From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Dave Wysochanski <dwysocha@redhat.com>,
Ronnie Sahlberg <lsahlber@redhat.com>,
Pavel Shilovsky <pshilov@microsoft.com>,
Sasha Levin <sashal@kernel.org>,
linux-cifs@vger.kernel.org
Subject: [PATCH AUTOSEL 4.14 22/24] cifs: Fix cifsInodeInfo lock_sem deadlock when reconnect occurs
Date: Wed, 30 Oct 2019 11:55:53 -0400 [thread overview]
Message-ID: <20191030155555.10494-22-sashal@kernel.org> (raw)
In-Reply-To: <20191030155555.10494-1-sashal@kernel.org>
From: Dave Wysochanski <dwysocha@redhat.com>
[ Upstream commit d46b0da7a33dd8c99d969834f682267a45444ab3 ]
There's a deadlock that is possible and can easily be seen with
a test where multiple readers open/read/close of the same file
and a disruption occurs causing reconnect. The deadlock is due
a reader thread inside cifs_strict_readv calling down_read and
obtaining lock_sem, and then after reconnect inside
cifs_reopen_file calling down_read a second time. If in
between the two down_read calls, a down_write comes from
another process, deadlock occurs.
CPU0 CPU1
---- ----
cifs_strict_readv()
down_read(&cifsi->lock_sem);
_cifsFileInfo_put
OR
cifs_new_fileinfo
down_write(&cifsi->lock_sem);
cifs_reopen_file()
down_read(&cifsi->lock_sem);
Fix the above by changing all down_write(lock_sem) calls to
down_write_trylock(lock_sem)/msleep() loop, which in turn
makes the second down_read call benign since it will never
block behind the writer while holding lock_sem.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Suggested-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed--by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
fs/cifs/cifsglob.h | 5 +++++
fs/cifs/cifsproto.h | 1 +
fs/cifs/file.c | 23 +++++++++++++++--------
fs/cifs/smb2file.c | 2 +-
4 files changed, 22 insertions(+), 9 deletions(-)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 7b7ab10a9db18..600bb838c15b8 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1210,6 +1210,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
struct cifsInodeInfo {
bool can_cache_brlcks;
struct list_head llist; /* locks helb by this inode */
+ /*
+ * NOTE: Some code paths call down_read(lock_sem) twice, so
+ * we must always use use cifs_down_write() instead of down_write()
+ * for this semaphore to avoid deadlocks.
+ */
struct rw_semaphore lock_sem; /* protect the fields above */
/* BB add in lists for dirty pages i.e. write caching info for oplock */
struct list_head openFileList;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index ccdb42f71b2e8..3a7fb8e750e97 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -149,6 +149,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile,
struct file_lock *flock, const unsigned int xid);
extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
+extern void cifs_down_write(struct rw_semaphore *sem);
extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
struct file *file,
struct tcon_link *tlink,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 71a960da7cce1..40f22932343c6 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -280,6 +280,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode)
return has_locks;
}
+void
+cifs_down_write(struct rw_semaphore *sem)
+{
+ while (!down_write_trylock(sem))
+ msleep(10);
+}
+
struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock)
@@ -305,7 +312,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
INIT_LIST_HEAD(&fdlocks->locks);
fdlocks->cfile = cfile;
cfile->llist = fdlocks;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add(&fdlocks->llist, &cinode->llist);
up_write(&cinode->lock_sem);
@@ -457,7 +464,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
* Delete any outstanding lock records. We'll lose them when the file
* is closed anyway.
*/
- down_write(&cifsi->lock_sem);
+ cifs_down_write(&cifsi->lock_sem);
list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
list_del(&li->llist);
cifs_del_lock_waiters(li);
@@ -1011,7 +1018,7 @@ static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_add_tail(&lock->llist, &cfile->llist->locks);
up_write(&cinode->lock_sem);
}
@@ -1033,7 +1040,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
try_again:
exist = false;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
lock->type, &conf_lock, CIFS_LOCK_OP);
@@ -1055,7 +1062,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
(lock->blist.next == &lock->blist));
if (!rc)
goto try_again;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_del_init(&lock->blist);
}
@@ -1108,7 +1115,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
return rc;
try_again:
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1314,7 +1321,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
int rc = 0;
/* we are going to update can_cache_brlcks here - need a write access */
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
if (!cinode->can_cache_brlcks) {
up_write(&cinode->lock_sem);
return rc;
@@ -1505,7 +1512,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
if (!buf)
return -ENOMEM;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
for (i = 0; i < 2; i++) {
cur = buf;
num = 0;
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 1add404618f06..2c809233084bb 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -139,7 +139,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
cur = buf;
- down_write(&cinode->lock_sem);
+ cifs_down_write(&cinode->lock_sem);
list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
if (flock->fl_start > li->offset ||
(flock->fl_start + length) <
--
2.20.1
next prev parent reply other threads:[~2019-10-30 15:57 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-30 15:55 [PATCH AUTOSEL 4.14 01/24] arm64: dts: Fix gpio to pinmux mapping Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 02/24] regulator: ti-abb: Fix timeout in ti_abb_wait_txdone/ti_abb_clear_all_txdone Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 03/24] regulator: pfuze100-regulator: Variable "val" in pfuze100_regulator_probe() could be uninitialized Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 04/24] ASoC: wm_adsp: Don't generate kcontrols without READ flags Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 05/24] ASoc: rockchip: i2s: Fix RPM imbalance Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 06/24] ARM: dts: logicpd-torpedo-som: Remove twl_keypad Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 07/24] pinctrl: ns2: Fix off by one bugs in ns2_pinmux_enable() Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 08/24] ARM: mm: fix alignment handler faults under memory pressure Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 09/24] scsi: scsi_dh_alua: handle RTPG sense code correctly during state transitions Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 10/24] scsi: sni_53c710: fix compilation error Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 11/24] scsi: fix kconfig dependency warning related to 53C700_LE_ON_BE Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 12/24] ARM: dts: imx7s: Correct GPT's ipg clock source Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 13/24] perf c2c: Fix memory leak in build_cl_output() Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 14/24] USB: legousbtower: fix a signedness bug in tower_probe() Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 15/24] perf kmem: Fix memory leak in compact_gfp_flags() Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 16/24] ARM: davinci: dm365: Fix McBSP dma_slave_map entry Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 17/24] scsi: target: core: Do not overwrite CDB byte 1 Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 18/24] ARM: 8926/1: v7m: remove register save to stack before svc Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 19/24] of: unittest: fix memory leak in unittest_data_add Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 20/24] MIPS: bmips: mark exception vectors as char arrays Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 21/24] i2c: stm32f7: remove warning when compiling with W=1 Sasha Levin
2019-10-30 15:55 ` Sasha Levin [this message]
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 23/24] nbd: handle racing with error'ed out commands Sasha Levin
2019-10-30 15:55 ` [PATCH AUTOSEL 4.14 24/24] nbd: verify socket is supported during setup Sasha Levin
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=20191030155555.10494-22-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=dwysocha@redhat.com \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lsahlber@redhat.com \
--cc=pshilov@microsoft.com \
--cc=stable@vger.kernel.org \
/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).