perf: Use hot regs with software sched switch/migrate events

Scheduler's task migration events don't work because they always
pass NULL regs perf_sw_event(). The event hence gets filtered
in perf_swevent_add().

Scheduler's context switches events use task_pt_regs() to get
the context when the event occured which is a wrong thing to
do as this won't give us the place in the kernel where we went
to sleep but the place where we left userspace. The result is
even more wrong if we switch from a kernel thread.

Use the hot regs snapshot for both events as they belong to the
non-interrupt/exception based events family. Unlike page faults
or so that provide the regs matching the exact origin of the event,
we need to save the current context.

This makes the task migration event working and fix the context
switch callchains and origin ip.

Example: perf record -a -e cs

Before:

    10.91%      ksoftirqd/0                  0  [k] 0000000000000000
                |
                --- (nil)
                    perf_callchain
                    perf_prepare_sample
                    __perf_event_overflow
                    perf_swevent_overflow
                    perf_swevent_add
                    perf_swevent_ctx_event
                    do_perf_sw_event
                    __perf_sw_event
                    perf_event_task_sched_out
                    schedule
                    run_ksoftirqd
                    kthread
                    kernel_thread_helper

After:

    23.77%  hald-addon-stor  [kernel.kallsyms]  [k] schedule
            |
            --- schedule
               |
               |--60.00%-- schedule_timeout
               |          wait_for_common
               |          wait_for_completion
               |          blk_execute_rq
               |          scsi_execute
               |          scsi_execute_req
               |          sr_test_unit_ready
               |          |
               |          |--66.67%-- sr_media_change
               |          |          media_changed
               |          |          cdrom_media_changed
               |          |          sr_block_media_changed
               |          |          check_disk_change
               |          |          cdrom_open

v2: Always build perf_arch_fetch_caller_regs() now that software
events need that too. They don't need it from modules, unlike trace
events, so we keep the EXPORT_SYMBOL in trace_event_perf.c

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Miller <davem@davemloft.net>

3 files changed, 15 insertions, 12 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 60398a0d947..5fb490c6ee5 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1702,7 +1702,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return entry;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 	regs->ip = ip;
@@ -1714,4 +1713,3 @@ void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int ski
 	regs->cs = __KERNEL_CS;
 	local_save_flags(regs->flags);
 }
-#endif
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 95477038a72..c8e37544040 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -842,13 +842,6 @@ extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
 extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
 
-static inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
-{
-	if (atomic_read(&perf_swevent_enabled[event_id]))
-		__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);
 
@@ -887,6 +880,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
 	return perf_arch_fetch_caller_regs(regs, ip, skip);
 }
 
+static inline void
+perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+{
+	if (atomic_read(&perf_swevent_enabled[event_id])) {
+		struct pt_regs hot_regs;
+
+		if (!regs) {
+			perf_fetch_caller_regs(&hot_regs, 1);
+			regs = &hot_regs;
+		}
+		__perf_sw_event(event_id, nr, nmi, regs, addr);
+	}
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 574ee58a304..b0feb4795af 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -1164,11 +1164,9 @@ void perf_event_task_sched_out(struct task_struct *task,
 	struct perf_event_context *ctx = task->perf_event_ctxp;
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
-	struct pt_regs *regs;
 	int do_switch = 1;
 
-	regs = task_pt_regs(task);
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;