1 files changed, 96 insertions, 69 deletions

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 7a809e32105..759d5e00451 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -12,10 +12,6 @@
 #include "trace.h"
 
 static DEFINE_MUTEX(syscall_trace_lock);
-static int sys_refcount_enter;
-static int sys_refcount_exit;
-static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
-static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
 static int syscall_enter_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data);
@@ -41,7 +37,7 @@ static inline bool arch_syscall_match_sym_name(const char *sym, const char *name
 	/*
 	 * Only compare after the "sys" prefix. Archs that use
 	 * syscall wrappers may have syscalls symbols aliases prefixed
-	 * with "SyS" instead of "sys", leading to an unwanted
+	 * with ".SyS" or ".sys" instead of "sys", leading to an unwanted
 	 * mismatch.
 	 */
 	return !strcmp(sym + 3, name + 3);
@@ -179,7 +175,7 @@ print_syscall_exit(struct trace_iterator *iter, int flags,
 	entry = syscall_nr_to_meta(syscall);
 
 	if (!entry) {
-		trace_seq_printf(s, "\n");
+		trace_seq_putc(s, '\n');
 		return TRACE_TYPE_HANDLED;
 	}
 
@@ -204,8 +200,8 @@ extern char *__bad_type_size(void);
 		#type, #name, offsetof(typeof(trace), name),		\
 		sizeof(trace.name), is_signed_type(type)
 
-static
-int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
+static int __init
+__set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 {
 	int i;
 	int pos = 0;
@@ -232,7 +228,7 @@ int  __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
 	return pos;
 }
 
-static int set_syscall_print_fmt(struct ftrace_event_call *call)
+static int __init set_syscall_print_fmt(struct ftrace_event_call *call)
 {
 	char *print_fmt;
 	int len;
@@ -257,7 +253,7 @@ static int set_syscall_print_fmt(struct ftrace_event_call *call)
 	return 0;
 }
 
-static void free_syscall_print_fmt(struct ftrace_event_call *call)
+static void __init free_syscall_print_fmt(struct ftrace_event_call *call)
 {
 	struct syscall_metadata *entry = call->data;
 
@@ -265,7 +261,7 @@ static void free_syscall_print_fmt(struct ftrace_event_call *call)
 		kfree(call->print_fmt);
 }
 
-static int syscall_enter_define_fields(struct ftrace_event_call *call)
+static int __init syscall_enter_define_fields(struct ftrace_event_call *call)
 {
 	struct syscall_trace_enter trace;
 	struct syscall_metadata *meta = call->data;
@@ -288,7 +284,7 @@ static int syscall_enter_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-static int syscall_exit_define_fields(struct ftrace_event_call *call)
+static int __init syscall_exit_define_fields(struct ftrace_event_call *call)
 {
 	struct syscall_trace_exit trace;
 	int ret;
@@ -303,19 +299,29 @@ static int syscall_exit_define_fields(struct ftrace_event_call *call)
 	return ret;
 }
 
-static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
+static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 {
+	struct trace_array *tr = data;
+	struct ftrace_event_file *ftrace_file;
 	struct syscall_trace_enter *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
 	int syscall_nr;
 	int size;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, enabled_enter_syscalls))
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
+	ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
+	if (!ftrace_file)
+		return;
+
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
@@ -324,8 +330,12 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
-	event = trace_current_buffer_lock_reserve(&buffer,
-			sys_data->enter_event->event.type, size, 0, 0);
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
+			sys_data->enter_event->event.type, size, irq_flags, pc);
 	if (!event)
 		return;
 
@@ -333,31 +343,45 @@ static void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	entry->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
 
-	if (!filter_current_check_discard(buffer, sys_data->enter_event,
-					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+	event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+				    irq_flags, pc);
 }
 
-static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
+static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 {
+	struct trace_array *tr = data;
+	struct ftrace_event_file *ftrace_file;
 	struct syscall_trace_exit *entry;
 	struct syscall_metadata *sys_data;
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
+	unsigned long irq_flags;
+	int pc;
 	int syscall_nr;
 
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0)
 		return;
-	if (!test_bit(syscall_nr, enabled_exit_syscalls))
+
+	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
+	ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
+	if (!ftrace_file)
+		return;
+
+	if (ftrace_trigger_soft_disabled(ftrace_file))
 		return;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
 		return;
 
-	event = trace_current_buffer_lock_reserve(&buffer,
-			sys_data->exit_event->event.type, sizeof(*entry), 0, 0);
+	local_save_flags(irq_flags);
+	pc = preempt_count();
+
+	buffer = tr->trace_buffer.buffer;
+	event = trace_buffer_lock_reserve(buffer,
+			sys_data->exit_event->event.type, sizeof(*entry),
+			irq_flags, pc);
 	if (!event)
 		return;
 
@@ -365,13 +389,14 @@ static void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	entry->nr = syscall_nr;
 	entry->ret = syscall_get_return_value(current, regs);
 
-	if (!filter_current_check_discard(buffer, sys_data->exit_event,
-					  entry, event))
-		trace_current_buffer_unlock_commit(buffer, event, 0, 0);
+	event_trigger_unlock_commit(ftrace_file, buffer, event, entry,
+				    irq_flags, pc);
 }
 
-static int reg_event_syscall_enter(struct ftrace_event_call *call)
+static int reg_event_syscall_enter(struct ftrace_event_file *file,
+				   struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int ret = 0;
 	int num;
 
@@ -379,33 +404,37 @@ static int reg_event_syscall_enter(struct ftrace_event_call *call)
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_refcount_enter)
-		ret = register_trace_sys_enter(ftrace_syscall_enter, NULL);
+	if (!tr->sys_refcount_enter)
+		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
 	if (!ret) {
-		set_bit(num, enabled_enter_syscalls);
-		sys_refcount_enter++;
+		rcu_assign_pointer(tr->enter_syscall_files[num], file);
+		tr->sys_refcount_enter++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-static void unreg_event_syscall_enter(struct ftrace_event_call *call)
+static void unreg_event_syscall_enter(struct ftrace_event_file *file,
+				      struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
-	sys_refcount_enter--;
-	clear_bit(num, enabled_enter_syscalls);
-	if (!sys_refcount_enter)
-		unregister_trace_sys_enter(ftrace_syscall_enter, NULL);
+	tr->sys_refcount_enter--;
+	rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
+	if (!tr->sys_refcount_enter)
+		unregister_trace_sys_enter(ftrace_syscall_enter, tr);
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int reg_event_syscall_exit(struct ftrace_event_call *call)
+static int reg_event_syscall_exit(struct ftrace_event_file *file,
+				  struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int ret = 0;
 	int num;
 
@@ -413,32 +442,34 @@ static int reg_event_syscall_exit(struct ftrace_event_call *call)
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
-	if (!sys_refcount_exit)
-		ret = register_trace_sys_exit(ftrace_syscall_exit, NULL);
+	if (!tr->sys_refcount_exit)
+		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
 	if (!ret) {
-		set_bit(num, enabled_exit_syscalls);
-		sys_refcount_exit++;
+		rcu_assign_pointer(tr->exit_syscall_files[num], file);
+		tr->sys_refcount_exit++;
 	}
 	mutex_unlock(&syscall_trace_lock);
 	return ret;
 }
 
-static void unreg_event_syscall_exit(struct ftrace_event_call *call)
+static void unreg_event_syscall_exit(struct ftrace_event_file *file,
+				     struct ftrace_event_call *call)
 {
+	struct trace_array *tr = file->tr;
 	int num;
 
 	num = ((struct syscall_metadata *)call->data)->syscall_nr;
 	if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
 		return;
 	mutex_lock(&syscall_trace_lock);
-	sys_refcount_exit--;
-	clear_bit(num, enabled_exit_syscalls);
-	if (!sys_refcount_exit)
-		unregister_trace_sys_exit(ftrace_syscall_exit, NULL);
+	tr->sys_refcount_exit--;
+	rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
+	if (!tr->sys_refcount_exit)
+		unregister_trace_sys_exit(ftrace_syscall_exit, tr);
 	mutex_unlock(&syscall_trace_lock);
 }
 
-static int init_syscall_trace(struct ftrace_event_call *call)
+static int __init init_syscall_trace(struct ftrace_event_call *call)
 {
 	int id;
 	int num;
@@ -471,7 +502,7 @@ struct trace_event_functions exit_syscall_print_funcs = {
 	.trace		= print_syscall_exit,
 };
 
-struct ftrace_event_class event_class_syscall_enter = {
+struct ftrace_event_class __refdata event_class_syscall_enter = {
 	.system		= "syscalls",
 	.reg		= syscall_enter_register,
 	.define_fields	= syscall_enter_define_fields,
@@ -479,7 +510,7 @@ struct ftrace_event_class event_class_syscall_enter = {
 	.raw_init	= init_syscall_trace,
 };
 
-struct ftrace_event_class event_class_syscall_exit = {
+struct ftrace_event_class __refdata event_class_syscall_exit = {
 	.system		= "syscalls",
 	.reg		= syscall_exit_register,
 	.define_fields	= syscall_exit_define_fields,
@@ -545,15 +576,15 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
+	head = this_cpu_ptr(sys_data->enter_event->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	/* get the size after alignment with the u32 buffer size field */
 	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
 	size = ALIGN(size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		      "perf buffer not large enough"))
-		return;
-
 	rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
 				sys_data->enter_event->event.type, regs, &rctx);
 	if (!rec)
@@ -562,8 +593,6 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
-
-	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
@@ -621,18 +650,14 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	head = this_cpu_ptr(sys_data->exit_event->perf_events);
+	if (hlist_empty(head))
+		return;
+
 	/* We can probably do that at build time */
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
 
-	/*
-	 * Impossible, but be paranoid with the future
-	 * How to put this check outside runtime?
-	 */
-	if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-		"exit event has grown above perf buffer size"))
-		return;
-
 	rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
 				sys_data->exit_event->event.type, regs, &rctx);
 	if (!rec)
@@ -640,8 +665,6 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
-
-	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
 }
 
@@ -685,11 +708,13 @@ static void perf_sysexit_disable(struct ftrace_event_call *call)
 static int syscall_enter_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data)
 {
+	struct ftrace_event_file *file = data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return reg_event_syscall_enter(event);
+		return reg_event_syscall_enter(file, event);
 	case TRACE_REG_UNREGISTER:
-		unreg_event_syscall_enter(event);
+		unreg_event_syscall_enter(file, event);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS
@@ -711,11 +736,13 @@ static int syscall_enter_register(struct ftrace_event_call *event,
 static int syscall_exit_register(struct ftrace_event_call *event,
 				 enum trace_reg type, void *data)
 {
+	struct ftrace_event_file *file = data;
+
 	switch (type) {
 	case TRACE_REG_REGISTER:
-		return reg_event_syscall_exit(event);
+		return reg_event_syscall_exit(file, event);
 	case TRACE_REG_UNREGISTER:
-		unreg_event_syscall_exit(event);
+		unreg_event_syscall_exit(file, event);
 		return 0;
 
 #ifdef CONFIG_PERF_EVENTS