thr3ads.net - Ocfs2 devel - [Ocfs2-devel] [PATCH 00/19 v4] Fix filesystem freezing deadlocks [Mar 2012]

If this information is useful, please help other people find it:
Share via:

Jan Kara

2012-Mar-28 23:43 UTC

[PATCH 04/19] btrfs: Push mnt_want_write() outside of i_mutex

When mnt_want_write() starts to handle freezing it will get a full lock
semantics requiring proper lock ordering. So push mnt_want_write() call
consistently outside of i_mutex.

CC: Chris Mason <chris.mason@oracle.com>
CC: linux-btrfs@vger.kernel.org
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/btrfs/ioctl.c |   23 +++++++++++------------
 1 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 03bb62a..c855e55 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -192,6 +192,10 @@ static int btrfs_ioctl_setflags(struct file *file, void
__user *arg)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
 	mutex_lock(&inode->i_mutex);
 
 	ip_oldflags = ip->flags;
@@ -206,10 +210,6 @@ static int btrfs_ioctl_setflags(struct file *file, void
__user *arg)
 		}
 	}
 
-	ret = mnt_want_write_file(file);
-	if (ret)
-		goto out_unlock;
-
 	if (flags & FS_SYNC_FL)
 		ip->flags |= BTRFS_INODE_SYNC;
 	else
@@ -271,9 +271,9 @@ static int btrfs_ioctl_setflags(struct file *file, void
__user *arg)
 		inode->i_flags = i_oldflags;
 	}
 
-	mnt_drop_write_file(file);
  out_unlock:
 	mutex_unlock(&inode->i_mutex);
+	mnt_drop_write_file(file);
 	return ret;
 }
 
@@ -624,6 +624,10 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	struct dentry *dentry;
 	int error;
 
+	error = mnt_want_write(parent->mnt);
+	if (error)
+		return error;
+
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
 
 	dentry = lookup_one_len(name, parent->dentry, namelen);
@@ -635,13 +639,9 @@ static noinline int btrfs_mksubvol(struct path *parent,
 	if (dentry->d_inode)
 		goto out_dput;
 
-	error = mnt_want_write(parent->mnt);
-	if (error)
-		goto out_dput;
-
 	error = btrfs_may_create(dir, dentry);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 
 	down_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
 
@@ -659,12 +659,11 @@ static noinline int btrfs_mksubvol(struct path *parent,
 		fsnotify_mkdir(dir, dentry);
 out_up_read:
 	up_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
-out_drop_write:
-	mnt_drop_write(parent->mnt);
 out_dput:
 	dput(dentry);
 out_unlock:
 	mutex_unlock(&dir->i_mutex);
+	mnt_drop_write(parent->mnt);
 	return error;
 }
 
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs"
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Jan Kara

2012-Mar-28 23:43 UTC

head link

[Ocfs2-devel] [PATCH 12/19] ocfs2: Convert to new freezing mechanism

Protect ocfs2_page_mkwrite() and ocfs2_file_aio_write() using the new
freeze protection. We also protect several ioctl entry points which
were missing the protection.

CC: Mark Fasheh <mfasheh at suse.com>
CC: Joel Becker <jlbec at evilplan.org>
CC: ocfs2-devel at oss.oracle.com
Signed-off-by: Jan Kara <jack at suse.cz>
---
 fs/ocfs2/file.c  |   11 +++++++++--
 fs/ocfs2/ioctl.c |   14 ++++++++++++--
 fs/ocfs2/mmap.c  |    2 ++
 3 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 061591a..9b1e3d4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1971,6 +1971,7 @@ int ocfs2_change_file_space(struct file *file, unsigned
int cmd,
 {
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int ret;
 
 	if ((cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64) &&
 	    !ocfs2_writes_unwritten_extents(osb))
@@ -1985,7 +1986,12 @@ int ocfs2_change_file_space(struct file *file, unsigned
int cmd,
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 
-	return __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0);
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+	ret = __ocfs2_change_file_space(file, inode, file->f_pos, cmd, sr, 0);
+	mnt_drop_write_file(file);
+	return ret;
 }
 
 static long ocfs2_fallocate(struct file *file, int mode, loff_t offset,
@@ -2261,7 +2267,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	if (iocb->ki_left == 0)
 		return 0;
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
 	appending = file->f_flags & O_APPEND ? 1 : 0;
 	direct_io = file->f_flags & O_DIRECT ? 1 : 0;
@@ -2434,6 +2440,7 @@ out_sems:
 		ocfs2_iocb_clear_sem_locked(iocb);
 
 	mutex_unlock(&inode->i_mutex);
+	sb_end_write(inode->i_sb);
 
 	if (written)
 		ret = written;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index a6fda3c..59de312 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -928,7 +928,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
 		if (get_user(new_clusters, (int __user *)arg))
 			return -EFAULT;
 
-		return ocfs2_group_extend(inode, new_clusters);
+		status = mnt_want_write_file(filp);
+		if (status)
+			return status;
+		status = ocfs2_group_extend(inode, new_clusters);
+		mnt_drop_write_file(filp);
+		return status;
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
 		if (!capable(CAP_SYS_RESOURCE))
@@ -937,7 +942,12 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
 		if (copy_from_user(&input, (int __user *) arg, sizeof(input)))
 			return -EFAULT;
 
-		return ocfs2_group_add(inode, &input);
+		status = mnt_want_write_file(filp);
+		if (status)
+			return status;
+		status = ocfs2_group_add(inode, &input);
+		mnt_drop_write_file(filp);
+		return status;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, (struct reflink_arguments *)arg,
 				   sizeof(args)))
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 9cd4108..d150372 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -136,6 +136,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
 	sigset_t oldset;
 	int ret;
 
+	sb_start_pagefault(inode->i_sb);
 	ocfs2_block_signals(&oldset);
 
 	/*
@@ -165,6 +166,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma,
struct vm_fault *vmf)
 
 out:
 	ocfs2_unblock_signals(&oldset);
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
-- 
1.7.1

Jan Kara

2012-Mar-28 23:43 UTC

head link

[PATCH 17/19] btrfs: Convert to new freezing mechanism

We convert btrfs_file_aio_write() to use new freeze check.  We also add proper
freeze protection to btrfs_page_mkwrite(). Checks in cleaner_kthread() and
transaction_kthread() can be safely removed since btrfs_freeze() will lock
the mutexes and thus block the threads (and they shouldn''t have
anything to
do anyway).

CC: linux-btrfs@vger.kernel.org
CC: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Jan Kara <jack@suse.cz>
---
 fs/btrfs/disk-io.c |    3 ---
 fs/btrfs/file.c    |    3 ++-
 fs/btrfs/inode.c   |    6 +++++-
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 811d9f9..fc0f74c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1586,8 +1586,6 @@ static int cleaner_kthread(void *arg)
 	struct btrfs_root *root = arg;
 
 	do {
-		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
-
 		if (!(root->fs_info->sb->s_flags & MS_RDONLY) &&
 		    mutex_trylock(&root->fs_info->cleaner_mutex)) {
 			btrfs_run_delayed_iputs(root);
@@ -1618,7 +1616,6 @@ static int transaction_kthread(void *arg)
 
 	do {
 		delay = HZ * 30;
-		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
 		spin_lock(&root->fs_info->trans_lock);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 859ba2d..1aac7ca 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1348,7 +1348,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 	ssize_t err = 0;
 	size_t count, ocount;
 
-	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+	sb_start_write(inode->i_sb);
 
 	mutex_lock(&inode->i_mutex);
 
@@ -1439,6 +1439,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 			num_written = err;
 	}
 out:
+	sb_end_write(inode->i_sb);
 	current->backing_dev_info = NULL;
 	return num_written ? num_written : err;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 32214fe..63c9006 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6405,6 +6405,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct
vm_fault *vmf)
 	u64 page_start;
 	u64 page_end;
 
+	sb_start_pagefault(inode->i_sb);
 	ret  = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE);
 	if (!ret) {
 		ret = btrfs_update_time(vma->vm_file);
@@ -6495,12 +6496,15 @@ again:
 	unlock_extent_cached(io_tree, page_start, page_end, &cached_state,
GFP_NOFS);
 
 out_unlock:
-	if (!ret)
+	if (!ret) {
+		sb_end_pagefault(inode->i_sb);
 		return VM_FAULT_LOCKED;
+	}
 	unlock_page(page);
 out:
 	btrfs_delalloc_release_space(inode, PAGE_CACHE_SIZE);
 out_noreserve:
+	sb_end_pagefault(inode->i_sb);
 	return ret;
 }
 
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs"
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Jan Kara

2012-Mar-28 23:44 UTC

head link

[Ocfs2-devel] [PATCH 02/19] fs: Push mnt_want_write() outside of i_mutex

Currently, mnt_want_write() is sometimes called with i_mutex held and sometimes
without it. This isn't really a problem because mnt_want_write() is a
non-blocking operation (essentially has a trylock semantics) but when the
function starts to handle also frozen filesystems, it will get a full lock
semantics and thus proper lock ordering has to be established. So move
all mnt_want_write() calls outside of i_mutex.

One non-trivial case needing conversion is kern_path_create() /
user_path_create() which didn't include mnt_want_write() but now needs to
because it acquires i_mutex.  Because there are virtual file systems which
don't bother with freeze / remount-ro protection we actually provide both
versions of the function - one which calls mnt_want_write() and one which does
not.

CC: ocfs2-devel at oss.oracle.com
CC: Mark Fasheh <mfasheh at suse.com>
CC: Joel Becker <jlbec at evilplan.org>
CC: "David S. Miller" <davem at davemloft.net>
BugLink: https://bugs.launchpad.net/bugs/897421
Tested-by: Kamal Mostafa <kamal at canonical.com>
Tested-by: Peter M. Petrakis <peter.petrakis at canonical.com>
Tested-by: Dann Frazier <dann.frazier at canonical.com>
Tested-by: Massimo Morana <massimo.morana at canonical.com>
Signed-off-by: Jan Kara <jack at suse.cz>
---
 fs/namei.c              |  115 +++++++++++++++++++++++++++--------------------
 fs/ocfs2/refcounttree.c |   10 +---
 include/linux/namei.h   |    2 +
 net/unix/af_unix.c      |   13 ++----
 4 files changed, 74 insertions(+), 66 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index a780ea5..575d3a4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2383,7 +2383,9 @@ struct file *do_file_open_root(struct dentry *dentry,
struct vfsmount *mnt,
 	return file;
 }
 
-struct dentry *kern_path_create(int dfd, const char *pathname, struct path
*path, int is_dir)
+static struct dentry *do_kern_path_create(int dfd, const char *pathname,
+					  struct path *path, int is_dir,
+					  int freeze_protect)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
 	struct nameidata nd;
@@ -2401,6 +2403,14 @@ struct dentry *kern_path_create(int dfd, const char
*pathname, struct path *path
 	nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
 	nd.intent.open.flags = O_EXCL;
 
+	if (freeze_protect) {
+		error = mnt_want_write(nd.path.mnt);
+		if (error) {
+			dentry = ERR_PTR(error);
+			goto out;
+		}
+	}
+
 	/*
 	 * Do the final lookup.
 	 */
@@ -2429,24 +2439,49 @@ eexist:
 	dentry = ERR_PTR(-EEXIST);
 fail:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	if (freeze_protect)
+		mnt_drop_write(nd.path.mnt);
 out:
 	path_put(&nd.path);
 	return dentry;
 }
+
+struct dentry *kern_path_create(int dfd, const char *pathname, struct path
*path, int is_dir)
+{
+	return do_kern_path_create(dfd, pathname, path, is_dir, 0);
+}
 EXPORT_SYMBOL(kern_path_create);
 
+struct dentry *kern_path_create_thawed(int dfd, const char *pathname, struct
path *path, int is_dir)
+{
+	return do_kern_path_create(dfd, pathname, path, is_dir, 1);
+}
+EXPORT_SYMBOL(kern_path_create_thawed);
+
 struct dentry *user_path_create(int dfd, const char __user *pathname, struct
path *path, int is_dir)
 {
 	char *tmp = getname(pathname);
 	struct dentry *res;
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	res = kern_path_create(dfd, tmp, path, is_dir);
+	res = do_kern_path_create(dfd, tmp, path, is_dir, 0);
 	putname(tmp);
 	return res;
 }
 EXPORT_SYMBOL(user_path_create);
 
+struct dentry *user_path_create_thawed(int dfd, const char __user *pathname,
struct path *path, int is_dir)
+{
+	char *tmp = getname(pathname);
+	struct dentry *res;
+	if (IS_ERR(tmp))
+		return ERR_CAST(tmp);
+	res = do_kern_path_create(dfd, tmp, path, is_dir, 1);
+	putname(tmp);
+	return res;
+}
+EXPORT_SYMBOL(user_path_create_thawed);
+
 int vfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t
dev)
 {
 	int error = may_create(dir, dentry);
@@ -2502,7 +2537,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *,
filename, umode_t, mode,
 	if (S_ISDIR(mode))
 		return -EPERM;
 
-	dentry = user_path_create(dfd, filename, &path, 0);
+	dentry = user_path_create_thawed(dfd, filename, &path, 0);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -2511,12 +2546,9 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *,
filename, umode_t, mode,
 	error = may_mknod(mode);
 	if (error)
 		goto out_dput;
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_mknod(&path, dentry, mode, dev);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 	switch (mode & S_IFMT) {
 		case 0: case S_IFREG:
 			error = vfs_create(path.dentry->d_inode,dentry,mode,NULL);
@@ -2529,11 +2561,10 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *,
filename, umode_t, mode,
 			error = vfs_mknod(path.dentry->d_inode,dentry,mode,0);
 			break;
 	}
-out_drop_write:
-	mnt_drop_write(path.mnt);
 out_dput:
 	dput(dentry);
 	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	mnt_drop_write(path.mnt);
 	path_put(&path);
 
 	return error;
@@ -2571,24 +2602,20 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *,
pathname, umode_t, mode)
 	struct path path;
 	int error;
 
-	dentry = user_path_create(dfd, pathname, &path, 1);
+	dentry = user_path_create_thawed(dfd, pathname, &path, 1);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
 	if (!IS_POSIXACL(path.dentry->d_inode))
 		mode &= ~current_umask();
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_mkdir(&path, dentry, mode);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 	error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
-out_drop_write:
-	mnt_drop_write(path.mnt);
 out_dput:
 	dput(dentry);
 	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	mnt_drop_write(path.mnt);
 	path_put(&path);
 	return error;
 }
@@ -2683,6 +2710,9 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	}
 
 	nd.flags &= ~LOOKUP_PARENT;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto exit1;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex,
I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
@@ -2693,19 +2723,15 @@ static long do_rmdir(int dfd, const char __user
*pathname)
 		error = -ENOENT;
 		goto exit3;
 	}
-	error = mnt_want_write(nd.path.mnt);
-	if (error)
-		goto exit3;
 	error = security_path_rmdir(&nd.path, dentry);
 	if (error)
-		goto exit4;
+		goto exit3;
 	error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
-exit4:
-	mnt_drop_write(nd.path.mnt);
 exit3:
 	dput(dentry);
 exit2:
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
 	putname(name);
@@ -2772,6 +2798,9 @@ static long do_unlinkat(int dfd, const char __user
*pathname)
 		goto exit1;
 
 	nd.flags &= ~LOOKUP_PARENT;
+	error = mnt_want_write(nd.path.mnt);
+	if (error)
+		goto exit1;
 
 	mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex,
I_MUTEX_PARENT);
 	dentry = lookup_hash(&nd);
@@ -2784,21 +2813,17 @@ static long do_unlinkat(int dfd, const char __user
*pathname)
 		if (!inode)
 			goto slashes;
 		ihold(inode);
-		error = mnt_want_write(nd.path.mnt);
-		if (error)
-			goto exit2;
 		error = security_path_unlink(&nd.path, dentry);
 		if (error)
-			goto exit3;
+			goto exit2;
 		error = vfs_unlink(nd.path.dentry->d_inode, dentry);
-exit3:
-		mnt_drop_write(nd.path.mnt);
-	exit2:
+exit2:
 		dput(dentry);
 	}
 	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
+	mnt_drop_write(nd.path.mnt);
 exit1:
 	path_put(&nd.path);
 	putname(name);
@@ -2858,23 +2883,19 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 	if (IS_ERR(from))
 		return PTR_ERR(from);
 
-	dentry = user_path_create(newdfd, newname, &path, 0);
+	dentry = user_path_create_thawed(newdfd, newname, &path, 0);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_putname;
 
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_symlink(&path, dentry, from);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 	error = vfs_symlink(path.dentry->d_inode, dentry, from);
-out_drop_write:
-	mnt_drop_write(path.mnt);
 out_dput:
 	dput(dentry);
 	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	mnt_drop_write(path.mnt);
 	path_put(&path);
 out_putname:
 	putname(from);
@@ -2964,7 +2985,7 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *,
oldname,
 	if (error)
 		return error;
 
-	new_dentry = user_path_create(newdfd, newname, &new_path, 0);
+	new_dentry = user_path_create_thawed(newdfd, newname, &new_path, 0);
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
 		goto out;
@@ -2972,18 +2993,14 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user
*, oldname,
 	error = -EXDEV;
 	if (old_path.mnt != new_path.mnt)
 		goto out_dput;
-	error = mnt_want_write(new_path.mnt);
-	if (error)
-		goto out_dput;
 	error = security_path_link(old_path.dentry, &new_path, new_dentry);
 	if (error)
-		goto out_drop_write;
+		goto out_dput;
 	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
-out_drop_write:
-	mnt_drop_write(new_path.mnt);
 out_dput:
 	dput(new_dentry);
 	mutex_unlock(&new_path.dentry->d_inode->i_mutex);
+	mnt_drop_write(new_path.mnt);
 	path_put(&new_path);
 out:
 	path_put(&old_path);
@@ -3174,6 +3191,10 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user
*, oldname,
 	if (newnd.last_type != LAST_NORM)
 		goto exit2;
 
+	error = mnt_want_write(oldnd.path.mnt);
+	if (error)
+		goto exit2;
+
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags |= LOOKUP_RENAME_TARGET;
@@ -3209,23 +3230,19 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user
*, oldname,
 	if (new_dentry == trap)
 		goto exit5;
 
-	error = mnt_want_write(oldnd.path.mnt);
-	if (error)
-		goto exit5;
 	error = security_path_rename(&oldnd.path, old_dentry,
 				     &newnd.path, new_dentry);
 	if (error)
-		goto exit6;
+		goto exit5;
 	error = vfs_rename(old_dir->d_inode, old_dentry,
 				   new_dir->d_inode, new_dentry);
-exit6:
-	mnt_drop_write(oldnd.path.mnt);
 exit5:
 	dput(new_dentry);
 exit4:
 	dput(old_dentry);
 exit3:
 	unlock_rename(new_dir, old_dir);
+	mnt_drop_write(oldnd.path.mnt);
 exit2:
 	path_put(&newnd.path);
 	putname(to);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index cf78233..a99b8e2 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4453,7 +4453,7 @@ int ocfs2_reflink_ioctl(struct inode *inode,
 		return error;
 	}
 
-	new_dentry = user_path_create(AT_FDCWD, newname, &new_path, 0);
+	new_dentry = user_path_create_thawed(AT_FDCWD, newname, &new_path, 0);
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry)) {
 		mlog_errno(error);
@@ -4466,19 +4466,13 @@ int ocfs2_reflink_ioctl(struct inode *inode,
 		goto out_dput;
 	}
 
-	error = mnt_want_write(new_path.mnt);
-	if (error) {
-		mlog_errno(error);
-		goto out_dput;
-	}
-
 	error = ocfs2_vfs_reflink(old_path.dentry,
 				  new_path.dentry->d_inode,
 				  new_dentry, preserve);
-	mnt_drop_write(new_path.mnt);
 out_dput:
 	dput(new_dentry);
 	mutex_unlock(&new_path.dentry->d_inode->i_mutex);
+	mnt_drop_write(new_path.mnt);
 	path_put(&new_path);
 out:
 	path_put(&old_path);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index ffc0213..432f6bb 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -77,7 +77,9 @@ extern int user_path_at_empty(int, const char __user *,
unsigned, struct path *,
 extern int kern_path(const char *, unsigned, struct path *);
 
 extern struct dentry *kern_path_create(int, const char *, struct path *, int);
+extern struct dentry *kern_path_create_thawed(int, const char *, struct path *,
int);
 extern struct dentry *user_path_create(int, const char __user *, struct path *,
int);
+extern struct dentry *user_path_create_thawed(int, const char __user *, struct
path *, int);
 extern int kern_path_parent(const char *, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct path *);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 85d3bb7..7888b09 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -856,7 +856,7 @@ static int unix_bind(struct socket *sock, struct sockaddr
*uaddr, int addr_len)
 		 * Get the parent directory, calculate the hash for last
 		 * component.
 		 */
-		dentry = kern_path_create(AT_FDCWD, sun_path, &path, 0);
+		dentry = kern_path_create_thawed(AT_FDCWD, sun_path, &path, 0);
 		err = PTR_ERR(dentry);
 		if (IS_ERR(dentry))
 			goto out_mknod_parent;
@@ -866,19 +866,13 @@ static int unix_bind(struct socket *sock, struct sockaddr
*uaddr, int addr_len)
 		 */
 		mode = S_IFSOCK |
 		       (SOCK_INODE(sock)->i_mode & ~current_umask());
-		err = mnt_want_write(path.mnt);
-		if (err)
-			goto out_mknod_dput;
 		err = security_path_mknod(&path, dentry, mode, 0);
 		if (err)
-			goto out_mknod_drop_write;
-		err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
-out_mknod_drop_write:
-		mnt_drop_write(path.mnt);
-		if (err)
 			goto out_mknod_dput;
+		err = vfs_mknod(path.dentry->d_inode, dentry, mode, 0);
 		mutex_unlock(&path.dentry->d_inode->i_mutex);
 		dput(path.dentry);
+		mnt_drop_write(path.mnt);
 		path.dentry = dentry;
 
 		addr->hash = UNIX_HASH_SIZE;
@@ -916,6 +910,7 @@ out:
 out_mknod_dput:
 	dput(dentry);
 	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	mnt_drop_write(path.mnt);
 	path_put(&path);
 out_mknod_parent:
 	if (err == -EEXIST)
-- 
1.7.1

Jan Kara

2012-Mar-28 23:44 UTC

head link

[Ocfs2-devel] [PATCH 00/19 v4] Fix filesystem freezing deadlocks

Hello,

  here is the fourth iteration of my patches to improve filesystem freezing.
Filesystem freezing is currently racy and thus we can end up with dirty data on
frozen filesystem (see changelog patch 06 for detailed race description). This
patch series aims at fixing this.

To be able to block all places where inodes get dirtied, I've moved
filesystem
freeze handling in mnt_want_write() / mnt_drop_write(). This however required
some code shuffling and changes to kern_path_create() (see patches 02-05). I
think the result is OK but opinions may differ ;). The advantage of this change
also is that all filesystems get freeze protection almost for free - even ext2
can handle freezing well now.

Another potential contention point might be patch 19. In that patch we make
freeze_super() refuse to freeze the filesystem when there are open but unlinked
files which may be impractical in some cases. The main reason for this is the
problem with handling of file deletion from fput() called with mmap_sem held
(e.g. from munmap(2)), and then there's the fact that we cannot really force
such filesystem into a consistent state... But if people think that freezing
with open but unlinked files should happen, then I have some possible
solutions in mind (maybe as a separate patchset since this is large enough).

I'm not able to hit any deadlocks, lockdep warnings, or dirty data on frozen
filesystem despite beating it with fsstress and bash-shared-mapping while
freezing and unfreezing for several hours (using ext4 and xfs) so I'm
reasonably confident this could finally be the right solution.

And for people wanting to test - this patchset is based on patch series
"Push file_update_time() into .page_mkwrite" so you'll need to
pull that one
in as well.

Changes since v3:
  * added third level of freezing for fs internal purposes - hooked some
    filesystems to use it (XFS, nilfs2)
  * removed racy i_size check from filemap_mkwrite()

Changes since v2:
  * completely rewritten
  * freezing is now blocked at VFS entry points
  * two stage freezing to handle both mmapped writes and other IO

The biggest changes since v1:
  * have two counters to provide safe state transitions for SB_FREEZE_WRITE
    and SB_FREEZE_TRANS states
  * use percpu counters instead of own percpu structure
  * added documentation fixes from the old fs freezing series
  * converted XFS to use SB_FREEZE_TRANS counter instead of its private
    m_active_trans counter

								Honza

CC: Alex Elder <elder at kernel.org>
CC: Anton Altaparmakov <anton at tuxera.com>
CC: Ben Myers <bpm at sgi.com>
CC: Chris Mason <chris.mason at oracle.com>
CC: cluster-devel at redhat.com
CC: "David S. Miller" <davem at davemloft.net>
CC: fuse-devel at lists.sourceforge.net
CC: "J. Bruce Fields" <bfields at fieldses.org>
CC: Joel Becker <jlbec at evilplan.org>
CC: KONISHI Ryusuke <konishi.ryusuke at lab.ntt.co.jp>
CC: linux-btrfs at vger.kernel.org
CC: linux-ext4 at vger.kernel.org
CC: linux-nfs at vger.kernel.org
CC: linux-nilfs at vger.kernel.org
CC: linux-ntfs-dev at lists.sourceforge.net
CC: Mark Fasheh <mfasheh at suse.com>
CC: Miklos Szeredi <miklos at szeredi.hu>
CC: ocfs2-devel at oss.oracle.com
CC: OGAWA Hirofumi <hirofumi at mail.parknet.co.jp>
CC: Steven Whitehouse <swhiteho at redhat.com>
CC: "Theodore Ts'o" <tytso at mit.edu>
CC: xfs at oss.sgi.com

Ocfs2 devel - Mar 2012 - [PATCH 00/19 v4] Fix filesystem freezing deadlocks

[PATCH 04/19] btrfs: Push mnt_want_write() outside of i_mutex

[Ocfs2-devel] [PATCH 12/19] ocfs2: Convert to new freezing mechanism

[PATCH 17/19] btrfs: Convert to new freezing mechanism

[Ocfs2-devel] [PATCH 02/19] fs: Push mnt_want_write() outside of i_mutex

[Ocfs2-devel] [PATCH 00/19 v4] Fix filesystem freezing deadlocks