[PATCH v3 12/14] perf, x86: use LBR call stack to get user callchain

["Yan, Zheng" <zheng.z.yan@intel.com>]

Haswell has a new feature that utilizes the existing Last Branch Record
facility to record call chains. When the feature is enabled, function
call will be collected as normal, but as return instructions are executed
the last captured branch record is popped from the on-chip LBR registers.
The LBR call stack facility can help perf to get call chains of progam
without frame pointer.

This patch makes x86's perf_callchain_user() failback to LBR callstack
when there is no frame pointer in the user program.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 arch/x86/kernel/cpu/perf_event.c           | 33 ++++++++++++++++++++++++++----
 arch/x86/kernel/cpu/perf_event_intel.c     | 10 ++++++++-
 arch/x86/kernel/cpu/perf_event_intel_lbr.c |  2 ++
 include/linux/perf_event.h                 |  1 +
 4 files changed, 41 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6094560..0d0fe2f3 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1975,12 +1975,28 @@ static unsigned long get_segment_base(unsigned int segment)
 	return get_desc_base(desc + idx);
 }
 
+static inline void
+perf_callchain_lbr_callstack(struct perf_callchain_entry *entry,
+			     struct perf_sample_data *data)
+{
+	struct perf_branch_stack *br_stack = data->br_stack;
+
+	if (br_stack && br_stack->user_callstack) {
+		int i = 0;
+		while (i < br_stack->nr && entry->nr < PERF_MAX_STACK_DEPTH) {
+			perf_callchain_store(entry, br_stack->entries[i].from);
+			i++;
+		}
+	}
+}
+
 #ifdef CONFIG_COMPAT
 
 #include <asm/compat.h>
 
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct perf_callchain_entry *entry,
+		      struct pt_regs *regs, struct perf_sample_data *data)
 {
 	/* 32-bit process in 64-bit kernel. */
 	unsigned long ss_base, cs_base;
@@ -2009,11 +2025,16 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
 		perf_callchain_store(entry, cs_base + frame.return_address);
 		fp = compat_ptr(ss_base + frame.next_frame);
 	}
+
+	if (fp == compat_ptr(regs->bp))
+		perf_callchain_lbr_callstack(entry, data);
+
 	return 1;
 }
 #else
 static inline int
-perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
+perf_callchain_user32(struct perf_callchain_entry *entry,
+		      struct pt_regs *regs, struct perf_sample_data *data)
 {
     return 0;
 }
@@ -2043,12 +2064,12 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 	if (!current->mm)
 		return;
 
-	if (perf_callchain_user32(regs, entry))
+	if (perf_callchain_user32(entry, regs, data))
 		return;
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH) {
 		unsigned long bytes;
-		frame.next_frame	     = NULL;
+		frame.next_frame = NULL;
 		frame.return_address = 0;
 
 		bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
@@ -2061,6 +2082,10 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 		perf_callchain_store(entry, frame.return_address);
 		fp = frame.next_frame;
 	}
+
+	/* try LBR callstack if there is no frame pointer */
+	if (fp == (void __user *)regs->bp)
+		perf_callchain_lbr_callstack(entry, data);
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 722171c..9057a20 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1030,6 +1030,14 @@ static __initconst const u64 slm_hw_cache_event_ids
  },
 };
 
+static inline bool intel_pmu_needs_lbr_callstack(struct perf_event *event)
+{
+	if ((event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
+	    (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK))
+		return true;
+	return false;
+}
+
 static void intel_pmu_disable_all(void)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -1398,7 +1406,7 @@ again:
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
+		if (needs_branch_stack(event))
 			data.br_stack = &cpuc->lbr_stack;
 
 		if (perf_event_overflow(event, &data, regs))
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index aa726af..7e26367 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -717,6 +717,8 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	int i, j, type;
 	bool compress = false;
 
+	cpuc->lbr_stack.user_callstack = branch_user_callstack(br_sel);
+
 	/* if sampling all branches, then nothing to filter */
 	if ((br_sel & X86_BR_ALL) == X86_BR_ALL)
 		return;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b87974a..517c34a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -74,6 +74,7 @@ struct perf_raw_record {
  * recent branch.
  */
 struct perf_branch_stack {
+	bool				user_callstack;
 	__u64				nr;
 	struct perf_branch_entry	entries[0];
 };
-- 
1.8.5.3