Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/random-tracing into perf/core

arch/x86/include/asm/kdebug.h

@@ -28,7 +28,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_registers(struct pt_regs *regs);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-		       unsigned long *sp, unsigned long bp);
+		       unsigned long *sp);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern void show_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);

arch/x86/include/asm/stacktrace.h

@@ -7,6 +7,7 @@
 #define _ASM_X86_STACKTRACE_H
 
 #include <linux/uaccess.h>
+#include <linux/ptrace.h>
 
 extern int kstack_depth_to_print;
 
@@ -46,7 +47,7 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
+		unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data);
 
 #ifdef CONFIG_X86_32
@@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	unsigned long bp;
+
+	if (regs)
+		return regs->bp;
+
+	if (task == current) {
+		/* Grab bp right from our regs */
+		get_bp(bp);
+		return bp;
+	}
+
+	/* bp is the last reg pushed by switch_to */
+	return *(unsigned long *)task->thread.sp;
+}
+#else
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	return 0;
+}
+#endif
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl);
+		   unsigned long *stack, char *log_lvl);
 
 extern void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *sp, unsigned long bp, char *log_lvl);
+		   unsigned long *sp, char *log_lvl);
 
 extern unsigned int code_bytes;
 

arch/x86/kernel/cpu/perf_event.c

@@ -1657,7 +1657,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	perf_callchain_store(entry, regs->ip);
 
-	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
+	dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
 }
 
 #ifdef CONFIG_COMPAT

arch/x86/kernel/dumpstack.c

@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
 
 void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
+		unsigned long *stack, char *log_lvl)
 {
 	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+	dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
+		unsigned long *stack)
 {
-	show_trace_log_lvl(task, regs, stack, bp, "");
+	show_trace_log_lvl(task, regs, stack, "");
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-	show_stack_log_lvl(task, NULL, sp, 0, "");
+	show_stack_log_lvl(task, NULL, sp, "");
 }
 
 /*
@@ -210,7 +210,7 @@ void dump_stack(void)
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
+	show_trace(NULL, NULL, &stack);
 }
 EXPORT_SYMBOL(dump_stack);
 

arch/x86/kernel/dumpstack_32.c

@@ -17,11 +17,12 @@
 #include <asm/stacktrace.h>
 
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
+void dump_trace(struct task_struct *task,
-		unsigned long *stack, unsigned long bp,
+		struct pt_regs *regs, unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data)
 {
 	int graph = 0;
+	unsigned long bp;
 
 	if (!task)
 		task = current;
@@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			stack = (unsigned long *)task->thread.sp;
 	}
 
-#ifdef CONFIG_FRAME_POINTER
+	bp = stack_frame(task, regs);
-	if (!bp) {
-		if (task == current) {
-			/* Grab bp right from our regs */
-			get_bp(bp);
-		} else {
-			/* bp is the last reg pushed by switch_to */
-			bp = *(unsigned long *) task->thread.sp;
-		}
-	}
-#endif
-
 	for (;;) {
 		struct thread_info *context;
 
@@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl)
+		   unsigned long *sp, char *log_lvl)
 {
 	unsigned long *stack;
 	int i;
@@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		touch_nmi_watchdog();
 	}
 	printk(KERN_CONT "\n");
-	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+	show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 
@@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs)
 		u8 *ip;
 
 		printk(KERN_EMERG "Stack:\n");
-		show_stack_log_lvl(NULL, regs, &regs->sp,
+		show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
-				0, KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 

arch/x86/kernel/dumpstack_64.c

@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
+void dump_trace(struct task_struct *task,
-		unsigned long *stack, unsigned long bp,
+		struct pt_regs *regs, unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
@@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	unsigned used = 0;
 	struct thread_info *tinfo;
 	int graph = 0;
+	unsigned long bp;
 
 	if (!task)
 		task = current;
@@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			stack = (unsigned long *)task->thread.sp;
 	}
 
-#ifdef CONFIG_FRAME_POINTER
+	bp = stack_frame(task, regs);
-	if (!bp) {
-		if (task == current) {
-			/* Grab bp right from our regs */
-			get_bp(bp);
-		} else {
-			/* bp is the last reg pushed by switch_to */
-			bp = *(unsigned long *) task->thread.sp;
-		}
-	}
-#endif
-
 	/*
 	 * Print function call entries in all stacks, starting at the
 	 * current stack address. If the stacks consist of nested
@@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl)
+		   unsigned long *sp, char *log_lvl)
 {
 	unsigned long *irq_stack_end;
 	unsigned long *irq_stack;
@@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	preempt_enable();
 
 	printk(KERN_CONT "\n");
-	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+	show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 void show_registers(struct pt_regs *regs)
@@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs)
 
 		printk(KERN_EMERG "Stack:\n");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				regs->bp, KERN_EMERG);
+				   KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 

arch/x86/kernel/process.c

@@ -91,8 +91,7 @@ void exit_thread(void)
 void show_regs(struct pt_regs *regs)
 {
 	show_registers(regs);
-	show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
+	show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
-		   regs->bp);
 }
 
 void show_regs_common(void)

arch/x86/kernel/stacktrace.c

@@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-	dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
+	dump_trace(current, NULL, NULL, &save_stack_ops, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
-void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp)
+void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
 {
-	dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace);
+	dump_trace(current, regs, NULL, &save_stack_ops, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
+	dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }

arch/x86/mm/kmemcheck/error.c

@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
 	e->trace.entries = e->trace_entries;
 	e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
 	e->trace.skip = 0;
-	save_stack_trace_bp(&e->trace, regs->bp);
+	save_stack_trace_regs(&e->trace, regs);
 
 	/* Round address down to nearest 16 bytes */
 	shadow_copy = kmemcheck_shadow_lookup(address

arch/x86/oprofile/backtrace.c

@@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 	if (!user_mode_vm(regs)) {
 		unsigned long stack = kernel_stack_pointer(regs);
 		if (depth)
-			dump_trace(NULL, regs, (unsigned long *)stack, 0,
+			dump_trace(NULL, regs, (unsigned long *)stack,
 				   &backtrace_ops, &depth);
 		return;
 	}

include/linux/ftrace_event.h

@@ -154,12 +154,14 @@ enum {
 	TRACE_EVENT_FL_ENABLED_BIT,
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
+	TRACE_EVENT_FL_CAP_ANY_BIT,
 };
 
 enum {
 	TRACE_EVENT_FL_ENABLED		= (1 << TRACE_EVENT_FL_ENABLED_BIT),
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
 	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
+	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 };
 
 struct ftrace_event_call {
@@ -196,6 +198,14 @@ struct ftrace_event_call {
 #endif
 };
 
+#define __TRACE_EVENT_FLAGS(name, value)				\
+	static int __init trace_init_flags_##name(void)			\
+	{								\
+		event_##name.flags = value;				\
+		return 0;						\
+	}								\
+	early_initcall(trace_init_flags_##name);
+
 #define PERF_MAX_TRACE_SIZE	2048
 
 #define MAX_FILTER_PRED		32

include/linux/stacktrace.h

@@ -2,6 +2,7 @@
 #define __LINUX_STACKTRACE_H
 
 struct task_struct;
+struct pt_regs;
 
 #ifdef CONFIG_STACKTRACE
 struct task_struct;
@@ -13,7 +14,8 @@ struct stack_trace {
 };
 
 extern void save_stack_trace(struct stack_trace *trace);
-extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp);
+extern void save_stack_trace_regs(struct stack_trace *trace,
+				  struct pt_regs *regs);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 

include/linux/syscalls.h

@@ -127,8 +127,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
 	static struct syscall_metadata					\
 	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
-	static struct ftrace_event_call					\
-	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -137,13 +135,12 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_enter,	\
 		.event.funcs            = &enter_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-	}
+	};								\
+	__TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
 	static struct syscall_metadata					\
 	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
-	static struct ftrace_event_call					\
-	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct ftrace_event_call __used				\
 	  __attribute__((__aligned__(4)))				\
 	  __attribute__((section("_ftrace_events")))			\
@@ -152,7 +149,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 		.class			= &event_class_syscall_exit,	\
 		.event.funcs		= &exit_syscall_print_funcs,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-	}
+	};								\
+	__TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
 
 #define SYSCALL_METADATA(sname, nb)				\
 	SYSCALL_TRACE_ENTER_EVENT(sname);			\

include/linux/tracepoint.h

@@ -234,6 +234,8 @@ do_trace:								\
 				PARAMS(void *__data, proto),		\
 				PARAMS(__data, args))
 
+#define TRACE_EVENT_FLAGS(event, flag)
+
 #endif /* DECLARE_TRACE */
 
 #ifndef TRACE_EVENT
@@ -354,4 +356,6 @@ do_trace:								\
 		assign, print, reg, unreg)			\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 
+#define TRACE_EVENT_FLAGS(event, flag)
+
 #endif /* ifdef TRACE_EVENT (see note above) */

include/trace/events/syscalls.h

@@ -40,6 +40,8 @@ TRACE_EVENT_FN(sys_enter,
 	syscall_regfunc, syscall_unregfunc
 );
 
+TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
+
 TRACE_EVENT_FN(sys_exit,
 
 	TP_PROTO(struct pt_regs *regs, long ret),
@@ -62,6 +64,8 @@ TRACE_EVENT_FN(sys_exit,
 	syscall_regfunc, syscall_unregfunc
 );
 
+TRACE_EVENT_FLAGS(sys_exit, TRACE_EVENT_FL_CAP_ANY)
+
 #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
 
 #endif /* _TRACE_EVENTS_SYSCALLS_H */

include/trace/ftrace.h

@@ -82,6 +82,10 @@
 	TRACE_EVENT(name, PARAMS(proto), PARAMS(args),			\
 		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
 
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(name, value)					\
+	__TRACE_EVENT_FLAGS(name, value)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 
@@ -129,6 +133,9 @@
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(event, flag)
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*

kernel/perf_event.c

@@ -4773,15 +4773,6 @@ static int perf_tp_event_init(struct perf_event *event)
 	if (event->attr.type != PERF_TYPE_TRACEPOINT)
 		return -ENOENT;
 
-	/*
-	 * Raw tracepoint data is a severe data leak, only allow root to
-	 * have these.
-	 */
-	if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
-			perf_paranoid_tracepoint_raw() &&
-			!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	err = perf_trace_init(event);
 	if (err)
 		return err;

kernel/trace/trace_event_perf.c

@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 /* Count the events in use (per event id, not per instance) */
 static int	total_ref_count;
 
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+				 struct perf_event *p_event)
+{
+	/* No tracing, just counting, so no obvious leak */
+	if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+		return 0;
+
+	/* Some events are ok to be traced by non-root users... */
+	if (p_event->attach_state == PERF_ATTACH_TASK) {
+		if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+			return 0;
+	}
+
+	/*
+	 * ...otherwise raw tracepoint data can be a severe data leak,
+	 * only allow root to have these.
+	 */
+	if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return 0;
+}
+
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
 	struct hlist_head __percpu *list;
-	int ret = -ENOMEM;
+	int ret;
 	int cpu;
 
+	ret = perf_trace_event_perm(tp_event, p_event);
+	if (ret)
+		return ret;
+
 	p_event->tp_event = tp_event;
 	if (tp_event->perf_refcount++ > 0)
 		return 0;
 
+	ret = -ENOMEM;
+
 	list = alloc_percpu(struct hlist_head);
 	if (!list)
 		goto fail;