[PATCH] sysfs: store sysfs inode nrs in s_ino to avoid readdir oopses

Backport of
ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.22-rc1/2.6.22-rc1-mm1/broken-out/gregkh-driver-sysfs-allocate-inode-number-using-ida.patch

For regular files in sysfs, sysfs_readdir wants to traverse
sysfs_dirent->s_dentry->d_inode->i_ino to get to the inode number.
But, the dentry can be reclaimed under memory pressure, and there is
no synchronization with readdir.  This patch follows Tejun's scheme of
allocating and storing an inode number in the new s_ino member of a
sysfs_dirent, when dirents are created, and retrieving it from there
for readdir, so that the pointer chain doesn't have to be traversed.

Tejun's upstream patch uses a new-ish "ida" allocator which brings
along some extra complexity; this -stable patch has a brain-dead
incrementing counter which does not guarantee uniqueness, but because
sysfs doesn't hash inodes as iunique expects, uniqueness wasn't
guaranteed today anyway.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

4 files changed, 14 insertions, 5 deletions

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 511edef8b32..37430863bc6 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -29,6 +29,14 @@ static struct dentry_operations sysfs_dentry_ops = {
 	.d_iput		= sysfs_d_iput,
 };
 
+static unsigned int sysfs_inode_counter;
+ino_t sysfs_get_inum(void)
+{
+	if (unlikely(sysfs_inode_counter < 3))
+		sysfs_inode_counter = 3;
+	return sysfs_inode_counter++;
+}
+
 /*
  * Allocates a new sysfs_dirent and links it to the parent sysfs_dirent
  */
@@ -42,6 +50,7 @@ static struct sysfs_dirent * sysfs_new_dirent(struct sysfs_dirent * parent_sd,
 		return NULL;
 
 	memset(sd, 0, sizeof(*sd));
+	sd->s_ino = sysfs_get_inum();
 	atomic_set(&sd->s_count, 1);
 	atomic_set(&sd->s_event, 1);
 	INIT_LIST_HEAD(&sd->s_children);
@@ -461,7 +470,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 
 	switch (i) {
 		case 0:
-			ino = dentry->d_inode->i_ino;
+			ino = parent_sd->s_ino;
 			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
 				break;
 			filp->f_pos++;
@@ -490,10 +499,7 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 
 				name = sysfs_get_name(next);
 				len = strlen(name);
-				if (next->s_dentry)
-					ino = next->s_dentry->d_inode->i_ino;
-				else
-					ino = iunique(sysfs_sb, 2);
+				ino = next->s_ino;
 
 				if (filldir(dirent, name, len, filp->f_pos, ino,
 						 dt_type(next)) < 0)
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index e79e38d52c0..bb2da9df368 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -129,6 +129,7 @@ struct inode * sysfs_new_inode(mode_t mode, struct sysfs_dirent * sd)
 		inode->i_mapping->a_ops = &sysfs_aops;
 		inode->i_mapping->backing_dev_info = &sysfs_backing_dev_info;
 		inode->i_op = &sysfs_inode_operations;
+		inode->i_ino = sd->s_ino;
 		lockdep_set_class(&inode->i_mutex, &sysfs_inode_imutex_key);
 
 		if (sd->s_iattr) {
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index e503f858fba..4305e460e20 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -29,6 +29,7 @@ static struct sysfs_dirent sysfs_root = {
 	.s_element	= NULL,
 	.s_type		= SYSFS_ROOT,
 	.s_iattr	= NULL,
+	.s_ino		= 1,
 };
 
 static int sysfs_fill_super(struct super_block *sb, void *data, int silent)
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 2129d1b6c87..8799dc3c92b 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -73,6 +73,7 @@ struct sysfs_dirent {
 	void 			* s_element;
 	int			s_type;
 	umode_t			s_mode;
+	ino_t			s_ino;
 	struct dentry		* s_dentry;
 	struct iattr		* s_iattr;
 	atomic_t		s_event;