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
  ...

6 files changed, 300 insertions, 228 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 4228fd3682c3..45dd798bcd37 100644
--- a/kernel/trace/bpf_trace.c
+++ b/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,
 };
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 3f743b147247..eca592f977b2 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,8 +62,6 @@
 #define FTRACE_HASH_DEFAULT_BITS 10
 #define FTRACE_HASH_MAX_BITS 12
 
-#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_CONTROL)
-
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define INIT_OPS_HASH(opsname)	\
 	.func_hash		= &opsname.local_hash,			\
@@ -113,14 +111,9 @@ static int ftrace_disabled __read_mostly;
 
 static DEFINE_MUTEX(ftrace_lock);
 
-static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
-static struct ftrace_ops control_ops;
-
-static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
-				   struct ftrace_ops *op, struct pt_regs *regs);
 
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
@@ -203,7 +196,7 @@ void clear_ftrace_function(void)
 	ftrace_trace_function = ftrace_stub;
 }
 
-static void control_ops_disable_all(struct ftrace_ops *ops)
+static void per_cpu_ops_disable_all(struct ftrace_ops *ops)
 {
 	int cpu;
 
@@ -211,16 +204,19 @@ static void control_ops_disable_all(struct ftrace_ops *ops)
 		*per_cpu_ptr(ops->disabled, cpu) = 1;
 }
 
-static int control_ops_alloc(struct ftrace_ops *ops)
+static int per_cpu_ops_alloc(struct ftrace_ops *ops)
 {
 	int __percpu *disabled;
 
+	if (WARN_ON_ONCE(!(ops->flags & FTRACE_OPS_FL_PER_CPU)))
+		return -EINVAL;
+
 	disabled = alloc_percpu(int);
 	if (!disabled)
 		return -ENOMEM;
 
 	ops->disabled = disabled;
-	control_ops_disable_all(ops);
+	per_cpu_ops_disable_all(ops);
 	return 0;
 }
 
@@ -256,10 +252,11 @@ static inline void update_function_graph_func(void) { }
 static ftrace_func_t ftrace_ops_get_list_func(struct ftrace_ops *ops)
 {
 	/*
-	 * If this is a dynamic ops or we force list func,
+	 * If this is a dynamic, RCU, or per CPU ops, or we force list func,
 	 * then it needs to call the list anyway.
 	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC || FTRACE_FORCE_LIST_FUNC)
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU |
+			  FTRACE_OPS_FL_RCU) || FTRACE_FORCE_LIST_FUNC)
 		return ftrace_ops_list_func;
 
 	return ftrace_ops_get_func(ops);
@@ -383,26 +380,6 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
 	return 0;
 }
 
-static void add_ftrace_list_ops(struct ftrace_ops **list,
-				struct ftrace_ops *main_ops,
-				struct ftrace_ops *ops)
-{
-	int first = *list == &ftrace_list_end;
-	add_ftrace_ops(list, ops);
-	if (first)
-		add_ftrace_ops(&ftrace_ops_list, main_ops);
-}
-
-static int remove_ftrace_list_ops(struct ftrace_ops **list,
-				  struct ftrace_ops *main_ops,
-				  struct ftrace_ops *ops)
-{
-	int ret = remove_ftrace_ops(list, ops);
-	if (!ret && *list == &ftrace_list_end)
-		ret = remove_ftrace_ops(&ftrace_ops_list, main_ops);
-	return ret;
-}
-
 static void ftrace_update_trampoline(struct ftrace_ops *ops);
 
 static int __register_ftrace_function(struct ftrace_ops *ops)
@@ -430,14 +407,12 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 	if (!core_kernel_data((unsigned long)ops))
 		ops->flags |= FTRACE_OPS_FL_DYNAMIC;
 
-	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
-		if (control_ops_alloc(ops))
+	if (ops->flags & FTRACE_OPS_FL_PER_CPU) {
+		if (per_cpu_ops_alloc(ops))
 			return -ENOMEM;
-		add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
-		/* The control_ops needs the trampoline update */
-		ops = &control_ops;
-	} else
-		add_ftrace_ops(&ftrace_ops_list, ops);
+	}
+
+	add_ftrace_ops(&ftrace_ops_list, ops);
 
 	/* Always save the function, and reset at unregistering */
 	ops->saved_func = ops->func;
@@ -460,11 +435,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (WARN_ON(!(ops->flags & FTRACE_OPS_FL_ENABLED)))
 		return -EBUSY;
 
-	if (ops->flags & FTRACE_OPS_FL_CONTROL) {
-		ret = remove_ftrace_list_ops(&ftrace_control_list,
-					     &control_ops, ops);
-	} else
-		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
+	ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
 	if (ret < 0)
 		return ret;
@@ -1687,6 +1658,9 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops,
 		int in_hash = 0;
 		int match = 0;
 
+		if (rec->flags & FTRACE_FL_DISABLED)
+			continue;
+
 		if (all) {
 			/*
 			 * Only the filter_hash affects all records.
@@ -1940,7 +1914,7 @@ static int ftrace_hash_ipmodify_update(struct ftrace_ops *ops,
 	return __ftrace_hash_update_ipmodify(ops, old_hash, new_hash);
 }
 
-static void print_ip_ins(const char *fmt, unsigned char *p)
+static void print_ip_ins(const char *fmt, const unsigned char *p)
 {
 	int i;
 
@@ -1952,6 +1926,31 @@ static void print_ip_ins(const char *fmt, unsigned char *p)
 
 static struct ftrace_ops *
 ftrace_find_tramp_ops_any(struct dyn_ftrace *rec);
+static struct ftrace_ops *
+ftrace_find_tramp_ops_next(struct dyn_ftrace *rec, struct ftrace_ops *ops);
+
+enum ftrace_bug_type ftrace_bug_type;
+const void *ftrace_expected;
+
+static void print_bug_type(void)
+{
+	switch (ftrace_bug_type) {
+	case FTRACE_BUG_UNKNOWN:
+		break;
+	case FTRACE_BUG_INIT:
+		pr_info("Initializing ftrace call sites\n");
+		break;
+	case FTRACE_BUG_NOP:
+		pr_info("Setting ftrace call site to NOP\n");
+		break;
+	case FTRACE_BUG_CALL:
+		pr_info("Setting ftrace call site to call ftrace function\n");
+		break;
+	case FTRACE_BUG_UPDATE:
+		pr_info("Updating ftrace call site to call a different ftrace function\n");
+		break;
+	}
+}
 
 /**
  * ftrace_bug - report and shutdown function tracer
@@ -1979,8 +1978,12 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		FTRACE_WARN_ON_ONCE(1);
 		pr_info("ftrace failed to modify ");
 		print_ip_sym(ip);
-		print_ip_ins(" actual: ", (unsigned char *)ip);
+		print_ip_ins(" actual:   ", (unsigned char *)ip);
 		pr_cont("\n");
+		if (ftrace_expected) {
+			print_ip_ins(" expected: ", ftrace_expected);
+			pr_cont("\n");
+		}
 		break;
 	case -EPERM:
 		FTRACE_WARN_ON_ONCE(1);
@@ -1992,6 +1995,7 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 		pr_info("ftrace faulted on unknown error ");
 		print_ip_sym(ip);
 	}
+	print_bug_type();
 	if (rec) {
 		struct ftrace_ops *ops = NULL;
 
@@ -2000,15 +2004,19 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec)
 			rec->flags & FTRACE_FL_REGS ? " R" : "  ");
 		if (rec->flags & FTRACE_FL_TRAMP_EN) {
 			ops = ftrace_find_tramp_ops_any(rec);
-			if (ops)
-				pr_cont("\ttramp: %pS",
-					(void *)ops->trampoline);
-			else
+			if (ops) {
+				do {
+					pr_cont("\ttramp: %pS (%pS)",
+						(void *)ops->trampoline,
+						(void *)ops->func);
+					ops = ftrace_find_tramp_ops_next(rec, ops);
+				} while (ops);
+			} else
 				pr_cont("\ttramp: ERROR!");
 
 		}
 		ip = ftrace_get_addr_curr(rec);
-		pr_cont(" expected tramp: %lx\n", ip);
+		pr_cont("\n expected tramp: %lx\n", ip);
 	}
 }
 
@@ -2016,6 +2024,11 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 {
 	unsigned long flag = 0UL;
 
+	ftrace_bug_type = FTRACE_BUG_UNKNOWN;
+
+	if (rec->flags & FTRACE_FL_DISABLED)
+		return FTRACE_UPDATE_IGNORE;
+
 	/*
 	 * If we are updating calls:
 	 *
@@ -2077,9 +2090,12 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 		 *   from the save regs, to a non-save regs function or
 		 *   vice versa, or from a trampoline call.
 		 */
-		if (flag & FTRACE_FL_ENABLED)
+		if (flag & FTRACE_FL_ENABLED) {
+			ftrace_bug_type = FTRACE_BUG_CALL;
 			return FTRACE_UPDATE_MAKE_CALL;
+		}
 
+		ftrace_bug_type = FTRACE_BUG_UPDATE;
 		return FTRACE_UPDATE_MODIFY_CALL;
 	}
 
@@ -2096,6 +2112,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update)
 					FTRACE_FL_REGS_EN);
 	}
 
+	ftrace_bug_type = FTRACE_BUG_NOP;
 	return FTRACE_UPDATE_MAKE_NOP;
 }
 
@@ -2145,6 +2162,24 @@ ftrace_find_tramp_ops_any(struct dyn_ftrace *rec)
 }
 
 static struct ftrace_ops *
+ftrace_find_tramp_ops_next(struct dyn_ftrace *rec,
+			   struct ftrace_ops *op)
+{
+	unsigned long ip = rec->ip;
+
+	while_for_each_ftrace_op(op) {
+
+		if (!op->trampoline)
+			continue;
+
+		if (hash_contains_ip(ip, op->func_hash))
+			return op;
+	} 
+
+	return NULL;
+}
+
+static struct ftrace_ops *
 ftrace_find_tramp_ops_curr(struct dyn_ftrace *rec)
 {
 	struct ftrace_ops *op;
@@ -2307,17 +2342,22 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_update_record(rec, enable);
 
+	ftrace_bug_type = FTRACE_BUG_UNKNOWN;
+
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
 	case FTRACE_UPDATE_MAKE_CALL:
+		ftrace_bug_type = FTRACE_BUG_CALL;
 		return ftrace_make_call(rec, ftrace_addr);
 
 	case FTRACE_UPDATE_MAKE_NOP:
+		ftrace_bug_type = FTRACE_BUG_NOP;
 		return ftrace_make_nop(NULL, rec, ftrace_old_addr);
 
 	case FTRACE_UPDATE_MODIFY_CALL:
+		ftrace_bug_type = FTRACE_BUG_UPDATE;
 		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
@@ -2425,6 +2465,7 @@ ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 
 	ret = ftrace_make_nop(mod, rec, MCOUNT_ADDR);
 	if (ret) {
+		ftrace_bug_type = FTRACE_BUG_INIT;
 		ftrace_bug(ret, rec);
 		return 0;
 	}
@@ -2566,7 +2607,7 @@ void __weak arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 {
 }
 
-static void control_ops_free(struct ftrace_ops *ops)
+static void per_cpu_ops_free(struct ftrace_ops *ops)
 {
 	free_percpu(ops->disabled);
 }
@@ -2667,13 +2708,13 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 
 	if (!command || !ftrace_enabled) {
 		/*
-		 * If these are control ops, they still need their
+		 * If these are per_cpu ops, they still need their
 		 * per_cpu field freed. Since, function tracing is
 		 * not currently active, we can just free them
 		 * without synchronizing all CPUs.
 		 */
-		if (ops->flags & FTRACE_OPS_FL_CONTROL)
-			control_ops_free(ops);
+		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
+			per_cpu_ops_free(ops);
 		return 0;
 	}
 
@@ -2714,7 +2755,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	/*
 	 * Dynamic ops may be freed, we must make sure that all
 	 * callers are done before leaving this function.
-	 * The same goes for freeing the per_cpu data of the control
+	 * The same goes for freeing the per_cpu data of the per_cpu
 	 * ops.
 	 *
 	 * Again, normal synchronize_sched() is not good enough.
@@ -2725,13 +2766,13 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 	 * infrastructure to do the synchronization, thus we must do it
 	 * ourselves.
 	 */
-	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_PER_CPU)) {
 		schedule_on_each_cpu(ftrace_sync);
 
 		arch_ftrace_trampoline_free(ops);
 
-		if (ops->flags & FTRACE_OPS_FL_CONTROL)
-			control_ops_free(ops);
+		if (ops->flags & FTRACE_OPS_FL_PER_CPU)
+			per_cpu_ops_free(ops);
 	}
 
 	return 0;
@@ -2798,9 +2839,9 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 	if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
 		return 0;
 
-	/* If ops traces all mods, we already accounted for it */
+	/* If ops traces all then it includes this function */
 	if (ops_traces_mod(ops))
-		return 0;
+		return 1;
 
 	/* The function must be in the filter */
 	if (!ftrace_hash_empty(ops->func_hash->filter_hash) &&
@@ -2814,64 +2855,41 @@ ops_references_rec(struct ftrace_ops *ops, struct dyn_ftrace *rec)
 	return 1;
 }
 
-static int referenced_filters(struct dyn_ftrace *rec)
-{
-	struct ftrace_ops *ops;
-	int cnt = 0;
-
-	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
-		if (ops_references_rec(ops, rec))
-		    cnt++;
-	}
-
-	return cnt;
-}
-
 static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 {
 	struct ftrace_page *pg;
 	struct dyn_ftrace *p;
 	cycle_t start, stop;
 	unsigned long update_cnt = 0;
-	unsigned long ref = 0;
-	bool test = false;
+	unsigned long rec_flags = 0;
 	int i;
 
+	start = ftrace_now(raw_smp_processor_id());
+
 	/*
-	 * When adding a module, we need to check if tracers are
-	 * currently enabled and if they are set to trace all functions.
-	 * If they are, we need to enable the module functions as well
-	 * as update the reference counts for those function records.
+	 * When a module is loaded, this function is called to convert
+	 * the calls to mcount in its text to nops, and also to create
+	 * an entry in the ftrace data. Now, if ftrace is activated
+	 * after this call, but before the module sets its text to
+	 * read-only, the modification of enabling ftrace can fail if
+	 * the read-only is done while ftrace is converting the calls.
+	 * To prevent this, the module's records are set as disabled
+	 * and will be enabled after the call to set the module's text
+	 * to read-only.
 	 */
-	if (mod) {
-		struct ftrace_ops *ops;
-
-		for (ops = ftrace_ops_list;
-		     ops != &ftrace_list_end; ops = ops->next) {
-			if (ops->flags & FTRACE_OPS_FL_ENABLED) {
-				if (ops_traces_mod(ops))
-					ref++;
-				else
-					test = true;
-			}
-		}
-	}
-
-	start = ftrace_now(raw_smp_processor_id());
+	if (mod)
+		rec_flags |= FTRACE_FL_DISABLED;
 
 	for (pg = new_pgs; pg; pg = pg->next) {
 
 		for (i = 0; i < pg->index; i++) {
-			int cnt = ref;
 
 			/* If something went wrong, bail without enabling anything */
 			if (unlikely(ftrace_disabled))
 				return -1;
 
 			p = &pg->records[i];
-			if (test)
-				cnt += referenced_filters(p);
-			p->flags = cnt;
+			p->flags = rec_flags;
 
 			/*
 			 * Do the initial record conversion from mcount jump
@@ -2881,21 +2899,6 @@ static int ftrace_update_code(struct module *mod, struct ftrace_page *new_pgs)
 				break;
 
 			update_cnt++;
-
-			/*
-			 * If the tracing is enabled, go ahead and enable the record.
-			 *
-			 * The reason not to enable the record immediatelly is the
-			 * inherent check of ftrace_make_nop/ftrace_make_call for
-			 * correct previous instructions.  Making first the NOP
-			 * conversion puts the module to the correct state, thus
-			 * passing the ftrace_make_call check.
-			 */
-			if (ftrace_start_up && cnt) {
-				int failed = __ftrace_replace_code(p, 1);
-				if (failed)
-					ftrace_bug(failed, p);
-			}
 		}
 	}
 
@@ -3258,7 +3261,7 @@ static int t_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "%ps", (void *)rec->ip);
 	if (iter->flags & FTRACE_ITER_ENABLED) {
-		struct ftrace_ops *ops = NULL;
+		struct ftrace_ops *ops;
 
 		seq_printf(m, " (%ld)%s%s",
 			   ftrace_rec_count(rec),
@@ -3266,14 +3269,19 @@ static int t_show(struct seq_file *m, void *v)
 			   rec->flags & FTRACE_FL_IPMODIFY ? " I" : "  ");
 		if (rec->flags & FTRACE_FL_TRAMP_EN) {
 			ops = ftrace_find_tramp_ops_any(rec);
-			if (ops)
-				seq_printf(m, "\ttramp: %pS",
-					   (void *)ops->trampoline);
-			else
+			if (ops) {
+				do {
+					seq_printf(m, "\ttramp: %pS (%pS)",
+						   (void *)ops->trampoline,
+						   (void *)ops->func);
+					add_trampoline_func(m, ops, rec);
+					ops = ftrace_find_tramp_ops_next(rec, ops);
+				} while (ops);
+			} else
 				seq_puts(m, "\ttramp: ERROR!");
-
+		} else {
+			add_trampoline_func(m, NULL, rec);
 		}
-		add_trampoline_func(m, ops, rec);
 	}	
 
 	seq_putc(m, '\n');
@@ -4898,6 +4906,19 @@ static int ftrace_process_locs(struct module *mod,
 
 #define next_to_ftrace_page(p) container_of(p, struct ftrace_page, next)
 
+static int referenced_filters(struct dyn_ftrace *rec)
+{
+	struct ftrace_ops *ops;
+	int cnt = 0;
+
+	for (ops = ftrace_ops_list; ops != &ftrace_list_end; ops = ops->next) {
+		if (ops_references_rec(ops, rec))
+		    cnt++;
+	}
+
+	return cnt;
+}
+
 void ftrace_release_mod(struct module *mod)
 {
 	struct dyn_ftrace *rec;
@@ -4940,41 +4961,112 @@ void ftrace_release_mod(struct module *mod)
 	mutex_unlock(&ftrace_lock);
 }
 
-static void ftrace_init_module(struct module *mod,
-			       unsigned long *start, unsigned long *end)
+static void ftrace_module_enable(struct module *mod)
 {
-	if (ftrace_disabled || start == end)
-		return;
-	ftrace_process_locs(mod, start, end);
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+
+	mutex_lock(&ftrace_lock);
+
+	if (ftrace_disabled)
+		goto out_unlock;
+
+	/*
+	 * If the tracing is enabled, go ahead and enable the record.
+	 *
+	 * The reason not to enable the record immediatelly is the
+	 * inherent check of ftrace_make_nop/ftrace_make_call for
+	 * correct previous instructions.  Making first the NOP
+	 * conversion puts the module to the correct state, thus
+	 * passing the ftrace_make_call check.
+	 *
+	 * We also delay this to after the module code already set the
+	 * text to read-only, as we now need to set it back to read-write
+	 * so that we can modify the text.
+	 */
+	if (ftrace_start_up)
+		ftrace_arch_code_modify_prepare();
+
+	do_for_each_ftrace_rec(pg, rec) {
+		int cnt;
+		/*
+		 * do_for_each_ftrace_rec() is a double loop.
+		 * module text shares the pg. If a record is
+		 * not part of this module, then skip this pg,
+		 * which the "break" will do.
+		 */
+		if (!within_module_core(rec->ip, mod))
+			break;
+
+		cnt = 0;
+
+		/*
+		 * When adding a module, we need to check if tracers are
+		 * currently enabled and if they are, and can trace this record,
+		 * we need to enable the module functions as well as update the
+		 * reference counts for those function records.
+		 */
+		if (ftrace_start_up)
+			cnt += referenced_filters(rec);
+
+		/* This clears FTRACE_FL_DISABLED */
+		rec->flags = cnt;
+
+		if (ftrace_start_up && cnt) {
+			int failed = __ftrace_replace_code(rec, 1);
+			if (failed) {
+				ftrace_bug(failed, rec);
+				goto out_loop;
+			}
+		}
+
+	} while_for_each_ftrace_rec();
+
+ out_loop:
+	if (ftrace_start_up)
+		ftrace_arch_code_modify_post_process();
+
+ out_unlock:
+	mutex_unlock(&ftrace_lock);
 }
 
 void ftrace_module_init(struct module *mod)
 {
-	ftrace_init_module(mod, mod->ftrace_callsites,
-			   mod->ftrace_callsites +
-			   mod->num_ftrace_callsites);
+	if (ftrace_disabled || !mod->num_ftrace_callsites)
+		return;
+
+	ftrace_process_locs(mod, mod->ftrace_callsites,
+			    mod->ftrace_callsites + mod->num_ftrace_callsites);
 }
 
-static int ftrace_module_notify_exit(struct notifier_block *self,
-				     unsigned long val, void *data)
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
 {
 	struct module *mod = data;
 
-	if (val == MODULE_STATE_GOING)
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ftrace_module_enable(mod);
+		break;
+	case MODULE_STATE_GOING:
 		ftrace_release_mod(mod);
+		break;
+	default:
+		break;
+	}
 
 	return 0;
 }
 #else
-static int ftrace_module_notify_exit(struct notifier_block *self,
-				     unsigned long val, void *data)
+static int ftrace_module_notify(struct notifier_block *self,
+				unsigned long val, void *data)
 {
 	return 0;
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_exit_nb = {
-	.notifier_call = ftrace_module_notify_exit,
+struct notifier_block ftrace_module_nb = {
+	.notifier_call = ftrace_module_notify,
 	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
 };
 
@@ -5006,7 +5098,7 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_exit_nb);
+	ret = register_module_notifier(&ftrace_module_nb);
 	if (ret)
 		pr_warning("Failed to register trace ftrace module exit notifier\n");
 
@@ -5116,44 +5208,6 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 	tr->ops->func = ftrace_stub;
 }
 
-static void
-ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
-			struct ftrace_ops *op, struct pt_regs *regs)
-{
-	if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
-		return;
-
-	/*
-	 * Some of the ops may be dynamically allocated,
-	 * they must be freed after a synchronize_sched().
-	 */
-	preempt_disable_notrace();
-	trace_recursion_set(TRACE_CONTROL_BIT);
-
-	/*
-	 * Control funcs (perf) uses RCU. Only trace if
-	 * RCU is currently active.
-	 */
-	if (!rcu_is_watching())
-		goto out;
-
-	do_for_each_ftrace_op(op, ftrace_control_list) {
-		if (!(op->flags & FTRACE_OPS_FL_STUB) &&
-		    !ftrace_function_local_disabled(op) &&
-		    ftrace_ops_test(op, ip, regs))
-			op->func(ip, parent_ip, op, regs);
-	} while_for_each_ftrace_op(op);
- out:
-	trace_recursion_clear(TRACE_CONTROL_BIT);
-	preempt_enable_notrace();
-}
-
-static struct ftrace_ops control_ops = {
-	.func	= ftrace_ops_control_func,
-	.flags	= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
-	INIT_OPS_HASH(control_ops)
-};
-
 static inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
@@ -5170,8 +5224,22 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	 * they must be freed after a synchronize_sched().
 	 */
 	preempt_disable_notrace();
+
 	do_for_each_ftrace_op(op, ftrace_ops_list) {
-		if (ftrace_ops_test(op, ip, regs)) {
+		/*
+		 * Check the following for each ops before calling their func:
+		 *  if RCU flag is set, then rcu_is_watching() must be true
+		 *  if PER_CPU is set, then ftrace_function_local_disable()
+		 *                          must be false
+		 *  Otherwise test if the ip matches the ops filter
+		 *
+		 * If any of the above fails then the op->func() is not executed.
+		 */
+		if ((!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) &&
+		    (!(op->flags & FTRACE_OPS_FL_PER_CPU) ||
+		     !ftrace_function_local_disabled(op)) &&
+		    ftrace_ops_test(op, ip, regs)) {
+		    
 			if (FTRACE_WARN_ON(!op->func)) {
 				pr_warn("op=%p %pS\n", op, op);
 				goto out;
@@ -5195,7 +5263,7 @@ out:
  * being NULL, or CONFIG_DYNAMIC_FTRACE_WITH_REGS.
  * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved.
  * An architecture can pass partial regs with ftrace_ops and still
- * set the ARCH_SUPPORT_FTARCE_OPS.
+ * set the ARCH_SUPPORTS_FTRACE_OPS.
  */
 #if ARCH_SUPPORTS_FTRACE_OPS
 static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
@@ -5212,20 +5280,29 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 
 /*
  * If there's only one function registered but it does not support
- * recursion, this function will be called by the mcount trampoline.
- * This function will handle recursion protection.
+ * recursion, needs RCU protection and/or requires per cpu handling, then
+ * this function will be called by the mcount trampoline.
  */
-static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
+static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 				   struct ftrace_ops *op, struct pt_regs *regs)
 {
 	int bit;
 
+	if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching())
+		return;
+
 	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
-	op->func(ip, parent_ip, op, regs);
+	preempt_disable_notrace();
 
+	if (!(op->flags & FTRACE_OPS_FL_PER_CPU) ||
+	    !ftrace_function_local_disabled(op)) {
+		op->func(ip, parent_ip, op, regs);
+	}
+
+	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
 
@@ -5243,12 +5320,12 @@ static void ftrace_ops_recurs_func(unsigned long ip, unsigned long parent_ip,
 ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
 {
 	/*
-	 * If the func handles its own recursion, call it directly.
-	 * Otherwise call the recursion protected function that
-	 * will call the ftrace ops function.
+	 * If the function does not handle recursion, needs to be RCU safe,
+	 * or does per cpu logic, then we need to call the assist handler.
 	 */
-	if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE))
-		return ftrace_ops_recurs_func;
+	if (!(ops->flags & FTRACE_OPS_FL_RECURSION_SAFE) ||
+	    ops->flags & (FTRACE_OPS_FL_RCU | FTRACE_OPS_FL_PER_CPU))
+		return ftrace_ops_assist_func;
 
 	return ops->func;
 }
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9c6045a27ba3..95181e36891a 100644
--- a/kernel/trace/ring_buffer.c
+++ b/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 */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 919d9d07686f..8414fa40bf27 100644
--- a/kernel/trace/trace.h
+++ b/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.
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index cc9f7a9319be..00df25fd86ef 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/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);
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 4b5e8ed68d77..b38f617b6181 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/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;
 		}
 	}