From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Al Viro <viro@zeniv.linux.org.uk>
Subject: [ 53/60] reiserfs: fix deadlock in umount
Date: Mon, 12 Aug 2013 23:34:20 -0700 [thread overview]
Message-ID: <20130813063338.636644858@linuxfoundation.org> (raw)
In-Reply-To: <20130813063331.950321483@linuxfoundation.org>
3.10-stable review patch. If anyone has any objections, please let me know.
------------------
From: Al Viro <viro@zeniv.linux.org.uk>
commit 672fe15d091ce76d6fb98e489962e9add7c1ba4c upstream.
Since remove_proc_entry() started to wait for IO in progress (i.e.
since 2007 or so), the locking in fs/reiserfs/proc.c became wrong;
if procfs read happens between the moment when umount() locks the
victim superblock and removal of /proc/fs/reiserfs/<device>/*,
we'll get a deadlock - read will wait for s_umount (in sget(),
called by r_start()), while umount will wait in remove_proc_entry()
for that read to finish, holding s_umount all along.
Fortunately, the same change allows a much simpler race avoidance -
all we need to do is remove the procfs entries in the very beginning
of reiserfs ->kill_sb(); that'll guarantee that pointer to superblock
will remain valid for the duration for procfs IO, so we don't need
sget() to keep the sucker alive. As the matter of fact, we can
get rid of the home-grown iterator completely, and use single_open()
instead.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
fs/reiserfs/procfs.c | 99 +++++++++------------------------------------------
fs/reiserfs/super.c | 3 -
2 files changed, 20 insertions(+), 82 deletions(-)
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -19,12 +19,13 @@
/*
* LOCKING:
*
- * We rely on new Alexander Viro's super-block locking.
+ * These guys are evicted from procfs as the very first step in ->kill_sb().
*
*/
-static int show_version(struct seq_file *m, struct super_block *sb)
+static int show_version(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
char *format;
if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
@@ -66,8 +67,9 @@ static int show_version(struct seq_file
#define DJP( x ) le32_to_cpu( jp -> x )
#define JF( x ) ( r -> s_journal -> x )
-static int show_super(struct seq_file *m, struct super_block *sb)
+static int show_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "state: \t%s\n"
@@ -128,8 +130,9 @@ static int show_super(struct seq_file *m
return 0;
}
-static int show_per_level(struct seq_file *m, struct super_block *sb)
+static int show_per_level(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
int level;
@@ -186,8 +189,9 @@ static int show_per_level(struct seq_fil
return 0;
}
-static int show_bitmap(struct seq_file *m, struct super_block *sb)
+static int show_bitmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "free_block: %lu\n"
@@ -218,8 +222,9 @@ static int show_bitmap(struct seq_file *
return 0;
}
-static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+static int show_on_disk_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
int hash_code = DFL(s_hash_function_code);
@@ -261,8 +266,9 @@ static int show_on_disk_super(struct seq
return 0;
}
-static int show_oidmap(struct seq_file *m, struct super_block *sb)
+static int show_oidmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
@@ -291,8 +297,9 @@ static int show_oidmap(struct seq_file *
return 0;
}
-static int show_journal(struct seq_file *m, struct super_block *sb)
+static int show_journal(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
struct reiserfs_super_block *rs = r->s_rs;
struct journal_params *jp = &rs->s_v1.s_journal;
@@ -383,92 +390,24 @@ static int show_journal(struct seq_file
return 0;
}
-/* iterator */
-static int test_sb(struct super_block *sb, void *data)
-{
- return data == sb;
-}
-
-static int set_sb(struct super_block *sb, void *data)
-{
- return -ENOENT;
-}
-
-struct reiserfs_seq_private {
- struct super_block *sb;
- int (*show) (struct seq_file *, struct super_block *);
-};
-
-static void *r_start(struct seq_file *m, loff_t * pos)
-{
- struct reiserfs_seq_private *priv = m->private;
- loff_t l = *pos;
-
- if (l)
- return NULL;
-
- if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb)))
- return NULL;
-
- up_write(&priv->sb->s_umount);
- return priv->sb;
-}
-
-static void *r_next(struct seq_file *m, void *v, loff_t * pos)
-{
- ++*pos;
- if (v)
- deactivate_super(v);
- return NULL;
-}
-
-static void r_stop(struct seq_file *m, void *v)
-{
- if (v)
- deactivate_super(v);
-}
-
-static int r_show(struct seq_file *m, void *v)
-{
- struct reiserfs_seq_private *priv = m->private;
- return priv->show(m, v);
-}
-
-static const struct seq_operations r_ops = {
- .start = r_start,
- .next = r_next,
- .stop = r_stop,
- .show = r_show,
-};
-
static int r_open(struct inode *inode, struct file *file)
{
- struct reiserfs_seq_private *priv;
- int ret = seq_open_private(file, &r_ops,
- sizeof(struct reiserfs_seq_private));
-
- if (!ret) {
- struct seq_file *m = file->private_data;
- priv = m->private;
- priv->sb = proc_get_parent_data(inode);
- priv->show = PDE_DATA(inode);
- }
- return ret;
+ return single_open(file, PDE_DATA(inode),
+ proc_get_parent_data(inode));
}
static const struct file_operations r_file_operations = {
.open = r_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
- .owner = THIS_MODULE,
+ .release = single_release,
};
static struct proc_dir_entry *proc_info_root = NULL;
static const char proc_info_root_name[] = "fs/reiserfs";
static void add_file(struct super_block *sb, char *name,
- int (*func) (struct seq_file *, struct super_block *))
+ int (*func) (struct seq_file *, void *))
{
proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
&r_file_operations, func);
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -499,6 +499,7 @@ int remove_save_link(struct inode *inode
static void reiserfs_kill_sb(struct super_block *s)
{
if (REISERFS_SB(s)) {
+ reiserfs_proc_info_done(s);
/*
* Force any pending inode evictions to occur now. Any
* inodes to be removed that have extended attributes
@@ -554,8 +555,6 @@ static void reiserfs_put_super(struct su
REISERFS_SB(s)->reserved_blocks);
}
- reiserfs_proc_info_done(s);
-
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
kfree(s->s_fs_info);
next prev parent reply other threads:[~2013-08-13 6:34 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-08-13 6:33 [ 00/60] 3.10.7-stable review Greg Kroah-Hartman
2013-08-13 6:33 ` [ 01/60] SCSI: Dont attempt to send extended INQUIRY command if skip_vpd_pages is set Greg Kroah-Hartman
2013-08-13 6:33 ` [ 02/60] SCSI: megaraid_sas: megaraid_sas driver init fails in kdump kernel Greg Kroah-Hartman
2013-08-13 6:33 ` [ 03/60] virtio-scsi: Fix virtqueue affinity setup Greg Kroah-Hartman
2013-08-13 6:33 ` [ 04/60] powerpc: On POWERNV enable PPC_DENORMALISATION by default Greg Kroah-Hartman
2013-08-13 6:33 ` [ 05/60] powerpc: Fix hypervisor facility unavaliable vector number Greg Kroah-Hartman
2013-08-13 6:33 ` [ 06/60] powerpc: Rework setting up H/FSCR bit definitions Greg Kroah-Hartman
2013-08-13 6:33 ` [ 07/60] powerpc: Fix context switch DSCR on POWER8 Greg Kroah-Hartman
2013-08-13 6:33 ` [ 08/60] powerpc: Save the TAR register earlier Greg Kroah-Hartman
2013-08-13 6:33 ` [ 09/60] powerpc/tm: Fix context switching TAR, PPR and DSCR SPRs Greg Kroah-Hartman
2013-08-13 6:33 ` [ 10/60] ext4: destroy ext4_es_cachep on module unload Greg Kroah-Hartman
2013-08-13 6:33 ` [ 11/60] ext4: make sure group number is bumped after a inode allocation race Greg Kroah-Hartman
2013-08-13 6:33 ` [ 12/60] ext4: fix retry handling in ext4_ext_truncate() Greg Kroah-Hartman
2013-08-13 6:33 ` [ 13/60] regmap: cache: Make sure to sync the last register in a block Greg Kroah-Hartman
2013-08-13 6:33 ` [ 14/60] regmap: Add missing header for !CONFIG_REGMAP stubs Greg Kroah-Hartman
2013-08-13 6:33 ` [ 15/60] hwmon: (adt7470) Fix incorrect return code check Greg Kroah-Hartman
2013-08-13 6:33 ` [ 16/60] staging: zcache: fix "zcache=" kernel parameter Greg Kroah-Hartman
2013-08-13 6:33 ` [ 17/60] media: em28xx: fix assignment of the eeprom data Greg Kroah-Hartman
2013-08-13 6:33 ` [ 18/60] i2c: i2c-mxs: Use DMA mode even for small transfers Greg Kroah-Hartman
2013-08-13 6:33 ` [ 19/60] cpufreq: loongson2: fix regression related to clock management Greg Kroah-Hartman
2013-08-13 6:33 ` [ 20/60] cpufreq: rename ignore_nice as ignore_nice_load Greg Kroah-Hartman
2013-08-13 6:33 ` [ 21/60] ACPI / PM: Walk physical_node_list under physical_node_lock Greg Kroah-Hartman
2013-08-13 6:33 ` [ 22/60] tracing: Fix fields of struct trace_iterator that are zeroed by mistake Greg Kroah-Hartman
2013-08-13 6:33 ` [ 23/60] tracing: Make TRACE_ITER_STOP_ON_FREE stop the correct buffer Greg Kroah-Hartman
2013-08-13 6:33 ` [ 24/60] tracing: Use flag buffer_disabled for irqsoff tracer Greg Kroah-Hartman
2013-08-13 6:33 ` [ 25/60] tracing: Fix reset of time stamps during trace_clock changes Greg Kroah-Hartman
2013-08-13 6:33 ` [ 26/60] ALSA: usb-audio: do not trust too-big wMaxPacketSize values Greg Kroah-Hartman
2013-08-13 6:33 ` [ 27/60] ALSA: 6fire: fix DMA issues with URB transfer_buffer usage Greg Kroah-Hartman
2013-08-13 6:33 ` [ 28/60] Btrfs: release both paths before logging dir/changed extents Greg Kroah-Hartman
2013-08-13 6:33 ` [ 29/60] LOCKD: Dont call utsname()->nodename from nlmclnt_setlockargs Greg Kroah-Hartman
2013-08-13 6:33 ` [ 30/60] SUNRPC: Dont auto-disconnect from the local rpcbind socket Greg Kroah-Hartman
2013-08-13 6:33 ` [ 31/60] SUNRPC: If the rpcbind channel is disconnected, fail the call to unregister Greg Kroah-Hartman
2013-08-13 6:33 ` [ 32/60] virtio/console: Quit from splice_write if pipe->nrbufs is 0 Greg Kroah-Hartman
2013-08-13 6:34 ` [ 33/60] virtio/console: Add pipe_lock/unlock for splice_write Greg Kroah-Hartman
2013-08-13 6:34 ` [ 34/60] virtio: console: fix race with port unplug and open/close Greg Kroah-Hartman
2013-08-13 6:34 ` [ 35/60] virtio: console: fix race in port_fops_open() and port unplug Greg Kroah-Hartman
2013-08-13 6:34 ` [ 36/60] virtio: console: clean up port data immediately at time of unplug Greg Kroah-Hartman
2013-08-13 6:34 ` [ 37/60] virtio: console: fix raising SIGIO after port unplug Greg Kroah-Hartman
2013-08-13 6:34 ` [ 38/60] virtio: console: return -ENODEV on all read operations after unplug Greg Kroah-Hartman
2013-08-13 6:34 ` [ 39/60] drm/cirrus: Invalidate page tables when pinning a BO Greg Kroah-Hartman
2013-08-13 6:34 ` [ 40/60] drm/mgag200: " Greg Kroah-Hartman
2013-08-13 6:34 ` [ 41/60] drm/ast: invalidate " Greg Kroah-Hartman
2013-08-13 6:34 ` [ 42/60] drm: Dont pass negative delta to ktime_sub_ns() Greg Kroah-Hartman
2013-08-13 6:34 ` [ 43/60] drm/radeon: select audio dto based on encoder id for DCE3 Greg Kroah-Hartman
2013-08-13 6:34 ` [ 44/60] drm/radeon: stop sending invalid UVD destroy msg Greg Kroah-Hartman
2013-08-13 6:34 ` [ 45/60] ext4: allow the mount options nodelalloc and data=journal Greg Kroah-Hartman
2013-08-13 6:34 ` [ 46/60] ext4: fix mount/remount error messages for incompatible mount options Greg Kroah-Hartman
2013-08-13 6:34 ` [ 47/60] ext4: flush the extent status cache during EXT4_IOC_SWAP_BOOT Greg Kroah-Hartman
2013-08-13 6:34 ` [ 48/60] cifs: extend the buffer length enought for sprintf() using Greg Kroah-Hartman
2013-08-13 6:34 ` [ 49/60] cifs: dont instantiate new dentries in readdir for inodes that need to be revalidated immediately Greg Kroah-Hartman
2013-08-13 6:34 ` [ 50/60] zram: allow request end to coincide with disksize Greg Kroah-Hartman
2013-08-13 6:34 ` [ 51/60] usb: core: dont try to reset_device() a port that got just disconnected Greg Kroah-Hartman
2013-08-13 6:34 ` [ 52/60] debugfs: debugfs_remove_recursive() must not rely on list_empty(d_subdirs) Greg Kroah-Hartman
2013-08-13 6:34 ` Greg Kroah-Hartman [this message]
2013-08-13 6:34 ` [ 54/60] drm/i915: initialize gt_lock early with other spin locks Greg Kroah-Hartman
2013-08-13 6:34 ` [ 55/60] drm/radeon: fix halting UVD Greg Kroah-Hartman
2013-08-13 6:34 ` [ 56/60] drm/radeon: only save UVD bo when we have open handles Greg Kroah-Hartman
2013-08-13 6:34 ` [ 57/60] drm/radeon: always program the MC on startup Greg Kroah-Hartman
2013-08-13 6:34 ` [ 58/60] SCSI: nsp32: use mdelay instead of large udelay constants Greg Kroah-Hartman
2013-08-13 6:34 ` [ 59/60] mtd: omap2: allow bulding as a module Greg Kroah-Hartman
2013-08-13 6:34 ` [ 60/60] MIPS: Expose missing pci_io{map,unmap} declarations Greg Kroah-Hartman
2013-08-13 11:57 ` [ 00/60] 3.10.7-stable review Guenter Roeck
2013-08-13 17:57 ` Greg Kroah-Hartman
2013-08-13 17:18 ` Shuah Khan
2013-08-13 17:57 ` Greg Kroah-Hartman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130813063338.636644858@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).