,...]>\n"
+	"\t            [:values=<field1[,field2,...]>]\n"
+	"\t            [:sort=<field1[,field2,...]>]\n"
+	"\t            [:size=#entries]\n"
+	"\t            [:pause][:continue][:clear]\n"
+	"\t            [:name=histname1]\n"
+	"\t            [if <filter>]\n\n"
+	"\t    When a matching event is hit, an entry is added to a hash\n"
+	"\t    table using the key(s) and value(s) named, and the value of a\n"
+	"\t    sum called 'hitcount' is incremented.  Keys and values\n"
+	"\t    correspond to fields in the event's format description.  Keys\n"
+	"\t    can be any field, or the special string 'stacktrace'.\n"
+	"\t    Compound keys consisting of up to two fields can be specified\n"
+	"\t    by the 'keys' keyword.  Values must correspond to numeric\n"
+	"\t    fields.  Sort keys consisting of up to two fields can be\n"
+	"\t    specified using the 'sort' keyword.  The sort direction can\n"
+	"\t    be modified by appending '.descending' or '.ascending' to a\n"
+	"\t    sort field.  The 'size' parameter can be used to specify more\n"
+	"\t    or fewer than the default 2048 entries for the hashtable size.\n"
+	"\t    If a hist trigger is given a name using the 'name' parameter,\n"
+	"\t    its histogram data will be shared with other triggers of the\n"
+	"\t    same name, and trigger hits will update this common data.\n\n"
+	"\t    Reading the 'hist' file for the event will dump the hash\n"
+	"\t    table in its entirety to stdout.  If there are multiple hist\n"
+	"\t    triggers attached to an event, there will be a table for each\n"
+	"\t    trigger in the output.  The table displayed for a named\n"
+	"\t    trigger will be the same as any other instance having the\n"
+	"\t    same name.  The default format used to display a given field\n"
+	"\t    can be modified by appending any of the following modifiers\n"
+	"\t    to the field name, as applicable:\n\n"
+	"\t            .hex        display a number as a hex value\n"
+	"\t            .sym        display an address as a symbol\n"
+	"\t            .sym-offset display an address as a symbol and offset\n"
+	"\t            .execname   display a common_pid as a program name\n"
+	"\t            .syscall    display a syscall id as a syscall name\n\n"
+	"\t            .log2       display log2 value rather than raw number\n\n"
+	"\t    The 'pause' parameter can be used to pause an existing hist\n"
+	"\t    trigger or to start a hist trigger but not log any events\n"
+	"\t    until told to do so.  'continue' can be used to start or\n"
+	"\t    restart a paused hist trigger.\n\n"
+	"\t    The 'clear' parameter will clear the contents of a running\n"
+	"\t    hist trigger and leave its current paused/active state\n"
+	"\t    unchanged.\n\n"
+	"\t    The enable_hist and disable_hist triggers can be used to\n"
+	"\t    have one event conditionally start and stop another event's\n"
+	"\t    already-attached hist trigger.  The syntax is analagous to\n"
+	"\t    the enable_event and disable_event triggers.\n"
+#endif
 ;
 
 static ssize_t
@@ -4474,7 +4631,7 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	if (cnt > MAX_TRACER_SIZE)
 		cnt = MAX_TRACER_SIZE;
 
-	if (copy_from_user(&buf, ubuf, cnt))
+	if (copy_from_user(buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
@@ -5264,7 +5421,7 @@ static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf,
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
 
-	if (copy_from_user(&buf, ubuf, cnt))
+	if (copy_from_user(buf, ubuf, cnt))
 		return -EFAULT;
 
 	buf[cnt] = 0;
@@ -6650,7 +6807,7 @@ static int instance_mkdir(const char *name)
 	if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL))
 		goto out_free_tr;
 
-	tr->trace_flags = global_trace.trace_flags;
+	tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS;
 
 	cpumask_copy(tr->tracing_cpumask, cpu_all_mask);
 
@@ -6724,6 +6881,12 @@ static int instance_rmdir(const char *name)
 
 	list_del(&tr->list);
 
+	/* Disable all the flags that were enabled coming in */
+	for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) {
+		if ((1 << i) & ZEROED_TRACE_FLAGS)
+			set_tracer_flag(tr, 1 << i, 0);
+	}
+
 	tracing_set_nop(tr);
 	event_trace_del_tracer(tr);
 	ftrace_destroy_function_files(tr);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3fff4adfd431..5167c366d6b7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -177,9 +177,8 @@ struct trace_options {
 };
 
 struct trace_pid_list {
-	unsigned int			nr_pids;
-	int				order;
-	pid_t				*pids;
+	int				pid_max;
+	unsigned long			*pids;
 };
 
 /*
@@ -656,6 +655,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 extern cycle_t ftrace_now(int cpu);
 
 extern void trace_find_cmdline(int pid, char comm[]);