Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Smtp-Origin-Hostprefix: devbig
From:   Song Liu <songliubraving@fb.com>
Smtp-Origin-Hostname: devbig102.frc2.facebook.com
To:     <linux-kernel@vger.kernel.org>
CC:     <kernel-team@fb.com>, Song Liu <songliubraving@fb.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ingo Molnar <mingo@redhat.com>,
        Howard McLauchlan <hmclauchlan@fb.com>,
        Josef Bacik <jbacik@fb.com>,
        Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
        Miklos Szeredi <miklos@szeredi.hu>
Smtp-Origin-Cluster: frc2c02
Subject: [PATCH v5 1/2] tracing: fix bad use of igrab in trace_uprobe.c
Date:   Mon, 23 Apr 2018 10:21:34 -0700
Message-ID: <20180423172135.4050588-1-songliubraving@fb.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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.

Fixes: f3f096cfedf8 ("tracing: Provide trace events interface for uprobes")
Fixes: 33ea4b24277b ("perf/core: Implement the 'perf_uprobe' PMU")
Cc: Steven Rostedt <rostedt@goodmis.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>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Reported-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Song Liu <songliubraving@fb.com>
---
 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 34fd0e0..ac89287 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);
 
-- 
2.9.5