[PATCH RESEND] perf inject --jit: Remove //anon mmap events

[Steve MacLean]

From: Steve MacLean <Steve.MacLean@xxxxxxxxxxxxx>

While a JIT is jitting code it will eventually need to commit more pages and
change these pages to executable permissions.

Typically the JIT will want these colocated to minimize branch displacements.

The kernel will coalesce these anonymous mapping with identical permissions
before sending an MMAP event for the new pages. This means the mmap event for
the new pages will include the older pages.

These anonymous mmap events will obscure the jitdump injected pseudo events.
This means that the jitdump generated symbols, machine code, debugging info,
and unwind info will no longer be used.

Observations:

When a process emits a jit dump marker and a jitdump file, the perf-xxx.map
file represents inferior information which has been superceded by the
jitdump jit-xxx.dump file.

Further the '//anon*' mmap events are only required for the legacy
perf-xxx.map mapping.

Summary:

Add rbtree to track which pids have sucessfully injected a jitdump file.

During "perf inject --jit", discard "//anon*" mmap events for any pid which
has sucessfully processed a jitdump file.

Committer testing:

// jitdump case
perf record <app with jitdump>
perf inject --jit --input perf.data --output perfjit.data

// verify mmap "//anon" events present initially
perf script --input perf.data --show-mmap-events | grep '//anon'
// verify mmap "//anon" events removed
perf script --input perfjit.data --show-mmap-events | grep '//anon'

// no jitdump case
perf record <app without jitdump>
perf inject --jit --input perf.data --output perfjit.data

// verify mmap "//anon" events present initially
perf script --input perf.data --show-mmap-events | grep '//anon'
// verify mmap "//anon" events not removed
perf script --input perfjit.data --show-mmap-events | grep '//anon'

Repro:

This issue was discovered while testing the initial CoreCLR jitdump
implementation. https://github.com/dotnet/coreclr/pull/26897.

Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Signed-off-by: Steve MacLean <Steve.MacLean@xxxxxxxxxxxxx>
---
 tools/perf/builtin-inject.c |  4 +--
 tools/perf/util/jitdump.c   | 63 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 372ecb3..0f38862 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -263,7 +263,7 @@ static int perf_event__jit_repipe_mmap(struct perf_tool *tool,
 	 * if jit marker, then inject jit mmaps and generate ELF images
 	 */
 	ret = jit_process(inject->session, &inject->output, machine,
-			  event->mmap.filename, sample->pid, &n);
+			  event->mmap.filename, event->mmap.pid, &n);
 	if (ret < 0)
 		return ret;
 	if (ret) {
@@ -301,7 +301,7 @@ static int perf_event__jit_repipe_mmap2(struct perf_tool *tool,
 	 * if jit marker, then inject jit mmaps and generate ELF images
 	 */
 	ret = jit_process(inject->session, &inject->output, machine,
-			  event->mmap2.filename, sample->pid, &n);
+			  event->mmap2.filename, event->mmap2.pid, &n);
 	if (ret < 0)
 		return ret;
 	if (ret) {
diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c
index e3ccb0c..6d891d1 100644
--- a/tools/perf/util/jitdump.c
+++ b/tools/perf/util/jitdump.c
@@ -749,6 +749,59 @@ static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
 	return 0;
 }
 
+struct pid_rbtree
+{
+	struct rb_node node;
+	pid_t pid;
+};
+
+static void jit_add_pid(struct rb_root *root, pid_t pid)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+	struct pid_rbtree* data = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct pid_rbtree *this = container_of(*new, struct pid_rbtree, node);
+		pid_t nodePid = this->pid;
+
+		parent = *new;
+		if (pid < nodePid)
+			new = &((*new)->rb_left);
+		else if (pid > nodePid)
+			new = &((*new)->rb_right);
+		else
+			return;
+	}
+
+	data = malloc(sizeof(struct pid_rbtree));
+	data->pid = pid;
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&data->node, parent, new);
+	rb_insert_color(&data->node, root);
+
+	return;
+}
+
+static bool jit_has_pid(struct rb_root *root, pid_t pid)
+{
+	struct rb_node *node = root->rb_node;
+
+	while (node) {
+		struct pid_rbtree *this = container_of(node, struct pid_rbtree, node);
+		pid_t nodePid = this->pid;
+
+		if (pid < nodePid)
+			node = node->rb_left;
+		else if (pid > nodePid)
+			node = node->rb_right;
+		else
+			return 1;
+	}
+	return 0;
+}
+
 int
 jit_process(struct perf_session *session,
 	    struct perf_data *output,
@@ -760,12 +813,21 @@ static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
 	struct evsel *first;
 	struct jit_buf_desc jd;
 	int ret;
+	static struct rb_root jitdump_pids = RB_ROOT;
 
 	/*
 	 * first, detect marker mmap (i.e., the jitdump mmap)
 	 */
 	if (jit_detect(filename, pid))
+	{
+		/*
+		 * Strip //anon* mmaps if we processed a jitdump for this pid
+		 */
+		if (jit_has_pid(&jitdump_pids, pid) && (strncmp(filename, "//anon", 6) == 0))
+			return 1;
+
 		return 0;
+	}
 
 	memset(&jd, 0, sizeof(jd));
 
@@ -784,6 +846,7 @@ static int jit_repipe_debug_info(struct jit_buf_desc *jd, union jr_entry *jr)
 
 	ret = jit_inject(&jd, filename);
 	if (!ret) {
+		jit_add_pid(&jitdump_pids, pid);
 		*nbytes = jd.bytes_written;
 		ret = 1;
 	}
-- 
1.8.3.1