tracing: Move syscalls metadata handling from arch to core

Most of the syscalls metadata processing is done from arch.
But these operations are mostly generic accross archs. Especially now
that we have a common variable name that expresses the number of
syscalls supported by an arch: NR_syscalls, the only remaining bits
that need to reside in arch is the syscall nr to addr translation.

v2: Compare syscalls symbols only after the "sys" prefix so that we
    avoid spurious mismatches with archs that have syscalls wrappers,
    in which case syscalls symbols have "SyS" prefixed aliases.
    (Reported by: Heiko Carstens)
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Acked-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>

arch/s390/kernel/ftrace.c

@@ -206,73 +206,10 @@ unsigned long prepare_ftrace_return(unsigned long ip, unsigned long parent)
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
 extern unsigned int sys_call_table[];
 
-static struct syscall_metadata **syscalls_metadata;
-
-struct syscall_metadata *syscall_nr_to_meta(int nr)
-{
-	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
-		return NULL;
-
-	return syscalls_metadata[nr];
-}
-
-int syscall_name_to_nr(char *name)
-{
-	int i;
-
-	if (!syscalls_metadata)
-		return -1;
-	for (i = 0; i < NR_syscalls; i++)
-		if (syscalls_metadata[i])
-			if (!strcmp(syscalls_metadata[i]->name, name))
-				return i;
-	return -1;
-}
-
-void set_syscall_enter_id(int num, int id)
-{
-	syscalls_metadata[num]->enter_id = id;
-}
-
-void set_syscall_exit_id(int num, int id)
+unsigned long __init arch_syscall_addr(int nr)
 {
-	syscalls_metadata[num]->exit_id = id;
-}
-
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
-{
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
-	char str[KSYM_SYMBOL_LEN];
-
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
-	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
-
-	for ( ; start < stop; start++) {
-		if (start->name && !strcmp(start->name + 3, str + 3))
-			return start;
-	}
-	return NULL;
-}
-
-static int __init arch_init_ftrace_syscalls(void)
-{
-	struct syscall_metadata *meta;
-	int i;
-	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls,
-				    GFP_KERNEL);
-	if (!syscalls_metadata)
-		return -ENOMEM;
-	for (i = 0; i < NR_syscalls; i++) {
-		meta = find_syscall_meta((unsigned long)sys_call_table[i]);
-		syscalls_metadata[i] = meta;
-	}
-	return 0;
+	return (unsigned long)sys_call_table[nr];
 }
-arch_initcall(arch_init_ftrace_syscalls);
 #endif

arch/x86/kernel/ftrace.c

@@ -470,82 +470,10 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
 extern unsigned long *sys_call_table;
 
-static struct syscall_metadata **syscalls_metadata;
-
-static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
-{
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
-	char str[KSYM_SYMBOL_LEN];
-
-
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
-	kallsyms_lookup((unsigned long) syscall, NULL, NULL, NULL, str);
-
-	for ( ; start < stop; start++) {
-		if (start->name && !strcmp(start->name, str))
-			return start;
-	}
-	return NULL;
-}
-
-struct syscall_metadata *syscall_nr_to_meta(int nr)
-{
-	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
-		return NULL;
-
-	return syscalls_metadata[nr];
-}
-
-int syscall_name_to_nr(char *name)
-{
-	int i;
-
-	if (!syscalls_metadata)
-		return -1;
-
-	for (i = 0; i < NR_syscalls; i++) {
-		if (syscalls_metadata[i]) {
-			if (!strcmp(syscalls_metadata[i]->name, name))
-				return i;
-		}
-	}
-	return -1;
-}
-
-void set_syscall_enter_id(int num, int id)
-{
-	syscalls_metadata[num]->enter_id = id;
-}
-
-void set_syscall_exit_id(int num, int id)
+unsigned long __init arch_syscall_addr(int nr)
 {
-	syscalls_metadata[num]->exit_id = id;
-}
-
-static int __init arch_init_ftrace_syscalls(void)
-{
-	int i;
-	struct syscall_metadata *meta;
-	unsigned long **psys_syscall_table = &sys_call_table;
-
-	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
-					NR_syscalls, GFP_KERNEL);
-	if (!syscalls_metadata) {
-		WARN_ON(1);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < NR_syscalls; i++) {
-		meta = find_syscall_meta(psys_syscall_table[i]);
-		syscalls_metadata[i] = meta;
-	}
-	return 0;
+	return (unsigned long)(&sys_call_table)[nr];
 }
-arch_initcall(arch_init_ftrace_syscalls);
 #endif

include/trace/syscall.h

@@ -33,7 +33,7 @@ struct syscall_metadata {
 };
 
 #ifdef CONFIG_FTRACE_SYSCALLS
-extern struct syscall_metadata *syscall_nr_to_meta(int nr);
+extern unsigned long arch_syscall_addr(int nr);
 extern int syscall_name_to_nr(char *name);
 void set_syscall_enter_id(int num, int id);
 void set_syscall_exit_id(int num, int id);

kernel/trace/trace_syscalls.c

@@ -14,6 +14,69 @@ static int sys_refcount_exit;
 static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
 static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
 
+extern unsigned long __start_syscalls_metadata[];
+extern unsigned long __stop_syscalls_metadata[];
+
+static struct syscall_metadata **syscalls_metadata;
+
+static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+{
+	struct syscall_metadata *start;
+	struct syscall_metadata *stop;
+	char str[KSYM_SYMBOL_LEN];
+
+
+	start = (struct syscall_metadata *)__start_syscalls_metadata;
+	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
+
+	for ( ; start < stop; start++) {
+		/*
+		 * 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
+		 * mismatch.
+		 */
+		if (start->name && !strcmp(start->name + 3, str + 3))
+			return start;
+	}
+	return NULL;
+}
+
+static struct syscall_metadata *syscall_nr_to_meta(int nr)
+{
+	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
+		return NULL;
+
+	return syscalls_metadata[nr];
+}
+
+int syscall_name_to_nr(char *name)
+{
+	int i;
+
+	if (!syscalls_metadata)
+		return -1;
+
+	for (i = 0; i < NR_syscalls; i++) {
+		if (syscalls_metadata[i]) {
+			if (!strcmp(syscalls_metadata[i]->name, name))
+				return i;
+		}
+	}
+	return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+	syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+	syscalls_metadata[num]->exit_id = id;
+}
+
 enum print_line_t
 print_syscall_enter(struct trace_iterator *iter, int flags)
 {
@@ -375,6 +438,29 @@ struct trace_event event_syscall_exit = {
 	.trace			= print_syscall_exit,
 };
 
+int __init init_ftrace_syscalls(void)
+{
+	struct syscall_metadata *meta;
+	unsigned long addr;
+	int i;
+
+	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
+					NR_syscalls, GFP_KERNEL);
+	if (!syscalls_metadata) {
+		WARN_ON(1);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < NR_syscalls; i++) {
+		addr = arch_syscall_addr(i);
+		meta = find_syscall_meta(addr);
+		syscalls_metadata[i] = meta;
+	}
+
+	return 0;
+}
+core_initcall(init_ftrace_syscalls);
+
 #ifdef CONFIG_EVENT_PROFILE
 
 static DECLARE_BITMAP(enabled_prof_enter_syscalls, NR_syscalls);