Eric Ren
2017-Jan-05 15:31 UTC
[Ocfs2-devel] [PATCH 2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points
Commit 743b5f1434f5 ("ocfs2: take inode lock in
ocfs2_iop_set/get_acl()")
results in a deadlock, as the author "Tariq Saeed" realized shortly
after the patch was merged. The discussion happened here
(https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html).
The reason why taking cluster inode lock at vfs entry points opens up
a self deadlock window, is explained in the previous patch of this
series.
So far, we have seen two different code paths that have this issue.
1. do_sys_open
may_open
inode_permission
ocfs2_permission
ocfs2_inode_lock() <=== take PR
generic_permission
get_acl
ocfs2_iop_get_acl
ocfs2_inode_lock() <=== take PR
2. fchmod|fchmodat
chmod_common
notify_change
ocfs2_setattr <=== take EX
posix_acl_chmod
get_acl
ocfs2_iop_get_acl <=== take PR
ocfs2_iop_set_acl <=== take EX
Fixes them by adding the tracking logic (in the previous patch) for
these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(),
ocfs2_setattr().
Signed-off-by: Eric Ren <zren at suse.com>
---
fs/ocfs2/acl.c | 39 ++++++++++++++++++++++++++++++++++-----
fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++----------
2 files changed, 68 insertions(+), 15 deletions(-)
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index bed1fcb..c539890 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct
posix_acl *acl, int type)
{
struct buffer_head *bh = NULL;
int status = 0;
-
- status = ocfs2_inode_lock(inode, &bh, 1);
+ int arg_flags = 0, has_locked;
+ struct ocfs2_holder oh;
+ struct ocfs2_lock_res *lockres;
+
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+ if (has_locked)
+ arg_flags = OCFS2_META_LOCK_GETBH;
+ status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
if (status < 0) {
if (status != -ENOENT)
mlog_errno(status);
return status;
}
+ if (!has_locked)
+ ocfs2_add_holder(lockres, &oh);
+
status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
- ocfs2_inode_unlock(inode, 1);
+
+ if (!has_locked) {
+ ocfs2_remove_holder(lockres, &oh);
+ ocfs2_inode_unlock(inode, 1);
+ }
brelse(bh);
+
return status;
}
@@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode,
int type)
struct buffer_head *di_bh = NULL;
struct posix_acl *acl;
int ret;
+ int arg_flags = 0, has_locked;
+ struct ocfs2_holder oh;
+ struct ocfs2_lock_res *lockres;
osb = OCFS2_SB(inode->i_sb);
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
return NULL;
- ret = ocfs2_inode_lock(inode, &di_bh, 0);
+
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+ if (has_locked)
+ arg_flags = OCFS2_META_LOCK_GETBH;
+ ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags);
if (ret < 0) {
if (ret != -ENOENT)
mlog_errno(ret);
return ERR_PTR(ret);
}
+ if (!has_locked)
+ ocfs2_add_holder(lockres, &oh);
acl = ocfs2_get_acl_nolock(inode, type, di_bh);
- ocfs2_inode_unlock(inode, 0);
+ if (!has_locked) {
+ ocfs2_remove_holder(lockres, &oh);
+ ocfs2_inode_unlock(inode, 0);
+ }
brelse(di_bh);
+
return acl;
}
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index c488965..62be75d 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr
*attr)
handle_t *handle = NULL;
struct dquot *transfer_to[MAXQUOTAS] = { };
int qtype;
+ int arg_flags = 0, had_lock;
+ struct ocfs2_holder oh;
+ struct ocfs2_lock_res *lockres;
trace_ocfs2_setattr(inode, dentry,
(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr
*attr)
}
}
- status = ocfs2_inode_lock(inode, &bh, 1);
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);
+ if (had_lock)
+ arg_flags = OCFS2_META_LOCK_GETBH;
+ status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags);
if (status < 0) {
if (status != -ENOENT)
mlog_errno(status);
goto bail_unlock_rw;
}
- inode_locked = 1;
+ if (!had_lock) {
+ ocfs2_add_holder(lockres, &oh);
+ inode_locked = 1;
+ }
if (size_change) {
status = inode_newsize_ok(inode, attr->ia_size);
@@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr
*attr)
bail_commit:
ocfs2_commit_trans(osb, handle);
bail_unlock:
- if (status) {
+ if (status && inode_locked) {
+ ocfs2_remove_holder(lockres, &oh);
ocfs2_inode_unlock(inode, 1);
inode_locked = 0;
}
@@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr
*attr)
if (status < 0)
mlog_errno(status);
}
- if (inode_locked)
+ if (inode_locked) {
+ ocfs2_remove_holder(lockres, &oh);
ocfs2_inode_unlock(inode, 1);
+ }
brelse(bh);
return status;
@@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt,
int ocfs2_permission(struct inode *inode, int mask)
{
int ret;
+ int has_locked;
+ struct ocfs2_holder oh;
+ struct ocfs2_lock_res *lockres;
if (mask & MAY_NOT_BLOCK)
return -ECHILD;
- ret = ocfs2_inode_lock(inode, NULL, 0);
- if (ret) {
- if (ret != -ENOENT)
- mlog_errno(ret);
- goto out;
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
+ if (!has_locked) {
+ ret = ocfs2_inode_lock(inode, NULL, 0);
+ if (ret) {
+ if (ret != -ENOENT)
+ mlog_errno(ret);
+ goto out;
+ }
+ ocfs2_add_holder(lockres, &oh);
}
ret = generic_permission(inode, mask);
- ocfs2_inode_unlock(inode, 0);
+ if (!has_locked) {
+ ocfs2_remove_holder(lockres, &oh);
+ ocfs2_inode_unlock(inode, 0);
+ }
out:
return ret;
}
--
2.6.6
Joseph Qi
2017-Jan-06 06:09 UTC
[Ocfs2-devel] [PATCH 2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points
Hi Eric, On 17/1/5 23:31, Eric Ren wrote:> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()") > results in a deadlock, as the author "Tariq Saeed" realized shortly > after the patch was merged. The discussion happened here > (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html). > > The reason why taking cluster inode lock at vfs entry points opens up > a self deadlock window, is explained in the previous patch of this > series. > > So far, we have seen two different code paths that have this issue. > 1. do_sys_open > may_open > inode_permission > ocfs2_permission > ocfs2_inode_lock() <=== take PR > generic_permission > get_acl > ocfs2_iop_get_acl > ocfs2_inode_lock() <=== take PR > 2. fchmod|fchmodat > chmod_common > notify_change > ocfs2_setattr <=== take EX > posix_acl_chmod > get_acl > ocfs2_iop_get_acl <=== take PR > ocfs2_iop_set_acl <=== take EX > > Fixes them by adding the tracking logic (in the previous patch) for > these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(), > ocfs2_setattr().As described cases above, shall we just add the tracking logic only for set/get_acl()? Thanks, Joseph> > Signed-off-by: Eric Ren <zren at suse.com> > --- > fs/ocfs2/acl.c | 39 ++++++++++++++++++++++++++++++++++----- > fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++---------- > 2 files changed, 68 insertions(+), 15 deletions(-) > > diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c > index bed1fcb..c539890 100644 > --- a/fs/ocfs2/acl.c > +++ b/fs/ocfs2/acl.c > @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) > { > struct buffer_head *bh = NULL; > int status = 0; > - > - status = ocfs2_inode_lock(inode, &bh, 1); > + int arg_flags = 0, has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > + > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (has_locked) > + arg_flags = OCFS2_META_LOCK_GETBH; > + status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags); > if (status < 0) { > if (status != -ENOENT) > mlog_errno(status); > return status; > } > + if (!has_locked) > + ocfs2_add_holder(lockres, &oh); > + > status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL); > - ocfs2_inode_unlock(inode, 1); > + > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 1); > + } > brelse(bh); > + > return status; > } > > @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) > struct buffer_head *di_bh = NULL; > struct posix_acl *acl; > int ret; > + int arg_flags = 0, has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > osb = OCFS2_SB(inode->i_sb); > if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) > return NULL; > - ret = ocfs2_inode_lock(inode, &di_bh, 0); > + > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (has_locked) > + arg_flags = OCFS2_META_LOCK_GETBH; > + ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags); > if (ret < 0) { > if (ret != -ENOENT) > mlog_errno(ret); > return ERR_PTR(ret); > } > + if (!has_locked) > + ocfs2_add_holder(lockres, &oh); > > acl = ocfs2_get_acl_nolock(inode, type, di_bh); > > - ocfs2_inode_unlock(inode, 0); > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 0); > + } > brelse(di_bh); > + > return acl; > } > > diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c > index c488965..62be75d 100644 > --- a/fs/ocfs2/file.c > +++ b/fs/ocfs2/file.c > @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > handle_t *handle = NULL; > struct dquot *transfer_to[MAXQUOTAS] = { }; > int qtype; > + int arg_flags = 0, had_lock; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > trace_ocfs2_setattr(inode, dentry, > (unsigned long long)OCFS2_I(inode)->ip_blkno, > @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > } > } > > - status = ocfs2_inode_lock(inode, &bh, 1); > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + had_lock = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (had_lock) > + arg_flags = OCFS2_META_LOCK_GETBH; > + status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags); > if (status < 0) { > if (status != -ENOENT) > mlog_errno(status); > goto bail_unlock_rw; > } > - inode_locked = 1; > + if (!had_lock) { > + ocfs2_add_holder(lockres, &oh); > + inode_locked = 1; > + } > > if (size_change) { > status = inode_newsize_ok(inode, attr->ia_size); > @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > bail_commit: > ocfs2_commit_trans(osb, handle); > bail_unlock: > - if (status) { > + if (status && inode_locked) { > + ocfs2_remove_holder(lockres, &oh); > ocfs2_inode_unlock(inode, 1); > inode_locked = 0; > } > @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > if (status < 0) > mlog_errno(status); > } > - if (inode_locked) > + if (inode_locked) { > + ocfs2_remove_holder(lockres, &oh); > ocfs2_inode_unlock(inode, 1); > + } > > brelse(bh); > return status; > @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt, > int ocfs2_permission(struct inode *inode, int mask) > { > int ret; > + int has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > if (mask & MAY_NOT_BLOCK) > return -ECHILD; > > - ret = ocfs2_inode_lock(inode, NULL, 0); > - if (ret) { > - if (ret != -ENOENT) > - mlog_errno(ret); > - goto out; > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (!has_locked) { > + ret = ocfs2_inode_lock(inode, NULL, 0); > + if (ret) { > + if (ret != -ENOENT) > + mlog_errno(ret); > + goto out; > + } > + ocfs2_add_holder(lockres, &oh); > } > > ret = generic_permission(inode, mask); > > - ocfs2_inode_unlock(inode, 0); > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 0); > + } > out: > return ret; > }
kbuild test robot
2017-Jan-06 14:52 UTC
[Ocfs2-devel] [PATCH 2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points
Hi Eric,
[auto build test ERROR on linus/master]
[also build test ERROR on v4.10-rc2 next-20170106]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Eric-Ren/fix-deadlock-caused-by-recursive-cluster-locking/20170106-200837
config: ia64-allyesconfig (attached as .config)
compiler: ia64-linux-gcc (GCC) 6.2.0
reproduce:
wget
https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross
-O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=ia64
All errors (new ones prefixed by >>):
In file included from fs/ocfs2/acl.c:31:0:
fs/ocfs2/acl.c: In function
'ocfs2_iop_set_acl':>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to
always_inline 'ocfs2_is_locked_by_me': function body not available
inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res
*lockres);
^~~~~~~~~~~~~~~~~~~~~
fs/ocfs2/acl.c:292:16: note: called from here
has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/acl.c:31:0:>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to
always_inline 'ocfs2_is_locked_by_me': function body not available
inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res
*lockres);
^~~~~~~~~~~~~~~~~~~~~
fs/ocfs2/acl.c:292:16: note: called from here
has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/acl.c:31:0:>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to
always_inline 'ocfs2_add_holder': function body not available
inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
^~~~~~~~~~~~~~~~
fs/ocfs2/acl.c:302:3: note: called from here
ocfs2_add_holder(lockres, &oh);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/acl.c:31:0:>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to
always_inline 'ocfs2_remove_holder': function body not available
inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
^~~~~~~~~~~~~~~~~~~
fs/ocfs2/acl.c:307:3: note: called from here
ocfs2_remove_holder(lockres, &oh);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
--
In file included from arch/ia64/include/uapi/asm/intrinsics.h:21:0,
from arch/ia64/include/asm/intrinsics.h:10,
from arch/ia64/include/asm/bitops.h:18,
from include/linux/bitops.h:36,
from include/linux/kernel.h:10,
from include/linux/list.h:8,
from include/linux/wait.h:6,
from include/linux/fs.h:5,
from fs/ocfs2/file.c:27:
fs/ocfs2/file.c: In function 'ocfs2_file_write_iter':
arch/ia64/include/uapi/asm/cmpxchg.h:56:2: warning: value computed is not
used [-Wunused-value]
((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr))))
~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
fs/ocfs2/file.c:2334:3: note: in expansion of macro 'xchg'
xchg(&iocb->ki_complete, saved_ki_complete);
^~~~
In file included from fs/ocfs2/file.c:49:0:
fs/ocfs2/file.c: In function
'ocfs2_permission':>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to
always_inline 'ocfs2_is_locked_by_me': function body not available
inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res
*lockres);
^~~~~~~~~~~~~~~~~~~~~
fs/ocfs2/file.c:1345:16: note: called from here
has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/file.c:49:0:>> fs/ocfs2/dlmglue.h:189:29: error: inlining failed in call to
always_inline 'ocfs2_is_locked_by_me': function body not available
inline struct ocfs2_holder *ocfs2_is_locked_by_me(struct ocfs2_lock_res
*lockres);
^~~~~~~~~~~~~~~~~~~~~
fs/ocfs2/file.c:1345:16: note: called from here
has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/file.c:49:0:>> fs/ocfs2/dlmglue.h:185:13: error: inlining failed in call to
always_inline 'ocfs2_add_holder': function body not available
inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
^~~~~~~~~~~~~~~~
fs/ocfs2/file.c:1353:3: note: called from here
ocfs2_add_holder(lockres, &oh);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from fs/ocfs2/file.c:49:0:>> fs/ocfs2/dlmglue.h:187:13: error: inlining failed in call to
always_inline 'ocfs2_remove_holder': function body not available
inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
^~~~~~~~~~~~~~~~~~~
fs/ocfs2/file.c:1359:3: note: called from here
ocfs2_remove_holder(lockres, &oh);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
vim +/ocfs2_is_locked_by_me +189 fs/ocfs2/dlmglue.h
63e0c48a Joel Becker 2008-01-30 179 void ocfs2_set_locking_protocol(void);
9fb5ed3a Eric Ren 2017-01-05 180
9fb5ed3a Eric Ren 2017-01-05 181 /*
9fb5ed3a Eric Ren 2017-01-05 182 * Keep a list of processes who have
interest in a lockres.
9fb5ed3a Eric Ren 2017-01-05 183 * Note: this is now only uesed for check
recursive cluster lock.
9fb5ed3a Eric Ren 2017-01-05 184 */
9fb5ed3a Eric Ren 2017-01-05 @185 inline void ocfs2_add_holder(struct
ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren 2017-01-05 186 struct ocfs2_holder *oh);
9fb5ed3a Eric Ren 2017-01-05 @187 inline void ocfs2_remove_holder(struct
ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren 2017-01-05 188 struct ocfs2_holder *oh);
9fb5ed3a Eric Ren 2017-01-05 @189 inline struct ocfs2_holder
*ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
9fb5ed3a Eric Ren 2017-01-05 190
ccd979bd Mark Fasheh 2005-12-15 191 #endif /* DLMGLUE_H */
:::::: The code at line 189 was first introduced by commit
:::::: 9fb5ed3abab2100ae8d99cee9b25fb92e3154224 ocfs2/dlmglue: prepare tracking
logic to avoid recursive cluster lock
:::::: TO: Eric Ren <zren at suse.com>
:::::: CC: 0day robot <fengguang.wu at intel.com>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
-------------- next part --------------
A non-text attachment was scrubbed...
Name: .config.gz
Type: application/gzip
Size: 48810 bytes
Desc: not available
Url :
http://oss.oracle.com/pipermail/ocfs2-devel/attachments/20170106/c484897a/attachment-0001.bin
kbuild test robot
2017-Jan-06 17:53 UTC
[Ocfs2-devel] [PATCH 2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points
Hi Eric,
[auto build test WARNING on linus/master]
[also build test WARNING on v4.10-rc2 next-20170106]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Eric-Ren/fix-deadlock-caused-by-recursive-cluster-locking/20170106-200837
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
include/linux/compiler.h:253:8: sparse: attribute
'no_sanitize_address': unknown attribute>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a
definition
fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a
definition>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a
definition
fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
--
include/linux/compiler.h:253:8: sparse: attribute
'no_sanitize_address': unknown attribute>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a
definition
fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a
definition>> fs/ocfs2/dlmglue.h:189:50: sparse: marked inline, but without a
definition
fs/ocfs2/dlmglue.h:185:29: sparse: marked inline, but without a definition
fs/ocfs2/dlmglue.h:187:32: sparse: marked inline, but without a definition
vim +189 fs/ocfs2/dlmglue.h
34d024f8 Mark Fasheh 2007-09-24 173 void ocfs2_wake_downconvert_thread(struct
ocfs2_super *osb);
ccd979bd Mark Fasheh 2005-12-15 174
ccd979bd Mark Fasheh 2005-12-15 175 struct ocfs2_dlm_debug
*ocfs2_new_dlm_debug(void);
ccd979bd Mark Fasheh 2005-12-15 176 void ocfs2_put_dlm_debug(struct
ocfs2_dlm_debug *dlm_debug);
ccd979bd Mark Fasheh 2005-12-15 177
63e0c48a Joel Becker 2008-01-30 178 /* To set the locking protocol on module
initialization */
63e0c48a Joel Becker 2008-01-30 179 void ocfs2_set_locking_protocol(void);
9fb5ed3a Eric Ren 2017-01-05 180
9fb5ed3a Eric Ren 2017-01-05 181 /*
9fb5ed3a Eric Ren 2017-01-05 182 * Keep a list of processes who have
interest in a lockres.
9fb5ed3a Eric Ren 2017-01-05 183 * Note: this is now only uesed for check
recursive cluster lock.
9fb5ed3a Eric Ren 2017-01-05 184 */
9fb5ed3a Eric Ren 2017-01-05 185 inline void ocfs2_add_holder(struct
ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren 2017-01-05 186 struct ocfs2_holder *oh);
9fb5ed3a Eric Ren 2017-01-05 187 inline void ocfs2_remove_holder(struct
ocfs2_lock_res *lockres,
9fb5ed3a Eric Ren 2017-01-05 188 struct ocfs2_holder *oh);
9fb5ed3a Eric Ren 2017-01-05 @189 inline struct ocfs2_holder
*ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres);
9fb5ed3a Eric Ren 2017-01-05 190
ccd979bd Mark Fasheh 2005-12-15 191 #endif /* DLMGLUE_H */
:::::: The code at line 189 was first introduced by commit
:::::: 9fb5ed3abab2100ae8d99cee9b25fb92e3154224 ocfs2/dlmglue: prepare tracking
logic to avoid recursive cluster lock
:::::: TO: Eric Ren <zren at suse.com>
:::::: CC: 0day robot <fengguang.wu at intel.com>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
Junxiao Bi
2017-Jan-13 04:22 UTC
[Ocfs2-devel] [PATCH 2/2] ocfs2: fix deadlocks when taking inode lock at vfs entry points
On 01/05/2017 11:31 PM, Eric Ren wrote:> Commit 743b5f1434f5 ("ocfs2: take inode lock in ocfs2_iop_set/get_acl()") > results in a deadlock, as the author "Tariq Saeed" realized shortly > after the patch was merged. The discussion happened here > (https://oss.oracle.com/pipermail/ocfs2-devel/2015-September/011085.html). > > The reason why taking cluster inode lock at vfs entry points opens up > a self deadlock window, is explained in the previous patch of this > series. > > So far, we have seen two different code paths that have this issue. > 1. do_sys_open > may_open > inode_permission > ocfs2_permission > ocfs2_inode_lock() <=== take PR > generic_permission > get_acl > ocfs2_iop_get_acl > ocfs2_inode_lock() <=== take PR > 2. fchmod|fchmodat > chmod_common > notify_change > ocfs2_setattr <=== take EX > posix_acl_chmod > get_acl > ocfs2_iop_get_acl <=== take PR > ocfs2_iop_set_acl <=== take EX > > Fixes them by adding the tracking logic (in the previous patch) for > these funcs above, ocfs2_permission(), ocfs2_iop_[set|get]_acl(), > ocfs2_setattr(). > > Signed-off-by: Eric Ren <zren at suse.com> > --- > fs/ocfs2/acl.c | 39 ++++++++++++++++++++++++++++++++++----- > fs/ocfs2/file.c | 44 ++++++++++++++++++++++++++++++++++---------- > 2 files changed, 68 insertions(+), 15 deletions(-) > > diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c > index bed1fcb..c539890 100644 > --- a/fs/ocfs2/acl.c > +++ b/fs/ocfs2/acl.c > @@ -284,16 +284,31 @@ int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type) > { > struct buffer_head *bh = NULL; > int status = 0; > - > - status = ocfs2_inode_lock(inode, &bh, 1); > + int arg_flags = 0, has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > + > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (has_locked) > + arg_flags = OCFS2_META_LOCK_GETBH; > + status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags); > if (status < 0) { > if (status != -ENOENT) > mlog_errno(status); > return status; > } > + if (!has_locked) > + ocfs2_add_holder(lockres, &oh); > + > status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL); > - ocfs2_inode_unlock(inode, 1); > + > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 1); > + } > brelse(bh); > + > return status; > } > > @@ -303,21 +318,35 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type) > struct buffer_head *di_bh = NULL; > struct posix_acl *acl; > int ret; > + int arg_flags = 0, has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > osb = OCFS2_SB(inode->i_sb); > if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL)) > return NULL; > - ret = ocfs2_inode_lock(inode, &di_bh, 0); > + > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL); > + if (has_locked) > + arg_flags = OCFS2_META_LOCK_GETBH; > + ret = ocfs2_inode_lock_full(inode, &di_bh, 0, arg_flags); > if (ret < 0) { > if (ret != -ENOENT) > mlog_errno(ret); > return ERR_PTR(ret); > } > + if (!has_locked) > + ocfs2_add_holder(lockres, &oh); > > acl = ocfs2_get_acl_nolock(inode, type, di_bh); > > - ocfs2_inode_unlock(inode, 0); > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 0); > + } > brelse(di_bh); > + > return acl; > } > > diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c > index c488965..62be75d 100644 > --- a/fs/ocfs2/file.c > +++ b/fs/ocfs2/file.c > @@ -1138,6 +1138,9 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > handle_t *handle = NULL; > struct dquot *transfer_to[MAXQUOTAS] = { }; > int qtype; > + int arg_flags = 0, had_lock; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > trace_ocfs2_setattr(inode, dentry, > (unsigned long long)OCFS2_I(inode)->ip_blkno, > @@ -1173,13 +1176,20 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > } > } > > - status = ocfs2_inode_lock(inode, &bh, 1); > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + had_lock = (ocfs2_is_locked_by_me(lockres) != NULL);If had_lock==true, it is a bug? I think we should BUG_ON for it, that can help us catch bug at the first time.> + if (had_lock) > + arg_flags = OCFS2_META_LOCK_GETBH; > + status = ocfs2_inode_lock_full(inode, &bh, 1, arg_flags); > if (status < 0) { > if (status != -ENOENT) > mlog_errno(status); > goto bail_unlock_rw; > } > - inode_locked = 1; > + if (!had_lock) { > + ocfs2_add_holder(lockres, &oh); > + inode_locked = 1; > + } > > if (size_change) { > status = inode_newsize_ok(inode, attr->ia_size); > @@ -1260,7 +1270,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > bail_commit: > ocfs2_commit_trans(osb, handle); > bail_unlock: > - if (status) { > + if (status && inode_locked) { > + ocfs2_remove_holder(lockres, &oh); > ocfs2_inode_unlock(inode, 1); > inode_locked = 0; > } > @@ -1278,8 +1289,10 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) > if (status < 0) > mlog_errno(status); > } > - if (inode_locked) > + if (inode_locked) { > + ocfs2_remove_holder(lockres, &oh); > ocfs2_inode_unlock(inode, 1); > + } > > brelse(bh); > return status; > @@ -1321,20 +1334,31 @@ int ocfs2_getattr(struct vfsmount *mnt, > int ocfs2_permission(struct inode *inode, int mask) > { > int ret; > + int has_locked; > + struct ocfs2_holder oh; > + struct ocfs2_lock_res *lockres; > > if (mask & MAY_NOT_BLOCK) > return -ECHILD; > > - ret = ocfs2_inode_lock(inode, NULL, 0); > - if (ret) { > - if (ret != -ENOENT) > - mlog_errno(ret); > - goto out; > + lockres = &OCFS2_I(inode)->ip_inode_lockres; > + has_locked = (ocfs2_is_locked_by_me(lockres) != NULL);The same thing as ocfs2_setattr. Thanks, Junxiao.> + if (!has_locked) { > + ret = ocfs2_inode_lock(inode, NULL, 0); > + if (ret) { > + if (ret != -ENOENT) > + mlog_errno(ret); > + goto out; > + } > + ocfs2_add_holder(lockres, &oh); > } > > ret = generic_permission(inode, mask); > > - ocfs2_inode_unlock(inode, 0); > + if (!has_locked) { > + ocfs2_remove_holder(lockres, &oh); > + ocfs2_inode_unlock(inode, 0); > + } > out: > return ret; > } >