Merge branch 'perf/urgent' into perf/core

Merge reason: We want to queue up a dependent patch.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 95 insertions, 47 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 6b7c444..c0f4b36 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -131,12 +131,12 @@ struct ftrace_event_call {
 	void			*mod;
 	void			*data;
 
-	int			profile_count;
-	int			(*profile_enable)(struct ftrace_event_call *);
-	void			(*profile_disable)(struct ftrace_event_call *);
+	int			perf_refcount;
+	int			(*perf_event_enable)(struct ftrace_event_call *);
+	void			(*perf_event_disable)(struct ftrace_event_call *);
 };
 
-#define FTRACE_MAX_PROFILE_SIZE	2048
+#define PERF_MAX_TRACE_SIZE	2048
 
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
@@ -187,22 +187,25 @@ do {									\
 
 #ifdef CONFIG_PERF_EVENTS
 struct perf_event;
-extern int ftrace_profile_enable(int event_id);
-extern void ftrace_profile_disable(int event_id);
+
+DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+
+extern int perf_trace_enable(int event_id);
+extern void perf_trace_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
 extern void *
-ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+perf_trace_buf_prepare(int size, unsigned short type, int *rctxp,
 			 unsigned long *irq_flags);
 
 static inline void
-ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, unsigned long irq_flags)
+perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+		       u64 count, unsigned long irq_flags, struct pt_regs *regs)
 {
 	struct trace_entry *entry = raw_data;
 
-	perf_tp_event(entry->type, addr, count, raw_data, size);
+	perf_tp_event(entry->type, addr, count, raw_data, size, regs);
 	perf_swevent_put_recursion_context(rctx);
 	local_irq_restore(irq_flags);
 }
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index be85f7c..2bccb7b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -459,6 +459,8 @@ enum perf_callchain_context {
 #include <linux/fs.h>
 #include <linux/pid_namespace.h>
 #include <linux/workqueue.h>
+#include <linux/ftrace.h>
+#include <linux/cpu.h>
 #include <asm/atomic.h>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -865,6 +867,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+{
+	unsigned long ip;
+
+	memset(regs, 0, sizeof(*regs));
+
+	switch (skip) {
+	case 1 :
+		ip = CALLER_ADDR0;
+		break;
+	case 2 :
+		ip = CALLER_ADDR1;
+		break;
+	case 3 :
+		ip = CALLER_ADDR2;
+		break;
+	case 4:
+		ip = CALLER_ADDR3;
+		break;
+	/* No need to support further for now */
+	default:
+		ip = 0;
+	}
+
+	return perf_arch_fetch_caller_regs(regs, ip, skip);
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
@@ -898,7 +938,8 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 8126f23..51435bc 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -101,18 +101,18 @@ struct perf_event_attr;
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
-	.profile_enable = prof_sysenter_enable,				       \
-	.profile_disable = prof_sysenter_disable,
+#define TRACE_SYS_ENTER_PERF_INIT(sname)				       \
+	.perf_event_enable = perf_sysenter_enable,			       \
+	.perf_event_disable = perf_sysenter_disable,
 
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
-	.profile_enable = prof_sysexit_enable,				       \
-	.profile_disable = prof_sysexit_disable,
+#define TRACE_SYS_EXIT_PERF_INIT(sname)					       \
+	.perf_event_enable = perf_sysexit_enable,			       \
+	.perf_event_disable = perf_sysexit_disable,
 #else
-#define TRACE_SYS_ENTER_PROFILE(sname)
-#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
-#define TRACE_SYS_EXIT_PROFILE(sname)
-#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#define TRACE_SYS_ENTER_PERF(sname)
+#define TRACE_SYS_ENTER_PERF_INIT(sname)
+#define TRACE_SYS_EXIT_PERF(sname)
+#define TRACE_SYS_EXIT_PERF_INIT(sname)
 #endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
@@ -149,7 +149,7 @@ struct perf_event_attr;
 		.regfunc		= reg_event_syscall_enter,	\
 		.unregfunc		= unreg_event_syscall_enter,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
+		TRACE_SYS_ENTER_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
@@ -171,7 +171,7 @@ struct perf_event_attr;
 		.regfunc		= reg_event_syscall_exit,	\
 		.unregfunc		= unreg_event_syscall_exit,	\
 		.data			= (void *)&__syscall_meta_##sname,\
-		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
+		TRACE_SYS_EXIT_PERF_INIT(sname)			\
 	}
 
 #define SYSCALL_METADATA(sname, nb)				\
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0804cd5..25ab56f 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -401,18 +401,18 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args)			\
 									\
-static void ftrace_profile_##name(proto);				\
+static void perf_trace_##name(proto);					\
 									\
 static notrace int							\
-ftrace_profile_enable_##name(struct ftrace_event_call *unused)		\
+perf_trace_enable_##name(struct ftrace_event_call *unused)		\
 {									\
-	return register_trace_##name(ftrace_profile_##name);		\
+	return register_trace_##name(perf_trace_##name);		\
 }									\
 									\
 static notrace void							\
-ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
+perf_trace_disable_##name(struct ftrace_event_call *unused)		\
 {									\
-	unregister_trace_##name(ftrace_profile_##name);			\
+	unregister_trace_##name(perf_trace_##name);			\
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -507,12 +507,12 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_enable = ftrace_profile_enable_##call,			\
-	.profile_disable = ftrace_profile_disable_##call,
+#define _TRACE_PERF_INIT(call)						\
+	.perf_event_enable = perf_trace_enable_##call,			\
+	.perf_event_disable = perf_trace_disable_##call,
 
 #else
-#define _TRACE_PROFILE_INIT(call)
+#define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
@@ -638,7 +638,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##template,			\
 	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
+	_TRACE_PERF_INIT(call)					\
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -657,18 +657,18 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 	.unregfunc		= ftrace_raw_unreg_event_##call,	\
 	.print_fmt		= print_fmt_##call,			\
 	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
+	_TRACE_PERF_INIT(call)					\
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Define the insertion callback to profile events
+ * Define the insertion callback to perf events
  *
  * The job is very similar to ftrace_raw_event_<call> except that we don't
  * insert in the ring buffer but in a perf counter.
  *
- * static void ftrace_profile_<call>(proto)
+ * static void ftrace_perf_<call>(proto)
  * {
  *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ftrace_event_call *event_call = &event_<call>;
@@ -757,13 +757,14 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
-ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
+perf_trace_templ_##call(struct ftrace_event_call *event_call,		\
 			    proto)					\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
+	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
@@ -773,10 +774,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,		\
+	if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,		\
 		      "profile buffer not large enough"))		\
 		return;							\
-	entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(	\
+	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
 		__entry_size, event_call->id, &rctx, &irq_flags);	\
 	if (!entry)							\
 		return;							\
@@ -784,17 +785,20 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 									\
 	{ assign; }							\
 									\
-	ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,	\
-			       __count, irq_flags);			\
+	__regs = &__get_cpu_var(perf_trace_regs);			\
+	perf_fetch_caller_regs(__regs, 2);				\
+									\
+	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
+			       __count, irq_flags, __regs);		\
 }
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)		\
-static notrace void ftrace_profile_##call(proto)		\
+static notrace void perf_trace_##call(proto)			\
 {								\
 	struct ftrace_event_call *event_call = &event_##call;	\
 								\
-	ftrace_profile_templ_##template(event_call, args);	\
+	perf_trace_templ_##template(event_call, args);		\
 }
 
 #undef DEFINE_EVENT_PRINT
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 0387100..e5e5f48 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
-int prof_sysenter_enable(struct ftrace_event_call *call);
-void prof_sysenter_disable(struct ftrace_event_call *call);
-int prof_sysexit_enable(struct ftrace_event_call *call);
-void prof_sysexit_disable(struct ftrace_event_call *call);
+int perf_sysenter_enable(struct ftrace_event_call *call);
+void perf_sysenter_disable(struct ftrace_event_call *call);
+int perf_sysexit_enable(struct ftrace_event_call *call);
+void perf_sysexit_disable(struct ftrace_event_call *call);
 #endif
 
 #endif /* _TRACE_SYSCALL_H */