Merge tag 'trace-v4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
"Nothing major this round. Mostly small clean ups and fixes.

Some visible changes:

- A new flag was added to distinguish traces done in NMI context.

- Preempt tracer now shows functions where preemption is disabled but
interrupts are still enabled.

Other notes:

- Updates were done to function tracing to allow better performance
with perf.

- Infrastructure code has been added to allow for a new histogram
feature for recording live trace event histograms that can be
configured by simple user commands. The feature itself was just
finished, but needs a round in linux-next before being pulled.

This only includes some infrastructure changes that will be needed"

* tag 'trace-v4.6' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (22 commits)
tracing: Record and show NMI state
tracing: Fix trace_printk() to print when not using bprintk()
tracing: Remove redundant reset per-CPU buff in irqsoff tracer
x86: ftrace: Fix the misleading comment for arch/x86/kernel/ftrace.c
tracing: Fix crash from reading trace_pipe with sendfile
tracing: Have preempt(irqs)off trace preempt disabled functions
tracing: Fix return while holding a lock in register_tracer()
ftrace: Use kasprintf() in ftrace_profile_tracefs()
ftrace: Update dynamic ftrace calls only if necessary
ftrace: Make ftrace_hash_rec_enable return update bool
tracing: Fix typoes in code comment and printk in trace_nop.c
tracing, writeback: Replace cgroup path to cgroup ino
tracing: Use flags instead of bool in trigger structure
tracing: Add an unreg_all() callback to trigger commands
tracing: Add needs_rec flag to event triggers
tracing: Add a per-event-trigger 'paused' field
tracing: Add get_syscall_name()
tracing: Add event record param to trigger_ops.func()
tracing: Make event trigger functions available
tracing: Make ftrace_event_field checking functions available
...

arch/x86/kernel/ftrace.c

···
 /*
- * Code for replacing ftrace calls with jumps.
+ * Dynamic function tracing support.
  *
  * Copyright (C) 2007-2008 Steven Rostedt <[e-mail]>
  *

include/linux/kernel.h

···
 
 #define do_trace_printk(fmt, args...)					\
 do {									\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(fmt) ? fmt : NULL;			\
 									\
···
  */
 
 #define trace_puts(str) ({						\
-	static const char *trace_printk_fmt				\
+	static const char *trace_printk_fmt __used			\
 		__attribute__((section("__trace_printk_fmt"))) =	\
 		__builtin_constant_p(str) ? str : NULL;			\
 									\
···
 #define ftrace_vprintk(fmt, vargs)					\
 do {									\
 	if (__builtin_constant_p(fmt)) {				\
-		static const char *trace_printk_fmt			\
+		static const char *trace_printk_fmt __used		\
 		  __attribute__((section("__trace_printk_fmt"))) =	\
 			__builtin_constant_p(fmt) ? fmt : NULL;		\
 									\

include/linux/trace_events.h

···
 extern enum event_trigger_type event_triggers_call(struct trace_event_file *file,
 						   void *rec);
 extern void event_triggers_post_call(struct trace_event_file *file,
-				     enum event_trigger_type tt);
+				     enum event_trigger_type tt,
+				     void *rec);
 
 bool trace_event_ignore_this_pid(struct trace_event_file *trace_file);
 
···
 		trace_buffer_unlock_commit(file->tr, buffer, event, irq_flags, pc);
 
 	if (tt)
-		event_triggers_post_call(file, tt);
+		event_triggers_post_call(file, tt, entry);
 }
 
 /**
···
 						irq_flags, pc, regs);
 
 	if (tt)
-		event_triggers_post_call(file, tt);
+		event_triggers_post_call(file, tt, entry);
 }
 
 #ifdef CONFIG_BPF_EVENTS

include/trace/events/kmem.h

···
 	TP_ARGS(call_site, ptr)
 );
 
-DEFINE_EVENT_CONDITION(kmem_free, kmem_cache_free,
+DEFINE_EVENT(kmem_free, kmem_cache_free,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
-	TP_ARGS(call_site, ptr),
-
-	/*
-	 * This trace can be potentially called from an offlined cpu.
-	 * Since trace points use RCU and RCU should not be used from
-	 * offline cpus, filter such calls out.
-	 * While this trace can be called from a preemptable section,
-	 * it has no impact on the condition since tasks can migrate
-	 * only from online cpus to other online cpus. Thus its safe
-	 * to use raw_smp_processor_id.
-	 */
-	TP_CONDITION(cpu_online(raw_smp_processor_id()))
+	TP_ARGS(call_site, ptr)
 );
 
-TRACE_EVENT_CONDITION(mm_page_free,
+TRACE_EVENT(mm_page_free,
 
 	TP_PROTO(struct page *page, unsigned int order),
 
 	TP_ARGS(page, order),
-
-
-	/*
-	 * This trace can be potentially called from an offlined cpu.
-	 * Since trace points use RCU and RCU should not be used from
-	 * offline cpus, filter such calls out.
-	 * While this trace can be called from a preemptable section,
-	 * it has no impact on the condition since tasks can migrate
-	 * only from online cpus to other online cpus. Thus its safe
-	 * to use raw_smp_processor_id.
-	 */
-	TP_CONDITION(cpu_online(raw_smp_processor_id())),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)
···
 	TP_ARGS(page, order, migratetype)
 );
 
-TRACE_EVENT_CONDITION(mm_page_pcpu_drain,
+TRACE_EVENT(mm_page_pcpu_drain,
 
 	TP_PROTO(struct page *page, unsigned int order, int migratetype),
 
 	TP_ARGS(page, order, migratetype),
-
-	/*
-	 * This trace can be potentially called from an offlined cpu.
-	 * Since trace points use RCU and RCU should not be used from
-	 * offline cpus, filter such calls out.
-	 * While this trace can be called from a preemptable section,
-	 * it has no impact on the condition since tasks can migrate
-	 * only from online cpus to other online cpus. Thus its safe
-	 * to use raw_smp_processor_id.
-	 */
-	TP_CONDITION(cpu_online(raw_smp_processor_id())),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	pfn		)

include/trace/events/tlb.h

···
 #define EM(a,b)		{ a, b },
 #define EMe(a,b)	{ a, b }
 
-TRACE_EVENT_CONDITION(tlb_flush,
+TRACE_EVENT(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
-
-	TP_CONDITION(cpu_online(smp_processor_id())),
 
 	TP_STRUCT__entry(
 		__field(	  int, reason)

include/trace/events/writeback.h

···
 #ifdef CREATE_TRACE_POINTS
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1;
+	return wb->memcg_css->cgroup->kn->ino;
 }
 
-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
-{
-	struct cgroup *cgrp = wb->memcg_css->cgroup;
-	char *path;
-
-	path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1);
-	WARN_ON_ONCE(path != buf);
-}
-
-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
 	if (wbc->wb)
-		return __trace_wb_cgroup_size(wbc->wb);
+		return __trace_wb_assign_cgroup(wbc->wb);
 	else
-		return 2;
+		return -1U;
 }
-
-static inline void __trace_wbc_assign_cgroup(char *buf,
-					     struct writeback_control *wbc)
-{
-	if (wbc->wb)
-		__trace_wb_assign_cgroup(buf, wbc->wb);
-	else
-		strcpy(buf, "/");
-}
-
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return 2;
+	return -1U;
 }
 
-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
-	strcpy(buf, "/");
-}
-
-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
-{
-	return 2;
-}
-
-static inline void __trace_wbc_assign_cgroup(char *buf,
-					     struct writeback_control *wbc)
-{
-	strcpy(buf, "/");
+	return -1U;
 }
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
···
 		__array(char, name, 32)
 		__field(unsigned long, ino)
 		__field(int, sync_mode)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 			dev_name(inode_to_bdi(inode)->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
-	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s",
+	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u",
 		__entry->name,
 		__entry->ino,
 		__entry->sync_mode,
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 );
 
···
 		__field(int, range_cyclic)
 		__field(int, for_background)
 		__field(int, reason)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
 		strncpy(__entry->name,
···
 		__entry->range_cyclic = work->range_cyclic;
 		__entry->for_background	= work->for_background;
 		__entry->reason = work->reason;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
-		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s",
+		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u",
 		  __entry->name,
 		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
 		  __entry->nr_pages,
···
 		  __entry->range_cyclic,
 		  __entry->for_background,
 		  __print_symbolic(__entry->reason, WB_WORK_REASON),
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_WORK_EVENT(name) \
···
 	TP_ARGS(wb),
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: cgroup=%s",
+	TP_printk("bdi %s: cgroup_ino=%u",
 		  __entry->name,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_EVENT(name) \
···
 		__field(int, range_cyclic)
 		__field(long, range_start)
 		__field(long, range_end)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
 		"bgrd=%d reclm=%d cyclic=%d "
-		"start=0x%lx end=0x%lx cgroup=%s",
+		"start=0x%lx end=0x%lx cgroup_ino=%u",
 		__entry->name,
 		__entry->nr_to_write,
 		__entry->pages_skipped,
···
 		__entry->range_cyclic,
 		__entry->range_start,
 		__entry->range_end,
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 )
 
···
 		__field(long,		age)
 		__field(int,		moved)
 		__field(int,		reason)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 	TP_fast_assign(
 		unsigned long *older_than_this = work->older_than_this;
···
 				  (jiffies - *older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s",
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u",
 		__entry->name,
 		__entry->older,	/* older_than_this in jiffies */
 		__entry->age,	/* older_than_this in relative milliseconds */
 		__entry->moved,
 		__print_symbolic(__entry->reason, WB_WORK_REASON),
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 );
 
···
 		__field(unsigned long,	dirty_ratelimit)
 		__field(unsigned long,	task_ratelimit)
 		__field(unsigned long,	balanced_dirty_ratelimit)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 		__entry->task_ratelimit	= KBps(task_ratelimit);
 		__entry->balanced_dirty_ratelimit =
 					KBps(wb->balanced_dirty_ratelimit);
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 
 	TP_printk("bdi %s: "
 		  "write_bw=%lu awrite_bw=%lu dirty_rate=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
-		  "balanced_dirty_ratelimit=%lu cgroup=%s",
+		  "balanced_dirty_ratelimit=%lu cgroup_ino=%u",
 		  __entry->bdi,
 		  __entry->write_bw,		/* write bandwidth */
 		  __entry->avg_write_bw,	/* avg write bandwidth */
···
 		  __entry->dirty_ratelimit,	/* base ratelimit */
 		  __entry->task_ratelimit, /* ratelimit with position control */
 		  __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 
···
 		__field(	 long,	pause)
 		__field(unsigned long,	period)
 		__field(	 long,	think)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 		__entry->period		= period * 1000 / HZ;
 		__entry->pause		= pause * 1000 / HZ;
 		__entry->paused		= (jiffies - start_time) * 1000 / HZ;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 
 
···
 		  "bdi_setpoint=%lu bdi_dirty=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
 		  "dirtied=%u dirtied_pause=%u "
-		  "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s",
+		  "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u",
 		  __entry->bdi,
 		  __entry->limit,
 		  __entry->setpoint,
···
 		  __entry->pause,	/* ms */
 		  __entry->period,	/* ms */
 		  __entry->think,	/* ms */
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	  )
 );
 
···
 		__field(unsigned long, ino)
 		__field(unsigned long, state)
 		__field(unsigned long, dirtied_when)
-		__dynamic_array(char, cgroup,
-				__trace_wb_cgroup_size(inode_to_wb(inode)))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
-		__trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode));
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(inode_to_wb(inode));
 	),
 
-	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s",
+	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u",
 		  __entry->name,
 		  __entry->ino,
 		  show_inode_state(__entry->state),
 		  __entry->dirtied_when,
 		  (jiffies - __entry->dirtied_when) / HZ,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 
···
 		__field(unsigned long, writeback_index)
 		__field(long, nr_to_write)
 		__field(unsigned long, wrote)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
···
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 		__entry->nr_to_write	= nr_to_write;
 		__entry->wrote		= nr_to_write - wbc->nr_to_write;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
 	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu "
-		  "index=%lu to_write=%ld wrote=%lu cgroup=%s",
+		  "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u",
 		  __entry->name,
 		  __entry->ino,
 		  show_inode_state(__entry->state),
···
 		  __entry->writeback_index,
 		  __entry->nr_to_write,
 		  __entry->wrote,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 

kernel/trace/ftrace.c

···
 	for_each_possible_cpu(cpu) {
 		stat = &per_cpu(ftrace_profile_stats, cpu);
 
-		/* allocate enough for function name + cpu number */
-		name = kmalloc(32, GFP_KERNEL);
+		name = kasprintf(GFP_KERNEL, "function%d", cpu);
 		if (!name) {
 			/*
 			 * The files created are permanent, if something happens
···
 			return;
 		}
 		stat->stat = function_stats;
-		snprintf(name, 32, "function%d", cpu);
 		stat->stat.name = name;
 		ret = register_stat_tracer(&stat->stat);
 		if (ret) {
···
 	return  keep_regs;
 }
 
-static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
+static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
 				     int filter_hash,
 				     bool inc)
 {
···
 	struct ftrace_hash *other_hash;
 	struct ftrace_page *pg;
 	struct dyn_ftrace *rec;
+	bool update = false;
 	int count = 0;
 	int all = 0;
 
 	/* Only update if the ops has been registered */
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
-		return;
+		return false;
 
 	/*
 	 * In the filter_hash case:
···
 		 * then there's nothing to do.
 		 */
 		if (ftrace_hash_empty(hash))
-			return;
+			return false;
 	}
 
 	do_for_each_ftrace_rec(pg, rec) {
···
 		if (inc) {
 			rec->flags++;
 			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == FTRACE_REF_MAX))
-				return;
+				return false;
 
 			/*
 			 * If there's only a single callback registered to a
···
 				rec->flags |= FTRACE_FL_REGS;
 		} else {
 			if (FTRACE_WARN_ON(ftrace_rec_count(rec) == 0))
-				return;
+				return false;
 			rec->flags--;
 
 			/*
···
 			 */
 		}
 		count++;
+
+		/* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */
+		update |= ftrace_test_record(rec, 1) != FTRACE_UPDATE_IGNORE;
+
 		/* Shortcut, if we handled all records, we are done. */
 		if (!all && count == hash->count)
-			return;
+			return update;
 	} while_for_each_ftrace_rec();
+
+	return update;
 }
 
-static void ftrace_hash_rec_disable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_disable(struct ftrace_ops *ops,
 				    int filter_hash)
 {
-	__ftrace_hash_rec_update(ops, filter_hash, 0);
+	return __ftrace_hash_rec_update(ops, filter_hash, 0);
 }
 
-static void ftrace_hash_rec_enable(struct ftrace_ops *ops,
+static bool ftrace_hash_rec_enable(struct ftrace_ops *ops,
 				   int filter_hash)
 {
-	__ftrace_hash_rec_update(ops, filter_hash, 1);
+	return __ftrace_hash_rec_update(ops, filter_hash, 1);
 }
 
 static void ftrace_hash_rec_update_modify(struct ftrace_ops *ops,
···
 		return ret;
 
 	ftrace_start_up++;
-	command |= FTRACE_UPDATE_CALLS;
 
 	/*
 	 * Note that ftrace probes uses this to start up
···
 		return ret;
 	}
 
-	ftrace_hash_rec_enable(ops, 1);
+	if (ftrace_hash_rec_enable(ops, 1))
+		command |= FTRACE_UPDATE_CALLS;
 
 	ftrace_startup_enable(command);
 
···
 
 	/* Disabling ipmodify never fails */
 	ftrace_hash_ipmodify_disable(ops);
-	ftrace_hash_rec_disable(ops, 1);
+
+	if (ftrace_hash_rec_disable(ops, 1))
+		command |= FTRACE_UPDATE_CALLS;
 
 	ops->flags &= ~FTRACE_OPS_FL_ENABLED;
-
-	command |= FTRACE_UPDATE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
 		saved_ftrace_func = ftrace_trace_function;

kernel/trace/trace.c

···
 	{ }
 };
 
-static struct tracer_flags dummy_tracer_flags = {
-	.val = 0,
-	.opts = dummy_tracer_opt
-};
-
 static int
 dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
···
 
 	if (!type->set_flag)
 		type->set_flag = &dummy_set_flag;
-	if (!type->flags)
-		type->flags = &dummy_tracer_flags;
-	else
+	if (!type->flags) {
+		/*allocate a dummy tracer_flags*/
+		type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL);
+		if (!type->flags) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		type->flags->val = 0;
+		type->flags->opts = dummy_tracer_opt;
+	} else
 		if (!type->flags->opts)
 			type->flags->opts = dummy_tracer_opt;
+
+	/* store the tracer for __set_tracer_option */
+	type->flags->trace = type;
 
 	ret = run_tracer_selftest(type);
 	if (ret < 0)
···
 #else
 		TRACE_FLAG_IRQS_NOSUPPORT |
 #endif
+		((pc & NMI_MASK    ) ? TRACE_FLAG_NMI     : 0) |
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
 		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) |
···
 			       struct tracer_flags *tracer_flags,
 			       struct tracer_opt *opts, int neg)
 {
-	struct tracer *trace = tr->current_trace;
+	struct tracer *trace = tracer_flags->trace;
 	int ret;
 
 	ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg);
···
 
 	spd.nr_pages = i;
 
-	ret = splice_to_pipe(pipe, &spd);
+	if (i)
+		ret = splice_to_pipe(pipe, &spd);
+	else
+		ret = 0;
 out:
 	splice_shrink_spd(&spd);
 	return ret;
···
 		return;
 
 	for (i = 0; i < tr->nr_topts; i++) {
-		/*
-		 * Check if these flags have already been added.
-		 * Some tracers share flags.
-		 */
-		if (tr->topts[i].tracer->flags == tracer->flags)
+		/* Make sure there's no duplicate flags. */
+		if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags))
 			return;
 	}
 

kernel/trace/trace.h

···
 	TRACE_FLAG_HARDIRQ		= 0x08,
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 	TRACE_FLAG_PREEMPT_RESCHED	= 0x20,
+	TRACE_FLAG_NMI			= 0x40,
 };
 
 #define TRACE_BUF_SIZE		1024
···
 struct tracer_flags {
 	u32			val;
 	struct tracer_opt	*opts;
+	struct tracer		*trace;
 };
 
 /* Makes more easy to define a tracer opt */
···
 	unsigned short		right;
 };
 
+static inline bool is_string_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_DYN_STRING ||
+	       field->filter_type == FILTER_STATIC_STRING ||
+	       field->filter_type == FILTER_PTR_STRING;
+}
+
+static inline bool is_function_field(struct ftrace_event_field *field)
+{
+	return field->filter_type == FILTER_TRACE_FN;
+}
+
 extern enum regex_type
 filter_parse_regex(char *buff, int len, char **search, int *not);
 extern void print_event_filter(struct trace_event_file *file,
···
 	struct event_filter __rcu	*filter;
 	char				*filter_str;
 	void				*private_data;
+	bool				paused;
 	struct list_head		list;
 };
+
+extern void trigger_data_free(struct event_trigger_data *data);
+extern int event_trigger_init(struct event_trigger_ops *ops,
+			      struct event_trigger_data *data);
+extern int trace_event_trigger_enable_disable(struct trace_event_file *file,
+					      int trigger_enable);
+extern void update_cond_flag(struct trace_event_file *file);
+extern void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+			       struct event_trigger_data *test,
+			       struct trace_event_file *file);
+extern int set_trigger_filter(char *filter_str,
+			      struct event_trigger_data *trigger_data,
+			      struct trace_event_file *file);
+extern int register_event_command(struct event_command *cmd);
 
 /**
  * struct event_trigger_ops - callbacks for trace event triggers
···
  * @func: The trigger 'probe' function called when the triggering
  *	event occurs.  The data passed into this callback is the data
  *	that was supplied to the event_command @reg() function that
- *	registered the trigger (see struct event_command).
+ *	registered the trigger (see struct event_command) along with
+ *	the trace record, rec.
  *
  * @init: An optional initialization function called for the trigger
  *	when the trigger is registered (via the event_command reg()
···
  *	(see trace_event_triggers.c).
  */
 struct event_trigger_ops {
-	void			(*func)(struct event_trigger_data *data);
+	void			(*func)(struct event_trigger_data *data,
+					void *rec);
 	int			(*init)(struct event_trigger_ops *ops,
 					struct event_trigger_data *data);
 	void			(*free)(struct event_trigger_ops *ops,
···
  *	values are defined by adding new values to the trigger_type
  *	enum in include/linux/trace_events.h.
  *
- * @post_trigger: A flag that says whether or not this command needs
- *	to have its action delayed until after the current event has
- *	been closed.  Some triggers need to avoid being invoked while
- *	an event is currently in the process of being logged, since
- *	the trigger may itself log data into the trace buffer.  Thus
- *	we make sure the current event is committed before invoking
- *	those triggers.  To do that, the trigger invocation is split
- *	in two - the first part checks the filter using the current
- *	trace record; if a command has the @post_trigger flag set, it
- *	sets a bit for itself in the return value, otherwise it
- *	directly invokes the trigger.  Once all commands have been
- *	either invoked or set their return flag, the current record is
- *	either committed or discarded.  At that point, if any commands
- *	have deferred their triggers, those commands are finally
- *	invoked following the close of the current event.  In other
- *	words, if the event_trigger_ops @func() probe implementation
- *	itself logs to the trace buffer, this flag should be set,
- *	otherwise it can be left unspecified.
+ * @flags: See the enum event_command_flags below.
  *
- * All the methods below, except for @set_filter(), must be
- * implemented.
+ * All the methods below, except for @set_filter() and @unreg_all(),
+ * must be implemented.
  *
  * @func: The callback function responsible for parsing and
  *	registering the trigger written to the 'trigger' file by the
···
  *	This is usually implemented by the generic utility function
  *	@unregister_trigger() (see trace_event_triggers.c).
  *
+ * @unreg_all: An optional function called to remove all the triggers
+ *	from the list of triggers associated with the event.  Called
+ *	when a trigger file is opened in truncate mode.
+ *
  * @set_filter: An optional function called to parse and set a filter
  *	for the trigger.  If no @set_filter() method is set for the
  *	event command, filters set by the user for the command will be
···
 	struct list_head	list;
 	char			*name;
 	enum event_trigger_type	trigger_type;
-	bool			post_trigger;
+	int			flags;
 	int			(*func)(struct event_command *cmd_ops,
 					struct trace_event_file *file,
 					char *glob, char *cmd, char *params);
···
 					 struct event_trigger_ops *ops,
 					 struct event_trigger_data *data,
 					 struct trace_event_file *file);
+	void			(*unreg_all)(struct trace_event_file *file);
 	int			(*set_filter)(char *filter_str,
 					      struct event_trigger_data *data,
 					      struct trace_event_file *file);
 	struct event_trigger_ops *(*get_trigger_ops)(char *cmd, char *param);
 };
+
+/**
+ * enum event_command_flags - flags for struct event_command
+ *
+ * @POST_TRIGGER: A flag that says whether or not this command needs
+ *	to have its action delayed until after the current event has
+ *	been closed.  Some triggers need to avoid being invoked while
+ *	an event is currently in the process of being logged, since
+ *	the trigger may itself log data into the trace buffer.  Thus
+ *	we make sure the current event is committed before invoking
+ *	those triggers.  To do that, the trigger invocation is split
+ *	in two - the first part checks the filter using the current
+ *	trace record; if a command has the @post_trigger flag set, it
+ *	sets a bit for itself in the return value, otherwise it
+ *	directly invokes the trigger.  Once all commands have been
+ *	either invoked or set their return flag, the current record is
+ *	either committed or discarded.  At that point, if any commands
+ *	have deferred their triggers, those commands are finally
+ *	invoked following the close of the current event.  In other
+ *	words, if the event_trigger_ops @func() probe implementation
+ *	itself logs to the trace buffer, this flag should be set,
+ *	otherwise it can be left unspecified.
+ *
+ * @NEEDS_REC: A flag that says whether or not this command needs
+ *	access to the trace record in order to perform its function,
+ *	regardless of whether or not it has a filter associated with
+ *	it (filters make a trigger require access to the trace record
+ *	but are not always present).
+ */
+enum event_command_flags {
+	EVENT_CMD_FL_POST_TRIGGER	= 1,
+	EVENT_CMD_FL_NEEDS_REC		= 2,
+};
+
+static inline bool event_command_post_trigger(struct event_command *cmd_ops)
+{
+	return cmd_ops->flags & EVENT_CMD_FL_POST_TRIGGER;
+}
+
+static inline bool event_command_needs_rec(struct event_command *cmd_ops)
+{
+	return cmd_ops->flags & EVENT_CMD_FL_NEEDS_REC;
+}
 
 extern int trace_event_enable_disable(struct trace_event_file *file,
 				      int enable, int soft_disable);
···
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 void init_ftrace_syscalls(void);
+const char *get_syscall_name(int syscall);
 #else
 static inline void init_ftrace_syscalls(void) { }
+static inline const char *get_syscall_name(int syscall)
+{
+	return NULL;
+}
 #endif
 
 #ifdef CONFIG_EVENT_TRACING

kernel/trace/trace_events_filter.c

···
 	return FILTER_OTHER;
 }
 
-static bool is_function_field(struct ftrace_event_field *field)
-{
-	return field->filter_type == FILTER_TRACE_FN;
-}
-
-static bool is_string_field(struct ftrace_event_field *field)
-{
-	return field->filter_type == FILTER_DYN_STRING ||
-	       field->filter_type == FILTER_STATIC_STRING ||
-	       field->filter_type == FILTER_PTR_STRING;
-}
-
 static bool is_legal_op(struct ftrace_event_field *field, int op)
 {
 	if (is_string_field(field) &&

kernel/trace/trace_events_trigger.c

···
 static LIST_HEAD(trigger_commands);
 static DEFINE_MUTEX(trigger_cmd_mutex);
 
-static void
-trigger_data_free(struct event_trigger_data *data)
+void trigger_data_free(struct event_trigger_data *data)
 {
 	if (data->cmd_ops->set_filter)
 		data->cmd_ops->set_filter(NULL, data, NULL);
···
 		return tt;
 
 	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (data->paused)
+			continue;
 		if (!rec) {
-			data->ops->func(data);
+			data->ops->func(data, rec);
 			continue;
 		}
 		filter = rcu_dereference_sched(data->filter);
 		if (filter && !filter_match_preds(filter, rec))
 			continue;
-		if (data->cmd_ops->post_trigger) {
+		if (event_command_post_trigger(data->cmd_ops)) {
 			tt |= data->cmd_ops->trigger_type;
 			continue;
 		}
-		data->ops->func(data);
+		data->ops->func(data, rec);
 	}
 	return tt;
 }
···
  * event_triggers_post_call - Call 'post_triggers' for a trace event
  * @file: The trace_event_file associated with the event
  * @tt: enum event_trigger_type containing a set bit for each trigger to invoke
+ * @rec: The trace entry for the event
  *
  * For each trigger associated with an event, invoke the trigger
  * function registered with the associated trigger command, if the
···
  */
 void
 event_triggers_post_call(struct trace_event_file *file,
-			 enum event_trigger_type tt)
+			 enum event_trigger_type tt,
+			 void *rec)
 {
 	struct event_trigger_data *data;
 
 	list_for_each_entry_rcu(data, &file->triggers, list) {
+		if (data->paused)
+			continue;
 		if (data->cmd_ops->trigger_type & tt)
-			data->ops->func(data);
+			data->ops->func(data, rec);
 	}
 }
 EXPORT_SYMBOL_GPL(event_triggers_post_call);
···
 	if (unlikely(!event_file_data(file))) {
 		mutex_unlock(&event_mutex);
 		return -ENODEV;
+	}
+
+	if ((file->f_mode & FMODE_WRITE) &&
+	    (file->f_flags & O_TRUNC)) {
+		struct trace_event_file *event_file;
+		struct event_command *p;
+
+		event_file = event_file_data(file);
+
+		list_for_each_entry(p, &trigger_commands, list) {
+			if (p->unreg_all)
+				p->unreg_all(event_file);
+		}
 	}
 
 	if (file->f_mode & FMODE_READ) {
···
  * Currently we only register event commands from __init, so mark this
  * __init too.
  */
-static __init int register_event_command(struct event_command *cmd)
+__init int register_event_command(struct event_command *cmd)
 {
 	struct event_command *p;
 	int ret = 0;
···
  *
  * Return: 0 on success, errno otherwise
  */
-static int
-event_trigger_init(struct event_trigger_ops *ops,
-		   struct event_trigger_data *data)
+int event_trigger_init(struct event_trigger_ops *ops,
+		       struct event_trigger_data *data)
 {
 	data->ref++;
 	return 0;
···
 		trigger_data_free(data);
 }
 
-static int trace_event_trigger_enable_disable(struct trace_event_file *file,
-					      int trigger_enable)
+int trace_event_trigger_enable_disable(struct trace_event_file *file,
+				       int trigger_enable)
 {
 	int ret = 0;
 
···
  * its TRIGGER_COND bit set, otherwise the TRIGGER_COND bit should be
  * cleared.
  */
-static void update_cond_flag(struct trace_event_file *file)
+void update_cond_flag(struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 	bool set_cond = false;
 
 	list_for_each_entry_rcu(data, &file->triggers, list) {
-		if (data->filter || data->cmd_ops->post_trigger) {
+		if (data->filter || event_command_post_trigger(data->cmd_ops) ||
+		    event_command_needs_rec(data->cmd_ops)) {
 			set_cond = true;
 			break;
 		}
···
  * Usually used directly as the @unreg method in event command
  * implementations.
  */
-static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
-			       struct event_trigger_data *test,
-			       struct trace_event_file *file)
+void unregister_trigger(char *glob, struct event_trigger_ops *ops,
+			struct event_trigger_data *test,
+			struct trace_event_file *file)
 {
 	struct event_trigger_data *data;
 	bool unregistered = false;
···
  *
  * Return: 0 on success, errno otherwise
  */
-static int set_trigger_filter(char *filter_str,
-			      struct event_trigger_data *trigger_data,
-			      struct trace_event_file *file)
+int set_trigger_filter(char *filter_str,
+		       struct event_trigger_data *trigger_data,
+		       struct trace_event_file *file)
 {
 	struct event_trigger_data *data = trigger_data;
 	struct event_filter *filter = NULL, *tmp;
···
 }
 
 static void
-traceon_trigger(struct event_trigger_data *data)
+traceon_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (tracing_is_on())
 		return;
···
 }
 
 static void
-traceon_count_trigger(struct event_trigger_data *data)
+traceon_count_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (tracing_is_on())
 		return;
···
 }
 
 static void
-traceoff_trigger(struct event_trigger_data *data)
+traceoff_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (!tracing_is_on())
 		return;
···
 }
 
 static void
-traceoff_count_trigger(struct event_trigger_data *data)
+traceoff_count_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (!tracing_is_on())
 		return;
···
 
 #ifdef CONFIG_TRACER_SNAPSHOT
 static void
-snapshot_trigger(struct event_trigger_data *data)
+snapshot_trigger(struct event_trigger_data *data, void *rec)
 {
 	tracing_snapshot();
 }
 
 static void
-snapshot_count_trigger(struct event_trigger_data *data)
+snapshot_count_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (!data->count)
 		return;
···
 	if (data->count != -1)
 		(data->count)--;
 
-	snapshot_trigger(data);
+	snapshot_trigger(data, rec);
 }
 
 static int
···
 #define STACK_SKIP 3
 
 static void
-stacktrace_trigger(struct event_trigger_data *data)
+stacktrace_trigger(struct event_trigger_data *data, void *rec)
 {
 	trace_dump_stack(STACK_SKIP);
 }
 
 static void
-stacktrace_count_trigger(struct event_trigger_data *data)
+stacktrace_count_trigger(struct event_trigger_data *data, void *rec)
 {
 	if (!data->count)
 		return;
···
 	if (data->count != -1)
 		(data->count)--;
 
-	stacktrace_trigger(data);
+	stacktrace_trigger(data, rec);
 }
 
 static int
···
 static struct event_command trigger_stacktrace_cmd = {
 	.name			= "stacktrace",
 	.trigger_type		= ETT_STACKTRACE,
-	.post_trigger		= true,
+	.flags			= EVENT_CMD_FL_POST_TRIGGER,
 	.func			= event_trigger_callback,
 	.reg			= register_trigger,
 	.unreg			= unregister_trigger,
···
 };
 
 static void
-event_enable_trigger(struct event_trigger_data *data)
+event_enable_trigger(struct event_trigger_data *data, void *rec)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
 
···
 }
 
 static void
-event_enable_count_trigger(struct event_trigger_data *data)
+event_enable_count_trigger(struct event_trigger_data *data, void *rec)
 {
 	struct enable_trigger_data *enable_data = data->private_data;
 
···
 	if (data->count != -1)
 		(data->count)--;
 
-	event_enable_trigger(data);
+	event_enable_trigger(data, rec);
 }
 
 static int

kernel/trace/trace_functions.c

···
 	unregister_ftrace_function(tr->ops);
 }
 
+static struct tracer function_trace;
+
 static int
 func_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
 {
···
 	case TRACE_FUNC_OPT_STACK:
 		/* do nothing if already set */
 		if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
+			break;
+
+		/* We can change this flag when not running. */
+		if (tr->current_trace != &function_trace)
 			break;
 
 		unregister_ftrace_function(tr->ops);

kernel/trace/trace_irqsoff.c

···
 		return 0;
 
 	local_save_flags(*flags);
-	/* slight chance to get a false positive on tracing_cpu */
-	if (!irqs_disabled_flags(*flags))
+	/*
+	 * Slight chance to get a false positive on tracing_cpu,
+	 * although I'm starting to think there isn't a chance.
+	 * Leave this for now just to be paranoid.
+	 */
+	if (!irqs_disabled_flags(*flags) && !preempt_count())
 		return 0;
 
 	*data = per_cpu_ptr(tr->trace_buffer.data, cpu);
···
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
-	tracing_reset_online_cpus(&tr->trace_buffer);
 
 	ftrace_init_array_ops(tr, irqsoff_tracer_call);
 

kernel/trace/trace_nop.c

···
 }
 
 /* It only serves as a signal handler and a callback to
- * accept or refuse tthe setting of a flag.
+ * accept or refuse the setting of a flag.
  * If you don't implement it, then the flag setting will be
  * automatically accepted.
  */
···
 
 	if (bit == TRACE_NOP_OPT_REFUSE) {
 		printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
-			"Now cat trace_options to see the result\n",
+			" Now cat trace_options to see the result\n",
 			set);
 		return -EINVAL;
 	}

kernel/trace/trace_output.c

···
 	char irqs_off;
 	int hardirq;
 	int softirq;
+	int nmi;
 
+	nmi = entry->flags & TRACE_FLAG_NMI;
 	hardirq = entry->flags & TRACE_FLAG_HARDIRQ;
 	softirq = entry->flags & TRACE_FLAG_SOFTIRQ;
 
···
 	}
 
 	hardsoft_irq =
+		(nmi && hardirq)     ? 'Z' :
+		nmi                  ? 'z' :
 		(hardirq && softirq) ? 'H' :
-		hardirq ? 'h' :
-		softirq ? 's' :
-		'.';
+		hardirq              ? 'h' :
+		softirq              ? 's' :
+		                       '.' ;
 
 	trace_seq_printf(s, "%c%c%c",
 			 irqs_off, need_resched, hardsoft_irq);

kernel/trace/trace_printk.c

···
 	const char *str = *fmt;
 	int i;
 
+	if (!*fmt)
+		return 0;
+
 	seq_printf(m, "0x%lx : \"", *(unsigned long *)fmt);
 
 	/*

kernel/trace/trace_syscalls.c

···
 	return syscalls_metadata[nr];
 }
 
+const char *get_syscall_name(int syscall)
+{
+	struct syscall_metadata *entry;
+
+	entry = syscall_nr_to_meta(syscall);
+	if (!entry)
+		return NULL;
+
+	return entry->name;
+}
+
 static enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags,
 		    struct trace_event *event)