perf_counter: allow for data addresses to be recorded

Paul suggested we allow for data addresses to be recorded along with
the traditional IPs as power can provide these.

For now, only the software pagefault events provide data addresses,
but in the future power might as well for some events.

x86 doesn't seem capable of providing this atm.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090408130409.394816925@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 29 insertions, 17 deletions

diff --git a/kernel/perf_counter.c b/kernel/perf_counter.c
index 4dc8600d282..321c57e3556 100644
--- a/kernel/perf_counter.c
+++ b/kernel/perf_counter.c
@@ -800,7 +800,7 @@ void perf_counter_task_sched_out(struct task_struct *task, int cpu)
 	update_context_time(ctx);
 
 	regs = task_pt_regs(task);
-	perf_swcounter_event(PERF_COUNT_CONTEXT_SWITCHES, 1, 1, regs);
+	perf_swcounter_event(PERF_COUNT_CONTEXT_SWITCHES, 1, 1, regs, 0);
 	__perf_counter_sched_out(ctx, cpuctx);
 
 	cpuctx->task_ctx = NULL;
@@ -1810,7 +1810,7 @@ static void perf_output_end(struct perf_output_handle *handle)
 }
 
 static void perf_counter_output(struct perf_counter *counter,
-				int nmi, struct pt_regs *regs)
+				int nmi, struct pt_regs *regs, u64 addr)
 {
 	int ret;
 	u64 record_type = counter->hw_event.record_type;
@@ -1860,6 +1860,11 @@ static void perf_counter_output(struct perf_counter *counter,
 		header.size += sizeof(u64);
 	}
 
+	if (record_type & PERF_RECORD_ADDR) {
+		header.type |= PERF_RECORD_ADDR;
+		header.size += sizeof(u64);
+	}
+
 	if (record_type & PERF_RECORD_GROUP) {
 		header.type |= PERF_RECORD_GROUP;
 		header.size += sizeof(u64) +
@@ -1892,6 +1897,9 @@ static void perf_counter_output(struct perf_counter *counter,
 	if (record_type & PERF_RECORD_TIME)
 		perf_output_put(&handle, time);
 
+	if (record_type & PERF_RECORD_ADDR)
+		perf_output_put(&handle, addr);
+
 	if (record_type & PERF_RECORD_GROUP) {
 		struct perf_counter *leader, *sub;
 		u64 nr = counter->nr_siblings;
@@ -2158,7 +2166,7 @@ void perf_counter_munmap(unsigned long addr, unsigned long len,
  */
 
 int perf_counter_overflow(struct perf_counter *counter,
-			  int nmi, struct pt_regs *regs)
+			  int nmi, struct pt_regs *regs, u64 addr)
 {
 	int events = atomic_read(&counter->event_limit);
 	int ret = 0;
@@ -2175,7 +2183,7 @@ int perf_counter_overflow(struct perf_counter *counter,
 			perf_counter_disable(counter);
 	}
 
-	perf_counter_output(counter, nmi, regs);
+	perf_counter_output(counter, nmi, regs, addr);
 	return ret;
 }
 
@@ -2240,7 +2248,7 @@ static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
 		regs = task_pt_regs(current);
 
 	if (regs) {
-		if (perf_counter_overflow(counter, 0, regs))
+		if (perf_counter_overflow(counter, 0, regs, 0))
 			ret = HRTIMER_NORESTART;
 	}
 
@@ -2250,11 +2258,11 @@ static enum hrtimer_restart perf_swcounter_hrtimer(struct hrtimer *hrtimer)
 }
 
 static void perf_swcounter_overflow(struct perf_counter *counter,
-				    int nmi, struct pt_regs *regs)
+				    int nmi, struct pt_regs *regs, u64 addr)
 {
 	perf_swcounter_update(counter);
 	perf_swcounter_set_period(counter);
-	if (perf_counter_overflow(counter, nmi, regs))
+	if (perf_counter_overflow(counter, nmi, regs, addr))
 		/* soft-disable the counter */
 		;
 
@@ -2286,16 +2294,17 @@ static int perf_swcounter_match(struct perf_counter *counter,
 }
 
 static void perf_swcounter_add(struct perf_counter *counter, u64 nr,
-			       int nmi, struct pt_regs *regs)
+			       int nmi, struct pt_regs *regs, u64 addr)
 {
 	int neg = atomic64_add_negative(nr, &counter->hw.count);
 	if (counter->hw.irq_period && !neg)
-		perf_swcounter_overflow(counter, nmi, regs);
+		perf_swcounter_overflow(counter, nmi, regs, addr);
 }
 
 static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
 				     enum perf_event_types type, u32 event,
-				     u64 nr, int nmi, struct pt_regs *regs)
+				     u64 nr, int nmi, struct pt_regs *regs,
+				     u64 addr)
 {
 	struct perf_counter *counter;
 
@@ -2305,7 +2314,7 @@ static void perf_swcounter_ctx_event(struct perf_counter_context *ctx,
 	rcu_read_lock();
 	list_for_each_entry_rcu(counter, &ctx->event_list, event_entry) {
 		if (perf_swcounter_match(counter, type, event, regs))
-			perf_swcounter_add(counter, nr, nmi, regs);
+			perf_swcounter_add(counter, nr, nmi, regs, addr);
 	}
 	rcu_read_unlock();
 }
@@ -2325,7 +2334,8 @@ static int *perf_swcounter_recursion_context(struct perf_cpu_context *cpuctx)
 }
 
 static void __perf_swcounter_event(enum perf_event_types type, u32 event,
-				   u64 nr, int nmi, struct pt_regs *regs)
+				   u64 nr, int nmi, struct pt_regs *regs,
+				   u64 addr)
 {
 	struct perf_cpu_context *cpuctx = &get_cpu_var(perf_cpu_context);
 	int *recursion = perf_swcounter_recursion_context(cpuctx);
@@ -2336,10 +2346,11 @@ static void __perf_swcounter_event(enum perf_event_types type, u32 event,
 	(*recursion)++;
 	barrier();
 
-	perf_swcounter_ctx_event(&cpuctx->ctx, type, event, nr, nmi, regs);
+	perf_swcounter_ctx_event(&cpuctx->ctx, type, event,
+				 nr, nmi, regs, addr);
 	if (cpuctx->task_ctx) {
 		perf_swcounter_ctx_event(cpuctx->task_ctx, type, event,
-				nr, nmi, regs);
+					 nr, nmi, regs, addr);
 	}
 
 	barrier();
@@ -2349,9 +2360,10 @@ out:
 	put_cpu_var(perf_cpu_context);
 }
 
-void perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs)
+void
+perf_swcounter_event(u32 event, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
-	__perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs);
+	__perf_swcounter_event(PERF_TYPE_SOFTWARE, event, nr, nmi, regs, addr);
 }
 
 static void perf_swcounter_read(struct perf_counter *counter)
@@ -2548,7 +2560,7 @@ void perf_tpcounter_event(int event_id)
 	if (!regs)
 		regs = task_pt_regs(current);
 
-	__perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs);
+	__perf_swcounter_event(PERF_TYPE_TRACEPOINT, event_id, 1, 1, regs, 0);
 }
 
 extern int ftrace_profile_enable(int);