[PATCH 1/7] tracing: Fix bad use of igrab in trace_uprobe.c

[PATCH 1/7] tracing: Fix bad use of igrab in trace_uprobe.c

[Steven Rostedt]

[-- Attachment #1: 0001-tracing-Fix-bad-use-of-igrab-in-trace_uprobe.c.patch --]
[-- Type: text/plain, Size: 5415 bytes --]

From: Song Liu <songliubraving@fb.com>

As Miklos reported and suggested:

  This pattern repeats two times in trace_uprobe.c and in
  kernel/events/core.c as well:

      ret = kern_path(filename, LOOKUP_FOLLOW, &path);
      if (ret)
          goto fail_address_parse;

      inode = igrab(d_inode(path.dentry));
      path_put(&path);

  And it's wrong.  You can only hold a reference to the inode if you
  have an active ref to the superblock as well (which is normally
  through path.mnt) or holding s_umount.

  This way unmounting the containing filesystem while the tracepoint is
  active will give you the "VFS: Busy inodes after unmount..." message
  and a crash when the inode is finally put.

  Solution: store path instead of inode.

This patch fixes two instances in trace_uprobe.c. struct path is added to
struct trace_uprobe to keep the inode and containing mount point
referenced.

Link: http://lkml.kernel.org/r/20180423172135.4050588-1-songliubraving@fb.com

Fixes: f3f096cfedf8 ("tracing: Provide trace events interface for uprobes")
Fixes: 33ea4b24277b ("perf/core: Implement the 'perf_uprobe' PMU")
Cc: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Howard McLauchlan <hmclauchlan@fb.com>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Miklos Szeredi <mszeredi@redhat.com>
Reported-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/trace/trace_uprobe.c | 35 ++++++++++++++---------------------
 1 file changed, 14 insertions(+), 21 deletions(-)

diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 34fd0e0ec51d..ac892878dbe6 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -55,6 +55,7 @@ struct trace_uprobe {
 	struct list_head		list;
 	struct trace_uprobe_filter	filter;
 	struct uprobe_consumer		consumer;
+	struct path			path;
 	struct inode			*inode;
 	char				*filename;
 	unsigned long			offset;
@@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu)
 	for (i = 0; i < tu->tp.nr_args; i++)
 		traceprobe_free_probe_arg(&tu->tp.args[i]);
 
-	iput(tu->inode);
+	path_put(&tu->path);
 	kfree(tu->tp.call.class->system);
 	kfree(tu->tp.call.name);
 	kfree(tu->filename);
@@ -363,7 +364,6 @@ static int register_trace_uprobe(struct trace_uprobe *tu)
 static int create_trace_uprobe(int argc, char **argv)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	char *arg, *event, *group, *filename;
 	char buf[MAX_EVENT_NAME_LEN];
 	struct path path;
@@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv)
 	bool is_delete, is_return;
 	int i, ret;
 
-	inode = NULL;
 	ret = 0;
 	is_delete = false;
 	is_return = false;
@@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv)
 	}
 	/* Find the last occurrence, in case the path contains ':' too. */
 	arg = strrchr(argv[1], ':');
-	if (!arg) {
-		ret = -EINVAL;
-		goto fail_address_parse;
-	}
+	if (!arg)
+		return -EINVAL;
 
 	*arg++ = '\0';
 	filename = argv[1];
 	ret = kern_path(filename, LOOKUP_FOLLOW, &path);
 	if (ret)
-		goto fail_address_parse;
-
-	inode = igrab(d_real_inode(path.dentry));
-	path_put(&path);
+		return ret;
 
-	if (!inode || !S_ISREG(inode->i_mode)) {
+	if (!d_is_reg(path.dentry)) {
 		ret = -EINVAL;
 		goto fail_address_parse;
 	}
@@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv)
 		goto fail_address_parse;
 	}
 	tu->offset = offset;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(filename, GFP_KERNEL);
 
 	if (!tu->filename) {
@@ -558,7 +552,7 @@ static int create_trace_uprobe(int argc, char **argv)
 	return ret;
 
 fail_address_parse:
-	iput(inode);
+	path_put(&path);
 
 	pr_info("Failed to parse address or file.\n");
 
@@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file,
 		goto err_flags;
 
 	tu->consumer.filter = filter;
+	tu->inode = d_real_inode(tu->path.dentry);
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
 	if (ret)
 		goto err_buffer;
@@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file)
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	uprobe_unregister(tu->inode, tu->offset, &tu->consumer);
+	tu->inode = NULL;
 	tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE;
 
 	uprobe_buffer_disable();
@@ -1337,7 +1333,6 @@ struct trace_event_call *
 create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 {
 	struct trace_uprobe *tu;
-	struct inode *inode;
 	struct path path;
 	int ret;
 
@@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (ret)
 		return ERR_PTR(ret);
 
-	inode = igrab(d_inode(path.dentry));
-	path_put(&path);
-
-	if (!inode || !S_ISREG(inode->i_mode)) {
-		iput(inode);
+	if (!d_is_reg(path.dentry)) {
+		path_put(&path);
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return)
 	if (IS_ERR(tu)) {
 		pr_info("Failed to allocate trace_uprobe.(%d)\n",
 			(int)PTR_ERR(tu));
+		path_put(&path);
 		return ERR_CAST(tu);
 	}
 
 	tu->offset = offs;
-	tu->inode = inode;
+	tu->path = path;
 	tu->filename = kstrdup(name, GFP_KERNEL);
 	init_trace_event_call(tu, &tu->tp.call);
 
-- 
2.17.0

[PATCH 7/7] tracepoint: Do not warn on ENOMEM

[Steven Rostedt]

[-- Attachment #1: 0007-tracepoint-Do-not-warn-on-ENOMEM.patch --]
[-- Type: text/plain, Size: 2091 bytes --]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

Tracepoint should only warn when a kernel API user does not respect the
required preconditions (e.g. same tracepoint enabled twice, or called
to remove a tracepoint that does not exist).

Silence warning in out-of-memory conditions, given that the error is
returned to the caller.

This ensures that out-of-memory error-injection testing does not trigger
warnings in tracepoint.c, which were seen by syzbot.

Link: https://lkml.kernel.org/r/001a114465e241a8720567419a72@google.com
Link: https://lkml.kernel.org/r/001a1140e0de15fc910567464190@google.com
Link: http://lkml.kernel.org/r/20180315124424.32319-1-mathieu.desnoyers@efficios.com

CC: Peter Zijlstra <peterz@infradead.org>
CC: Jiri Olsa <jolsa@redhat.com>
CC: Arnaldo Carvalho de Melo <acme@kernel.org>
CC: Alexander Shishkin <alexander.shishkin@linux.intel.com>
CC: Namhyung Kim <namhyung@kernel.org>
CC: stable@vger.kernel.org
Fixes: de7b2973903c6 ("tracepoint: Use struct pointer instead of name hash for reg/unreg tracepoints")
Reported-by: syzbot+9c0d616860575a73166a@syzkaller.appspotmail.com
Reported-by: syzbot+4e9ae7fa46233396f64d@syzkaller.appspotmail.com
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
---
 kernel/tracepoint.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 671b13457387..1e37da2e0c25 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -207,7 +207,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_add(&tp_funcs, func, prio);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
 
@@ -239,7 +239,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			lockdep_is_held(&tracepoints_mutex));
 	old = func_remove(&tp_funcs, func);
 	if (IS_ERR(old)) {
-		WARN_ON_ONCE(1);
+		WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM);
 		return PTR_ERR(old);
 	}
 
-- 
2.17.0