Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "Kernel side changes:

   - AMD range breakpoints support:

     Extend breakpoint tools and core to support address range through
     perf event with initial backend support for AMD extended
     breakpoints.

     The syntax is:

         perf record -e mem:addr/len:type

     For example set write breakpoint from 0x1000 to 0x1200 (0x1000 + 512)

         perf record -e mem:0x1000/512:w

   - event throttling/rotating fixes

   - various event group handling fixes, cleanups and general paranoia
     code to be more robust against bugs in the future.

    - kernel stack overhead fixes

  User-visible tooling side changes:

   - Show precise number of samples in at the end of a 'record' session,
     if processing build ids, since we will then traverse the whole
     perf.data file and see all the PERF_RECORD_SAMPLE records,
     otherwise stop showing the previous off-base heuristicly counted
     number of "samples" (Namhyung Kim).

   - Support to read compressed module from build-id cache (Namhyung
     Kim)

   - Enable sampling loads and stores simultaneously in 'perf mem'
     (Stephane Eranian)

   - 'perf diff' output improvements (Namhyung Kim)

   - Fix error reporting for evsel pgfault constructor (Arnaldo Carvalho
     de Melo)

  Tooling side infrastructure changes:

   - Cache eh/debug frame offset for dwarf unwind (Namhyung Kim)

   - Support parsing parameterized events (Cody P Schafer)

   - Add support for IP address formats in libtraceevent (David Ahern)

  Plus other misc fixes"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (48 commits)
  perf: Decouple unthrottling and rotating
  perf: Drop module reference on event init failure
  perf: Use POLLIN instead of POLL_IN for perf poll data in flag
  perf: Fix put_event() ctx lock
  perf: Fix move_group() order
  perf: Fix event->ctx locking
  perf: Add a bit of paranoia
  perf symbols: Convert lseek + read to pread
  perf tools: Use perf_data_file__fd() consistently
  perf symbols: Support to read compressed module from build-id cache
  perf evsel: Set attr.task bit for a tracking event
  perf header: Set header version correctly
  perf record: Show precise number of samples
  perf tools: Do not use __perf_session__process_events() directly
  perf callchain: Cache eh/debug frame offset for dwarf unwind
  perf tools: Provide stub for missing pthread_attr_setaffinity_np
  perf evsel: Don't rely on malloc working for sz 0
  tools lib traceevent: Add support for IP address formats
  perf ui/tui: Show fatal error message only if exists
  perf tests: Fix typo in sample-parsing.c
  ...

3 files changed, 27 insertions, 12 deletions

diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 0bebb5c348b8..d36f68b08acc 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -595,7 +595,7 @@ 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 *perf_trace_buf_prepare(int size, unsigned short type,
-				    struct pt_regs *regs, int *rctxp);
+				    struct pt_regs **regs, int *rctxp);
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 664de5a4ec46..5cad0e6f3552 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -469,6 +469,7 @@ struct perf_event_context {
 	 */
 	struct mutex			mutex;
 
+	struct list_head		active_ctx_list;
 	struct list_head		pinned_groups;
 	struct list_head		flexible_groups;
 	struct list_head		event_list;
@@ -519,7 +520,6 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct hrtimer			hrtimer;
 	ktime_t				hrtimer_interval;
-	struct list_head		rotation_list;
 	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };
@@ -659,6 +659,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
+extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64);
 extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
@@ -683,14 +684,25 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
-	struct pt_regs hot_regs;
+	if (static_key_false(&perf_swevent_enabled[event_id]))
+		__perf_sw_event(event_id, nr, regs, addr);
+}
+
+DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]);
 
+/*
+ * 'Special' version for the scheduler, it hard assumes no recursion,
+ * which is guaranteed by us not actually scheduling inside other swevents
+ * because those disable preemption.
+ */
+static __always_inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)
+{
 	if (static_key_false(&perf_swevent_enabled[event_id])) {
-		if (!regs) {
-			perf_fetch_caller_regs(&hot_regs);
-			regs = &hot_regs;
-		}
-		__perf_sw_event(event_id, nr, regs, addr);
+		struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]);
+
+		perf_fetch_caller_regs(regs);
+		___perf_sw_event(event_id, nr, regs, addr);
 	}
 }
 
@@ -706,7 +718,7 @@ static inline void perf_event_task_sched_in(struct task_struct *prev,
 static inline void perf_event_task_sched_out(struct task_struct *prev,
 					     struct task_struct *next)
 {
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
+	perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0);
 
 	if (static_key_false(&perf_sched_events.key))
 		__perf_event_task_sched_out(prev, next);
@@ -817,6 +829,8 @@ static inline int perf_event_refresh(struct perf_event *event, int refresh)
 static inline void
 perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)	{ }
 static inline void
+perf_sw_event_sched(u32 event_id, u64 nr, u64 addr)			{ }
+static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
 static inline int perf_register_guest_info_callbacks
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 139b5067345b..27609dfcce25 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -763,7 +763,7 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
-	struct pt_regs __regs;						\
+	struct pt_regs *__regs;						\
 	u64 __addr = 0, __count = 1;					\
 	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
@@ -782,18 +782,19 @@ perf_trace_##call(void *__data, proto)					\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	perf_fetch_caller_regs(&__regs);				\
 	entry = perf_trace_buf_prepare(__entry_size,			\
 			event_call->event.type, &__regs, &rctx);	\
 	if (!entry)							\
 		return;							\
 									\
+	perf_fetch_caller_regs(__regs);					\
+									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head, __task);			\
+		__count, __regs, head, __task);				\
 }
 
 /*