perf tools: Separate accounting of contexts and real addresses in a stack trace

The perf_sample->ip_callchain->nr value includes all the entries in the
ip_callchain->ip[] array, real addresses and PERF_CONTEXT_{KERNEL,USER,etc},
while what the user expects is that what is in the kernel.perf_event_max_stack
sysctl or in the upcoming per event perf_event_attr.sample_max_stack knob be
honoured in terms of IP addresses in the stack trace.

So match the kernel support and validate chain->nr taking into account
both kernel.perf_event_max_stack and kernel.perf_event_max_contexts_per_stack.

Cc: Adrian Hunter <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Alexei Starovoitov <[email protected]>
Cc: Brendan Gregg <[email protected]>
Cc: David Ahern <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: He Kuang <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Milian Wolff <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Vince Weaver <[email protected]>
Cc: Wang Nan <[email protected]>
Cc: Zefan Li <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: acmel

tools/perf/perf.c

@@ -549,6 +549,9 @@ int main(int argc, const char **argv)
 	if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
 		sysctl_perf_event_max_stack = value;
 
+	if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+		sysctl_perf_event_max_contexts_per_stack = value;
+
 	cmd = extract_argv0_path(argv[0]);
 	if (!cmd)
 		cmd = "perf-help";

tools/perf/util/machine.c

@@ -1811,9 +1811,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
 	struct branch_stack *branch = sample->branch_stack;
 	struct ip_callchain *chain = sample->callchain;
-	int chain_nr = min(max_stack, (int)chain->nr);
+	int chain_nr = chain->nr;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err;
+	int i, j, err, nr_entries, nr_contexts;
 	int skip_idx = -1;
 	int first_call = 0;
 
@@ -1828,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	if (chain->nr < sysctl_perf_event_max_stack)
+	if (chain_nr < sysctl_perf_event_max_stack)
 		skip_idx = arch_skip_callchain_idx(thread, chain);
 
 	/*
@@ -1889,12 +1889,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	}
 
 check_calls:
-	if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
-
-	for (i = first_call; i < chain_nr; i++) {
+	for (i = first_call, nr_entries = 0, nr_contexts = 0;
+	     i < chain_nr && nr_entries < max_stack; i++) {
 		u64 ip;
 
 		if (callchain_param.order == ORDER_CALLEE)
@@ -1908,13 +1904,25 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 #endif
 		ip = chain->ips[j];
 
+		if (ip >= PERF_CONTEXT_MAX) {
+			if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
+				goto out_corrupted_callchain;
+		} else {
+			if (++nr_entries > sysctl_perf_event_max_stack)
+				goto out_corrupted_callchain;
+		}
+
 		err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
 		if (err)
 			return (err < 0) ? err : 0;
 	}
 
 	return 0;
+
+out_corrupted_callchain:
+	pr_warning("corrupted callchain. skipping...\n");
+	return 0;
 }
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)

tools/perf/util/util.c

@@ -33,7 +33,8 @@ struct callchain_param	callchain_param = {
 unsigned int page_size;
 int cacheline_size;
 
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
 bool test_attr__enabled;
 

tools/perf/util/util.h

@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
 struct parse_tag {
 	char tag;