Merge tag 'trace-v4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:
 "Not much new with tracing for this release.  Mostly just clean ups and
  minor fixes.

  Here's what else is new:

   - A new TRACE_EVENT_FN_COND macro, combining both _FN and _COND for
     those that want both.

   - New selftest to test the instance create and delete

   - Better debug output when ftrace fails"

* tag 'trace-v4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (24 commits)
  ftrace: Fix the race between ftrace and insmod
  ftrace: Add infrastructure for delayed enabling of module functions
  x86: ftrace: Fix the comments for ftrace_modify_code_direct()
  tracing: Fix comment to use tracing_on over tracing_enable
  metag: ftrace: Fix the comments for ftrace_modify_code
  sh: ftrace: Fix the comments for ftrace_modify_code()
  ia64: ftrace: Fix the comments for ftrace_modify_code()
  ftrace: Clean up ftrace_module_init() code
  ftrace: Join functions ftrace_module_init() and ftrace_init_module()
  tracing: Introduce TRACE_EVENT_FN_COND macro
  tracing: Use seq_buf_used() in seq_buf_to_user() instead of len
  bpf: Constify bpf_verifier_ops structure
  ftrace: Have ftrace_ops_get_func() handle RCU and PER_CPU flags too
  ftrace: Remove use of control list and ops
  ftrace: Fix output of enabled_functions for showing tramp
  ftrace: Fix a typo in comment
  ftrace: Show all tramps registered to a record on ftrace_bug()
  ftrace: Add variable ftrace_expected for archs to show expected code
  ftrace: Add new type to distinguish what kind of ftrace_bug()
  tracing: Update cond flag when enabling or disabling a trigger
  ...

arch/ia64/kernel/ftrace.c

@@ -97,13 +97,11 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
-	 * Note: Due to modules and __init, code can
-	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing. We do this by using the
-	 *  probe_kernel_* functions.
-	 *
-	 * No real locking needed, this code is run through
-	 * kstop_machine, or before SMP starts.
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
 	 */
 
 	if (!do_check)

arch/metag/kernel/ftrace.c

@@ -54,12 +54,11 @@ static int ftrace_modify_code(unsigned long pc, unsigned char *old_code,
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
-	 * Note: Due to modules and __init, code can
-	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
-	 *
-	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
 	 */
 
 	/* read the text we want to modify */

arch/sh/kernel/ftrace.c

@@ -212,13 +212,11 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
-	 * Note: Due to modules and __init, code can
-	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing. We do this by using the
-	 *  probe_kernel_* functions.
-	 *
-	 * No real locking needed, this code is run through
-	 * kstop_machine, or before SMP starts.
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
 	 */
 
 	/* read the text we want to modify */

arch/x86/kernel/ftrace.c

@@ -105,14 +105,14 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
+	ftrace_expected = old_code;
+
 	/*
-	 * Note: Due to modules and __init, code can
-	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing. We do this by using the
-	 *  probe_kernel_* functions.
-	 *
-	 * No real locking needed, this code is run through
-	 * kstop_machine, or before SMP starts.
+	 * Note:
+	 * We are paranoid about modifying text, as if a bug was to happen, it
+	 * could cause us to read or write to someplace that could cause harm.
+	 * Carefully read and modify the code with probe_kernel_*(), and make
+	 * sure what we read is what we expected it to be before modifying it.
 	 */
 
 	/* read the text we want to modify */
@@ -154,6 +154,8 @@ int ftrace_make_nop(struct module *mod,
 	if (addr == MCOUNT_ADDR)
 		return ftrace_modify_code_direct(rec->ip, old, new);
 
+	ftrace_expected = NULL;
+
 	/* Normal cases use add_brk_on_nop */
 	WARN_ONCE(1, "invalid use of ftrace_make_nop");
 	return -EINVAL;
@@ -220,6 +222,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
 				 unsigned long addr)
 {
 	WARN_ON(1);
+	ftrace_expected = NULL;
 	return -EINVAL;
 }
 
@@ -314,6 +317,8 @@ static int add_break(unsigned long ip, const char *old)
 	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
 		return -EFAULT;
 
+	ftrace_expected = old;
+
 	/* Make sure it is what we expect it to be */
 	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
@@ -413,6 +418,8 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 		ftrace_addr = ftrace_get_addr_curr(rec);
 		nop = ftrace_call_replace(ip, ftrace_addr);
 
+		ftrace_expected = nop;
+
 		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
 			return -EINVAL;
 	}

include/linux/ftrace.h

@@ -76,8 +76,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  * ENABLED - set/unset when ftrace_ops is registered/unregistered
  * DYNAMIC - set when ftrace_ops is registered to denote dynamically
  *           allocated ftrace_ops which need special care
- * CONTROL - set manualy by ftrace_ops user to denote the ftrace_ops
- *           could be controled by following calls:
+ * PER_CPU - set manualy by ftrace_ops user to denote the ftrace_ops
+ *           could be controlled by following calls:
  *             ftrace_function_local_enable
  *             ftrace_function_local_disable
  * SAVE_REGS - The ftrace_ops wants regs saved at each function called
@@ -121,7 +121,7 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
 	FTRACE_OPS_FL_DYNAMIC			= 1 << 1,
-	FTRACE_OPS_FL_CONTROL			= 1 << 2,
+	FTRACE_OPS_FL_PER_CPU			= 1 << 2,
 	FTRACE_OPS_FL_SAVE_REGS			= 1 << 3,
 	FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED	= 1 << 4,
 	FTRACE_OPS_FL_RECURSION_SAFE		= 1 << 5,
@@ -134,6 +134,7 @@ enum {
 	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 12,
 	FTRACE_OPS_FL_IPMODIFY			= 1 << 13,
 	FTRACE_OPS_FL_PID			= 1 << 14,
+	FTRACE_OPS_FL_RCU			= 1 << 15,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -146,11 +147,11 @@ struct ftrace_ops_hash {
 #endif
 
 /*
- * Note, ftrace_ops can be referenced outside of RCU protection.
- * (Although, for perf, the control ops prevent that). If ftrace_ops is
- * allocated and not part of kernel core data, the unregistering of it will
- * perform a scheduling on all CPUs to make sure that there are no more users.
- * Depending on the load of the system that may take a bit of time.
+ * Note, ftrace_ops can be referenced outside of RCU protection, unless
+ * the RCU flag is set. If ftrace_ops is allocated and not part of kernel
+ * core data, the unregistering of it will perform a scheduling on all CPUs
+ * to make sure that there are no more users. Depending on the load of the
+ * system that may take a bit of time.
  *
  * Any private data added must also take care not to be freed and if private
  * data is added to a ftrace_ops that is in core code, the user of the
@@ -196,34 +197,34 @@ int unregister_ftrace_function(struct ftrace_ops *ops);
 void clear_ftrace_function(void);
 
 /**
- * ftrace_function_local_enable - enable controlled ftrace_ops on current cpu
+ * ftrace_function_local_enable - enable ftrace_ops on current cpu
  *
  * This function enables tracing on current cpu by decreasing
  * the per cpu control variable.
  * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
  * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
  */
 static inline void ftrace_function_local_enable(struct ftrace_ops *ops)
 {
-	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
 		return;
 
 	(*this_cpu_ptr(ops->disabled))--;
 }
 
 /**
- * ftrace_function_local_disable - enable controlled ftrace_ops on current cpu
+ * ftrace_function_local_disable - disable ftrace_ops on current cpu
  *
- * This function enables tracing on current cpu by decreasing
+ * This function disables tracing on current cpu by increasing
  * the per cpu control variable.
  * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
  * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
  */
 static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
 {
-	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL)))
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
 		return;
 
 	(*this_cpu_ptr(ops->disabled))++;
@@ -235,12 +236,12 @@ static inline void ftrace_function_local_disable(struct ftrace_ops *ops)
  *
  * This function returns value of ftrace_ops::disabled on current cpu.
  * It must be called with preemption disabled and only on ftrace_ops
- * registered with FTRACE_OPS_FL_CONTROL. If called without preemption
+ * registered with FTRACE_OPS_FL_PER_CPU. If called without preemption
  * disabled, this_cpu_ptr will complain when CONFIG_DEBUG_PREEMPT is enabled.
  */
 static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
 {
-	WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_CONTROL));
+	WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU));
 	return *this_cpu_ptr(ops->disabled);
 }
 
@@ -296,6 +297,21 @@ int ftrace_arch_code_modify_post_process(void);
 
 struct dyn_ftrace;
 
+enum ftrace_bug_type {
+	FTRACE_BUG_UNKNOWN,
+	FTRACE_BUG_INIT,
+	FTRACE_BUG_NOP,
+	FTRACE_BUG_CALL,
+	FTRACE_BUG_UPDATE,
+};
+extern enum ftrace_bug_type ftrace_bug_type;
+
+/*
+ * Archs can set this to point to a variable that holds the value that was
+ * expected at the call site before calling ftrace_bug().
+ */
+extern const void *ftrace_expected;
+
 void ftrace_bug(int err, struct dyn_ftrace *rec);
 
 struct seq_file;
@@ -341,6 +357,7 @@ bool is_ftrace_trampoline(unsigned long addr);
  *  REGS    - the record wants the function to save regs
  *  REGS_EN - the function is set up to save regs.
  *  IPMODIFY - the record allows for the IP address to be changed.
+ *  DISABLED - the record is not ready to be touched yet
  *
  * When a new ftrace_ops is registered and wants a function to save
  * pt_regs, the rec->flag REGS is set. When the function has been
@@ -355,10 +372,11 @@ enum {
 	FTRACE_FL_TRAMP		= (1UL << 28),
 	FTRACE_FL_TRAMP_EN	= (1UL << 27),
 	FTRACE_FL_IPMODIFY	= (1UL << 26),
+	FTRACE_FL_DISABLED	= (1UL << 25),
 };
 
-#define FTRACE_REF_MAX_SHIFT	26
-#define FTRACE_FL_BITS		6
+#define FTRACE_REF_MAX_SHIFT	25
+#define FTRACE_FL_BITS		7
 #define FTRACE_FL_MASKED_BITS	((1UL << FTRACE_FL_BITS) - 1)
 #define FTRACE_FL_MASK		(FTRACE_FL_MASKED_BITS << FTRACE_REF_MAX_SHIFT)
 #define FTRACE_REF_MAX		((1UL << FTRACE_REF_MAX_SHIFT) - 1)

include/linux/tracepoint.h

@@ -479,6 +479,10 @@ extern void syscall_unregfunc(void);
 #define TRACE_EVENT_FN(name, proto, args, struct,		\
 		assign, print, reg, unreg)			\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#define TRACE_EVENT_FN_COND(name, proto, args, cond, struct,		\
+		assign, print, reg, unreg)			\
+	DECLARE_TRACE_CONDITION(name, PARAMS(proto),	\
+			PARAMS(args), PARAMS(cond))
 #define TRACE_EVENT_CONDITION(name, proto, args, cond,		\
 			      struct, assign, print)		\
 	DECLARE_TRACE_CONDITION(name, PARAMS(proto),		\

include/trace/define_trace.h

@@ -40,6 +40,11 @@
 		assign, print, reg, unreg)			\
 	DEFINE_TRACE_FN(name, reg, unreg)
 
+#undef TRACE_EVENT_FN_COND
+#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct,		\
+		assign, print, reg, unreg)			\
+	DEFINE_TRACE_FN(name, reg, unreg)
+
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args) \
 	DEFINE_TRACE(name)
@@ -93,6 +98,7 @@
 
 #undef TRACE_EVENT
 #undef TRACE_EVENT_FN
+#undef TRACE_EVENT_FN_COND
 #undef TRACE_EVENT_CONDITION
 #undef DECLARE_EVENT_CLASS
 #undef DEFINE_EVENT

include/trace/trace_events.h

@@ -123,6 +123,12 @@ TRACE_MAKE_SYSTEM_STR();
 	TRACE_EVENT(name, PARAMS(proto), PARAMS(args),			\
 		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
 
+#undef TRACE_EVENT_FN_COND
+#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct,	\
+		assign, print, reg, unreg)				\
+	TRACE_EVENT_CONDITION(name, PARAMS(proto), PARAMS(args), PARAMS(cond),		\
+		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
+
 #undef TRACE_EVENT_FLAGS
 #define TRACE_EVENT_FLAGS(name, value)					\
 	__TRACE_EVENT_FLAGS(name, value)

kernel/trace/bpf_trace.c

@@ -316,7 +316,7 @@ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type
 	return true;
 }
 
-static struct bpf_verifier_ops kprobe_prog_ops = {
+static const struct bpf_verifier_ops kprobe_prog_ops = {
 	.get_func_proto  = kprobe_prog_func_proto,
 	.is_valid_access = kprobe_prog_is_valid_access,
 };

kernel/trace/ring_buffer.c

@@ -1001,17 +1001,13 @@ static int rb_head_page_replace(struct buffer_page *old,
 
 /*
  * rb_tail_page_update - move the tail page forward
- *
- * Returns 1 if moved tail page, 0 if someone else did.
  */
-static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
+static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 			       struct buffer_page *tail_page,
 			       struct buffer_page *next_page)
 {
-	struct buffer_page *old_tail;
 	unsigned long old_entries;
 	unsigned long old_write;
-	int ret = 0;
 
 	/*
 	 * The tail page now needs to be moved forward.
@@ -1036,7 +1032,7 @@ static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 	 * it is, then it is up to us to update the tail
 	 * pointer.
 	 */
-	if (tail_page == cpu_buffer->tail_page) {
+	if (tail_page == READ_ONCE(cpu_buffer->tail_page)) {
 		/* Zero the write counter */
 		unsigned long val = old_write & ~RB_WRITE_MASK;
 		unsigned long eval = old_entries & ~RB_WRITE_MASK;
@@ -1061,14 +1057,9 @@ static int rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
 		 */
 		local_set(&next_page->page->commit, 0);
 
-		old_tail = cmpxchg(&cpu_buffer->tail_page,
-				   tail_page, next_page);
-
-		if (old_tail == tail_page)
-			ret = 1;
+		/* Again, either we update tail_page or an interrupt does */
+		(void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
 	}
-
-	return ret;
 }
 
 static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
@@ -2036,12 +2027,15 @@ rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
 	 * the tail page would have moved.
 	 */
 	if (ret == RB_PAGE_NORMAL) {
+		struct buffer_page *buffer_tail_page;
+
+		buffer_tail_page = READ_ONCE(cpu_buffer->tail_page);
 		/*
 		 * If the tail had moved passed next, then we need
 		 * to reset the pointer.
 		 */
-		if (cpu_buffer->tail_page != tail_page &&
-		    cpu_buffer->tail_page != next_page)
+		if (buffer_tail_page != tail_page &&
+		    buffer_tail_page != next_page)
 			rb_head_page_set_normal(cpu_buffer, new_head,
 						next_page,
 						RB_PAGE_HEAD);
@@ -2135,6 +2129,8 @@ rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	local_sub(length, &tail_page->write);
 }
 
+static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer);
+
 /*
  * This is the slow path, force gcc not to inline it.
  */
@@ -2147,7 +2143,6 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct buffer_page *next_page;
 	int ret;
-	u64 ts;
 
 	next_page = tail_page;
 
@@ -2221,20 +2216,17 @@ rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
 		}
 	}
 
-	ret = rb_tail_page_update(cpu_buffer, tail_page, next_page);
-	if (ret) {
-		/*
-		 * Nested commits always have zero deltas, so
-		 * just reread the time stamp
-		 */
-		ts = rb_time_stamp(buffer);
-		next_page->page->time_stamp = ts;
-	}
+	rb_tail_page_update(cpu_buffer, tail_page, next_page);
 
  out_again:
 
 	rb_reset_tail(cpu_buffer, tail, info);
 
+	/* Commit what we have for now. */
+	rb_end_commit(cpu_buffer);
+	/* rb_end_commit() decs committing */
+	local_inc(&cpu_buffer->committing);
+
 	/* fail and let the caller try again */
 	return ERR_PTR(-EAGAIN);
 
@@ -2362,7 +2354,7 @@ rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
 	addr = (unsigned long)event;
 	addr &= PAGE_MASK;
 
-	bpage = cpu_buffer->tail_page;
+	bpage = READ_ONCE(cpu_buffer->tail_page);
 
 	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
 		unsigned long write_mask =
@@ -2410,7 +2402,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
  again:
 	max_count = cpu_buffer->nr_pages * 100;
 
-	while (cpu_buffer->commit_page != cpu_buffer->tail_page) {
+	while (cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)) {
 		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
 			return;
 		if (RB_WARN_ON(cpu_buffer,
@@ -2419,8 +2411,10 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 		local_set(&cpu_buffer->commit_page->page->commit,
 			  rb_page_write(cpu_buffer->commit_page));
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
-		cpu_buffer->write_stamp =
-			cpu_buffer->commit_page->page->time_stamp;
+		/* Only update the write stamp if the page has an event */
+		if (rb_page_write(cpu_buffer->commit_page))
+			cpu_buffer->write_stamp =
+				cpu_buffer->commit_page->page->time_stamp;
 		/* add barrier to keep gcc from optimizing too much */
 		barrier();
 	}
@@ -2443,7 +2437,7 @@ rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
 	 * and pushed the tail page forward, we will be left with
 	 * a dangling commit that will never go forward.
 	 */
-	if (unlikely(cpu_buffer->commit_page != cpu_buffer->tail_page))
+	if (unlikely(cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)))
 		goto again;
 }
 
@@ -2699,7 +2693,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (unlikely(info->add_timestamp))
 		info->length += RB_LEN_TIME_EXTEND;
 
-	tail_page = info->tail_page = cpu_buffer->tail_page;
+	/* Don't let the compiler play games with cpu_buffer->tail_page */
+	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
 	write = local_add_return(info->length, &tail_page->write);
 
 	/* set write to only the index of the write */

kernel/trace/trace.h

@@ -363,8 +363,8 @@ struct trace_option_dentry {
  * @name: the name chosen to select it on the available_tracers file
  * @init: called when one switches to this tracer (echo name > current_tracer)
  * @reset: called when one switches to another tracer
- * @start: called when tracing is unpaused (echo 1 > tracing_enabled)
- * @stop: called when tracing is paused (echo 0 > tracing_enabled)
+ * @start: called when tracing is unpaused (echo 1 > tracing_on)
+ * @stop: called when tracing is paused (echo 0 > tracing_on)
  * @update_thresh: called when tracing_thresh is updated
  * @open: called when the trace file is opened
  * @pipe_open: called when the trace_pipe file is opened
@@ -467,8 +467,6 @@ enum {
 	TRACE_INTERNAL_IRQ_BIT,
 	TRACE_INTERNAL_SIRQ_BIT,
 
-	TRACE_CONTROL_BIT,
-
 	TRACE_BRANCH_BIT,
 /*
  * Abuse of the trace_recursion.

kernel/trace/trace_event_perf.c

@@ -334,7 +334,7 @@ static int perf_ftrace_function_register(struct perf_event *event)
 {
 	struct ftrace_ops *ops = &event->ftrace_ops;
 
-	ops->flags |= FTRACE_OPS_FL_CONTROL;
+	ops->flags |= FTRACE_OPS_FL_PER_CPU | FTRACE_OPS_FL_RCU;
 	ops->func = perf_ftrace_function_call;
 	return register_ftrace_function(ops);
 }

kernel/trace/trace_events_trigger.c

@@ -538,11 +538,12 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops,
 	list_add_rcu(&data->list, &file->triggers);
 	ret++;
 
+	update_cond_flag(file);
 	if (trace_event_trigger_enable_disable(file, 1) < 0) {
 		list_del_rcu(&data->list);
+		update_cond_flag(file);
 		ret--;
 	}
-	update_cond_flag(file);
 out:
 	return ret;
 }
@@ -570,8 +571,8 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops,
 		if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) {
 			unregistered = true;
 			list_del_rcu(&data->list);
-			update_cond_flag(file);
 			trace_event_trigger_enable_disable(file, 0);
+			update_cond_flag(file);
 			break;
 		}
 	}
@@ -1314,11 +1315,12 @@ static int event_enable_register_trigger(char *glob,
 	list_add_rcu(&data->list, &file->triggers);
 	ret++;
 
+	update_cond_flag(file);
 	if (trace_event_trigger_enable_disable(file, 1) < 0) {
 		list_del_rcu(&data->list);
+		update_cond_flag(file);
 		ret--;
 	}
-	update_cond_flag(file);
 out:
 	return ret;
 }
@@ -1339,8 +1341,8 @@ static void event_enable_unregister_trigger(char *glob,
 		    (enable_data->file == test_enable_data->file)) {
 			unregistered = true;
 			list_del_rcu(&data->list);
-			update_cond_flag(file);
 			trace_event_trigger_enable_disable(file, 0);
+			update_cond_flag(file);
 			break;
 		}
 	}

lib/seq_buf.c

@@ -306,10 +306,12 @@ int seq_buf_to_user(struct seq_buf *s, char __user *ubuf, int cnt)
 	if (!cnt)
 		return 0;
 
-	if (s->len <= s->readpos)
+	len = seq_buf_used(s);
+
+	if (len <= s->readpos)
 		return -EBUSY;
 
-	len = seq_buf_used(s) - s->readpos;
+	len -= s->readpos;
 	if (cnt > len)
 		cnt = len;
 	ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);

tools/testing/selftests/ftrace/test.d/instances/instance.tc

+#!/bin/sh
+# description: Test creation and deletion of trace instances
+
+if [ ! -d instances ] ; then
+    echo "no instance directory with this kernel"
+    exit_unsupported;
+fi
+
+fail() { # mesg
+    rmdir x y z 2>/dev/null
+    echo $1
+    set -e
+    exit $FAIL
+}
+
+cd instances
+
+# we don't want to fail on error
+set +e
+
+mkdir x
+rmdir x
+result=$?
+
+if [ $result -ne 0 ]; then
+    echo "instance rmdir not supported"
+    exit_unsupported
+fi
+
+instance_slam() {
+    while :; do
+	mkdir x
+	mkdir y
+	mkdir z
+	rmdir x
+	rmdir y
+	rmdir z
+    done 2>/dev/null
+}
+
+instance_slam &
+x=`jobs -l`
+p1=`echo $x | cut -d' ' -f2`
+echo $p1
+
+instance_slam &
+x=`jobs -l | tail -1`
+p2=`echo $x | cut -d' ' -f2`
+echo $p2
+
+instance_slam &
+x=`jobs -l | tail -1`
+p3=`echo $x | cut -d' ' -f2`
+echo $p3
+
+instance_slam &
+x=`jobs -l | tail -1`
+p4=`echo $x | cut -d' ' -f2`
+echo $p4
+
+instance_slam &
+x=`jobs -l | tail -1`
+p5=`echo $x | cut -d' ' -f2`
+echo $p5
+
+ls -lR >/dev/null
+sleep 1
+
+kill -1 $p1
+kill -1 $p2
+kill -1 $p3
+kill -1 $p4
+kill -1 $p5
+
+echo "Wait for processes to finish"
+wait $p1 $p2 $p3 $p4 $p5
+echo "all processes finished, wait for cleanup"
+
+mkdir x y z
+ls x y z
+rmdir x y z
+for d in x y z; do
+        if [ -d $d ]; then
+                fail "instance $d still exists"
+        fi
+done
+
+set -e
+
+exit 0