[PATCH 1/3] sysfs: store sysfs inode nrs in s_ino to avoid readdir oopses

From: Tejun Heo
Date: Mon Jun 11 2007 - 01:03:11 EST


From: Eric Sandeen <sandeen@xxxxxxxxxxx>

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@xxxxxxxxxx>
Signed-off-by: Tejun Heo <htejun@xxxxxxxxx>
---
fs/sysfs/dir.c | 16 +++++++++++-----
fs/sysfs/inode.c | 1 +
fs/sysfs/mount.c | 1 +
fs/sysfs/sysfs.h | 1 +
4 files changed, 14 insertions(+), 5 deletions(-)

Index: work1/fs/sysfs/dir.c
===================================================================
--- work1.orig/fs/sysfs/dir.c
+++ work1/fs/sysfs/dir.c
@@ -30,6 +30,14 @@ static struct dentry_operations sysfs_de
.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
*/
@@ -41,6 +49,7 @@ static struct sysfs_dirent * __sysfs_new
if (!sd)
return NULL;

+ sd->s_ino = sysfs_get_inum();
atomic_set(&sd->s_count, 1);
atomic_set(&sd->s_event, 1);
INIT_LIST_HEAD(&sd->s_children);
@@ -509,7 +518,7 @@ static int sysfs_readdir(struct file * f

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++;
@@ -538,10 +547,7 @@ static int sysfs_readdir(struct file * f

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)
Index: work1/fs/sysfs/inode.c
===================================================================
--- work1.orig/fs/sysfs/inode.c
+++ work1/fs/sysfs/inode.c
@@ -141,6 +141,7 @@ struct inode * sysfs_new_inode(mode_t mo
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) {
Index: work1/fs/sysfs/mount.c
===================================================================
--- work1.orig/fs/sysfs/mount.c
+++ work1/fs/sysfs/mount.c
@@ -33,6 +33,7 @@ static struct sysfs_dirent sysfs_root =
.s_element = NULL,
.s_type = SYSFS_ROOT,
.s_iattr = NULL,
+ .s_ino = 1,
};

static void sysfs_clear_inode(struct inode *inode)
Index: work1/fs/sysfs/sysfs.h
===================================================================
--- work1.orig/fs/sysfs/sysfs.h
+++ work1/fs/sysfs/sysfs.h
@@ -5,6 +5,7 @@ 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;
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/