Merge commit '9249e17fe094d853d1ef7475dd559a2cc7e23d42' into nfs-for-3.6
Resolve conflicts with the VFS atomic open and sget changes.
Conflicts:
fs/nfs/nfs4proc.c
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index e78956c..34c59f1 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -144,7 +144,7 @@
extern void v9fs_session_cancel(struct v9fs_session_info *v9ses);
extern void v9fs_session_begin_cancel(struct v9fs_session_info *v9ses);
extern struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nameidata);
+ unsigned int flags);
extern int v9fs_vfs_unlink(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rmdir(struct inode *i, struct dentry *d);
extern int v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c
index d529437..64600b5 100644
--- a/fs/9p/vfs_dentry.c
+++ b/fs/9p/vfs_dentry.c
@@ -100,13 +100,13 @@
}
}
-static int v9fs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct p9_fid *fid;
struct inode *inode;
struct v9fs_inode *v9inode;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 57ccb75..cbf9dbb 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -712,88 +712,34 @@
}
/**
- * v9fs_vfs_create - VFS hook to create files
+ * v9fs_vfs_create - VFS hook to create a regular file
+ *
+ * open(.., O_CREAT) is handled in v9fs_vfs_atomic_open(). This is only called
+ * for mknod(2).
+ *
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
* @mode: create permissions
- * @nd: path information
*
*/
static int
v9fs_vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- int err;
- u32 perm;
- int flags;
- struct file *filp;
- struct v9fs_inode *v9inode;
- struct v9fs_session_info *v9ses;
- struct p9_fid *fid, *inode_fid;
+ struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir);
+ u32 perm = unixmode2p9mode(v9ses, mode);
+ struct p9_fid *fid;
- err = 0;
- fid = NULL;
- v9ses = v9fs_inode2v9ses(dir);
- perm = unixmode2p9mode(v9ses, mode);
- if (nd)
- flags = nd->intent.open.flags;
- else
- flags = O_RDWR;
-
- fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
- v9fs_uflags2omode(flags,
- v9fs_proto_dotu(v9ses)));
- if (IS_ERR(fid)) {
- err = PTR_ERR(fid);
- fid = NULL;
- goto error;
- }
+ /* P9_OEXCL? */
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm, P9_ORDWR);
+ if (IS_ERR(fid))
+ return PTR_ERR(fid);
v9fs_invalidate_inode_attr(dir);
- /* if we are opening a file, assign the open fid to the file */
- if (nd) {
- v9inode = V9FS_I(dentry->d_inode);
- mutex_lock(&v9inode->v_mutex);
- if (v9ses->cache && !v9inode->writeback_fid &&
- ((flags & O_ACCMODE) != O_RDONLY)) {
- /*
- * clone a fid and add it to writeback_fid
- * we do it during open time instead of
- * page dirty time via write_begin/page_mkwrite
- * because we want write after unlink usecase
- * to work.
- */
- inode_fid = v9fs_writeback_fid(dentry);
- if (IS_ERR(inode_fid)) {
- err = PTR_ERR(inode_fid);
- mutex_unlock(&v9inode->v_mutex);
- goto error;
- }
- v9inode->writeback_fid = (void *) inode_fid;
- }
- mutex_unlock(&v9inode->v_mutex);
- filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
- if (IS_ERR(filp)) {
- err = PTR_ERR(filp);
- goto error;
- }
-
- filp->private_data = fid;
-#ifdef CONFIG_9P_FSCACHE
- if (v9ses->cache)
- v9fs_cache_inode_set_cookie(dentry->d_inode, filp);
-#endif
- } else
- p9_client_clunk(fid);
+ p9_client_clunk(fid);
return 0;
-
-error:
- if (fid)
- p9_client_clunk(fid);
-
- return err;
}
/**
@@ -839,7 +785,7 @@
*/
struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nameidata)
+ unsigned int flags)
{
struct dentry *res;
struct super_block *sb;
@@ -849,8 +795,8 @@
char *name;
int result = 0;
- p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p nameidata: %p\n",
- dir, dentry->d_name.name, dentry, nameidata);
+ p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%s) %p flags: %x\n",
+ dir, dentry->d_name.name, dentry, flags);
if (dentry->d_name.len > NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
@@ -910,6 +856,86 @@
return ERR_PTR(result);
}
+static int
+v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
+{
+ int err;
+ u32 perm;
+ struct v9fs_inode *v9inode;
+ struct v9fs_session_info *v9ses;
+ struct p9_fid *fid, *inode_fid;
+ struct dentry *res = NULL;
+
+ if (d_unhashed(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || dentry->d_inode)
+ return finish_no_open(file, res);
+
+ err = 0;
+ fid = NULL;
+ v9ses = v9fs_inode2v9ses(dir);
+ perm = unixmode2p9mode(v9ses, mode);
+ fid = v9fs_create(v9ses, dir, dentry, NULL, perm,
+ v9fs_uflags2omode(flags,
+ v9fs_proto_dotu(v9ses)));
+ if (IS_ERR(fid)) {
+ err = PTR_ERR(fid);
+ fid = NULL;
+ goto error;
+ }
+
+ v9fs_invalidate_inode_attr(dir);
+ v9inode = V9FS_I(dentry->d_inode);
+ mutex_lock(&v9inode->v_mutex);
+ if (v9ses->cache && !v9inode->writeback_fid &&
+ ((flags & O_ACCMODE) != O_RDONLY)) {
+ /*
+ * clone a fid and add it to writeback_fid
+ * we do it during open time instead of
+ * page dirty time via write_begin/page_mkwrite
+ * because we want write after unlink usecase
+ * to work.
+ */
+ inode_fid = v9fs_writeback_fid(dentry);
+ if (IS_ERR(inode_fid)) {
+ err = PTR_ERR(inode_fid);
+ mutex_unlock(&v9inode->v_mutex);
+ goto error;
+ }
+ v9inode->writeback_fid = (void *) inode_fid;
+ }
+ mutex_unlock(&v9inode->v_mutex);
+ err = finish_open(file, dentry, generic_file_open, opened);
+ if (err)
+ goto error;
+
+ file->private_data = fid;
+#ifdef CONFIG_9P_FSCACHE
+ if (v9ses->cache)
+ v9fs_cache_inode_set_cookie(dentry->d_inode, file);
+#endif
+
+ *opened |= FILE_CREATED;
+out:
+ dput(res);
+ return err;
+
+error:
+ if (fid)
+ p9_client_clunk(fid);
+ goto out;
+}
+
/**
* v9fs_vfs_unlink - VFS unlink hook to delete an inode
* @i: inode that is being unlinked
@@ -1488,6 +1514,7 @@
static const struct inode_operations v9fs_dir_inode_operations_dotu = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
.symlink = v9fs_vfs_symlink,
.link = v9fs_vfs_link,
.unlink = v9fs_vfs_unlink,
@@ -1502,6 +1529,7 @@
static const struct inode_operations v9fs_dir_inode_operations = {
.create = v9fs_vfs_create,
.lookup = v9fs_vfs_lookup,
+ .atomic_open = v9fs_vfs_atomic_open,
.unlink = v9fs_vfs_unlink,
.mkdir = v9fs_vfs_mkdir,
.rmdir = v9fs_vfs_rmdir,
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index e3dd2a1..4089554 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -230,20 +230,25 @@
* @dir: directory inode that is being created
* @dentry: dentry that is being deleted
* @mode: create permissions
- * @nd: path information
*
*/
static int
v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
- struct nameidata *nd)
+ bool excl)
+{
+ return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
+}
+
+static int
+v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t omode,
+ int *opened)
{
int err = 0;
gid_t gid;
- int flags;
umode_t mode;
char *name = NULL;
- struct file *filp;
struct p9_qid qid;
struct inode *inode;
struct p9_fid *fid = NULL;
@@ -251,18 +256,22 @@
struct p9_fid *dfid, *ofid, *inode_fid;
struct v9fs_session_info *v9ses;
struct posix_acl *pacl = NULL, *dacl = NULL;
+ struct dentry *res = NULL;
+
+ if (d_unhashed(dentry)) {
+ res = v9fs_vfs_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || dentry->d_inode)
+ return finish_no_open(file, res);
v9ses = v9fs_inode2v9ses(dir);
- if (nd)
- flags = nd->intent.open.flags;
- else {
- /*
- * create call without LOOKUP_OPEN is due
- * to mknod of regular files. So use mknod
- * operation.
- */
- return v9fs_vfs_mknod_dotl(dir, dentry, omode, 0);
- }
name = (char *) dentry->d_name.name;
p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
@@ -272,7 +281,7 @@
if (IS_ERR(dfid)) {
err = PTR_ERR(dfid);
p9_debug(P9_DEBUG_VFS, "fid lookup failed %d\n", err);
- return err;
+ goto out;
}
/* clone a fid to use for creation */
@@ -280,7 +289,7 @@
if (IS_ERR(ofid)) {
err = PTR_ERR(ofid);
p9_debug(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
- return err;
+ goto out;
}
gid = v9fs_get_fsgid_for_create(dir);
@@ -345,17 +354,18 @@
}
mutex_unlock(&v9inode->v_mutex);
/* Since we are opening a file, assign the open fid to the file */
- filp = lookup_instantiate_filp(nd, dentry, generic_file_open);
- if (IS_ERR(filp)) {
- err = PTR_ERR(filp);
+ err = finish_open(file, dentry, generic_file_open, opened);
+ if (err)
goto err_clunk_old_fid;
- }
- filp->private_data = ofid;
+ file->private_data = ofid;
#ifdef CONFIG_9P_FSCACHE
if (v9ses->cache)
- v9fs_cache_inode_set_cookie(inode, filp);
+ v9fs_cache_inode_set_cookie(inode, file);
#endif
- return 0;
+ *opened |= FILE_CREATED;
+out:
+ dput(res);
+ return err;
error:
if (fid)
@@ -364,7 +374,7 @@
if (ofid)
p9_client_clunk(ofid);
v9fs_set_create_acl(NULL, &dacl, &pacl);
- return err;
+ goto out;
}
/**
@@ -982,6 +992,7 @@
const struct inode_operations v9fs_dir_inode_operations_dotl = {
.create = v9fs_vfs_create_dotl,
+ .atomic_open = v9fs_vfs_atomic_open_dotl,
.lookup = v9fs_vfs_lookup,
.link = v9fs_vfs_link_dotl,
.symlink = v9fs_vfs_symlink_dotl,
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 8c92a9ba..137d503 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -89,7 +89,7 @@
if (v9ses->cache)
sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_CACHE_SIZE;
- sb->s_flags = flags | MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
+ sb->s_flags |= MS_ACTIVE | MS_DIRSYNC | MS_NOATIME;
if (!v9ses->cache)
sb->s_flags |= MS_SYNCHRONOUS;
@@ -137,7 +137,7 @@
goto close_session;
}
- sb = sget(fs_type, NULL, v9fs_set_super, v9ses);
+ sb = sget(fs_type, NULL, v9fs_set_super, flags, v9ses);
if (IS_ERR(sb)) {
retval = PTR_ERR(sb);
goto clunk_fid;
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 3d83075a..b3be2e7 100644
--- a/fs/adfs/dir.c
+++ b/fs/adfs/dir.c
@@ -266,7 +266,7 @@
};
static struct dentry *
-adfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+adfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode = NULL;
struct object_info obj;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 06fdcc9..bdaec92 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -246,7 +246,6 @@
static void adfs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(adfs_inode_cachep, ADFS_I(inode));
}
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 1fceb32..6e21641 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -3,6 +3,7 @@
#include <linux/buffer_head.h>
#include <linux/amigaffs.h>
#include <linux/mutex.h>
+#include <linux/workqueue.h>
/* AmigaOS allows file names with up to 30 characters length.
* Names longer than that will be silently truncated. If you
@@ -100,6 +101,10 @@
char *s_prefix; /* Prefix for volumes and assigns. */
char s_volume[32]; /* Volume prefix for absolute symlinks. */
spinlock_t symlink_lock; /* protects the previous two */
+ struct super_block *sb; /* the VFS superblock object */
+ int work_queued; /* non-zero delayed work is queued */
+ struct delayed_work sb_work; /* superblock flush delayed work */
+ spinlock_t work_lock; /* protects sb_work and work_queued */
};
#define SF_INTL 0x0001 /* International filesystem. */
@@ -120,6 +125,8 @@
return sb->s_fs_info;
}
+void affs_mark_sb_dirty(struct super_block *sb);
+
/* amigaffs.c */
extern int affs_insert_hash(struct inode *inode, struct buffer_head *bh);
@@ -146,9 +153,9 @@
/* namei.c */
extern int affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len);
-extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *);
+extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
extern int affs_unlink(struct inode *dir, struct dentry *dentry);
-extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *);
+extern int affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool);
extern int affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
extern int affs_rmdir(struct inode *dir, struct dentry *dentry);
extern int affs_link(struct dentry *olddentry, struct inode *dir,
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 52a6407..eb82ee5 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -122,22 +122,16 @@
}
static void
-affs_fix_dcache(struct dentry *dentry, u32 entry_ino)
+affs_fix_dcache(struct inode *inode, u32 entry_ino)
{
- struct inode *inode = dentry->d_inode;
- void *data = dentry->d_fsdata;
- struct list_head *head, *next;
-
+ struct dentry *dentry;
+ struct hlist_node *p;
spin_lock(&inode->i_lock);
- head = &inode->i_dentry;
- next = head->next;
- while (next != head) {
- dentry = list_entry(next, struct dentry, d_alias);
+ hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
if (entry_ino == (u32)(long)dentry->d_fsdata) {
- dentry->d_fsdata = data;
+ dentry->d_fsdata = (void *)inode->i_ino;
break;
}
- next = next->next;
}
spin_unlock(&inode->i_lock);
}
@@ -177,7 +171,11 @@
}
affs_lock_dir(dir);
- affs_fix_dcache(dentry, link_ino);
+ /*
+ * if there's a dentry for that block, make it
+ * refer to inode itself.
+ */
+ affs_fix_dcache(inode, link_ino);
retval = affs_remove_hash(dir, link_bh);
if (retval) {
affs_unlock_dir(dir);
diff --git a/fs/affs/bitmap.c b/fs/affs/bitmap.c
index 3e26271..6e0be43 100644
--- a/fs/affs/bitmap.c
+++ b/fs/affs/bitmap.c
@@ -103,7 +103,7 @@
*(__be32 *)bh->b_data = cpu_to_be32(tmp - mask);
mark_buffer_dirty(bh);
- sb->s_dirt = 1;
+ affs_mark_sb_dirty(sb);
bm->bm_free++;
mutex_unlock(&sbi->s_bmlock);
@@ -248,7 +248,7 @@
*(__be32 *)bh->b_data = cpu_to_be32(tmp + mask);
mark_buffer_dirty(bh);
- sb->s_dirt = 1;
+ affs_mark_sb_dirty(sb);
mutex_unlock(&sbi->s_bmlock);
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 4780694..ff65884 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -211,7 +211,7 @@
}
struct dentry *
-affs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct buffer_head *bh;
@@ -255,7 +255,7 @@
}
int
-affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 0782653..c70f1e5 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -17,6 +17,7 @@
#include <linux/magic.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/writeback.h>
#include "affs.h"
extern struct timezone sys_tz;
@@ -25,15 +26,17 @@
static int affs_remount (struct super_block *sb, int *flags, char *data);
static void
-affs_commit_super(struct super_block *sb, int wait, int clean)
+affs_commit_super(struct super_block *sb, int wait)
{
struct affs_sb_info *sbi = AFFS_SB(sb);
struct buffer_head *bh = sbi->s_root_bh;
struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
- tail->bm_flag = cpu_to_be32(clean);
+ lock_buffer(bh);
secs_to_datestamp(get_seconds(), &tail->disk_change);
affs_fix_checksum(sb, bh);
+ unlock_buffer(bh);
+
mark_buffer_dirty(bh);
if (wait)
sync_dirty_buffer(bh);
@@ -45,9 +48,7 @@
struct affs_sb_info *sbi = AFFS_SB(sb);
pr_debug("AFFS: put_super()\n");
- if (!(sb->s_flags & MS_RDONLY) && sb->s_dirt)
- affs_commit_super(sb, 1, 1);
-
+ cancel_delayed_work_sync(&sbi->sb_work);
kfree(sbi->s_prefix);
affs_free_bitmap(sb);
affs_brelse(sbi->s_root_bh);
@@ -55,28 +56,45 @@
sb->s_fs_info = NULL;
}
-static void
-affs_write_super(struct super_block *sb)
-{
- lock_super(sb);
- if (!(sb->s_flags & MS_RDONLY))
- affs_commit_super(sb, 1, 2);
- sb->s_dirt = 0;
- unlock_super(sb);
-
- pr_debug("AFFS: write_super() at %lu, clean=2\n", get_seconds());
-}
-
static int
affs_sync_fs(struct super_block *sb, int wait)
{
- lock_super(sb);
- affs_commit_super(sb, wait, 2);
- sb->s_dirt = 0;
- unlock_super(sb);
+ affs_commit_super(sb, wait);
return 0;
}
+static void flush_superblock(struct work_struct *work)
+{
+ struct affs_sb_info *sbi;
+ struct super_block *sb;
+
+ sbi = container_of(work, struct affs_sb_info, sb_work.work);
+ sb = sbi->sb;
+
+ spin_lock(&sbi->work_lock);
+ sbi->work_queued = 0;
+ spin_unlock(&sbi->work_lock);
+
+ affs_commit_super(sb, 1);
+}
+
+void affs_mark_sb_dirty(struct super_block *sb)
+{
+ struct affs_sb_info *sbi = AFFS_SB(sb);
+ unsigned long delay;
+
+ if (sb->s_flags & MS_RDONLY)
+ return;
+
+ spin_lock(&sbi->work_lock);
+ if (!sbi->work_queued) {
+ delay = msecs_to_jiffies(dirty_writeback_interval * 10);
+ queue_delayed_work(system_long_wq, &sbi->sb_work, delay);
+ sbi->work_queued = 1;
+ }
+ spin_unlock(&sbi->work_lock);
+}
+
static struct kmem_cache * affs_inode_cachep;
static struct inode *affs_alloc_inode(struct super_block *sb)
@@ -138,7 +156,6 @@
.write_inode = affs_write_inode,
.evict_inode = affs_evict_inode,
.put_super = affs_put_super,
- .write_super = affs_write_super,
.sync_fs = affs_sync_fs,
.statfs = affs_statfs,
.remount_fs = affs_remount,
@@ -305,8 +322,11 @@
return -ENOMEM;
sb->s_fs_info = sbi;
+ sbi->sb = sb;
mutex_init(&sbi->s_bmlock);
spin_lock_init(&sbi->symlink_lock);
+ spin_lock_init(&sbi->work_lock);
+ INIT_DELAYED_WORK(&sbi->sb_work, flush_superblock);
if (!parse_options(data,&uid,&gid,&i,&reserved,&root_block,
&blocksize,&sbi->s_prefix,
@@ -531,6 +551,7 @@
return -EINVAL;
}
+ flush_delayed_work_sync(&sbi->sb_work);
replace_mount_options(sb, new_opts);
sbi->s_flags = mount_flags;
@@ -549,10 +570,9 @@
if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
return 0;
- if (*flags & MS_RDONLY) {
- affs_write_super(sb);
+ if (*flags & MS_RDONLY)
affs_free_bitmap(sb);
- } else
+ else
res = affs_init_bitmap(sb, flags);
return res;
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index e22dc4b..db47790 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -20,16 +20,16 @@
#include "internal.h"
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
static int afs_dir_open(struct inode *inode, struct file *file);
static int afs_readdir(struct file *file, void *dirent, filldir_t filldir);
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd);
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags);
static int afs_d_delete(const struct dentry *dentry);
static void afs_d_release(struct dentry *dentry);
static int afs_lookup_filldir(void *_cookie, const char *name, int nlen,
loff_t fpos, u64 ino, unsigned dtype);
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd);
+ bool excl);
static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode);
static int afs_rmdir(struct inode *dir, struct dentry *dentry);
static int afs_unlink(struct inode *dir, struct dentry *dentry);
@@ -516,7 +516,7 @@
* look up an entry in a directory
*/
static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct afs_vnode *vnode;
struct afs_fid fid;
@@ -598,7 +598,7 @@
* - NOTE! the hit can be a negative hit too, so we can't assume we have an
* inode
*/
-static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int afs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct afs_vnode *vnode, *dir;
struct afs_fid uninitialized_var(fid);
@@ -607,7 +607,7 @@
void *dir_version;
int ret;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
vnode = AFS_FS_I(dentry->d_inode);
@@ -949,7 +949,7 @@
* create a regular file on an AFS filesystem
*/
static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct afs_file_status status;
struct afs_callback cb;
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 298cf89..9682c33 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -22,7 +22,7 @@
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
static int afs_mntpt_open(struct inode *inode, struct file *file);
static void afs_mntpt_expiry_timed_out(struct work_struct *work);
@@ -104,7 +104,7 @@
*/
static struct dentry *afs_mntpt_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
_enter("%p,%p{%p{%s},%s}",
dir,
diff --git a/fs/afs/super.c b/fs/afs/super.c
index f02b31e..df8c604 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -395,7 +395,7 @@
as->volume = vol;
/* allocate a deviceless superblock */
- sb = sget(fs_type, afs_test_super, afs_set_super, as);
+ sb = sget(fs_type, afs_test_super, afs_set_super, flags, as);
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
afs_put_volume(vol);
@@ -406,7 +406,6 @@
if (!sb->s_root) {
/* initial superblock/root creation */
_debug("create");
- sb->s_flags = flags;
ret = afs_fill_super(sb, ¶ms);
if (ret < 0) {
deactivate_locked_super(sb);
diff --git a/fs/attr.c b/fs/attr.c
index 0da9095..29e38a1 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -171,6 +171,8 @@
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
+ WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
+
if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) {
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
return -EPERM;
@@ -250,5 +252,4 @@
return error;
}
-
EXPORT_SYMBOL(notify_change);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 75e5f1c..e7396cf 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -32,7 +32,7 @@
static long autofs4_root_compat_ioctl(struct file *,unsigned int,unsigned long);
#endif
static int autofs4_dir_open(struct inode *inode, struct file *file);
-static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
+static struct dentry *autofs4_lookup(struct inode *,struct dentry *, unsigned int);
static struct vfsmount *autofs4_d_automount(struct path *);
static int autofs4_d_manage(struct dentry *, bool);
static void autofs4_dentry_release(struct dentry *);
@@ -458,7 +458,7 @@
}
/* Lookups in the root directory */
-static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct autofs_sb_info *sbi;
struct autofs_info *ino;
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 1b35d6b..b1342ff 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -173,13 +173,13 @@
};
static int bad_inode_create (struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
return -EIO;
}
static struct dentry *bad_inode_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
return ERR_PTR(-EIO);
}
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index e18da23..cf7f3c6 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -34,7 +34,7 @@
static int befs_get_block(struct inode *, sector_t, struct buffer_head *, int);
static int befs_readpage(struct file *file, struct page *page);
static sector_t befs_bmap(struct address_space *mapping, sector_t block);
-static struct dentry *befs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *befs_lookup(struct inode *, struct dentry *, unsigned int);
static struct inode *befs_iget(struct super_block *, unsigned long);
static struct inode *befs_alloc_inode(struct super_block *sb);
static void befs_destroy_inode(struct inode *inode);
@@ -159,7 +159,7 @@
}
static struct dentry *
-befs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+befs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode = NULL;
struct super_block *sb = dir->i_sb;
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index d12c796..2785ef9 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@ -85,7 +85,7 @@
extern void dump_imap(const char *, struct super_block *);
static int bfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int err;
struct inode *inode;
@@ -133,7 +133,7 @@
}
static struct dentry *bfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct buffer_head *bh;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 7301cdb..a383c18 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -301,10 +301,14 @@
goto out;
eb = path->nodes[level];
- if (!eb) {
- WARN_ON(1);
- ret = 1;
- goto out;
+ while (!eb) {
+ if (!level) {
+ WARN_ON(1);
+ ret = 1;
+ goto out;
+ }
+ level--;
+ eb = path->nodes[level];
}
ret = add_all_parents(root, path, parents, level, &ref->key_for_search,
@@ -835,6 +839,7 @@
}
ret = __add_delayed_refs(head, delayed_ref_seq,
&prefs_delayed);
+ mutex_unlock(&head->mutex);
if (ret) {
spin_unlock(&delayed_refs->lock);
goto out;
@@ -928,8 +933,6 @@
}
out:
- if (head)
- mutex_unlock(&head->mutex);
btrfs_free_path(path);
while (!list_empty(&prefs)) {
ref = list_first_entry(&prefs, struct __prelim_ref, list);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 15cbc2b..8206b39 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1024,11 +1024,18 @@
if (!looped && !tm)
return 0;
/*
- * we must have key remove operations in the log before the
- * replace operation.
+ * if there are no tree operation for the oldest root, we simply
+ * return it. this should only happen if that (old) root is at
+ * level 0.
*/
- BUG_ON(!tm);
+ if (!tm)
+ break;
+ /*
+ * if there's an operation that's not a root replacement, we
+ * found the oldest version of our root. normally, we'll find a
+ * MOD_LOG_KEY_REMOVE_WHILE_FREEING operation here.
+ */
if (tm->op != MOD_LOG_ROOT_REPLACE)
break;
@@ -1087,11 +1094,7 @@
tm->generation);
break;
case MOD_LOG_KEY_ADD:
- if (tm->slot != n - 1) {
- o_dst = btrfs_node_key_ptr_offset(tm->slot);
- o_src = btrfs_node_key_ptr_offset(tm->slot + 1);
- memmove_extent_buffer(eb, o_dst, o_src, p_size);
- }
+ /* if a move operation is needed it's in the log */
n--;
break;
case MOD_LOG_MOVE_KEYS:
@@ -1192,16 +1195,8 @@
}
tm = tree_mod_log_search(root->fs_info, logical, time_seq);
- /*
- * there was an item in the log when __tree_mod_log_oldest_root
- * returned. this one must not go away, because the time_seq passed to
- * us must be blocking its removal.
- */
- BUG_ON(!tm);
-
if (old_root)
- eb = alloc_dummy_extent_buffer(tm->index << PAGE_CACHE_SHIFT,
- root->nodesize);
+ eb = alloc_dummy_extent_buffer(logical, root->nodesize);
else
eb = btrfs_clone_extent_buffer(root->node);
btrfs_tree_read_unlock(root->node);
@@ -1216,7 +1211,10 @@
btrfs_set_header_level(eb, old_root->level);
btrfs_set_header_generation(eb, old_generation);
}
- __tree_mod_log_rewind(eb, time_seq, tm);
+ if (tm)
+ __tree_mod_log_rewind(eb, time_seq, tm);
+ else
+ WARN_ON(btrfs_header_level(eb) != 0);
extent_buffer_get(eb);
return eb;
@@ -2995,7 +2993,7 @@
static void insert_ptr(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_disk_key *key, u64 bytenr,
- int slot, int level, int tree_mod_log)
+ int slot, int level)
{
struct extent_buffer *lower;
int nritems;
@@ -3008,7 +3006,7 @@
BUG_ON(slot > nritems);
BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(root));
if (slot != nritems) {
- if (tree_mod_log && level)
+ if (level)
tree_mod_log_eb_move(root->fs_info, lower, slot + 1,
slot, nritems - slot);
memmove_extent_buffer(lower,
@@ -3016,7 +3014,7 @@
btrfs_node_key_ptr_offset(slot),
(nritems - slot) * sizeof(struct btrfs_key_ptr));
}
- if (tree_mod_log && level) {
+ if (level) {
ret = tree_mod_log_insert_key(root->fs_info, lower, slot,
MOD_LOG_KEY_ADD);
BUG_ON(ret < 0);
@@ -3104,7 +3102,7 @@
btrfs_mark_buffer_dirty(split);
insert_ptr(trans, root, path, &disk_key, split->start,
- path->slots[level + 1] + 1, level + 1, 1);
+ path->slots[level + 1] + 1, level + 1);
if (path->slots[level] >= mid) {
path->slots[level] -= mid;
@@ -3641,7 +3639,7 @@
btrfs_set_header_nritems(l, mid);
btrfs_item_key(right, &disk_key, 0);
insert_ptr(trans, root, path, &disk_key, right->start,
- path->slots[1] + 1, 1, 0);
+ path->slots[1] + 1, 1);
btrfs_mark_buffer_dirty(right);
btrfs_mark_buffer_dirty(l);
@@ -3848,7 +3846,7 @@
if (mid <= slot) {
btrfs_set_header_nritems(right, 0);
insert_ptr(trans, root, path, &disk_key, right->start,
- path->slots[1] + 1, 1, 0);
+ path->slots[1] + 1, 1);
btrfs_tree_unlock(path->nodes[0]);
free_extent_buffer(path->nodes[0]);
path->nodes[0] = right;
@@ -3857,7 +3855,7 @@
} else {
btrfs_set_header_nritems(right, 0);
insert_ptr(trans, root, path, &disk_key, right->start,
- path->slots[1], 1, 0);
+ path->slots[1], 1);
btrfs_tree_unlock(path->nodes[0]);
free_extent_buffer(path->nodes[0]);
path->nodes[0] = right;
@@ -5121,6 +5119,18 @@
if (!path->skip_locking) {
ret = btrfs_try_tree_read_lock(next);
+ if (!ret && time_seq) {
+ /*
+ * If we don't get the lock, we may be racing
+ * with push_leaf_left, holding that lock while
+ * itself waiting for the leaf we've currently
+ * locked. To solve this situation, we give up
+ * on our lock and cycle.
+ */
+ btrfs_release_path(path);
+ cond_resched();
+ goto again;
+ }
if (!ret) {
btrfs_set_path_blocking(path);
btrfs_tree_read_lock(next);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7b845ff..2936ca4 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2354,12 +2354,17 @@
BTRFS_CSUM_TREE_OBJECTID, csum_root);
if (ret)
goto recovery_tree_root;
-
csum_root->track_dirty = 1;
fs_info->generation = generation;
fs_info->last_trans_committed = generation;
+ ret = btrfs_recover_balance(fs_info);
+ if (ret) {
+ printk(KERN_WARNING "btrfs: failed to recover balance\n");
+ goto fail_block_groups;
+ }
+
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n",
@@ -2485,20 +2490,23 @@
goto fail_trans_kthread;
}
- if (!(sb->s_flags & MS_RDONLY)) {
- down_read(&fs_info->cleanup_work_sem);
- err = btrfs_orphan_cleanup(fs_info->fs_root);
- if (!err)
- err = btrfs_orphan_cleanup(fs_info->tree_root);
+ if (sb->s_flags & MS_RDONLY)
+ return 0;
+
+ down_read(&fs_info->cleanup_work_sem);
+ if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) ||
+ (ret = btrfs_orphan_cleanup(fs_info->tree_root))) {
up_read(&fs_info->cleanup_work_sem);
+ close_ctree(tree_root);
+ return ret;
+ }
+ up_read(&fs_info->cleanup_work_sem);
- if (!err)
- err = btrfs_recover_balance(fs_info->tree_root);
-
- if (err) {
- close_ctree(tree_root);
- return err;
- }
+ ret = btrfs_resume_balance_async(fs_info);
+ if (ret) {
+ printk(KERN_WARNING "btrfs: failed to resume balance\n");
+ close_ctree(tree_root);
+ return ret;
}
return 0;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4b5a1e1..6e1d367 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2347,12 +2347,10 @@
return count;
}
-
static void wait_for_more_refs(struct btrfs_delayed_ref_root *delayed_refs,
- unsigned long num_refs)
+ unsigned long num_refs,
+ struct list_head *first_seq)
{
- struct list_head *first_seq = delayed_refs->seq_head.next;
-
spin_unlock(&delayed_refs->lock);
pr_debug("waiting for more refs (num %ld, first %p)\n",
num_refs, first_seq);
@@ -2381,6 +2379,7 @@
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_delayed_ref_node *ref;
struct list_head cluster;
+ struct list_head *first_seq = NULL;
int ret;
u64 delayed_start;
int run_all = count == (unsigned long)-1;
@@ -2436,8 +2435,10 @@
*/
consider_waiting = 1;
num_refs = delayed_refs->num_entries;
+ first_seq = root->fs_info->tree_mod_seq_list.next;
} else {
- wait_for_more_refs(delayed_refs, num_refs);
+ wait_for_more_refs(delayed_refs,
+ num_refs, first_seq);
/*
* after waiting, things have changed. we
* dropped the lock and someone else might have
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index aaa12c1..01c21b6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3324,6 +3324,7 @@
writepage_t writepage, void *data,
void (*flush_fn)(void *))
{
+ struct inode *inode = mapping->host;
int ret = 0;
int done = 0;
int nr_to_write_done = 0;
@@ -3334,6 +3335,18 @@
int scanned = 0;
int tag;
+ /*
+ * We have to hold onto the inode so that ordered extents can do their
+ * work when the IO finishes. The alternative to this is failing to add
+ * an ordered extent if the igrab() fails there and that is a huge pain
+ * to deal with, so instead just hold onto the inode throughout the
+ * writepages operation. If it fails here we are freeing up the inode
+ * anyway and we'd rather not waste our time writing out stuff that is
+ * going to be truncated anyway.
+ */
+ if (!igrab(inode))
+ return 0;
+
pagevec_init(&pvec, 0);
if (wbc->range_cyclic) {
index = mapping->writeback_index; /* Start from prev offset */
@@ -3428,6 +3441,7 @@
index = 0;
goto retry;
}
+ btrfs_add_delayed_iput(inode);
return ret;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 70dc8ca..9aa01ec 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1334,7 +1334,6 @@
loff_t *ppos, size_t count, size_t ocount)
{
struct file *file = iocb->ki_filp;
- struct inode *inode = fdentry(file)->d_inode;
struct iov_iter i;
ssize_t written;
ssize_t written_buffered;
@@ -1344,18 +1343,6 @@
written = generic_file_direct_write(iocb, iov, &nr_segs, pos, ppos,
count, ocount);
- /*
- * the generic O_DIRECT will update in-memory i_size after the
- * DIOs are done. But our endio handlers that update the on
- * disk i_size never update past the in memory i_size. So we
- * need one more update here to catch any additions to the
- * file
- */
- if (inode->i_size != BTRFS_I(inode)->disk_i_size) {
- btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
- mark_inode_dirty(inode);
- }
-
if (written < 0 || written == count)
return written;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 81296c5..6c4e2ba 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1543,29 +1543,26 @@
end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1;
/*
- * XXX - this can go away after a few releases.
- *
- * since the only user of btrfs_remove_free_space is the tree logging
- * stuff, and the only way to test that is under crash conditions, we
- * want to have this debug stuff here just in case somethings not
- * working. Search the bitmap for the space we are trying to use to
- * make sure its actually there. If its not there then we need to stop
- * because something has gone wrong.
+ * We need to search for bits in this bitmap. We could only cover some
+ * of the extent in this bitmap thanks to how we add space, so we need
+ * to search for as much as it as we can and clear that amount, and then
+ * go searching for the next bit.
*/
search_start = *offset;
- search_bytes = *bytes;
+ search_bytes = ctl->unit;
search_bytes = min(search_bytes, end - search_start + 1);
ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes);
BUG_ON(ret < 0 || search_start != *offset);
- if (*offset > bitmap_info->offset && *offset + *bytes > end) {
- bitmap_clear_bits(ctl, bitmap_info, *offset, end - *offset + 1);
- *bytes -= end - *offset + 1;
- *offset = end + 1;
- } else if (*offset >= bitmap_info->offset && *offset + *bytes <= end) {
- bitmap_clear_bits(ctl, bitmap_info, *offset, *bytes);
- *bytes = 0;
- }
+ /* We may have found more bits than what we need */
+ search_bytes = min(search_bytes, *bytes);
+
+ /* Cannot clear past the end of the bitmap */
+ search_bytes = min(search_bytes, end - search_start + 1);
+
+ bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes);
+ *offset += search_bytes;
+ *bytes -= search_bytes;
if (*bytes) {
struct rb_node *next = rb_next(&bitmap_info->offset_index);
@@ -1596,7 +1593,7 @@
* everything over again.
*/
search_start = *offset;
- search_bytes = *bytes;
+ search_bytes = ctl->unit;
ret = search_bitmap(ctl, bitmap_info, &search_start,
&search_bytes);
if (ret < 0 || search_start != *offset)
@@ -1879,12 +1876,14 @@
{
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
struct btrfs_free_space *info;
- struct btrfs_free_space *next_info = NULL;
int ret = 0;
spin_lock(&ctl->tree_lock);
again:
+ if (!bytes)
+ goto out_lock;
+
info = tree_search_offset(ctl, offset, 0, 0);
if (!info) {
/*
@@ -1905,88 +1904,48 @@
}
}
- if (info->bytes < bytes && rb_next(&info->offset_index)) {
- u64 end;
- next_info = rb_entry(rb_next(&info->offset_index),
- struct btrfs_free_space,
- offset_index);
-
- if (next_info->bitmap)
- end = next_info->offset +
- BITS_PER_BITMAP * ctl->unit - 1;
- else
- end = next_info->offset + next_info->bytes;
-
- if (next_info->bytes < bytes ||
- next_info->offset > offset || offset > end) {
- printk(KERN_CRIT "Found free space at %llu, size %llu,"
- " trying to use %llu\n",
- (unsigned long long)info->offset,
- (unsigned long long)info->bytes,
- (unsigned long long)bytes);
- WARN_ON(1);
- ret = -EINVAL;
- goto out_lock;
- }
-
- info = next_info;
- }
-
- if (info->bytes == bytes) {
+ if (!info->bitmap) {
unlink_free_space(ctl, info);
- if (info->bitmap) {
- kfree(info->bitmap);
- ctl->total_bitmaps--;
- }
- kmem_cache_free(btrfs_free_space_cachep, info);
- ret = 0;
- goto out_lock;
- }
+ if (offset == info->offset) {
+ u64 to_free = min(bytes, info->bytes);
- if (!info->bitmap && info->offset == offset) {
- unlink_free_space(ctl, info);
- info->offset += bytes;
- info->bytes -= bytes;
- ret = link_free_space(ctl, info);
- WARN_ON(ret);
- goto out_lock;
- }
+ info->bytes -= to_free;
+ info->offset += to_free;
+ if (info->bytes) {
+ ret = link_free_space(ctl, info);
+ WARN_ON(ret);
+ } else {
+ kmem_cache_free(btrfs_free_space_cachep, info);
+ }
- if (!info->bitmap && info->offset <= offset &&
- info->offset + info->bytes >= offset + bytes) {
- u64 old_start = info->offset;
- /*
- * we're freeing space in the middle of the info,
- * this can happen during tree log replay
- *
- * first unlink the old info and then
- * insert it again after the hole we're creating
- */
- unlink_free_space(ctl, info);
- if (offset + bytes < info->offset + info->bytes) {
- u64 old_end = info->offset + info->bytes;
+ offset += to_free;
+ bytes -= to_free;
+ goto again;
+ } else {
+ u64 old_end = info->bytes + info->offset;
- info->offset = offset + bytes;
- info->bytes = old_end - info->offset;
+ info->bytes = offset - info->offset;
ret = link_free_space(ctl, info);
WARN_ON(ret);
if (ret)
goto out_lock;
- } else {
- /* the hole we're creating ends at the end
- * of the info struct, just free the info
- */
- kmem_cache_free(btrfs_free_space_cachep, info);
- }
- spin_unlock(&ctl->tree_lock);
- /* step two, insert a new info struct to cover
- * anything before the hole
- */
- ret = btrfs_add_free_space(block_group, old_start,
- offset - old_start);
- WARN_ON(ret); /* -ENOMEM */
- goto out;
+ /* Not enough bytes in this entry to satisfy us */
+ if (old_end < offset + bytes) {
+ bytes -= old_end - offset;
+ offset = old_end;
+ goto again;
+ } else if (old_end == offset + bytes) {
+ /* all done */
+ goto out_lock;
+ }
+ spin_unlock(&ctl->tree_lock);
+
+ ret = btrfs_add_free_space(block_group, offset + bytes,
+ old_end - (offset + bytes));
+ WARN_ON(ret);
+ goto out;
+ }
}
ret = remove_from_bitmap(ctl, info, &offset, &bytes);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d8bb0db..fb8d671 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3754,7 +3754,7 @@
btrfs_wait_ordered_range(inode, 0, (u64)-1);
if (root->fs_info->log_root_recovering) {
- BUG_ON(!test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
+ BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags));
goto no_delete;
}
@@ -4247,7 +4247,7 @@
}
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret;
@@ -4893,7 +4893,7 @@
}
static int btrfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(dir)->root;
@@ -5876,8 +5876,17 @@
bh_result->b_size = len;
bh_result->b_bdev = em->bdev;
set_buffer_mapped(bh_result);
- if (create && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- set_buffer_new(bh_result);
+ if (create) {
+ if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ set_buffer_new(bh_result);
+
+ /*
+ * Need to update the i_size under the extent lock so buffered
+ * readers will get the updated i_size when we unlock.
+ */
+ if (start + len > i_size_read(inode))
+ i_size_write(inode, start + len);
+ }
free_extent_map(em);
@@ -6360,12 +6369,48 @@
*/
ordered = btrfs_lookup_ordered_range(inode, lockstart,
lockend - lockstart + 1);
- if (!ordered)
+
+ /*
+ * We need to make sure there are no buffered pages in this
+ * range either, we could have raced between the invalidate in
+ * generic_file_direct_write and locking the extent. The
+ * invalidate needs to happen so that reads after a write do not
+ * get stale data.
+ */
+ if (!ordered && (!writing ||
+ !test_range_bit(&BTRFS_I(inode)->io_tree,
+ lockstart, lockend, EXTENT_UPTODATE, 0,
+ cached_state)))
break;
+
unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
&cached_state, GFP_NOFS);
- btrfs_start_ordered_extent(inode, ordered, 1);
- btrfs_put_ordered_extent(ordered);
+
+ if (ordered) {
+ btrfs_start_ordered_extent(inode, ordered, 1);
+ btrfs_put_ordered_extent(ordered);
+ } else {
+ /* Screw you mmap */
+ ret = filemap_write_and_wait_range(file->f_mapping,
+ lockstart,
+ lockend);
+ if (ret)
+ goto out;
+
+ /*
+ * If we found a page that couldn't be invalidated just
+ * fall back to buffered.
+ */
+ ret = invalidate_inode_pages2_range(file->f_mapping,
+ lockstart >> PAGE_CACHE_SHIFT,
+ lockend >> PAGE_CACHE_SHIFT);
+ if (ret) {
+ if (ret == -EBUSY)
+ ret = 0;
+ goto out;
+ }
+ }
+
cond_resched();
}
@@ -6942,7 +6987,7 @@
struct btrfs_ordered_extent *ordered;
struct btrfs_root *root = BTRFS_I(inode)->root;
- WARN_ON(!list_empty(&inode->i_dentry));
+ WARN_ON(!hlist_empty(&inode->i_dentry));
WARN_ON(inode->i_data.nrpages);
WARN_ON(BTRFS_I(inode)->outstanding_extents);
WARN_ON(BTRFS_I(inode)->reserved_extents);
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index 497c530..e440aa6 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -339,7 +339,7 @@
#define BTRFS_IOC_WAIT_SYNC _IOW(BTRFS_IOCTL_MAGIC, 22, __u64)
#define BTRFS_IOC_SNAP_CREATE_V2 _IOW(BTRFS_IOCTL_MAGIC, 23, \
struct btrfs_ioctl_vol_args_v2)
-#define BTRFS_IOC_SUBVOL_GETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 25, __u64)
+#define BTRFS_IOC_SUBVOL_GETFLAGS _IOR(BTRFS_IOCTL_MAGIC, 25, __u64)
#define BTRFS_IOC_SUBVOL_SETFLAGS _IOW(BTRFS_IOCTL_MAGIC, 26, __u64)
#define BTRFS_IOC_SCRUB _IOWR(BTRFS_IOCTL_MAGIC, 27, \
struct btrfs_ioctl_scrub_args)
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0eb9a4d..b19d755 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1068,7 +1068,8 @@
}
bdev = fs_devices->latest_bdev;
- s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info);
+ s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
+ fs_info);
if (IS_ERR(s)) {
error = PTR_ERR(s);
goto error_close_devices;
@@ -1082,7 +1083,6 @@
} else {
char b[BDEVNAME_SIZE];
- s->s_flags = flags | MS_NOSEC;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
btrfs_sb(s)->bdev_holder = fs_type;
error = btrfs_fill_super(s, fs_devices, data,
@@ -1187,6 +1187,10 @@
if (ret)
goto restore;
+ ret = btrfs_resume_balance_async(fs_info);
+ if (ret)
+ goto restore;
+
sb->s_flags &= ~MS_RDONLY;
}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2017d0f..8abeae4 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -690,6 +690,8 @@
kfree(name);
iput(inode);
+
+ btrfs_run_delayed_items(trans, root);
return ret;
}
@@ -895,6 +897,7 @@
ret = btrfs_unlink_inode(trans, root, dir,
inode, victim_name,
victim_name_len);
+ btrfs_run_delayed_items(trans, root);
}
kfree(victim_name);
ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
@@ -1475,6 +1478,9 @@
ret = btrfs_unlink_inode(trans, root, dir, inode,
name, name_len);
BUG_ON(ret);
+
+ btrfs_run_delayed_items(trans, root);
+
kfree(name);
iput(inode);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8a3d259..ecaad40 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2845,31 +2845,48 @@
static int balance_kthread(void *data)
{
- struct btrfs_balance_control *bctl =
- (struct btrfs_balance_control *)data;
- struct btrfs_fs_info *fs_info = bctl->fs_info;
+ struct btrfs_fs_info *fs_info = data;
int ret = 0;
mutex_lock(&fs_info->volume_mutex);
mutex_lock(&fs_info->balance_mutex);
- set_balance_control(bctl);
-
- if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
- printk(KERN_INFO "btrfs: force skipping balance\n");
- } else {
+ if (fs_info->balance_ctl) {
printk(KERN_INFO "btrfs: continuing balance\n");
- ret = btrfs_balance(bctl, NULL);
+ ret = btrfs_balance(fs_info->balance_ctl, NULL);
}
mutex_unlock(&fs_info->balance_mutex);
mutex_unlock(&fs_info->volume_mutex);
+
return ret;
}
-int btrfs_recover_balance(struct btrfs_root *tree_root)
+int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
{
struct task_struct *tsk;
+
+ spin_lock(&fs_info->balance_lock);
+ if (!fs_info->balance_ctl) {
+ spin_unlock(&fs_info->balance_lock);
+ return 0;
+ }
+ spin_unlock(&fs_info->balance_lock);
+
+ if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
+ printk(KERN_INFO "btrfs: force skipping balance\n");
+ return 0;
+ }
+
+ tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
+ if (IS_ERR(tsk))
+ return PTR_ERR(tsk);
+
+ return 0;
+}
+
+int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
+{
struct btrfs_balance_control *bctl;
struct btrfs_balance_item *item;
struct btrfs_disk_balance_args disk_bargs;
@@ -2882,29 +2899,30 @@
if (!path)
return -ENOMEM;
+ key.objectid = BTRFS_BALANCE_OBJECTID;
+ key.type = BTRFS_BALANCE_ITEM_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ if (ret > 0) { /* ret = -ENOENT; */
+ ret = 0;
+ goto out;
+ }
+
bctl = kzalloc(sizeof(*bctl), GFP_NOFS);
if (!bctl) {
ret = -ENOMEM;
goto out;
}
- key.objectid = BTRFS_BALANCE_OBJECTID;
- key.type = BTRFS_BALANCE_ITEM_KEY;
- key.offset = 0;
-
- ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
- if (ret < 0)
- goto out_bctl;
- if (ret > 0) { /* ret = -ENOENT; */
- ret = 0;
- goto out_bctl;
- }
-
leaf = path->nodes[0];
item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
- bctl->fs_info = tree_root->fs_info;
- bctl->flags = btrfs_balance_flags(leaf, item) | BTRFS_BALANCE_RESUME;
+ bctl->fs_info = fs_info;
+ bctl->flags = btrfs_balance_flags(leaf, item);
+ bctl->flags |= BTRFS_BALANCE_RESUME;
btrfs_balance_data(leaf, item, &disk_bargs);
btrfs_disk_balance_args_to_cpu(&bctl->data, &disk_bargs);
@@ -2913,14 +2931,13 @@
btrfs_balance_sys(leaf, item, &disk_bargs);
btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
- tsk = kthread_run(balance_kthread, bctl, "btrfs-balance");
- if (IS_ERR(tsk))
- ret = PTR_ERR(tsk);
- else
- goto out;
+ mutex_lock(&fs_info->volume_mutex);
+ mutex_lock(&fs_info->balance_mutex);
-out_bctl:
- kfree(bctl);
+ set_balance_control(bctl);
+
+ mutex_unlock(&fs_info->balance_mutex);
+ mutex_unlock(&fs_info->volume_mutex);
out:
btrfs_free_path(path);
return ret;
@@ -4061,16 +4078,18 @@
BUG_ON(stripe_index >= bbio->num_stripes);
dev = bbio->stripes[stripe_index].dev;
- if (bio->bi_rw & WRITE)
- btrfs_dev_stat_inc(dev,
- BTRFS_DEV_STAT_WRITE_ERRS);
- else
- btrfs_dev_stat_inc(dev,
- BTRFS_DEV_STAT_READ_ERRS);
- if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH)
- btrfs_dev_stat_inc(dev,
- BTRFS_DEV_STAT_FLUSH_ERRS);
- btrfs_dev_stat_print_on_error(dev);
+ if (dev->bdev) {
+ if (bio->bi_rw & WRITE)
+ btrfs_dev_stat_inc(dev,
+ BTRFS_DEV_STAT_WRITE_ERRS);
+ else
+ btrfs_dev_stat_inc(dev,
+ BTRFS_DEV_STAT_READ_ERRS);
+ if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH)
+ btrfs_dev_stat_inc(dev,
+ BTRFS_DEV_STAT_FLUSH_ERRS);
+ btrfs_dev_stat_print_on_error(dev);
+ }
}
}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 74366f2..95f6637 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -281,7 +281,8 @@
int btrfs_init_new_device(struct btrfs_root *root, char *path);
int btrfs_balance(struct btrfs_balance_control *bctl,
struct btrfs_ioctl_balance_args *bargs);
-int btrfs_recover_balance(struct btrfs_root *tree_root);
+int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info);
+int btrfs_recover_balance(struct btrfs_fs_info *fs_info);
int btrfs_pause_balance(struct btrfs_fs_info *fs_info);
int btrfs_cancel_balance(struct btrfs_fs_info *fs_info);
int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset);
diff --git a/fs/buffer.c b/fs/buffer.c
index 838a9cf..c7062c89 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1036,6 +1036,9 @@
static struct buffer_head *
__getblk_slow(struct block_device *bdev, sector_t block, int size)
{
+ int ret;
+ struct buffer_head *bh;
+
/* Size must be multiple of hard sectorsize */
if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
(size < 512 || size > PAGE_SIZE))) {
@@ -1048,20 +1051,21 @@
return NULL;
}
- for (;;) {
- struct buffer_head * bh;
- int ret;
+retry:
+ bh = __find_get_block(bdev, block, size);
+ if (bh)
+ return bh;
+ ret = grow_buffers(bdev, block, size);
+ if (ret == 0) {
+ free_more_memory();
+ goto retry;
+ } else if (ret > 0) {
bh = __find_get_block(bdev, block, size);
if (bh)
return bh;
-
- ret = grow_buffers(bdev, block, size);
- if (ret < 0)
- return NULL;
- if (ret == 0)
- free_more_memory();
}
+ return NULL;
}
/*
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 7f0771d..b0b5f7c 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -567,7 +567,7 @@
if (ret < 0)
goto create_error;
start = jiffies;
- ret = vfs_create(dir->d_inode, next, S_IFREG, NULL);
+ ret = vfs_create(dir->d_inode, next, S_IFREG, true);
cachefiles_hist(cachefiles_create_histogram, start);
if (ret < 0)
goto create_error;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 3e8094b..00894ff 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -576,7 +576,7 @@
* the MDS so that it gets our 'caps wanted' value in a single op.
*/
static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
@@ -594,14 +594,6 @@
if (err < 0)
return ERR_PTR(err);
- /* open (but not create!) intent? */
- if (nd &&
- (nd->flags & LOOKUP_OPEN) &&
- !(nd->intent.open.flags & O_CREAT)) {
- int mode = nd->intent.open.create_mode & ~current->fs->umask;
- return ceph_lookup_open(dir, dentry, nd, mode, 1);
- }
-
/* can we conclude ENOENT locally? */
if (dentry->d_inode == NULL) {
struct ceph_inode_info *ci = ceph_inode(dir);
@@ -642,13 +634,51 @@
return dentry;
}
+int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
+{
+ int err;
+ struct dentry *res = NULL;
+
+ if (!(flags & O_CREAT)) {
+ if (dentry->d_name.len > NAME_MAX)
+ return -ENAMETOOLONG;
+
+ err = ceph_init_dentry(dentry);
+ if (err < 0)
+ return err;
+
+ return ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+ }
+
+ if (d_unhashed(dentry)) {
+ res = ceph_lookup(dir, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* We don't deal with positive dentries here */
+ if (dentry->d_inode)
+ return finish_no_open(file, res);
+
+ *opened |= FILE_CREATED;
+ err = ceph_lookup_open(dir, dentry, file, flags, mode, opened);
+ dput(res);
+
+ return err;
+}
+
/*
* If we do a create but get no trace back from the MDS, follow up with
* a lookup (the VFS expects us to link up the provided dentry).
*/
int ceph_handle_notrace_create(struct inode *dir, struct dentry *dentry)
{
- struct dentry *result = ceph_lookup(dir, dentry, NULL);
+ struct dentry *result = ceph_lookup(dir, dentry, 0);
if (result && !IS_ERR(result)) {
/*
@@ -700,25 +730,9 @@
}
static int ceph_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- dout("create in dir %p dentry %p name '%.*s'\n",
- dir, dentry, dentry->d_name.len, dentry->d_name.name);
-
- if (ceph_snap(dir) != CEPH_NOSNAP)
- return -EROFS;
-
- if (nd) {
- BUG_ON((nd->flags & LOOKUP_OPEN) == 0);
- dentry = ceph_lookup_open(dir, dentry, nd, mode, 0);
- /* hrm, what should i do here if we get aliased? */
- if (IS_ERR(dentry))
- return PTR_ERR(dentry);
- return 0;
- }
-
- /* fall back to mknod */
- return ceph_mknod(dir, dentry, (mode & ~S_IFMT) | S_IFREG, 0);
+ return ceph_mknod(dir, dentry, mode, 0);
}
static int ceph_symlink(struct inode *dir, struct dentry *dentry,
@@ -1028,12 +1042,12 @@
/*
* Check if cached dentry can be trusted.
*/
-static int ceph_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
{
int valid = 0;
struct inode *dir;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
dout("d_revalidate %p '%.*s' inode %p offset %lld\n", dentry,
@@ -1080,7 +1094,7 @@
}
static int ceph_snapdir_d_revalidate(struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/*
* Eventually, we'll want to revalidate snapped metadata
@@ -1357,6 +1371,7 @@
.rmdir = ceph_unlink,
.rename = ceph_rename,
.create = ceph_create,
+ .atomic_open = ceph_atomic_open,
};
const struct dentry_operations ceph_dentry_ops = {
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 988d4f3..1b81d6c 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -213,22 +213,15 @@
* may_open() fails, the struct *file gets cleaned up (i.e.
* ceph_release gets called). So fear not!
*/
-/*
- * flags
- * path_lookup_open -> LOOKUP_OPEN
- * path_lookup_create -> LOOKUP_OPEN|LOOKUP_CREATE
- */
-struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir)
+int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned flags, umode_t mode,
+ int *opened)
{
struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
struct ceph_mds_client *mdsc = fsc->mdsc;
- struct file *file;
struct ceph_mds_request *req;
struct dentry *ret;
int err;
- int flags = nd->intent.open.flags;
dout("ceph_lookup_open dentry %p '%.*s' flags %d mode 0%o\n",
dentry, dentry->d_name.len, dentry->d_name.name, flags, mode);
@@ -236,7 +229,7 @@
/* do the open */
req = prepare_open_request(dir->i_sb, flags, mode);
if (IS_ERR(req))
- return ERR_CAST(req);
+ return PTR_ERR(req);
req->r_dentry = dget(dentry);
req->r_num_caps = 2;
if (flags & O_CREAT) {
@@ -254,14 +247,17 @@
err = ceph_handle_notrace_create(dir, dentry);
if (err)
goto out;
- file = lookup_instantiate_filp(nd, req->r_dentry, ceph_open);
- if (IS_ERR(file))
- err = PTR_ERR(file);
+ err = finish_open(file, req->r_dentry, ceph_open, opened);
out:
ret = ceph_finish_lookup(req, dentry, err);
ceph_mdsc_put_request(req);
dout("ceph_lookup_open result=%p\n", ret);
- return ret;
+
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+
+ dput(ret);
+ return err;
}
int ceph_release(struct inode *inode, struct file *file)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 1e67dd7..7076109 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -871,7 +871,7 @@
if (ceph_test_opt(fsc->client, NOSHARE))
compare_super = NULL;
- sb = sget(fs_type, compare_super, ceph_set_super, fsc);
+ sb = sget(fs_type, compare_super, ceph_set_super, flags, fsc);
if (IS_ERR(sb)) {
res = ERR_CAST(sb);
goto out;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index fc35036..f4d5522 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -806,9 +806,9 @@
loff_t off, size_t len);
extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
extern int ceph_open(struct inode *inode, struct file *file);
-extern struct dentry *ceph_lookup_open(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd, int mode,
- int locked_dir);
+extern int ceph_lookup_open(struct inode *dir, struct dentry *dentry,
+ struct file *od, unsigned flags,
+ umode_t mode, int *opened);
extern int ceph_release(struct inode *inode, struct file *filp);
/* dir.c */
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 8b6e344..a7610cf 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -257,7 +257,6 @@
static void cifs_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(cifs_inode_cachep, CIFS_I(inode));
}
@@ -638,7 +637,10 @@
mnt_data.cifs_sb = cifs_sb;
mnt_data.flags = flags;
- sb = sget(fs_type, cifs_match_super, cifs_set_super, &mnt_data);
+ /* BB should we make this contingent on mount parm? */
+ flags |= MS_NODIRATIME | MS_NOATIME;
+
+ sb = sget(fs_type, cifs_match_super, cifs_set_super, flags, &mnt_data);
if (IS_ERR(sb)) {
root = ERR_CAST(sb);
cifs_umount(cifs_sb);
@@ -649,10 +651,6 @@
cFYI(1, "Use existing superblock");
cifs_umount(cifs_sb);
} else {
- sb->s_flags = flags;
- /* BB should we make this contingent on mount parm? */
- sb->s_flags |= MS_NODIRATIME | MS_NOATIME;
-
rc = cifs_read_super(sb);
if (rc) {
root = ERR_PTR(rc);
@@ -778,6 +776,7 @@
};
const struct inode_operations cifs_dir_inode_ops = {
.create = cifs_create,
+ .atomic_open = cifs_atomic_open,
.lookup = cifs_lookup,
.getattr = cifs_getattr,
.unlink = cifs_unlink,
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 6536535..1c49c5a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -45,9 +45,12 @@
extern const struct inode_operations cifs_dir_inode_ops;
extern struct inode *cifs_root_iget(struct super_block *);
extern int cifs_create(struct inode *, struct dentry *, umode_t,
- struct nameidata *);
+ bool excl);
+extern int cifs_atomic_open(struct inode *, struct dentry *,
+ struct file *, unsigned, umode_t,
+ int *);
extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
- struct nameidata *);
+ unsigned int);
extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
extern int cifs_hardlink(struct dentry *, struct inode *, struct dentry *);
extern int cifs_mknod(struct inode *, struct dentry *, umode_t, dev_t);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 78db68a..0ae86dd 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1653,24 +1653,26 @@
* If yes, we have encountered a double deliminator
* reset the NULL character to the deliminator
*/
- if (tmp_end < end && tmp_end[1] == delim)
+ if (tmp_end < end && tmp_end[1] == delim) {
tmp_end[0] = delim;
- /* Keep iterating until we get to a single deliminator
- * OR the end
- */
- while ((tmp_end = strchr(tmp_end, delim)) != NULL &&
- (tmp_end[1] == delim)) {
- tmp_end = (char *) &tmp_end[2];
- }
+ /* Keep iterating until we get to a single
+ * deliminator OR the end
+ */
+ while ((tmp_end = strchr(tmp_end, delim))
+ != NULL && (tmp_end[1] == delim)) {
+ tmp_end = (char *) &tmp_end[2];
+ }
- /* Reset var options to point to next element */
- if (tmp_end) {
- tmp_end[0] = '\0';
- options = (char *) &tmp_end[1];
- } else
- /* Reached the end of the mount option string */
- options = end;
+ /* Reset var options to point to next element */
+ if (tmp_end) {
+ tmp_end[0] = '\0';
+ options = (char *) &tmp_end[1];
+ } else
+ /* Reached the end of the mount option
+ * string */
+ options = end;
+ }
/* Now build new password string */
temp_len = strlen(value);
@@ -3493,18 +3495,15 @@
* MS-CIFS indicates that servers are only limited by the client's
* bufsize for reads, testing against win98se shows that it throws
* INVALID_PARAMETER errors if you try to request too large a read.
+ * OS/2 just sends back short reads.
*
- * If the server advertises a MaxBufferSize of less than one page,
- * assume that it also can't satisfy reads larger than that either.
- *
- * FIXME: Is there a better heuristic for this?
+ * If the server doesn't advertise CAP_LARGE_READ_X, then assume that
+ * it can't handle a read request larger than its MaxBufferSize either.
*/
if (tcon->unix_ext && (unix_cap & CIFS_UNIX_LARGE_READ_CAP))
defsize = CIFS_DEFAULT_IOSIZE;
else if (server->capabilities & CAP_LARGE_READ_X)
defsize = CIFS_DEFAULT_NON_POSIX_RSIZE;
- else if (server->maxBuf >= PAGE_CACHE_SIZE)
- defsize = CIFSMaxBufSize;
else
defsize = server->maxBuf - sizeof(READ_RSP);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ec4e9a2..a180265 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -133,100 +133,133 @@
return full_path;
}
+/*
+ * Don't allow the separator character in a path component.
+ * The VFS will not allow "/", but "\" is allowed by posix.
+ */
+static int
+check_name(struct dentry *direntry)
+{
+ struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+ int i;
+
+ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
+ for (i = 0; i < direntry->d_name.len; i++) {
+ if (direntry->d_name.name[i] == '\\') {
+ cFYI(1, "Invalid file name");
+ return -EINVAL;
+ }
+ }
+ }
+ return 0;
+}
+
+
/* Inode operations in similar order to how they appear in Linux file fs.h */
-int
-cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
- struct nameidata *nd)
+static int cifs_do_create(struct inode *inode, struct dentry *direntry,
+ int xid, struct tcon_link *tlink, unsigned oflags,
+ umode_t mode, __u32 *oplock, __u16 *fileHandle,
+ int *created)
{
int rc = -ENOENT;
- int xid;
int create_options = CREATE_NOT_DIR;
- __u32 oplock = 0;
- int oflags;
- /*
- * BB below access is probably too much for mknod to request
- * but we have to do query and setpathinfo so requesting
- * less could fail (unless we want to request getatr and setatr
- * permissions (only). At least for POSIX we do not have to
- * request so much.
- */
- int desiredAccess = GENERIC_READ | GENERIC_WRITE;
- __u16 fileHandle;
- struct cifs_sb_info *cifs_sb;
- struct tcon_link *tlink;
- struct cifs_tcon *tcon;
+ int desiredAccess;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct cifs_tcon *tcon = tlink_tcon(tlink);
char *full_path = NULL;
FILE_ALL_INFO *buf = NULL;
struct inode *newinode = NULL;
- int disposition = FILE_OVERWRITE_IF;
+ int disposition;
- xid = GetXid();
-
- cifs_sb = CIFS_SB(inode->i_sb);
- tlink = cifs_sb_tlink(cifs_sb);
- if (IS_ERR(tlink)) {
- FreeXid(xid);
- return PTR_ERR(tlink);
- }
- tcon = tlink_tcon(tlink);
-
+ *oplock = 0;
if (tcon->ses->server->oplocks)
- oplock = REQ_OPLOCK;
-
- if (nd)
- oflags = nd->intent.open.file->f_flags;
- else
- oflags = O_RDONLY | O_CREAT;
+ *oplock = REQ_OPLOCK;
full_path = build_path_from_dentry(direntry);
if (full_path == NULL) {
rc = -ENOMEM;
- goto cifs_create_out;
+ goto out;
}
if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
+ !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
le64_to_cpu(tcon->fsUnixInfo.Capability))) {
rc = cifs_posix_open(full_path, &newinode,
- inode->i_sb, mode, oflags, &oplock, &fileHandle, xid);
- /* EIO could indicate that (posix open) operation is not
- supported, despite what server claimed in capability
- negotiation. EREMOTE indicates DFS junction, which is not
- handled in posix open */
-
- if (rc == 0) {
- if (newinode == NULL) /* query inode info */
+ inode->i_sb, mode, oflags, oplock, fileHandle, xid);
+ switch (rc) {
+ case 0:
+ if (newinode == NULL) {
+ /* query inode info */
goto cifs_create_get_file_info;
- else /* success, no need to query */
- goto cifs_create_set_dentry;
- } else if ((rc != -EIO) && (rc != -EREMOTE) &&
- (rc != -EOPNOTSUPP) && (rc != -EINVAL))
- goto cifs_create_out;
- /* else fallthrough to retry, using older open call, this is
- case where server does not support this SMB level, and
- falsely claims capability (also get here for DFS case
- which should be rare for path not covered on files) */
+ }
+
+ if (!S_ISREG(newinode->i_mode)) {
+ /*
+ * The server may allow us to open things like
+ * FIFOs, but the client isn't set up to deal
+ * with that. If it's not a regular file, just
+ * close it and proceed as if it were a normal
+ * lookup.
+ */
+ CIFSSMBClose(xid, tcon, *fileHandle);
+ goto cifs_create_get_file_info;
+ }
+ /* success, no need to query */
+ goto cifs_create_set_dentry;
+
+ case -ENOENT:
+ goto cifs_create_get_file_info;
+
+ case -EIO:
+ case -EINVAL:
+ /*
+ * EIO could indicate that (posix open) operation is not
+ * supported, despite what server claimed in capability
+ * negotiation.
+ *
+ * POSIX open in samba versions 3.3.1 and earlier could
+ * incorrectly fail with invalid parameter.
+ */
+ tcon->broken_posix_open = true;
+ break;
+
+ case -EREMOTE:
+ case -EOPNOTSUPP:
+ /*
+ * EREMOTE indicates DFS junction, which is not handled
+ * in posix open. If either that or op not supported
+ * returned, follow the normal lookup.
+ */
+ break;
+
+ default:
+ goto out;
+ }
+ /*
+ * fallthrough to retry, using older open call, this is case
+ * where server does not support this SMB level, and falsely
+ * claims capability (also get here for DFS case which should be
+ * rare for path not covered on files)
+ */
}
- if (nd) {
- /* if the file is going to stay open, then we
- need to set the desired access properly */
- desiredAccess = 0;
- if (OPEN_FMODE(oflags) & FMODE_READ)
- desiredAccess |= GENERIC_READ; /* is this too little? */
- if (OPEN_FMODE(oflags) & FMODE_WRITE)
- desiredAccess |= GENERIC_WRITE;
+ desiredAccess = 0;
+ if (OPEN_FMODE(oflags) & FMODE_READ)
+ desiredAccess |= GENERIC_READ; /* is this too little? */
+ if (OPEN_FMODE(oflags) & FMODE_WRITE)
+ desiredAccess |= GENERIC_WRITE;
- if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
- disposition = FILE_CREATE;
- else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
- disposition = FILE_OVERWRITE_IF;
- else if ((oflags & O_CREAT) == O_CREAT)
- disposition = FILE_OPEN_IF;
- else
- cFYI(1, "Create flag not set in create function");
- }
+ disposition = FILE_OVERWRITE_IF;
+ if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
+ disposition = FILE_CREATE;
+ else if ((oflags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
+ disposition = FILE_OVERWRITE_IF;
+ else if ((oflags & O_CREAT) == O_CREAT)
+ disposition = FILE_OPEN_IF;
+ else
+ cFYI(1, "Create flag not set in create function");
/* BB add processing to set equivalent of mode - e.g. via CreateX with
ACLs */
@@ -234,7 +267,7 @@
buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
if (buf == NULL) {
rc = -ENOMEM;
- goto cifs_create_out;
+ goto out;
}
/*
@@ -250,7 +283,7 @@
if (tcon->ses->capabilities & CAP_NT_SMBS)
rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
- &fileHandle, &oplock, buf, cifs_sb->local_nls,
+ fileHandle, oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
else
rc = -EIO; /* no NT SMB support fall into legacy open below */
@@ -259,17 +292,17 @@
/* old server, retry the open legacy style */
rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
desiredAccess, create_options,
- &fileHandle, &oplock, buf, cifs_sb->local_nls,
+ fileHandle, oplock, buf, cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
}
if (rc) {
cFYI(1, "cifs_create returned 0x%x", rc);
- goto cifs_create_out;
+ goto out;
}
/* If Open reported that we actually created a file
then we now have to set the mode if possible */
- if ((tcon->unix_ext) && (oplock & CIFS_CREATE_ACTION)) {
+ if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) {
struct cifs_unix_set_info_args args = {
.mode = mode,
.ctime = NO_CHANGE_64,
@@ -278,6 +311,7 @@
.device = 0,
};
+ *created |= FILE_CREATED;
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) {
args.uid = (__u64) current_fsuid();
if (inode->i_mode & S_ISGID)
@@ -288,7 +322,7 @@
args.uid = NO_CHANGE_64;
args.gid = NO_CHANGE_64;
}
- CIFSSMBUnixSetFileInfo(xid, tcon, &args, fileHandle,
+ CIFSSMBUnixSetFileInfo(xid, tcon, &args, *fileHandle,
current->tgid);
} else {
/* BB implement mode setting via Windows security
@@ -305,11 +339,11 @@
inode->i_sb, xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf,
- inode->i_sb, xid, &fileHandle);
+ inode->i_sb, xid, fileHandle);
if (newinode) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)
newinode->i_mode = mode;
- if ((oplock & CIFS_CREATE_ACTION) &&
+ if ((*oplock & CIFS_CREATE_ACTION) &&
(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
newinode->i_uid = current_fsuid();
if (inode->i_mode & S_ISGID)
@@ -321,40 +355,139 @@
}
cifs_create_set_dentry:
- if (rc == 0)
- d_instantiate(direntry, newinode);
- else
+ if (rc != 0) {
cFYI(1, "Create worked, get_inode_info failed rc = %d", rc);
-
- if (newinode && nd) {
- struct cifsFileInfo *pfile_info;
- struct file *filp;
-
- filp = lookup_instantiate_filp(nd, direntry, generic_file_open);
- if (IS_ERR(filp)) {
- rc = PTR_ERR(filp);
- CIFSSMBClose(xid, tcon, fileHandle);
- goto cifs_create_out;
- }
-
- pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
- if (pfile_info == NULL) {
- fput(filp);
- CIFSSMBClose(xid, tcon, fileHandle);
- rc = -ENOMEM;
- }
- } else {
- CIFSSMBClose(xid, tcon, fileHandle);
+ goto out;
}
+ d_drop(direntry);
+ d_add(direntry, newinode);
-cifs_create_out:
+ /* ENOENT for create? How weird... */
+ rc = -ENOENT;
+ if (!newinode) {
+ CIFSSMBClose(xid, tcon, *fileHandle);
+ goto out;
+ }
+ rc = 0;
+
+out:
kfree(buf);
kfree(full_path);
+ return rc;
+}
+
+int
+cifs_atomic_open(struct inode *inode, struct dentry *direntry,
+ struct file *file, unsigned oflags, umode_t mode,
+ int *opened)
+{
+ int rc;
+ int xid;
+ struct tcon_link *tlink;
+ struct cifs_tcon *tcon;
+ __u16 fileHandle;
+ __u32 oplock;
+ struct file *filp;
+ struct cifsFileInfo *pfile_info;
+
+ /* Posix open is only called (at lookup time) for file create now. For
+ * opens (rather than creates), because we do not know if it is a file
+ * or directory yet, and current Samba no longer allows us to do posix
+ * open on dirs, we could end up wasting an open call on what turns out
+ * to be a dir. For file opens, we wait to call posix open till
+ * cifs_open. It could be added to atomic_open in the future but the
+ * performance tradeoff of the extra network request when EISDIR or
+ * EACCES is returned would have to be weighed against the 50% reduction
+ * in network traffic in the other paths.
+ */
+ if (!(oflags & O_CREAT)) {
+ struct dentry *res = cifs_lookup(inode, direntry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ return finish_no_open(file, res);
+ }
+
+ rc = check_name(direntry);
+ if (rc)
+ return rc;
+
+ xid = GetXid();
+
+ cFYI(1, "parent inode = 0x%p name is: %s and dentry = 0x%p",
+ inode, direntry->d_name.name, direntry);
+
+ tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+ filp = ERR_CAST(tlink);
+ if (IS_ERR(tlink))
+ goto free_xid;
+
+ tcon = tlink_tcon(tlink);
+
+ rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+ &oplock, &fileHandle, opened);
+
+ if (rc)
+ goto out;
+
+ rc = finish_open(file, direntry, generic_file_open, opened);
+ if (rc) {
+ CIFSSMBClose(xid, tcon, fileHandle);
+ goto out;
+ }
+
+ pfile_info = cifs_new_fileinfo(fileHandle, filp, tlink, oplock);
+ if (pfile_info == NULL) {
+ CIFSSMBClose(xid, tcon, fileHandle);
+ fput(filp);
+ rc = -ENOMEM;
+ }
+
+out:
cifs_put_tlink(tlink);
+free_xid:
FreeXid(xid);
return rc;
}
+int cifs_create(struct inode *inode, struct dentry *direntry, umode_t mode,
+ bool excl)
+{
+ int rc;
+ int xid = GetXid();
+ /*
+ * BB below access is probably too much for mknod to request
+ * but we have to do query and setpathinfo so requesting
+ * less could fail (unless we want to request getatr and setatr
+ * permissions (only). At least for POSIX we do not have to
+ * request so much.
+ */
+ unsigned oflags = O_EXCL | O_CREAT | O_RDWR;
+ struct tcon_link *tlink;
+ __u16 fileHandle;
+ __u32 oplock;
+ int created = FILE_CREATED;
+
+ cFYI(1, "cifs_create parent inode = 0x%p name is: %s and dentry = 0x%p",
+ inode, direntry->d_name.name, direntry);
+
+ tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb));
+ rc = PTR_ERR(tlink);
+ if (IS_ERR(tlink))
+ goto free_xid;
+
+ rc = cifs_do_create(inode, direntry, xid, tlink, oflags, mode,
+ &oplock, &fileHandle, &created);
+ if (!rc)
+ CIFSSMBClose(xid, tlink_tcon(tlink), fileHandle);
+
+ cifs_put_tlink(tlink);
+free_xid:
+ FreeXid(xid);
+
+ return rc;
+}
+
int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
dev_t device_number)
{
@@ -488,20 +621,15 @@
struct dentry *
cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
- struct nameidata *nd)
+ unsigned int flags)
{
int xid;
int rc = 0; /* to get around spurious gcc warning, set to zero here */
- __u32 oplock;
- __u16 fileHandle = 0;
- bool posix_open = false;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
struct cifs_tcon *pTcon;
- struct cifsFileInfo *cfile;
struct inode *newInode = NULL;
char *full_path = NULL;
- struct file *filp;
xid = GetXid();
@@ -518,31 +646,9 @@
}
pTcon = tlink_tcon(tlink);
- oplock = pTcon->ses->server->oplocks ? REQ_OPLOCK : 0;
-
- /*
- * Don't allow the separator character in a path component.
- * The VFS will not allow "/", but "\" is allowed by posix.
- */
- if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) {
- int i;
- for (i = 0; i < direntry->d_name.len; i++)
- if (direntry->d_name.name[i] == '\\') {
- cFYI(1, "Invalid file name");
- rc = -EINVAL;
- goto lookup_out;
- }
- }
-
- /*
- * O_EXCL: optimize away the lookup, but don't hash the dentry. Let
- * the VFS handle the create.
- */
- if (nd && (nd->flags & LOOKUP_EXCL)) {
- d_instantiate(direntry, NULL);
- rc = 0;
+ rc = check_name(direntry);
+ if (rc)
goto lookup_out;
- }
/* can not grab the rename sem here since it would
deadlock in the cases (beginning of sys_rename itself)
@@ -560,80 +666,16 @@
}
cFYI(1, "Full path: %s inode = 0x%p", full_path, direntry->d_inode);
- /* Posix open is only called (at lookup time) for file create now.
- * For opens (rather than creates), because we do not know if it
- * is a file or directory yet, and current Samba no longer allows
- * us to do posix open on dirs, we could end up wasting an open call
- * on what turns out to be a dir. For file opens, we wait to call posix
- * open till cifs_open. It could be added here (lookup) in the future
- * but the performance tradeoff of the extra network request when EISDIR
- * or EACCES is returned would have to be weighed against the 50%
- * reduction in network traffic in the other paths.
- */
if (pTcon->unix_ext) {
- if (nd && !(nd->flags & LOOKUP_DIRECTORY) &&
- (nd->flags & LOOKUP_OPEN) && !pTcon->broken_posix_open &&
- (nd->intent.open.file->f_flags & O_CREAT)) {
- rc = cifs_posix_open(full_path, &newInode,
- parent_dir_inode->i_sb,
- nd->intent.open.create_mode,
- nd->intent.open.file->f_flags, &oplock,
- &fileHandle, xid);
- /*
- * The check below works around a bug in POSIX
- * open in samba versions 3.3.1 and earlier where
- * open could incorrectly fail with invalid parameter.
- * If either that or op not supported returned, follow
- * the normal lookup.
- */
- switch (rc) {
- case 0:
- /*
- * The server may allow us to open things like
- * FIFOs, but the client isn't set up to deal
- * with that. If it's not a regular file, just
- * close it and proceed as if it were a normal
- * lookup.
- */
- if (newInode && !S_ISREG(newInode->i_mode)) {
- CIFSSMBClose(xid, pTcon, fileHandle);
- break;
- }
- case -ENOENT:
- posix_open = true;
- case -EOPNOTSUPP:
- break;
- default:
- pTcon->broken_posix_open = true;
- }
- }
- if (!posix_open)
- rc = cifs_get_inode_info_unix(&newInode, full_path,
- parent_dir_inode->i_sb, xid);
- } else
+ rc = cifs_get_inode_info_unix(&newInode, full_path,
+ parent_dir_inode->i_sb, xid);
+ } else {
rc = cifs_get_inode_info(&newInode, full_path, NULL,
parent_dir_inode->i_sb, xid, NULL);
+ }
if ((rc == 0) && (newInode != NULL)) {
d_add(direntry, newInode);
- if (posix_open) {
- filp = lookup_instantiate_filp(nd, direntry,
- generic_file_open);
- if (IS_ERR(filp)) {
- rc = PTR_ERR(filp);
- CIFSSMBClose(xid, pTcon, fileHandle);
- goto lookup_out;
- }
-
- cfile = cifs_new_fileinfo(fileHandle, filp, tlink,
- oplock);
- if (cfile == NULL) {
- fput(filp);
- CIFSSMBClose(xid, pTcon, fileHandle);
- rc = -ENOMEM;
- goto lookup_out;
- }
- }
/* since paths are not looked up by component - the parent
directories are presumed to be good here */
renew_parental_timestamps(direntry);
@@ -658,9 +700,9 @@
}
static int
-cifs_d_revalidate(struct dentry *direntry, struct nameidata *nd)
+cifs_d_revalidate(struct dentry *direntry, unsigned int flags)
{
- if (nd && (nd->flags & LOOKUP_RCU))
+ if (flags & LOOKUP_RCU)
return -ECHILD;
if (direntry->d_inode) {
@@ -689,7 +731,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -697,7 +739,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
if (time_after(jiffies, direntry->d_time + HZ) || !lookupCacheEnabled)
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 745da3d..8e8bb49 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -800,7 +800,7 @@
return 0;
/* if it's not a directory or has no dentries, then flag it */
- if (S_ISDIR(inode->i_mode) && !list_empty(&inode->i_dentry))
+ if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry))
fattr->cf_flags |= CIFS_FATTR_INO_COLLISION;
return 1;
@@ -825,9 +825,10 @@
inode_has_hashed_dentries(struct inode *inode)
{
struct dentry *dentry;
+ struct hlist_node *p;
spin_lock(&inode->i_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
if (!d_unhashed(dentry) || IS_ROOT(dentry)) {
spin_unlock(&inode->i_lock);
return true;
diff --git a/fs/coda/cache.c b/fs/coda/cache.c
index 6901578..958ae0e 100644
--- a/fs/coda/cache.c
+++ b/fs/coda/cache.c
@@ -89,17 +89,13 @@
/* this won't do any harm: just flag all children */
static void coda_flag_children(struct dentry *parent, int flag)
{
- struct list_head *child;
struct dentry *de;
spin_lock(&parent->d_lock);
- list_for_each(child, &parent->d_subdirs)
- {
- de = list_entry(child, struct dentry, d_u.d_child);
+ list_for_each_entry(de, &parent->d_subdirs, d_u.d_child) {
/* don't know what to do with negative dentries */
- if ( ! de->d_inode )
- continue;
- coda_flag_inode(de->d_inode, flag);
+ if (de->d_inode )
+ coda_flag_inode(de->d_inode, flag);
}
spin_unlock(&parent->d_lock);
return;
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index 1775158..49fe52d 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -30,8 +30,8 @@
#include "coda_int.h"
/* dir inode-ops */
-static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, struct nameidata *nd);
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, struct nameidata *nd);
+static int coda_create(struct inode *dir, struct dentry *new, umode_t mode, bool excl);
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *target, unsigned int flags);
static int coda_link(struct dentry *old_dentry, struct inode *dir_inode,
struct dentry *entry);
static int coda_unlink(struct inode *dir_inode, struct dentry *entry);
@@ -46,7 +46,7 @@
static int coda_readdir(struct file *file, void *buf, filldir_t filldir);
/* dentry ops */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd);
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags);
static int coda_dentry_delete(const struct dentry *);
/* support routines */
@@ -94,7 +94,7 @@
/* inode operations for directories */
/* access routines: lookup, readlink, permission */
-static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, struct nameidata *nd)
+static struct dentry *coda_lookup(struct inode *dir, struct dentry *entry, unsigned int flags)
{
struct super_block *sb = dir->i_sb;
const char *name = entry->d_name.name;
@@ -188,7 +188,7 @@
}
/* creation routines: create, mknod, mkdir, link, symlink */
-static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, struct nameidata *nd)
+static int coda_create(struct inode *dir, struct dentry *de, umode_t mode, bool excl)
{
int error;
const char *name=de->d_name.name;
@@ -536,12 +536,12 @@
}
/* called when a cache lookup succeeds */
-static int coda_dentry_revalidate(struct dentry *de, struct nameidata *nd)
+static int coda_dentry_revalidate(struct dentry *de, unsigned int flags)
{
struct inode *inode;
struct coda_inode_info *cii;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = de->d_inode;
diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 7e6c52d..7414ae2 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -442,7 +442,7 @@
static struct dentry * configfs_lookup(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct configfs_dirent * parent_sd = dentry->d_parent->d_fsdata;
struct configfs_dirent * sd;
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index d013c46..28cca01 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -417,7 +417,7 @@
/*
* Lookup and fill in the inode data..
*/
-static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
unsigned int offset = 0;
struct inode *inode = NULL;
diff --git a/fs/dcache.c b/fs/dcache.c
index 4046904..8086636 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -218,7 +218,7 @@
{
struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
- WARN_ON(!list_empty(&dentry->d_alias));
+ WARN_ON(!hlist_unhashed(&dentry->d_alias));
if (dname_external(dentry))
kfree(dentry->d_name.name);
kmem_cache_free(dentry_cache, dentry);
@@ -267,7 +267,7 @@
struct inode *inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_alias);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
if (!inode->i_nlink)
@@ -291,7 +291,7 @@
{
struct inode *inode = dentry->d_inode;
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_alias);
dentry_rcuwalk_barrier(dentry);
spin_unlock(&dentry->d_lock);
spin_unlock(&inode->i_lock);
@@ -699,10 +699,11 @@
static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
{
struct dentry *alias, *discon_alias;
+ struct hlist_node *p;
again:
discon_alias = NULL;
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
spin_lock(&alias->d_lock);
if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
if (IS_ROOT(alias) &&
@@ -737,7 +738,7 @@
{
struct dentry *de = NULL;
- if (!list_empty(&inode->i_dentry)) {
+ if (!hlist_empty(&inode->i_dentry)) {
spin_lock(&inode->i_lock);
de = __d_find_alias(inode, 0);
spin_unlock(&inode->i_lock);
@@ -753,9 +754,10 @@
void d_prune_aliases(struct inode *inode)
{
struct dentry *dentry;
+ struct hlist_node *p;
restart:
spin_lock(&inode->i_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (!dentry->d_count) {
__dget_dlock(dentry);
@@ -977,7 +979,7 @@
inode = dentry->d_inode;
if (inode) {
dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
+ hlist_del_init(&dentry->d_alias);
if (dentry->d_op && dentry->d_op->d_iput)
dentry->d_op->d_iput(dentry, inode);
else
@@ -1312,7 +1314,7 @@
INIT_HLIST_BL_NODE(&dentry->d_hash);
INIT_LIST_HEAD(&dentry->d_lru);
INIT_LIST_HEAD(&dentry->d_subdirs);
- INIT_LIST_HEAD(&dentry->d_alias);
+ INIT_HLIST_NODE(&dentry->d_alias);
INIT_LIST_HEAD(&dentry->d_u.d_child);
d_set_d_op(dentry, dentry->d_sb->s_d_op);
@@ -1400,7 +1402,7 @@
if (inode) {
if (unlikely(IS_AUTOMOUNT(inode)))
dentry->d_flags |= DCACHE_NEED_AUTOMOUNT;
- list_add(&dentry->d_alias, &inode->i_dentry);
+ hlist_add_head(&dentry->d_alias, &inode->i_dentry);
}
dentry->d_inode = inode;
dentry_rcuwalk_barrier(dentry);
@@ -1425,7 +1427,7 @@
void d_instantiate(struct dentry *entry, struct inode * inode)
{
- BUG_ON(!list_empty(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_alias));
if (inode)
spin_lock(&inode->i_lock);
__d_instantiate(entry, inode);
@@ -1458,13 +1460,14 @@
int len = entry->d_name.len;
const char *name = entry->d_name.name;
unsigned int hash = entry->d_name.hash;
+ struct hlist_node *p;
if (!inode) {
__d_instantiate(entry, NULL);
return NULL;
}
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
/*
* Don't need alias->d_lock here, because aliases with
* d_parent == entry->d_parent are not subject to name or
@@ -1490,7 +1493,7 @@
{
struct dentry *result;
- BUG_ON(!list_empty(&entry->d_alias));
+ BUG_ON(!hlist_unhashed(&entry->d_alias));
if (inode)
spin_lock(&inode->i_lock);
@@ -1531,9 +1534,9 @@
{
struct dentry *alias;
- if (list_empty(&inode->i_dentry))
+ if (hlist_empty(&inode->i_dentry))
return NULL;
- alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias);
+ alias = hlist_entry(inode->i_dentry.first, struct dentry, d_alias);
__dget(alias);
return alias;
}
@@ -1607,7 +1610,7 @@
spin_lock(&tmp->d_lock);
tmp->d_inode = inode;
tmp->d_flags |= DCACHE_DISCONNECTED;
- list_add(&tmp->d_alias, &inode->i_dentry);
+ hlist_add_head(&tmp->d_alias, &inode->i_dentry);
hlist_bl_lock(&tmp->d_sb->s_anon);
hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_anon);
hlist_bl_unlock(&tmp->d_sb->s_anon);
@@ -2384,14 +2387,13 @@
struct dentry *dentry, struct dentry *alias)
{
struct mutex *m1 = NULL, *m2 = NULL;
- struct dentry *ret;
+ struct dentry *ret = ERR_PTR(-EBUSY);
/* If alias and dentry share a parent, then no extra locks required */
if (alias->d_parent == dentry->d_parent)
goto out_unalias;
/* See lock_rename() */
- ret = ERR_PTR(-EBUSY);
if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
goto out_err;
m1 = &dentry->d_sb->s_vfs_rename_mutex;
@@ -2399,8 +2401,10 @@
goto out_err;
m2 = &alias->d_parent->d_inode->i_mutex;
out_unalias:
- __d_move(alias, dentry);
- ret = alias;
+ if (likely(!d_mountpoint(alias))) {
+ __d_move(alias, dentry);
+ ret = alias;
+ }
out_err:
spin_unlock(&inode->i_lock);
if (m2)
@@ -2622,7 +2626,7 @@
if (!slash)
error = prepend(buffer, buflen, "/", 1);
if (!error)
- error = real_mount(vfsmnt)->mnt_ns ? 1 : 2;
+ error = is_mounted(vfsmnt) ? 1 : 2;
goto out;
}
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index b80bc84..d17c20f 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -54,13 +54,12 @@
break;
case S_IFLNK:
inode->i_op = &debugfs_link_operations;
- inode->i_fop = fops;
inode->i_private = data;
break;
case S_IFDIR:
inode->i_op = &simple_dir_inode_operations;
- inode->i_fop = fops ? fops : &simple_dir_operations;
- inode->i_private = data;
+ inode->i_fop = &simple_dir_operations;
+ inode->i_private = NULL;
/* directory inodes start off with i_nlink == 2
* (for "." entry) */
@@ -91,13 +90,12 @@
return error;
}
-static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode,
- void *data, const struct file_operations *fops)
+static int debugfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int res;
mode = (mode & (S_IRWXUGO | S_ISVTX)) | S_IFDIR;
- res = debugfs_mknod(dir, dentry, mode, 0, data, fops);
+ res = debugfs_mknod(dir, dentry, mode, 0, NULL, NULL);
if (!res) {
inc_nlink(dir);
fsnotify_mkdir(dir, dentry);
@@ -106,10 +104,10 @@
}
static int debugfs_link(struct inode *dir, struct dentry *dentry, umode_t mode,
- void *data, const struct file_operations *fops)
+ void *data)
{
mode = (mode & S_IALLUGO) | S_IFLNK;
- return debugfs_mknod(dir, dentry, mode, 0, data, fops);
+ return debugfs_mknod(dir, dentry, mode, 0, data, NULL);
}
static int debugfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
@@ -293,13 +291,19 @@
.kill_sb = kill_litter_super,
};
-static int debugfs_create_by_name(const char *name, umode_t mode,
- struct dentry *parent,
- struct dentry **dentry,
- void *data,
- const struct file_operations *fops)
+struct dentry *__create_file(const char *name, umode_t mode,
+ struct dentry *parent, void *data,
+ const struct file_operations *fops)
{
- int error = 0;
+ struct dentry *dentry = NULL;
+ int error;
+
+ pr_debug("debugfs: creating file '%s'\n",name);
+
+ error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
+ &debugfs_mount_count);
+ if (error)
+ goto exit;
/* If the parent is not specified, we create it in the root.
* We need the root dentry to do this, which is in the super
@@ -309,30 +313,35 @@
if (!parent)
parent = debugfs_mount->mnt_root;
- *dentry = NULL;
+ dentry = NULL;
mutex_lock(&parent->d_inode->i_mutex);
- *dentry = lookup_one_len(name, parent, strlen(name));
- if (!IS_ERR(*dentry)) {
+ dentry = lookup_one_len(name, parent, strlen(name));
+ if (!IS_ERR(dentry)) {
switch (mode & S_IFMT) {
case S_IFDIR:
- error = debugfs_mkdir(parent->d_inode, *dentry, mode,
- data, fops);
+ error = debugfs_mkdir(parent->d_inode, dentry, mode);
+
break;
case S_IFLNK:
- error = debugfs_link(parent->d_inode, *dentry, mode,
- data, fops);
+ error = debugfs_link(parent->d_inode, dentry, mode,
+ data);
break;
default:
- error = debugfs_create(parent->d_inode, *dentry, mode,
+ error = debugfs_create(parent->d_inode, dentry, mode,
data, fops);
break;
}
- dput(*dentry);
+ dput(dentry);
} else
- error = PTR_ERR(*dentry);
+ error = PTR_ERR(dentry);
mutex_unlock(&parent->d_inode->i_mutex);
- return error;
+ if (error) {
+ dentry = NULL;
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ }
+exit:
+ return dentry;
}
/**
@@ -365,25 +374,15 @@
struct dentry *parent, void *data,
const struct file_operations *fops)
{
- struct dentry *dentry = NULL;
- int error;
-
- pr_debug("debugfs: creating file '%s'\n",name);
-
- error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
- &debugfs_mount_count);
- if (error)
- goto exit;
-
- error = debugfs_create_by_name(name, mode, parent, &dentry,
- data, fops);
- if (error) {
- dentry = NULL;
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
- goto exit;
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ case 0:
+ break;
+ default:
+ BUG();
}
-exit:
- return dentry;
+
+ return __create_file(name, mode, parent, data, fops);
}
EXPORT_SYMBOL_GPL(debugfs_create_file);
@@ -407,8 +406,7 @@
*/
struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
{
- return debugfs_create_file(name,
- S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+ return __create_file(name, S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
parent, NULL, NULL);
}
EXPORT_SYMBOL_GPL(debugfs_create_dir);
@@ -446,8 +444,7 @@
if (!link)
return NULL;
- result = debugfs_create_file(name, S_IFLNK | S_IRWXUGO, parent, link,
- NULL);
+ result = __create_file(name, S_IFLNK | S_IRWXUGO, parent, link, NULL);
if (!result)
kfree(link);
return result;
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 979c1e3..14afbab 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -439,15 +439,15 @@
return ERR_PTR(error);
if (opts.newinstance)
- s = sget(fs_type, NULL, set_anon_super, NULL);
+ s = sget(fs_type, NULL, set_anon_super, flags, NULL);
else
- s = sget(fs_type, compare_init_pts_sb, set_anon_super, NULL);
+ s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags,
+ NULL);
if (IS_ERR(s))
return ERR_CAST(s);
if (!s->s_root) {
- s->s_flags = flags;
error = devpts_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error)
goto out_undo_sget;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0c85fae..1faf4cb 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1258,7 +1258,7 @@
*/
BUG_ON(retval == -EIOCBQUEUED);
if (dio->is_async && retval == 0 && dio->result &&
- ((rw & READ) || (dio->result == sdio.size)))
+ ((rw == READ) || (dio->result == sdio.size)))
retval = -EIOCBQUEUED;
if (retval != -EIOCBQUEUED)
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 534c1d4..1b5d9af 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -32,7 +32,7 @@
/**
* ecryptfs_d_revalidate - revalidate an ecryptfs dentry
* @dentry: The ecryptfs dentry
- * @nd: The associated nameidata
+ * @flags: lookup flags
*
* Called when the VFS needs to revalidate a dentry. This
* is called whenever a name lookup finds a dentry in the
@@ -42,32 +42,20 @@
* Returns 1 if valid, 0 otherwise.
*
*/
-static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *lower_dentry;
struct vfsmount *lower_mnt;
- struct dentry *dentry_save = NULL;
- struct vfsmount *vfsmount_save = NULL;
int rc = 1;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
goto out;
- if (nd) {
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
- }
- rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
- if (nd) {
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
- }
+ rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags);
if (dentry->d_inode) {
struct inode *lower_inode =
ecryptfs_inode_to_lower(dentry->d_inode);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a07441a..da52cdb 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -173,7 +173,7 @@
inode = ERR_CAST(lower_dir_dentry);
goto out;
}
- rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, NULL);
+ rc = vfs_create(lower_dir_dentry->d_inode, lower_dentry, mode, true);
if (rc) {
printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
"rc = [%d]\n", __func__, rc);
@@ -240,7 +240,6 @@
* @dir: The inode of the directory in which to create the file.
* @dentry: The eCryptfs dentry
* @mode: The mode of the new file.
- * @nd: nameidata
*
* Creates a new file.
*
@@ -248,7 +247,7 @@
*/
static int
ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct inode *ecryptfs_inode;
int rc;
@@ -374,7 +373,7 @@
*/
static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
struct dentry *ecryptfs_dentry,
- struct nameidata *ecryptfs_nd)
+ unsigned int flags)
{
char *encrypted_and_encoded_name = NULL;
size_t encrypted_and_encoded_name_size;
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 69f994a..0dbe58a 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -149,7 +149,7 @@
(*lower_file) = dentry_open(lower_dentry, lower_mnt, flags, cred);
if (!IS_ERR(*lower_file))
goto out;
- if (flags & O_RDONLY) {
+ if ((flags & O_ACCMODE) == O_RDONLY) {
rc = PTR_ERR((*lower_file));
goto out;
}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 6895493..7edeb3d 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -499,13 +499,12 @@
goto out;
}
- s = sget(fs_type, NULL, set_anon_super, NULL);
+ s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s)) {
rc = PTR_ERR(s);
goto out;
}
- s->s_flags = flags;
rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs", BDI_CAP_MAP_COPY);
if (rc)
goto out1;
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 3a06f40..c0038f6 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -49,7 +49,10 @@
mutex_lock(&ecryptfs_daemon_hash_mux);
/* TODO: Just use file->private_data? */
rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
- BUG_ON(rc || !daemon);
+ if (rc || !daemon) {
+ mutex_unlock(&ecryptfs_daemon_hash_mux);
+ return -EINVAL;
+ }
mutex_lock(&daemon->mux);
mutex_unlock(&ecryptfs_daemon_hash_mux);
if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
@@ -122,6 +125,7 @@
goto out_unlock_daemon;
}
daemon->flags |= ECRYPTFS_DAEMON_MISCDEV_OPEN;
+ file->private_data = daemon;
atomic_inc(&ecryptfs_num_miscdev_opens);
out_unlock_daemon:
mutex_unlock(&daemon->mux);
@@ -152,9 +156,9 @@
mutex_lock(&ecryptfs_daemon_hash_mux);
rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
- BUG_ON(rc || !daemon);
+ if (rc || !daemon)
+ daemon = file->private_data;
mutex_lock(&daemon->mux);
- BUG_ON(daemon->pid != task_pid(current));
BUG_ON(!(daemon->flags & ECRYPTFS_DAEMON_MISCDEV_OPEN));
daemon->flags &= ~ECRYPTFS_DAEMON_MISCDEV_OPEN;
atomic_dec(&ecryptfs_num_miscdev_opens);
@@ -191,31 +195,32 @@
struct ecryptfs_msg_ctx *msg_ctx, u8 msg_type,
u16 msg_flags, struct ecryptfs_daemon *daemon)
{
- int rc = 0;
+ struct ecryptfs_message *msg;
- mutex_lock(&msg_ctx->mux);
- msg_ctx->msg = kmalloc((sizeof(*msg_ctx->msg) + data_size),
- GFP_KERNEL);
- if (!msg_ctx->msg) {
- rc = -ENOMEM;
+ msg = kmalloc((sizeof(*msg) + data_size), GFP_KERNEL);
+ if (!msg) {
printk(KERN_ERR "%s: Out of memory whilst attempting "
"to kmalloc(%zd, GFP_KERNEL)\n", __func__,
- (sizeof(*msg_ctx->msg) + data_size));
- goto out_unlock;
+ (sizeof(*msg) + data_size));
+ return -ENOMEM;
}
+
+ mutex_lock(&msg_ctx->mux);
+ msg_ctx->msg = msg;
msg_ctx->msg->index = msg_ctx->index;
msg_ctx->msg->data_len = data_size;
msg_ctx->type = msg_type;
memcpy(msg_ctx->msg->data, data, data_size);
msg_ctx->msg_size = (sizeof(*msg_ctx->msg) + data_size);
- mutex_lock(&daemon->mux);
list_add_tail(&msg_ctx->daemon_out_list, &daemon->msg_ctx_out_queue);
+ mutex_unlock(&msg_ctx->mux);
+
+ mutex_lock(&daemon->mux);
daemon->num_queued_msg_ctx++;
wake_up_interruptible(&daemon->wait);
mutex_unlock(&daemon->mux);
-out_unlock:
- mutex_unlock(&msg_ctx->mux);
- return rc;
+
+ return 0;
}
/*
@@ -269,8 +274,16 @@
mutex_lock(&ecryptfs_daemon_hash_mux);
/* TODO: Just use file->private_data? */
rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns());
- BUG_ON(rc || !daemon);
+ if (rc || !daemon) {
+ mutex_unlock(&ecryptfs_daemon_hash_mux);
+ return -EINVAL;
+ }
mutex_lock(&daemon->mux);
+ if (task_pid(current) != daemon->pid) {
+ mutex_unlock(&daemon->mux);
+ mutex_unlock(&ecryptfs_daemon_hash_mux);
+ return -EPERM;
+ }
if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) {
rc = 0;
mutex_unlock(&ecryptfs_daemon_hash_mux);
@@ -307,9 +320,6 @@
* message from the queue; try again */
goto check_list;
}
- BUG_ON(euid != daemon->euid);
- BUG_ON(current_user_ns() != daemon->user_ns);
- BUG_ON(task_pid(current) != daemon->pid);
msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue,
struct ecryptfs_msg_ctx, daemon_out_list);
BUG_ON(!msg_ctx);
diff --git a/fs/efs/efs.h b/fs/efs/efs.h
index d8305b5..5528926 100644
--- a/fs/efs/efs.h
+++ b/fs/efs/efs.h
@@ -129,7 +129,7 @@
extern efs_block_t efs_map_block(struct inode *, efs_block_t);
extern int efs_get_block(struct inode *, sector_t, struct buffer_head *, int);
-extern struct dentry *efs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *efs_lookup(struct inode *, struct dentry *, unsigned int);
extern struct dentry *efs_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type);
extern struct dentry *efs_fh_to_parent(struct super_block *sb, struct fid *fid,
diff --git a/fs/efs/namei.c b/fs/efs/namei.c
index 832b10d..96f66d2 100644
--- a/fs/efs/namei.c
+++ b/fs/efs/namei.c
@@ -58,7 +58,8 @@
return(0);
}
-struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) {
+struct dentry *efs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
efs_ino_t inodenum;
struct inode *inode = NULL;
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
index fc7161d..4731fd9 100644
--- a/fs/exofs/namei.c
+++ b/fs/exofs/namei.c
@@ -46,7 +46,7 @@
}
static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode;
ino_t ino;
@@ -60,7 +60,7 @@
}
static int exofs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode = exofs_new_inode(dir, mode);
int err = PTR_ERR(inode);
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index b0201ca..b42063c 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -44,13 +44,14 @@
{
struct dentry *dentry, *toput = NULL;
struct inode *inode;
+ struct hlist_node *p;
if (acceptable(context, result))
return result;
inode = result->d_inode;
spin_lock(&inode->i_lock);
- list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
dget(dentry);
spin_unlock(&inode->i_lock);
if (toput)
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index f663a67..9ba7de0 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -55,7 +55,7 @@
* Methods themselves.
*/
-static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext2_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode;
ino_t ino;
@@ -94,7 +94,7 @@
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
-static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd)
+static int ext2_create (struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
{
struct inode *inode;
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index eeb63df..85286db 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -1011,7 +1011,7 @@
return NULL;
}
-static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode;
struct ext3_dir_entry_2 * de;
@@ -1690,7 +1690,7 @@
* with d_instantiate().
*/
static int ext3_create (struct inode * dir, struct dentry * dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
handle_t *handle;
struct inode * inode;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index bb6c7d8..2a1dcea 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -135,14 +135,7 @@
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
- dentry = NULL;
- spin_lock(&inode->i_lock);
- if (!list_empty(&inode->i_dentry)) {
- dentry = list_first_entry(&inode->i_dentry,
- struct dentry, d_alias);
- dget(dentry);
- }
- spin_unlock(&inode->i_lock);
+ dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(dentry->d_parent->d_inode);
@@ -232,7 +225,7 @@
if (!journal) {
ret = __sync_inode(inode, datasync);
- if (!ret && !list_empty(&inode->i_dentry))
+ if (!ret && !hlist_empty(&inode->i_dentry))
ret = ext4_sync_parent(inode);
goto out;
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5845cd9..eca3e48 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1312,7 +1312,7 @@
return NULL;
}
-static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct ext4_dir_entry_2 *de;
@@ -2091,7 +2091,7 @@
* with d_instantiate().
*/
static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
handle_t *handle;
struct inode *inode;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index a3d81eb..0038b32 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -738,22 +738,21 @@
fat_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent)
{
int len = *lenp;
- u32 ipos_h, ipos_m, ipos_l;
+ struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+ loff_t i_pos;
if (len < 5) {
*lenp = 5;
return 255; /* no room */
}
- ipos_h = MSDOS_I(inode)->i_pos >> 8;
- ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
- ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28;
+ i_pos = fat_i_pos_read(sbi, inode);
*lenp = 5;
fh[0] = inode->i_ino;
fh[1] = inode->i_generation;
- fh[2] = ipos_h;
- fh[3] = ipos_m | MSDOS_I(inode)->i_logstart;
- fh[4] = ipos_l;
+ fh[2] = i_pos >> 8;
+ fh[3] = ((i_pos & 0xf0) << 24) | MSDOS_I(inode)->i_logstart;
+ fh[4] = (i_pos & 0x0f) << 28;
if (parent)
fh[4] |= MSDOS_I(parent)->i_logstart;
return 3;
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index c5938c9..70d993a 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -201,7 +201,7 @@
/***** Get inode using directory and name */
static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct fat_slot_info sinfo;
@@ -265,7 +265,7 @@
/***** Create a file */
static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode = NULL;
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 98ae804..6cc4806 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -41,9 +41,9 @@
return ret;
}
-static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate(struct dentry *dentry, unsigned int flags)
{
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
/* This is not negative dentry. Always valid. */
@@ -52,9 +52,9 @@
return vfat_revalidate_shortname(dentry);
}
-static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
+static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags)
{
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
/*
@@ -74,7 +74,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -82,7 +82,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
return vfat_revalidate_shortname(dentry);
@@ -714,7 +714,7 @@
}
static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct super_block *sb = dir->i_sb;
struct fat_slot_info sinfo;
@@ -772,7 +772,7 @@
}
static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct super_block *sb = dir->i_sb;
struct inode *inode;
diff --git a/fs/file_table.c b/fs/file_table.c
index a305d9e..9ace278 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -483,10 +483,8 @@
{
struct file *f;
-retry:
lg_global_lock(&files_lglock);
do_file_list_for_each_entry(sb, f) {
- struct vfsmount *mnt;
if (!S_ISREG(f->f_path.dentry->d_inode->i_mode))
continue;
if (!file_count(f))
@@ -499,12 +497,7 @@
if (file_check_writeable(f) != 0)
continue;
file_release_write(f);
- mnt = mntget(f->f_path.mnt);
- /* This can sleep, so we can't hold the spinlock. */
- lg_global_unlock(&files_lglock);
- mnt_drop_write(mnt);
- mntput(mnt);
- goto retry;
+ mnt_drop_write_file(f);
} while_file_list_for_each_entry;
lg_global_unlock(&files_lglock);
}
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index 3360f1e..bd447e8 100644
--- a/fs/freevxfs/vxfs_lookup.c
+++ b/fs/freevxfs/vxfs_lookup.c
@@ -48,7 +48,7 @@
#define VXFS_BLOCK_PER_PAGE(sbp) ((PAGE_CACHE_SIZE / (sbp)->s_blocksize))
-static struct dentry * vxfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry * vxfs_lookup(struct inode *, struct dentry *, unsigned int);
static int vxfs_readdir(struct file *, void *, filldir_t);
const struct inode_operations vxfs_dir_inode_ops = {
@@ -203,7 +203,7 @@
* in the return pointer.
*/
static struct dentry *
-vxfs_lookup(struct inode *dip, struct dentry *dp, struct nameidata *nd)
+vxfs_lookup(struct inode *dip, struct dentry *dp, unsigned int flags)
{
struct inode *ip = NULL;
ino_t ino;
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index e159e68..5df4775 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -6,18 +6,6 @@
#include <linux/fs_struct.h>
#include "internal.h"
-static inline void path_get_longterm(struct path *path)
-{
- path_get(path);
- mnt_make_longterm(path->mnt);
-}
-
-static inline void path_put_longterm(struct path *path)
-{
- mnt_make_shortterm(path->mnt);
- path_put(path);
-}
-
/*
* Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
* It can block.
@@ -26,7 +14,7 @@
{
struct path old_root;
- path_get_longterm(path);
+ path_get(path);
spin_lock(&fs->lock);
write_seqcount_begin(&fs->seq);
old_root = fs->root;
@@ -34,7 +22,7 @@
write_seqcount_end(&fs->seq);
spin_unlock(&fs->lock);
if (old_root.dentry)
- path_put_longterm(&old_root);
+ path_put(&old_root);
}
/*
@@ -45,7 +33,7 @@
{
struct path old_pwd;
- path_get_longterm(path);
+ path_get(path);
spin_lock(&fs->lock);
write_seqcount_begin(&fs->seq);
old_pwd = fs->pwd;
@@ -54,7 +42,7 @@
spin_unlock(&fs->lock);
if (old_pwd.dentry)
- path_put_longterm(&old_pwd);
+ path_put(&old_pwd);
}
static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
@@ -84,7 +72,7 @@
write_seqcount_end(&fs->seq);
while (hits--) {
count++;
- path_get_longterm(new_root);
+ path_get(new_root);
}
spin_unlock(&fs->lock);
}
@@ -92,13 +80,13 @@
} while_each_thread(g, p);
read_unlock(&tasklist_lock);
while (count--)
- path_put_longterm(old_root);
+ path_put(old_root);
}
void free_fs_struct(struct fs_struct *fs)
{
- path_put_longterm(&fs->root);
- path_put_longterm(&fs->pwd);
+ path_put(&fs->root);
+ path_put(&fs->pwd);
kmem_cache_free(fs_cachep, fs);
}
@@ -132,9 +120,9 @@
spin_lock(&old->lock);
fs->root = old->root;
- path_get_longterm(&fs->root);
+ path_get(&fs->root);
fs->pwd = old->pwd;
- path_get_longterm(&fs->pwd);
+ path_get(&fs->pwd);
spin_unlock(&old->lock);
}
return fs;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 334e0b1..8964cf3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -154,7 +154,7 @@
* the lookup once more. If the lookup results in the same inode,
* then refresh the attributes, timeouts and mark the dentry valid.
*/
-static int fuse_dentry_revalidate(struct dentry *entry, struct nameidata *nd)
+static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
{
struct inode *inode;
@@ -174,7 +174,7 @@
if (!inode)
return 0;
- if (nd && (nd->flags & LOOKUP_RCU))
+ if (flags & LOOKUP_RCU)
return -ECHILD;
fc = get_fuse_conn(inode);
@@ -249,7 +249,7 @@
/* This tries to shrink the subtree below alias */
fuse_invalidate_entry(alias);
dput(alias);
- if (!list_empty(&inode->i_dentry))
+ if (!hlist_empty(&inode->i_dentry))
return ERR_PTR(-EBUSY);
} else {
dput(alias);
@@ -316,7 +316,7 @@
}
static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
- struct nameidata *nd)
+ unsigned int flags)
{
int err;
struct fuse_entry_out outarg;
@@ -370,7 +370,8 @@
* 'mknod' + 'open' requests.
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
- umode_t mode, struct nameidata *nd)
+ struct file *file, unsigned flags,
+ umode_t mode, int *opened)
{
int err;
struct inode *inode;
@@ -381,15 +382,11 @@
struct fuse_open_out outopen;
struct fuse_entry_out outentry;
struct fuse_file *ff;
- struct file *file;
- int flags = nd->intent.open.flags;
-
- if (fc->no_create)
- return -ENOSYS;
forget = fuse_alloc_forget();
+ err = -ENOMEM;
if (!forget)
- return -ENOMEM;
+ goto out_err;
req = fuse_get_req(fc);
err = PTR_ERR(req);
@@ -428,11 +425,8 @@
req->out.args[1].value = &outopen;
fuse_request_send(fc, req);
err = req->out.h.error;
- if (err) {
- if (err == -ENOSYS)
- fc->no_create = 1;
+ if (err)
goto out_free_ff;
- }
err = -EIO;
if (!S_ISREG(outentry.attr.mode) || invalid_nodeid(outentry.nodeid))
@@ -448,28 +442,74 @@
flags &= ~(O_CREAT | O_EXCL | O_TRUNC);
fuse_sync_release(ff, flags);
fuse_queue_forget(fc, forget, outentry.nodeid, 1);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto out_err;
}
kfree(forget);
d_instantiate(entry, inode);
fuse_change_entry_timeout(entry, &outentry);
fuse_invalidate_attr(dir);
- file = lookup_instantiate_filp(nd, entry, generic_file_open);
- if (IS_ERR(file)) {
+ err = finish_open(file, entry, generic_file_open, opened);
+ if (err) {
fuse_sync_release(ff, flags);
- return PTR_ERR(file);
+ } else {
+ file->private_data = fuse_file_get(ff);
+ fuse_finish_open(inode, file);
}
- file->private_data = fuse_file_get(ff);
- fuse_finish_open(inode, file);
- return 0;
-
- out_free_ff:
- fuse_file_free(ff);
- out_put_request:
- fuse_put_request(fc, req);
- out_put_forget_req:
- kfree(forget);
return err;
+
+out_free_ff:
+ fuse_file_free(ff);
+out_put_request:
+ fuse_put_request(fc, req);
+out_put_forget_req:
+ kfree(forget);
+out_err:
+ return err;
+}
+
+static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
+static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
+ struct file *file, unsigned flags,
+ umode_t mode, int *opened)
+{
+ int err;
+ struct fuse_conn *fc = get_fuse_conn(dir);
+ struct dentry *res = NULL;
+
+ if (d_unhashed(entry)) {
+ res = fuse_lookup(dir, entry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ entry = res;
+ }
+
+ if (!(flags & O_CREAT) || entry->d_inode)
+ goto no_open;
+
+ /* Only creates */
+ *opened |= FILE_CREATED;
+
+ if (fc->no_create)
+ goto mknod;
+
+ err = fuse_create_open(dir, entry, file, flags, mode, opened);
+ if (err == -ENOSYS) {
+ fc->no_create = 1;
+ goto mknod;
+ }
+out_dput:
+ dput(res);
+ return err;
+
+mknod:
+ err = fuse_mknod(dir, entry, mode, 0);
+ if (err)
+ goto out_dput;
+no_open:
+ return finish_no_open(file, res);
}
/*
@@ -571,14 +611,8 @@
}
static int fuse_create(struct inode *dir, struct dentry *entry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
- if (nd) {
- int err = fuse_create_open(dir, entry, mode, nd);
- if (err != -ENOSYS)
- return err;
- /* Fall back on mknod */
- }
return fuse_mknod(dir, entry, mode, 0);
}
@@ -1646,6 +1680,7 @@
.link = fuse_link,
.setattr = fuse_setattr,
.create = fuse_create,
+ .atomic_open = fuse_atomic_open,
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 0da8da2..4fddb3c 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -25,7 +25,7 @@
/**
* gfs2_drevalidate - Check directory lookup consistency
* @dentry: the mapping to check
- * @nd:
+ * @flags: lookup flags
*
* Check to make sure the lookup necessary to arrive at this inode from its
* parent is still good.
@@ -33,7 +33,7 @@
* Returns: 1 if the dentry is ok, 0 if it isn't
*/
-static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
+static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *parent;
struct gfs2_sbd *sdp;
@@ -44,7 +44,7 @@
int error;
int had_lock = 0;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index a9ba244..8676747 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -755,11 +755,8 @@
*/
static int gfs2_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
- int excl = 0;
- if (nd && (nd->flags & LOOKUP_EXCL))
- excl = 1;
return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
}
@@ -775,7 +772,7 @@
*/
static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = gfs2_lookupi(dir, &dentry->d_name, 0);
if (inode && !IS_ERR(inode)) {
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index b8c250f..6c90607 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1286,7 +1286,7 @@
error = -EBUSY;
goto error_bdev;
}
- s = sget(fs_type, test_gfs2_super, set_gfs2_super, bdev);
+ s = sget(fs_type, test_gfs2_super, set_gfs2_super, flags, bdev);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
error = PTR_ERR(s);
if (IS_ERR(s))
@@ -1316,7 +1316,6 @@
} else {
char b[BDEVNAME_SIZE];
- s->s_flags = flags;
s->s_mode = mode;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(bdev));
@@ -1360,7 +1359,7 @@
dev_name, error);
return ERR_PTR(error);
}
- s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super,
+ s = sget(&gfs2_fs_type, test_gfs2_super, set_meta_super, flags,
path.dentry->d_inode->i_sb->s_bdev);
path_put(&path);
if (IS_ERR(s)) {
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 62fc14e..422dde2 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -18,7 +18,7 @@
* hfs_lookup()
*/
static struct dentry *hfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
hfs_cat_rec rec;
struct hfs_find_data fd;
@@ -187,7 +187,7 @@
* the directory and the name (and its length) of the new file.
*/
static int hfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
int res;
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 761ec06..451c972 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -489,7 +489,7 @@
}
static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
hfs_cat_rec rec;
diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c
index 19cf291..91b91fd 100644
--- a/fs/hfs/sysdep.c
+++ b/fs/hfs/sysdep.c
@@ -13,12 +13,12 @@
/* dentry case-handling: just lowercase everything */
-static int hfs_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
+static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
int diff;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 26b53fb..378ea0c 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -25,7 +25,7 @@
/* Find the entry inside dir named dentry->d_name */
static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct hfs_find_data fd;
@@ -465,7 +465,7 @@
}
static int hfsplus_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return hfsplus_mknod(dir, dentry, mode, 0);
}
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 82b69ee..7009265 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -168,7 +168,7 @@
};
static struct dentry *hfsplus_file_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct hfs_find_data fd;
struct super_block *sb = dir->i_sb;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2afa5bb..1241465 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -553,7 +553,7 @@
}
int hostfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
char *name;
@@ -595,7 +595,7 @@
}
struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode;
char *name;
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index b8472f8..78e12b2 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -189,7 +189,7 @@
* to tell read_inode to read fnode or not.
*/
-struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index c07ef1f..ac1ead1 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -220,7 +220,7 @@
/* dir.c */
-struct dentry *hpfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int);
extern const struct file_operations hpfs_dir_ops;
/* dnode.c */
diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c
index 9083ef8..bc90824 100644
--- a/fs/hpfs/namei.c
+++ b/fs/hpfs/namei.c
@@ -115,7 +115,7 @@
return err;
}
-static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
const unsigned char *name = dentry->d_name.name;
unsigned len = dentry->d_name.len;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index d4f93b5..e5c0653 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -138,7 +138,7 @@
}
static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *proc_dentry, *parent;
struct qstr *name = &dentry->d_name;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cc9281b..e13e9bd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -565,7 +565,7 @@
return retval;
}
-static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
diff --git a/fs/inode.c b/fs/inode.c
index c99163b..775cbab 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -182,7 +182,7 @@
}
inode->i_private = NULL;
inode->i_mapping = mapping;
- INIT_LIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
+ INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
#ifdef CONFIG_FS_POSIX_ACL
inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif
diff --git a/fs/internal.h b/fs/internal.h
index 18bc216..8a9f5fa 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -50,8 +50,6 @@
extern struct vfsmount *lookup_mnt(struct path *);
extern int finish_automount(struct vfsmount *, struct path *);
-extern void mnt_make_longterm(struct vfsmount *);
-extern void mnt_make_shortterm(struct vfsmount *);
extern int sb_prepare_remount_readonly(struct super_block *);
extern void __init mnt_init(void);
@@ -84,9 +82,6 @@
/*
* open.c
*/
-struct nameidata;
-extern struct file *nameidata_to_filp(struct nameidata *);
-extern void release_open_intent(struct nameidata *);
struct open_flags {
int open_flag;
umode_t mode;
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 0e73f63..3620ad1 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -114,7 +114,7 @@
int get_joliet_filename(struct iso_directory_record *, unsigned char *, struct inode *);
int get_acorn_filename(struct iso_directory_record *, char *, struct inode *);
-extern struct dentry *isofs_lookup(struct inode *, struct dentry *, struct nameidata *);
+extern struct dentry *isofs_lookup(struct inode *, struct dentry *, unsigned int flags);
extern struct buffer_head *isofs_bread(struct inode *, sector_t);
extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long);
diff --git a/fs/isofs/namei.c b/fs/isofs/namei.c
index 1e2946f..c167028 100644
--- a/fs/isofs/namei.c
+++ b/fs/isofs/namei.c
@@ -163,7 +163,7 @@
return 0;
}
-struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *isofs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
int found;
unsigned long uninitialized_var(block);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index b560188..2324519 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -25,9 +25,9 @@
static int jffs2_readdir (struct file *, void *, filldir_t);
static int jffs2_create (struct inode *,struct dentry *,umode_t,
- struct nameidata *);
+ bool);
static struct dentry *jffs2_lookup (struct inode *,struct dentry *,
- struct nameidata *);
+ unsigned int);
static int jffs2_link (struct dentry *,struct inode *,struct dentry *);
static int jffs2_unlink (struct inode *,struct dentry *);
static int jffs2_symlink (struct inode *,struct dentry *,const char *);
@@ -74,7 +74,7 @@
nice and simple
*/
static struct dentry *jffs2_lookup(struct inode *dir_i, struct dentry *target,
- struct nameidata *nd)
+ unsigned int flags)
{
struct jffs2_inode_info *dir_f;
struct jffs2_full_dirent *fd = NULL, *fd_list;
@@ -175,7 +175,7 @@
static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct jffs2_raw_inode *ri;
struct jffs2_inode_info *f, *dir_f;
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 07c91ca..c426293 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -73,7 +73,7 @@
*
*/
static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int rc = 0;
tid_t tid; /* transaction id */
@@ -1436,7 +1436,7 @@
return rc;
}
-static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *jfs_lookup(struct inode *dip, struct dentry *dentry, unsigned int flags)
{
struct btstack btstack;
ino_t inum;
@@ -1570,7 +1570,7 @@
return result;
}
-static int jfs_ci_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags)
{
/*
* This is not negative dentry. Always valid.
@@ -1589,7 +1589,7 @@
* This may be nfsd (or something), anyway, we can't see the
* intent of this. So, since this can be for creation, drop it.
*/
- if (!nd)
+ if (!flags)
return 0;
/*
@@ -1597,7 +1597,7 @@
* case sensitive name which is specified by user if this is
* for creation.
*/
- if (nd->flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
+ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
return 0;
return 1;
}
diff --git a/fs/libfs.c b/fs/libfs.c
index f86ec27..a74cb17 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -53,7 +53,7 @@
* Lookup the data. This is trivial - if the dentry didn't already
* exist, we know it is negative. Set d_op to delete negative dentries.
*/
-struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
static const struct dentry_operations simple_dentry_operations = {
.d_delete = simple_delete_dentry,
@@ -222,15 +222,15 @@
const struct super_operations *ops,
const struct dentry_operations *dops, unsigned long magic)
{
- struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
+ struct super_block *s;
struct dentry *dentry;
struct inode *root;
struct qstr d_name = QSTR_INIT(name, strlen(name));
+ s = sget(fs_type, NULL, set_anon_super, MS_NOUSER, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
- s->s_flags = MS_NOUSER;
s->s_maxbytes = MAX_LFS_FILESIZE;
s->s_blocksize = PAGE_SIZE;
s->s_blocksize_bits = PAGE_SHIFT;
diff --git a/fs/locks.c b/fs/locks.c
index 814c51d..fce6238 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1465,7 +1465,7 @@
case F_WRLCK:
return generic_add_lease(filp, arg, flp);
default:
- BUG();
+ return -EINVAL;
}
}
EXPORT_SYMBOL(generic_setlease);
diff --git a/fs/logfs/dir.c b/fs/logfs/dir.c
index bea5d1b..26e4a94 100644
--- a/fs/logfs/dir.c
+++ b/fs/logfs/dir.c
@@ -349,7 +349,7 @@
}
static struct dentry *logfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct page *page;
struct logfs_disk_dentry *dd;
@@ -502,7 +502,7 @@
}
static int logfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
diff --git a/fs/logfs/super.c b/fs/logfs/super.c
index 97bca62..345c24b 100644
--- a/fs/logfs/super.c
+++ b/fs/logfs/super.c
@@ -519,7 +519,7 @@
log_super("LogFS: Start mount %x\n", mount_count++);
err = -EINVAL;
- sb = sget(type, logfs_sb_test, logfs_sb_set, super);
+ sb = sget(type, logfs_sb_test, logfs_sb_set, flags | MS_NOATIME, super);
if (IS_ERR(sb)) {
super->s_devops->put_device(super);
kfree(super);
@@ -542,7 +542,6 @@
sb->s_maxbytes = (1ull << 43) - 1;
sb->s_max_links = LOGFS_LINK_MAX;
sb->s_op = &logfs_super_operations;
- sb->s_flags = flags | MS_NOATIME;
err = logfs_read_sb(sb, sb->s_flags & MS_RDONLY);
if (err)
diff --git a/fs/minix/namei.c b/fs/minix/namei.c
index 2d0ee17..0db73d9 100644
--- a/fs/minix/namei.c
+++ b/fs/minix/namei.c
@@ -18,7 +18,7 @@
return err;
}
-static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *minix_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -55,7 +55,7 @@
}
static int minix_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return minix_mknod(dir, dentry, mode, 0);
}
diff --git a/fs/mount.h b/fs/mount.h
index 4ef36d9..4f291f9 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -22,7 +22,6 @@
struct vfsmount mnt;
#ifdef CONFIG_SMP
struct mnt_pcp __percpu *mnt_pcp;
- atomic_t mnt_longterm; /* how many of the refs are longterm */
#else
int mnt_count;
int mnt_writers;
@@ -49,6 +48,8 @@
int mnt_ghosts;
};
+#define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
+
static inline struct mount *real_mount(struct vfsmount *mnt)
{
return container_of(mnt, struct mount, mnt);
@@ -59,6 +60,12 @@
return mnt != mnt->mnt_parent;
}
+static inline int is_mounted(struct vfsmount *mnt)
+{
+ /* neither detached nor internal? */
+ return !IS_ERR_OR_NULL(real_mount(mnt));
+}
+
extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *, int);
static inline void get_mnt_ns(struct mnt_namespace *ns)
@@ -67,10 +74,12 @@
}
struct proc_mounts {
- struct seq_file m; /* must be the first element */
+ struct seq_file m;
struct mnt_namespace *ns;
struct path root;
int (*show)(struct seq_file *, struct vfsmount *);
};
+#define proc_mounts(p) (container_of((p), struct proc_mounts, m))
+
extern const struct seq_operations mounts_op;
diff --git a/fs/namei.c b/fs/namei.c
index 7d69419..c6dcb4c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -463,25 +463,9 @@
return -ECHILD;
}
-/**
- * release_open_intent - free up open intent resources
- * @nd: pointer to nameidata
- */
-void release_open_intent(struct nameidata *nd)
+static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
- struct file *file = nd->intent.open.file;
-
- if (file && !IS_ERR(file)) {
- if (file->f_path.dentry == NULL)
- put_filp(file);
- else
- fput(file);
- }
-}
-
-static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- return dentry->d_op->d_revalidate(dentry, nd);
+ return dentry->d_op->d_revalidate(dentry, flags);
}
/**
@@ -527,7 +511,7 @@
return 0;
/* Note: we do not d_invalidate() */
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
@@ -602,10 +586,25 @@
nd->path.dentry = path->dentry;
}
+/*
+ * Helper to directly jump to a known parsed path from ->follow_link,
+ * caller must have taken a reference to path beforehand.
+ */
+void nd_jump_link(struct nameidata *nd, struct path *path)
+{
+ path_put(&nd->path);
+
+ nd->path = *path;
+ nd->inode = nd->path.dentry->d_inode;
+ nd->flags |= LOOKUP_JUMPED;
+
+ BUG_ON(nd->inode->i_op->follow_link);
+}
+
static inline void put_link(struct nameidata *nd, struct path *link, void *cookie)
{
struct inode *inode = link->dentry->d_inode;
- if (!IS_ERR(cookie) && inode->i_op->put_link)
+ if (inode->i_op->put_link)
inode->i_op->put_link(link->dentry, nd, cookie);
path_put(link);
}
@@ -613,19 +612,19 @@
static __always_inline int
follow_link(struct path *link, struct nameidata *nd, void **p)
{
- int error;
struct dentry *dentry = link->dentry;
+ int error;
+ char *s;
BUG_ON(nd->flags & LOOKUP_RCU);
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
- if (unlikely(current->total_link_count >= 40)) {
- *p = ERR_PTR(-ELOOP); /* no ->put_link(), please */
- path_put(&nd->path);
- return -ELOOP;
- }
+ error = -ELOOP;
+ if (unlikely(current->total_link_count >= 40))
+ goto out_put_nd_path;
+
cond_resched();
current->total_link_count++;
@@ -633,30 +632,28 @@
nd_set_link(nd, NULL);
error = security_inode_follow_link(link->dentry, nd);
- if (error) {
- *p = ERR_PTR(error); /* no ->put_link(), please */
- path_put(&nd->path);
- return error;
- }
+ if (error)
+ goto out_put_nd_path;
nd->last_type = LAST_BIND;
*p = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(*p);
- if (!IS_ERR(*p)) {
- char *s = nd_get_link(nd);
- error = 0;
- if (s)
- error = __vfs_follow_link(nd, s);
- else if (nd->last_type == LAST_BIND) {
- nd->flags |= LOOKUP_JUMPED;
- nd->inode = nd->path.dentry->d_inode;
- if (nd->inode->i_op->follow_link) {
- /* stepped on a _really_ weird one */
- path_put(&nd->path);
- error = -ELOOP;
- }
- }
+ if (IS_ERR(*p))
+ goto out_put_nd_path;
+
+ error = 0;
+ s = nd_get_link(nd);
+ if (s) {
+ error = __vfs_follow_link(nd, s);
+ if (unlikely(error))
+ put_link(nd, link, *p);
}
+
+ return error;
+
+out_put_nd_path:
+ path_put(&nd->path);
+ path_put(link);
return error;
}
@@ -675,6 +672,16 @@
return 1;
}
+/*
+ * follow_up - Find the mountpoint of path's vfsmount
+ *
+ * Given a path, find the mountpoint of its source file system.
+ * Replace @path with the path of the mountpoint in the parent mount.
+ * Up is towards /.
+ *
+ * Return 1 if we went up a level and 0 if we were already at the
+ * root.
+ */
int follow_up(struct path *path)
{
struct mount *mnt = real_mount(path->mnt);
@@ -1048,7 +1055,7 @@
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
- struct nameidata *nd, bool *need_lookup)
+ unsigned int flags, bool *need_lookup)
{
struct dentry *dentry;
int error;
@@ -1059,7 +1066,7 @@
if (d_need_lookup(dentry)) {
*need_lookup = true;
} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
- error = d_revalidate(dentry, nd);
+ error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (error < 0) {
dput(dentry);
@@ -1089,7 +1096,7 @@
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *old;
@@ -1099,7 +1106,7 @@
return ERR_PTR(-ENOENT);
}
- old = dir->i_op->lookup(dir, dentry, nd);
+ old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
dput(dentry);
dentry = old;
@@ -1108,16 +1115,16 @@
}
static struct dentry *__lookup_hash(struct qstr *name,
- struct dentry *base, struct nameidata *nd)
+ struct dentry *base, unsigned int flags)
{
bool need_lookup;
struct dentry *dentry;
- dentry = lookup_dcache(name, base, nd, &need_lookup);
+ dentry = lookup_dcache(name, base, flags, &need_lookup);
if (!need_lookup)
return dentry;
- return lookup_real(base->d_inode, dentry, nd);
+ return lookup_real(base->d_inode, dentry, flags);
}
/*
@@ -1167,7 +1174,7 @@
if (unlikely(d_need_lookup(dentry)))
goto unlazy;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status != -ECHILD)
need_reval = 0;
@@ -1197,7 +1204,7 @@
}
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
- status = d_revalidate(dentry, nd);
+ status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status < 0) {
dput(dentry);
@@ -1236,7 +1243,7 @@
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
- dentry = __lookup_hash(name, parent, nd);
+ dentry = __lookup_hash(name, parent, nd->flags);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
@@ -1383,9 +1390,10 @@
void *cookie;
res = follow_link(&link, nd, &cookie);
- if (!res)
- res = walk_component(nd, path, &nd->last,
- nd->last_type, LOOKUP_FOLLOW);
+ if (res)
+ break;
+ res = walk_component(nd, path, &nd->last,
+ nd->last_type, LOOKUP_FOLLOW);
put_link(nd, &link, cookie);
} while (res > 0);
@@ -1777,8 +1785,9 @@
struct path link = path;
nd->flags |= LOOKUP_PARENT;
err = follow_link(&link, nd, &cookie);
- if (!err)
- err = lookup_last(nd, &path);
+ if (err)
+ break;
+ err = lookup_last(nd, &path);
put_link(nd, &link, cookie);
}
}
@@ -1821,9 +1830,27 @@
return retval;
}
-int kern_path_parent(const char *name, struct nameidata *nd)
+/* does lookup, returns the object with parent locked */
+struct dentry *kern_path_locked(const char *name, struct path *path)
{
- return do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, nd);
+ struct nameidata nd;
+ struct dentry *d;
+ int err = do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, &nd);
+ if (err)
+ return ERR_PTR(err);
+ if (nd.last_type != LAST_NORM) {
+ path_put(&nd.path);
+ return ERR_PTR(-EINVAL);
+ }
+ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ d = lookup_one_len(nd.last.name, nd.path.dentry, nd.last.len);
+ if (IS_ERR(d)) {
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
+ return d;
+ }
+ *path = nd.path;
+ return d;
}
int kern_path(const char *name, unsigned int flags, struct path *path)
@@ -1866,7 +1893,7 @@
*/
static struct dentry *lookup_hash(struct nameidata *nd)
{
- return __lookup_hash(&nd->last, nd->path.dentry, nd);
+ return __lookup_hash(&nd->last, nd->path.dentry, nd->flags);
}
/**
@@ -1913,7 +1940,7 @@
if (err)
return ERR_PTR(err);
- return __lookup_hash(&this, base, NULL);
+ return __lookup_hash(&this, base, 0);
}
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
@@ -2086,10 +2113,9 @@
}
int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool want_excl)
{
int error = may_create(dir, dentry);
-
if (error)
return error;
@@ -2100,7 +2126,7 @@
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
- error = dir->i_op->create(dir, dentry, mode, nd);
+ error = dir->i_op->create(dir, dentry, mode, want_excl);
if (!error)
fsnotify_create(dir, dentry);
return error;
@@ -2187,21 +2213,275 @@
return flag;
}
+static int may_o_create(struct path *dir, struct dentry *dentry, umode_t mode)
+{
+ int error = security_path_mknod(dir, dentry, mode, 0);
+ if (error)
+ return error;
+
+ error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
+ if (error)
+ return error;
+
+ return security_inode_create(dir->dentry->d_inode, dentry, mode);
+}
+
+/*
+ * Attempt to atomically look up, create and open a file from a negative
+ * dentry.
+ *
+ * Returns 0 if successful. The file will have been created and attached to
+ * @file by the filesystem calling finish_open().
+ *
+ * Returns 1 if the file was looked up only or didn't need creating. The
+ * caller will need to perform the open themselves. @path will have been
+ * updated to point to the new dentry. This may be negative.
+ *
+ * Returns an error code otherwise.
+ */
+static int atomic_open(struct nameidata *nd, struct dentry *dentry,
+ struct path *path, struct file *file,
+ const struct open_flags *op,
+ bool *want_write, bool need_lookup,
+ int *opened)
+{
+ struct inode *dir = nd->path.dentry->d_inode;
+ unsigned open_flag = open_to_namei_flags(op->open_flag);
+ umode_t mode;
+ int error;
+ int acc_mode;
+ int create_error = 0;
+ struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
+
+ BUG_ON(dentry->d_inode);
+
+ /* Don't create child dentry for a dead directory. */
+ if (unlikely(IS_DEADDIR(dir))) {
+ error = -ENOENT;
+ goto out;
+ }
+
+ mode = op->mode & S_IALLUGO;
+ if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
+ mode &= ~current_umask();
+
+ if (open_flag & O_EXCL) {
+ open_flag &= ~O_TRUNC;
+ *opened |= FILE_CREATED;
+ }
+
+ /*
+ * Checking write permission is tricky, bacuse we don't know if we are
+ * going to actually need it: O_CREAT opens should work as long as the
+ * file exists. But checking existence breaks atomicity. The trick is
+ * to check access and if not granted clear O_CREAT from the flags.
+ *
+ * Another problem is returing the "right" error value (e.g. for an
+ * O_EXCL open we want to return EEXIST not EROFS).
+ */
+ if ((open_flag & (O_CREAT | O_TRUNC)) ||
+ (open_flag & O_ACCMODE) != O_RDONLY) {
+ error = mnt_want_write(nd->path.mnt);
+ if (!error) {
+ *want_write = true;
+ } else if (!(open_flag & O_CREAT)) {
+ /*
+ * No O_CREATE -> atomicity not a requirement -> fall
+ * back to lookup + open
+ */
+ goto no_open;
+ } else if (open_flag & (O_EXCL | O_TRUNC)) {
+ /* Fall back and fail with the right error */
+ create_error = error;
+ goto no_open;
+ } else {
+ /* No side effects, safe to clear O_CREAT */
+ create_error = error;
+ open_flag &= ~O_CREAT;
+ }
+ }
+
+ if (open_flag & O_CREAT) {
+ error = may_o_create(&nd->path, dentry, op->mode);
+ if (error) {
+ create_error = error;
+ if (open_flag & O_EXCL)
+ goto no_open;
+ open_flag &= ~O_CREAT;
+ }
+ }
+
+ if (nd->flags & LOOKUP_DIRECTORY)
+ open_flag |= O_DIRECTORY;
+
+ file->f_path.dentry = DENTRY_NOT_SET;
+ file->f_path.mnt = nd->path.mnt;
+ error = dir->i_op->atomic_open(dir, dentry, file, open_flag, mode,
+ opened);
+ if (error < 0) {
+ if (create_error && error == -ENOENT)
+ error = create_error;
+ goto out;
+ }
+
+ acc_mode = op->acc_mode;
+ if (*opened & FILE_CREATED) {
+ fsnotify_create(dir, dentry);
+ acc_mode = MAY_OPEN;
+ }
+
+ if (error) { /* returned 1, that is */
+ if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+ error = -EIO;
+ goto out;
+ }
+ if (file->f_path.dentry) {
+ dput(dentry);
+ dentry = file->f_path.dentry;
+ }
+ goto looked_up;
+ }
+
+ /*
+ * We didn't have the inode before the open, so check open permission
+ * here.
+ */
+ error = may_open(&file->f_path, acc_mode, open_flag);
+ if (error)
+ fput(file);
+
+out:
+ dput(dentry);
+ return error;
+
+no_open:
+ if (need_lookup) {
+ dentry = lookup_real(dir, dentry, nd->flags);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+
+ if (create_error) {
+ int open_flag = op->open_flag;
+
+ error = create_error;
+ if ((open_flag & O_EXCL)) {
+ if (!dentry->d_inode)
+ goto out;
+ } else if (!dentry->d_inode) {
+ goto out;
+ } else if ((open_flag & O_TRUNC) &&
+ S_ISREG(dentry->d_inode->i_mode)) {
+ goto out;
+ }
+ /* will fail later, go on to get the right error */
+ }
+ }
+looked_up:
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
+}
+
+/*
+ * Look up and maybe create and open the last component.
+ *
+ * Must be called with i_mutex held on parent.
+ *
+ * Returns 0 if the file was successfully atomically created (if necessary) and
+ * opened. In this case the file will be returned attached to @file.
+ *
+ * Returns 1 if the file was not completely opened at this time, though lookups
+ * and creations will have been performed and the dentry returned in @path will
+ * be positive upon return if O_CREAT was specified. If O_CREAT wasn't
+ * specified then a negative dentry may be returned.
+ *
+ * An error code is returned otherwise.
+ *
+ * FILE_CREATE will be set in @*opened if the dentry was created and will be
+ * cleared otherwise prior to returning.
+ */
+static int lookup_open(struct nameidata *nd, struct path *path,
+ struct file *file,
+ const struct open_flags *op,
+ bool *want_write, int *opened)
+{
+ struct dentry *dir = nd->path.dentry;
+ struct inode *dir_inode = dir->d_inode;
+ struct dentry *dentry;
+ int error;
+ bool need_lookup;
+
+ *opened &= ~FILE_CREATED;
+ dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+
+ /* Cached positive dentry: will open in f_op->open */
+ if (!need_lookup && dentry->d_inode)
+ goto out_no_open;
+
+ if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) {
+ return atomic_open(nd, dentry, path, file, op, want_write,
+ need_lookup, opened);
+ }
+
+ if (need_lookup) {
+ BUG_ON(dentry->d_inode);
+
+ dentry = lookup_real(dir_inode, dentry, nd->flags);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ }
+
+ /* Negative dentry, just create the file */
+ if (!dentry->d_inode && (op->open_flag & O_CREAT)) {
+ umode_t mode = op->mode;
+ if (!IS_POSIXACL(dir->d_inode))
+ mode &= ~current_umask();
+ /*
+ * This write is needed to ensure that a
+ * rw->ro transition does not occur between
+ * the time when the file is created and when
+ * a permanent write count is taken through
+ * the 'struct file' in finish_open().
+ */
+ error = mnt_want_write(nd->path.mnt);
+ if (error)
+ goto out_dput;
+ *want_write = true;
+ *opened |= FILE_CREATED;
+ error = security_path_mknod(&nd->path, dentry, mode, 0);
+ if (error)
+ goto out_dput;
+ error = vfs_create(dir->d_inode, dentry, mode,
+ nd->flags & LOOKUP_EXCL);
+ if (error)
+ goto out_dput;
+ }
+out_no_open:
+ path->dentry = dentry;
+ path->mnt = nd->path.mnt;
+ return 1;
+
+out_dput:
+ dput(dentry);
+ return error;
+}
+
/*
* Handle the last step of open()
*/
-static struct file *do_last(struct nameidata *nd, struct path *path,
- const struct open_flags *op, const char *pathname)
+static int do_last(struct nameidata *nd, struct path *path,
+ struct file *file, const struct open_flags *op,
+ int *opened, const char *pathname)
{
struct dentry *dir = nd->path.dentry;
- struct dentry *dentry;
int open_flag = op->open_flag;
- int will_truncate = open_flag & O_TRUNC;
- int want_write = 0;
+ bool will_truncate = (open_flag & O_TRUNC) != 0;
+ bool want_write = false;
int acc_mode = op->acc_mode;
- struct file *filp;
struct inode *inode;
- int symlink_ok = 0;
+ bool symlink_ok = false;
struct path save_parent = { .dentry = NULL, .mnt = NULL };
bool retried = false;
int error;
@@ -2214,112 +2494,99 @@
case LAST_DOT:
error = handle_dots(nd, nd->last_type);
if (error)
- return ERR_PTR(error);
+ return error;
/* fallthrough */
case LAST_ROOT:
error = complete_walk(nd);
if (error)
- return ERR_PTR(error);
+ return error;
audit_inode(pathname, nd->path.dentry);
if (open_flag & O_CREAT) {
error = -EISDIR;
- goto exit;
+ goto out;
}
- goto ok;
+ goto finish_open;
case LAST_BIND:
error = complete_walk(nd);
if (error)
- return ERR_PTR(error);
+ return error;
audit_inode(pathname, dir);
- goto ok;
+ goto finish_open;
}
if (!(open_flag & O_CREAT)) {
if (nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
if (open_flag & O_PATH && !(nd->flags & LOOKUP_FOLLOW))
- symlink_ok = 1;
+ symlink_ok = true;
/* we _can_ be in RCU mode here */
error = lookup_fast(nd, &nd->last, path, &inode);
- if (unlikely(error)) {
- if (error < 0)
- goto exit;
+ if (likely(!error))
+ goto finish_lookup;
- error = lookup_slow(nd, &nd->last, path);
- if (error < 0)
- goto exit;
+ if (error < 0)
+ goto out;
- inode = path->dentry->d_inode;
- }
- goto finish_lookup;
+ BUG_ON(nd->inode != dir->d_inode);
+ } else {
+ /* create side of things */
+ /*
+ * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED
+ * has been cleared when we got to the last component we are
+ * about to look up
+ */
+ error = complete_walk(nd);
+ if (error)
+ return error;
+
+ audit_inode(pathname, dir);
+ error = -EISDIR;
+ /* trailing slashes? */
+ if (nd->last.name[nd->last.len])
+ goto out;
}
- /* create side of things */
- /*
- * This will *only* deal with leaving RCU mode - LOOKUP_JUMPED has been
- * cleared when we got to the last component we are about to look up
- */
- error = complete_walk(nd);
- if (error)
- return ERR_PTR(error);
-
- audit_inode(pathname, dir);
- error = -EISDIR;
- /* trailing slashes? */
- if (nd->last.name[nd->last.len])
- goto exit;
-
retry_lookup:
mutex_lock(&dir->d_inode->i_mutex);
+ error = lookup_open(nd, path, file, op, &want_write, opened);
+ mutex_unlock(&dir->d_inode->i_mutex);
- dentry = lookup_hash(nd);
- error = PTR_ERR(dentry);
- if (IS_ERR(dentry)) {
- mutex_unlock(&dir->d_inode->i_mutex);
- goto exit;
+ if (error <= 0) {
+ if (error)
+ goto out;
+
+ if ((*opened & FILE_CREATED) ||
+ !S_ISREG(file->f_path.dentry->d_inode->i_mode))
+ will_truncate = false;
+
+ audit_inode(pathname, file->f_path.dentry);
+ goto opened;
}
- path->dentry = dentry;
- path->mnt = nd->path.mnt;
-
- /* Negative dentry, just create the file */
- if (!dentry->d_inode) {
- umode_t mode = op->mode;
- if (!IS_POSIXACL(dir->d_inode))
- mode &= ~current_umask();
- /*
- * This write is needed to ensure that a
- * rw->ro transition does not occur between
- * the time when the file is created and when
- * a permanent write count is taken through
- * the 'struct file' in nameidata_to_filp().
- */
- error = mnt_want_write(nd->path.mnt);
- if (error)
- goto exit_mutex_unlock;
- want_write = 1;
+ if (*opened & FILE_CREATED) {
/* Don't check for write permission, don't truncate */
open_flag &= ~O_TRUNC;
- will_truncate = 0;
+ will_truncate = false;
acc_mode = MAY_OPEN;
- error = security_path_mknod(&nd->path, dentry, mode, 0);
- if (error)
- goto exit_mutex_unlock;
- error = vfs_create(dir->d_inode, dentry, mode, nd);
- if (error)
- goto exit_mutex_unlock;
- mutex_unlock(&dir->d_inode->i_mutex);
- dput(nd->path.dentry);
- nd->path.dentry = dentry;
- goto common;
+ path_to_nameidata(path, nd);
+ goto finish_open_created;
}
/*
* It already exists.
*/
- mutex_unlock(&dir->d_inode->i_mutex);
audit_inode(pathname, path->dentry);
+ /*
+ * If atomic_open() acquired write access it is dropped now due to
+ * possible mount and symlink following (this might be optimized away if
+ * necessary...)
+ */
+ if (want_write) {
+ mnt_drop_write(nd->path.mnt);
+ want_write = false;
+ }
+
error = -EEXIST;
if (open_flag & O_EXCL)
goto exit_dput;
@@ -2338,18 +2605,18 @@
error = -ENOENT;
if (!inode) {
path_to_nameidata(path, nd);
- goto exit;
+ goto out;
}
if (should_follow_link(inode, !symlink_ok)) {
if (nd->flags & LOOKUP_RCU) {
if (unlikely(unlazy_walk(nd, path->dentry))) {
error = -ECHILD;
- goto exit;
+ goto out;
}
}
BUG_ON(inode != path->dentry->d_inode);
- return NULL;
+ return 1;
}
if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path->mnt) {
@@ -2365,119 +2632,122 @@
error = complete_walk(nd);
if (error) {
path_put(&save_parent);
- return ERR_PTR(error);
+ return error;
}
error = -EISDIR;
if ((open_flag & O_CREAT) && S_ISDIR(nd->inode->i_mode))
- goto exit;
+ goto out;
error = -ENOTDIR;
if ((nd->flags & LOOKUP_DIRECTORY) && !nd->inode->i_op->lookup)
- goto exit;
+ goto out;
audit_inode(pathname, nd->path.dentry);
-ok:
+finish_open:
if (!S_ISREG(nd->inode->i_mode))
- will_truncate = 0;
+ will_truncate = false;
if (will_truncate) {
error = mnt_want_write(nd->path.mnt);
if (error)
- goto exit;
- want_write = 1;
+ goto out;
+ want_write = true;
}
-common:
+finish_open_created:
error = may_open(&nd->path, acc_mode, open_flag);
if (error)
- goto exit;
- filp = nameidata_to_filp(nd);
- if (filp == ERR_PTR(-EOPENSTALE) && save_parent.dentry && !retried) {
- BUG_ON(save_parent.dentry != dir);
- path_put(&nd->path);
- nd->path = save_parent;
- nd->inode = dir->d_inode;
- save_parent.mnt = NULL;
- save_parent.dentry = NULL;
- if (want_write) {
- mnt_drop_write(nd->path.mnt);
- want_write = 0;
- }
- retried = true;
- goto retry_lookup;
+ goto out;
+ file->f_path.mnt = nd->path.mnt;
+ error = finish_open(file, nd->path.dentry, NULL, opened);
+ if (error) {
+ if (error == -EOPENSTALE)
+ goto stale_open;
+ goto out;
}
- if (!IS_ERR(filp)) {
- error = ima_file_check(filp, op->acc_mode);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
- if (!IS_ERR(filp)) {
- if (will_truncate) {
- error = handle_truncate(filp);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- }
+opened:
+ error = open_check_o_direct(file);
+ if (error)
+ goto exit_fput;
+ error = ima_file_check(file, op->acc_mode);
+ if (error)
+ goto exit_fput;
+
+ if (will_truncate) {
+ error = handle_truncate(file);
+ if (error)
+ goto exit_fput;
}
out:
if (want_write)
mnt_drop_write(nd->path.mnt);
path_put(&save_parent);
terminate_walk(nd);
- return filp;
+ return error;
-exit_mutex_unlock:
- mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
path_put_conditional(path, nd);
-exit:
- filp = ERR_PTR(error);
goto out;
+exit_fput:
+ fput(file);
+ goto out;
+
+stale_open:
+ /* If no saved parent or already retried then can't retry */
+ if (!save_parent.dentry || retried)
+ goto out;
+
+ BUG_ON(save_parent.dentry != dir);
+ path_put(&nd->path);
+ nd->path = save_parent;
+ nd->inode = dir->d_inode;
+ save_parent.mnt = NULL;
+ save_parent.dentry = NULL;
+ if (want_write) {
+ mnt_drop_write(nd->path.mnt);
+ want_write = false;
+ }
+ retried = true;
+ goto retry_lookup;
}
static struct file *path_openat(int dfd, const char *pathname,
struct nameidata *nd, const struct open_flags *op, int flags)
{
struct file *base = NULL;
- struct file *filp;
+ struct file *file;
struct path path;
+ int opened = 0;
int error;
- filp = get_empty_filp();
- if (!filp)
+ file = get_empty_filp();
+ if (!file)
return ERR_PTR(-ENFILE);
- filp->f_flags = op->open_flag;
- nd->intent.open.file = filp;
- nd->intent.open.flags = open_to_namei_flags(op->open_flag);
- nd->intent.open.create_mode = op->mode;
+ file->f_flags = op->open_flag;
error = path_init(dfd, pathname, flags | LOOKUP_PARENT, nd, &base);
if (unlikely(error))
- goto out_filp;
+ goto out;
current->total_link_count = 0;
error = link_path_walk(pathname, nd);
if (unlikely(error))
- goto out_filp;
+ goto out;
- filp = do_last(nd, &path, op, pathname);
- while (unlikely(!filp)) { /* trailing symlink */
+ error = do_last(nd, &path, file, op, &opened, pathname);
+ while (unlikely(error > 0)) { /* trailing symlink */
struct path link = path;
void *cookie;
if (!(nd->flags & LOOKUP_FOLLOW)) {
path_put_conditional(&path, nd);
path_put(&nd->path);
- filp = ERR_PTR(-ELOOP);
+ error = -ELOOP;
break;
}
nd->flags |= LOOKUP_PARENT;
nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
error = follow_link(&link, nd, &cookie);
if (unlikely(error))
- filp = ERR_PTR(error);
- else
- filp = do_last(nd, &path, op, pathname);
+ break;
+ error = do_last(nd, &path, file, op, &opened, pathname);
put_link(nd, &link, cookie);
}
out:
@@ -2485,18 +2755,20 @@
path_put(&nd->root);
if (base)
fput(base);
- release_open_intent(nd);
- if (filp == ERR_PTR(-EOPENSTALE)) {
- if (flags & LOOKUP_RCU)
- filp = ERR_PTR(-ECHILD);
- else
- filp = ERR_PTR(-ESTALE);
+ if (!(opened & FILE_OPENED)) {
+ BUG_ON(!error);
+ put_filp(file);
}
- return filp;
-
-out_filp:
- filp = ERR_PTR(error);
- goto out;
+ if (unlikely(error)) {
+ if (error == -EOPENSTALE) {
+ if (flags & LOOKUP_RCU)
+ error = -ECHILD;
+ else
+ error = -ESTALE;
+ }
+ file = ERR_PTR(error);
+ }
+ return file;
}
struct file *do_filp_open(int dfd, const char *pathname,
@@ -2551,7 +2823,6 @@
goto out;
nd.flags &= ~LOOKUP_PARENT;
nd.flags |= LOOKUP_CREATE | LOOKUP_EXCL;
- nd.intent.open.flags = O_EXCL;
/*
* Do the final lookup.
@@ -2670,7 +2941,7 @@
goto out_drop_write;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create(path.dentry->d_inode,dentry,mode,NULL);
+ error = vfs_create(path.dentry->d_inode,dentry,mode,true);
break;
case S_IFCHR: case S_IFBLK:
error = vfs_mknod(path.dentry->d_inode,dentry,mode,
diff --git a/fs/namespace.c b/fs/namespace.c
index 1e4a5fe..c53d338 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -515,8 +515,20 @@
}
/*
- * lookup_mnt increments the ref count before returning
- * the vfsmount struct.
+ * lookup_mnt - Return the first child mount mounted at path
+ *
+ * "First" means first mounted chronologically. If you create the
+ * following mounts:
+ *
+ * mount /dev/sda1 /mnt
+ * mount /dev/sda2 /mnt
+ * mount /dev/sda3 /mnt
+ *
+ * Then lookup_mnt() on the base /mnt dentry in the root mount will
+ * return successively the root dentry and vfsmount of /dev/sda1, then
+ * /dev/sda2, then /dev/sda3, then NULL.
+ *
+ * lookup_mnt takes a reference to the found vfsmount.
*/
struct vfsmount *lookup_mnt(struct path *path)
{
@@ -621,21 +633,6 @@
list_add_tail(&mnt->mnt_child, &real_mount(path->mnt)->mnt_mounts);
}
-static inline void __mnt_make_longterm(struct mount *mnt)
-{
-#ifdef CONFIG_SMP
- atomic_inc(&mnt->mnt_longterm);
-#endif
-}
-
-/* needs vfsmount lock for write */
-static inline void __mnt_make_shortterm(struct mount *mnt)
-{
-#ifdef CONFIG_SMP
- atomic_dec(&mnt->mnt_longterm);
-#endif
-}
-
/*
* vfsmount lock must be held for write
*/
@@ -649,10 +646,8 @@
BUG_ON(parent == mnt);
list_add_tail(&head, &mnt->mnt_list);
- list_for_each_entry(m, &head, mnt_list) {
+ list_for_each_entry(m, &head, mnt_list)
m->mnt_ns = n;
- __mnt_make_longterm(m);
- }
list_splice(&head, n->list.prev);
@@ -725,56 +720,60 @@
int flag)
{
struct super_block *sb = old->mnt.mnt_sb;
- struct mount *mnt = alloc_vfsmnt(old->mnt_devname);
+ struct mount *mnt;
+ int err;
- if (mnt) {
- if (flag & (CL_SLAVE | CL_PRIVATE))
- mnt->mnt_group_id = 0; /* not a peer of original */
- else
- mnt->mnt_group_id = old->mnt_group_id;
+ mnt = alloc_vfsmnt(old->mnt_devname);
+ if (!mnt)
+ return ERR_PTR(-ENOMEM);
- if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
- int err = mnt_alloc_group_id(mnt);
- if (err)
- goto out_free;
- }
+ if (flag & (CL_SLAVE | CL_PRIVATE))
+ mnt->mnt_group_id = 0; /* not a peer of original */
+ else
+ mnt->mnt_group_id = old->mnt_group_id;
- mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
- atomic_inc(&sb->s_active);
- mnt->mnt.mnt_sb = sb;
- mnt->mnt.mnt_root = dget(root);
- mnt->mnt_mountpoint = mnt->mnt.mnt_root;
- mnt->mnt_parent = mnt;
- br_write_lock(&vfsmount_lock);
- list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
- br_write_unlock(&vfsmount_lock);
-
- if (flag & CL_SLAVE) {
- list_add(&mnt->mnt_slave, &old->mnt_slave_list);
- mnt->mnt_master = old;
- CLEAR_MNT_SHARED(mnt);
- } else if (!(flag & CL_PRIVATE)) {
- if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
- list_add(&mnt->mnt_share, &old->mnt_share);
- if (IS_MNT_SLAVE(old))
- list_add(&mnt->mnt_slave, &old->mnt_slave);
- mnt->mnt_master = old->mnt_master;
- }
- if (flag & CL_MAKE_SHARED)
- set_mnt_shared(mnt);
-
- /* stick the duplicate mount on the same expiry list
- * as the original if that was on one */
- if (flag & CL_EXPIRE) {
- if (!list_empty(&old->mnt_expire))
- list_add(&mnt->mnt_expire, &old->mnt_expire);
- }
+ if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
+ err = mnt_alloc_group_id(mnt);
+ if (err)
+ goto out_free;
}
+
+ mnt->mnt.mnt_flags = old->mnt.mnt_flags & ~MNT_WRITE_HOLD;
+ atomic_inc(&sb->s_active);
+ mnt->mnt.mnt_sb = sb;
+ mnt->mnt.mnt_root = dget(root);
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
+ mnt->mnt_parent = mnt;
+ br_write_lock(&vfsmount_lock);
+ list_add_tail(&mnt->mnt_instance, &sb->s_mounts);
+ br_write_unlock(&vfsmount_lock);
+
+ if (flag & CL_SLAVE) {
+ list_add(&mnt->mnt_slave, &old->mnt_slave_list);
+ mnt->mnt_master = old;
+ CLEAR_MNT_SHARED(mnt);
+ } else if (!(flag & CL_PRIVATE)) {
+ if ((flag & CL_MAKE_SHARED) || IS_MNT_SHARED(old))
+ list_add(&mnt->mnt_share, &old->mnt_share);
+ if (IS_MNT_SLAVE(old))
+ list_add(&mnt->mnt_slave, &old->mnt_slave);
+ mnt->mnt_master = old->mnt_master;
+ }
+ if (flag & CL_MAKE_SHARED)
+ set_mnt_shared(mnt);
+
+ /* stick the duplicate mount on the same expiry list
+ * as the original if that was on one */
+ if (flag & CL_EXPIRE) {
+ if (!list_empty(&old->mnt_expire))
+ list_add(&mnt->mnt_expire, &old->mnt_expire);
+ }
+
return mnt;
out_free:
free_vfsmnt(mnt);
- return NULL;
+ return ERR_PTR(err);
}
static inline void mntfree(struct mount *mnt)
@@ -804,7 +803,8 @@
put_again:
#ifdef CONFIG_SMP
br_read_lock(&vfsmount_lock);
- if (likely(atomic_read(&mnt->mnt_longterm))) {
+ if (likely(mnt->mnt_ns)) {
+ /* shouldn't be the last one */
mnt_add_count(mnt, -1);
br_read_unlock(&vfsmount_lock);
return;
@@ -939,7 +939,7 @@
/* iterator; we want it to have access to namespace_sem, thus here... */
static void *m_start(struct seq_file *m, loff_t *pos)
{
- struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+ struct proc_mounts *p = proc_mounts(m);
down_read(&namespace_sem);
return seq_list_start(&p->ns->list, *pos);
@@ -947,7 +947,7 @@
static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
- struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+ struct proc_mounts *p = proc_mounts(m);
return seq_list_next(v, &p->ns->list, pos);
}
@@ -959,7 +959,7 @@
static int m_show(struct seq_file *m, void *v)
{
- struct proc_mounts *p = container_of(m, struct proc_mounts, m);
+ struct proc_mounts *p = proc_mounts(m);
struct mount *r = list_entry(v, struct mount, mnt_list);
return p->show(m, &r->mnt);
}
@@ -1074,8 +1074,6 @@
list_del_init(&p->mnt_expire);
list_del_init(&p->mnt_list);
__touch_mnt_namespace(p->mnt_ns);
- if (p->mnt_ns)
- __mnt_make_shortterm(p);
p->mnt_ns = NULL;
list_del_init(&p->mnt_child);
if (mnt_has_parent(p)) {
@@ -1260,11 +1258,12 @@
struct path path;
if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt))
- return NULL;
+ return ERR_PTR(-EINVAL);
res = q = clone_mnt(mnt, dentry, flag);
- if (!q)
- goto Enomem;
+ if (IS_ERR(q))
+ return q;
+
q->mnt_mountpoint = mnt->mnt_mountpoint;
p = mnt;
@@ -1286,8 +1285,8 @@
path.mnt = &q->mnt;
path.dentry = p->mnt_mountpoint;
q = clone_mnt(p, p->mnt.mnt_root, flag);
- if (!q)
- goto Enomem;
+ if (IS_ERR(q))
+ goto out;
br_write_lock(&vfsmount_lock);
list_add_tail(&q->mnt_list, &res->mnt_list);
attach_mnt(q, &path);
@@ -1295,7 +1294,7 @@
}
}
return res;
-Enomem:
+out:
if (res) {
LIST_HEAD(umount_list);
br_write_lock(&vfsmount_lock);
@@ -1303,9 +1302,11 @@
br_write_unlock(&vfsmount_lock);
release_mounts(&umount_list);
}
- return NULL;
+ return q;
}
+/* Caller should check returned pointer for errors */
+
struct vfsmount *collect_mounts(struct path *path)
{
struct mount *tree;
@@ -1313,7 +1314,9 @@
tree = copy_tree(real_mount(path->mnt), path->dentry,
CL_COPY_ALL | CL_PRIVATE);
up_write(&namespace_sem);
- return tree ? &tree->mnt : NULL;
+ if (IS_ERR(tree))
+ return NULL;
+ return &tree->mnt;
}
void drop_collected_mounts(struct vfsmount *mnt)
@@ -1608,14 +1611,15 @@
if (!check_mnt(real_mount(path->mnt)) || !check_mnt(old))
goto out2;
- err = -ENOMEM;
if (recurse)
mnt = copy_tree(old, old_path.dentry, 0);
else
mnt = clone_mnt(old, old_path.dentry, 0);
- if (!mnt)
- goto out2;
+ if (IS_ERR(mnt)) {
+ err = PTR_ERR(mnt);
+ goto out;
+ }
err = graft_tree(mnt, path);
if (err) {
@@ -2209,23 +2213,6 @@
return new_ns;
}
-void mnt_make_longterm(struct vfsmount *mnt)
-{
- __mnt_make_longterm(real_mount(mnt));
-}
-
-void mnt_make_shortterm(struct vfsmount *m)
-{
-#ifdef CONFIG_SMP
- struct mount *mnt = real_mount(m);
- if (atomic_add_unless(&mnt->mnt_longterm, -1, 1))
- return;
- br_write_lock(&vfsmount_lock);
- atomic_dec(&mnt->mnt_longterm);
- br_write_unlock(&vfsmount_lock);
-#endif
-}
-
/*
* Allocate a new namespace structure and populate it with contents
* copied from the namespace of the passed in task structure.
@@ -2246,10 +2233,10 @@
down_write(&namespace_sem);
/* First pass: copy the tree topology */
new = copy_tree(old, old->mnt.mnt_root, CL_COPY_ALL | CL_EXPIRE);
- if (!new) {
+ if (IS_ERR(new)) {
up_write(&namespace_sem);
kfree(new_ns);
- return ERR_PTR(-ENOMEM);
+ return ERR_CAST(new);
}
new_ns->root = new;
br_write_lock(&vfsmount_lock);
@@ -2265,18 +2252,13 @@
q = new;
while (p) {
q->mnt_ns = new_ns;
- __mnt_make_longterm(q);
if (fs) {
if (&p->mnt == fs->root.mnt) {
fs->root.mnt = mntget(&q->mnt);
- __mnt_make_longterm(q);
- mnt_make_shortterm(&p->mnt);
rootmnt = &p->mnt;
}
if (&p->mnt == fs->pwd.mnt) {
fs->pwd.mnt = mntget(&q->mnt);
- __mnt_make_longterm(q);
- mnt_make_shortterm(&p->mnt);
pwdmnt = &p->mnt;
}
}
@@ -2320,7 +2302,6 @@
if (!IS_ERR(new_ns)) {
struct mount *mnt = real_mount(m);
mnt->mnt_ns = new_ns;
- __mnt_make_longterm(mnt);
new_ns->root = mnt;
list_add(&new_ns->list, &mnt->mnt_list);
} else {
@@ -2615,7 +2596,7 @@
* it is a longterm mount, don't release mnt until
* we unmount before file sys is unregistered
*/
- mnt_make_longterm(mnt);
+ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
}
return mnt;
}
@@ -2625,7 +2606,9 @@
{
/* release long term mount so mount point can be released */
if (!IS_ERR_OR_NULL(mnt)) {
- mnt_make_shortterm(mnt);
+ br_write_lock(&vfsmount_lock);
+ real_mount(mnt)->mnt_ns = NULL;
+ br_write_unlock(&vfsmount_lock);
mntput(mnt);
}
}
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index aeed93a..4117e7b 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -30,8 +30,8 @@
static int ncp_readdir(struct file *, void *, filldir_t);
-static int ncp_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
-static struct dentry *ncp_lookup(struct inode *, struct dentry *, struct nameidata *);
+static int ncp_create(struct inode *, struct dentry *, umode_t, bool);
+static struct dentry *ncp_lookup(struct inode *, struct dentry *, unsigned int);
static int ncp_unlink(struct inode *, struct dentry *);
static int ncp_mkdir(struct inode *, struct dentry *, umode_t);
static int ncp_rmdir(struct inode *, struct dentry *);
@@ -72,7 +72,7 @@
/*
* Dentry operations routines
*/
-static int ncp_lookup_validate(struct dentry *, struct nameidata *);
+static int ncp_lookup_validate(struct dentry *, unsigned int);
static int ncp_hash_dentry(const struct dentry *, const struct inode *,
struct qstr *);
static int ncp_compare_dentry(const struct dentry *, const struct inode *,
@@ -290,7 +290,7 @@
static int
-ncp_lookup_validate(struct dentry *dentry, struct nameidata *nd)
+ncp_lookup_validate(struct dentry *dentry, unsigned int flags)
{
struct ncp_server *server;
struct dentry *parent;
@@ -302,7 +302,7 @@
if (dentry == dentry->d_sb->s_root)
return 1;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
@@ -836,7 +836,7 @@
return result;
}
-static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ncp_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct ncp_server *server = NCP_SERVER(dir);
struct inode *inode = NULL;
@@ -980,7 +980,7 @@
}
static int ncp_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return ncp_create_new(dir, dentry, mode, 0, 0);
}
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 68e451f..b713685 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -46,8 +46,8 @@
static int nfs_opendir(struct inode *, struct file *);
static int nfs_closedir(struct inode *, struct file *);
static int nfs_readdir(struct file *, void *, filldir_t);
-static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *);
+static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int);
+static int nfs_create(struct inode *, struct dentry *, umode_t, bool);
static int nfs_mkdir(struct inode *, struct dentry *, umode_t);
static int nfs_rmdir(struct inode *, struct dentry *);
static int nfs_unlink(struct inode *, struct dentry *);
@@ -111,11 +111,13 @@
#ifdef CONFIG_NFS_V4
-static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *);
-static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd);
+static int nfs_atomic_open(struct inode *, struct dentry *,
+ struct file *, unsigned, umode_t,
+ int *);
const struct inode_operations nfs4_dir_inode_operations = {
- .create = nfs_open_create,
- .lookup = nfs_atomic_lookup,
+ .create = nfs_create,
+ .lookup = nfs_lookup,
+ .atomic_open = nfs_atomic_open,
.link = nfs_link,
.unlink = nfs_unlink,
.symlink = nfs_symlink,
@@ -1029,27 +1031,14 @@
}
/*
- * Return the intent data that applies to this particular path component
- *
- * Note that the current set of intents only apply to the very last
- * component of the path and none of them is set before that last
- * component.
- */
-static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd,
- unsigned int mask)
-{
- return nd->flags & mask;
-}
-
-/*
* Use intent information to check whether or not we're going to do
* an O_EXCL create using this path component.
*/
-static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
+static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
{
if (NFS_PROTO(dir)->version == 2)
return 0;
- return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL);
+ return flags & LOOKUP_EXCL;
}
/*
@@ -1061,25 +1050,20 @@
*
*/
static inline
-int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd)
+int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
{
struct nfs_server *server = NFS_SERVER(inode);
if (IS_AUTOMOUNT(inode))
return 0;
- if (nd != NULL) {
- /* VFS wants an on-the-wire revalidation */
- if (nd->flags & LOOKUP_REVAL)
- goto out_force;
- /* This is an open(2) */
- if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 &&
- !(server->flags & NFS_MOUNT_NOCTO) &&
- (S_ISREG(inode->i_mode) ||
- S_ISDIR(inode->i_mode)))
- goto out_force;
- return 0;
- }
- return nfs_revalidate_inode(server, inode);
+ /* VFS wants an on-the-wire revalidation */
+ if (flags & LOOKUP_REVAL)
+ goto out_force;
+ /* This is an open(2) */
+ if ((flags & LOOKUP_OPEN) && !(server->flags & NFS_MOUNT_NOCTO) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+ goto out_force;
+ return 0;
out_force:
return __nfs_revalidate_inode(server, inode);
}
@@ -1093,10 +1077,10 @@
*/
static inline
int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
/* Don't revalidate a negative dentry if we're creating a new file */
- if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0)
+ if (flags & LOOKUP_CREATE)
return 0;
if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
return 1;
@@ -1114,7 +1098,7 @@
* If the parent directory is seen to have changed, we throw out the
* cached dentry and do a new lookup.
*/
-static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *dir;
struct inode *inode;
@@ -1123,7 +1107,7 @@
struct nfs_fattr *fattr = NULL;
int error;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
@@ -1132,7 +1116,7 @@
inode = dentry->d_inode;
if (!inode) {
- if (nfs_neg_need_reval(dir, dentry, nd))
+ if (nfs_neg_need_reval(dir, dentry, flags))
goto out_bad;
goto out_valid_noent;
}
@@ -1148,8 +1132,8 @@
goto out_set_verifier;
/* Force a full look up iff the parent directory has changed */
- if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) {
- if (nfs_lookup_verify_inode(inode, nd))
+ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
+ if (nfs_lookup_verify_inode(inode, flags))
goto out_zap_parent;
goto out_valid;
}
@@ -1286,7 +1270,7 @@
.d_release = nfs_d_release,
};
-static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
struct dentry *parent;
@@ -1307,7 +1291,7 @@
* If we're doing an exclusive create, optimize away the lookup
* but don't hash the dentry.
*/
- if (nfs_is_exclusive_create(dir, nd)) {
+ if (nfs_is_exclusive_create(dir, flags)) {
d_instantiate(dentry, NULL);
res = NULL;
goto out;
@@ -1354,7 +1338,7 @@
}
#ifdef CONFIG_NFS_V4
-static int nfs4_lookup_revalidate(struct dentry *, struct nameidata *);
+static int nfs4_lookup_revalidate(struct dentry *, unsigned int);
const struct dentry_operations nfs4_dentry_operations = {
.d_revalidate = nfs4_lookup_revalidate,
@@ -1364,24 +1348,6 @@
.d_release = nfs_d_release,
};
-/*
- * Use intent information to determine whether we need to substitute
- * the NFSv4-style stateful OPEN for the LOOKUP call
- */
-static int is_atomic_open(struct nameidata *nd)
-{
- if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0)
- return 0;
- /* NFS does not (yet) have a stateful open for directories */
- if (nd->flags & LOOKUP_DIRECTORY)
- return 0;
- /* Are we trying to write to a read only partition? */
- if (__mnt_is_readonly(nd->path.mnt) &&
- (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE)))
- return 0;
- return 1;
-}
-
static fmode_t flags_to_mode(int flags)
{
fmode_t res = (__force fmode_t)flags & FMODE_EXEC;
@@ -1403,136 +1369,143 @@
return 0;
}
-static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx)
+static int nfs_finish_open(struct nfs_open_context *ctx,
+ struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ int *opened)
{
- struct file *filp;
- int ret = 0;
+ int err;
+
+ if (ctx->dentry != dentry) {
+ dput(ctx->dentry);
+ ctx->dentry = dget(dentry);
+ }
/* If the open_intent is for execute, we have an extra check to make */
if (ctx->mode & FMODE_EXEC) {
- ret = nfs_may_open(ctx->dentry->d_inode,
- ctx->cred,
- nd->intent.open.flags);
- if (ret < 0)
+ err = nfs_may_open(dentry->d_inode, ctx->cred, open_flags);
+ if (err < 0)
goto out;
}
- filp = lookup_instantiate_filp(nd, ctx->dentry, do_open);
- if (IS_ERR(filp))
- ret = PTR_ERR(filp);
- else
- nfs_file_set_open_context(filp, ctx);
+
+ err = finish_open(file, dentry, do_open, opened);
+ if (err)
+ goto out;
+ nfs_file_set_open_context(file, ctx);
+
out:
put_nfs_open_context(ctx);
- return ret;
+ return err;
}
-static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
+ struct file *file, unsigned open_flags,
+ umode_t mode, int *opened)
{
struct nfs_open_context *ctx;
- struct iattr attr;
- struct dentry *res = NULL;
+ struct dentry *res;
+ struct iattr attr = { .ia_valid = ATTR_OPEN };
struct inode *inode;
- int open_flags;
int err;
- dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n",
+ /* Expect a negative dentry */
+ BUG_ON(dentry->d_inode);
+
+ dfprintk(VFS, "NFS: atomic_open(%s/%ld), %s\n",
dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
- /* Check that we are indeed trying to open this file */
- if (!is_atomic_open(nd))
+ /* NFS only supports OPEN on regular files */
+ if ((open_flags & O_DIRECTORY)) {
+ if (!d_unhashed(dentry)) {
+ /*
+ * Hashed negative dentry with O_DIRECTORY: dentry was
+ * revalidated and is fine, no need to perform lookup
+ * again
+ */
+ return -ENOENT;
+ }
goto no_open;
-
- if (dentry->d_name.len > NFS_SERVER(dir)->namelen) {
- res = ERR_PTR(-ENAMETOOLONG);
- goto out;
}
- /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
- * the dentry. */
- if (nd->flags & LOOKUP_EXCL) {
- d_instantiate(dentry, NULL);
- goto out;
- }
+ if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
+ return -ENAMETOOLONG;
- open_flags = nd->intent.open.flags;
- attr.ia_valid = ATTR_OPEN;
-
- ctx = create_nfs_open_context(dentry, open_flags);
- res = ERR_CAST(ctx);
- if (IS_ERR(ctx))
- goto out;
-
- if (nd->flags & LOOKUP_CREATE) {
- attr.ia_mode = nd->intent.open.create_mode;
+ if (open_flags & O_CREAT) {
attr.ia_valid |= ATTR_MODE;
- attr.ia_mode &= ~current_umask();
- } else
- open_flags &= ~(O_EXCL | O_CREAT);
-
+ attr.ia_mode = mode & ~current_umask();
+ }
if (open_flags & O_TRUNC) {
attr.ia_valid |= ATTR_SIZE;
attr.ia_size = 0;
}
- /* Open the file on the server */
+ ctx = create_nfs_open_context(dentry, open_flags);
+ err = PTR_ERR(ctx);
+ if (IS_ERR(ctx))
+ goto out;
+
nfs_block_sillyrename(dentry->d_parent);
inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr);
+ d_drop(dentry);
if (IS_ERR(inode)) {
nfs_unblock_sillyrename(dentry->d_parent);
put_nfs_open_context(ctx);
- switch (PTR_ERR(inode)) {
- /* Make a negative dentry */
- case -ENOENT:
- d_add(dentry, NULL);
- res = NULL;
- goto out;
- /* This turned out not to be a regular file */
- case -EISDIR:
- case -ENOTDIR:
+ err = PTR_ERR(inode);
+ switch (err) {
+ case -ENOENT:
+ d_add(dentry, NULL);
+ break;
+ case -EISDIR:
+ case -ENOTDIR:
+ goto no_open;
+ case -ELOOP:
+ if (!(open_flags & O_NOFOLLOW))
goto no_open;
- case -ELOOP:
- if (!(nd->intent.open.flags & O_NOFOLLOW))
- goto no_open;
+ break;
/* case -EINVAL: */
- default:
- res = ERR_CAST(inode);
- goto out;
+ default:
+ break;
}
+ goto out;
}
res = d_add_unique(dentry, inode);
- nfs_unblock_sillyrename(dentry->d_parent);
- if (res != NULL) {
- dput(ctx->dentry);
- ctx->dentry = dget(res);
+ if (res != NULL)
dentry = res;
- }
- err = nfs_intent_set_file(nd, ctx);
- if (err < 0) {
- if (res != NULL)
- dput(res);
- return ERR_PTR(err);
- }
-out:
+
+ nfs_unblock_sillyrename(dentry->d_parent);
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- return res;
+
+ err = nfs_finish_open(ctx, dentry, file, open_flags, opened);
+
+ dput(res);
+out:
+ return err;
+
no_open:
- return nfs_lookup(dir, dentry, nd);
+ res = nfs_lookup(dir, dentry, 0);
+ err = PTR_ERR(res);
+ if (IS_ERR(res))
+ goto out;
+
+ return finish_no_open(file, res);
}
-static int nfs4_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
struct dentry *parent = NULL;
struct inode *inode;
struct inode *dir;
- int openflags, ret = 0;
+ int ret = 0;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
- inode = dentry->d_inode;
- if (!is_atomic_open(nd) || d_mountpoint(dentry))
+ if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
+ goto no_open;
+ if (d_mountpoint(dentry))
goto no_open;
+ inode = dentry->d_inode;
parent = dget_parent(dentry);
dir = parent->d_inode;
@@ -1540,7 +1513,7 @@
* optimize away revalidation of negative dentries.
*/
if (inode == NULL) {
- if (!nfs_neg_need_reval(dir, dentry, nd))
+ if (!nfs_neg_need_reval(dir, dentry, flags))
ret = 1;
goto out;
}
@@ -1548,9 +1521,8 @@
/* NFS only supports OPEN on regular files */
if (!S_ISREG(inode->i_mode))
goto no_open_dput;
- openflags = nd->intent.open.flags;
/* We cannot do exclusive creation on a positive dentry */
- if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
+ if (flags & LOOKUP_EXCL)
goto no_open_dput;
/* Let f_op->open() actually open (and revalidate) the file */
@@ -1563,48 +1535,7 @@
no_open_dput:
dput(parent);
no_open:
- return nfs_lookup_revalidate(dentry, nd);
-}
-
-static int nfs_open_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
-{
- struct nfs_open_context *ctx = NULL;
- struct iattr attr;
- int error;
- int open_flags = O_CREAT|O_EXCL;
-
- dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
- dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
-
- attr.ia_mode = mode;
- attr.ia_valid = ATTR_MODE;
-
- if (nd)
- open_flags = nd->intent.open.flags;
-
- ctx = create_nfs_open_context(dentry, open_flags);
- error = PTR_ERR(ctx);
- if (IS_ERR(ctx))
- goto out_err_drop;
-
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx);
- if (error != 0)
- goto out_put_ctx;
- if (nd) {
- error = nfs_intent_set_file(nd, ctx);
- if (error < 0)
- goto out_err;
- } else {
- put_nfs_open_context(ctx);
- }
- return 0;
-out_put_ctx:
- put_nfs_open_context(ctx);
-out_err_drop:
- d_drop(dentry);
-out_err:
- return error;
+ return nfs_lookup_revalidate(dentry, flags);
}
#endif /* CONFIG_NFSV4 */
@@ -1658,11 +1589,11 @@
* reply path made it appear to have failed.
*/
static int nfs_create(struct inode *dir, struct dentry *dentry,
- umode_t mode, struct nameidata *nd)
+ umode_t mode, bool excl)
{
struct iattr attr;
+ int open_flags = excl ? O_CREAT | O_EXCL : O_CREAT;
int error;
- int open_flags = O_CREAT|O_EXCL;
dfprintk(VFS, "NFS: create(%s/%ld), %s\n",
dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
@@ -1670,10 +1601,7 @@
attr.ia_mode = mode;
attr.ia_valid = ATTR_MODE;
- if (nd)
- open_flags = nd->intent.open.flags;
-
- error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL);
+ error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
if (error != 0)
goto out_err;
return 0;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 9a4cbfc..4825337 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -484,6 +484,7 @@
list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
if (!nfs_pageio_add_request(&desc, req)) {
+ nfs_list_remove_request(req);
nfs_list_add_request(req, &failed);
spin_lock(cinfo.lock);
dreq->flags = 0;
@@ -494,8 +495,11 @@
}
nfs_pageio_complete(&desc);
- while (!list_empty(&failed))
+ while (!list_empty(&failed)) {
+ req = nfs_list_entry(failed.next);
+ nfs_list_remove_request(req);
nfs_unlock_and_release_request(req);
+ }
if (put_dreq(dreq))
nfs_direct_write_complete(dreq, dreq->inode);
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 8abfb19..a67990f 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -62,7 +62,7 @@
*/
spin_lock(&sb->s_root->d_inode->i_lock);
spin_lock(&sb->s_root->d_lock);
- list_del_init(&sb->s_root->d_alias);
+ hlist_del_init(&sb->s_root->d_alias);
spin_unlock(&sb->s_root->d_lock);
spin_unlock(&sb->s_root->d_inode->i_lock);
}
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index f3344f7..f580358 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -314,7 +314,7 @@
*/
static int
nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
struct nfs3_createdata *data;
umode_t mode = sattr->ia_mode;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7d387cb..006e98d 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2804,39 +2804,24 @@
}
/*
- * Got race?
- * We will need to arrange for the VFS layer to provide an atomic open.
- * Until then, this create/open method is prone to inefficiency and race
- * conditions due to the lookup, create, and open VFS calls from sys_open()
- * placed on the wire.
- *
- * Given the above sorry state of affairs, I'm simply sending an OPEN.
- * The file will be opened again in the subsequent VFS open call
- * (nfs4_proc_file_open).
- *
- * The open for read will just hang around to be used by any process that
- * opens the file O_RDONLY. This will all be resolved with the VFS changes.
+ * This is just for mknod. open(O_CREAT) will always do ->open_context().
*/
-
static int
nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
- struct dentry *de = dentry;
+ struct nfs_open_context *ctx;
struct nfs4_state *state;
- struct rpc_cred *cred = NULL;
- struct nfs4_threshold **thp = NULL;
- fmode_t fmode = 0;
int status = 0;
- if (ctx != NULL) {
- cred = ctx->cred;
- de = ctx->dentry;
- fmode = ctx->mode;
- thp = &ctx->mdsthreshold;
- }
+ ctx = alloc_nfs_open_context(dentry, FMODE_READ);
+ if (IS_ERR(ctx))
+ return PTR_ERR(ctx);
+
sattr->ia_mode &= ~current_umask();
- state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, thp);
+ state = nfs4_do_open(dir, dentry, ctx->mode,
+ flags, sattr, ctx->cred,
+ &ctx->mdsthreshold);
d_drop(dentry);
if (IS_ERR(state)) {
status = PTR_ERR(state);
@@ -2844,11 +2829,9 @@
}
d_add(dentry, igrab(state->inode));
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
- if (ctx != NULL)
- ctx->state = state;
- else
- nfs4_close_sync(state, fmode);
+ ctx->state = state;
out:
+ put_nfs_open_context(ctx);
return status;
}
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index cf64997..c5ed1c0 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -259,7 +259,7 @@
static int
nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
- int flags, struct nfs_open_context *ctx)
+ int flags)
{
struct nfs_createdata *data;
struct rpc_message msg = {
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 9d33fb2..9bad4e7 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2418,7 +2418,7 @@
sb_mntdata.mntflags |= MS_SYNCHRONOUS;
/* Get a superblock - note that we may end up sharing one that already exists */
- s = sget(fs_type, compare_super, nfs_set_super, &sb_mntdata);
+ s = sget(fs_type, compare_super, nfs_set_super, flags, &sb_mntdata);
if (IS_ERR(s)) {
mntroot = ERR_CAST(s);
goto out_err_nosb;
@@ -2859,6 +2859,8 @@
dfprintk(MOUNT, "--> nfs4_try_mount()\n");
+ mount_info->fill_super = nfs4_fill_super;
+
export_path = data->nfs_server.export_path;
data->nfs_server.export_path = "/";
root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index c8bd9c3..05d9eee 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1329,7 +1329,7 @@
err = 0;
switch (type) {
case S_IFREG:
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
if (!host_err)
nfsd_check_ignore_resizing(iap);
break;
@@ -1492,7 +1492,7 @@
goto out;
}
- host_err = vfs_create(dirp, dchild, iap->ia_mode, NULL);
+ host_err = vfs_create(dirp, dchild, iap->ia_mode, true);
if (host_err < 0) {
fh_drop_write(fhp);
goto out_nfserr;
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index b728479..1d0c0b8 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -63,7 +63,7 @@
*/
static struct dentry *
-nilfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
ino_t ino;
@@ -85,7 +85,7 @@
* with d_instantiate().
*/
static int nilfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
struct nilfs_transaction_info ti;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 1099a76..d57c42f9 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1288,7 +1288,8 @@
err = -EBUSY;
goto failed;
}
- s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, sd.bdev);
+ s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags,
+ sd.bdev);
mutex_unlock(&sd.bdev->bd_fsfreeze_mutex);
if (IS_ERR(s)) {
err = PTR_ERR(s);
@@ -1301,7 +1302,6 @@
s_new = true;
/* New superblock instance created */
- s->s_flags = flags;
s->s_mode = mode;
strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(sd.bdev));
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index b39c5c1..6baadb5 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -52,6 +52,7 @@
void __fsnotify_update_child_dentry_flags(struct inode *inode)
{
struct dentry *alias;
+ struct hlist_node *p;
int watched;
if (!S_ISDIR(inode->i_mode))
@@ -63,7 +64,7 @@
spin_lock(&inode->i_lock);
/* run all of the dentries associated with this inode. Since this is a
* directory, there damn well better only be one item on this list */
- list_for_each_entry(alias, &inode->i_dentry, d_alias) {
+ hlist_for_each_entry(alias, p, &inode->i_dentry, d_alias) {
struct dentry *child;
/* run all of the children of the original inode and fix their
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 358273e5..436f360 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -101,7 +101,7 @@
* Locking: Caller must hold i_mutex on the directory.
*/
static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
- struct nameidata *nd)
+ unsigned int flags)
{
ntfs_volume *vol = NTFS_SB(dir_ino->i_sb);
struct inode *dent_inode;
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index e5ba348..8db4b58 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -49,14 +49,13 @@
}
-static int ocfs2_dentry_revalidate(struct dentry *dentry,
- struct nameidata *nd)
+static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
int ret = 0; /* if all else fails, just return false */
struct ocfs2_super *osb;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
@@ -170,13 +169,11 @@
u64 parent_blkno,
int skip_unhashed)
{
- struct list_head *p;
- struct dentry *dentry = NULL;
+ struct hlist_node *p;
+ struct dentry *dentry;
spin_lock(&inode->i_lock);
- list_for_each(p, &inode->i_dentry) {
- dentry = list_entry(p, struct dentry, d_alias);
-
+ hlist_for_each_entry(dentry, p, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
if (ocfs2_match_dentry(dentry, parent_blkno, skip_unhashed)) {
trace_ocfs2_find_local_alias(dentry->d_name.len,
@@ -184,16 +181,13 @@
dget_dlock(dentry);
spin_unlock(&dentry->d_lock);
- break;
+ spin_unlock(&inode->i_lock);
+ return dentry;
}
spin_unlock(&dentry->d_lock);
-
- dentry = NULL;
}
-
spin_unlock(&inode->i_lock);
-
- return dentry;
+ return NULL;
}
DEFINE_SPINLOCK(dentry_attach_lock);
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index e31d6ae..83b6f98 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -526,7 +526,7 @@
static int dlmfs_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int status = 0;
struct inode *inode;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 81a4cd2..4f7795f 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -456,7 +456,7 @@
stats->ls_gets++;
stats->ls_total += ktime_to_ns(kt);
/* overflow */
- if (unlikely(stats->ls_gets) == 0) {
+ if (unlikely(stats->ls_gets == 0)) {
stats->ls_gets++;
stats->ls_total = ktime_to_ns(kt);
}
@@ -3932,6 +3932,8 @@
static void ocfs2_schedule_blocked_lock(struct ocfs2_super *osb,
struct ocfs2_lock_res *lockres)
{
+ unsigned long flags;
+
assert_spin_locked(&lockres->l_lock);
if (lockres->l_flags & OCFS2_LOCK_FREEING) {
@@ -3945,21 +3947,22 @@
lockres_or_flags(lockres, OCFS2_LOCK_QUEUED);
- spin_lock(&osb->dc_task_lock);
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
if (list_empty(&lockres->l_blocked_list)) {
list_add_tail(&lockres->l_blocked_list,
&osb->blocked_lock_list);
osb->blocked_lock_count++;
}
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
}
static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb)
{
unsigned long processed;
+ unsigned long flags;
struct ocfs2_lock_res *lockres;
- spin_lock(&osb->dc_task_lock);
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
/* grab this early so we know to try again if a state change and
* wake happens part-way through our work */
osb->dc_work_sequence = osb->dc_wake_sequence;
@@ -3972,38 +3975,40 @@
struct ocfs2_lock_res, l_blocked_list);
list_del_init(&lockres->l_blocked_list);
osb->blocked_lock_count--;
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
BUG_ON(!processed);
processed--;
ocfs2_process_blocked_lock(osb, lockres);
- spin_lock(&osb->dc_task_lock);
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
}
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
}
static int ocfs2_downconvert_thread_lists_empty(struct ocfs2_super *osb)
{
int empty = 0;
+ unsigned long flags;
- spin_lock(&osb->dc_task_lock);
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
if (list_empty(&osb->blocked_lock_list))
empty = 1;
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
return empty;
}
static int ocfs2_downconvert_thread_should_wake(struct ocfs2_super *osb)
{
int should_wake = 0;
+ unsigned long flags;
- spin_lock(&osb->dc_task_lock);
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
if (osb->dc_work_sequence != osb->dc_wake_sequence)
should_wake = 1;
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
return should_wake;
}
@@ -4033,10 +4038,12 @@
void ocfs2_wake_downconvert_thread(struct ocfs2_super *osb)
{
- spin_lock(&osb->dc_task_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&osb->dc_task_lock, flags);
/* make sure the voting thread gets a swipe at whatever changes
* the caller may have made to the voting state */
osb->dc_wake_sequence++;
- spin_unlock(&osb->dc_task_lock);
+ spin_unlock_irqrestore(&osb->dc_task_lock, flags);
wake_up(&osb->dc_event);
}
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 2f5b92e..70b5863 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -923,8 +923,6 @@
ocfs2_inode_unlock(inode, 0);
out:
- if (ret && ret != -ENXIO)
- ret = -ENXIO;
return ret;
}
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 061591a..7602783 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1950,7 +1950,7 @@
if (ret < 0)
mlog_errno(ret);
- if (file->f_flags & O_SYNC)
+ if (file && (file->f_flags & O_SYNC))
handle->h_sync = 1;
ocfs2_commit_trans(osb, handle);
@@ -2422,8 +2422,10 @@
unaligned_dio = 0;
}
- if (unaligned_dio)
+ if (unaligned_dio) {
+ ocfs2_iocb_clear_unaligned_aio(iocb);
atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio);
+ }
out:
if (rw_level != -1)
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 9f39c64..f1fd074 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -98,7 +98,7 @@
#define OCFS2_ORPHAN_NAMELEN ((int)(2 * sizeof(u64)))
static struct dentry *ocfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int status;
u64 blkno;
@@ -618,7 +618,7 @@
static int ocfs2_create(struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int ret;
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 92fcd57..0a86e30 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -399,8 +399,6 @@
msecs_to_jiffies(oinfo->dqi_syncms));
out_err:
- if (status)
- mlog_errno(status);
return status;
out_unlock:
ocfs2_unlock_global_qf(oinfo, 0);
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index f00576e..fb5b3ff 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -285,13 +285,13 @@
}
static int omfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
return omfs_add_node(dir, dentry, mode | S_IFREG);
}
static struct dentry *omfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct buffer_head *bh;
struct inode *inode = NULL;
diff --git a/fs/open.c b/fs/open.c
index d6c79a0..75bea86 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -397,10 +397,10 @@
{
struct file *file;
struct inode *inode;
- int error;
+ int error, fput_needed;
error = -EBADF;
- file = fget(fd);
+ file = fget_raw_light(fd, &fput_needed);
if (!file)
goto out;
@@ -414,7 +414,7 @@
if (!error)
set_fs_pwd(current->fs, &file->f_path);
out_putf:
- fput(file);
+ fput_light(file, fput_needed);
out:
return error;
}
@@ -537,25 +537,6 @@
return error;
}
-SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
-{
- struct path path;
- int error;
-
- error = user_path(filename, &path);
- if (error)
- goto out;
- error = mnt_want_write(path.mnt);
- if (error)
- goto out_release;
- error = chown_common(&path, user, group);
- mnt_drop_write(path.mnt);
-out_release:
- path_put(&path);
-out:
- return error;
-}
-
SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
gid_t, group, int, flag)
{
@@ -583,23 +564,15 @@
return error;
}
+SYSCALL_DEFINE3(chown, const char __user *, filename, uid_t, user, gid_t, group)
+{
+ return sys_fchownat(AT_FDCWD, filename, user, group, 0);
+}
+
SYSCALL_DEFINE3(lchown, const char __user *, filename, uid_t, user, gid_t, group)
{
- struct path path;
- int error;
-
- error = user_lpath(filename, &path);
- if (error)
- goto out;
- error = mnt_want_write(path.mnt);
- if (error)
- goto out_release;
- error = chown_common(&path, user, group);
- mnt_drop_write(path.mnt);
-out_release:
- path_put(&path);
-out:
- return error;
+ return sys_fchownat(AT_FDCWD, filename, user, group,
+ AT_SYMLINK_NOFOLLOW);
}
SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
@@ -667,10 +640,9 @@
return 0;
}
-static struct file *do_dentry_open(struct dentry *dentry, struct vfsmount *mnt,
- struct file *f,
- int (*open)(struct inode *, struct file *),
- const struct cred *cred)
+static int do_dentry_open(struct file *f,
+ int (*open)(struct inode *, struct file *),
+ const struct cred *cred)
{
static const struct file_operations empty_fops = {};
struct inode *inode;
@@ -682,9 +654,9 @@
if (unlikely(f->f_flags & O_PATH))
f->f_mode = FMODE_PATH;
- inode = dentry->d_inode;
+ inode = f->f_path.dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
- error = __get_file_write_access(inode, mnt);
+ error = __get_file_write_access(inode, f->f_path.mnt);
if (error)
goto cleanup_file;
if (!special_file(inode->i_mode))
@@ -692,14 +664,12 @@
}
f->f_mapping = inode->i_mapping;
- f->f_path.dentry = dentry;
- f->f_path.mnt = mnt;
f->f_pos = 0;
file_sb_list_add(f, inode->i_sb);
if (unlikely(f->f_mode & FMODE_PATH)) {
f->f_op = &empty_fops;
- return f;
+ return 0;
}
f->f_op = fops_get(inode->i_fop);
@@ -726,10 +696,11 @@
file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
- return f;
+ return 0;
cleanup_all:
fops_put(f->f_op);
+ file_sb_list_del(f);
if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
if (!special_file(inode->i_mode)) {
@@ -740,118 +711,60 @@
* here, so just reset the state.
*/
file_reset_write(f);
- mnt_drop_write(mnt);
+ mnt_drop_write(f->f_path.mnt);
}
}
- file_sb_list_del(f);
- f->f_path.dentry = NULL;
- f->f_path.mnt = NULL;
cleanup_file:
- dput(dentry);
- mntput(mnt);
- return ERR_PTR(error);
-}
-
-static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
- struct file *f,
- int (*open)(struct inode *, struct file *),
- const struct cred *cred)
-{
- struct file *res = do_dentry_open(dentry, mnt, f, open, cred);
- if (!IS_ERR(res)) {
- int error = open_check_o_direct(f);
- if (error) {
- fput(res);
- res = ERR_PTR(error);
- }
- } else {
- put_filp(f);
- }
- return res;
+ path_put(&f->f_path);
+ f->f_path.mnt = NULL;
+ f->f_path.dentry = NULL;
+ return error;
}
/**
- * lookup_instantiate_filp - instantiates the open intent filp
- * @nd: pointer to nameidata
+ * finish_open - finish opening a file
+ * @od: opaque open data
* @dentry: pointer to dentry
* @open: open callback
*
- * Helper for filesystems that want to use lookup open intents and pass back
- * a fully instantiated struct file to the caller.
- * This function is meant to be called from within a filesystem's
- * lookup method.
- * Beware of calling it for non-regular files! Those ->open methods might block
- * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo,
- * leading to a deadlock, as nobody can open that fifo anymore, because
- * another process to open fifo will block on locked parent when doing lookup).
- * Note that in case of error, nd->intent.open.file is destroyed, but the
- * path information remains valid.
+ * This can be used to finish opening a file passed to i_op->atomic_open().
+ *
* If the open callback is set to NULL, then the standard f_op->open()
* filesystem callback is substituted.
*/
-struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
- int (*open)(struct inode *, struct file *))
+int finish_open(struct file *file, struct dentry *dentry,
+ int (*open)(struct inode *, struct file *),
+ int *opened)
{
- const struct cred *cred = current_cred();
+ int error;
+ BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
- if (IS_ERR(nd->intent.open.file))
- goto out;
- if (IS_ERR(dentry))
- goto out_err;
- nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
- nd->intent.open.file,
- open, cred);
-out:
- return nd->intent.open.file;
-out_err:
- release_open_intent(nd);
- nd->intent.open.file = ERR_CAST(dentry);
- goto out;
+ mntget(file->f_path.mnt);
+ file->f_path.dentry = dget(dentry);
+
+ error = do_dentry_open(file, open, current_cred());
+ if (!error)
+ *opened |= FILE_OPENED;
+
+ return error;
}
-EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
+EXPORT_SYMBOL(finish_open);
/**
- * nameidata_to_filp - convert a nameidata to an open filp.
- * @nd: pointer to nameidata
- * @flags: open flags
+ * finish_no_open - finish ->atomic_open() without opening the file
*
- * Note that this function destroys the original nameidata
+ * @od: opaque open data
+ * @dentry: dentry or NULL (as returned from ->lookup())
+ *
+ * This can be used to set the result of a successful lookup in ->atomic_open().
+ * The filesystem's atomic_open() method shall return NULL after calling this.
*/
-struct file *nameidata_to_filp(struct nameidata *nd)
+int finish_no_open(struct file *file, struct dentry *dentry)
{
- const struct cred *cred = current_cred();
- struct file *filp;
-
- /* Pick up the filp from the open intent */
- filp = nd->intent.open.file;
-
- /* Has the filesystem initialised the file for us? */
- if (filp->f_path.dentry != NULL) {
- nd->intent.open.file = NULL;
- } else {
- struct file *res;
-
- path_get(&nd->path);
- res = do_dentry_open(nd->path.dentry, nd->path.mnt,
- filp, NULL, cred);
- if (!IS_ERR(res)) {
- int error;
-
- nd->intent.open.file = NULL;
- BUG_ON(res != filp);
-
- error = open_check_o_direct(filp);
- if (error) {
- fput(filp);
- filp = ERR_PTR(error);
- }
- } else {
- /* Allow nd->intent.open.file to be recycled */
- filp = res;
- }
- }
- return filp;
+ file->f_path.dentry = dentry;
+ return 1;
}
+EXPORT_SYMBOL(finish_no_open);
/*
* dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
@@ -877,7 +790,20 @@
}
f->f_flags = flags;
- return __dentry_open(dentry, mnt, f, NULL, cred);
+ f->f_path.mnt = mnt;
+ f->f_path.dentry = dentry;
+ error = do_dentry_open(f, NULL, cred);
+ if (!error) {
+ error = open_check_o_direct(f);
+ if (error) {
+ fput(f);
+ f = ERR_PTR(error);
+ }
+ } else {
+ put_filp(f);
+ f = ERR_PTR(error);
+ }
+ return f;
}
EXPORT_SYMBOL(dentry_open);
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index bc49c97..4a34779 100644
--- a/fs/openpromfs/inode.c
+++ b/fs/openpromfs/inode.c
@@ -170,13 +170,13 @@
.llseek = generic_file_llseek,
};
-static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, struct nameidata *);
+static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, unsigned int);
static const struct inode_operations openprom_inode_operations = {
.lookup = openpromfs_lookup,
};
-static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct op_inode_info *ent_oi, *oi = OP_I(dir);
struct device_node *dp, *child;
diff --git a/fs/pnode.c b/fs/pnode.c
index bed378d..3e000a5 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -237,8 +237,9 @@
source = get_source(m, prev_dest_mnt, prev_src_mnt, &type);
- if (!(child = copy_tree(source, source->mnt.mnt_root, type))) {
- ret = -ENOMEM;
+ child = copy_tree(source, source->mnt.mnt_root, type);
+ if (IS_ERR(child)) {
+ ret = PTR_ERR(child);
list_splice(tree_list, tmp_list.prev);
goto out;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 437195f..2772208 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1427,16 +1427,19 @@
static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd)
{
struct inode *inode = dentry->d_inode;
+ struct path path;
int error = -EACCES;
- /* We don't need a base pointer in the /proc filesystem */
- path_put(&nd->path);
-
/* Are we allowed to snoop on the tasks file descriptors? */
if (!proc_fd_access_allowed(inode))
goto out;
- error = PROC_I(inode)->op.proc_get_link(dentry, &nd->path);
+ error = PROC_I(inode)->op.proc_get_link(dentry, &path);
+ if (error)
+ goto out;
+
+ nd_jump_link(nd, &path);
+ return NULL;
out:
return ERR_PTR(error);
}
@@ -1601,13 +1604,13 @@
* made this apply to all per process world readable and executable
* directories.
*/
-int pid_revalidate(struct dentry *dentry, struct nameidata *nd)
+int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
const struct cred *cred;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
@@ -1781,7 +1784,7 @@
return proc_fd_info(dentry->d_inode, path, NULL);
}
-static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
@@ -1789,7 +1792,7 @@
struct files_struct *files;
const struct cred *cred;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
@@ -1868,7 +1871,7 @@
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, NULL))
+ if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
@@ -1956,7 +1959,7 @@
}
static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
}
@@ -2003,7 +2006,7 @@
return 0;
}
-static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
bool exact_vma_exists = false;
@@ -2013,7 +2016,7 @@
struct inode *inode;
int status = 0;
- if (nd && nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
if (!capable(CAP_SYS_ADMIN)) {
@@ -2145,7 +2148,7 @@
}
static struct dentry *proc_map_files_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
unsigned long vm_start, vm_end;
struct vm_area_struct *vma;
@@ -2371,7 +2374,7 @@
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (tid_fd_revalidate(dentry, NULL))
+ if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
@@ -2380,7 +2383,7 @@
static struct dentry *proc_lookupfdinfo(struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
}
@@ -2430,7 +2433,7 @@
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
@@ -2630,7 +2633,7 @@
};
static struct dentry *proc_attr_dir_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
return proc_pident_lookup(dir, dentry,
attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
@@ -3114,7 +3117,8 @@
.llseek = default_llseek,
};
-static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
return proc_pident_lookup(dir, dentry,
tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
}
@@ -3237,13 +3241,13 @@
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *result;
struct task_struct *task;
@@ -3470,7 +3474,8 @@
tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
}
-static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){
+static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
+{
return proc_pident_lookup(dir, dentry,
tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
}
@@ -3508,13 +3513,13 @@
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
-static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *result = ERR_PTR(-ENOENT);
struct task_struct *task;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 2edf34f..b3647fe 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -446,7 +446,7 @@
}
struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
return proc_lookup_de(PDE(dir), dir, dentry);
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index eca4aca..e1167a1 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -106,7 +106,7 @@
extern spinlock_t proc_subdir_lock;
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
+struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int);
int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
unsigned long task_vsize(struct mm_struct *);
unsigned long task_statm(struct mm_struct *,
@@ -132,7 +132,7 @@
* of the /proc/<pid> subdirectories.
*/
int proc_readdir(struct file *, void *, filldir_t);
-struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
+struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
@@ -142,7 +142,7 @@
int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
const char *name, int len,
instantiate_t instantiate, struct task_struct *task, const void *ptr);
-int pid_revalidate(struct dentry *dentry, struct nameidata *nd);
+int pid_revalidate(struct dentry *dentry, unsigned int flags);
struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task);
extern const struct dentry_operations pid_dentry_operations;
int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 0d9e23a..b178ed7 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -56,7 +56,7 @@
d_set_d_op(dentry, &pid_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
- if (pid_revalidate(dentry, NULL))
+ if (pid_revalidate(dentry, 0))
error = NULL;
out:
return error;
@@ -140,7 +140,7 @@
};
static struct dentry *proc_ns_dir_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct dentry *error;
struct task_struct *task = get_proc_task(dir);
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 06e1cc1..fe72cd0 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -119,7 +119,7 @@
}
static struct dentry *proc_tgid_net_lookup(struct inode *dir,
- struct dentry *dentry, struct nameidata *nd)
+ struct dentry *dentry, unsigned int flags)
{
struct dentry *de;
struct net *net;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 3476bca..dfafeb2 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -433,7 +433,7 @@
}
static struct dentry *proc_sys_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct ctl_table_header *head = grab_header(dir);
struct ctl_table_header *h = NULL;
@@ -794,9 +794,9 @@
.getattr = proc_sys_getattr,
};
-static int proc_sys_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags)
{
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
return !PROC_I(dentry->d_inode)->sysctl->unregistering;
}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 7c30fce..9a2d9fd 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -111,7 +111,7 @@
options = data;
}
- sb = sget(fs_type, proc_test_super, proc_set_super, ns);
+ sb = sget(fs_type, proc_test_super, proc_set_super, flags, ns);
if (IS_ERR(sb))
return ERR_CAST(sb);
@@ -121,7 +121,6 @@
}
if (!sb->s_root) {
- sb->s_flags = flags;
err = proc_fill_super(sb);
if (err) {
deactivate_locked_super(sb);
@@ -200,13 +199,12 @@
return 0;
}
-static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
- if (!proc_lookup(dir, dentry, nd)) {
+ if (!proc_lookup(dir, dentry, flags))
return NULL;
- }
- return proc_pid_lookup(dir, dentry, nd);
+ return proc_pid_lookup(dir, dentry, flags);
}
static int proc_root_readdir(struct file * filp,
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 5e289a7..5fe34c3 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -17,7 +17,7 @@
static unsigned mounts_poll(struct file *file, poll_table *wait)
{
- struct proc_mounts *p = file->private_data;
+ struct proc_mounts *p = proc_mounts(file->private_data);
struct mnt_namespace *ns = p->ns;
unsigned res = POLLIN | POLLRDNORM;
@@ -121,7 +121,7 @@
static int show_mountinfo(struct seq_file *m, struct vfsmount *mnt)
{
- struct proc_mounts *p = m->private;
+ struct proc_mounts *p = proc_mounts(m);
struct mount *r = real_mount(mnt);
struct super_block *sb = mnt->mnt_sb;
struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
@@ -268,7 +268,6 @@
if (ret)
goto err_free;
- p->m.private = p;
p->ns = ns;
p->root = root;
p->m.poll_event = ns->event;
@@ -288,7 +287,7 @@
static int mounts_release(struct inode *inode, struct file *file)
{
- struct proc_mounts *p = file->private_data;
+ struct proc_mounts *p = proc_mounts(file->private_data);
path_put(&p->root);
put_mnt_ns(p->ns);
return seq_release(inode, file);
diff --git a/fs/qnx4/namei.c b/fs/qnx4/namei.c
index a512c0b..d024505 100644
--- a/fs/qnx4/namei.c
+++ b/fs/qnx4/namei.c
@@ -95,7 +95,7 @@
return NULL;
}
-struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+struct dentry * qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
int ino;
struct qnx4_inode_entry *de;
diff --git a/fs/qnx4/qnx4.h b/fs/qnx4/qnx4.h
index 244d462..34e2d32 100644
--- a/fs/qnx4/qnx4.h
+++ b/fs/qnx4/qnx4.h
@@ -23,7 +23,7 @@
};
extern struct inode *qnx4_iget(struct super_block *, unsigned long);
-extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd);
+extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
diff --git a/fs/qnx6/inode.c b/fs/qnx6/inode.c
index e44012d..2049c81 100644
--- a/fs/qnx6/inode.c
+++ b/fs/qnx6/inode.c
@@ -622,7 +622,6 @@
static void qnx6_i_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
- INIT_LIST_HEAD(&inode->i_dentry);
kmem_cache_free(qnx6_inode_cachep, QNX6_I(inode));
}
diff --git a/fs/qnx6/namei.c b/fs/qnx6/namei.c
index 8a97289..0561326 100644
--- a/fs/qnx6/namei.c
+++ b/fs/qnx6/namei.c
@@ -13,7 +13,7 @@
#include "qnx6.h"
struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
unsigned ino;
struct page *page;
diff --git a/fs/qnx6/qnx6.h b/fs/qnx6/qnx6.h
index 6c5e02a..b00fcc9 100644
--- a/fs/qnx6/qnx6.h
+++ b/fs/qnx6/qnx6.h
@@ -45,7 +45,7 @@
extern struct inode *qnx6_iget(struct super_block *sb, unsigned ino);
extern struct dentry *qnx6_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd);
+ unsigned int flags);
#ifdef CONFIG_QNX6FS_DEBUG
extern void qnx6_superblock_debug(struct qnx6_super_block *,
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index fbb0b47..d5378d0 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -110,6 +110,7 @@
/* prevent the page from being discarded on memory pressure */
SetPageDirty(page);
+ SetPageUptodate(page);
unlock_page(page);
put_page(page);
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index a1fdabe..eab8c09 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -114,7 +114,7 @@
return retval;
}
-static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd)
+static int ramfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
{
return ramfs_mknod(dir, dentry, mode | S_IFREG, 0);
}
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 84e8a69..3916be1 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -322,7 +322,7 @@
}
static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int retval;
int lock_depth;
@@ -573,7 +573,7 @@
}
static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
int retval;
struct inode *inode;
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 2c1ade6..e60e870 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -403,7 +403,7 @@
if (l)
return NULL;
- if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, s)))
+ if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, s)))
return NULL;
up_write(&s->s_umount);
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 46fc1c2..d319963 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -62,7 +62,7 @@
static int xattr_create(struct inode *dir, struct dentry *dentry, int mode)
{
BUG_ON(!mutex_is_locked(&dir->i_mutex));
- return dir->i_op->create(dir, dentry, mode, NULL);
+ return dir->i_op->create(dir, dentry, mode, true);
}
#endif
@@ -942,7 +942,7 @@
return generic_permission(inode, mask);
}
-static int xattr_hide_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int xattr_hide_revalidate(struct dentry *dentry, unsigned int flags)
{
return -EPERM;
}
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index e64f6b5..77c5f21 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -210,7 +210,7 @@
* look up an entry in a directory
*/
static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
unsigned long offset, maxoff;
struct inode *inode;
diff --git a/fs/splice.c b/fs/splice.c
index c9f1318..7bf08fa 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -273,13 +273,16 @@
* Check if we need to grow the arrays holding pages and partial page
* descriptions.
*/
-int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
{
- if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ unsigned int buffers = ACCESS_ONCE(pipe->buffers);
+
+ spd->nr_pages_max = buffers;
+ if (buffers <= PIPE_DEF_BUFFERS)
return 0;
- spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL);
- spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL);
+ spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL);
+ spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL);
if (spd->pages && spd->partial)
return 0;
@@ -289,10 +292,9 @@
return -ENOMEM;
}
-void splice_shrink_spd(struct pipe_inode_info *pipe,
- struct splice_pipe_desc *spd)
+void splice_shrink_spd(struct splice_pipe_desc *spd)
{
- if (pipe->buffers <= PIPE_DEF_BUFFERS)
+ if (spd->nr_pages_max <= PIPE_DEF_BUFFERS)
return;
kfree(spd->pages);
@@ -315,6 +317,7 @@
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -326,7 +329,7 @@
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- nr_pages = min(req_pages, pipe->buffers);
+ nr_pages = min(req_pages, spd.nr_pages_max);
/*
* Lookup the (hopefully) full range of pages we need.
@@ -497,7 +500,7 @@
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return error;
}
@@ -598,6 +601,7 @@
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &default_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -608,8 +612,8 @@
res = -ENOMEM;
vec = __vec;
- if (pipe->buffers > PIPE_DEF_BUFFERS) {
- vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL);
+ if (spd.nr_pages_max > PIPE_DEF_BUFFERS) {
+ vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL);
if (!vec)
goto shrink_ret;
}
@@ -617,7 +621,7 @@
offset = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) {
+ for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) {
struct page *page;
page = alloc_page(GFP_USER);
@@ -665,7 +669,7 @@
shrink_ret:
if (vec != __vec)
kfree(vec);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return res;
err:
@@ -1614,6 +1618,7 @@
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &user_page_pipe_buf_ops,
.spd_release = spd_release_page,
@@ -1629,13 +1634,13 @@
spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages,
spd.partial, false,
- pipe->buffers);
+ spd.nr_pages_max);
if (spd.nr_pages <= 0)
ret = spd.nr_pages;
else
ret = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
return ret;
}
diff --git a/fs/squashfs/namei.c b/fs/squashfs/namei.c
index abcc58f..7834a51 100644
--- a/fs/squashfs/namei.c
+++ b/fs/squashfs/namei.c
@@ -134,7 +134,7 @@
static struct dentry *squashfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
const unsigned char *name = dentry->d_name.name;
int len = dentry->d_name.len;
diff --git a/fs/super.c b/fs/super.c
index cf00177..c743fb3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -105,11 +105,12 @@
/**
* alloc_super - create new superblock
* @type: filesystem type superblock should belong to
+ * @flags: the mount flags
*
* Allocates and initializes a new &struct super_block. alloc_super()
* returns a pointer new superblock or %NULL if allocation had failed.
*/
-static struct super_block *alloc_super(struct file_system_type *type)
+static struct super_block *alloc_super(struct file_system_type *type, int flags)
{
struct super_block *s = kzalloc(sizeof(struct super_block), GFP_USER);
static const struct super_operations default_op;
@@ -136,6 +137,7 @@
#else
INIT_LIST_HEAD(&s->s_files);
#endif
+ s->s_flags = flags;
s->s_bdi = &default_backing_dev_info;
INIT_HLIST_NODE(&s->s_instances);
INIT_HLIST_BL_HEAD(&s->s_anon);
@@ -415,11 +417,13 @@
* @type: filesystem type superblock should belong to
* @test: comparison callback
* @set: setup callback
+ * @flags: mount flags
* @data: argument to each of them
*/
struct super_block *sget(struct file_system_type *type,
int (*test)(struct super_block *,void *),
int (*set)(struct super_block *,void *),
+ int flags,
void *data)
{
struct super_block *s = NULL;
@@ -450,7 +454,7 @@
}
if (!s) {
spin_unlock(&sb_lock);
- s = alloc_super(type);
+ s = alloc_super(type, flags);
if (!s)
return ERR_PTR(-ENOMEM);
goto retry;
@@ -925,13 +929,12 @@
{
struct super_block *sb;
- sb = sget(fs_type, ns_test_super, ns_set_super, data);
+ sb = sget(fs_type, ns_test_super, ns_set_super, flags, data);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!sb->s_root) {
int err;
- sb->s_flags = flags;
err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (err) {
deactivate_locked_super(sb);
@@ -992,7 +995,8 @@
error = -EBUSY;
goto error_bdev;
}
- s = sget(fs_type, test_bdev_super, set_bdev_super, bdev);
+ s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC,
+ bdev);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s))
goto error_s;
@@ -1017,7 +1021,6 @@
} else {
char b[BDEVNAME_SIZE];
- s->s_flags = flags | MS_NOSEC;
s->s_mode = mode;
strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
sb_set_blocksize(s, block_size(bdev));
@@ -1062,13 +1065,11 @@
int (*fill_super)(struct super_block *, void *, int))
{
int error;
- struct super_block *s = sget(fs_type, NULL, set_anon_super, NULL);
+ struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
- s->s_flags = flags;
-
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
@@ -1091,11 +1092,10 @@
struct super_block *s;
int error;
- s = sget(fs_type, compare_single, set_anon_super, NULL);
+ s = sget(fs_type, compare_single, set_anon_super, flags, NULL);
if (IS_ERR(s))
return ERR_CAST(s);
if (!s->s_root) {
- s->s_flags = flags;
error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(s);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index e6bb9b2..a5cf784 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -300,15 +300,15 @@
static int sysfs_dentry_delete(const struct dentry *dentry)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
- return !!(sd->s_flags & SYSFS_FLAG_REMOVED);
+ return !(sd && !(sd->s_flags & SYSFS_FLAG_REMOVED));
}
-static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd)
+static int sysfs_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
struct sysfs_dirent *sd;
int is_dir;
- if (nd->flags & LOOKUP_RCU)
+ if (flags & LOOKUP_RCU)
return -ECHILD;
sd = dentry->d_fsdata;
@@ -355,18 +355,15 @@
return 0;
}
-static void sysfs_dentry_iput(struct dentry *dentry, struct inode *inode)
+static void sysfs_dentry_release(struct dentry *dentry)
{
- struct sysfs_dirent * sd = dentry->d_fsdata;
-
- sysfs_put(sd);
- iput(inode);
+ sysfs_put(dentry->d_fsdata);
}
-static const struct dentry_operations sysfs_dentry_ops = {
+const struct dentry_operations sysfs_dentry_ops = {
.d_revalidate = sysfs_dentry_revalidate,
.d_delete = sysfs_dentry_delete,
- .d_iput = sysfs_dentry_iput,
+ .d_release = sysfs_dentry_release,
};
struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
@@ -764,7 +761,7 @@
}
static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct dentry *ret = NULL;
struct dentry *parent = dentry->d_parent;
@@ -786,6 +783,7 @@
ret = ERR_PTR(-ENOENT);
goto out_unlock;
}
+ dentry->d_fsdata = sysfs_get(sd);
/* attach dentry and inode */
inode = sysfs_get_inode(dir->i_sb, sd);
@@ -795,16 +793,7 @@
}
/* instantiate and hash dentry */
- ret = d_find_alias(inode);
- if (!ret) {
- d_set_d_op(dentry, &sysfs_dentry_ops);
- dentry->d_fsdata = sysfs_get(sd);
- d_add(dentry, inode);
- } else {
- d_move(ret, dentry);
- iput(inode);
- }
-
+ ret = d_materialise_unique(dentry, inode);
out_unlock:
mutex_unlock(&sysfs_mutex);
return ret;
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 52c3bdb..71eb7e2 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -68,6 +68,7 @@
}
root->d_fsdata = &sysfs_root;
sb->s_root = root;
+ sb->s_d_op = &sysfs_dentry_ops;
return 0;
}
@@ -117,13 +118,12 @@
for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
info->ns[type] = kobj_ns_grab_current(type);
- sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info);
+ sb = sget(fs_type, sysfs_test_super, sysfs_set_super, flags, info);
if (IS_ERR(sb) || sb->s_fs_info != info)
free_sysfs_super_info(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!sb->s_root) {
- sb->s_flags = flags;
error = sysfs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (error) {
deactivate_locked_super(sb);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index 661a963..d73c093 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -157,6 +157,7 @@
*/
extern struct mutex sysfs_mutex;
extern spinlock_t sysfs_assoc_lock;
+extern const struct dentry_operations sysfs_dentry_ops;
extern const struct file_operations sysfs_dir_operations;
extern const struct inode_operations sysfs_dir_inode_operations;
diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c
index d7466e2..1c0d5f2 100644
--- a/fs/sysv/namei.c
+++ b/fs/sysv/namei.c
@@ -43,7 +43,7 @@
.d_hash = sysv_hash,
};
-static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, struct nameidata *nd)
+static struct dentry *sysv_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -80,7 +80,7 @@
return err;
}
-static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, struct nameidata *nd)
+static int sysv_create(struct inode * dir, struct dentry * dentry, umode_t mode, bool excl)
{
return sysv_mknod(dir, dentry, mode, 0);
}
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 84a7e6f..92df3b0 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -2918,7 +2918,7 @@
struct dentry *dent;
struct ubifs_debug_info *d = c->dbg;
- if (!IS_ENABLED(DEBUG_FS))
+ if (!IS_ENABLED(CONFIG_DEBUG_FS))
return 0;
n = snprintf(d->dfs_dir_name, UBIFS_DFS_DIR_LEN + 1, UBIFS_DFS_DIR_NAME,
@@ -3013,7 +3013,7 @@
*/
void dbg_debugfs_exit_fs(struct ubifs_info *c)
{
- if (IS_ENABLED(DEBUG_FS))
+ if (IS_ENABLED(CONFIG_DEBUG_FS))
debugfs_remove_recursive(c->dbg->dfs_dir);
}
@@ -3099,7 +3099,7 @@
const char *fname;
struct dentry *dent;
- if (!IS_ENABLED(DEBUG_FS))
+ if (!IS_ENABLED(CONFIG_DEBUG_FS))
return 0;
fname = "ubifs";
@@ -3166,7 +3166,7 @@
*/
void dbg_debugfs_exit(void)
{
- if (IS_ENABLED(DEBUG_FS))
+ if (IS_ENABLED(CONFIG_DEBUG_FS))
debugfs_remove_recursive(dfs_rootdir);
}
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index a6d42ef..b1cca89 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -184,7 +184,7 @@
}
static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
int err;
union ubifs_key key;
@@ -246,7 +246,7 @@
}
static int ubifs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
struct ubifs_info *c = dir->i_sb->s_fs_info;
diff --git a/fs/ubifs/find.c b/fs/ubifs/find.c
index 2559d17..28ec13a 100644
--- a/fs/ubifs/find.c
+++ b/fs/ubifs/find.c
@@ -939,8 +939,8 @@
}
dbg_find("LEB %d, dirty %d and free %d flags %#x", lp->lnum, lp->dirty,
lp->free, lp->flags);
- ubifs_assert(lp->flags | LPROPS_TAKEN);
- ubifs_assert(lp->flags | LPROPS_INDEX);
+ ubifs_assert(lp->flags & LPROPS_TAKEN);
+ ubifs_assert(lp->flags & LPROPS_INDEX);
return lnum;
}
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 5862dd9..1c766c3 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -2136,7 +2136,7 @@
dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
- sb = sget(fs_type, sb_test, sb_set, c);
+ sb = sget(fs_type, sb_test, sb_set, flags, c);
if (IS_ERR(sb)) {
err = PTR_ERR(sb);
kfree(c);
@@ -2153,7 +2153,6 @@
goto out_deact;
}
} else {
- sb->s_flags = flags;
err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (err)
goto out_deact;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 1802417..544b279 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -251,7 +251,7 @@
}
static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct inode *inode = NULL;
struct fileIdentDesc cfi;
@@ -551,7 +551,7 @@
}
static int udf_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct udf_fileident_bh fibh;
struct inode *inode;
diff --git a/fs/udf/super.c b/fs/udf/super.c
index ac8a348..8d86a87 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -56,6 +56,7 @@
#include <linux/seq_file.h>
#include <linux/bitmap.h>
#include <linux/crc-itu-t.h>
+#include <linux/log2.h>
#include <asm/byteorder.h>
#include "udf_sb.h"
@@ -1215,16 +1216,65 @@
return ret;
}
+static int udf_load_sparable_map(struct super_block *sb,
+ struct udf_part_map *map,
+ struct sparablePartitionMap *spm)
+{
+ uint32_t loc;
+ uint16_t ident;
+ struct sparingTable *st;
+ struct udf_sparing_data *sdata = &map->s_type_specific.s_sparing;
+ int i;
+ struct buffer_head *bh;
+
+ map->s_partition_type = UDF_SPARABLE_MAP15;
+ sdata->s_packet_len = le16_to_cpu(spm->packetLength);
+ if (!is_power_of_2(sdata->s_packet_len)) {
+ udf_err(sb, "error loading logical volume descriptor: "
+ "Invalid packet length %u\n",
+ (unsigned)sdata->s_packet_len);
+ return -EIO;
+ }
+ if (spm->numSparingTables > 4) {
+ udf_err(sb, "error loading logical volume descriptor: "
+ "Too many sparing tables (%d)\n",
+ (int)spm->numSparingTables);
+ return -EIO;
+ }
+
+ for (i = 0; i < spm->numSparingTables; i++) {
+ loc = le32_to_cpu(spm->locSparingTable[i]);
+ bh = udf_read_tagged(sb, loc, loc, &ident);
+ if (!bh)
+ continue;
+
+ st = (struct sparingTable *)bh->b_data;
+ if (ident != 0 ||
+ strncmp(st->sparingIdent.ident, UDF_ID_SPARING,
+ strlen(UDF_ID_SPARING)) ||
+ sizeof(*st) + le16_to_cpu(st->reallocationTableLen) >
+ sb->s_blocksize) {
+ brelse(bh);
+ continue;
+ }
+
+ sdata->s_spar_map[i] = bh;
+ }
+ map->s_partition_func = udf_get_pblock_spar15;
+ return 0;
+}
+
static int udf_load_logicalvol(struct super_block *sb, sector_t block,
struct kernel_lb_addr *fileset)
{
struct logicalVolDesc *lvd;
- int i, j, offset;
+ int i, offset;
uint8_t type;
struct udf_sb_info *sbi = UDF_SB(sb);
struct genericPartitionMap *gpm;
uint16_t ident;
struct buffer_head *bh;
+ unsigned int table_len;
int ret = 0;
bh = udf_read_tagged(sb, block, block, &ident);
@@ -1232,15 +1282,20 @@
return 1;
BUG_ON(ident != TAG_IDENT_LVD);
lvd = (struct logicalVolDesc *)bh->b_data;
-
- i = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps));
- if (i != 0) {
- ret = i;
+ table_len = le32_to_cpu(lvd->mapTableLength);
+ if (sizeof(*lvd) + table_len > sb->s_blocksize) {
+ udf_err(sb, "error loading logical volume descriptor: "
+ "Partition table too long (%u > %lu)\n", table_len,
+ sb->s_blocksize - sizeof(*lvd));
goto out_bh;
}
+ ret = udf_sb_alloc_partition_maps(sb, le32_to_cpu(lvd->numPartitionMaps));
+ if (ret)
+ goto out_bh;
+
for (i = 0, offset = 0;
- i < sbi->s_partitions && offset < le32_to_cpu(lvd->mapTableLength);
+ i < sbi->s_partitions && offset < table_len;
i++, offset += gpm->partitionMapLength) {
struct udf_part_map *map = &sbi->s_partmaps[i];
gpm = (struct genericPartitionMap *)
@@ -1275,38 +1330,9 @@
} else if (!strncmp(upm2->partIdent.ident,
UDF_ID_SPARABLE,
strlen(UDF_ID_SPARABLE))) {
- uint32_t loc;
- struct sparingTable *st;
- struct sparablePartitionMap *spm =
- (struct sparablePartitionMap *)gpm;
-
- map->s_partition_type = UDF_SPARABLE_MAP15;
- map->s_type_specific.s_sparing.s_packet_len =
- le16_to_cpu(spm->packetLength);
- for (j = 0; j < spm->numSparingTables; j++) {
- struct buffer_head *bh2;
-
- loc = le32_to_cpu(
- spm->locSparingTable[j]);
- bh2 = udf_read_tagged(sb, loc, loc,
- &ident);
- map->s_type_specific.s_sparing.
- s_spar_map[j] = bh2;
-
- if (bh2 == NULL)
- continue;
-
- st = (struct sparingTable *)bh2->b_data;
- if (ident != 0 || strncmp(
- st->sparingIdent.ident,
- UDF_ID_SPARING,
- strlen(UDF_ID_SPARING))) {
- brelse(bh2);
- map->s_type_specific.s_sparing.
- s_spar_map[j] = NULL;
- }
- }
- map->s_partition_func = udf_get_pblock_spar15;
+ if (udf_load_sparable_map(sb, map,
+ (struct sparablePartitionMap *)gpm) < 0)
+ goto out_bh;
} else if (!strncmp(upm2->partIdent.ident,
UDF_ID_METADATA,
strlen(UDF_ID_METADATA))) {
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index a2281ca..90d74b8 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -46,7 +46,7 @@
return err;
}
-static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, unsigned int flags)
{
struct inode * inode = NULL;
ino_t ino;
@@ -71,7 +71,7 @@
* with d_instantiate().
*/
static int ufs_create (struct inode * dir, struct dentry * dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
struct inode *inode;
int err;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 1a25fd8..9c4340f 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -179,7 +179,7 @@
struct inode *dir,
struct dentry *dentry,
umode_t mode,
- struct nameidata *nd)
+ bool flags)
{
return xfs_vn_mknod(dir, dentry, mode, 0);
}
@@ -197,7 +197,7 @@
xfs_vn_lookup(
struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct xfs_inode *cip;
struct xfs_name name;
@@ -222,7 +222,7 @@
xfs_vn_ci_lookup(
struct inode *dir,
struct dentry *dentry,
- struct nameidata *nd)
+ unsigned int flags)
{
struct xfs_inode *ip;
struct xfs_name xname;