summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/aio.c40
-rw-r--r--fs/anon_inodes.c18
-rw-r--r--fs/autofs4/autofs_i.h38
-rw-r--r--fs/autofs4/expire.c8
-rw-r--r--fs/autofs4/inode.c2
-rw-r--r--fs/autofs4/root.c616
-rw-r--r--fs/binfmt_elf.c11
-rw-r--r--fs/binfmt_elf_fdpic.c8
-rw-r--r--fs/btrfs/acl.c47
-rw-r--r--fs/cachefiles/bind.c11
-rw-r--r--fs/cachefiles/rdwr.c2
-rw-r--r--fs/cifs/export.c2
-rw-r--r--fs/compat.c2
-rw-r--r--fs/dcache.c1
-rw-r--r--fs/direct-io.c165
-rw-r--r--fs/ecryptfs/main.c7
-rw-r--r--fs/exportfs/expfs.c2
-rw-r--r--fs/ext2/acl.c79
-rw-r--r--fs/ext2/dir.c2
-rw-r--r--fs/ext2/ext2.h1
-rw-r--r--fs/ext2/file.c21
-rw-r--r--fs/ext2/super.c22
-rw-r--r--fs/ext2/xattr.c11
-rw-r--r--fs/ext2/xattr_security.c16
-rw-r--r--fs/ext2/xattr_trusted.c16
-rw-r--r--fs/ext2/xattr_user.c25
-rw-r--r--fs/ext3/acl.c74
-rw-r--r--fs/ext3/xattr.c31
-rw-r--r--fs/ext3/xattr_security.c20
-rw-r--r--fs/ext3/xattr_trusted.c18
-rw-r--r--fs/ext3/xattr_user.c25
-rw-r--r--fs/ext4/acl.c74
-rw-r--r--fs/ext4/xattr.c31
-rw-r--r--fs/ext4/xattr_security.c20
-rw-r--r--fs/ext4/xattr_trusted.c20
-rw-r--r--fs/ext4/xattr_user.c25
-rw-r--r--fs/fat/fat.h3
-rw-r--r--fs/fat/fatent.c25
-rw-r--r--fs/fat/inode.c8
-rw-r--r--fs/fat/misc.c57
-rw-r--r--fs/file_table.c49
-rw-r--r--fs/fscache/object-list.c2
-rw-r--r--fs/generic_acl.c158
-rw-r--r--fs/gfs2/acl.c16
-rw-r--r--fs/gfs2/inode.c3
-rw-r--r--fs/gfs2/xattr.c69
-rw-r--r--fs/gfs2/xattr.h7
-rw-r--r--fs/hpfs/super.c17
-rw-r--r--fs/hugetlbfs/inode.c17
-rw-r--r--fs/internal.h1
-rw-r--r--fs/isofs/export.c2
-rw-r--r--fs/jffs2/acl.c65
-rw-r--r--fs/jffs2/gc.c3
-rw-r--r--fs/jffs2/readinode.c2
-rw-r--r--fs/jffs2/security.c18
-rw-r--r--fs/jffs2/summary.c2
-rw-r--r--fs/jffs2/xattr.c6
-rw-r--r--fs/jffs2/xattr_trusted.c18
-rw-r--r--fs/jffs2/xattr_user.c18
-rw-r--r--fs/libfs.c1
-rw-r--r--fs/lockd/svc4proc.c4
-rw-r--r--fs/lockd/svcproc.c4
-rw-r--r--fs/namei.c466
-rw-r--r--fs/namespace.c3
-rw-r--r--fs/nfs/Kconfig2
-rw-r--r--fs/nfs/nfs4_fs.h5
-rw-r--r--fs/nfs/nfs4proc.c203
-rw-r--r--fs/nfs/nfs4state.c60
-rw-r--r--fs/nfs/super.c8
-rw-r--r--fs/nfsctl.c2
-rw-r--r--fs/nfsd/auth.c12
-rw-r--r--fs/nfsd/cache.h83
-rw-r--r--fs/nfsd/export.c65
-rw-r--r--fs/nfsd/lockd.c10
-rw-r--r--fs/nfsd/nfs2acl.c27
-rw-r--r--fs/nfsd/nfs3acl.c15
-rw-r--r--fs/nfsd/nfs3proc.c20
-rw-r--r--fs/nfsd/nfs3xdr.c15
-rw-r--r--fs/nfsd/nfs4acl.c12
-rw-r--r--fs/nfsd/nfs4callback.c19
-rw-r--r--fs/nfsd/nfs4idmap.c17
-rw-r--r--fs/nfsd/nfs4proc.c19
-rw-r--r--fs/nfsd/nfs4recover.c16
-rw-r--r--fs/nfsd/nfs4state.c84
-rw-r--r--fs/nfsd/nfs4xdr.c26
-rw-r--r--fs/nfsd/nfscache.c14
-rw-r--r--fs/nfsd/nfsctl.c51
-rw-r--r--fs/nfsd/nfsd.h338
-rw-r--r--fs/nfsd/nfsfh.c102
-rw-r--r--fs/nfsd/nfsfh.h208
-rw-r--r--fs/nfsd/nfsproc.c22
-rw-r--r--fs/nfsd/nfssvc.c22
-rw-r--r--fs/nfsd/nfsxdr.c12
-rw-r--r--fs/nfsd/state.h408
-rw-r--r--fs/nfsd/stats.c11
-rw-r--r--fs/nfsd/vfs.c139
-rw-r--r--fs/nfsd/vfs.h101
-rw-r--r--fs/nfsd/xdr.h173
-rw-r--r--fs/nfsd/xdr3.h344
-rw-r--r--fs/nfsd/xdr4.h562
-rw-r--r--fs/nilfs2/super.c3
-rw-r--r--fs/notify/inotify/inotify_user.c29
-rw-r--r--fs/ocfs2/acl.c87
-rw-r--r--fs/ocfs2/alloc.c4
-rw-r--r--fs/ocfs2/aops.c34
-rw-r--r--fs/ocfs2/xattr.c72
-rw-r--r--fs/open.c4
-rw-r--r--fs/pipe.c29
-rw-r--r--fs/proc/base.c4
-rw-r--r--fs/proc/generic.c21
-rw-r--r--fs/proc/inode.c31
-rw-r--r--fs/proc/internal.h10
-rw-r--r--fs/qnx4/bitmap.c24
-rw-r--r--fs/qnx4/inode.c22
-rw-r--r--fs/reiserfs/Makefile6
-rw-r--r--fs/reiserfs/procfs.c65
-rw-r--r--fs/reiserfs/super.c4
-rw-r--r--fs/reiserfs/xattr.c36
-rw-r--r--fs/reiserfs/xattr_acl.c69
-rw-r--r--fs/reiserfs/xattr_security.c21
-rw-r--r--fs/reiserfs/xattr_trusted.c21
-rw-r--r--fs/reiserfs/xattr_user.c21
-rw-r--r--fs/ufs/dir.c10
-rw-r--r--fs/ufs/namei.c8
-rw-r--r--fs/ufs/super.c52
-rw-r--r--fs/ufs/ufs.h4
-rw-r--r--fs/xattr.c28
-rw-r--r--fs/xfs/linux-2.6/xfs_acl.c57
-rw-r--r--fs/xfs/linux-2.6/xfs_aops.c20
-rw-r--r--fs/xfs/linux-2.6/xfs_xattr.c71
-rw-r--r--fs/xfs/xfs_acl.h3
131 files changed, 4329 insertions, 2323 deletions
diff --git a/fs/aio.c b/fs/aio.c
index c30dfc00610..1cf12b3dd83 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -711,10 +711,8 @@ static ssize_t aio_run_iocb(struct kiocb *iocb)
*/
ret = retry(iocb);
- if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED) {
- BUG_ON(!list_empty(&iocb->ki_wait.task_list));
+ if (ret != -EIOCBRETRY && ret != -EIOCBQUEUED)
aio_complete(iocb, ret, 0);
- }
out:
spin_lock_irq(&ctx->ctx_lock);
@@ -866,13 +864,6 @@ static void try_queue_kicked_iocb(struct kiocb *iocb)
unsigned long flags;
int run = 0;
- /* We're supposed to be the only path putting the iocb back on the run
- * list. If we find that the iocb is *back* on a wait queue already
- * than retry has happened before we could queue the iocb. This also
- * means that the retry could have completed and freed our iocb, no
- * good. */
- BUG_ON((!list_empty(&iocb->ki_wait.task_list)));
-
spin_lock_irqsave(&ctx->ctx_lock, flags);
/* set this inside the lock so that we can't race with aio_run_iocb()
* testing it and putting the iocb on the run list under the lock */
@@ -886,7 +877,7 @@ static void try_queue_kicked_iocb(struct kiocb *iocb)
/*
* kick_iocb:
* Called typically from a wait queue callback context
- * (aio_wake_function) to trigger a retry of the iocb.
+ * to trigger a retry of the iocb.
* The retry is usually executed by aio workqueue
* threads (See aio_kick_handler).
*/
@@ -1520,31 +1511,6 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb)
return 0;
}
-/*
- * aio_wake_function:
- * wait queue callback function for aio notification,
- * Simply triggers a retry of the operation via kick_iocb.
- *
- * This callback is specified in the wait queue entry in
- * a kiocb.
- *
- * Note:
- * This routine is executed with the wait queue lock held.
- * Since kick_iocb acquires iocb->ctx->ctx_lock, it nests
- * the ioctx lock inside the wait queue lock. This is safe
- * because this callback isn't used for wait queues which
- * are nested inside ioctx lock (i.e. ctx->wait)
- */
-static int aio_wake_function(wait_queue_t *wait, unsigned mode,
- int sync, void *key)
-{
- struct kiocb *iocb = container_of(wait, struct kiocb, ki_wait);
-
- list_del_init(&wait->task_list);
- kick_iocb(iocb);
- return 1;
-}
-
static void aio_batch_add(struct address_space *mapping,
struct hlist_head *batch_hash)
{
@@ -1642,8 +1608,6 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
req->ki_buf = (char __user *)(unsigned long)iocb->aio_buf;
req->ki_left = req->ki_nbytes = iocb->aio_nbytes;
req->ki_opcode = iocb->aio_lio_opcode;
- init_waitqueue_func_entry(&req->ki_wait, aio_wake_function);
- INIT_LIST_HEAD(&req->ki_wait.task_list);
ret = aio_setup_iocb(req);
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 2ca7a7cafdb..94f5110c465 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -88,7 +88,7 @@ struct file *anon_inode_getfile(const char *name,
void *priv, int flags)
{
struct qstr this;
- struct dentry *dentry;
+ struct path path;
struct file *file;
int error;
@@ -106,10 +106,11 @@ struct file *anon_inode_getfile(const char *name,
this.name = name;
this.len = strlen(name);
this.hash = 0;
- dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
- if (!dentry)
+ path.dentry = d_alloc(anon_inode_mnt->mnt_sb->s_root, &this);
+ if (!path.dentry)
goto err_module;
+ path.mnt = mntget(anon_inode_mnt);
/*
* We know the anon_inode inode count is always greater than zero,
* so we can avoid doing an igrab() and we can use an open-coded
@@ -117,14 +118,13 @@ struct file *anon_inode_getfile(const char *name,
*/
atomic_inc(&anon_inode_inode->i_count);
- dentry->d_op = &anon_inodefs_dentry_operations;
+ path.dentry->d_op = &anon_inodefs_dentry_operations;
/* Do not publish this dentry inside the global dentry hash table */
- dentry->d_flags &= ~DCACHE_UNHASHED;
- d_instantiate(dentry, anon_inode_inode);
+ path.dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(path.dentry, anon_inode_inode);
error = -ENFILE;
- file = alloc_file(anon_inode_mnt, dentry,
- FMODE_READ | FMODE_WRITE, fops);
+ file = alloc_file(&path, FMODE_READ | FMODE_WRITE, fops);
if (!file)
goto err_dput;
file->f_mapping = anon_inode_inode->i_mapping;
@@ -137,7 +137,7 @@ struct file *anon_inode_getfile(const char *name,
return file;
err_dput:
- dput(dentry);
+ path_put(&path);
err_module:
module_put(fops->owner);
return ERR_PTR(error);
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 8f7cdde4173..0118d67221b 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -60,6 +60,11 @@ do { \
current->pid, __func__, ##args); \
} while (0)
+struct rehash_entry {
+ struct task_struct *task;
+ struct list_head list;
+};
+
/* Unified info structure. This is pointed to by both the dentry and
inode structures. Each file in the filesystem has an instance of this
structure. It holds a reference to the dentry, so dentries are never
@@ -75,6 +80,9 @@ struct autofs_info {
struct completion expire_complete;
struct list_head active;
+ int active_count;
+ struct list_head rehash_list;
+
struct list_head expiring;
struct autofs_sb_info *sbi;
@@ -95,6 +103,8 @@ struct autofs_info {
#define AUTOFS_INF_EXPIRING (1<<0) /* dentry is in the process of expiring */
#define AUTOFS_INF_MOUNTPOINT (1<<1) /* mountpoint status for direct expire */
+#define AUTOFS_INF_PENDING (1<<2) /* dentry pending mount */
+#define AUTOFS_INF_REHASH (1<<3) /* dentry in transit to ->lookup() */
struct autofs_wait_queue {
wait_queue_head_t queue;
@@ -161,7 +171,7 @@ static inline int autofs4_ispending(struct dentry *dentry)
{
struct autofs_info *inf = autofs4_dentry_ino(dentry);
- if (dentry->d_flags & DCACHE_AUTOFS_PENDING)
+ if (inf->flags & AUTOFS_INF_PENDING)
return 1;
if (inf->flags & AUTOFS_INF_EXPIRING)
@@ -264,5 +274,31 @@ out:
return ret;
}
+static inline void autofs4_add_expiring(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ if (ino) {
+ spin_lock(&sbi->lookup_lock);
+ if (list_empty(&ino->expiring))
+ list_add(&ino->expiring, &sbi->expiring_list);
+ spin_unlock(&sbi->lookup_lock);
+ }
+ return;
+}
+
+static inline void autofs4_del_expiring(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ if (ino) {
+ spin_lock(&sbi->lookup_lock);
+ if (!list_empty(&ino->expiring))
+ list_del_init(&ino->expiring);
+ spin_unlock(&sbi->lookup_lock);
+ }
+ return;
+}
+
void autofs4_dentry_release(struct dentry *);
extern void autofs4_kill_sb(struct super_block *);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 3da18d45348..74bc9aa6df3 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -27,7 +27,7 @@ static inline int autofs4_can_expire(struct dentry *dentry,
return 0;
/* No point expiring a pending mount */
- if (dentry->d_flags & DCACHE_AUTOFS_PENDING)
+ if (ino->flags & AUTOFS_INF_PENDING)
return 0;
if (!do_now) {
@@ -279,6 +279,7 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
root->d_mounted--;
}
ino->flags |= AUTOFS_INF_EXPIRING;
+ autofs4_add_expiring(root);
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
return root;
@@ -406,6 +407,7 @@ found:
expired, (int)expired->d_name.len, expired->d_name.name);
ino = autofs4_dentry_ino(expired);
ino->flags |= AUTOFS_INF_EXPIRING;
+ autofs4_add_expiring(expired);
init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
spin_lock(&dcache_lock);
@@ -433,7 +435,7 @@ int autofs4_expire_wait(struct dentry *dentry)
DPRINTK("expire done status=%d", status);
- if (d_unhashed(dentry))
+ if (d_unhashed(dentry) && IS_DEADDIR(dentry->d_inode))
return -EAGAIN;
return status;
@@ -473,6 +475,7 @@ int autofs4_expire_run(struct super_block *sb,
spin_lock(&sbi->fs_lock);
ino = autofs4_dentry_ino(dentry);
ino->flags &= ~AUTOFS_INF_EXPIRING;
+ autofs4_del_expiring(dentry);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
@@ -503,6 +506,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
}
ino->flags &= ~AUTOFS_INF_EXPIRING;
+ autofs4_del_expiring(dentry);
complete_all(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
dput(dentry);
diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c
index 69c8142da83..d0a3de24745 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -49,6 +49,8 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
ino->dentry = NULL;
ino->size = 0;
INIT_LIST_HEAD(&ino->active);
+ INIT_LIST_HEAD(&ino->rehash_list);
+ ino->active_count = 0;
INIT_LIST_HEAD(&ino->expiring);
atomic_set(&ino->count, 0);
}
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index b96a3c57359..30cc9ddf4b7 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -72,6 +72,139 @@ const struct inode_operations autofs4_dir_inode_operations = {
.rmdir = autofs4_dir_rmdir,
};
+static void autofs4_add_active(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ if (ino) {
+ spin_lock(&sbi->lookup_lock);
+ if (!ino->active_count) {
+ if (list_empty(&ino->active))
+ list_add(&ino->active, &sbi->active_list);
+ }
+ ino->active_count++;
+ spin_unlock(&sbi->lookup_lock);
+ }
+ return;
+}
+
+static void autofs4_del_active(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ if (ino) {
+ spin_lock(&sbi->lookup_lock);
+ ino->active_count--;
+ if (!ino->active_count) {
+ if (!list_empty(&ino->active))
+ list_del_init(&ino->active);
+ }
+ spin_unlock(&sbi->lookup_lock);
+ }
+ return;
+}
+
+static void autofs4_add_rehash_entry(struct autofs_info *ino,
+ struct rehash_entry *entry)
+{
+ entry->task = current;
+ INIT_LIST_HEAD(&entry->list);
+ list_add(&entry->list, &ino->rehash_list);
+ return;
+}
+
+static void autofs4_remove_rehash_entry(struct autofs_info *ino)
+{
+ struct list_head *head = &ino->rehash_list;
+ struct rehash_entry *entry;
+ list_for_each_entry(entry, head, list) {
+ if (entry->task == current) {
+ list_del(&entry->list);
+ kfree(entry);
+ break;
+ }
+ }
+ return;
+}
+
+static void autofs4_remove_rehash_entrys(struct autofs_info *ino)
+{
+ struct autofs_sb_info *sbi = ino->sbi;
+ struct rehash_entry *entry, *next;
+ struct list_head *head;
+
+ spin_lock(&sbi->fs_lock);
+ spin_lock(&sbi->lookup_lock);
+ if (!(ino->flags & AUTOFS_INF_REHASH)) {
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&sbi->fs_lock);
+ return;
+ }
+ ino->flags &= ~AUTOFS_INF_REHASH;
+ head = &ino->rehash_list;
+ list_for_each_entry_safe(entry, next, head, list) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&sbi->fs_lock);
+ dput(ino->dentry);
+
+ return;
+}
+
+static void autofs4_revalidate_drop(struct dentry *dentry,
+ struct rehash_entry *entry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ /*
+ * Add to the active list so we can pick this up in
+ * ->lookup(). Also add an entry to a rehash list so
+ * we know when there are no dentrys in flight so we
+ * know when we can rehash the dentry.
+ */
+ spin_lock(&sbi->lookup_lock);
+ if (list_empty(&ino->active))
+ list_add(&ino->active, &sbi->active_list);
+ autofs4_add_rehash_entry(ino, entry);
+ spin_unlock(&sbi->lookup_lock);
+ if (!(ino->flags & AUTOFS_INF_REHASH)) {
+ ino->flags |= AUTOFS_INF_REHASH;
+ dget(dentry);
+ spin_lock(&dentry->d_lock);
+ __d_drop(dentry);
+ spin_unlock(&dentry->d_lock);
+ }
+ return;
+}
+
+static void autofs4_revalidate_rehash(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ if (ino->flags & AUTOFS_INF_REHASH) {
+ spin_lock(&sbi->lookup_lock);
+ autofs4_remove_rehash_entry(ino);
+ if (list_empty(&ino->rehash_list)) {
+ spin_unlock(&sbi->lookup_lock);
+ ino->flags &= ~AUTOFS_INF_REHASH;
+ d_rehash(dentry);
+ dput(ino->dentry);
+ } else
+ spin_unlock(&sbi->lookup_lock);
+ }
+ return;
+}
+
+static unsigned int autofs4_need_mount(unsigned int flags)
+{
+ unsigned int res = 0;
+ if (flags & (TRIGGER_FLAGS | TRIGGER_INTENTS))
+ res = 1;
+ return res;
+}
+
static int autofs4_dir_open(struct inode *inode, struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
@@ -93,7 +226,7 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
* it.
*/
spin_lock(&dcache_lock);
- if (!d_mountpoint(dentry) && __simple_empty(dentry)) {
+ if (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
spin_unlock(&dcache_lock);
return -ENOENT;
}
@@ -103,7 +236,7 @@ out:
return dcache_dir_open(inode, file);
}
-static int try_to_fill_dentry(struct dentry *dentry, int flags)
+static int try_to_fill_dentry(struct dentry *dentry)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
@@ -116,55 +249,17 @@ static int try_to_fill_dentry(struct dentry *dentry, int flags)
* Wait for a pending mount, triggering one if there
* isn't one already
*/
- if (dentry->d_inode == NULL) {
- DPRINTK("waiting for mount name=%.*s",
- dentry->d_name.len, dentry->d_name.name);
-
- status = autofs4_wait(sbi, dentry, NFY_MOUNT);
-
- DPRINTK("mount done status=%d", status);
-
- /* Turn this into a real negative dentry? */
- if (status == -ENOENT) {
- spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
- return status;
- } else if (status) {
- /* Return a negative dentry, but leave it "pending" */
- return status;
- }
- /* Trigger mount for path component or follow link */
- } else if (dentry->d_flags & DCACHE_AUTOFS_PENDING ||
- flags & (TRIGGER_FLAGS | TRIGGER_INTENTS) ||
- current->link_count) {
- DPRINTK("waiting for mount name=%.*s",
- dentry->d_name.len, dentry->d_name.name);
-
- spin_lock(&dentry->d_lock);
- dentry->d_flags |= DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
- status = autofs4_wait(sbi, dentry, NFY_MOUNT);
+ DPRINTK("waiting for mount name=%.*s",
+ dentry->d_name.len, dentry->d_name.name);
- DPRINTK("mount done status=%d", status);
+ status = autofs4_wait(sbi, dentry, NFY_MOUNT);
- if (status) {
- spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
- return status;
- }
- }
-
- /* Initialize expiry counter after successful mount */
- if (ino)
- ino->last_used = jiffies;
+ DPRINTK("mount done status=%d", status);
- spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
+ /* Update expiry counter */
+ ino->last_used = jiffies;
- return 0;
+ return status;
}
/* For autofs direct mounts the follow link triggers the mount */
@@ -202,27 +297,39 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
autofs4_expire_wait(dentry);
/* We trigger a mount for almost all flags */
- lookup_type = nd->flags & (TRIGGER_FLAGS | TRIGGER_INTENTS);
- if (!(lookup_type || dentry->d_flags & DCACHE_AUTOFS_PENDING))
+ lookup_type = autofs4_need_mount(nd->flags);
+ spin_lock(&sbi->fs_lock);
+ spin_lock(&dcache_lock);
+ if (!(lookup_type || ino->flags & AUTOFS_INF_PENDING)) {
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
goto follow;
+ }
/*
* If the dentry contains directories then it is an autofs
* multi-mount with no root mount offset. So don't try to
* mount it again.
*/
- spin_lock(&dcache_lock);
- if (dentry->d_flags & DCACHE_AUTOFS_PENDING ||
- (!d_mountpoint(dentry) && __simple_empty(dentry))) {
+ if (ino->flags & AUTOFS_INF_PENDING ||
+ (!d_mountpoint(dentry) && list_empty(&dentry->d_subdirs))) {
+ ino->flags |= AUTOFS_INF_PENDING;
spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+
+ status = try_to_fill_dentry(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ ino->flags &= ~AUTOFS_INF_PENDING;
+ spin_unlock(&sbi->fs_lock);
- status = try_to_fill_dentry(dentry, 0);
if (status)
goto out_error;
goto follow;
}
spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
follow:
/*
* If there is no root mount it must be an autofs
@@ -254,18 +361,47 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
{
struct inode *dir = dentry->d_parent->d_inode;
struct autofs_sb_info *sbi = autofs4_sbi(dir->i_sb);
- int oz_mode = autofs4_oz_mode(sbi);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ struct rehash_entry *entry;
int flags = nd ? nd->flags : 0;
- int status = 1;
+ unsigned int mutex_aquired;
+
+ DPRINTK("name = %.*s oz_mode = %d",
+ dentry->d_name.len, dentry->d_name.name, oz_mode);
+
+ /* Daemon never causes a mount to trigger */
+ if (autofs4_oz_mode(sbi))
+ return 1;
+
+ entry = kmalloc(sizeof(struct rehash_entry), GFP_KERNEL);
+ if (!entry)
+ return -ENOMEM;
+
+ mutex_aquired = mutex_trylock(&dir->i_mutex);
- /* Pending dentry */
spin_lock(&sbi->fs_lock);
+ spin_lock(&dcache_lock);
+ /* Pending dentry */
if (autofs4_ispending(dentry)) {
- /* The daemon never causes a mount to trigger */
- spin_unlock(&sbi->fs_lock);
+ int status;
- if (oz_mode)
- return 1;
+ /*
+ * We can only unhash and send this to ->lookup() if
+ * the directory mutex is held over d_revalidate() and
+ * ->lookup(). This prevents the VFS from incorrectly
+ * seeing the dentry as non-existent.
+ */
+ ino->flags |= AUTOFS_INF_PENDING;
+ if (!mutex_aquired) {
+ autofs4_revalidate_drop(dentry, entry);
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+ return 0;
+ }
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+ mutex_unlock(&dir->i_mutex);
+ kfree(entry);
/*
* If the directory has gone away due to an expire
@@ -279,46 +415,82 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
* A zero status is success otherwise we have a
* negative error code.
*/
- status = try_to_fill_dentry(dentry, flags);
+ status = try_to_fill_dentry(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ ino->flags &= ~AUTOFS_INF_PENDING;
+ spin_unlock(&sbi->fs_lock);
+
if (status == 0)
return 1;
return status;
}
- spin_unlock(&sbi->fs_lock);
-
- /* Negative dentry.. invalidate if "old" */
- if (dentry->d_inode == NULL)
- return 0;
/* Check for a non-mountpoint directory with no contents */
- spin_lock(&dcache_lock);
if (S_ISDIR(dentry->d_inode->i_mode) &&
- !d_mountpoint(dentry) &&
- __simple_empty(dentry)) {
+ !d_mountpoint(dentry) && list_empty(&dentry->d_subdirs)) {
DPRINTK("dentry=%p %.*s, emptydir",
dentry, dentry->d_name.len, dentry->d_name.name);
- spin_unlock(&dcache_lock);
- /* The daemon never causes a mount to trigger */
- if (oz_mode)
- return 1;
+ if (autofs4_need_mount(flags) || current->link_count) {
+ int status;
- /*
- * A zero status is success otherwise we have a
- * negative error code.
- */
- status = try_to_fill_dentry(dentry, flags);
- if (status == 0)
- return 1;
+ /*
+ * We can only unhash and send this to ->lookup() if
+ * the directory mutex is held over d_revalidate() and
+ * ->lookup(). This prevents the VFS from incorrectly
+ * seeing the dentry as non-existent.
+ */
+ ino->flags |= AUTOFS_INF_PENDING;
+ if (!mutex_aquired) {
+ autofs4_revalidate_drop(dentry, entry);
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+ return 0;
+ }
+ spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+ mutex_unlock(&dir->i_mutex);
+ kfree(entry);
- return status;
+ /*
+ * A zero status is success otherwise we have a
+ * negative error code.
+ */
+ status = try_to_fill_dentry(dentry);
+
+ spin_lock(&sbi->fs_lock);
+ ino->flags &= ~AUTOFS_INF_PENDING;
+ spin_unlock(&sbi->fs_lock);
+
+ if (status == 0)
+ return 1;
+
+ return status;
+ }
}
spin_unlock(&dcache_lock);
+ spin_unlock(&sbi->fs_lock);
+
+ if (mutex_aquired)
+ mutex_unlock(&dir->i_mutex);
+
+ kfree(entry);
return 1;
}
+static void autofs4_free_rehash_entrys(struct autofs_info *inf)
+{
+ struct list_head *head = &inf->rehash_list;
+ struct rehash_entry *entry, *next;
+ list_for_each_entry_safe(entry, next, head, list) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+}
+
void autofs4_dentry_release(struct dentry *de)
{
struct autofs_info *inf;
@@ -337,6 +509,8 @@ void autofs4_dentry_release(struct dentry *de)
list_del(&inf->active);
if (!list_empty(&inf->expiring))
list_del(&inf->expiring);
+ if (!list_empty(&inf->rehash_list))
+ autofs4_free_rehash_entrys(inf);
spin_unlock(&sbi->lookup_lock);
}
@@ -359,35 +533,52 @@ static const struct dentry_operations autofs4_dentry_operations = {
.d_release = autofs4_dentry_release,
};
-static struct dentry *autofs4_lookup_active(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+static struct dentry *autofs4_lookup_active(struct dentry *dentry)
{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct dentry *parent = dentry->d_parent;
+ struct qstr *name = &dentry->d_name;
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
struct list_head *p, *head;
+restart:
spin_lock(&dcache_lock);
spin_lock(&sbi->lookup_lock);
head = &sbi->active_list;
list_for_each(p, head) {
struct autofs_info *ino;
- struct dentry *dentry;
+ struct dentry *active;
struct qstr *qstr;
ino = list_entry(p, struct autofs_info, active);
- dentry = ino->dentry;
+ active = ino->dentry;
- spin_lock(&dentry->d_lock);
+ spin_lock(&active->d_lock);
/* Already gone? */
- if (atomic_read(&dentry->d_count) == 0)
+ if (atomic_read(&active->d_count) == 0)
goto next;
- qstr = &dentry->d_name;
+ if (active->d_inode && IS_DEADDIR(active->d_inode)) {
+ if (!list_empty(&ino->rehash_list)) {
+ dget(active);
+ spin_unlock(&active->d_lock);
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&dcache_lock);
+ autofs4_remove_rehash_entrys(ino);
+ dput(active);
+ goto restart;
+ }
+ goto next;
+ }
+
+ qstr = &active->d_name;
- if (dentry->d_name.hash != hash)
+ if (active->d_name.hash != hash)
goto next;
- if (dentry->d_parent != parent)
+ if (active->d_parent != parent)
goto next;
if (qstr->len != len)
@@ -395,15 +586,13 @@ static struct dentry *autofs4_lookup_active(struct autofs_sb_info *sbi, struct d
if (memcmp(qstr->name, str, len))
goto next;
- if (d_unhashed(dentry)) {
- dget(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&sbi->lookup_lock);
- spin_unlock(&dcache_lock);
- return dentry;
- }
+ dget(active);
+ spin_unlock(&active->d_lock);
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&dcache_lock);
+ return active;
next:
- spin_unlock(&dentry->d_lock);
+ spin_unlock(&active->d_lock);
}
spin_unlock(&sbi->lookup_lock);
spin_unlock(&dcache_lock);
@@ -411,8 +600,11 @@ next:
return NULL;
}
-static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+static struct dentry *autofs4_lookup_expiring(struct dentry *dentry)
{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct dentry *parent = dentry->d_parent;
+ struct qstr *name = &dentry->d_name;
unsigned int len = name->len;
unsigned int hash = name->hash;
const unsigned char *str = name->name;
@@ -423,23 +615,23 @@ static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct
head = &sbi->expiring_list;
list_for_each(p, head) {
struct autofs_info *ino;
- struct dentry *dentry;
+ struct dentry *expiring;
struct qstr *qstr;
ino = list_entry(p, struct autofs_info, expiring);
- dentry = ino->dentry;
+ expiring = ino->dentry;
- spin_lock(&dentry->d_lock);
+ spin_lock(&expiring->d_lock);
/* Bad luck, we've already been dentry_iput */
- if (!dentry->d_inode)
+ if (!expiring->d_inode)
goto next;
- qstr = &dentry->d_name;
+ qstr = &expiring->d_name;
- if (dentry->d_name.hash != hash)
+ if (expiring->d_name.hash != hash)
goto next;
- if (dentry->d_parent != parent)
+ if (expiring->d_parent != parent)
goto next;
if (qstr->len != len)
@@ -447,15 +639,13 @@ static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct
if (memcmp(qstr->name, str, len))
goto next;
- if (d_unhashed(dentry)) {
- dget(dentry);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&sbi->lookup_lock);
- spin_unlock(&dcache_lock);
- return dentry;
- }
+ dget(expiring);
+ spin_unlock(&expiring->d_lock);
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&dcache_lock);
+ return expiring;
next:
- spin_unlock(&dentry->d_lock);
+ spin_unlock(&expiring->d_lock);
}
spin_unlock(&sbi->lookup_lock);
spin_unlock(&dcache_lock);
@@ -463,13 +653,56 @@ next:
return NULL;
}
+static struct autofs_info *init_new_dentry(struct autofs_sb_info *sbi,
+ struct dentry *dentry, int oz_mode)
+{
+ struct autofs_info *ino;
+
+ /*
+ * Mark the dentry incomplete but don't hash it. We do this
+ * to serialize our inode creation operations (symlink and
+ * mkdir) which prevents deadlock during the callback to
+ * the daemon. Subsequent user space lookups for the same
+ * dentry are placed on the wait queue while the daemon
+ * itself is allowed passage unresticted so the create
+ * operation itself can then hash the dentry. Finally,
+ * we check for the hashed dentry and return the newly
+ * hashed dentry.
+ */
+ dentry->d_op = &autofs4_root_dentry_operations;
+
+ /*
+ * And we need to ensure that the same dentry is used for
+ * all following lookup calls until it is hashed so that
+ * the dentry flags are persistent throughout the request.
+ */
+ ino = autofs4_init_ino(NULL, sbi, 0555);
+ if (!ino)
+ return ERR_PTR(-ENOMEM);
+
+ dentry->d_fsdata = ino;
+ ino->dentry = dentry;
+
+ /*
+ * Only set the mount pending flag for new dentrys not created
+ * by the daemon.
+ */
+ if (!oz_mode)
+ ino->flags |= AUTOFS_INF_PENDING;
+
+ d_instantiate(dentry, NULL);
+
+ return ino;
+}
+
/* Lookups in the root directory */
static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
struct autofs_sb_info *sbi;
struct autofs_info *ino;
- struct dentry *expiring, *unhashed;
+ struct dentry *expiring, *active;
int oz_mode;
+ int status = 0;
DPRINTK("name = %.*s",
dentry->d_name.len, dentry->d_name.name);
@@ -484,123 +717,100 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
DPRINTK("pid = %u, pgrp = %u, catatonic = %d, oz_mode = %d",
current->pid, task_pgrp_nr(current), sbi->catatonic, oz_mode);
- unhashed = autofs4_lookup_active(sbi, dentry->d_parent, &dentry->d_name);
- if (unhashed)
- dentry = unhashed;
- else {
- /*
- * Mark the dentry incomplete but don't hash it. We do this
- * to serialize our inode creation operations (symlink and
- * mkdir) which prevents deadlock during the callback to
- * the daemon. Subsequent user space lookups for the same
- * dentry are placed on the wait queue while the daemon
- * itself is allowed passage unresticted so the create
- * operation itself can then hash the dentry. Finally,
- * we check for the hashed dentry and return the newly
- * hashed dentry.
- */
- dentry->d_op = &autofs4_root_dentry_operations;
-
- /*
- * And we need to ensure that the same dentry is used for
- * all following lookup calls until it is hashed so that
- * the dentry flags are persistent throughout the request.
- */
- ino = autofs4_init_ino(NULL, sbi, 0555);
- if (!ino)
- return ERR_PTR(-ENOMEM);
-
- dentry->d_fsdata = ino;
- ino->dentry = dentry;
-
- spin_lock(&sbi->lookup_lock);
- list_add(&ino->active, &sbi->active_list);
- spin_unlock(&sbi->lookup_lock);
-
- d_instantiate(dentry, NULL);
+ spin_lock(&sbi->fs_lock);
+ active = autofs4_lookup_active(dentry);
+ if (active) {
+ dentry = active;
+ ino = autofs4_dentry_ino(dentry);
+ /* If this came from revalidate, rehash it */
+ autofs4_revalidate_rehash(dentry);
+ spin_unlock(&sbi->fs_lock);
+ } else {
+ spin_unlock(&sbi->fs_lock);
+ ino = init_new_dentry(sbi, dentry, oz_mode);
+ if (IS_ERR(ino))
+ return (struct dentry *) ino;
}
+ autofs4_add_active(dentry);
+
if (!oz_mode) {
+ expiring = autofs4_lookup_expiring(dentry);
mutex_unlock(&dir->i_mutex);
- expiring = autofs4_lookup_expiring(sbi,
- dentry->d_parent,
- &dentry->d_name);
if (expiring) {
/*
* If we are racing with expire the request might not
* be quite complete but the directory has been removed
* so it must have been successful, so just wait for it.
*/
- ino = autofs4_dentry_ino(expiring);
autofs4_expire_wait(expiring);
- spin_lock(&sbi->lookup_lock);
- if (!list_empty(&ino->expiring))
- list_del_init(&ino->expiring);
- spin_unlock(&sbi->lookup_lock);
dput(expiring);
}
-
- spin_lock(&dentry->d_lock);
- dentry->d_flags |= DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
- if (dentry->d_op && dentry->d_op->d_revalidate)
- (dentry->d_op->d_revalidate)(dentry, nd);
+ status = try_to_fill_dentry(dentry);
mutex_lock(&dir->i_mutex);
+ spin_lock(&sbi->fs_lock);
+ ino->flags &= ~AUTOFS_INF_PENDING;
+ spin_unlock(&sbi->fs_lock);
}
+ autofs4_del_active(dentry);
+
/*
- * If we are still pending, check if we had to handle
+ * If we had a mount fail, check if we had to handle
* a signal. If so we can force a restart..
*/
- if (dentry->d_flags & DCACHE_AUTOFS_PENDING) {
+ if (status) {
/* See if we were interrupted */
if (signal_pending(current)) {
sigset_t *sigset = &current->pending.signal;
if (sigismember (sigset, SIGKILL) ||
sigismember (sigset, SIGQUIT) ||
sigismember (sigset, SIGINT)) {
- if (unhashed)
- dput(unhashed);
+ if (active)
+ dput(active);
return ERR_PTR(-ERESTARTNOINTR);
}
}
- if (!oz_mode) {
- spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
+ }
+
+ /*
+ * User space can (and has done in the past) remove and re-create
+ * this directory during the callback. This can leave us with an
+ * unhashed dentry, but a successful mount! So we need to
+ * perform another cached lookup in case the dentry now exists.
+ */
+ if (!oz_mode && !have_submounts(dentry)) {
+ struct dentry *new;
+ new = d_lookup(dentry->d_parent, &dentry->d_name);
+ if (new) {
+ if (active)
+ dput(active);
+ return new;
+ } else {
+ if (!status)
+ status = -ENOENT;
}
}
/*
- * If this dentry is unhashed, then we shouldn't honour this
- * lookup. Returning ENOENT here doesn't do the right thing
- * for all system calls, but it should be OK for the operations
- * we permit from an autofs.
+ * If we had a mount failure, return status to user space.
+ * If the mount succeeded and we used a dentry from the active queue
+ * return it.
*/
- if (!oz_mode && d_unhashed(dentry)) {
+ if (status) {
+ dentry = ERR_PTR(status);
+ if (active)
+ dput(active);
+ return dentry;
+ } else {
/*
- * A user space application can (and has done in the past)
- * remove and re-create this directory during the callback.
- * This can leave us with an unhashed dentry, but a
- * successful mount! So we need to perform another
- * cached lookup in case the dentry now exists.
+ * Valid successful mount, return active dentry or NULL
+ * for a new dentry.
*/
- struct dentry *parent = dentry->d_parent;
- struct dentry *new = d_lookup(parent, &dentry->d_name);
- if (new != NULL)
- dentry = new;
- else
- dentry = ERR_PTR(-ENOENT);
-
- if (unhashed)
- dput(unhashed);
-
- return dentry;
+ if (active)
+ return active;
}
- if (unhashed)
- return unhashed;
-
return NULL;
}
@@ -624,11 +834,6 @@ static int autofs4_dir_symlink(struct inode *dir,
if (!ino)
return -ENOMEM;
- spin_lock(&sbi->lookup_lock);
- if (!list_empty(&ino->active))
- list_del_init(&ino->active);
- spin_unlock(&sbi->lookup_lock);
-
ino->size = strlen(symname);
cp = kmalloc(ino->size + 1, GFP_KERNEL);
if (!cp) {
@@ -705,10 +910,6 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
dir->i_mtime = CURRENT_TIME;
spin_lock(&dcache_lock);
- spin_lock(&sbi->lookup_lock);
- if (list_empty(&ino->expiring))
- list_add(&ino->expiring, &sbi->expiring_list);
- spin_unlock(&sbi->lookup_lock);
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
@@ -734,10 +935,6 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
spin_unlock(&dcache_lock);
return -ENOTEMPTY;
}
- spin_lock(&sbi->lookup_lock);
- if (list_empty(&ino->expiring))
- list_add(&ino->expiring, &sbi->expiring_list);
- spin_unlock(&sbi->lookup_lock);
spin_lock(&dentry->d_lock);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
@@ -775,11 +972,6 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
if (!ino)
return -ENOMEM;
- spin_lock(&sbi->lookup_lock);
- if (!list_empty(&ino->active))
- list_del_init(&ino->active);
- spin_unlock(&sbi->lookup_lock);
-
inode = autofs4_get_inode(dir->i_sb, ino);
if (!inode) {
if (!dentry->d_fsdata)
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d15ea1790bf..97b6e9efeb7 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -44,7 +44,7 @@ static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
* If we don't support core dumping, then supply a NULL so we
* don't even try.
*/
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit);
#else
#define elf_core_dump NULL
@@ -1101,12 +1101,7 @@ out:
return error;
}
-/*
- * Note that some platforms still use traditional core dumps and not
- * the ELF core dump. Each platform can select it as appropriate.
- */
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
-
+#ifdef CONFIG_ELF_CORE
/*
* ELF core dumper
*
@@ -2063,7 +2058,7 @@ out:
return has_dumped;
}
-#endif /* USE_ELF_CORE_DUMP */
+#endif /* CONFIG_ELF_CORE */
static int __init init_elf_binfmt(void)
{
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 79d2b1aa389..7b055385db8 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -75,14 +75,14 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(struct elf_fdpic_params *,
static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *,
struct file *, struct mm_struct *);
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
static int elf_fdpic_core_dump(long, struct pt_regs *, struct file *, unsigned long limit);
#endif
static struct linux_binfmt elf_fdpic_format = {
.module = THIS_MODULE,
.load_binary = load_elf_fdpic_binary,
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
.core_dump = elf_fdpic_core_dump,
#endif
.min_coredump = ELF_EXEC_PAGESIZE,
@@ -1201,7 +1201,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
*
* Modelled on fs/binfmt_elf.c core dumper
*/
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
/*
* These are the only things you should do on a core-file: use only these
@@ -1826,4 +1826,4 @@ cleanup:
#undef NUM_NOTES
}
-#endif /* USE_ELF_CORE_DUMP */
+#endif /* CONFIG_ELF_CORE */
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 36160424427..52cbe47022b 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -73,13 +73,13 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
return acl;
}
-static int btrfs_xattr_get_acl(struct inode *inode, int type,
- void *value, size_t size)
+static int btrfs_xattr_acl_get(struct dentry *dentry, const char *name,
+ void *value, size_t size, int type)
{
struct posix_acl *acl;
int ret = 0;
- acl = btrfs_get_acl(inode, type);
+ acl = btrfs_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
@@ -151,8 +151,8 @@ out:
return ret;
}
-static int btrfs_xattr_set_acl(struct inode *inode, int type,
- const void *value, size_t size)
+static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
int ret = 0;
struct posix_acl *acl = NULL;
@@ -167,38 +167,13 @@ static int btrfs_xattr_set_acl(struct inode *inode, int type,
}
}
- ret = btrfs_set_acl(inode, acl, type);
+ ret = btrfs_set_acl(dentry->d_inode, acl, type);
posix_acl_release(acl);
return ret;
}
-
-static int btrfs_xattr_acl_access_get(struct inode *inode, const char *name,
- void *value, size_t size)
-{
- return btrfs_xattr_get_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int btrfs_xattr_acl_access_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return btrfs_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int btrfs_xattr_acl_default_get(struct inode *inode, const char *name,
- void *value, size_t size)
-{
- return btrfs_xattr_get_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
-static int btrfs_xattr_acl_default_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return btrfs_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
int btrfs_check_acl(struct inode *inode, int mask)
{
struct posix_acl *acl;
@@ -303,14 +278,16 @@ int btrfs_acl_chmod(struct inode *inode)
struct xattr_handler btrfs_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
- .get = btrfs_xattr_acl_default_get,
- .set = btrfs_xattr_acl_default_set,
+ .flags = ACL_TYPE_DEFAULT,
+ .get = btrfs_xattr_acl_get,
+ .set = btrfs_xattr_acl_set,
};
struct xattr_handler btrfs_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
- .get = btrfs_xattr_acl_access_get,
- .set = btrfs_xattr_acl_access_set,
+ .flags = ACL_TYPE_ACCESS,
+ .get = btrfs_xattr_acl_get,
+ .set = btrfs_xattr_acl_set,
};
#else /* CONFIG_BTRFS_FS_POSIX_ACL */
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index 3797e0077b3..2906077ac79 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -84,7 +84,7 @@ int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
{
struct cachefiles_object *fsdef;
- struct nameidata nd;
+ struct path path;
struct kstatfs stats;
struct dentry *graveyard, *cachedir, *root;
const struct cred *saved_cred;
@@ -114,15 +114,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
_debug("- fsdef %p", fsdef);
/* look up the directory at the root of the cache */
- memset(&nd, 0, sizeof(nd));
-
- ret = path_lookup(cache->rootdirname, LOOKUP_DIRECTORY, &nd);
+ ret = kern_path(cache->rootdirname, LOOKUP_DIRECTORY, &path);
if (ret < 0)
goto error_open_root;
- cache->mnt = mntget(nd.path.mnt);
- root = dget(nd.path.dentry);
- path_put(&nd.path);
+ cache->mnt = path.mnt;
+ root = path.dentry;
/* check parameters */
ret = -EOPNOTSUPP;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index a6c8c6fe8df..1d833256386 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -11,7 +11,6 @@
#include <linux/mount.h>
#include <linux/file.h>
-#include <linux/ima.h>
#include "internal.h"
/*
@@ -923,7 +922,6 @@ int cachefiles_write_page(struct fscache_storage *op, struct page *page)
if (IS_ERR(file)) {
ret = PTR_ERR(file);
} else {
- ima_counts_get(file);
ret = -EIO;
if (file->f_op->write) {
pos = (loff_t) page->index << PAGE_SHIFT;
diff --git a/fs/cifs/export.c b/fs/cifs/export.c
index 75949d6a5f1..6177f7cca16 100644
--- a/fs/cifs/export.c
+++ b/fs/cifs/export.c
@@ -24,7 +24,7 @@
*/
/*
- * See Documentation/filesystems/Exporting
+ * See Documentation/filesystems/nfs/Exporting
* and examples in fs/exportfs
*
* Since cifs is a network file system, an "fsid" must be included for
diff --git a/fs/compat.c b/fs/compat.c
index 6c19040ffee..00d90c2e66f 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -38,8 +38,6 @@
#include <linux/dirent.h>
#include <linux/fsnotify.h>
#include <linux/highuid.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/syscall.h>
#include <linux/personality.h>
#include <linux/rwsem.h>
diff --git a/fs/dcache.c b/fs/dcache.c
index a100fa35a48..953173a293a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -978,6 +978,7 @@ struct dentry *d_alloc_name(struct dentry *parent, const char *name)
q.hash = full_name_hash(q.name, q.len);
return d_alloc(parent, &q);
}
+EXPORT_SYMBOL(d_alloc_name);
/* the caller must hold dcache_lock */
static void __d_instantiate(struct dentry *dentry, struct inode *inode)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index b912270942f..4012885d027 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -53,13 +53,6 @@
*
* If blkfactor is zero then the user's request was aligned to the filesystem's
* blocksize.
- *
- * lock_type is DIO_LOCKING for regular files on direct-IO-naive filesystems.
- * This determines whether we need to do the fancy locking which prevents
- * direct-IO from being able to read uninitialised disk blocks. If its zero
- * (blockdev) this locking is not done, and if it is DIO_OWN_LOCKING i_mutex is
- * not held for the entire direct write (taken briefly, initially, during a
- * direct read though, but its never held for the duration of a direct-IO).
*/
struct dio {
@@ -68,7 +61,7 @@ struct dio {
struct inode *inode;
int rw;
loff_t i_size; /* i_size when submitted */
- int lock_type; /* doesn't change */
+ int flags; /* doesn't change */
unsigned blkbits; /* doesn't change */
unsigned blkfactor; /* When we're using an alignment which
is finer than the filesystem's soft
@@ -104,6 +97,18 @@ struct dio {
unsigned cur_page_len; /* Nr of bytes at cur_page_offset */
sector_t cur_page_block; /* Where it starts */
+ /* BIO completion state */
+ spinlock_t bio_lock; /* protects BIO fields below */
+ unsigned long refcount; /* direct_io_worker() and bios */
+ struct bio *bio_list; /* singly linked via bi_private */
+ struct task_struct *waiter; /* waiting task (NULL if none) */
+
+ /* AIO related stuff */
+ struct kiocb *iocb; /* kiocb */
+ int is_async; /* is IO async ? */
+ int io_error; /* IO error in completion path */
+ ssize_t result; /* IO result */
+
/*
* Page fetching state. These variables belong to dio_refill_pages().
*/
@@ -115,22 +120,16 @@ struct dio {
* Page queue. These variables belong to dio_refill_pages() and
* dio_get_page().
*/
- struct page *pages[DIO_PAGES]; /* page buffer */
unsigned head; /* next page to process */
unsigned tail; /* last valid page + 1 */
int page_errors; /* errno from get_user_pages() */
- /* BIO completion state */
- spinlock_t bio_lock; /* protects BIO fields below */
- unsigned long refcount; /* direct_io_worker() and bios */
- struct bio *bio_list; /* singly linked via bi_private */
- struct task_struct *waiter; /* waiting task (NULL if none) */
-
- /* AIO related stuff */
- struct kiocb *iocb; /* kiocb */
- int is_async; /* is IO async ? */
- int io_error; /* IO error in completion path */
- ssize_t result; /* IO result */
+ /*
+ * pages[] (and any fields placed after it) are not zeroed out at
+ * allocation time. Don't add new fields after pages[] unless you
+ * wish that they not be zeroed.
+ */
+ struct page *pages[DIO_PAGES]; /* page buffer */
};
/*
@@ -240,7 +239,8 @@ static int dio_complete(struct dio *dio, loff_t offset, int ret)
if (dio->end_io && dio->result)
dio->end_io(dio->iocb, offset, transferred,
dio->map_bh.b_private);
- if (dio->lock_type == DIO_LOCKING)
+
+ if (dio->flags & DIO_LOCKING)
/* lockdep: non-owner release */
up_read_non_owner(&dio->inode->i_alloc_sem);
@@ -515,21 +515,24 @@ static int get_more_blocks(struct dio *dio)
map_bh->b_state = 0;
map_bh->b_size = fs_count << dio->inode->i_blkbits;
+ /*
+ * For writes inside i_size on a DIO_SKIP_HOLES filesystem we
+ * forbid block creations: only overwrites are permitted.
+ * We will return early to the caller once we see an
+ * unmapped buffer head returned, and the caller will fall
+ * back to buffered I/O.
+ *
+ * Otherwise the decision is left to the get_blocks method,
+ * which may decide to handle it or also return an unmapped
+ * buffer head.
+ */
create = dio->rw & WRITE;
- if (dio->lock_type == DIO_LOCKING) {
+ if (dio->flags & DIO_SKIP_HOLES) {
if (dio->block_in_file < (i_size_read(dio->inode) >>
dio->blkbits))
create = 0;
- } else if (dio->lock_type == DIO_NO_LOCKING) {
- create = 0;
}
- /*
- * For writes inside i_size we forbid block creations: only
- * overwrites are permitted. We fall back to buffered writes
- * at a higher level for inside-i_size block-instantiating
- * writes.
- */
ret = (*dio->get_block)(dio->inode, fs_startblk,
map_bh, create);
}
@@ -1039,7 +1042,7 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
* we can let i_mutex go now that its achieved its purpose
* of protecting us from looking up uninitialized blocks.
*/
- if ((rw == READ) && (dio->lock_type == DIO_LOCKING))
+ if (rw == READ && (dio->flags & DIO_LOCKING))
mutex_unlock(&dio->inode->i_mutex);
/*
@@ -1086,30 +1089,28 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode,
/*
* This is a library function for use by filesystem drivers.
- * The locking rules are governed by the dio_lock_type parameter.
*
- * DIO_NO_LOCKING (no locking, for raw block device access)
- * For writes, i_mutex is not held on entry; it is never taken.
+ * The locking rules are governed by the flags parameter:
+ * - if the flags value contains DIO_LOCKING we use a fancy locking
+ * scheme for dumb filesystems.
+ * For writes this function is called under i_mutex and returns with
+ * i_mutex held, for reads, i_mutex is not held on entry, but it is
+ * taken and dropped again before returning.
+ * For reads and writes i_alloc_sem is taken in shared mode and released
+ * on I/O completion (which may happen asynchronously after returning to
+ * the caller).
*
- * DIO_LOCKING (simple locking for regular files)
- * For writes we are called under i_mutex and return with i_mutex held, even
- * though it is internally dropped.
- * For reads, i_mutex is not held on entry, but it is taken and dropped before
- * returning.
- *
- * DIO_OWN_LOCKING (filesystem provides synchronisation and handling of
- * uninitialised data, allowing parallel direct readers and writers)
- * For writes we are called without i_mutex, return without it, never touch it.
- * For reads we are called under i_mutex and return with i_mutex held, even
- * though it may be internally dropped.
- *
- * Additional i_alloc_sem locking requirements described inline below.
+ * - if the flags value does NOT contain DIO_LOCKING we don't use any
+ * internal locking but rather rely on the filesystem to synchronize
+ * direct I/O reads/writes versus each other and truncate.
+ * For reads and writes both i_mutex and i_alloc_sem are not held on
+ * entry and are never taken.
*/
ssize_t
__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
struct block_device *bdev, const struct iovec *iov, loff_t offset,
unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
- int dio_lock_type)
+ int flags)
{
int seg;
size_t size;
@@ -1120,8 +1121,6 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
ssize_t retval = -EINVAL;
loff_t end = offset;
struct dio *dio;
- int release_i_mutex = 0;
- int acquire_i_mutex = 0;
if (rw & WRITE)
rw = WRITE_ODIRECT_PLUG;
@@ -1151,48 +1150,41 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
}
}
- dio = kzalloc(sizeof(*dio), GFP_KERNEL);
+ dio = kmalloc(sizeof(*dio), GFP_KERNEL);
retval = -ENOMEM;
if (!dio)
goto out;
-
/*
- * For block device access DIO_NO_LOCKING is used,
- * neither readers nor writers do any locking at all
- * For regular files using DIO_LOCKING,
- * readers need to grab i_mutex and i_alloc_sem
- * writers need to grab i_alloc_sem only (i_mutex is already held)
- * For regular files using DIO_OWN_LOCKING,
- * neither readers nor writers take any locks here
+ * Believe it or not, zeroing out the page array caused a .5%
+ * performance regression in a database benchmark. So, we take
+ * care to only zero out what's needed.
*/
- dio->lock_type = dio_lock_type;
- if (dio_lock_type != DIO_NO_LOCKING) {
+ memset(dio, 0, offsetof(struct dio, pages));
+
+ dio->flags = flags;
+ if (dio->flags & DIO_LOCKING) {
/* watch out for a 0 len io from a tricksy fs */
if (rw == READ && end > offset) {
- struct address_space *mapping;
+ struct address_space *mapping =
+ iocb->ki_filp->f_mapping;
- mapping = iocb->ki_filp->f_mapping;
- if (dio_lock_type != DIO_OWN_LOCKING) {
- mutex_lock(&inode->i_mutex);
- release_i_mutex = 1;
- }
+ /* will be released by direct_io_worker */
+ mutex_lock(&inode->i_mutex);
retval = filemap_write_and_wait_range(mapping, offset,
end - 1);
if (retval) {
+ mutex_unlock(&inode->i_mutex);
kfree(dio);
goto out;
}
-
- if (dio_lock_type == DIO_OWN_LOCKING) {
- mutex_unlock(&inode->i_mutex);
- acquire_i_mutex = 1;
- }
}
- if (dio_lock_type == DIO_LOCKING)
- /* lockdep: not the owner will release it */
- down_read_non_owner(&inode->i_alloc_sem);
+ /*
+ * Will be released at I/O completion, possibly in a
+ * different thread.
+ */
+ down_read_non_owner(&inode->i_alloc_sem);
}
/*
@@ -1210,24 +1202,19 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
/*
* In case of error extending write may have instantiated a few
* blocks outside i_size. Trim these off again for DIO_LOCKING.
- * NOTE: DIO_NO_LOCK/DIO_OWN_LOCK callers have to handle this by
- * it's own meaner.
+ *
+ * NOTE: filesystems with their own locking have to handle this
+ * on their own.
*/
- if (unlikely(retval < 0 && (rw & WRITE))) {
- loff_t isize = i_size_read(inode);
-
- if (end > isize && dio_lock_type == DIO_LOCKING)
- vmtruncate(inode, isize);
+ if (dio->flags & DIO_LOCKING) {
+ if (unlikely((rw & WRITE) && retval < 0)) {
+ loff_t isize = i_size_read(inode);
+ if (end > isize)
+ vmtruncate(inode, isize);
+ }
}
- if (rw == READ && dio_lock_type == DIO_LOCKING)
- release_i_mutex = 0;
-
out:
- if (release_i_mutex)
- mutex_unlock(&inode->i_mutex);
- else if (acquire_i_mutex)
- mutex_lock(&inode->i_mutex);
return retval;
}
EXPORT_SYMBOL(__blockdev_direct_IO);
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index c6ac85d6c70..101fe4c7b1e 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -35,7 +35,6 @@
#include <linux/key.h>
#include <linux/parser.h>
#include <linux/fs_stack.h>
-#include <linux/ima.h>
#include "ecryptfs_kernel.h"
/**
@@ -119,7 +118,6 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
const struct cred *cred = current_cred();
struct ecryptfs_inode_info *inode_info =
ecryptfs_inode_to_private(ecryptfs_dentry->d_inode);
- int opened_lower_file = 0;
int rc = 0;
mutex_lock(&inode_info->lower_file_mutex);
@@ -136,12 +134,9 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
"for lower_dentry [0x%p] and lower_mnt [0x%p]; "
"rc = [%d]\n", lower_dentry, lower_mnt, rc);
inode_info->lower_file = NULL;
- } else
- opened_lower_file = 1;
+ }
}
mutex_unlock(&inode_info->lower_file_mutex);
- if (opened_lower_file)
- ima_counts_get(inode_info->lower_file);
return rc;
}
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 197c7db583c..e9e175949a6 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -6,7 +6,7 @@
* and for mapping back from file handles to dentries.
*
* For details on why we do all the strange and hairy things in here
- * take a look at Documentation/filesystems/Exporting.
+ * take a look at Documentation/filesystems/nfs/Exporting.
*/
#include <linux/exportfs.h>
#include <linux/fs.h>
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index a63d44256a7..a99e54318c3 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -339,12 +339,12 @@ ext2_acl_chmod(struct inode *inode)
* Extended attribut handlers
*/
static size_t
-ext2_xattr_list_acl_access(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext2_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_size)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -352,12 +352,12 @@ ext2_xattr_list_acl_access(struct inode *inode, char *list, size_t list_size,
}
static size_t
-ext2_xattr_list_acl_default(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext2_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_size)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -365,15 +365,18 @@ ext2_xattr_list_acl_default(struct inode *inode, char *list, size_t list_size,
}
static int
-ext2_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+ext2_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- acl = ext2_get_acl(inode, type);
+ acl = ext2_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -385,33 +388,17 @@ ext2_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
}
static int
-ext2_xattr_get_acl_access(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext2_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext2_xattr_get_acl_default(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext2_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext2_xattr_set_acl(struct inode *inode, int type, const void *value,
- size_t size)
+ext2_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- if (!is_owner_or_cap(inode))
+ if (!is_owner_or_cap(dentry->d_inode))
return -EPERM;
if (value) {
@@ -426,41 +413,25 @@ ext2_xattr_set_acl(struct inode *inode, int type, const void *value,
} else
acl = NULL;
- error = ext2_set_acl(inode, type, acl);
+ error = ext2_set_acl(dentry->d_inode, type, acl);
release_and_out:
posix_acl_release(acl);
return error;
}
-static int
-ext2_xattr_set_acl_access(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext2_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext2_xattr_set_acl_default(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext2_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ext2_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ext2_xattr_list_acl_access,
- .get = ext2_xattr_get_acl_access,
- .set = ext2_xattr_set_acl_access,
+ .get = ext2_xattr_get_acl,
+ .set = ext2_xattr_set_acl,
};
struct xattr_handler ext2_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ext2_xattr_list_acl_default,
- .get = ext2_xattr_get_acl_default,
- .set = ext2_xattr_set_acl_default,
+ .get = ext2_xattr_get_acl,
+ .set = ext2_xattr_set_acl,
};
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index fc2bd05d355..7516957273e 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -721,5 +721,5 @@ const struct file_operations ext2_dir_operations = {
#ifdef CONFIG_COMPAT
.compat_ioctl = ext2_compat_ioctl,
#endif
- .fsync = simple_fsync,
+ .fsync = ext2_fsync,
};
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index da318b0fa63..061914add3c 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -155,6 +155,7 @@ extern void ext2_write_super (struct super_block *);
extern const struct file_operations ext2_dir_operations;
/* file.c */
+extern int ext2_fsync(struct file *file, struct dentry *dentry, int datasync);
extern const struct inode_operations ext2_file_inode_operations;
extern const struct file_operations ext2_file_operations;
extern const struct file_operations ext2_xip_file_operations;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index a2f3afd1a1c..586e3589d4c 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -19,6 +19,7 @@
*/
#include <linux/time.h>
+#include <linux/pagemap.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
@@ -38,6 +39,22 @@ static int ext2_release_file (struct inode * inode, struct file * filp)
return 0;
}
+int ext2_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+ int ret;
+ struct super_block *sb = dentry->d_inode->i_sb;
+ struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+
+ ret = simple_fsync(file, dentry, datasync);
+ if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
+ /* We don't really know where the IO error happened... */
+ ext2_error(sb, __func__,
+ "detected IO error when writing metadata buffers");
+ ret = -EIO;
+ }
+ return ret;
+}
+
/*
* We have mostly NULL's here: the current defaults are ok for
* the ext2 filesystem.
@@ -55,7 +72,7 @@ const struct file_operations ext2_file_operations = {
.mmap = generic_file_mmap,
.open = generic_file_open,
.release = ext2_release_file,
- .fsync = simple_fsync,
+ .fsync = ext2_fsync,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
};
@@ -72,7 +89,7 @@ const struct file_operations ext2_xip_file_operations = {
.mmap = xip_file_mmap,
.open = generic_file_open,
.release = ext2_release_file,
- .fsync = simple_fsync,
+ .fsync = ext2_fsync,
};
#endif
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 1388802b780..f9cb54a585c 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -1105,9 +1105,30 @@ failed_sbi:
return ret;
}
+static void ext2_clear_super_error(struct super_block *sb)
+{
+ struct buffer_head *sbh = EXT2_SB(sb)->s_sbh;
+
+ if (buffer_write_io_error(sbh)) {
+ /*
+ * Oh, dear. A previous attempt to write the
+ * superblock failed. This could happen because the
+ * USB device was yanked out. Or it could happen to
+ * be a transient write error and maybe the block will
+ * be remapped. Nothing we can do but to retry the
+ * write and hope for the best.
+ */
+ printk(KERN_ERR "EXT2-fs: %s previous I/O error to "
+ "superblock detected", sb->s_id);
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
+ }
+}
+
static void ext2_commit_super (struct super_block * sb,
struct ext2_super_block * es)
{
+ ext2_clear_super_error(sb);
es->s_wtime = cpu_to_le32(get_seconds());
mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
sb->s_dirt = 0;
@@ -1115,6 +1136,7 @@ static void ext2_commit_super (struct super_block * sb,
static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
{
+ ext2_clear_super_error(sb);
es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
es->s_wtime = cpu_to_le32(get_seconds());
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index 7913531ec6d..904f00642f8 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -60,6 +60,7 @@
#include <linux/mbcache.h>
#include <linux/quotaops.h>
#include <linux/rwsem.h>
+#include <linux/security.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
@@ -249,8 +250,9 @@ cleanup:
* used / required on success.
*/
static int
-ext2_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
struct ext2_xattr_entry *entry;
char *end;
@@ -300,9 +302,10 @@ bad_block: ext2_error(inode->i_sb, "ext2_xattr_list",
ext2_xattr_handler(entry->e_name_index);
if (handler) {
- size_t size = handler->list(inode, buffer, rest,
+ size_t size = handler->list(dentry, buffer, rest,
entry->e_name,
- entry->e_name_len);
+ entry->e_name_len,
+ handler->flags);
if (buffer) {
if (size > rest) {
error = -ERANGE;
@@ -330,7 +333,7 @@ cleanup:
ssize_t
ext2_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- return ext2_xattr_list(dentry->d_inode, buffer, size);
+ return ext2_xattr_list(dentry, buffer, size);
}
/*
diff --git a/fs/ext2/xattr_security.c b/fs/ext2/xattr_security.c
index 70c0dbdcdcb..c8155845ac0 100644
--- a/fs/ext2/xattr_security.c
+++ b/fs/ext2/xattr_security.c
@@ -11,8 +11,8 @@
#include "xattr.h"
static size_t
-ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext2_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const int prefix_len = XATTR_SECURITY_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -26,22 +26,22 @@ ext2_xattr_security_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext2_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext2_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_get(inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
buffer, size);
}
static int
-ext2_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext2_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_set(inode, EXT2_XATTR_INDEX_SECURITY, name,
+ return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_SECURITY, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_trusted.c b/fs/ext2/xattr_trusted.c
index e8219f8eae9..2a26d71f477 100644
--- a/fs/ext2/xattr_trusted.c
+++ b/fs/ext2/xattr_trusted.c
@@ -13,8 +13,8 @@
#include "xattr.h"
static size_t
-ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext2_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const int prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -31,22 +31,22 @@ ext2_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext2_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext2_xattr_trusted_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_get(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
buffer, size);
}
static int
-ext2_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext2_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext2_xattr_set(inode, EXT2_XATTR_INDEX_TRUSTED, name,
+ return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext2/xattr_user.c b/fs/ext2/xattr_user.c
index 92495d28c62..3f6caf3684b 100644
--- a/fs/ext2/xattr_user.c
+++ b/fs/ext2/xattr_user.c
@@ -12,13 +12,13 @@
#include "xattr.h"
static size_t
-ext2_xattr_user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext2_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return 0;
if (list && total_len <= list_size) {
@@ -30,27 +30,28 @@ ext2_xattr_user_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext2_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext2_xattr_user_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_get(inode, EXT2_XATTR_INDEX_USER, name, buffer, size);
+ return ext2_xattr_get(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ name, buffer, size);
}
static int
-ext2_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext2_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext2_xattr_set(inode, EXT2_XATTR_INDEX_USER, name,
- value, size, flags);
+ return ext2_xattr_set(dentry->d_inode, EXT2_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ext2_xattr_user_handler = {
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index c9b0df376b5..82ba3415866 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -366,12 +366,12 @@ out:
* Extended attribute handlers
*/
static size_t
-ext3_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext3_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -379,12 +379,12 @@ ext3_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
}
static size_t
-ext3_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext3_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -392,15 +392,18 @@ ext3_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
}
static int
-ext3_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+ext3_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- acl = ext3_get_acl(inode, type);
+ acl = ext3_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -412,31 +415,16 @@ ext3_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
}
static int
-ext3_xattr_get_acl_access(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext3_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext3_xattr_get_acl_default(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext3_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext3_xattr_set_acl(struct inode *inode, int type, const void *value,
- size_t size)
+ext3_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
handle_t *handle;
struct posix_acl *acl;
int error, retries = 0;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
if (!is_owner_or_cap(inode))
@@ -468,34 +456,18 @@ release_and_out:
return error;
}
-static int
-ext3_xattr_set_acl_access(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext3_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext3_xattr_set_acl_default(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext3_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ext3_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ext3_xattr_list_acl_access,
- .get = ext3_xattr_get_acl_access,
- .set = ext3_xattr_set_acl_access,
+ .get = ext3_xattr_get_acl,
+ .set = ext3_xattr_set_acl,
};
struct xattr_handler ext3_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ext3_xattr_list_acl_default,
- .get = ext3_xattr_get_acl_default,
- .set = ext3_xattr_set_acl_default,
+ .get = ext3_xattr_get_acl,
+ .set = ext3_xattr_set_acl,
};
diff --git a/fs/ext3/xattr.c b/fs/ext3/xattr.c
index 387d92d00b9..66895ccf76c 100644
--- a/fs/ext3/xattr.c
+++ b/fs/ext3/xattr.c
@@ -99,7 +99,7 @@ static struct buffer_head *ext3_xattr_cache_find(struct inode *,
struct mb_cache_entry **);
static void ext3_xattr_rehash(struct ext3_xattr_header *,
struct ext3_xattr_entry *);
-static int ext3_xattr_list(struct inode *inode, char *buffer,
+static int ext3_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
static struct mb_cache *ext3_xattr_cache;
@@ -147,7 +147,7 @@ ext3_xattr_handler(int name_index)
ssize_t
ext3_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- return ext3_xattr_list(dentry->d_inode, buffer, size);
+ return ext3_xattr_list(dentry, buffer, size);
}
static int
@@ -332,7 +332,7 @@ ext3_xattr_get(struct inode *inode, int name_index, const char *name,
}
static int
-ext3_xattr_list_entries(struct inode *inode, struct ext3_xattr_entry *entry,
+ext3_xattr_list_entries(struct dentry *dentry, struct ext3_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
@@ -342,9 +342,10 @@ ext3_xattr_list_entries(struct inode *inode, struct ext3_xattr_entry *entry,
ext3_xattr_handler(entry->e_name_index);
if (handler) {
- size_t size = handler->list(inode, buffer, rest,
+ size_t size = handler->list(dentry, buffer, rest,
entry->e_name,
- entry->e_name_len);
+ entry->e_name_len,
+ handler->flags);
if (buffer) {
if (size > rest)
return -ERANGE;
@@ -357,8 +358,9 @@ ext3_xattr_list_entries(struct inode *inode, struct ext3_xattr_entry *entry,
}
static int
-ext3_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext3_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
int error;
@@ -383,7 +385,7 @@ ext3_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
goto cleanup;
}
ext3_xattr_cache_insert(bh);
- error = ext3_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);
+ error = ext3_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
@@ -392,8 +394,9 @@ cleanup:
}
static int
-ext3_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext3_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct ext3_xattr_ibody_header *header;
struct ext3_inode *raw_inode;
struct ext3_iloc iloc;
@@ -411,7 +414,7 @@ ext3_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
error = ext3_xattr_check_names(IFIRST(header), end);
if (error)
goto cleanup;
- error = ext3_xattr_list_entries(inode, IFIRST(header),
+ error = ext3_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
@@ -430,12 +433,12 @@ cleanup:
* used / required on success.
*/
static int
-ext3_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext3_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int i_error, b_error;
- down_read(&EXT3_I(inode)->xattr_sem);
- i_error = ext3_xattr_ibody_list(inode, buffer, buffer_size);
+ down_read(&EXT3_I(dentry->d_inode)->xattr_sem);
+ i_error = ext3_xattr_ibody_list(dentry, buffer, buffer_size);
if (i_error < 0) {
b_error = 0;
} else {
@@ -443,11 +446,11 @@ ext3_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
buffer += i_error;
buffer_size -= i_error;
}
- b_error = ext3_xattr_block_list(inode, buffer, buffer_size);
+ b_error = ext3_xattr_block_list(dentry, buffer, buffer_size);
if (b_error < 0)
i_error = 0;
}
- up_read(&EXT3_I(inode)->xattr_sem);
+ up_read(&EXT3_I(dentry->d_inode)->xattr_sem);
return i_error + b_error;
}
diff --git a/fs/ext3/xattr_security.c b/fs/ext3/xattr_security.c
index 37b81097bdf..474348788dd 100644
--- a/fs/ext3/xattr_security.c
+++ b/fs/ext3/xattr_security.c
@@ -12,8 +12,8 @@
#include "xattr.h"
static size_t
-ext3_xattr_security_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext3_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -28,23 +28,23 @@ ext3_xattr_security_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext3_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext3_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_get(inode, EXT3_XATTR_INDEX_SECURITY, name,
- buffer, size);
+ return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_SECURITY,
+ name, buffer, size);
}
static int
-ext3_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext3_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_set(inode, EXT3_XATTR_INDEX_SECURITY, name,
- value, size, flags);
+ return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_SECURITY,
+ name, value, size, flags);
}
int
diff --git a/fs/ext3/xattr_trusted.c b/fs/ext3/xattr_trusted.c
index c7c41a410c4..e5562845ed9 100644
--- a/fs/ext3/xattr_trusted.c
+++ b/fs/ext3/xattr_trusted.c
@@ -14,8 +14,8 @@
#include "xattr.h"
static size_t
-ext3_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext3_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -32,22 +32,22 @@ ext3_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext3_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext3_xattr_trusted_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_get(inode, EXT3_XATTR_INDEX_TRUSTED, name,
- buffer, size);
+ return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_TRUSTED,
+ name, buffer, size);
}
static int
-ext3_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext3_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext3_xattr_set(inode, EXT3_XATTR_INDEX_TRUSTED, name,
+ return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_TRUSTED, name,
value, size, flags);
}
diff --git a/fs/ext3/xattr_user.c b/fs/ext3/xattr_user.c
index 430fe63b31b..3bcfe9ee0a6 100644
--- a/fs/ext3/xattr_user.c
+++ b/fs/ext3/xattr_user.c
@@ -13,13 +13,13 @@
#include "xattr.h"
static size_t
-ext3_xattr_user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext3_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return 0;
if (list && total_len <= list_size) {
@@ -31,26 +31,27 @@ ext3_xattr_user_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext3_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext3_xattr_user_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext3_xattr_get(inode, EXT3_XATTR_INDEX_USER, name, buffer, size);
+ return ext3_xattr_get(dentry->d_inode, EXT3_XATTR_INDEX_USER,
+ name, buffer, size);
}
static int
-ext3_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext3_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext3_xattr_set(inode, EXT3_XATTR_INDEX_USER, name,
- value, size, flags);
+ return ext3_xattr_set(dentry->d_inode, EXT3_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ext3_xattr_user_handler = {
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 0df88b2a69b..8a2a29d35a6 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -364,12 +364,12 @@ out:
* Extended attribute handlers
*/
static size_t
-ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_access(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -377,12 +377,12 @@ ext4_xattr_list_acl_access(struct inode *inode, char *list, size_t list_len,
}
static size_t
-ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t name_len)
+ext4_xattr_list_acl_default(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return 0;
if (list && size <= list_len)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -390,15 +390,18 @@ ext4_xattr_list_acl_default(struct inode *inode, char *list, size_t list_len,
}
static int
-ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+ext4_xattr_get_acl(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!test_opt(inode->i_sb, POSIX_ACL))
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+ if (!test_opt(dentry->d_sb, POSIX_ACL))
return -EOPNOTSUPP;
- acl = ext4_get_acl(inode, type);
+ acl = ext4_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -410,31 +413,16 @@ ext4_xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
}
static int
-ext4_xattr_get_acl_access(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-ext4_xattr_get_acl_default(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-ext4_xattr_set_acl(struct inode *inode, int type, const void *value,
- size_t size)
+ext4_xattr_set_acl(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
handle_t *handle;
struct posix_acl *acl;
int error, retries = 0;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!test_opt(inode->i_sb, POSIX_ACL))
return -EOPNOTSUPP;
if (!is_owner_or_cap(inode))
@@ -466,34 +454,18 @@ release_and_out:
return error;
}
-static int
-ext4_xattr_set_acl_access(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int
-ext4_xattr_set_acl_default(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ext4_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ext4_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ext4_xattr_list_acl_access,
- .get = ext4_xattr_get_acl_access,
- .set = ext4_xattr_set_acl_access,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
struct xattr_handler ext4_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ext4_xattr_list_acl_default,
- .get = ext4_xattr_get_acl_default,
- .set = ext4_xattr_set_acl_default,
+ .get = ext4_xattr_get_acl,
+ .set = ext4_xattr_set_acl,
};
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 910bf9a59cb..83218bebbc7 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -92,7 +92,7 @@ static struct buffer_head *ext4_xattr_cache_find(struct inode *,
struct mb_cache_entry **);
static void ext4_xattr_rehash(struct ext4_xattr_header *,
struct ext4_xattr_entry *);
-static int ext4_xattr_list(struct inode *inode, char *buffer,
+static int ext4_xattr_list(struct dentry *dentry, char *buffer,
size_t buffer_size);
static struct mb_cache *ext4_xattr_cache;
@@ -140,7 +140,7 @@ ext4_xattr_handler(int name_index)
ssize_t
ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- return ext4_xattr_list(dentry->d_inode, buffer, size);
+ return ext4_xattr_list(dentry, buffer, size);
}
static int
@@ -325,7 +325,7 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
}
static int
-ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
+ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry,
char *buffer, size_t buffer_size)
{
size_t rest = buffer_size;
@@ -335,9 +335,10 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
ext4_xattr_handler(entry->e_name_index);
if (handler) {
- size_t size = handler->list(inode, buffer, rest,
+ size_t size = handler->list(dentry, buffer, rest,
entry->e_name,
- entry->e_name_len);
+ entry->e_name_len,
+ handler->flags);
if (buffer) {
if (size > rest)
return -ERANGE;
@@ -350,8 +351,9 @@ ext4_xattr_list_entries(struct inode *inode, struct ext4_xattr_entry *entry,
}
static int
-ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct buffer_head *bh = NULL;
int error;
@@ -376,7 +378,7 @@ ext4_xattr_block_list(struct inode *inode, char *buffer, size_t buffer_size)
goto cleanup;
}
ext4_xattr_cache_insert(bh);
- error = ext4_xattr_list_entries(inode, BFIRST(bh), buffer, buffer_size);
+ error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
cleanup:
brelse(bh);
@@ -385,8 +387,9 @@ cleanup:
}
static int
-ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
+ struct inode *inode = dentry->d_inode;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
@@ -404,7 +407,7 @@ ext4_xattr_ibody_list(struct inode *inode, char *buffer, size_t buffer_size)
error = ext4_xattr_check_names(IFIRST(header), end);
if (error)
goto cleanup;
- error = ext4_xattr_list_entries(inode, IFIRST(header),
+ error = ext4_xattr_list_entries(dentry, IFIRST(header),
buffer, buffer_size);
cleanup:
@@ -423,12 +426,12 @@ cleanup:
* used / required on success.
*/
static int
-ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
+ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
{
int i_error, b_error;
- down_read(&EXT4_I(inode)->xattr_sem);
- i_error = ext4_xattr_ibody_list(inode, buffer, buffer_size);
+ down_read(&EXT4_I(dentry->d_inode)->xattr_sem);
+ i_error = ext4_xattr_ibody_list(dentry, buffer, buffer_size);
if (i_error < 0) {
b_error = 0;
} else {
@@ -436,11 +439,11 @@ ext4_xattr_list(struct inode *inode, char *buffer, size_t buffer_size)
buffer += i_error;
buffer_size -= i_error;
}
- b_error = ext4_xattr_block_list(inode, buffer, buffer_size);
+ b_error = ext4_xattr_block_list(dentry, buffer, buffer_size);
if (b_error < 0)
i_error = 0;
}
- up_read(&EXT4_I(inode)->xattr_sem);
+ up_read(&EXT4_I(dentry->d_inode)->xattr_sem);
return i_error + b_error;
}
diff --git a/fs/ext4/xattr_security.c b/fs/ext4/xattr_security.c
index ca5f89fc6ca..983c253999a 100644
--- a/fs/ext4/xattr_security.c
+++ b/fs/ext4/xattr_security.c
@@ -12,8 +12,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_security_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = sizeof(XATTR_SECURITY_PREFIX)-1;
const size_t total_len = prefix_len + name_len + 1;
@@ -28,23 +28,23 @@ ext4_xattr_security_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_SECURITY, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, buffer, size);
}
static int
-ext4_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_SECURITY, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_SECURITY,
+ name, value, size, flags);
}
int
diff --git a/fs/ext4/xattr_trusted.c b/fs/ext4/xattr_trusted.c
index ac1a52cf2a3..15b50edc658 100644
--- a/fs/ext4/xattr_trusted.c
+++ b/fs/ext4/xattr_trusted.c
@@ -14,8 +14,8 @@
#include "xattr.h"
static size_t
-ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -32,23 +32,23 @@ ext4_xattr_trusted_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_trusted_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, buffer, size);
}
static int
-ext4_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_TRUSTED, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_TRUSTED,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_trusted_handler = {
diff --git a/fs/ext4/xattr_user.c b/fs/ext4/xattr_user.c
index d91aa61b42a..c4ce05746ce 100644
--- a/fs/ext4/xattr_user.c
+++ b/fs/ext4/xattr_user.c
@@ -13,13 +13,13 @@
#include "xattr.h"
static size_t
-ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+ext4_xattr_user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return 0;
if (list && total_len <= list_size) {
@@ -31,26 +31,27 @@ ext4_xattr_user_list(struct inode *inode, char *list, size_t list_size,
}
static int
-ext4_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+ext4_xattr_user_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_get(inode, EXT4_XATTR_INDEX_USER, name, buffer, size);
+ return ext4_xattr_get(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, buffer, size);
}
static int
-ext4_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+ext4_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- if (!test_opt(inode->i_sb, XATTR_USER))
+ if (!test_opt(dentry->d_sb, XATTR_USER))
return -EOPNOTSUPP;
- return ext4_xattr_set(inode, EXT4_XATTR_INDEX_USER, name,
- value, size, flags);
+ return ext4_xattr_set(dentry->d_inode, EXT4_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ext4_xattr_user_handler = {
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 7db0979c6b7..e6efdfa0f6d 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -44,7 +44,8 @@ struct fat_mount_options {
nocase:1, /* Does this need case conversion? 0=need case conversion*/
usefree:1, /* Use free_clusters for FAT32 */
tz_utc:1, /* Filesystem timestamps are in UTC */
- rodir:1; /* allow ATTR_RO for directory */
+ rodir:1, /* allow ATTR_RO for directory */
+ discard:1; /* Issue discard requests on deletions */
};
#define FAT_HASH_BITS 8
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index a81037721a6..81184d3b75a 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -566,16 +566,21 @@ int fat_free_clusters(struct inode *inode, int cluster)
goto error;
}
- /*
- * Issue discard for the sectors we no longer care about,
- * batching contiguous clusters into one request
- */
- if (cluster != fatent.entry + 1) {
- int nr_clus = fatent.entry - first_cl + 1;
-
- sb_issue_discard(sb, fat_clus_to_blknr(sbi, first_cl),
- nr_clus * sbi->sec_per_clus);
- first_cl = cluster;
+ if (sbi->options.discard) {
+ /*
+ * Issue discard for the sectors we no longer
+ * care about, batching contiguous clusters
+ * into one request
+ */
+ if (cluster != fatent.entry + 1) {
+ int nr_clus = fatent.entry - first_cl + 1;
+
+ sb_issue_discard(sb,
+ fat_clus_to_blknr(sbi, first_cl),
+ nr_clus * sbi->sec_per_clus);
+
+ first_cl = cluster;
+ }
}
ops->ent_put(&fatent, FAT_ENT_FREE);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 76b7961ab66..14da530b05c 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -858,6 +858,8 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
seq_puts(m, ",errors=panic");
else
seq_puts(m, ",errors=remount-ro");
+ if (opts->discard)
+ seq_puts(m, ",discard");
return 0;
}
@@ -871,7 +873,7 @@ enum {
Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont,
- Opt_err_panic, Opt_err_ro, Opt_err,
+ Opt_err_panic, Opt_err_ro, Opt_discard, Opt_err,
};
static const match_table_t fat_tokens = {
@@ -899,6 +901,7 @@ static const match_table_t fat_tokens = {
{Opt_err_cont, "errors=continue"},
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
+ {Opt_discard, "discard"},
{Opt_obsolate, "conv=binary"},
{Opt_obsolate, "conv=text"},
{Opt_obsolate, "conv=auto"},
@@ -1136,6 +1139,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
case Opt_rodir:
opts->rodir = 1;
break;
+ case Opt_discard:
+ opts->discard = 1;
+ break;
/* obsolete mount options */
case Opt_obsolate:
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 0f55f5cb732..d3da05f2646 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -9,6 +9,7 @@
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
+#include <linux/time.h>
#include "fat.h"
/*
@@ -157,10 +158,6 @@ extern struct timezone sys_tz;
#define SECS_PER_MIN 60
#define SECS_PER_HOUR (60 * 60)
#define SECS_PER_DAY (SECS_PER_HOUR * 24)
-#define UNIX_SECS_1980 315532800L
-#if BITS_PER_LONG == 64
-#define UNIX_SECS_2108 4354819200L
-#endif
/* days between 1.1.70 and 1.1.80 (2 leap days) */
#define DAYS_DELTA (365 * 10 + 2)
/* 120 (2100 - 1980) isn't leap year */
@@ -213,58 +210,35 @@ void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts,
void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts,
__le16 *time, __le16 *date, u8 *time_cs)
{
- time_t second = ts->tv_sec;
- time_t day, leap_day, month, year;
+ struct tm tm;
+ time_to_tm(ts->tv_sec, sbi->options.tz_utc ? 0 :
+ -sys_tz.tz_minuteswest * 60, &tm);
- if (!sbi->options.tz_utc)
- second -= sys_tz.tz_minuteswest * SECS_PER_MIN;
-
- /* Jan 1 GMT 00:00:00 1980. But what about another time zone? */
- if (second < UNIX_SECS_1980) {
+ /* FAT can only support year between 1980 to 2107 */
+ if (tm.tm_year < 1980 - 1900) {
*time = 0;
*date = cpu_to_le16((0 << 9) | (1 << 5) | 1);
if (time_cs)
*time_cs = 0;
return;
}
-#if BITS_PER_LONG == 64
- if (second >= UNIX_SECS_2108) {
+ if (tm.tm_year > 2107 - 1900) {
*time = cpu_to_le16((23 << 11) | (59 << 5) | 29);
*date = cpu_to_le16((127 << 9) | (12 << 5) | 31);
if (time_cs)
*time_cs = 199;
return;
}
-#endif
- day = second / SECS_PER_DAY - DAYS_DELTA;
- year = day / 365;
- leap_day = (year + 3) / 4;
- if (year > YEAR_2100) /* 2100 isn't leap year */
- leap_day--;
- if (year * 365 + leap_day > day)
- year--;
- leap_day = (year + 3) / 4;
- if (year > YEAR_2100) /* 2100 isn't leap year */
- leap_day--;
- day -= year * 365 + leap_day;
-
- if (IS_LEAP_YEAR(year) && day == days_in_year[3]) {
- month = 2;
- } else {
- if (IS_LEAP_YEAR(year) && day > days_in_year[3])
- day--;
- for (month = 1; month < 12; month++) {
- if (days_in_year[month + 1] > day)
- break;
- }
- }
- day -= days_in_year[month];
+ /* from 1900 -> from 1980 */
+ tm.tm_year -= 80;
+ /* 0~11 -> 1~12 */
+ tm.tm_mon++;
+ /* 0~59 -> 0~29(2sec counts) */
+ tm.tm_sec >>= 1;
- *time = cpu_to_le16(((second / SECS_PER_HOUR) % 24) << 11
- | ((second / SECS_PER_MIN) % 60) << 5
- | (second % SECS_PER_MIN) >> 1);
- *date = cpu_to_le16((year << 9) | (month << 5) | (day + 1));
+ *time = cpu_to_le16(tm.tm_hour << 11 | tm.tm_min << 5 | tm.tm_sec);
+ *date = cpu_to_le16(tm.tm_year << 9 | tm.tm_mon << 5 | tm.tm_mday);
if (time_cs)
*time_cs = (ts->tv_sec & 1) * 100 + ts->tv_nsec / 10000000;
}
@@ -285,4 +259,3 @@ int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs)
}
return err;
}
-
diff --git a/fs/file_table.c b/fs/file_table.c
index 4bef4c01ec6..17a55b81be2 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -21,9 +21,12 @@
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/percpu_counter.h>
+#include <linux/ima.h>
#include <asm/atomic.h>
+#include "internal.h"
+
/* sysctl tunables... */
struct files_stat_struct files_stat = {
.max_files = NR_FILE
@@ -147,8 +150,6 @@ fail:
return NULL;
}
-EXPORT_SYMBOL(get_empty_filp);
-
/**
* alloc_file - allocate and initialize a 'struct file'
* @mnt: the vfsmount on which the file will reside
@@ -164,8 +165,8 @@ EXPORT_SYMBOL(get_empty_filp);
* If all the callers of init_file() are eliminated, its
* code should be moved into this function.
*/
-struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
- fmode_t mode, const struct file_operations *fop)
+struct file *alloc_file(struct path *path, fmode_t mode,
+ const struct file_operations *fop)
{
struct file *file;
@@ -173,35 +174,8 @@ struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
if (!file)
return NULL;
- init_file(file, mnt, dentry, mode, fop);
- return file;
-}
-EXPORT_SYMBOL(alloc_file);
-
-/**
- * init_file - initialize a 'struct file'
- * @file: the already allocated 'struct file' to initialized
- * @mnt: the vfsmount on which the file resides
- * @dentry: the dentry representing this file
- * @mode: the mode the file is opened with
- * @fop: the 'struct file_operations' for this file
- *
- * Use this instead of setting the members directly. Doing so
- * avoids making mistakes like forgetting the mntget() or
- * forgetting to take a write on the mnt.
- *
- * Note: This is a crappy interface. It is here to make
- * merging with the existing users of get_empty_filp()
- * who have complex failure logic easier. All users
- * of this should be moving to alloc_file().
- */
-int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
- fmode_t mode, const struct file_operations *fop)
-{
- int error = 0;
- file->f_path.dentry = dentry;
- file->f_path.mnt = mntget(mnt);
- file->f_mapping = dentry->d_inode->i_mapping;
+ file->f_path = *path;
+ file->f_mapping = path->dentry->d_inode->i_mapping;
file->f_mode = mode;
file->f_op = fop;
@@ -211,14 +185,15 @@ int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
* visible. We do this for consistency, and so
* that we can do debugging checks at __fput()
*/
- if ((mode & FMODE_WRITE) && !special_file(dentry->d_inode->i_mode)) {
+ if ((mode & FMODE_WRITE) && !special_file(path->dentry->d_inode->i_mode)) {
+ int error = 0;
file_take_write(file);
- error = mnt_clone_write(mnt);
+ error = mnt_clone_write(path->mnt);
WARN_ON(error);
}
- return error;
+ ima_counts_get(file);
+ return file;
}
-EXPORT_SYMBOL(init_file);
void fput(struct file *file)
{
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index e590242fa41..3221a0c7944 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -91,7 +91,7 @@ EXPORT_SYMBOL(fscache_object_destroy);
*/
static struct fscache_object *fscache_objlist_lookup(loff_t *_pos)
{
- struct fscache_object *pobj, *obj, *minobj = NULL;
+ struct fscache_object *pobj, *obj = NULL, *minobj = NULL;
struct rb_node *p;
unsigned long pos;
diff --git a/fs/generic_acl.c b/fs/generic_acl.c
index e0b53aa7bbe..55458031e50 100644
--- a/fs/generic_acl.c
+++ b/fs/generic_acl.c
@@ -1,62 +1,58 @@
/*
- * fs/generic_acl.c
- *
* (C) 2005 Andreas Gruenbacher <agruen@suse.de>
*
* This file is released under the GPL.
+ *
+ * Generic ACL support for in-memory filesystems.
*/
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/generic_acl.h>
+#include <linux/posix_acl.h>
+#include <linux/posix_acl_xattr.h>
-/**
- * generic_acl_list - Generic xattr_handler->list() operation
- * @ops: Filesystem specific getacl and setacl callbacks
- */
-size_t
-generic_acl_list(struct inode *inode, struct generic_acl_operations *ops,
- int type, char *list, size_t list_size)
+
+static size_t
+generic_acl_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int type)
{
struct posix_acl *acl;
- const char *name;
+ const char *xname;
size_t size;
- acl = ops->getacl(inode, type);
+ acl = get_cached_acl(dentry->d_inode, type);
if (!acl)
return 0;
posix_acl_release(acl);
- switch(type) {
- case ACL_TYPE_ACCESS:
- name = POSIX_ACL_XATTR_ACCESS;
- break;
-
- case ACL_TYPE_DEFAULT:
- name = POSIX_ACL_XATTR_DEFAULT;
- break;
-
- default:
- return 0;
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ xname = POSIX_ACL_XATTR_ACCESS;
+ break;
+ case ACL_TYPE_DEFAULT:
+ xname = POSIX_ACL_XATTR_DEFAULT;
+ break;
+ default:
+ return 0;
}
- size = strlen(name) + 1;
+ size = strlen(xname) + 1;
if (list && size <= list_size)
- memcpy(list, name, size);
+ memcpy(list, xname, size);
return size;
}
-/**
- * generic_acl_get - Generic xattr_handler->get() operation
- * @ops: Filesystem specific getacl and setacl callbacks
- */
-int
-generic_acl_get(struct inode *inode, struct generic_acl_operations *ops,
- int type, void *buffer, size_t size)
+static int
+generic_acl_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- acl = ops->getacl(inode, type);
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
+
+ acl = get_cached_acl(dentry->d_inode, type);
if (!acl)
return -ENODATA;
error = posix_acl_to_xattr(acl, buffer, size);
@@ -65,17 +61,16 @@ generic_acl_get(struct inode *inode, struct generic_acl_operations *ops,
return error;
}
-/**
- * generic_acl_set - Generic xattr_handler->set() operation
- * @ops: Filesystem specific getacl and setacl callbacks
- */
-int
-generic_acl_set(struct inode *inode, struct generic_acl_operations *ops,
- int type, const void *value, size_t size)
+static int
+generic_acl_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
struct posix_acl *acl = NULL;
int error;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
if (!is_owner_or_cap(inode))
@@ -91,28 +86,27 @@ generic_acl_set(struct inode *inode, struct generic_acl_operations *ops,
error = posix_acl_valid(acl);
if (error)
goto failed;
- switch(type) {
- case ACL_TYPE_ACCESS:
- mode = inode->i_mode;
- error = posix_acl_equiv_mode(acl, &mode);
- if (error < 0)
- goto failed;
- inode->i_mode = mode;
- if (error == 0) {
- posix_acl_release(acl);
- acl = NULL;
- }
- break;
-
- case ACL_TYPE_DEFAULT:
- if (!S_ISDIR(inode->i_mode)) {
- error = -EINVAL;
- goto failed;
- }
- break;
+ switch (type) {
+ case ACL_TYPE_ACCESS:
+ mode = inode->i_mode;
+ error = posix_acl_equiv_mode(acl, &mode);
+ if (error < 0)
+ goto failed;
+ inode->i_mode = mode;
+ if (error == 0) {
+ posix_acl_release(acl);
+ acl = NULL;
+ }
+ break;
+ case ACL_TYPE_DEFAULT:
+ if (!S_ISDIR(inode->i_mode)) {
+ error = -EINVAL;
+ goto failed;
+ }
+ break;
}
}
- ops->setacl(inode, type, acl);
+ set_cached_acl(inode, type, acl);
error = 0;
failed:
posix_acl_release(acl);
@@ -121,14 +115,12 @@ failed:
/**
* generic_acl_init - Take care of acl inheritance at @inode create time
- * @ops: Filesystem specific getacl and setacl callbacks
*
* Files created inside a directory with a default ACL inherit the
* directory's default ACL.
*/
int
-generic_acl_init(struct inode *inode, struct inode *dir,
- struct generic_acl_operations *ops)
+generic_acl_init(struct inode *inode, struct inode *dir)
{
struct posix_acl *acl = NULL;
mode_t mode = inode->i_mode;
@@ -136,7 +128,7 @@ generic_acl_init(struct inode *inode, struct inode *dir,
inode->i_mode = mode & ~current_umask();
if (!S_ISLNK(inode->i_mode))
- acl = ops->getacl(dir, ACL_TYPE_DEFAULT);
+ acl = get_cached_acl(dir, ACL_TYPE_DEFAULT);
if (acl) {
struct posix_acl *clone;
@@ -145,7 +137,7 @@ generic_acl_init(struct inode *inode, struct inode *dir,
error = -ENOMEM;
if (!clone)
goto cleanup;
- ops->setacl(inode, ACL_TYPE_DEFAULT, clone);
+ set_cached_acl(inode, ACL_TYPE_DEFAULT, clone);
posix_acl_release(clone);
}
clone = posix_acl_clone(acl, GFP_KERNEL);
@@ -156,7 +148,7 @@ generic_acl_init(struct inode *inode, struct inode *dir,
if (error >= 0) {
inode->i_mode = mode;
if (error > 0)
- ops->setacl(inode, ACL_TYPE_ACCESS, clone);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, clone);
}
posix_acl_release(clone);
}
@@ -169,20 +161,19 @@ cleanup:
/**
* generic_acl_chmod - change the access acl of @inode upon chmod()
- * @ops: FIlesystem specific getacl and setacl callbacks
*
* A chmod also changes the permissions of the owner, group/mask, and
* other ACL entries.
*/
int
-generic_acl_chmod(struct inode *inode, struct generic_acl_operations *ops)
+generic_acl_chmod(struct inode *inode)
{
struct posix_acl *acl, *clone;
int error = 0;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
- acl = ops->getacl(inode, ACL_TYPE_ACCESS);
+ acl = get_cached_acl(inode, ACL_TYPE_ACCESS);
if (acl) {
clone = posix_acl_clone(acl, GFP_KERNEL);
posix_acl_release(acl);
@@ -190,8 +181,37 @@ generic_acl_chmod(struct inode *inode, struct generic_acl_operations *ops)
return -ENOMEM;
error = posix_acl_chmod_masq(clone, inode->i_mode);
if (!error)
- ops->setacl(inode, ACL_TYPE_ACCESS, clone);
+ set_cached_acl(inode, ACL_TYPE_ACCESS, clone);
posix_acl_release(clone);
}
return error;
}
+
+int
+generic_check_acl(struct inode *inode, int mask)
+{
+ struct posix_acl *acl = get_cached_acl(inode, ACL_TYPE_ACCESS);
+
+ if (acl) {
+ int error = posix_acl_permission(inode, acl, mask);
+ posix_acl_release(acl);
+ return error;
+ }
+ return -EAGAIN;
+}
+
+struct xattr_handler generic_acl_access_handler = {
+ .prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .list = generic_acl_list,
+ .get = generic_acl_get,
+ .set = generic_acl_set,
+};
+
+struct xattr_handler generic_acl_default_handler = {
+ .prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .list = generic_acl_list,
+ .get = generic_acl_get,
+ .set = generic_acl_set,
+};
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 3eb1ea84617..87ee309d4c2 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -126,7 +126,7 @@ static int gfs2_acl_set(struct inode *inode, int type, struct posix_acl *acl)
error = posix_acl_to_xattr(acl, data, len);
if (error < 0)
goto out;
- error = gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, data, len, 0);
+ error = __gfs2_xattr_set(inode, name, data, len, 0, GFS2_EATYPE_SYS);
if (!error)
set_cached_acl(inode, type, acl);
out:
@@ -232,9 +232,10 @@ static int gfs2_acl_type(const char *name)
return -EINVAL;
}
-static int gfs2_xattr_system_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int gfs2_xattr_system_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int xtype)
{
+ struct inode *inode = dentry->d_inode;
struct posix_acl *acl;
int type;
int error;
@@ -255,9 +256,11 @@ static int gfs2_xattr_system_get(struct inode *inode, const char *name,
return error;
}
-static int gfs2_xattr_system_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int gfs2_xattr_system_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags,
+ int xtype)
{
+ struct inode *inode = dentry->d_inode;
struct gfs2_sbd *sdp = GFS2_SB(inode);
struct posix_acl *acl = NULL;
int error = 0, type;
@@ -319,7 +322,7 @@ static int gfs2_xattr_system_set(struct inode *inode, const char *name,
}
set_acl:
- error = gfs2_xattr_set(inode, GFS2_EATYPE_SYS, name, value, size, 0);
+ error = __gfs2_xattr_set(inode, name, value, size, 0, GFS2_EATYPE_SYS);
if (!error) {
if (acl)
set_cached_acl(inode, type, acl);
@@ -334,6 +337,7 @@ out:
struct xattr_handler gfs2_xattr_system_handler = {
.prefix = XATTR_SYSTEM_PREFIX,
+ .flags = GFS2_EATYPE_SYS,
.get = gfs2_xattr_system_get,
.set = gfs2_xattr_system_set,
};
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 26ba2a4c4a2..3ff32fa793d 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -801,7 +801,8 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
return err;
}
- err = gfs2_xattr_set(&ip->i_inode, GFS2_EATYPE_SECURITY, name, value, len, 0);
+ err = __gfs2_xattr_set(&ip->i_inode, name, value, len, 0,
+ GFS2_EATYPE_SECURITY);
kfree(value);
kfree(name);
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 912f5cbc474..8a04108e0c2 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -567,18 +567,17 @@ out:
/**
* gfs2_xattr_get - Get a GFS2 extended attribute
* @inode: The inode
- * @type: The type of extended attribute
* @name: The name of the extended attribute
* @buffer: The buffer to write the result into
* @size: The size of the buffer
+ * @type: The type of extended attribute
*
* Returns: actual size of data on success, -errno on error
*/
-
-int gfs2_xattr_get(struct inode *inode, int type, const char *name,
- void *buffer, size_t size)
+static int gfs2_xattr_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
- struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
struct gfs2_ea_location el;
int error;
@@ -1119,7 +1118,7 @@ static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
/**
* gfs2_xattr_remove - Remove a GFS2 extended attribute
- * @inode: The inode
+ * @ip: The inode
* @type: The type of the extended attribute
* @name: The name of the extended attribute
*
@@ -1130,9 +1129,8 @@ static int ea_remove_stuffed(struct gfs2_inode *ip, struct gfs2_ea_location *el)
* Returns: 0, or errno on failure
*/
-static int gfs2_xattr_remove(struct inode *inode, int type, const char *name)
+static int gfs2_xattr_remove(struct gfs2_inode *ip, int type, const char *name)
{
- struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_ea_location el;
int error;
@@ -1156,24 +1154,24 @@ static int gfs2_xattr_remove(struct inode *inode, int type, const char *name)
}
/**
- * gfs2_xattr_set - Set (or remove) a GFS2 extended attribute
- * @inode: The inode
- * @type: The type of the extended attribute
+ * __gfs2_xattr_set - Set (or remove) a GFS2 extended attribute
+ * @ip: The inode
* @name: The name of the extended attribute
* @value: The value of the extended attribute (NULL for remove)
* @size: The size of the @value argument
* @flags: Create or Replace
+ * @type: The type of the extended attribute
*
* See gfs2_xattr_remove() for details of the removal of xattrs.
*
* Returns: 0 or errno on failure
*/
-int gfs2_xattr_set(struct inode *inode, int type, const char *name,
- const void *value, size_t size, int flags)
+int __gfs2_xattr_set(struct inode *inode, const char *name,
+ const void *value, size_t size, int flags, int type)
{
- struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct gfs2_ea_location el;
unsigned int namel = strlen(name);
int error;
@@ -1184,7 +1182,7 @@ int gfs2_xattr_set(struct inode *inode, int type, const char *name,
return -ERANGE;
if (value == NULL)
- return gfs2_xattr_remove(inode, type, name);
+ return gfs2_xattr_remove(ip, type, name);
if (ea_check_size(sdp, namel, size))
return -ERANGE;
@@ -1224,6 +1222,13 @@ int gfs2_xattr_set(struct inode *inode, int type, const char *name,
return error;
}
+static int gfs2_xattr_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
+{
+ return __gfs2_xattr_set(dentry->d_inode, name, value,
+ size, flags, type);
+}
+
static int ea_acl_chmod_unstuffed(struct gfs2_inode *ip,
struct gfs2_ea_header *ea, char *data)
{
@@ -1529,40 +1534,18 @@ out_alloc:
return error;
}
-static int gfs2_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- return gfs2_xattr_get(inode, GFS2_EATYPE_USR, name, buffer, size);
-}
-
-static int gfs2_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return gfs2_xattr_set(inode, GFS2_EATYPE_USR, name, value, size, flags);
-}
-
-static int gfs2_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- return gfs2_xattr_get(inode, GFS2_EATYPE_SECURITY, name, buffer, size);
-}
-
-static int gfs2_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return gfs2_xattr_set(inode, GFS2_EATYPE_SECURITY, name, value, size, flags);
-}
-
static struct xattr_handler gfs2_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
- .get = gfs2_xattr_user_get,
- .set = gfs2_xattr_user_set,
+ .flags = GFS2_EATYPE_USR,
+ .get = gfs2_xattr_get,
+ .set = gfs2_xattr_set,
};
static struct xattr_handler gfs2_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
- .get = gfs2_xattr_security_get,
- .set = gfs2_xattr_security_set,
+ .flags = GFS2_EATYPE_SECURITY,
+ .get = gfs2_xattr_get,
+ .set = gfs2_xattr_set,
};
struct xattr_handler *gfs2_xattr_handlers[] = {
diff --git a/fs/gfs2/xattr.h b/fs/gfs2/xattr.h
index 8d6ae5813c4..d392f8358f2 100644
--- a/fs/gfs2/xattr.h
+++ b/fs/gfs2/xattr.h
@@ -53,10 +53,9 @@ struct gfs2_ea_location {
struct gfs2_ea_header *el_prev;
};
-extern int gfs2_xattr_get(struct inode *inode, int type, const char *name,
- void *buffer, size_t size);
-extern int gfs2_xattr_set(struct inode *inode, int type, const char *name,
- const void *value, size_t size, int flags);
+extern int __gfs2_xattr_set(struct inode *inode, const char *name,
+ const void *value, size_t size,
+ int flags, int type);
extern ssize_t gfs2_listxattr(struct dentry *dentry, char *buffer, size_t size);
extern int gfs2_ea_dealloc(struct gfs2_inode *ip);
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index f2feaa06bf2..cadc4ce4865 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -14,6 +14,7 @@
#include <linux/magic.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
+#include <linux/bitmap.h>
/* Mark the filesystem dirty, so that chkdsk checks it when os/2 booted */
@@ -115,15 +116,13 @@ static void hpfs_put_super(struct super_block *s)
unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
{
struct quad_buffer_head qbh;
- unsigned *bits;
- unsigned i, count;
- if (!(bits = hpfs_map_4sectors(s, secno, &qbh, 4))) return 0;
- count = 0;
- for (i = 0; i < 2048 / sizeof(unsigned); i++) {
- unsigned b;
- if (!bits[i]) continue;
- for (b = bits[i]; b; b>>=1) count += b & 1;
- }
+ unsigned long *bits;
+ unsigned count;
+
+ bits = hpfs_map_4sectors(s, secno, &qbh, 4);
+ if (!bits)
+ return 0;
+ count = bitmap_weight(bits, 2048 * BITS_PER_BYTE);
hpfs_brelse4(&qbh);
return count;
}
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 87a1258953b..a0bbd3d1b41 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -30,7 +30,6 @@
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
-#include <linux/ima.h>
#include <linux/magic.h>
#include <asm/uaccess.h>
@@ -922,7 +921,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
int error = -ENOMEM;
struct file *file;
struct inode *inode;
- struct dentry *dentry, *root;
+ struct path path;
+ struct dentry *root;
struct qstr quick_string;
*user = NULL;
@@ -944,10 +944,11 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
quick_string.name = name;
quick_string.len = strlen(quick_string.name);
quick_string.hash = 0;
- dentry = d_alloc(root, &quick_string);
- if (!dentry)
+ path.dentry = d_alloc(root, &quick_string);
+ if (!path.dentry)
goto out_shm_unlock;
+ path.mnt = mntget(hugetlbfs_vfsmount);
error = -ENOSPC;
inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(),
current_fsgid(), S_IFREG | S_IRWXUGO, 0);
@@ -960,24 +961,22 @@ struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
acctflag))
goto out_inode;
- d_instantiate(dentry, inode);
+ d_instantiate(path.dentry, inode);
inode->i_size = size;
inode->i_nlink = 0;
error = -ENFILE;
- file = alloc_file(hugetlbfs_vfsmount, dentry,
- FMODE_WRITE | FMODE_READ,
+ file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
&hugetlbfs_file_operations);
if (!file)
goto out_dentry; /* inode is already attached */
- ima_counts_get(file);
return file;
out_inode:
iput(inode);
out_dentry:
- dput(dentry);
+ path_put(&path);
out_shm_unlock:
if (*user) {
user_shm_unlock(size, *user);
diff --git a/fs/internal.h b/fs/internal.h
index 515175b8b72..f67cd141d9a 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -79,6 +79,7 @@ extern void chroot_fs_refs(struct path *, struct path *);
* file_table.c
*/
extern void mark_files_ro(struct super_block *);
+extern struct file *get_empty_filp(void);
/*
* super.c
diff --git a/fs/isofs/export.c b/fs/isofs/export.c
index e81a30593ba..ed752cb3847 100644
--- a/fs/isofs/export.c
+++ b/fs/isofs/export.c
@@ -9,7 +9,7 @@
*
* The following files are helpful:
*
- * Documentation/filesystems/Exporting
+ * Documentation/filesystems/nfs/Exporting
* fs/exportfs/expfs.c.
*/
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index 7edb62e9741..7cdc3196476 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -350,8 +350,8 @@ int jffs2_acl_chmod(struct inode *inode)
return rc;
}
-static size_t jffs2_acl_access_listxattr(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t jffs2_acl_access_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
{
const int retlen = sizeof(POSIX_ACL_XATTR_ACCESS);
@@ -360,8 +360,8 @@ static size_t jffs2_acl_access_listxattr(struct inode *inode, char *list, size_t
return retlen;
}
-static size_t jffs2_acl_default_listxattr(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t jffs2_acl_default_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
{
const int retlen = sizeof(POSIX_ACL_XATTR_DEFAULT);
@@ -370,12 +370,16 @@ static size_t jffs2_acl_default_listxattr(struct inode *inode, char *list, size_
return retlen;
}
-static int jffs2_acl_getxattr(struct inode *inode, int type, void *buffer, size_t size)
+static int jffs2_acl_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
struct posix_acl *acl;
int rc;
- acl = jffs2_get_acl(inode, type);
+ if (name[0] != '\0')
+ return -EINVAL;
+
+ acl = jffs2_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (!acl)
@@ -386,26 +390,15 @@ static int jffs2_acl_getxattr(struct inode *inode, int type, void *buffer, size_
return rc;
}
-static int jffs2_acl_access_getxattr(struct inode *inode, const char *name, void *buffer, size_t size)
-{
- if (name[0] != '\0')
- return -EINVAL;
- return jffs2_acl_getxattr(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int jffs2_acl_default_getxattr(struct inode *inode, const char *name, void *buffer, size_t size)
-{
- if (name[0] != '\0')
- return -EINVAL;
- return jffs2_acl_getxattr(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int jffs2_acl_setxattr(struct inode *inode, int type, const void *value, size_t size)
+static int jffs2_acl_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
struct posix_acl *acl;
int rc;
- if (!is_owner_or_cap(inode))
+ if (name[0] != '\0')
+ return -EINVAL;
+ if (!is_owner_or_cap(dentry->d_inode))
return -EPERM;
if (value) {
@@ -420,38 +413,24 @@ static int jffs2_acl_setxattr(struct inode *inode, int type, const void *value,
} else {
acl = NULL;
}
- rc = jffs2_set_acl(inode, type, acl);
+ rc = jffs2_set_acl(dentry->d_inode, type, acl);
out:
posix_acl_release(acl);
return rc;
}
-static int jffs2_acl_access_setxattr(struct inode *inode, const char *name,
- const void *buffer, size_t size, int flags)
-{
- if (name[0] != '\0')
- return -EINVAL;
- return jffs2_acl_setxattr(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int jffs2_acl_default_setxattr(struct inode *inode, const char *name,
- const void *buffer, size_t size, int flags)
-{
- if (name[0] != '\0')
- return -EINVAL;
- return jffs2_acl_setxattr(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
struct xattr_handler jffs2_acl_access_xattr_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_DEFAULT,
.list = jffs2_acl_access_listxattr,
- .get = jffs2_acl_access_getxattr,
- .set = jffs2_acl_access_setxattr,
+ .get = jffs2_acl_getxattr,
+ .set = jffs2_acl_setxattr,
};
struct xattr_handler jffs2_acl_default_xattr_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = jffs2_acl_default_listxattr,
- .get = jffs2_acl_default_getxattr,
- .set = jffs2_acl_default_setxattr,
+ .get = jffs2_acl_getxattr,
+ .set = jffs2_acl_setxattr,
};
diff --git a/fs/jffs2/gc.c b/fs/jffs2/gc.c
index 090c556ffed..3b6f2fa12cf 100644
--- a/fs/jffs2/gc.c
+++ b/fs/jffs2/gc.c
@@ -700,7 +700,8 @@ static int jffs2_garbage_collect_metadata(struct jffs2_sb_info *c, struct jffs2_
struct jffs2_raw_inode ri;
struct jffs2_node_frag *last_frag;
union jffs2_device_node dev;
- char *mdata = NULL, mdatalen = 0;
+ char *mdata = NULL;
+ int mdatalen = 0;
uint32_t alloclen, ilen;
int ret;
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index 378991cfe40..e22de8397b7 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -1284,7 +1284,7 @@ static int jffs2_do_read_inode_internal(struct jffs2_sb_info *c,
f->target = NULL;
mutex_unlock(&f->sem);
jffs2_do_clear_inode(c, f);
- return -ret;
+ return ret;
}
f->target[je32_to_cpu(latest_node->csize)] = '\0';
diff --git a/fs/jffs2/security.c b/fs/jffs2/security.c
index 02c39c64ecb..eaccee05858 100644
--- a/fs/jffs2/security.c
+++ b/fs/jffs2/security.c
@@ -44,26 +44,28 @@ int jffs2_init_security(struct inode *inode, struct inode *dir)
}
/* ---- XATTR Handler for "security.*" ----------------- */
-static int jffs2_security_getxattr(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int jffs2_security_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_getxattr(inode, JFFS2_XPREFIX_SECURITY, name, buffer, size);
+ return do_jffs2_getxattr(dentry->d_inode, JFFS2_XPREFIX_SECURITY,
+ name, buffer, size);
}
-static int jffs2_security_setxattr(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+static int jffs2_security_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_setxattr(inode, JFFS2_XPREFIX_SECURITY, name, buffer, size, flags);
+ return do_jffs2_setxattr(dentry->d_inode, JFFS2_XPREFIX_SECURITY,
+ name, buffer, size, flags);
}
-static size_t jffs2_security_listxattr(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t jffs2_security_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
{
size_t retlen = XATTR_SECURITY_PREFIX_LEN + name_len + 1;
diff --git a/fs/jffs2/summary.c b/fs/jffs2/summary.c
index 6caf1e1ee26..800171dca53 100644
--- a/fs/jffs2/summary.c
+++ b/fs/jffs2/summary.c
@@ -23,7 +23,7 @@
int jffs2_sum_init(struct jffs2_sb_info *c)
{
- uint32_t sum_size = max_t(uint32_t, c->sector_size, MAX_SUMMARY_SIZE);
+ uint32_t sum_size = min_t(uint32_t, c->sector_size, MAX_SUMMARY_SIZE);
c->summary = kzalloc(sizeof(struct jffs2_summary), GFP_KERNEL);
diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c
index 4b107881acd..9e75c62c85d 100644
--- a/fs/jffs2/xattr.c
+++ b/fs/jffs2/xattr.c
@@ -990,9 +990,11 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size)
if (!xhandle)
continue;
if (buffer) {
- rc = xhandle->list(inode, buffer+len, size-len, xd->xname, xd->name_len);
+ rc = xhandle->list(dentry, buffer+len, size-len,
+ xd->xname, xd->name_len, xd->flags);
} else {
- rc = xhandle->list(inode, NULL, 0, xd->xname, xd->name_len);
+ rc = xhandle->list(dentry, NULL, 0, xd->xname,
+ xd->name_len, xd->flags);
}
if (rc < 0)
goto out;
diff --git a/fs/jffs2/xattr_trusted.c b/fs/jffs2/xattr_trusted.c
index 8ec5765ef34..3e5a5e356e0 100644
--- a/fs/jffs2/xattr_trusted.c
+++ b/fs/jffs2/xattr_trusted.c
@@ -16,24 +16,26 @@
#include <linux/mtd/mtd.h>
#include "nodelist.h"
-static int jffs2_trusted_getxattr(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int jffs2_trusted_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_getxattr(inode, JFFS2_XPREFIX_TRUSTED, name, buffer, size);
+ return do_jffs2_getxattr(dentry->d_inode, JFFS2_XPREFIX_TRUSTED,
+ name, buffer, size);
}
-static int jffs2_trusted_setxattr(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+static int jffs2_trusted_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_setxattr(inode, JFFS2_XPREFIX_TRUSTED, name, buffer, size, flags);
+ return do_jffs2_setxattr(dentry->d_inode, JFFS2_XPREFIX_TRUSTED,
+ name, buffer, size, flags);
}
-static size_t jffs2_trusted_listxattr(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t jffs2_trusted_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
{
size_t retlen = XATTR_TRUSTED_PREFIX_LEN + name_len + 1;
diff --git a/fs/jffs2/xattr_user.c b/fs/jffs2/xattr_user.c
index 8bbeab90ada..8544af67dff 100644
--- a/fs/jffs2/xattr_user.c
+++ b/fs/jffs2/xattr_user.c
@@ -16,24 +16,26 @@
#include <linux/mtd/mtd.h>
#include "nodelist.h"
-static int jffs2_user_getxattr(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int jffs2_user_getxattr(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_getxattr(inode, JFFS2_XPREFIX_USER, name, buffer, size);
+ return do_jffs2_getxattr(dentry->d_inode, JFFS2_XPREFIX_USER,
+ name, buffer, size);
}
-static int jffs2_user_setxattr(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+static int jffs2_user_setxattr(struct dentry *dentry, const char *name,
+ const void *buffer, size_t size, int flags, int type)
{
if (!strcmp(name, ""))
return -EINVAL;
- return do_jffs2_setxattr(inode, JFFS2_XPREFIX_USER, name, buffer, size, flags);
+ return do_jffs2_setxattr(dentry->d_inode, JFFS2_XPREFIX_USER,
+ name, buffer, size, flags);
}
-static size_t jffs2_user_listxattr(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t jffs2_user_listxattr(struct dentry *dentry, char *list,
+ size_t list_size, const char *name, size_t name_len, int type)
{
size_t retlen = XATTR_USER_PREFIX_LEN + name_len + 1;
diff --git a/fs/libfs.c b/fs/libfs.c
index 219576c52d8..6e8d17e1dc4 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -848,7 +848,6 @@ EXPORT_SYMBOL(simple_write_end);
EXPORT_SYMBOL(simple_dir_inode_operations);
EXPORT_SYMBOL(simple_dir_operations);
EXPORT_SYMBOL(simple_empty);
-EXPORT_SYMBOL(d_alloc_name);
EXPORT_SYMBOL(simple_fill_super);
EXPORT_SYMBOL(simple_getattr);
EXPORT_SYMBOL(simple_link);
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index bd173a6ca3b..a7966eed3c1 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -11,10 +11,6 @@
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/lockd/lockd.h>
#include <linux/lockd/share.h>
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index e1d28ddd216..56c9519d900 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -11,10 +11,6 @@
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/lockd/lockd.h>
#include <linux/lockd/share.h>
diff --git a/fs/namei.c b/fs/namei.c
index 87f97ba90ad..d2783c8a770 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -35,6 +35,8 @@
#include <linux/fs_struct.h>
#include <asm/uaccess.h>
+#include "internal.h"
+
#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
/* [Feb-1997 T. Schoebel-Theuer]
@@ -108,8 +110,6 @@
* any extra contention...
*/
-static int __link_path_walk(const char *name, struct nameidata *nd);
-
/* In order to reduce some races, while at the same time doing additional
* checking and hopefully speeding things up, we copy filenames to the
* kernel data space before using them..
@@ -414,36 +414,55 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
}
/*
- * Internal lookup() using the new generic dcache.
- * SMP-safe
+ * force_reval_path - force revalidation of a dentry
+ *
+ * In some situations the path walking code will trust dentries without
+ * revalidating them. This causes problems for filesystems that depend on
+ * d_revalidate to handle file opens (e.g. NFSv4). When FS_REVAL_DOT is set
+ * (which indicates that it's possible for the dentry to go stale), force
+ * a d_revalidate call before proceeding.
+ *
+ * Returns 0 if the revalidation was successful. If the revalidation fails,
+ * either return the error returned by d_revalidate or -ESTALE if the
+ * revalidation it just returned 0. If d_revalidate returns 0, we attempt to
+ * invalidate the dentry. It's up to the caller to handle putting references
+ * to the path if necessary.
*/
-static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
+static int
+force_reval_path(struct path *path, struct nameidata *nd)
{
- struct dentry * dentry = __d_lookup(parent, name);
+ int status;
+ struct dentry *dentry = path->dentry;
- /* lockess __d_lookup may fail due to concurrent d_move()
- * in some unrelated directory, so try with d_lookup
+ /*
+ * only check on filesystems where it's possible for the dentry to
+ * become stale. It's assumed that if this flag is set then the
+ * d_revalidate op will also be defined.
*/
- if (!dentry)
- dentry = d_lookup(parent, name);
+ if (!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT))
+ return 0;
- if (dentry && dentry->d_op && dentry->d_op->d_revalidate)
- dentry = do_revalidate(dentry, nd);
+ status = dentry->d_op->d_revalidate(dentry, nd);
+ if (status > 0)
+ return 0;
- return dentry;
+ if (!status) {
+ d_invalidate(dentry);
+ status = -ESTALE;
+ }
+ return status;
}
/*
- * Short-cut version of permission(), for calling by
- * path_walk(), when dcache lock is held. Combines parts
- * of permission() and generic_permission(), and tests ONLY for
- * MAY_EXEC permission.
+ * Short-cut version of permission(), for calling on directories
+ * during pathname resolution. Combines parts of permission()
+ * and generic_permission(), and tests ONLY for MAY_EXEC permission.
*
* If appropriate, check DAC only. If not appropriate, or
- * short-cut DAC fails, then call permission() to do more
+ * short-cut DAC fails, then call ->permission() to do more
* complete permission check.
*/
-static int exec_permission_lite(struct inode *inode)
+static int exec_permission(struct inode *inode)
{
int ret;
@@ -465,99 +484,6 @@ ok:
return security_inode_permission(inode, MAY_EXEC);
}
-/*
- * This is called when everything else fails, and we actually have
- * to go to the low-level filesystem to find out what we should do..
- *
- * We get the directory semaphore, and after getting that we also
- * make sure that nobody added the entry to the dcache in the meantime..
- * SMP-safe
- */
-static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
-{
- struct dentry * result;
- struct inode *dir = parent->d_inode;
-
- mutex_lock(&dir->i_mutex);
- /*
- * First re-do the cached lookup just in case it was created
- * while we waited for the directory semaphore..
- *
- * FIXME! This could use version numbering or similar to
- * avoid unnecessary cache lookups.
- *
- * The "dcache_lock" is purely to protect the RCU list walker
- * from concurrent renames at this point (we mustn't get false
- * negatives from the RCU list walk here, unlike the optimistic
- * fast walk).
- *
- * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
- */
- result = d_lookup(parent, name);
- if (!result) {
- struct dentry *dentry;
-
- /* Don't create child dentry for a dead directory. */
- result = ERR_PTR(-ENOENT);
- if (IS_DEADDIR(dir))
- goto out_unlock;
-
- dentry = d_alloc(parent, name);
- result = ERR_PTR(-ENOMEM);
- if (dentry) {
- result = dir->i_op->lookup(dir, dentry, nd);
- if (result)
- dput(dentry);
- else
- result = dentry;
- }
-out_unlock:
- mutex_unlock(&dir->i_mutex);
- return result;
- }
-
- /*
- * Uhhuh! Nasty case: the cache was re-populated while
- * we waited on the semaphore. Need to revalidate.
- */
- mutex_unlock(&dir->i_mutex);
- if (result->d_op && result->d_op->d_revalidate) {
- result = do_revalidate(result, nd);
- if (!result)
- result = ERR_PTR(-ENOENT);
- }
- return result;
-}
-
-/*
- * Wrapper to retry pathname resolution whenever the underlying
- * file system returns an ESTALE.
- *
- * Retry the whole path once, forcing real lookup requests
- * instead of relying on the dcache.
- */
-static __always_inline int link_path_walk(const char *name, struct nameidata *nd)
-{
- struct path save = nd->path;
- int result;
-
- /* make sure the stuff we saved doesn't go away */
- path_get(&save);
-
- result = __link_path_walk(name, nd);
- if (result == -ESTALE) {
- /* nd->path had been dropped */
- nd->path = save;
- path_get(&nd->path);
- nd->flags |= LOOKUP_REVAL;
- result = __link_path_walk(name, nd);
- }
-
- path_put(&save);
-
- return result;
-}
-
static __always_inline void set_root(struct nameidata *nd)
{
if (!nd->root.mnt) {
@@ -569,6 +495,8 @@ static __always_inline void set_root(struct nameidata *nd)
}
}
+static int link_path_walk(const char *, struct nameidata *);
+
static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
int res = 0;
@@ -641,11 +569,14 @@ static __always_inline int __do_follow_link(struct path *path, struct nameidata
error = 0;
if (s)
error = __vfs_follow_link(nd, s);
+ else if (nd->last_type == LAST_BIND) {
+ error = force_reval_path(&nd->path, nd);
+ if (error)
+ path_put(&nd->path);
+ }
if (dentry->d_inode->i_op->put_link)
dentry->d_inode->i_op->put_link(dentry, nd, cookie);
}
- path_put(path);
-
return error;
}
@@ -672,6 +603,7 @@ static inline int do_follow_link(struct path *path, struct nameidata *nd)
current->total_link_count++;
nd->depth++;
err = __do_follow_link(path, nd);
+ path_put(path);
current->link_count--;
nd->depth--;
return err;
@@ -797,8 +729,19 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
struct path *path)
{
struct vfsmount *mnt = nd->path.mnt;
- struct dentry *dentry = __d_lookup(nd->path.dentry, name);
+ struct dentry *dentry, *parent;
+ struct inode *dir;
+ /*
+ * See if the low-level filesystem might want
+ * to use its own hash..
+ */
+ if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
+ int err = nd->path.dentry->d_op->d_hash(nd->path.dentry, name);
+ if (err < 0)
+ return err;
+ }
+ dentry = __d_lookup(nd->path.dentry, name);
if (!dentry)
goto need_lookup;
if (dentry->d_op && dentry->d_op->d_revalidate)
@@ -810,7 +753,59 @@ done:
return 0;
need_lookup:
- dentry = real_lookup(nd->path.dentry, name, nd);
+ parent = nd->path.dentry;
+ dir = parent->d_inode;
+
+ mutex_lock(&dir->i_mutex);
+ /*
+ * First re-do the cached lookup just in case it was created
+ * while we waited for the directory semaphore..
+ *
+ * FIXME! This could use version numbering or similar to
+ * avoid unnecessary cache lookups.
+ *
+ * The "dcache_lock" is purely to protect the RCU list walker
+ * from concurrent renames at this point (we mustn't get false
+ * negatives from the RCU list walk here, unlike the optimistic
+ * fast walk).
+ *
+ * so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
+ */
+ dentry = d_lookup(parent, name);
+ if (!dentry) {
+ struct dentry *new;
+
+ /* Don't create child dentry for a dead directory. */
+ dentry = ERR_PTR(-ENOENT);
+ if (IS_DEADDIR(dir))
+ goto out_unlock;
+
+ new = d_alloc(parent, name);
+ dentry = ERR_PTR(-ENOMEM);
+ if (new) {
+ dentry = dir->i_op->lookup(dir, new, nd);
+ if (dentry)
+ dput(new);
+ else
+ dentry = new;
+ }
+out_unlock:
+ mutex_unlock(&dir->i_mutex);
+ if (IS_ERR(dentry))
+ goto fail;
+ goto done;
+ }
+
+ /*
+ * Uhhuh! Nasty case: the cache was re-populated while
+ * we waited on the semaphore. Need to revalidate.
+ */
+ mutex_unlock(&dir->i_mutex);
+ if (dentry->d_op && dentry->d_op->d_revalidate) {
+ dentry = do_revalidate(dentry, nd);
+ if (!dentry)
+ dentry = ERR_PTR(-ENOENT);
+ }
if (IS_ERR(dentry))
goto fail;
goto done;
@@ -835,7 +830,7 @@ fail:
* Returns 0 and nd will have valid dentry and mnt on success.
* Returns error and drops reference to input namei data on failure.
*/
-static int __link_path_walk(const char *name, struct nameidata *nd)
+static int link_path_walk(const char *name, struct nameidata *nd)
{
struct path next;
struct inode *inode;
@@ -858,7 +853,7 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
unsigned int c;
nd->flags |= LOOKUP_CONTINUE;
- err = exec_permission_lite(inode);
+ err = exec_permission(inode);
if (err)
break;
@@ -898,16 +893,6 @@ static int __link_path_walk(const char *name, struct nameidata *nd)
case 1:
continue;
}
- /*
- * See if the low-level filesystem might want
- * to use its own hash..
- */
- if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
- err = nd->path.dentry->d_op->d_hash(nd->path.dentry,
- &this);
- if (err < 0)
- break;
- }
/* This does the actual lookups.. */
err = do_lookup(nd, &this, &next);
if (err)
@@ -953,12 +938,6 @@ last_component:
case 1:
goto return_reval;
}
- if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
- err = nd->path.dentry->d_op->d_hash(nd->path.dentry,
- &this);
- if (err < 0)
- break;
- }
err = do_lookup(nd, &this, &next);
if (err)
break;
@@ -1017,8 +996,27 @@ return_err:
static int path_walk(const char *name, struct nameidata *nd)
{
+ struct path save = nd->path;
+ int result;
+
current->total_link_count = 0;
- return link_path_walk(name, nd);
+
+ /* make sure the stuff we saved doesn't go away */
+ path_get(&save);
+
+ result = link_path_walk(name, nd);
+ if (result == -ESTALE) {
+ /* nd->path had been dropped */
+ current->total_link_count = 0;
+ nd->path = save;
+ path_get(&nd->path);
+ nd->flags |= LOOKUP_REVAL;
+ result = link_path_walk(name, nd);
+ }
+
+ path_put(&save);
+
+ return result;
}
static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
@@ -1141,36 +1139,6 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
return retval;
}
-/**
- * path_lookup_open - lookup a file path with open intent
- * @dfd: the directory to use as base, or AT_FDCWD
- * @name: pointer to file name
- * @lookup_flags: lookup intent flags
- * @nd: pointer to nameidata
- * @open_flags: open intent flags
- */
-static int path_lookup_open(int dfd, const char *name,
- unsigned int lookup_flags, struct nameidata *nd, int open_flags)
-{
- struct file *filp = get_empty_filp();
- int err;
-
- if (filp == NULL)
- return -ENFILE;
- nd->intent.open.file = filp;
- nd->intent.open.flags = open_flags;
- nd->intent.open.create_mode = 0;
- err = do_path_lookup(dfd, name, lookup_flags|LOOKUP_OPEN, nd);
- if (IS_ERR(nd->intent.open.file)) {
- if (err == 0) {
- err = PTR_ERR(nd->intent.open.file);
- path_put(&nd->path);
- }
- } else if (err != 0)
- release_open_intent(nd);
- return err;
-}
-
static struct dentry *__lookup_hash(struct qstr *name,
struct dentry *base, struct nameidata *nd)
{
@@ -1191,7 +1159,17 @@ static struct dentry *__lookup_hash(struct qstr *name,
goto out;
}
- dentry = cached_lookup(base, name, nd);
+ dentry = __d_lookup(base, name);
+
+ /* lockess __d_lookup may fail due to concurrent d_move()
+ * in some unrelated directory, so try with d_lookup
+ */
+ if (!dentry)
+ dentry = d_lookup(base, name);
+
+ if (dentry && dentry->d_op && dentry->d_op->d_revalidate)
+ dentry = do_revalidate(dentry, nd);
+
if (!dentry) {
struct dentry *new;
@@ -1223,7 +1201,7 @@ static struct dentry *lookup_hash(struct nameidata *nd)
{
int err;
- err = inode_permission(nd->path.dentry->d_inode, MAY_EXEC);
+ err = exec_permission(nd->path.dentry->d_inode);
if (err)
return ERR_PTR(err);
return __lookup_hash(&nd->last, nd->path.dentry, nd);
@@ -1273,7 +1251,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
if (err)
return ERR_PTR(err);
- err = inode_permission(base->d_inode, MAY_EXEC);
+ err = exec_permission(base->d_inode);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, NULL);
@@ -1511,69 +1489,45 @@ int may_open(struct path *path, int acc_mode, int flag)
if (error)
return error;
- error = ima_path_check(path, acc_mode ?
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC) :
- ACC_MODE(flag) & (MAY_READ | MAY_WRITE),
- IMA_COUNT_UPDATE);
-
- if (error)
- return error;
/*
* An append-only file must be opened in append mode for writing.
*/
if (IS_APPEND(inode)) {
- error = -EPERM;
if ((flag & FMODE_WRITE) && !(flag & O_APPEND))
- goto err_out;
+ return -EPERM;
if (flag & O_TRUNC)
- goto err_out;
+ return -EPERM;
}
/* O_NOATIME can only be set by the owner or superuser */
- if (flag & O_NOATIME)
- if (!is_owner_or_cap(inode)) {
- error = -EPERM;
- goto err_out;
- }
+ if (flag & O_NOATIME && !is_owner_or_cap(inode))
+ return -EPERM;
/*
* Ensure there are no outstanding leases on the file.
*/
- error = break_lease(inode, flag);
- if (error)
- goto err_out;
-
- if (flag & O_TRUNC) {
- error = get_write_access(inode);
- if (error)
- goto err_out;
-
- /*
- * Refuse to truncate files with mandatory locks held on them.
- */
- error = locks_verify_locked(inode);
- if (!error)
- error = security_path_truncate(path, 0,
- ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
- if (!error) {
- vfs_dq_init(inode);
-
- error = do_truncate(dentry, 0,
- ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
- NULL);
- }
- put_write_access(inode);
- if (error)
- goto err_out;
- } else
- if (flag & FMODE_WRITE)
- vfs_dq_init(inode);
+ return break_lease(inode, flag);
+}
- return 0;
-err_out:
- ima_counts_put(path, acc_mode ?
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC) :
- ACC_MODE(flag) & (MAY_READ | MAY_WRITE));
+static int handle_truncate(struct path *path)
+{
+ struct inode *inode = path->dentry->d_inode;
+ int error = get_write_access(inode);
+ if (error)
+ return error;
+ /*
+ * Refuse to truncate files with mandatory locks held on them.
+ */
+ error = locks_verify_locked(inode);
+ if (!error)
+ error = security_path_truncate(path, 0,
+ ATTR_MTIME|ATTR_CTIME|ATTR_OPEN);
+ if (!error) {
+ error = do_truncate(path->dentry, 0,
+ ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
+ NULL);
+ }
+ put_write_access(inode);
return error;
}
@@ -1628,7 +1582,7 @@ static inline int open_to_namei_flags(int flag)
return flag;
}
-static int open_will_write_to_fs(int flag, struct inode *inode)
+static int open_will_truncate(int flag, struct inode *inode)
{
/*
* We'll never write to the fs underlying
@@ -1650,10 +1604,10 @@ struct file *do_filp_open(int dfd, const char *pathname,
struct file *filp;
struct nameidata nd;
int error;
- struct path path;
+ struct path path, save;
struct dentry *dir;
int count = 0;
- int will_write;
+ int will_truncate;
int flag = open_to_namei_flags(open_flag);
/*
@@ -1681,8 +1635,22 @@ struct file *do_filp_open(int dfd, const char *pathname,
* The simplest case - just a plain lookup.
*/
if (!(flag & O_CREAT)) {
- error = path_lookup_open(dfd, pathname, lookup_flags(flag),
- &nd, flag);
+ filp = get_empty_filp();
+
+ if (filp == NULL)
+ return ERR_PTR(-ENFILE);
+ nd.intent.open.file = filp;
+ nd.intent.open.flags = flag;
+ nd.intent.open.create_mode = 0;
+ error = do_path_lookup(dfd, pathname,
+ lookup_flags(flag)|LOOKUP_OPEN, &nd);
+ if (IS_ERR(nd.intent.open.file)) {
+ if (error == 0) {
+ error = PTR_ERR(nd.intent.open.file);
+ path_put(&nd.path);
+ }
+ } else if (error)
+ release_open_intent(&nd);
if (error)
return ERR_PTR(error);
goto ok;
@@ -1758,13 +1726,17 @@ do_last:
goto exit;
}
filp = nameidata_to_filp(&nd, open_flag);
- if (IS_ERR(filp))
- ima_counts_put(&nd.path,
- acc_mode & (MAY_READ | MAY_WRITE |
- MAY_EXEC));
mnt_drop_write(nd.path.mnt);
if (nd.root.mnt)
path_put(&nd.root);
+ if (!IS_ERR(filp)) {
+ error = ima_path_check(&filp->f_path, filp->f_mode &
+ (MAY_READ | MAY_WRITE | MAY_EXEC));
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
return filp;
}
@@ -1805,28 +1777,45 @@ ok:
* be avoided. Taking this mnt write here
* ensures that (2) can not occur.
*/
- will_write = open_will_write_to_fs(flag, nd.path.dentry->d_inode);
- if (will_write) {
+ will_truncate = open_will_truncate(flag, nd.path.dentry->d_inode);
+ if (will_truncate) {
error = mnt_want_write(nd.path.mnt);
if (error)
goto exit;
}
error = may_open(&nd.path, acc_mode, flag);
if (error) {
- if (will_write)
+ if (will_truncate)
mnt_drop_write(nd.path.mnt);
goto exit;
}
filp = nameidata_to_filp(&nd, open_flag);
- if (IS_ERR(filp))
- ima_counts_put(&nd.path,
- acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
+ if (!IS_ERR(filp)) {
+ error = ima_path_check(&filp->f_path, filp->f_mode &
+ (MAY_READ | MAY_WRITE | MAY_EXEC));
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ if (!IS_ERR(filp)) {
+ if (acc_mode & MAY_WRITE)
+ vfs_dq_init(nd.path.dentry->d_inode);
+
+ if (will_truncate) {
+ error = handle_truncate(&nd.path);
+ if (error) {
+ fput(filp);
+ filp = ERR_PTR(error);
+ }
+ }
+ }
/*
* It is now safe to drop the mnt write
* because the filp has had a write taken
* on its behalf.
*/
- if (will_write)
+ if (will_truncate)
mnt_drop_write(nd.path.mnt);
if (nd.root.mnt)
path_put(&nd.root);
@@ -1863,7 +1852,18 @@ do_link:
error = security_inode_follow_link(path.dentry, &nd);
if (error)
goto exit_dput;
+ save = nd.path;
+ path_get(&save);
error = __do_follow_link(&path, &nd);
+ if (error == -ESTALE) {
+ /* nd.path had been dropped */
+ nd.path = save;
+ path_get(&nd.path);
+ nd.flags |= LOOKUP_REVAL;
+ error = __do_follow_link(&path, &nd);
+ }
+ path_put(&save);
+ path_put(&path);
if (error) {
/* Does someone understand code flow here? Or it is only
* me so stupid? Anathema to whoever designed this non-sense
diff --git a/fs/namespace.c b/fs/namespace.c
index 7d70d63ceb2..faab1273281 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2068,7 +2068,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
* create_mnt_ns - creates a private namespace and adds a root filesystem
* @mnt: pointer to the new root filesystem mountpoint
*/
-struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
+static struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
{
struct mnt_namespace *new_ns;
@@ -2080,7 +2080,6 @@ struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
}
return new_ns;
}
-EXPORT_SYMBOL(create_mnt_ns);
SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
char __user *, type, unsigned long, flags, void __user *, data)
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 2a77bc25d5a..59e5673b459 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -90,7 +90,7 @@ config ROOT_NFS
If you want your system to mount its root file system via NFS,
choose Y here. This is common practice for managing systems
without local permanent storage. For details, read
- <file:Documentation/filesystems/nfsroot.txt>.
+ <file:Documentation/filesystems/nfs/nfsroot.txt>.
Most people say N here.
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 7e57b04e401..865265bdca0 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -108,6 +108,10 @@ enum {
NFS_OWNER_RECLAIM_NOGRACE
};
+#define NFS_LOCK_NEW 0
+#define NFS_LOCK_RECLAIM 1
+#define NFS_LOCK_EXPIRED 2
+
/*
* struct nfs4_state maintains the client-side state for a given
* (state_owner,inode) tuple (OPEN) or state_owner (LOCK).
@@ -282,6 +286,7 @@ extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter);
extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
+extern void nfs_release_seqid(struct nfs_seqid *seqid);
extern void nfs_free_seqid(struct nfs_seqid *seqid);
extern const nfs4_stateid zero_stateid;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9f5f11ecfd9..198d51d17c1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -64,6 +64,7 @@
struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
+static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
static int _nfs4_proc_lookup(struct inode *dir, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr);
@@ -341,6 +342,27 @@ nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
free_slotid, tbl->highest_used_slotid);
}
+/*
+ * Signal state manager thread if session is drained
+ */
+static void nfs41_check_drain_session_complete(struct nfs4_session *ses)
+{
+ struct rpc_task *task;
+
+ if (!test_bit(NFS4CLNT_SESSION_DRAINING, &ses->clp->cl_state)) {
+ task = rpc_wake_up_next(&ses->fc_slot_table.slot_tbl_waitq);
+ if (task)
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ return;
+ }
+
+ if (ses->fc_slot_table.highest_used_slotid != -1)
+ return;
+
+ dprintk("%s COMPLETE: Session Drained\n", __func__);
+ complete(&ses->complete);
+}
+
static void nfs41_sequence_free_slot(const struct nfs_client *clp,
struct nfs4_sequence_res *res)
{
@@ -356,15 +378,7 @@ static void nfs41_sequence_free_slot(const struct nfs_client *clp,
spin_lock(&tbl->slot_tbl_lock);
nfs4_free_slot(tbl, res->sr_slotid);
-
- /* Signal state manager thread if session is drained */
- if (test_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state)) {
- if (tbl->highest_used_slotid == -1) {
- dprintk("%s COMPLETE: Session Drained\n", __func__);
- complete(&clp->cl_session->complete);
- }
- } else
- rpc_wake_up_next(&tbl->slot_tbl_waitq);
+ nfs41_check_drain_session_complete(clp->cl_session);
spin_unlock(&tbl->slot_tbl_lock);
res->sr_slotid = NFS4_MAX_SLOT_TABLE;
}
@@ -421,7 +435,7 @@ out:
* Note: must be called with under the slot_tbl_lock.
*/
static u8
-nfs4_find_slot(struct nfs4_slot_table *tbl, struct rpc_task *task)
+nfs4_find_slot(struct nfs4_slot_table *tbl)
{
int slotid;
u8 ret_id = NFS4_MAX_SLOT_TABLE;
@@ -463,7 +477,8 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
tbl = &session->fc_slot_table;
spin_lock(&tbl->slot_tbl_lock);
- if (test_bit(NFS4CLNT_SESSION_DRAINING, &session->clp->cl_state)) {
+ if (test_bit(NFS4CLNT_SESSION_DRAINING, &session->clp->cl_state) &&
+ !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
/*
* The state manager will wait until the slot table is empty.
* Schedule the reset thread
@@ -474,7 +489,15 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
return -EAGAIN;
}
- slotid = nfs4_find_slot(tbl, task);
+ if (!rpc_queue_empty(&tbl->slot_tbl_waitq) &&
+ !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
+ rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+ spin_unlock(&tbl->slot_tbl_lock);
+ dprintk("%s enforce FIFO order\n", __func__);
+ return -EAGAIN;
+ }
+
+ slotid = nfs4_find_slot(tbl);
if (slotid == NFS4_MAX_SLOT_TABLE) {
rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
spin_unlock(&tbl->slot_tbl_lock);
@@ -483,6 +506,7 @@ static int nfs41_setup_sequence(struct nfs4_session *session,
}
spin_unlock(&tbl->slot_tbl_lock);
+ rpc_task_set_priority(task, RPC_PRIORITY_NORMAL);
slot = tbl->slots + slotid;
args->sa_session = session;
args->sa_slotid = slotid;
@@ -545,6 +569,12 @@ static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
rpc_call_start(task);
}
+static void nfs41_call_priv_sync_prepare(struct rpc_task *task, void *calldata)
+{
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ nfs41_call_sync_prepare(task, calldata);
+}
+
static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
{
struct nfs41_call_sync_data *data = calldata;
@@ -557,12 +587,18 @@ struct rpc_call_ops nfs41_call_sync_ops = {
.rpc_call_done = nfs41_call_sync_done,
};
+struct rpc_call_ops nfs41_call_priv_sync_ops = {
+ .rpc_call_prepare = nfs41_call_priv_sync_prepare,
+ .rpc_call_done = nfs41_call_sync_done,
+};
+
static int nfs4_call_sync_sequence(struct nfs_client *clp,
struct rpc_clnt *clnt,
struct rpc_message *msg,
struct nfs4_sequence_args *args,
struct nfs4_sequence_res *res,
- int cache_reply)
+ int cache_reply,
+ int privileged)
{
int ret;
struct rpc_task *task;
@@ -580,6 +616,8 @@ static int nfs4_call_sync_sequence(struct nfs_client *clp,
};
res->sr_slotid = NFS4_MAX_SLOT_TABLE;
+ if (privileged)
+ task_setup.callback_ops = &nfs41_call_priv_sync_ops;
task = rpc_run_task(&task_setup);
if (IS_ERR(task))
ret = PTR_ERR(task);
@@ -597,7 +635,7 @@ int _nfs4_call_sync_session(struct nfs_server *server,
int cache_reply)
{
return nfs4_call_sync_sequence(server->nfs_client, server->client,
- msg, args, res, cache_reply);
+ msg, args, res, cache_reply, 0);
}
#endif /* CONFIG_NFS_V4_1 */
@@ -1035,7 +1073,7 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
memset(&opendata->o_res, 0, sizeof(opendata->o_res));
memset(&opendata->c_res, 0, sizeof(opendata->c_res));
nfs4_init_opendata_res(opendata);
- ret = _nfs4_proc_open(opendata);
+ ret = _nfs4_recover_proc_open(opendata);
if (ret != 0)
return ret;
newstate = nfs4_opendata_to_nfs4_state(opendata);
@@ -1326,6 +1364,12 @@ out_no_action:
}
+static void nfs4_recover_open_prepare(struct rpc_task *task, void *calldata)
+{
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ nfs4_open_prepare(task, calldata);
+}
+
static void nfs4_open_done(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
@@ -1384,10 +1428,13 @@ static const struct rpc_call_ops nfs4_open_ops = {
.rpc_release = nfs4_open_release,
};
-/*
- * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
- */
-static int _nfs4_proc_open(struct nfs4_opendata *data)
+static const struct rpc_call_ops nfs4_recover_open_ops = {
+ .rpc_call_prepare = nfs4_recover_open_prepare,
+ .rpc_call_done = nfs4_open_done,
+ .rpc_release = nfs4_open_release,
+};
+
+static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
{
struct inode *dir = data->dir->d_inode;
struct nfs_server *server = NFS_SERVER(dir);
@@ -1414,21 +1461,57 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
data->rpc_done = 0;
data->rpc_status = 0;
data->cancelled = 0;
+ if (isrecover)
+ task_setup_data.callback_ops = &nfs4_recover_open_ops;
task = rpc_run_task(&task_setup_data);
- if (IS_ERR(task))
- return PTR_ERR(task);
- status = nfs4_wait_for_completion_rpc_task(task);
- if (status != 0) {
- data->cancelled = 1;
- smp_wmb();
- } else
- status = data->rpc_status;
- rpc_put_task(task);
+ if (IS_ERR(task))
+ return PTR_ERR(task);
+ status = nfs4_wait_for_completion_rpc_task(task);
+ if (status != 0) {
+ data->cancelled = 1;
+ smp_wmb();
+ } else
+ status = data->rpc_status;
+ rpc_put_task(task);
+
+ return status;
+}
+
+static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
+{
+ struct inode *dir = data->dir->d_inode;
+ struct nfs_openres *o_res = &data->o_res;
+ int status;
+
+ status = nfs4_run_open_task(data, 1);
if (status != 0 || !data->rpc_done)
return status;
- if (o_res->fh.size == 0)
- _nfs4_proc_lookup(dir, o_arg->name, &o_res->fh, o_res->f_attr);
+ nfs_refresh_inode(dir, o_res->dir_attr);
+
+ if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
+ status = _nfs4_proc_open_confirm(data);
+ if (status != 0)
+ return status;
+ }
+
+ return status;
+}
+
+/*
+ * Note: On error, nfs4_proc_open will free the struct nfs4_opendata
+ */
+static int _nfs4_proc_open(struct nfs4_opendata *data)
+{
+ struct inode *dir = data->dir->d_inode;
+ struct nfs_server *server = NFS_SERVER(dir);
+ struct nfs_openargs *o_arg = &data->o_arg;
+ struct nfs_openres *o_res = &data->o_res;
+ int status;
+
+ status = nfs4_run_open_task(data, 0);
+ if (status != 0 || !data->rpc_done)
+ return status;
if (o_arg->open_flags & O_CREAT) {
update_changeattr(dir, &o_res->cinfo);
@@ -1752,11 +1835,10 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
if (calldata->arg.fmode == 0)
break;
default:
- if (nfs4_async_handle_error(task, server, state) == -EAGAIN) {
- nfs_restart_rpc(task, server->nfs_client);
- return;
- }
+ if (nfs4_async_handle_error(task, server, state) == -EAGAIN)
+ rpc_restart_call_prepare(task);
}
+ nfs_release_seqid(calldata->arg.seqid);
nfs_refresh_inode(calldata->inode, calldata->res.fattr);
}
@@ -1848,8 +1930,6 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, int wait)
calldata->state = state;
calldata->arg.fh = NFS_FH(state->inode);
calldata->arg.stateid = &state->open_stateid;
- if (nfs4_has_session(server->nfs_client))
- memset(calldata->arg.stateid->data, 0, 4); /* clear seqid */
/* Serialization for the sequence id */
calldata->arg.seqid = nfs_alloc_seqid(&state->owner->so_seqid);
if (calldata->arg.seqid == NULL)
@@ -3941,6 +4021,12 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
dprintk("%s: done!, ret = %d\n", __func__, data->rpc_status);
}
+static void nfs4_recover_lock_prepare(struct rpc_task *task, void *calldata)
+{
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ nfs4_lock_prepare(task, calldata);
+}
+
static void nfs4_lock_done(struct rpc_task *task, void *calldata)
{
struct nfs4_lockdata *data = calldata;
@@ -3996,7 +4082,13 @@ static const struct rpc_call_ops nfs4_lock_ops = {
.rpc_release = nfs4_lock_release,
};
-static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int reclaim)
+static const struct rpc_call_ops nfs4_recover_lock_ops = {
+ .rpc_call_prepare = nfs4_recover_lock_prepare,
+ .rpc_call_done = nfs4_lock_done,
+ .rpc_release = nfs4_lock_release,
+};
+
+static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *fl, int recovery_type)
{
struct nfs4_lockdata *data;
struct rpc_task *task;
@@ -4020,8 +4112,11 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
return -ENOMEM;
if (IS_SETLKW(cmd))
data->arg.block = 1;
- if (reclaim != 0)
- data->arg.reclaim = 1;
+ if (recovery_type > NFS_LOCK_NEW) {
+ if (recovery_type == NFS_LOCK_RECLAIM)
+ data->arg.reclaim = NFS_LOCK_RECLAIM;
+ task_setup_data.callback_ops = &nfs4_recover_lock_ops;
+ }
msg.rpc_argp = &data->arg,
msg.rpc_resp = &data->res,
task_setup_data.callback_data = data;
@@ -4048,7 +4143,7 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request
/* Cache the lock if possible... */
if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
return 0;
- err = _nfs4_do_setlk(state, F_SETLK, request, 1);
+ err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM);
if (err != -NFS4ERR_DELAY)
break;
nfs4_handle_exception(server, err, &exception);
@@ -4068,7 +4163,7 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request
do {
if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0)
return 0;
- err = _nfs4_do_setlk(state, F_SETLK, request, 0);
+ err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_EXPIRED);
switch (err) {
default:
goto out;
@@ -4104,7 +4199,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
status = do_vfs_lock(request->fl_file, request);
goto out_unlock;
}
- status = _nfs4_do_setlk(state, cmd, request, 0);
+ status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
if (status != 0)
goto out_unlock;
/* Note: we always want to sleep here! */
@@ -4187,7 +4282,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
if (err != 0)
goto out;
do {
- err = _nfs4_do_setlk(state, F_SETLK, fl, 0);
+ err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
switch (err) {
default:
printk(KERN_ERR "%s: unhandled error %d.\n",
@@ -4395,11 +4490,12 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
(struct nfs4_get_lease_time_data *)calldata;
dprintk("--> %s\n", __func__);
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
/* just setup sequence, do not trigger session recovery
since we're invoked within one */
ret = nfs41_setup_sequence(data->clp->cl_session,
- &data->args->la_seq_args,
- &data->res->lr_seq_res, 0, task);
+ &data->args->la_seq_args,
+ &data->res->lr_seq_res, 0, task);
BUG_ON(ret == -EAGAIN);
rpc_call_start(task);
@@ -4619,7 +4715,7 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
tbl = &session->fc_slot_table;
tbl->highest_used_slotid = -1;
spin_lock_init(&tbl->slot_tbl_lock);
- rpc_init_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
+ rpc_init_priority_wait_queue(&tbl->slot_tbl_waitq, "ForeChannel Slot table");
tbl = &session->bc_slot_table;
tbl->highest_used_slotid = -1;
@@ -4838,14 +4934,22 @@ int nfs4_init_session(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_session *session;
+ unsigned int rsize, wsize;
int ret;
if (!nfs4_has_session(clp))
return 0;
+ rsize = server->rsize;
+ if (rsize == 0)
+ rsize = NFS_MAX_FILE_IO_SIZE;
+ wsize = server->wsize;
+ if (wsize == 0)
+ wsize = NFS_MAX_FILE_IO_SIZE;
+
session = clp->cl_session;
- session->fc_attrs.max_rqst_sz = server->wsize + nfs41_maxwrite_overhead;
- session->fc_attrs.max_resp_sz = server->rsize + nfs41_maxread_overhead;
+ session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
+ session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
ret = nfs4_recover_expired_lease(server);
if (!ret)
@@ -4871,7 +4975,7 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred)
args.sa_cache_this = 0;
return nfs4_call_sync_sequence(clp, clp->cl_rpcclient, &msg, &args,
- &res, 0);
+ &res, args.sa_cache_this, 1);
}
void nfs41_sequence_call_done(struct rpc_task *task, void *data)
@@ -4953,6 +5057,7 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
{
struct nfs4_reclaim_complete_data *calldata = data;
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
if (nfs4_setup_sequence(calldata->clp, &calldata->arg.seq_args,
&calldata->res.seq_res, 0, task))
return;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e76427e6346..6d263ed79e9 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -135,16 +135,30 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp)
return status;
}
-static void nfs41_end_drain_session(struct nfs_client *clp,
- struct nfs4_session *ses)
+static void nfs4_end_drain_session(struct nfs_client *clp)
{
- if (test_and_clear_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state))
- rpc_wake_up(&ses->fc_slot_table.slot_tbl_waitq);
+ struct nfs4_session *ses = clp->cl_session;
+ int max_slots;
+
+ if (test_and_clear_bit(NFS4CLNT_SESSION_DRAINING, &clp->cl_state)) {
+ spin_lock(&ses->fc_slot_table.slot_tbl_lock);
+ max_slots = ses->fc_slot_table.max_slots;
+ while (max_slots--) {
+ struct rpc_task *task;
+
+ task = rpc_wake_up_next(&ses->fc_slot_table.
+ slot_tbl_waitq);
+ if (!task)
+ break;
+ rpc_task_set_priority(task, RPC_PRIORITY_PRIVILEGED);
+ }
+ spin_unlock(&ses->fc_slot_table.slot_tbl_lock);
+ }
}
-static int nfs41_begin_drain_session(struct nfs_client *clp,
- struct nfs4_session *ses)
+static int nfs4_begin_drain_session(struct nfs_client *clp)
{
+ struct nfs4_session *ses = clp->cl_session;
struct nfs4_slot_table *tbl = &ses->fc_slot_table;
spin_lock(&tbl->slot_tbl_lock);
@@ -162,16 +176,13 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
{
int status;
- status = nfs41_begin_drain_session(clp, clp->cl_session);
- if (status != 0)
- goto out;
+ nfs4_begin_drain_session(clp);
status = nfs4_proc_exchange_id(clp, cred);
if (status != 0)
goto out;
status = nfs4_proc_create_session(clp);
if (status != 0)
goto out;
- nfs41_end_drain_session(clp, clp->cl_session);
nfs41_setup_state_renewal(clp);
nfs_mark_client_ready(clp, NFS_CS_READY);
out:
@@ -755,16 +766,21 @@ struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter)
return new;
}
-void nfs_free_seqid(struct nfs_seqid *seqid)
+void nfs_release_seqid(struct nfs_seqid *seqid)
{
if (!list_empty(&seqid->list)) {
struct rpc_sequence *sequence = seqid->sequence->sequence;
spin_lock(&sequence->lock);
- list_del(&seqid->list);
+ list_del_init(&seqid->list);
spin_unlock(&sequence->lock);
rpc_wake_up(&sequence->wait);
}
+}
+
+void nfs_free_seqid(struct nfs_seqid *seqid)
+{
+ nfs_release_seqid(seqid);
kfree(seqid);
}
@@ -1257,13 +1273,9 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
static int nfs4_reset_session(struct nfs_client *clp)
{
- struct nfs4_session *ses = clp->cl_session;
int status;
- status = nfs41_begin_drain_session(clp, ses);
- if (status != 0)
- return status;
-
+ nfs4_begin_drain_session(clp);
status = nfs4_proc_destroy_session(clp->cl_session);
if (status && status != -NFS4ERR_BADSESSION &&
status != -NFS4ERR_DEADSESSION) {
@@ -1279,19 +1291,17 @@ static int nfs4_reset_session(struct nfs_client *clp)
out:
/*
* Let the state manager reestablish state
- * without waking other tasks yet.
*/
- if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
- /* Wake up the next rpc task */
- nfs41_end_drain_session(clp, ses);
- if (status == 0)
- nfs41_setup_state_renewal(clp);
- }
+ if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
+ status == 0)
+ nfs41_setup_state_renewal(clp);
+
return status;
}
#else /* CONFIG_NFS_V4_1 */
static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
+static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
#endif /* CONFIG_NFS_V4_1 */
/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
@@ -1382,6 +1392,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
goto out_error;
}
+ nfs4_end_drain_session(clp);
if (test_and_clear_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state)) {
nfs_client_return_marked_delegations(clp);
continue;
@@ -1398,6 +1409,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
out_error:
printk(KERN_WARNING "Error: state manager failed on NFSv4 server %s"
" with error %d\n", clp->cl_hostname, -status);
+ nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ce907efc550..d5b112bcf3d 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2648,21 +2648,13 @@ out_freepage:
static int nfs_follow_remote_path(struct vfsmount *root_mnt,
const char *export_path, struct vfsmount *mnt_target)
{
- struct mnt_namespace *ns_private;
struct nameidata nd;
struct super_block *s;
int ret;
- ns_private = create_mnt_ns(root_mnt);
- ret = PTR_ERR(ns_private);
- if (IS_ERR(ns_private))
- goto out_mntput;
-
ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
export_path, LOOKUP_FOLLOW, &nd);
- put_mnt_ns(ns_private);
-
if (ret != 0)
goto out_err;
diff --git a/fs/nfsctl.c b/fs/nfsctl.c
index 8f9a20556f7..d3854d94b7c 100644
--- a/fs/nfsctl.c
+++ b/fs/nfsctl.c
@@ -7,8 +7,6 @@
#include <linux/types.h>
#include <linux/file.h>
#include <linux/fs.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/syscall.h>
#include <linux/cred.h>
#include <linux/sched.h>
diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c
index 36fcabbf518..79717a40dab 100644
--- a/fs/nfsd/auth.c
+++ b/fs/nfsd/auth.c
@@ -1,15 +1,7 @@
-/*
- * linux/fs/nfsd/auth.c
- *
- * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
- */
+/* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de> */
-#include <linux/types.h>
#include <linux/sched.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/svcauth.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/export.h>
+#include "nfsd.h"
#include "auth.h"
int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
new file mode 100644
index 00000000000..d892be61016
--- /dev/null
+++ b/fs/nfsd/cache.h
@@ -0,0 +1,83 @@
+/*
+ * Request reply cache. This was heavily inspired by the
+ * implementation in 4.3BSD/4.4BSD.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef NFSCACHE_H
+#define NFSCACHE_H
+
+#include <linux/sunrpc/svc.h>
+
+/*
+ * Representation of a reply cache entry.
+ */
+struct svc_cacherep {
+ struct hlist_node c_hash;
+ struct list_head c_lru;
+
+ unsigned char c_state, /* unused, inprog, done */
+ c_type, /* status, buffer */
+ c_secure : 1; /* req came from port < 1024 */
+ struct sockaddr_in c_addr;
+ __be32 c_xid;
+ u32 c_prot;
+ u32 c_proc;
+ u32 c_vers;
+ unsigned long c_timestamp;
+ union {
+ struct kvec u_vec;
+ __be32 u_status;
+ } c_u;
+};
+
+#define c_replvec c_u.u_vec
+#define c_replstat c_u.u_status
+
+/* cache entry states */
+enum {
+ RC_UNUSED,
+ RC_INPROG,
+ RC_DONE
+};
+
+/* return values */
+enum {
+ RC_DROPIT,
+ RC_REPLY,
+ RC_DOIT,
+ RC_INTR
+};
+
+/*
+ * Cache types.
+ * We may want to add more types one day, e.g. for diropres and
+ * attrstat replies. Using cache entries with fixed length instead
+ * of buffer pointers may be more efficient.
+ */
+enum {
+ RC_NOCACHE,
+ RC_REPLSTAT,
+ RC_REPLBUFF,
+};
+
+/*
+ * If requests are retransmitted within this interval, they're dropped.
+ */
+#define RC_DELAY (HZ/5)
+
+int nfsd_reply_cache_init(void);
+void nfsd_reply_cache_shutdown(void);
+int nfsd_cache_lookup(struct svc_rqst *, int);
+void nfsd_cache_update(struct svc_rqst *, int, __be32 *);
+
+#ifdef CONFIG_NFSD_V4
+void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp);
+#else /* CONFIG_NFSD_V4 */
+static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
+{
+}
+#endif /* CONFIG_NFSD_V4 */
+
+#endif /* NFSCACHE_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index c1c9e035d4a..c487810a236 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -1,7 +1,5 @@
#define MSNFS /* HACK HACK */
/*
- * linux/fs/nfsd/export.c
- *
* NFS exporting and validation.
*
* We maintain a list of clients, each of which has a list of
@@ -14,29 +12,16 @@
* Copyright (C) 1995, 1996 Olaf Kirch, <okir@monad.swb.de>
*/
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/stat.h>
-#include <linux/in.h>
-#include <linux/seq_file.h>
-#include <linux/syscalls.h>
-#include <linux/rwsem.h>
-#include <linux/dcache.h>
#include <linux/namei.h>
-#include <linux/mount.h>
-#include <linux/hash.h>
#include <linux/module.h>
#include <linux/exportfs.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/nfsfh.h>
#include <linux/nfsd/syscall.h>
-#include <linux/lockd/bind.h>
-#include <linux/sunrpc/msg_prot.h>
-#include <linux/sunrpc/gss_api.h>
#include <net/ipv6.h>
+#include "nfsd.h"
+#include "nfsfh.h"
+
#define NFSDDBG_FACILITY NFSDDBG_EXPORT
typedef struct auth_domain svc_client;
@@ -369,16 +354,25 @@ static struct svc_export *svc_export_update(struct svc_export *new,
struct svc_export *old);
static struct svc_export *svc_export_lookup(struct svc_export *);
-static int check_export(struct inode *inode, int flags, unsigned char *uuid)
+static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
{
- /* We currently export only dirs and regular files.
- * This is what umountd does.
+ /*
+ * We currently export only dirs, regular files, and (for v4
+ * pseudoroot) symlinks.
*/
if (!S_ISDIR(inode->i_mode) &&
+ !S_ISLNK(inode->i_mode) &&
!S_ISREG(inode->i_mode))
return -ENOTDIR;
+ /*
+ * Mountd should never pass down a writeable V4ROOT export, but,
+ * just to make sure:
+ */
+ if (*flags & NFSEXP_V4ROOT)
+ *flags |= NFSEXP_READONLY;
+
/* There are two requirements on a filesystem to be exportable.
* 1: We must be able to identify the filesystem from a number.
* either a device number (so FS_REQUIRES_DEV needed)
@@ -387,7 +381,7 @@ static int check_export(struct inode *inode, int flags, unsigned char *uuid)
* This means that s_export_op must be set.
*/
if (!(inode->i_sb->s_type->fs_flags & FS_REQUIRES_DEV) &&
- !(flags & NFSEXP_FSID) &&
+ !(*flags & NFSEXP_FSID) &&
uuid == NULL) {
dprintk("exp_export: export of non-dev fs without fsid\n");
return -EINVAL;
@@ -602,7 +596,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
goto out4;
}
- err = check_export(exp.ex_path.dentry->d_inode, exp.ex_flags,
+ err = check_export(exp.ex_path.dentry->d_inode, &exp.ex_flags,
exp.ex_uuid);
if (err)
goto out4;
@@ -1041,7 +1035,7 @@ exp_export(struct nfsctl_export *nxp)
goto finish;
}
- err = check_export(path.dentry->d_inode, nxp->ex_flags, NULL);
+ err = check_export(path.dentry->d_inode, &nxp->ex_flags, NULL);
if (err) goto finish;
err = -ENOMEM;
@@ -1320,6 +1314,23 @@ rqst_exp_parent(struct svc_rqst *rqstp, struct path *path)
return exp;
}
+static struct svc_export *find_fsidzero_export(struct svc_rqst *rqstp)
+{
+ struct svc_export *exp;
+ u32 fsidv[2];
+
+ mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL);
+
+ exp = rqst_exp_find(rqstp, FSID_NUM, fsidv);
+ /*
+ * We shouldn't have accepting an nfsv4 request at all if we
+ * don't have a pseudoexport!:
+ */
+ if (IS_ERR(exp) && PTR_ERR(exp) == -ENOENT)
+ exp = ERR_PTR(-ESERVERFAULT);
+ return exp;
+}
+
/*
* Called when we need the filehandle for the root of the pseudofs,
* for a given NFSv4 client. The root is defined to be the
@@ -1330,11 +1341,8 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
{
struct svc_export *exp;
__be32 rv;
- u32 fsidv[2];
- mk_fsid(FSID_NUM, fsidv, 0, 0, 0, NULL);
-
- exp = rqst_exp_find(rqstp, FSID_NUM, fsidv);
+ exp = find_fsidzero_export(rqstp);
if (IS_ERR(exp))
return nfserrno(PTR_ERR(exp));
rv = fh_compose(fhp, exp, exp->ex_path.dentry, NULL);
@@ -1425,6 +1433,7 @@ static struct flags {
{ NFSEXP_CROSSMOUNT, {"crossmnt", ""}},
{ NFSEXP_NOSUBTREECHECK, {"no_subtree_check", ""}},
{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
+ { NFSEXP_V4ROOT, {"v4root", ""}},
#ifdef MSNFS
{ NFSEXP_MSNFS, {"msnfs", ""}},
#endif
diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c
index b2786a5f9af..0c6d8167013 100644
--- a/fs/nfsd/lockd.c
+++ b/fs/nfsd/lockd.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/lockd.c
- *
* This file contains all the stubs needed when communicating with lockd.
* This level of indirection is necessary so we can run nfsd+lockd without
* requiring the nfs client to be compiled in/loaded, and vice versa.
@@ -8,14 +6,10 @@
* Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/types.h>
-#include <linux/fs.h>
#include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/lockd/bind.h>
+#include "nfsd.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_LOCKD
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index 4e3219e8411..f20589d2ae2 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -1,19 +1,15 @@
/*
- * linux/fs/nfsd/nfs2acl.c
- *
* Process version 2 NFSACL requests.
*
* Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
*/
-#include <linux/sunrpc/svc.h>
-#include <linux/nfs.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/posix_acl.h>
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
#include <linux/nfsacl.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
#define RETURN_STATUS(st) { resp->status = (st); return (st); }
@@ -217,6 +213,16 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
* XDR encode functions
*/
+/*
+ * There must be an encoding function for void results so svc_process
+ * will work properly.
+ */
+int
+nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+{
+ return xdr_ressize_check(rqstp, p);
+}
+
/* GETACL */
static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
struct nfsd3_getaclres *resp)
@@ -308,7 +314,6 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
}
#define nfsaclsvc_decode_voidargs NULL
-#define nfsaclsvc_encode_voidres NULL
#define nfsaclsvc_release_void NULL
#define nfsd3_fhandleargs nfsd_fhandle
#define nfsd3_attrstatres nfsd_attrstat
@@ -346,5 +351,5 @@ struct svc_version nfsd_acl_version2 = {
.vs_proc = nfsd_acl_procedures2,
.vs_dispatch = nfsd_dispatch,
.vs_xdrsize = NFS3_SVC_XDRSIZE,
- .vs_hidden = 1,
+ .vs_hidden = 0,
};
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 9981dbb377a..e0c4846bad9 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -1,18 +1,15 @@
/*
- * linux/fs/nfsd/nfs3acl.c
- *
* Process version 3 NFSACL requests.
*
* Copyright (C) 2002-2003 Andreas Gruenbacher <agruen@suse.de>
*/
-#include <linux/sunrpc/svc.h>
-#include <linux/nfs3.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/posix_acl.h>
+#include "nfsd.h"
+/* FIXME: nfsacl.h is a broken header */
#include <linux/nfsacl.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
#define RETURN_STATUS(st) { resp->status = (st); return (st); }
@@ -264,6 +261,6 @@ struct svc_version nfsd_acl_version3 = {
.vs_proc = nfsd_acl_procedures3,
.vs_dispatch = nfsd_dispatch,
.vs_xdrsize = NFS3_SVC_XDRSIZE,
- .vs_hidden = 1,
+ .vs_hidden = 0,
};
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index a713c418a92..3d68f45a37b 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -1,30 +1,16 @@
/*
- * linux/fs/nfsd/nfs3proc.c
- *
* Process version 3 NFS requests.
*
* Copyright (C) 1996, 1997, 1998 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/ext2_fs.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/major.h>
#include <linux/magic.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr3.h>
-#include <linux/nfs3.h>
+#include "cache.h"
+#include "xdr3.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index d0a2ce1b432..2a533a0af2a 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/nfs3xdr.c
- *
* XDR support for nfsd/protocol version 3.
*
* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
@@ -8,19 +6,8 @@
* 2003-08-09 Jamie Lokier: Use htonl() for nanoseconds, not htons()!
*/
-#include <linux/types.h>
-#include <linux/time.h>
-#include <linux/nfs3.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/dcache.h>
#include <linux/namei.h>
-#include <linux/mm.h>
-#include <linux/vfs.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/xdr3.h>
+#include "xdr3.h"
#include "auth.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 725d02f210e..88150685df3 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -1,6 +1,4 @@
/*
- * fs/nfs4acl/acl.c
- *
* Common NFSv4 ACL handling code.
*
* Copyright (c) 2002, 2003 The Regents of the University of Michigan.
@@ -36,15 +34,7 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
-#include <linux/string.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/types.h>
-#include <linux/fs.h>
-#include <linux/module.h>
#include <linux/nfs_fs.h>
-#include <linux/posix_acl.h>
-#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
@@ -389,7 +379,7 @@ sort_pacl(struct posix_acl *pacl)
sort_pacl_range(pacl, 1, i-1);
BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
- j = i++;
+ j = ++i;
while (pacl->a_entries[j].e_tag == ACL_GROUP)
j++;
sort_pacl_range(pacl, i, j-1);
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 24e8d78f8dd..c6eed2a3b09 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/nfs4callback.c
- *
* Copyright (c) 2001 The Regents of the University of Michigan.
* All rights reserved.
*
@@ -33,22 +31,9 @@
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
-#include <linux/module.h>
-#include <linux/list.h>
-#include <linux/inet.h>
-#include <linux/errno.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/kthread.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svcsock.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/state.h>
-#include <linux/sunrpc/sched.h>
-#include <linux/nfs4.h>
-#include <linux/sunrpc/xprtsock.h>
+#include "nfsd.h"
+#include "state.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index ba2c199592f..6e2983b27f3 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -1,6 +1,4 @@
/*
- * fs/nfsd/nfs4idmap.c
- *
* Mapping of UID/GIDs to name and vice versa.
*
* Copyright (c) 2002, 2003 The Regents of the University of
@@ -35,22 +33,9 @@
*/
#include <linux/module.h>
-#include <linux/init.h>
-
-#include <linux/mm.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfs.h>
-#include <linux/nfs4.h>
-#include <linux/nfs_fs.h>
-#include <linux/nfs_page.h>
-#include <linux/sunrpc/cache.h>
#include <linux/nfsd_idmap.h>
-#include <linux/list.h>
-#include <linux/time.h>
#include <linux/seq_file.h>
-#include <linux/sunrpc/svcauth.h>
+#include <linux/sched.h>
/*
* Cache entry
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index bebc0c2e1b0..37514c46984 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1,6 +1,4 @@
/*
- * fs/nfsd/nfs4proc.c
- *
* Server-side procedures for NFSv4.
*
* Copyright (c) 2002 The Regents of the University of Michigan.
@@ -34,20 +32,11 @@
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
-
-#include <linux/param.h>
-#include <linux/major.h>
-#include <linux/slab.h>
#include <linux/file.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
-#include <linux/nfs4_acl.h>
-#include <linux/sunrpc/gss_api.h>
+#include "cache.h"
+#include "xdr4.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -170,7 +159,7 @@ do_open_permission(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfs
accmode |= NFSD_MAY_READ;
if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
accmode |= (NFSD_MAY_WRITE | NFSD_MAY_TRUNC);
- if (open->op_share_deny & NFS4_SHARE_DENY_WRITE)
+ if (open->op_share_deny & NFS4_SHARE_DENY_READ)
accmode |= NFSD_MAY_WRITE;
status = fh_verify(rqstp, current_fh, S_IFREG, accmode);
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index b5348405046..5a754f7b71e 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -1,6 +1,4 @@
/*
-* linux/fs/nfsd/nfs4recover.c
-*
* Copyright (c) 2004 The Regents of the University of Michigan.
* All rights reserved.
*
@@ -33,20 +31,14 @@
*
*/
-#include <linux/err.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
-#include <linux/param.h>
#include <linux/file.h>
#include <linux/namei.h>
-#include <asm/uaccess.h>
-#include <linux/scatterlist.h>
#include <linux/crypto.h>
#include <linux/sched.h>
-#include <linux/mount.h>
+
+#include "nfsd.h"
+#include "state.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2153f9bdbeb..f19ed866c95 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1,6 +1,4 @@
/*
-* linux/fs/nfsd/nfs4state.c
-*
* Copyright (c) 2001 The Regents of the University of Michigan.
* All rights reserved.
*
@@ -34,28 +32,14 @@
*
*/
-#include <linux/param.h>
-#include <linux/major.h>
-#include <linux/slab.h>
-
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
#include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/workqueue.h>
#include <linux/smp_lock.h>
-#include <linux/kthread.h>
-#include <linux/nfs4.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
#include <linux/namei.h>
#include <linux/swap.h>
-#include <linux/mutex.h>
-#include <linux/lockd/bind.h>
-#include <linux/module.h>
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/clnt.h>
+#include "xdr4.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
@@ -477,13 +461,14 @@ static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
/*
* fchan holds the client values on input, and the server values on output
+ * sv_max_mesg is the maximum payload plus one page for overhead.
*/
static int init_forechannel_attrs(struct svc_rqst *rqstp,
struct nfsd4_channel_attrs *session_fchan,
struct nfsd4_channel_attrs *fchan)
{
int status = 0;
- __u32 maxcount = svc_max_payload(rqstp);
+ __u32 maxcount = nfsd_serv->sv_max_mesg;
/* headerpadsz set to zero in encode routine */
@@ -523,6 +508,15 @@ free_session_slots(struct nfsd4_session *ses)
kfree(ses->se_slots[i]);
}
+/*
+ * We don't actually need to cache the rpc and session headers, so we
+ * can allocate a little less for each slot:
+ */
+static inline int slot_bytes(struct nfsd4_channel_attrs *ca)
+{
+ return ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+}
+
static int
alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
struct nfsd4_create_session *cses)
@@ -554,7 +548,7 @@ alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
memcpy(new, &tmp, sizeof(*new));
/* allocate each struct nfsd4_slot and data cache in one piece */
- cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
+ cachesize = slot_bytes(&new->se_fchannel);
for (i = 0; i < new->se_fchannel.maxreqs; i++) {
sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
if (!sp)
@@ -628,10 +622,12 @@ void
free_session(struct kref *kref)
{
struct nfsd4_session *ses;
+ int mem;
ses = container_of(kref, struct nfsd4_session, se_ref);
spin_lock(&nfsd_drc_lock);
- nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
+ mem = ses->se_fchannel.maxreqs * slot_bytes(&ses->se_fchannel);
+ nfsd_drc_mem_used -= mem;
spin_unlock(&nfsd_drc_lock);
free_session_slots(ses);
kfree(ses);
@@ -2404,11 +2400,8 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid));
- dprintk("NFSD: delegation stateid=(%08x/%08x/%08x/%08x)\n\n",
- dp->dl_stateid.si_boot,
- dp->dl_stateid.si_stateownerid,
- dp->dl_stateid.si_fileid,
- dp->dl_stateid.si_generation);
+ dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
+ STATEID_VAL(&dp->dl_stateid));
out:
if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS
&& flag == NFS4_OPEN_DELEGATE_NONE
@@ -2498,9 +2491,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
status = nfs_ok;
- dprintk("nfs4_process_open2: stateid=(%08x/%08x/%08x/%08x)\n",
- stp->st_stateid.si_boot, stp->st_stateid.si_stateownerid,
- stp->st_stateid.si_fileid, stp->st_stateid.si_generation);
+ dprintk("%s: stateid=" STATEID_FMT "\n", __func__,
+ STATEID_VAL(&stp->st_stateid));
out:
if (fp)
put_nfs4_file(fp);
@@ -2666,9 +2658,8 @@ STALE_STATEID(stateid_t *stateid)
{
if (time_after((unsigned long)boot_time,
(unsigned long)stateid->si_boot)) {
- dprintk("NFSD: stale stateid (%08x/%08x/%08x/%08x)!\n",
- stateid->si_boot, stateid->si_stateownerid,
- stateid->si_fileid, stateid->si_generation);
+ dprintk("NFSD: stale stateid " STATEID_FMT "!\n",
+ STATEID_VAL(stateid));
return 1;
}
return 0;
@@ -2680,9 +2671,8 @@ EXPIRED_STATEID(stateid_t *stateid)
if (time_before((unsigned long)boot_time,
((unsigned long)stateid->si_boot)) &&
time_before((unsigned long)(stateid->si_boot + lease_time), get_seconds())) {
- dprintk("NFSD: expired stateid (%08x/%08x/%08x/%08x)!\n",
- stateid->si_boot, stateid->si_stateownerid,
- stateid->si_fileid, stateid->si_generation);
+ dprintk("NFSD: expired stateid " STATEID_FMT "!\n",
+ STATEID_VAL(stateid));
return 1;
}
return 0;
@@ -2696,9 +2686,8 @@ stateid_error_map(stateid_t *stateid)
if (EXPIRED_STATEID(stateid))
return nfserr_expired;
- dprintk("NFSD: bad stateid (%08x/%08x/%08x/%08x)!\n",
- stateid->si_boot, stateid->si_stateownerid,
- stateid->si_fileid, stateid->si_generation);
+ dprintk("NFSD: bad stateid " STATEID_FMT "!\n",
+ STATEID_VAL(stateid));
return nfserr_bad_stateid;
}
@@ -2884,10 +2873,8 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
struct svc_fh *current_fh = &cstate->current_fh;
__be32 status;
- dprintk("NFSD: preprocess_seqid_op: seqid=%d "
- "stateid = (%08x/%08x/%08x/%08x)\n", seqid,
- stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid,
- stateid->si_generation);
+ dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__,
+ seqid, STATEID_VAL(stateid));
*stpp = NULL;
*sopp = NULL;
@@ -3019,12 +3006,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
sop->so_confirmed = 1;
update_stateid(&stp->st_stateid);
memcpy(&oc->oc_resp_stateid, &stp->st_stateid, sizeof(stateid_t));
- dprintk("NFSD: nfsd4_open_confirm: success, seqid=%d "
- "stateid=(%08x/%08x/%08x/%08x)\n", oc->oc_seqid,
- stp->st_stateid.si_boot,
- stp->st_stateid.si_stateownerid,
- stp->st_stateid.si_fileid,
- stp->st_stateid.si_generation);
+ dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n",
+ __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stateid));
nfsd4_create_clid_dir(sop->so_client);
out:
@@ -3283,9 +3266,8 @@ find_delegation_stateid(struct inode *ino, stateid_t *stid)
struct nfs4_file *fp;
struct nfs4_delegation *dl;
- dprintk("NFSD:find_delegation_stateid stateid=(%08x/%08x/%08x/%08x)\n",
- stid->si_boot, stid->si_stateownerid,
- stid->si_fileid, stid->si_generation);
+ dprintk("NFSD: %s: stateid=" STATEID_FMT "\n", __func__,
+ STATEID_VAL(stid));
fp = find_file(ino);
if (!fp)
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0fbd50cee1f..a8587e90fd5 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -40,24 +40,16 @@
* at the end of nfs4svc_decode_compoundargs.
*/
-#include <linux/param.h>
-#include <linux/smp.h>
-#include <linux/fs.h>
#include <linux/namei.h>
-#include <linux/vfs.h>
+#include <linux/statfs.h>
#include <linux/utsname.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/state.h>
-#include <linux/nfsd/xdr4.h>
#include <linux/nfsd_idmap.h>
-#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
-#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/svcauth_gss.h>
+#include "xdr4.h"
+#include "vfs.h"
+
#define NFSDDBG_FACILITY NFSDDBG_XDR
/*
@@ -2204,11 +2196,14 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
* we will not follow the cross mount and will fill the attribtutes
* directly from the mountpoint dentry.
*/
- if (d_mountpoint(dentry) && !attributes_need_mount(cd->rd_bmval))
- ignore_crossmnt = 1;
- else if (d_mountpoint(dentry)) {
+ if (nfsd_mountpoint(dentry, exp)) {
int err;
+ if (!(exp->ex_flags & NFSEXP_V4ROOT)
+ && !attributes_need_mount(cd->rd_bmval)) {
+ ignore_crossmnt = 1;
+ goto out_encode;
+ }
/*
* Why the heck aren't we just using nfsd_lookup??
* Different "."/".." handling? Something else?
@@ -2224,6 +2219,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
goto out_put;
}
+out_encode:
nfserr = nfsd4_encode_fattr(NULL, exp, dentry, p, buflen, cd->rd_bmval,
cd->rd_rqstp, ignore_crossmnt);
out_put:
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 4638635c5d8..da08560c481 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/nfscache.c
- *
* Request reply cache. This is currently a global cache, but this may
* change in the future and be a per-client cache.
*
@@ -10,16 +8,8 @@
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <linux/spinlock.h>
-#include <linux/list.h>
-
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
+#include "nfsd.h"
+#include "cache.h"
/* Size of reply cache. Common values are:
* 4.3BSD: 128
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 5c01fc148ce..2604c3e70ea 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1,46 +1,20 @@
/*
- * linux/fs/nfsd/nfsctl.c
- *
* Syscall interface to knfsd.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/module.h>
-
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
#include <linux/namei.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
-#include <linux/syscalls.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
-#include <linux/inet.h>
-#include <linux/string.h>
#include <linux/ctype.h>
-#include <linux/nfs.h>
#include <linux/nfsd_idmap.h>
-#include <linux/lockd/bind.h>
-#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/svcsock.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
#include <linux/nfsd/syscall.h>
#include <linux/lockd/lockd.h>
#include <linux/sunrpc/clnt.h>
-#include <asm/uaccess.h>
-#include <net/ipv6.h>
+#include "nfsd.h"
+#include "cache.h"
/*
* We have a single directory with 9 nodes in it.
@@ -55,6 +29,7 @@ enum {
NFSD_Getfd,
NFSD_Getfs,
NFSD_List,
+ NFSD_Export_features,
NFSD_Fh,
NFSD_FO_UnlockIP,
NFSD_FO_UnlockFS,
@@ -173,6 +148,24 @@ static const struct file_operations exports_operations = {
.owner = THIS_MODULE,
};
+static int export_features_show(struct seq_file *m, void *v)
+{
+ seq_printf(m, "0x%x 0x%x\n", NFSEXP_ALLFLAGS, NFSEXP_SECINFO_FLAGS);
+ return 0;
+}
+
+static int export_features_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, export_features_show, NULL);
+}
+
+static struct file_operations export_features_operations = {
+ .open = export_features_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
extern int nfsd_pool_stats_open(struct inode *inode, struct file *file);
extern int nfsd_pool_stats_release(struct inode *inode, struct file *file);
@@ -1330,6 +1323,8 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
[NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+ [NFSD_Export_features] = {"export_features",
+ &export_features_operations, S_IRUGO},
[NFSD_FO_UnlockIP] = {"unlock_ip",
&transaction_ops, S_IWUSR|S_IRUSR},
[NFSD_FO_UnlockFS] = {"unlock_filesystem",
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
new file mode 100644
index 00000000000..e942a1aaac9
--- /dev/null
+++ b/fs/nfsd/nfsd.h
@@ -0,0 +1,338 @@
+/*
+ * Hodge-podge collection of knfsd-related stuff.
+ * I will sort this out later.
+ *
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_NFSD_H
+#define LINUX_NFSD_NFSD_H
+
+#include <linux/types.h>
+#include <linux/mount.h>
+
+#include <linux/nfsd/debug.h>
+#include <linux/nfsd/export.h>
+#include <linux/nfsd/stats.h>
+/*
+ * nfsd version
+ */
+#define NFSD_SUPPORTED_MINOR_VERSION 1
+
+struct readdir_cd {
+ __be32 err; /* 0, nfserr, or nfserr_eof */
+};
+
+
+extern struct svc_program nfsd_program;
+extern struct svc_version nfsd_version2, nfsd_version3,
+ nfsd_version4;
+extern u32 nfsd_supported_minorversion;
+extern struct mutex nfsd_mutex;
+extern struct svc_serv *nfsd_serv;
+extern spinlock_t nfsd_drc_lock;
+extern unsigned int nfsd_drc_max_mem;
+extern unsigned int nfsd_drc_mem_used;
+
+extern const struct seq_operations nfs_exports_op;
+
+/*
+ * Function prototypes.
+ */
+int nfsd_svc(unsigned short port, int nrservs);
+int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp);
+
+int nfsd_nrthreads(void);
+int nfsd_nrpools(void);
+int nfsd_get_nrthreads(int n, int *);
+int nfsd_set_nrthreads(int n, int *);
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+#ifdef CONFIG_NFSD_V2_ACL
+extern struct svc_version nfsd_acl_version2;
+#else
+#define nfsd_acl_version2 NULL
+#endif
+#ifdef CONFIG_NFSD_V3_ACL
+extern struct svc_version nfsd_acl_version3;
+#else
+#define nfsd_acl_version3 NULL
+#endif
+#endif
+
+enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
+int nfsd_vers(int vers, enum vers_op change);
+int nfsd_minorversion(u32 minorversion, enum vers_op change);
+void nfsd_reset_versions(void);
+int nfsd_create_serv(void);
+
+extern int nfsd_max_blksize;
+
+static inline int nfsd_v4client(struct svc_rqst *rq)
+{
+ return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
+}
+
+/*
+ * NFSv4 State
+ */
+#ifdef CONFIG_NFSD_V4
+extern unsigned int max_delegations;
+int nfs4_state_init(void);
+void nfsd4_free_slabs(void);
+int nfs4_state_start(void);
+void nfs4_state_shutdown(void);
+time_t nfs4_lease_time(void);
+void nfs4_reset_lease(time_t leasetime);
+int nfs4_reset_recoverydir(char *recdir);
+#else
+static inline int nfs4_state_init(void) { return 0; }
+static inline void nfsd4_free_slabs(void) { }
+static inline int nfs4_state_start(void) { return 0; }
+static inline void nfs4_state_shutdown(void) { }
+static inline time_t nfs4_lease_time(void) { return 0; }
+static inline void nfs4_reset_lease(time_t leasetime) { }
+static inline int nfs4_reset_recoverydir(char *recdir) { return 0; }
+#endif
+
+/*
+ * lockd binding
+ */
+void nfsd_lockd_init(void);
+void nfsd_lockd_shutdown(void);
+
+
+/*
+ * These macros provide pre-xdr'ed values for faster operation.
+ */
+#define nfs_ok cpu_to_be32(NFS_OK)
+#define nfserr_perm cpu_to_be32(NFSERR_PERM)
+#define nfserr_noent cpu_to_be32(NFSERR_NOENT)
+#define nfserr_io cpu_to_be32(NFSERR_IO)
+#define nfserr_nxio cpu_to_be32(NFSERR_NXIO)
+#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN)
+#define nfserr_acces cpu_to_be32(NFSERR_ACCES)
+#define nfserr_exist cpu_to_be32(NFSERR_EXIST)
+#define nfserr_xdev cpu_to_be32(NFSERR_XDEV)
+#define nfserr_nodev cpu_to_be32(NFSERR_NODEV)
+#define nfserr_notdir cpu_to_be32(NFSERR_NOTDIR)
+#define nfserr_isdir cpu_to_be32(NFSERR_ISDIR)
+#define nfserr_inval cpu_to_be32(NFSERR_INVAL)
+#define nfserr_fbig cpu_to_be32(NFSERR_FBIG)
+#define nfserr_nospc cpu_to_be32(NFSERR_NOSPC)
+#define nfserr_rofs cpu_to_be32(NFSERR_ROFS)
+#define nfserr_mlink cpu_to_be32(NFSERR_MLINK)
+#define nfserr_opnotsupp cpu_to_be32(NFSERR_OPNOTSUPP)
+#define nfserr_nametoolong cpu_to_be32(NFSERR_NAMETOOLONG)
+#define nfserr_notempty cpu_to_be32(NFSERR_NOTEMPTY)
+#define nfserr_dquot cpu_to_be32(NFSERR_DQUOT)
+#define nfserr_stale cpu_to_be32(NFSERR_STALE)
+#define nfserr_remote cpu_to_be32(NFSERR_REMOTE)
+#define nfserr_wflush cpu_to_be32(NFSERR_WFLUSH)
+#define nfserr_badhandle cpu_to_be32(NFSERR_BADHANDLE)
+#define nfserr_notsync cpu_to_be32(NFSERR_NOT_SYNC)
+#define nfserr_badcookie cpu_to_be32(NFSERR_BAD_COOKIE)
+#define nfserr_notsupp cpu_to_be32(NFSERR_NOTSUPP)
+#define nfserr_toosmall cpu_to_be32(NFSERR_TOOSMALL)
+#define nfserr_serverfault cpu_to_be32(NFSERR_SERVERFAULT)
+#define nfserr_badtype cpu_to_be32(NFSERR_BADTYPE)
+#define nfserr_jukebox cpu_to_be32(NFSERR_JUKEBOX)
+#define nfserr_denied cpu_to_be32(NFSERR_DENIED)
+#define nfserr_deadlock cpu_to_be32(NFSERR_DEADLOCK)
+#define nfserr_expired cpu_to_be32(NFSERR_EXPIRED)
+#define nfserr_bad_cookie cpu_to_be32(NFSERR_BAD_COOKIE)
+#define nfserr_same cpu_to_be32(NFSERR_SAME)
+#define nfserr_clid_inuse cpu_to_be32(NFSERR_CLID_INUSE)
+#define nfserr_stale_clientid cpu_to_be32(NFSERR_STALE_CLIENTID)
+#define nfserr_resource cpu_to_be32(NFSERR_RESOURCE)
+#define nfserr_moved cpu_to_be32(NFSERR_MOVED)
+#define nfserr_nofilehandle cpu_to_be32(NFSERR_NOFILEHANDLE)
+#define nfserr_minor_vers_mismatch cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH)
+#define nfserr_share_denied cpu_to_be32(NFSERR_SHARE_DENIED)
+#define nfserr_stale_stateid cpu_to_be32(NFSERR_STALE_STATEID)
+#define nfserr_old_stateid cpu_to_be32(NFSERR_OLD_STATEID)
+#define nfserr_bad_stateid cpu_to_be32(NFSERR_BAD_STATEID)
+#define nfserr_bad_seqid cpu_to_be32(NFSERR_BAD_SEQID)
+#define nfserr_symlink cpu_to_be32(NFSERR_SYMLINK)
+#define nfserr_not_same cpu_to_be32(NFSERR_NOT_SAME)
+#define nfserr_restorefh cpu_to_be32(NFSERR_RESTOREFH)
+#define nfserr_attrnotsupp cpu_to_be32(NFSERR_ATTRNOTSUPP)
+#define nfserr_bad_xdr cpu_to_be32(NFSERR_BAD_XDR)
+#define nfserr_openmode cpu_to_be32(NFSERR_OPENMODE)
+#define nfserr_locks_held cpu_to_be32(NFSERR_LOCKS_HELD)
+#define nfserr_op_illegal cpu_to_be32(NFSERR_OP_ILLEGAL)
+#define nfserr_grace cpu_to_be32(NFSERR_GRACE)
+#define nfserr_no_grace cpu_to_be32(NFSERR_NO_GRACE)
+#define nfserr_reclaim_bad cpu_to_be32(NFSERR_RECLAIM_BAD)
+#define nfserr_badname cpu_to_be32(NFSERR_BADNAME)
+#define nfserr_cb_path_down cpu_to_be32(NFSERR_CB_PATH_DOWN)
+#define nfserr_locked cpu_to_be32(NFSERR_LOCKED)
+#define nfserr_wrongsec cpu_to_be32(NFSERR_WRONGSEC)
+#define nfserr_badiomode cpu_to_be32(NFS4ERR_BADIOMODE)
+#define nfserr_badlayout cpu_to_be32(NFS4ERR_BADLAYOUT)
+#define nfserr_bad_session_digest cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST)
+#define nfserr_badsession cpu_to_be32(NFS4ERR_BADSESSION)
+#define nfserr_badslot cpu_to_be32(NFS4ERR_BADSLOT)
+#define nfserr_complete_already cpu_to_be32(NFS4ERR_COMPLETE_ALREADY)
+#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+#define nfserr_deleg_already_wanted cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED)
+#define nfserr_back_chan_busy cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY)
+#define nfserr_layouttrylater cpu_to_be32(NFS4ERR_LAYOUTTRYLATER)
+#define nfserr_layoutunavailable cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE)
+#define nfserr_nomatching_layout cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT)
+#define nfserr_recallconflict cpu_to_be32(NFS4ERR_RECALLCONFLICT)
+#define nfserr_unknown_layouttype cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE)
+#define nfserr_seq_misordered cpu_to_be32(NFS4ERR_SEQ_MISORDERED)
+#define nfserr_sequence_pos cpu_to_be32(NFS4ERR_SEQUENCE_POS)
+#define nfserr_req_too_big cpu_to_be32(NFS4ERR_REQ_TOO_BIG)
+#define nfserr_rep_too_big cpu_to_be32(NFS4ERR_REP_TOO_BIG)
+#define nfserr_rep_too_big_to_cache cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE)
+#define nfserr_retry_uncached_rep cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP)
+#define nfserr_unsafe_compound cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND)
+#define nfserr_too_many_ops cpu_to_be32(NFS4ERR_TOO_MANY_OPS)
+#define nfserr_op_not_in_session cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION)
+#define nfserr_hash_alg_unsupp cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP)
+#define nfserr_clientid_busy cpu_to_be32(NFS4ERR_CLIENTID_BUSY)
+#define nfserr_pnfs_io_hole cpu_to_be32(NFS4ERR_PNFS_IO_HOLE)
+#define nfserr_seq_false_retry cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY)
+#define nfserr_bad_high_slot cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT)
+#define nfserr_deadsession cpu_to_be32(NFS4ERR_DEADSESSION)
+#define nfserr_encr_alg_unsupp cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP)
+#define nfserr_pnfs_no_layout cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT)
+#define nfserr_not_only_op cpu_to_be32(NFS4ERR_NOT_ONLY_OP)
+#define nfserr_wrong_cred cpu_to_be32(NFS4ERR_WRONG_CRED)
+#define nfserr_wrong_type cpu_to_be32(NFS4ERR_WRONG_TYPE)
+#define nfserr_dirdeleg_unavail cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL)
+#define nfserr_reject_deleg cpu_to_be32(NFS4ERR_REJECT_DELEG)
+#define nfserr_returnconflict cpu_to_be32(NFS4ERR_RETURNCONFLICT)
+#define nfserr_deleg_revoked cpu_to_be32(NFS4ERR_DELEG_REVOKED)
+
+/* error codes for internal use */
+/* if a request fails due to kmalloc failure, it gets dropped.
+ * Client should resend eventually
+ */
+#define nfserr_dropit cpu_to_be32(30000)
+/* end-of-file indicator in readdir */
+#define nfserr_eof cpu_to_be32(30001)
+/* replay detected */
+#define nfserr_replay_me cpu_to_be32(11001)
+/* nfs41 replay detected */
+#define nfserr_replay_cache cpu_to_be32(11002)
+
+/* Check for dir entries '.' and '..' */
+#define isdotent(n, l) (l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
+
+/*
+ * Time of server startup
+ */
+extern struct timeval nfssvc_boot;
+
+#ifdef CONFIG_NFSD_V4
+
+/* before processing a COMPOUND operation, we have to check that there
+ * is enough space in the buffer for XDR encode to succeed. otherwise,
+ * we might process an operation with side effects, and be unable to
+ * tell the client that the operation succeeded.
+ *
+ * COMPOUND_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an "ordinary" _successful_ operation. (GETATTR,
+ * READ, READDIR, and READLINK have their own buffer checks.) if we
+ * fall below this level, we fail the next operation with NFS4ERR_RESOURCE.
+ *
+ * COMPOUND_ERR_SLACK_SPACE - this is the minimum bytes of buffer space
+ * needed to encode an operation which has failed with NFS4ERR_RESOURCE.
+ * care is taken to ensure that we never fall below this level for any
+ * reason.
+ */
+#define COMPOUND_SLACK_SPACE 140 /* OP_GETFH */
+#define COMPOUND_ERR_SLACK_SPACE 12 /* OP_SETATTR */
+
+#define NFSD_LEASE_TIME (nfs4_lease_time())
+#define NFSD_LAUNDROMAT_MINTIMEOUT 10 /* seconds */
+
+/*
+ * The following attributes are currently not supported by the NFSv4 server:
+ * ARCHIVE (deprecated anyway)
+ * HIDDEN (unlikely to be supported any time soon)
+ * MIMETYPE (unlikely to be supported any time soon)
+ * QUOTA_* (will be supported in a forthcoming patch)
+ * SYSTEM (unlikely to be supported any time soon)
+ * TIME_BACKUP (unlikely to be supported any time soon)
+ * TIME_CREATE (unlikely to be supported any time soon)
+ */
+#define NFSD4_SUPPORTED_ATTRS_WORD0 \
+(FATTR4_WORD0_SUPPORTED_ATTRS | FATTR4_WORD0_TYPE | FATTR4_WORD0_FH_EXPIRE_TYPE \
+ | FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE | FATTR4_WORD0_LINK_SUPPORT \
+ | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR | FATTR4_WORD0_FSID \
+ | FATTR4_WORD0_UNIQUE_HANDLES | FATTR4_WORD0_LEASE_TIME | FATTR4_WORD0_RDATTR_ERROR \
+ | FATTR4_WORD0_ACLSUPPORT | FATTR4_WORD0_CANSETTIME | FATTR4_WORD0_CASE_INSENSITIVE \
+ | FATTR4_WORD0_CASE_PRESERVING | FATTR4_WORD0_CHOWN_RESTRICTED \
+ | FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FILEID | FATTR4_WORD0_FILES_AVAIL \
+ | FATTR4_WORD0_FILES_FREE | FATTR4_WORD0_FILES_TOTAL | FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_HOMOGENEOUS \
+ | FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXLINK | FATTR4_WORD0_MAXNAME \
+ | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_ACL)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD1 \
+(FATTR4_WORD1_MODE | FATTR4_WORD1_NO_TRUNC | FATTR4_WORD1_NUMLINKS \
+ | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP | FATTR4_WORD1_RAWDEV \
+ | FATTR4_WORD1_SPACE_AVAIL | FATTR4_WORD1_SPACE_FREE | FATTR4_WORD1_SPACE_TOTAL \
+ | FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS | FATTR4_WORD1_TIME_ACCESS_SET \
+ | FATTR4_WORD1_TIME_DELTA | FATTR4_WORD1_TIME_METADATA \
+ | FATTR4_WORD1_TIME_MODIFY | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID)
+
+#define NFSD4_SUPPORTED_ATTRS_WORD2 0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
+ NFSD4_SUPPORTED_ATTRS_WORD0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
+ NFSD4_SUPPORTED_ATTRS_WORD1
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
+ (NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+
+static inline u32 nfsd_suppattrs0(u32 minorversion)
+{
+ return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
+ : NFSD4_SUPPORTED_ATTRS_WORD0;
+}
+
+static inline u32 nfsd_suppattrs1(u32 minorversion)
+{
+ return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1
+ : NFSD4_SUPPORTED_ATTRS_WORD1;
+}
+
+static inline u32 nfsd_suppattrs2(u32 minorversion)
+{
+ return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2
+ : NFSD4_SUPPORTED_ATTRS_WORD2;
+}
+
+/* These will return ERR_INVAL if specified in GETATTR or READDIR. */
+#define NFSD_WRITEONLY_ATTRS_WORD1 \
+(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
+
+/* These are the only attrs allowed in CREATE/OPEN/SETATTR. */
+#define NFSD_WRITEABLE_ATTRS_WORD0 \
+(FATTR4_WORD0_SIZE | FATTR4_WORD0_ACL )
+#define NFSD_WRITEABLE_ATTRS_WORD1 \
+(FATTR4_WORD1_MODE | FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP \
+ | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
+#define NFSD_WRITEABLE_ATTRS_WORD2 0
+
+#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
+ NFSD_WRITEABLE_ATTRS_WORD0
+/*
+ * we currently store the exclusive create verifier in the v_{a,m}time
+ * attributes so the client can't set these at create time using EXCLUSIVE4_1
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \
+ (NFSD_WRITEABLE_ATTRS_WORD1 & \
+ ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET))
+#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \
+ NFSD_WRITEABLE_ATTRS_WORD2
+
+#endif /* CONFIG_NFSD_V4 */
+
+#endif /* LINUX_NFSD_NFSD_H */
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index 01965b2f3a7..1c12177b908 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/nfsfh.c
- *
* NFS server file handle treatment.
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
@@ -9,19 +7,11 @@
* ... and again Southern-Winter 2001 to support export_operations
*/
-#include <linux/slab.h>
-#include <linux/fs.h>
-#include <linux/unistd.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/dcache.h>
#include <linux/exportfs.h>
-#include <linux/mount.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/nfsd/nfsd.h>
+#include "nfsd.h"
+#include "vfs.h"
#include "auth.h"
#define NFSDDBG_FACILITY NFSDDBG_FH
@@ -96,8 +86,10 @@ nfsd_mode_check(struct svc_rqst *rqstp, umode_t mode, int type)
static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
struct svc_export *exp)
{
+ int flags = nfsexp_flags(rqstp, exp);
+
/* Check if the request originated from a secure port. */
- if (!rqstp->rq_secure && EX_SECURE(exp)) {
+ if (!rqstp->rq_secure && (flags & NFSEXP_INSECURE_PORT)) {
RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
dprintk(KERN_WARNING
"nfsd: request from insecure port %s!\n",
@@ -109,6 +101,36 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
return nfserrno(nfsd_setuser(rqstp, exp));
}
+static inline __be32 check_pseudo_root(struct svc_rqst *rqstp,
+ struct dentry *dentry, struct svc_export *exp)
+{
+ if (!(exp->ex_flags & NFSEXP_V4ROOT))
+ return nfs_ok;
+ /*
+ * v2/v3 clients have no need for the V4ROOT export--they use
+ * the mount protocl instead; also, further V4ROOT checks may be
+ * in v4-specific code, in which case v2/v3 clients could bypass
+ * them.
+ */
+ if (!nfsd_v4client(rqstp))
+ return nfserr_stale;
+ /*
+ * We're exposing only the directories and symlinks that have to be
+ * traversed on the way to real exports:
+ */
+ if (unlikely(!S_ISDIR(dentry->d_inode->i_mode) &&
+ !S_ISLNK(dentry->d_inode->i_mode)))
+ return nfserr_stale;
+ /*
+ * A pseudoroot export gives permission to access only one
+ * single directory; the kernel has to make another upcall
+ * before granting access to anything else under it:
+ */
+ if (unlikely(dentry != exp->ex_path.dentry))
+ return nfserr_stale;
+ return nfs_ok;
+}
+
/*
* Use the given filehandle to look up the corresponding export and
* dentry. On success, the results are used to set fh_export and
@@ -232,14 +254,6 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
goto out;
}
- if (exp->ex_flags & NFSEXP_NOSUBTREECHECK) {
- error = nfsd_setuser_and_check_port(rqstp, exp);
- if (error) {
- dput(dentry);
- goto out;
- }
- }
-
if (S_ISDIR(dentry->d_inode->i_mode) &&
(dentry->d_flags & DCACHE_DISCONNECTED)) {
printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
@@ -294,28 +308,32 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
error = nfsd_set_fh_dentry(rqstp, fhp);
if (error)
goto out;
- dentry = fhp->fh_dentry;
- exp = fhp->fh_export;
- } else {
- /*
- * just rechecking permissions
- * (e.g. nfsproc_create calls fh_verify, then nfsd_create
- * does as well)
- */
- dprintk("nfsd: fh_verify - just checking\n");
- dentry = fhp->fh_dentry;
- exp = fhp->fh_export;
- /*
- * Set user creds for this exportpoint; necessary even
- * in the "just checking" case because this may be a
- * filehandle that was created by fh_compose, and that
- * is about to be used in another nfsv4 compound
- * operation.
- */
- error = nfsd_setuser_and_check_port(rqstp, exp);
- if (error)
- goto out;
}
+ dentry = fhp->fh_dentry;
+ exp = fhp->fh_export;
+ /*
+ * We still have to do all these permission checks, even when
+ * fh_dentry is already set:
+ * - fh_verify may be called multiple times with different
+ * "access" arguments (e.g. nfsd_proc_create calls
+ * fh_verify(...,NFSD_MAY_EXEC) first, then later (in
+ * nfsd_create) calls fh_verify(...,NFSD_MAY_CREATE).
+ * - in the NFSv4 case, the filehandle may have been filled
+ * in by fh_compose, and given a dentry, but further
+ * compound operations performed with that filehandle
+ * still need permissions checks. In the worst case, a
+ * mountpoint crossing may have changed the export
+ * options, and we may now need to use a different uid
+ * (for example, if different id-squashing options are in
+ * effect on the new filesystem).
+ */
+ error = check_pseudo_root(rqstp, dentry, exp);
+ if (error)
+ goto out;
+
+ error = nfsd_setuser_and_check_port(rqstp, exp);
+ if (error)
+ goto out;
error = nfsd_mode_check(rqstp, dentry->d_inode->i_mode, type);
if (error)
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
new file mode 100644
index 00000000000..cdfb8c6a420
--- /dev/null
+++ b/fs/nfsd/nfsfh.h
@@ -0,0 +1,208 @@
+/* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de> */
+
+#ifndef _LINUX_NFSD_FH_INT_H
+#define _LINUX_NFSD_FH_INT_H
+
+#include <linux/nfsd/nfsfh.h>
+
+enum nfsd_fsid {
+ FSID_DEV = 0,
+ FSID_NUM,
+ FSID_MAJOR_MINOR,
+ FSID_ENCODE_DEV,
+ FSID_UUID4_INUM,
+ FSID_UUID8,
+ FSID_UUID16,
+ FSID_UUID16_INUM,
+};
+
+enum fsid_source {
+ FSIDSOURCE_DEV,
+ FSIDSOURCE_FSID,
+ FSIDSOURCE_UUID,
+};
+extern enum fsid_source fsid_source(struct svc_fh *fhp);
+
+
+/* This might look a little large to "inline" but in all calls except
+ * one, 'vers' is constant so moste of the function disappears.
+ */
+static inline void mk_fsid(int vers, u32 *fsidv, dev_t dev, ino_t ino,
+ u32 fsid, unsigned char *uuid)
+{
+ u32 *up;
+ switch(vers) {
+ case FSID_DEV:
+ fsidv[0] = htonl((MAJOR(dev)<<16) |
+ MINOR(dev));
+ fsidv[1] = ino_t_to_u32(ino);
+ break;
+ case FSID_NUM:
+ fsidv[0] = fsid;
+ break;
+ case FSID_MAJOR_MINOR:
+ fsidv[0] = htonl(MAJOR(dev));
+ fsidv[1] = htonl(MINOR(dev));
+ fsidv[2] = ino_t_to_u32(ino);
+ break;
+
+ case FSID_ENCODE_DEV:
+ fsidv[0] = new_encode_dev(dev);
+ fsidv[1] = ino_t_to_u32(ino);
+ break;
+
+ case FSID_UUID4_INUM:
+ /* 4 byte fsid and inode number */
+ up = (u32*)uuid;
+ fsidv[0] = ino_t_to_u32(ino);
+ fsidv[1] = up[0] ^ up[1] ^ up[2] ^ up[3];
+ break;
+
+ case FSID_UUID8:
+ /* 8 byte fsid */
+ up = (u32*)uuid;
+ fsidv[0] = up[0] ^ up[2];
+ fsidv[1] = up[1] ^ up[3];
+ break;
+
+ case FSID_UUID16:
+ /* 16 byte fsid - NFSv3+ only */
+ memcpy(fsidv, uuid, 16);
+ break;
+
+ case FSID_UUID16_INUM:
+ /* 8 byte inode and 16 byte fsid */
+ *(u64*)fsidv = (u64)ino;
+ memcpy(fsidv+2, uuid, 16);
+ break;
+ default: BUG();
+ }
+}
+
+static inline int key_len(int type)
+{
+ switch(type) {
+ case FSID_DEV: return 8;
+ case FSID_NUM: return 4;
+ case FSID_MAJOR_MINOR: return 12;
+ case FSID_ENCODE_DEV: return 8;
+ case FSID_UUID4_INUM: return 8;
+ case FSID_UUID8: return 8;
+ case FSID_UUID16: return 16;
+ case FSID_UUID16_INUM: return 24;
+ default: return 0;
+ }
+}
+
+/*
+ * Shorthand for dprintk()'s
+ */
+extern char * SVCFH_fmt(struct svc_fh *fhp);
+
+/*
+ * Function prototypes
+ */
+__be32 fh_verify(struct svc_rqst *, struct svc_fh *, int, int);
+__be32 fh_compose(struct svc_fh *, struct svc_export *, struct dentry *, struct svc_fh *);
+__be32 fh_update(struct svc_fh *);
+void fh_put(struct svc_fh *);
+
+static __inline__ struct svc_fh *
+fh_copy(struct svc_fh *dst, struct svc_fh *src)
+{
+ WARN_ON(src->fh_dentry || src->fh_locked);
+
+ *dst = *src;
+ return dst;
+}
+
+static inline void
+fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
+{
+ dst->fh_size = src->fh_size;
+ memcpy(&dst->fh_base, &src->fh_base, src->fh_size);
+}
+
+static __inline__ struct svc_fh *
+fh_init(struct svc_fh *fhp, int maxsize)
+{
+ memset(fhp, 0, sizeof(*fhp));
+ fhp->fh_maxsize = maxsize;
+ return fhp;
+}
+
+#ifdef CONFIG_NFSD_V3
+/*
+ * Fill in the pre_op attr for the wcc data
+ */
+static inline void
+fill_pre_wcc(struct svc_fh *fhp)
+{
+ struct inode *inode;
+
+ inode = fhp->fh_dentry->d_inode;
+ if (!fhp->fh_pre_saved) {
+ fhp->fh_pre_mtime = inode->i_mtime;
+ fhp->fh_pre_ctime = inode->i_ctime;
+ fhp->fh_pre_size = inode->i_size;
+ fhp->fh_pre_change = inode->i_version;
+ fhp->fh_pre_saved = 1;
+ }
+}
+
+extern void fill_post_wcc(struct svc_fh *);
+#else
+#define fill_pre_wcc(ignored)
+#define fill_post_wcc(notused)
+#endif /* CONFIG_NFSD_V3 */
+
+
+/*
+ * Lock a file handle/inode
+ * NOTE: both fh_lock and fh_unlock are done "by hand" in
+ * vfs.c:nfsd_rename as it needs to grab 2 i_mutex's at once
+ * so, any changes here should be reflected there.
+ */
+
+static inline void
+fh_lock_nested(struct svc_fh *fhp, unsigned int subclass)
+{
+ struct dentry *dentry = fhp->fh_dentry;
+ struct inode *inode;
+
+ BUG_ON(!dentry);
+
+ if (fhp->fh_locked) {
+ printk(KERN_WARNING "fh_lock: %s/%s already locked!\n",
+ dentry->d_parent->d_name.name, dentry->d_name.name);
+ return;
+ }
+
+ inode = dentry->d_inode;
+ mutex_lock_nested(&inode->i_mutex, subclass);
+ fill_pre_wcc(fhp);
+ fhp->fh_locked = 1;
+}
+
+static inline void
+fh_lock(struct svc_fh *fhp)
+{
+ fh_lock_nested(fhp, I_MUTEX_NORMAL);
+}
+
+/*
+ * Unlock a file handle/inode
+ */
+static inline void
+fh_unlock(struct svc_fh *fhp)
+{
+ BUG_ON(!fhp->fh_dentry);
+
+ if (fhp->fh_locked) {
+ fill_post_wcc(fhp);
+ mutex_unlock(&fhp->fh_dentry->d_inode->i_mutex);
+ fhp->fh_locked = 0;
+ }
+}
+
+#endif /* _LINUX_NFSD_FH_INT_H */
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 0eb9c820b7a..a047ad6111e 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -1,29 +1,14 @@
/*
- * nfsproc2.c Process version 2 NFS requests.
- * linux/fs/nfsd/nfs2proc.c
- *
* Process version 2 NFS requests.
*
* Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/linkage.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/stat.h>
-#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/in.h>
#include <linux/namei.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/sunrpc/clnt.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/xdr.h>
+#include "cache.h"
+#include "xdr.h"
+#include "vfs.h"
typedef struct svc_rqst svc_rqst;
typedef struct svc_buf svc_buf;
@@ -758,6 +743,7 @@ nfserrno (int errno)
{ nfserr_io, -ETXTBSY },
{ nfserr_notsupp, -EOPNOTSUPP },
{ nfserr_toosmall, -ETOOSMALL },
+ { nfserr_serverfault, -ESERVERFAULT },
};
int i;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 67ea83eedd4..171699eb07c 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/nfssvc.c
- *
* Central processing for nfsd.
*
* Authors: Olaf Kirch (okir@monad.swb.de)
@@ -8,33 +6,19 @@
* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/module.h>
#include <linux/sched.h>
-#include <linux/time.h>
-#include <linux/errno.h>
-#include <linux/nfs.h>
-#include <linux/in.h>
-#include <linux/uio.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/smp.h>
#include <linux/freezer.h>
#include <linux/fs_struct.h>
-#include <linux/kthread.h>
#include <linux/swap.h>
-#include <linux/sunrpc/types.h>
#include <linux/sunrpc/stats.h>
-#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/svcsock.h>
-#include <linux/sunrpc/cache.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/stats.h>
-#include <linux/nfsd/cache.h>
-#include <linux/nfsd/syscall.h>
#include <linux/lockd/bind.h>
#include <linux/nfsacl.h>
#include <linux/seq_file.h>
+#include "nfsd.h"
+#include "cache.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_SVC
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index afd08e2c90a..4ce005dbf3e 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -1,20 +1,10 @@
/*
- * linux/fs/nfsd/nfsxdr.c
- *
* XDR support for nfsd
*
* Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/types.h>
-#include <linux/time.h>
-#include <linux/nfs.h>
-#include <linux/vfs.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#include <linux/nfsd/xdr.h>
-#include <linux/mm.h>
+#include "xdr.h"
#include "auth.h"
#define NFSDDBG_FACILITY NFSDDBG_XDR
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
new file mode 100644
index 00000000000..fefeae27f25
--- /dev/null
+++ b/fs/nfsd/state.h
@@ -0,0 +1,408 @@
+/*
+ * Copyright (c) 2001 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ * Kendrick Smith <kmsmith@umich.edu>
+ * Andy Adamson <andros@umich.edu>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the University nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _NFSD4_STATE_H
+#define _NFSD4_STATE_H
+
+#include <linux/nfsd/nfsfh.h>
+#include "nfsfh.h"
+
+typedef struct {
+ u32 cl_boot;
+ u32 cl_id;
+} clientid_t;
+
+typedef struct {
+ u32 so_boot;
+ u32 so_stateownerid;
+ u32 so_fileid;
+} stateid_opaque_t;
+
+typedef struct {
+ u32 si_generation;
+ stateid_opaque_t si_opaque;
+} stateid_t;
+#define si_boot si_opaque.so_boot
+#define si_stateownerid si_opaque.so_stateownerid
+#define si_fileid si_opaque.so_fileid
+
+#define STATEID_FMT "(%08x/%08x/%08x/%08x)"
+#define STATEID_VAL(s) \
+ (s)->si_boot, \
+ (s)->si_stateownerid, \
+ (s)->si_fileid, \
+ (s)->si_generation
+
+struct nfsd4_cb_sequence {
+ /* args/res */
+ u32 cbs_minorversion;
+ struct nfs4_client *cbs_clp;
+};
+
+struct nfs4_delegation {
+ struct list_head dl_perfile;
+ struct list_head dl_perclnt;
+ struct list_head dl_recall_lru; /* delegation recalled */
+ atomic_t dl_count; /* ref count */
+ struct nfs4_client *dl_client;
+ struct nfs4_file *dl_file;
+ struct file_lock *dl_flock;
+ struct file *dl_vfs_file;
+ u32 dl_type;
+ time_t dl_time;
+/* For recall: */
+ u32 dl_ident;
+ stateid_t dl_stateid;
+ struct knfsd_fh dl_fh;
+ int dl_retries;
+};
+
+/* client delegation callback info */
+struct nfs4_cb_conn {
+ /* SETCLIENTID info */
+ struct sockaddr_storage cb_addr;
+ size_t cb_addrlen;
+ u32 cb_prog;
+ u32 cb_minorversion;
+ u32 cb_ident; /* minorversion 0 only */
+ /* RPC client info */
+ atomic_t cb_set; /* successful CB_NULL call */
+ struct rpc_clnt * cb_client;
+};
+
+/* Maximum number of slots per session. 160 is useful for long haul TCP */
+#define NFSD_MAX_SLOTS_PER_SESSION 160
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND 16
+/* Maximum session per slot cache size */
+#define NFSD_SLOT_CACHE_SIZE 1024
+/* Maximum number of NFSD_SLOT_CACHE_SIZE slots per session */
+#define NFSD_CACHE_SIZE_SLOTS_PER_SESSION 32
+#define NFSD_MAX_MEM_PER_SESSION \
+ (NFSD_CACHE_SIZE_SLOTS_PER_SESSION * NFSD_SLOT_CACHE_SIZE)
+
+struct nfsd4_slot {
+ bool sl_inuse;
+ bool sl_cachethis;
+ u16 sl_opcnt;
+ u32 sl_seqid;
+ __be32 sl_status;
+ u32 sl_datalen;
+ char sl_data[];
+};
+
+struct nfsd4_channel_attrs {
+ u32 headerpadsz;
+ u32 maxreq_sz;
+ u32 maxresp_sz;
+ u32 maxresp_cached;
+ u32 maxops;
+ u32 maxreqs;
+ u32 nr_rdma_attrs;
+ u32 rdma_attrs;
+};
+
+struct nfsd4_create_session {
+ clientid_t clientid;
+ struct nfs4_sessionid sessionid;
+ u32 seqid;
+ u32 flags;
+ struct nfsd4_channel_attrs fore_channel;
+ struct nfsd4_channel_attrs back_channel;
+ u32 callback_prog;
+ u32 uid;
+ u32 gid;
+};
+
+/* The single slot clientid cache structure */
+struct nfsd4_clid_slot {
+ u32 sl_seqid;
+ __be32 sl_status;
+ struct nfsd4_create_session sl_cr_ses;
+};
+
+struct nfsd4_session {
+ struct kref se_ref;
+ struct list_head se_hash; /* hash by sessionid */
+ struct list_head se_perclnt;
+ u32 se_flags;
+ struct nfs4_client *se_client; /* for expire_client */
+ struct nfs4_sessionid se_sessionid;
+ struct nfsd4_channel_attrs se_fchannel;
+ struct nfsd4_channel_attrs se_bchannel;
+ struct nfsd4_slot *se_slots[]; /* forward channel slots */
+};
+
+static inline void
+nfsd4_put_session(struct nfsd4_session *ses)
+{
+ extern void free_session(struct kref *kref);
+ kref_put(&ses->se_ref, free_session);
+}
+
+static inline void
+nfsd4_get_session(struct nfsd4_session *ses)
+{
+ kref_get(&ses->se_ref);
+}
+
+/* formatted contents of nfs4_sessionid */
+struct nfsd4_sessionid {
+ clientid_t clientid;
+ u32 sequence;
+ u32 reserved;
+};
+
+#define HEXDIR_LEN 33 /* hex version of 16 byte md5 of cl_name plus '\0' */
+
+/*
+ * struct nfs4_client - one per client. Clientids live here.
+ * o Each nfs4_client is hashed by clientid.
+ *
+ * o Each nfs4_clients is also hashed by name
+ * (the opaque quantity initially sent by the client to identify itself).
+ *
+ * o cl_perclient list is used to ensure no dangling stateowner references
+ * when we expire the nfs4_client
+ */
+struct nfs4_client {
+ struct list_head cl_idhash; /* hash by cl_clientid.id */
+ struct list_head cl_strhash; /* hash by cl_name */
+ struct list_head cl_openowners;
+ struct list_head cl_delegations;
+ struct list_head cl_lru; /* tail queue */
+ struct xdr_netobj cl_name; /* id generated by client */
+ char cl_recdir[HEXDIR_LEN]; /* recovery dir */
+ nfs4_verifier cl_verifier; /* generated by client */
+ time_t cl_time; /* time of last lease renewal */
+ struct sockaddr_storage cl_addr; /* client ipaddress */
+ u32 cl_flavor; /* setclientid pseudoflavor */
+ char *cl_principal; /* setclientid principal name */
+ struct svc_cred cl_cred; /* setclientid principal */
+ clientid_t cl_clientid; /* generated by server */
+ nfs4_verifier cl_confirm; /* generated by server */
+ struct nfs4_cb_conn cl_cb_conn; /* callback info */
+ atomic_t cl_count; /* ref count */
+ u32 cl_firststate; /* recovery dir creation */
+
+ /* for nfs41 */
+ struct list_head cl_sessions;
+ struct nfsd4_clid_slot cl_cs_slot; /* create_session slot */
+ u32 cl_exchange_flags;
+ struct nfs4_sessionid cl_sessionid;
+
+ /* for nfs41 callbacks */
+ /* We currently support a single back channel with a single slot */
+ unsigned long cl_cb_slot_busy;
+ u32 cl_cb_seq_nr;
+ struct svc_xprt *cl_cb_xprt; /* 4.1 callback transport */
+ struct rpc_wait_queue cl_cb_waitq; /* backchannel callers may */
+ /* wait here for slots */
+};
+
+/* struct nfs4_client_reset
+ * one per old client. Populates reset_str_hashtbl. Filled from conf_id_hashtbl
+ * upon lease reset, or from upcall to state_daemon (to read in state
+ * from non-volitile storage) upon reboot.
+ */
+struct nfs4_client_reclaim {
+ struct list_head cr_strhash; /* hash by cr_name */
+ char cr_recdir[HEXDIR_LEN]; /* recover dir */
+};
+
+static inline void
+update_stateid(stateid_t *stateid)
+{
+ stateid->si_generation++;
+}
+
+/* A reasonable value for REPLAY_ISIZE was estimated as follows:
+ * The OPEN response, typically the largest, requires
+ * 4(status) + 8(stateid) + 20(changeinfo) + 4(rflags) + 8(verifier) +
+ * 4(deleg. type) + 8(deleg. stateid) + 4(deleg. recall flag) +
+ * 20(deleg. space limit) + ~32(deleg. ace) = 112 bytes
+ */
+
+#define NFSD4_REPLAY_ISIZE 112
+
+/*
+ * Replay buffer, where the result of the last seqid-mutating operation
+ * is cached.
+ */
+struct nfs4_replay {
+ __be32 rp_status;
+ unsigned int rp_buflen;
+ char *rp_buf;
+ unsigned intrp_allocated;
+ struct knfsd_fh rp_openfh;
+ char rp_ibuf[NFSD4_REPLAY_ISIZE];
+};
+
+/*
+* nfs4_stateowner can either be an open_owner, or a lock_owner
+*
+* so_idhash: stateid_hashtbl[] for open owner, lockstateid_hashtbl[]
+* for lock_owner
+* so_strhash: ownerstr_hashtbl[] for open_owner, lock_ownerstr_hashtbl[]
+* for lock_owner
+* so_perclient: nfs4_client->cl_perclient entry - used when nfs4_client
+* struct is reaped.
+* so_perfilestate: heads the list of nfs4_stateid (either open or lock)
+* and is used to ensure no dangling nfs4_stateid references when we
+* release a stateowner.
+* so_perlockowner: (open) nfs4_stateid->st_perlockowner entry - used when
+* close is called to reap associated byte-range locks
+* so_close_lru: (open) stateowner is placed on this list instead of being
+* reaped (when so_perfilestate is empty) to hold the last close replay.
+* reaped by laundramat thread after lease period.
+*/
+struct nfs4_stateowner {
+ struct kref so_ref;
+ struct list_head so_idhash; /* hash by so_id */
+ struct list_head so_strhash; /* hash by op_name */
+ struct list_head so_perclient;
+ struct list_head so_stateids;
+ struct list_head so_perstateid; /* for lockowners only */
+ struct list_head so_close_lru; /* tail queue */
+ time_t so_time; /* time of placement on so_close_lru */
+ int so_is_open_owner; /* 1=openowner,0=lockowner */
+ u32 so_id;
+ struct nfs4_client * so_client;
+ /* after increment in ENCODE_SEQID_OP_TAIL, represents the next
+ * sequence id expected from the client: */
+ u32 so_seqid;
+ struct xdr_netobj so_owner; /* open owner name */
+ int so_confirmed; /* successful OPEN_CONFIRM? */
+ struct nfs4_replay so_replay;
+};
+
+/*
+* nfs4_file: a file opened by some number of (open) nfs4_stateowners.
+* o fi_perfile list is used to search for conflicting
+* share_acces, share_deny on the file.
+*/
+struct nfs4_file {
+ atomic_t fi_ref;
+ struct list_head fi_hash; /* hash by "struct inode *" */
+ struct list_head fi_stateids;
+ struct list_head fi_delegations;
+ struct inode *fi_inode;
+ u32 fi_id; /* used with stateowner->so_id
+ * for stateid_hashtbl hash */
+ bool fi_had_conflict;
+};
+
+/*
+* nfs4_stateid can either be an open stateid or (eventually) a lock stateid
+*
+* (open)nfs4_stateid: one per (open)nfs4_stateowner, nfs4_file
+*
+* st_hash: stateid_hashtbl[] entry or lockstateid_hashtbl entry
+* st_perfile: file_hashtbl[] entry.
+* st_perfile_state: nfs4_stateowner->so_perfilestate
+* st_perlockowner: (open stateid) list of lock nfs4_stateowners
+* st_access_bmap: used only for open stateid
+* st_deny_bmap: used only for open stateid
+* st_openstp: open stateid lock stateid was derived from
+*
+* XXX: open stateids and lock stateids have diverged sufficiently that
+* we should consider defining separate structs for the two cases.
+*/
+
+struct nfs4_stateid {
+ struct list_head st_hash;
+ struct list_head st_perfile;
+ struct list_head st_perstateowner;
+ struct list_head st_lockowners;
+ struct nfs4_stateowner * st_stateowner;
+ struct nfs4_file * st_file;
+ stateid_t st_stateid;
+ struct file * st_vfs_file;
+ unsigned long st_access_bmap;
+ unsigned long st_deny_bmap;
+ struct nfs4_stateid * st_openstp;
+};
+
+/* flags for preprocess_seqid_op() */
+#define HAS_SESSION 0x00000001
+#define CONFIRM 0x00000002
+#define OPEN_STATE 0x00000004
+#define LOCK_STATE 0x00000008
+#define RD_STATE 0x00000010
+#define WR_STATE 0x00000020
+#define CLOSE_STATE 0x00000040
+
+#define seqid_mutating_err(err) \
+ (((err) != nfserr_stale_clientid) && \
+ ((err) != nfserr_bad_seqid) && \
+ ((err) != nfserr_stale_stateid) && \
+ ((err) != nfserr_bad_stateid))
+
+struct nfsd4_compound_state;
+
+extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
+ stateid_t *stateid, int flags, struct file **filp);
+extern void nfs4_lock_state(void);
+extern void nfs4_unlock_state(void);
+extern int nfs4_in_grace(void);
+extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
+extern void put_nfs4_client(struct nfs4_client *clp);
+extern void nfs4_free_stateowner(struct kref *kref);
+extern int set_callback_cred(void);
+extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
+extern void nfs4_put_delegation(struct nfs4_delegation *dp);
+extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
+extern void nfsd4_init_recdir(char *recdir_name);
+extern int nfsd4_recdir_load(void);
+extern void nfsd4_shutdown_recdir(void);
+extern int nfs4_client_to_reclaim(const char *name);
+extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
+extern void nfsd4_recdir_purge_old(void);
+extern int nfsd4_create_clid_dir(struct nfs4_client *clp);
+extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);
+
+static inline void
+nfs4_put_stateowner(struct nfs4_stateowner *so)
+{
+ kref_put(&so->so_ref, nfs4_free_stateowner);
+}
+
+static inline void
+nfs4_get_stateowner(struct nfs4_stateowner *so)
+{
+ kref_get(&so->so_ref);
+}
+
+#endif /* NFSD4_STATE_H */
diff --git a/fs/nfsd/stats.c b/fs/nfsd/stats.c
index 71944cddf68..5232d3e8fb2 100644
--- a/fs/nfsd/stats.c
+++ b/fs/nfsd/stats.c
@@ -1,6 +1,4 @@
/*
- * linux/fs/nfsd/stats.c
- *
* procfs-based user access to knfsd statistics
*
* /proc/net/rpc/nfsd
@@ -23,18 +21,13 @@
* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
*/
-#include <linux/kernel.h>
-#include <linux/time.h>
-#include <linux/proc_fs.h>
#include <linux/seq_file.h>
-#include <linux/stat.h>
#include <linux/module.h>
-
-#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/stats.h>
-#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/stats.h>
+#include "nfsd.h"
+
struct nfsd_stats nfsdstats;
struct svc_stat nfsd_svcstats = {
.program = &nfsd_program,
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index a293f027326..7c2e337d05a 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1,7 +1,5 @@
#define MSNFS /* HACK HACK */
/*
- * linux/fs/nfsd/vfs.c
- *
* File operations used by nfsd. Some of these have been ripped from
* other parts of the kernel because they weren't exported, others
* are partial duplicates with added or changed functionality.
@@ -16,48 +14,31 @@
* Zerocpy NFS support (C) 2002 Hirokazu Takahashi <taka@valinux.co.jp>
*/
-#include <linux/string.h>
-#include <linux/time.h>
-#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
-#include <linux/mount.h>
-#include <linux/major.h>
#include <linux/splice.h>
-#include <linux/proc_fs.h>
-#include <linux/stat.h>
#include <linux/fcntl.h>
-#include <linux/net.h>
-#include <linux/unistd.h>
-#include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/in.h>
-#include <linux/module.h>
#include <linux/namei.h>
-#include <linux/vfs.h>
#include <linux/delay.h>
-#include <linux/sunrpc/svc.h>
-#include <linux/nfsd/nfsd.h>
-#ifdef CONFIG_NFSD_V3
-#include <linux/nfs3.h>
-#include <linux/nfsd/xdr3.h>
-#endif /* CONFIG_NFSD_V3 */
-#include <linux/nfsd/nfsfh.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
-#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/xattr.h>
+#include <linux/jhash.h>
+#include <linux/ima.h>
+#include <asm/uaccess.h>
+
+#ifdef CONFIG_NFSD_V3
+#include "xdr3.h"
+#endif /* CONFIG_NFSD_V3 */
+
#ifdef CONFIG_NFSD_V4
-#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>
#include <linux/nfsd_idmap.h>
-#include <linux/security.h>
#endif /* CONFIG_NFSD_V4 */
-#include <linux/jhash.h>
-#include <linux/ima.h>
-#include <asm/uaccess.h>
+#include "nfsd.h"
+#include "vfs.h"
#define NFSDDBG_FACILITY NFSDDBG_FILEOP
@@ -89,12 +70,6 @@ struct raparm_hbucket {
#define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1)
static struct raparm_hbucket raparm_hash[RAPARM_HASH_SIZE];
-static inline int
-nfsd_v4client(struct svc_rqst *rq)
-{
- return rq->rq_prog == NFS_PROGRAM && rq->rq_vers == 4;
-}
-
/*
* Called from nfsd_lookup and encode_dirent. Check if we have crossed
* a mount point.
@@ -116,8 +91,16 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
exp2 = rqst_exp_get_by_name(rqstp, &path);
if (IS_ERR(exp2)) {
- if (PTR_ERR(exp2) != -ENOENT)
- err = PTR_ERR(exp2);
+ err = PTR_ERR(exp2);
+ /*
+ * We normally allow NFS clients to continue
+ * "underneath" a mountpoint that is not exported.
+ * The exception is V4ROOT, where no traversal is ever
+ * allowed without an explicit export of the new
+ * directory.
+ */
+ if (err == -ENOENT && !(exp->ex_flags & NFSEXP_V4ROOT))
+ err = 0;
path_put(&path);
goto out;
}
@@ -141,6 +124,53 @@ out:
return err;
}
+static void follow_to_parent(struct path *path)
+{
+ struct dentry *dp;
+
+ while (path->dentry == path->mnt->mnt_root && follow_up(path))
+ ;
+ dp = dget_parent(path->dentry);
+ dput(path->dentry);
+ path->dentry = dp;
+}
+
+static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, struct svc_export **exp, struct dentry **dentryp)
+{
+ struct svc_export *exp2;
+ struct path path = {.mnt = mntget((*exp)->ex_path.mnt),
+ .dentry = dget(dparent)};
+
+ follow_to_parent(&path);
+
+ exp2 = rqst_exp_parent(rqstp, &path);
+ if (PTR_ERR(exp2) == -ENOENT) {
+ *dentryp = dget(dparent);
+ } else if (IS_ERR(exp2)) {
+ path_put(&path);
+ return PTR_ERR(exp2);
+ } else {
+ *dentryp = dget(path.dentry);
+ exp_put(*exp);
+ *exp = exp2;
+ }
+ path_put(&path);
+ return 0;
+}
+
+/*
+ * For nfsd purposes, we treat V4ROOT exports as though there was an
+ * export at *every* directory.
+ */
+int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
+{
+ if (d_mountpoint(dentry))
+ return 1;
+ if (!(exp->ex_flags & NFSEXP_V4ROOT))
+ return 0;
+ return dentry->d_inode != NULL;
+}
+
__be32
nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
const char *name, unsigned int len,
@@ -169,35 +199,13 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
dentry = dget(dparent);
else if (dparent != exp->ex_path.dentry)
dentry = dget_parent(dparent);
- else if (!EX_NOHIDE(exp))
+ else if (!EX_NOHIDE(exp) && !nfsd_v4client(rqstp))
dentry = dget(dparent); /* .. == . just like at / */
else {
/* checking mountpoint crossing is very different when stepping up */
- struct svc_export *exp2 = NULL;
- struct dentry *dp;
- struct path path = {.mnt = mntget(exp->ex_path.mnt),
- .dentry = dget(dparent)};
-
- while (path.dentry == path.mnt->mnt_root &&
- follow_up(&path))
- ;
- dp = dget_parent(path.dentry);
- dput(path.dentry);
- path.dentry = dp;
-
- exp2 = rqst_exp_parent(rqstp, &path);
- if (PTR_ERR(exp2) == -ENOENT) {
- dentry = dget(dparent);
- } else if (IS_ERR(exp2)) {
- host_err = PTR_ERR(exp2);
- path_put(&path);
+ host_err = nfsd_lookup_parent(rqstp, dparent, &exp, &dentry);
+ if (host_err)
goto out_nfserr;
- } else {
- dentry = dget(path.dentry);
- exp_put(exp);
- exp = exp2;
- }
- path_put(&path);
}
} else {
fh_lock(fhp);
@@ -208,7 +216,7 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
/*
* check if we have crossed a mount point ...
*/
- if (d_mountpoint(dentry)) {
+ if (nfsd_mountpoint(dentry, exp)) {
if ((host_err = nfsd_cross_mnt(rqstp, &dentry, &exp))) {
dput(dentry);
goto out_nfserr;
@@ -744,8 +752,6 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
flags, current_cred());
if (IS_ERR(*filp))
host_err = PTR_ERR(*filp);
- else
- ima_counts_get(*filp);
out_nfserr:
err = nfserrno(host_err);
out:
@@ -2124,8 +2130,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp,
*/
path.mnt = exp->ex_path.mnt;
path.dentry = dentry;
- err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC),
- IMA_COUNT_LEAVE);
+ err = ima_path_check(&path, acc & (MAY_READ | MAY_WRITE | MAY_EXEC));
nfsd_out:
return err? nfserrno(err) : 0;
}
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
new file mode 100644
index 00000000000..4b1de0a9ea7
--- /dev/null
+++ b/fs/nfsd/vfs.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef LINUX_NFSD_VFS_H
+#define LINUX_NFSD_VFS_H
+
+#include "nfsfh.h"
+
+/*
+ * Flags for nfsd_permission
+ */
+#define NFSD_MAY_NOP 0
+#define NFSD_MAY_EXEC 1 /* == MAY_EXEC */
+#define NFSD_MAY_WRITE 2 /* == MAY_WRITE */
+#define NFSD_MAY_READ 4 /* == MAY_READ */
+#define NFSD_MAY_SATTR 8
+#define NFSD_MAY_TRUNC 16
+#define NFSD_MAY_LOCK 32
+#define NFSD_MAY_OWNER_OVERRIDE 64
+#define NFSD_MAY_LOCAL_ACCESS 128 /* IRIX doing local access check on device special file*/
+#define NFSD_MAY_BYPASS_GSS_ON_ROOT 256
+
+#define NFSD_MAY_CREATE (NFSD_MAY_EXEC|NFSD_MAY_WRITE)
+#define NFSD_MAY_REMOVE (NFSD_MAY_EXEC|NFSD_MAY_WRITE|NFSD_MAY_TRUNC)
+
+/*
+ * Callback function for readdir
+ */
+typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
+
+/* nfsd/vfs.c */
+int fh_lock_parent(struct svc_fh *, struct dentry *);
+int nfsd_racache_init(int);
+void nfsd_racache_shutdown(void);
+int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
+ struct svc_export **expp);
+__be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *,
+ const char *, unsigned int, struct svc_fh *);
+__be32 nfsd_lookup_dentry(struct svc_rqst *, struct svc_fh *,
+ const char *, unsigned int,
+ struct svc_export **, struct dentry **);
+__be32 nfsd_setattr(struct svc_rqst *, struct svc_fh *,
+ struct iattr *, int, time_t);
+int nfsd_mountpoint(struct dentry *, struct svc_export *);
+#ifdef CONFIG_NFSD_V4
+__be32 nfsd4_set_nfs4_acl(struct svc_rqst *, struct svc_fh *,
+ struct nfs4_acl *);
+int nfsd4_get_nfs4_acl(struct svc_rqst *, struct dentry *, struct nfs4_acl **);
+#endif /* CONFIG_NFSD_V4 */
+__be32 nfsd_create(struct svc_rqst *, struct svc_fh *,
+ char *name, int len, struct iattr *attrs,
+ int type, dev_t rdev, struct svc_fh *res);
+#ifdef CONFIG_NFSD_V3
+__be32 nfsd_access(struct svc_rqst *, struct svc_fh *, u32 *, u32 *);
+__be32 nfsd_create_v3(struct svc_rqst *, struct svc_fh *,
+ char *name, int len, struct iattr *attrs,
+ struct svc_fh *res, int createmode,
+ u32 *verifier, int *truncp, int *created);
+__be32 nfsd_commit(struct svc_rqst *, struct svc_fh *,
+ loff_t, unsigned long);
+#endif /* CONFIG_NFSD_V3 */
+__be32 nfsd_open(struct svc_rqst *, struct svc_fh *, int,
+ int, struct file **);
+void nfsd_close(struct file *);
+__be32 nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *,
+ loff_t, struct kvec *, int, unsigned long *);
+__be32 nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
+ loff_t, struct kvec *,int, unsigned long *, int *);
+__be32 nfsd_readlink(struct svc_rqst *, struct svc_fh *,
+ char *, int *);
+__be32 nfsd_symlink(struct svc_rqst *, struct svc_fh *,
+ char *name, int len, char *path, int plen,
+ struct svc_fh *res, struct iattr *);
+__be32 nfsd_link(struct svc_rqst *, struct svc_fh *,
+ char *, int, struct svc_fh *);
+__be32 nfsd_rename(struct svc_rqst *,
+ struct svc_fh *, char *, int,
+ struct svc_fh *, char *, int);
+__be32 nfsd_remove(struct svc_rqst *,
+ struct svc_fh *, char *, int);
+__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
+ char *name, int len);
+int nfsd_truncate(struct svc_rqst *, struct svc_fh *,
+ unsigned long size);
+__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *,
+ loff_t *, struct readdir_cd *, filldir_t);
+__be32 nfsd_statfs(struct svc_rqst *, struct svc_fh *,
+ struct kstatfs *, int access);
+
+int nfsd_notify_change(struct inode *, struct iattr *);
+__be32 nfsd_permission(struct svc_rqst *, struct svc_export *,
+ struct dentry *, int);
+int nfsd_sync_dir(struct dentry *dp);
+
+#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
+struct posix_acl *nfsd_get_posix_acl(struct svc_fh *, int);
+int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
+#endif
+
+#endif /* LINUX_NFSD_VFS_H */
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
new file mode 100644
index 00000000000..53b1863dd8f
--- /dev/null
+++ b/fs/nfsd/xdr.h
@@ -0,0 +1,173 @@
+/* XDR types for nfsd. This is mainly a typing exercise. */
+
+#ifndef LINUX_NFSD_H
+#define LINUX_NFSD_H
+
+#include <linux/vfs.h>
+#include "nfsd.h"
+#include "nfsfh.h"
+
+struct nfsd_fhandle {
+ struct svc_fh fh;
+};
+
+struct nfsd_sattrargs {
+ struct svc_fh fh;
+ struct iattr attrs;
+};
+
+struct nfsd_diropargs {
+ struct svc_fh fh;
+ char * name;
+ unsigned int len;
+};
+
+struct nfsd_readargs {
+ struct svc_fh fh;
+ __u32 offset;
+ __u32 count;
+ int vlen;
+};
+
+struct nfsd_writeargs {
+ svc_fh fh;
+ __u32 offset;
+ int len;
+ int vlen;
+};
+
+struct nfsd_createargs {
+ struct svc_fh fh;
+ char * name;
+ unsigned int len;
+ struct iattr attrs;
+};
+
+struct nfsd_renameargs {
+ struct svc_fh ffh;
+ char * fname;
+ unsigned int flen;
+ struct svc_fh tfh;
+ char * tname;
+ unsigned int tlen;
+};
+
+struct nfsd_readlinkargs {
+ struct svc_fh fh;
+ char * buffer;
+};
+
+struct nfsd_linkargs {
+ struct svc_fh ffh;
+ struct svc_fh tfh;
+ char * tname;
+ unsigned int tlen;
+};
+
+struct nfsd_symlinkargs {
+ struct svc_fh ffh;
+ char * fname;
+ unsigned int flen;
+ char * tname;
+ unsigned int tlen;
+ struct iattr attrs;
+};
+
+struct nfsd_readdirargs {
+ struct svc_fh fh;
+ __u32 cookie;
+ __u32 count;
+ __be32 * buffer;
+};
+
+struct nfsd_attrstat {
+ struct svc_fh fh;
+ struct kstat stat;
+};
+
+struct nfsd_diropres {
+ struct svc_fh fh;
+ struct kstat stat;
+};
+
+struct nfsd_readlinkres {
+ int len;
+};
+
+struct nfsd_readres {
+ struct svc_fh fh;
+ unsigned long count;
+ struct kstat stat;
+};
+
+struct nfsd_readdirres {
+ int count;
+
+ struct readdir_cd common;
+ __be32 * buffer;
+ int buflen;
+ __be32 * offset;
+};
+
+struct nfsd_statfsres {
+ struct kstatfs stats;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd_xdrstore {
+ struct nfsd_sattrargs sattr;
+ struct nfsd_diropargs dirop;
+ struct nfsd_readargs read;
+ struct nfsd_writeargs write;
+ struct nfsd_createargs create;
+ struct nfsd_renameargs rename;
+ struct nfsd_linkargs link;
+ struct nfsd_symlinkargs symlink;
+ struct nfsd_readdirargs readdir;
+};
+
+#define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore)
+
+
+int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *);
+int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *,
+ struct nfsd_sattrargs *);
+int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *,
+ struct nfsd_diropargs *);
+int nfssvc_decode_readargs(struct svc_rqst *, __be32 *,
+ struct nfsd_readargs *);
+int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *,
+ struct nfsd_writeargs *);
+int nfssvc_decode_createargs(struct svc_rqst *, __be32 *,
+ struct nfsd_createargs *);
+int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *,
+ struct nfsd_renameargs *);
+int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *,
+ struct nfsd_readlinkargs *);
+int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *,
+ struct nfsd_linkargs *);
+int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *,
+ struct nfsd_symlinkargs *);
+int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *,
+ struct nfsd_readdirargs *);
+int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
+int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
+int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
+int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *);
+int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *);
+int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *);
+int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *);
+
+int nfssvc_encode_entry(void *, const char *name,
+ int namlen, loff_t offset, u64 ino, unsigned int);
+
+int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+
+/* Helper functions for NFSv2 ACL code */
+__be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp);
+__be32 *nfs2svc_decode_fh(__be32 *p, struct svc_fh *fhp);
+
+#endif /* LINUX_NFSD_H */
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
new file mode 100644
index 00000000000..7df980eb056
--- /dev/null
+++ b/fs/nfsd/xdr3.h
@@ -0,0 +1,344 @@
+/*
+ * XDR types for NFSv3 in nfsd.
+ *
+ * Copyright (C) 1996-1998, Olaf Kirch <okir@monad.swb.de>
+ */
+
+#ifndef _LINUX_NFSD_XDR3_H
+#define _LINUX_NFSD_XDR3_H
+
+#include "xdr.h"
+
+struct nfsd3_sattrargs {
+ struct svc_fh fh;
+ struct iattr attrs;
+ int check_guard;
+ time_t guardtime;
+};
+
+struct nfsd3_diropargs {
+ struct svc_fh fh;
+ char * name;
+ unsigned int len;
+};
+
+struct nfsd3_accessargs {
+ struct svc_fh fh;
+ unsigned int access;
+};
+
+struct nfsd3_readargs {
+ struct svc_fh fh;
+ __u64 offset;
+ __u32 count;
+ int vlen;
+};
+
+struct nfsd3_writeargs {
+ svc_fh fh;
+ __u64 offset;
+ __u32 count;
+ int stable;
+ __u32 len;
+ int vlen;
+};
+
+struct nfsd3_createargs {
+ struct svc_fh fh;
+ char * name;
+ unsigned int len;
+ int createmode;
+ struct iattr attrs;
+ __be32 * verf;
+};
+
+struct nfsd3_mknodargs {
+ struct svc_fh fh;
+ char * name;
+ unsigned int len;
+ __u32 ftype;
+ __u32 major, minor;
+ struct iattr attrs;
+};
+
+struct nfsd3_renameargs {
+ struct svc_fh ffh;
+ char * fname;
+ unsigned int flen;
+ struct svc_fh tfh;
+ char * tname;
+ unsigned int tlen;
+};
+
+struct nfsd3_readlinkargs {
+ struct svc_fh fh;
+ char * buffer;
+};
+
+struct nfsd3_linkargs {
+ struct svc_fh ffh;
+ struct svc_fh tfh;
+ char * tname;
+ unsigned int tlen;
+};
+
+struct nfsd3_symlinkargs {
+ struct svc_fh ffh;
+ char * fname;
+ unsigned int flen;
+ char * tname;
+ unsigned int tlen;
+ struct iattr attrs;
+};
+
+struct nfsd3_readdirargs {
+ struct svc_fh fh;
+ __u64 cookie;
+ __u32 dircount;
+ __u32 count;
+ __be32 * verf;
+ __be32 * buffer;
+};
+
+struct nfsd3_commitargs {
+ struct svc_fh fh;
+ __u64 offset;
+ __u32 count;
+};
+
+struct nfsd3_getaclargs {
+ struct svc_fh fh;
+ int mask;
+};
+
+struct posix_acl;
+struct nfsd3_setaclargs {
+ struct svc_fh fh;
+ int mask;
+ struct posix_acl *acl_access;
+ struct posix_acl *acl_default;
+};
+
+struct nfsd3_attrstat {
+ __be32 status;
+ struct svc_fh fh;
+ struct kstat stat;
+};
+
+/* LOOKUP, CREATE, MKDIR, SYMLINK, MKNOD */
+struct nfsd3_diropres {
+ __be32 status;
+ struct svc_fh dirfh;
+ struct svc_fh fh;
+};
+
+struct nfsd3_accessres {
+ __be32 status;
+ struct svc_fh fh;
+ __u32 access;
+};
+
+struct nfsd3_readlinkres {
+ __be32 status;
+ struct svc_fh fh;
+ __u32 len;
+};
+
+struct nfsd3_readres {
+ __be32 status;
+ struct svc_fh fh;
+ unsigned long count;
+ int eof;
+};
+
+struct nfsd3_writeres {
+ __be32 status;
+ struct svc_fh fh;
+ unsigned long count;
+ int committed;
+};
+
+struct nfsd3_renameres {
+ __be32 status;
+ struct svc_fh ffh;
+ struct svc_fh tfh;
+};
+
+struct nfsd3_linkres {
+ __be32 status;
+ struct svc_fh tfh;
+ struct svc_fh fh;
+};
+
+struct nfsd3_readdirres {
+ __be32 status;
+ struct svc_fh fh;
+ int count;
+ __be32 verf[2];
+
+ struct readdir_cd common;
+ __be32 * buffer;
+ int buflen;
+ __be32 * offset;
+ __be32 * offset1;
+ struct svc_rqst * rqstp;
+
+};
+
+struct nfsd3_fsstatres {
+ __be32 status;
+ struct kstatfs stats;
+ __u32 invarsec;
+};
+
+struct nfsd3_fsinfores {
+ __be32 status;
+ __u32 f_rtmax;
+ __u32 f_rtpref;
+ __u32 f_rtmult;
+ __u32 f_wtmax;
+ __u32 f_wtpref;
+ __u32 f_wtmult;
+ __u32 f_dtpref;
+ __u64 f_maxfilesize;
+ __u32 f_properties;
+};
+
+struct nfsd3_pathconfres {
+ __be32 status;
+ __u32 p_link_max;
+ __u32 p_name_max;
+ __u32 p_no_trunc;
+ __u32 p_chown_restricted;
+ __u32 p_case_insensitive;
+ __u32 p_case_preserving;
+};
+
+struct nfsd3_commitres {
+ __be32 status;
+ struct svc_fh fh;
+};
+
+struct nfsd3_getaclres {
+ __be32 status;
+ struct svc_fh fh;
+ int mask;
+ struct posix_acl *acl_access;
+ struct posix_acl *acl_default;
+};
+
+/* dummy type for release */
+struct nfsd3_fhandle_pair {
+ __u32 dummy;
+ struct svc_fh fh1;
+ struct svc_fh fh2;
+};
+
+/*
+ * Storage requirements for XDR arguments and results.
+ */
+union nfsd3_xdrstore {
+ struct nfsd3_sattrargs sattrargs;
+ struct nfsd3_diropargs diropargs;
+ struct nfsd3_readargs readargs;
+ struct nfsd3_writeargs writeargs;
+ struct nfsd3_createargs createargs;
+ struct nfsd3_renameargs renameargs;
+ struct nfsd3_linkargs linkargs;
+ struct nfsd3_symlinkargs symlinkargs;
+ struct nfsd3_readdirargs readdirargs;
+ struct nfsd3_diropres diropres;
+ struct nfsd3_accessres accessres;
+ struct nfsd3_readlinkres readlinkres;
+ struct nfsd3_readres readres;
+ struct nfsd3_writeres writeres;
+ struct nfsd3_renameres renameres;
+ struct nfsd3_linkres linkres;
+ struct nfsd3_readdirres readdirres;
+ struct nfsd3_fsstatres fsstatres;
+ struct nfsd3_fsinfores fsinfores;
+ struct nfsd3_pathconfres pathconfres;
+ struct nfsd3_commitres commitres;
+ struct nfsd3_getaclres getaclres;
+};
+
+#define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore)
+
+int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_sattrargs *);
+int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_diropargs *);
+int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_accessargs *);
+int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_readargs *);
+int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_writeargs *);
+int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_createargs *);
+int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_createargs *);
+int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_mknodargs *);
+int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_renameargs *);
+int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_readlinkargs *);
+int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_linkargs *);
+int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_symlinkargs *);
+int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_readdirargs *);
+int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_readdirargs *);
+int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *,
+ struct nfsd3_commitargs *);
+int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
+ struct nfsd3_attrstat *);
+int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *,
+ struct nfsd3_attrstat *);
+int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *,
+ struct nfsd3_diropres *);
+int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *,
+ struct nfsd3_accessres *);
+int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *,
+ struct nfsd3_readlinkres *);
+int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *);
+int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *);
+int nfs3svc_encode_createres(struct svc_rqst *, __be32 *,
+ struct nfsd3_diropres *);
+int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *,
+ struct nfsd3_renameres *);
+int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *,
+ struct nfsd3_linkres *);
+int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *,
+ struct nfsd3_readdirres *);
+int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *,
+ struct nfsd3_fsstatres *);
+int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *,
+ struct nfsd3_fsinfores *);
+int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
+ struct nfsd3_pathconfres *);
+int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
+ struct nfsd3_commitres *);
+
+int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *,
+ struct nfsd3_attrstat *);
+int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *,
+ struct nfsd3_fhandle_pair *);
+int nfs3svc_encode_entry(void *, const char *name,
+ int namlen, loff_t offset, u64 ino,
+ unsigned int);
+int nfs3svc_encode_entry_plus(void *, const char *name,
+ int namlen, loff_t offset, u64 ino,
+ unsigned int);
+/* Helper functions for NFSv3 ACL code */
+__be32 *nfs3svc_encode_post_op_attr(struct svc_rqst *rqstp, __be32 *p,
+ struct svc_fh *fhp);
+__be32 *nfs3svc_decode_fh(__be32 *p, struct svc_fh *fhp);
+
+
+#endif /* _LINUX_NFSD_XDR3_H */
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
new file mode 100644
index 00000000000..efa33773953
--- /dev/null
+++ b/fs/nfsd/xdr4.h
@@ -0,0 +1,562 @@
+/*
+ * Server-side types for NFSv4.
+ *
+ * Copyright (c) 2002 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ * Kendrick Smith <kmsmith@umich.edu>
+ * Andy Adamson <andros@umich.edu>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the University nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef _LINUX_NFSD_XDR4_H
+#define _LINUX_NFSD_XDR4_H
+
+#include "state.h"
+#include "nfsd.h"
+
+#define NFSD4_MAX_TAGLEN 128
+#define XDR_LEN(n) (((n) + 3) & ~3)
+
+struct nfsd4_compound_state {
+ struct svc_fh current_fh;
+ struct svc_fh save_fh;
+ struct nfs4_stateowner *replay_owner;
+ /* For sessions DRC */
+ struct nfsd4_session *session;
+ struct nfsd4_slot *slot;
+ __be32 *datap;
+ size_t iovlen;
+ u32 minorversion;
+ u32 status;
+};
+
+static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
+{
+ return cs->slot != NULL;
+}
+
+struct nfsd4_change_info {
+ u32 atomic;
+ bool change_supported;
+ u32 before_ctime_sec;
+ u32 before_ctime_nsec;
+ u64 before_change;
+ u32 after_ctime_sec;
+ u32 after_ctime_nsec;
+ u64 after_change;
+};
+
+struct nfsd4_access {
+ u32 ac_req_access; /* request */
+ u32 ac_supported; /* response */
+ u32 ac_resp_access; /* response */
+};
+
+struct nfsd4_close {
+ u32 cl_seqid; /* request */
+ stateid_t cl_stateid; /* request+response */
+ struct nfs4_stateowner * cl_stateowner; /* response */
+};
+
+struct nfsd4_commit {
+ u64 co_offset; /* request */
+ u32 co_count; /* request */
+ nfs4_verifier co_verf; /* response */
+};
+
+struct nfsd4_create {
+ u32 cr_namelen; /* request */
+ char * cr_name; /* request */
+ u32 cr_type; /* request */
+ union { /* request */
+ struct {
+ u32 namelen;
+ char *name;
+ } link; /* NF4LNK */
+ struct {
+ u32 specdata1;
+ u32 specdata2;
+ } dev; /* NF4BLK, NF4CHR */
+ } u;
+ u32 cr_bmval[3]; /* request */
+ struct iattr cr_iattr; /* request */
+ struct nfsd4_change_info cr_cinfo; /* response */
+ struct nfs4_acl *cr_acl;
+};
+#define cr_linklen u.link.namelen
+#define cr_linkname u.link.name
+#define cr_specdata1 u.dev.specdata1
+#define cr_specdata2 u.dev.specdata2
+
+struct nfsd4_delegreturn {
+ stateid_t dr_stateid;
+};
+
+struct nfsd4_getattr {
+ u32 ga_bmval[3]; /* request */
+ struct svc_fh *ga_fhp; /* response */
+};
+
+struct nfsd4_link {
+ u32 li_namelen; /* request */
+ char * li_name; /* request */
+ struct nfsd4_change_info li_cinfo; /* response */
+};
+
+struct nfsd4_lock_denied {
+ clientid_t ld_clientid;
+ struct nfs4_stateowner *ld_sop;
+ u64 ld_start;
+ u64 ld_length;
+ u32 ld_type;
+};
+
+struct nfsd4_lock {
+ /* request */
+ u32 lk_type;
+ u32 lk_reclaim; /* boolean */
+ u64 lk_offset;
+ u64 lk_length;
+ u32 lk_is_new;
+ union {
+ struct {
+ u32 open_seqid;
+ stateid_t open_stateid;
+ u32 lock_seqid;
+ clientid_t clientid;
+ struct xdr_netobj owner;
+ } new;
+ struct {
+ stateid_t lock_stateid;
+ u32 lock_seqid;
+ } old;
+ } v;
+
+ /* response */
+ union {
+ struct {
+ stateid_t stateid;
+ } ok;
+ struct nfsd4_lock_denied denied;
+ } u;
+ /* The lk_replay_owner is the open owner in the open_to_lock_owner
+ * case and the lock owner otherwise: */
+ struct nfs4_stateowner *lk_replay_owner;
+};
+#define lk_new_open_seqid v.new.open_seqid
+#define lk_new_open_stateid v.new.open_stateid
+#define lk_new_lock_seqid v.new.lock_seqid
+#define lk_new_clientid v.new.clientid
+#define lk_new_owner v.new.owner
+#define lk_old_lock_stateid v.old.lock_stateid
+#define lk_old_lock_seqid v.old.lock_seqid
+
+#define lk_rflags u.ok.rflags
+#define lk_resp_stateid u.ok.stateid
+#define lk_denied u.denied
+
+
+struct nfsd4_lockt {
+ u32 lt_type;
+ clientid_t lt_clientid;
+ struct xdr_netobj lt_owner;
+ u64 lt_offset;
+ u64 lt_length;
+ struct nfs4_stateowner * lt_stateowner;
+ struct nfsd4_lock_denied lt_denied;
+};
+
+
+struct nfsd4_locku {
+ u32 lu_type;
+ u32 lu_seqid;
+ stateid_t lu_stateid;
+ u64 lu_offset;
+ u64 lu_length;
+ struct nfs4_stateowner *lu_stateowner;
+};
+
+
+struct nfsd4_lookup {
+ u32 lo_len; /* request */
+ char * lo_name; /* request */
+};
+
+struct nfsd4_putfh {
+ u32 pf_fhlen; /* request */
+ char *pf_fhval; /* request */
+};
+
+struct nfsd4_open {
+ u32 op_claim_type; /* request */
+ struct xdr_netobj op_fname; /* request - everything but CLAIM_PREV */
+ u32 op_delegate_type; /* request - CLAIM_PREV only */
+ stateid_t op_delegate_stateid; /* request - response */
+ u32 op_create; /* request */
+ u32 op_createmode; /* request */
+ u32 op_bmval[3]; /* request */
+ struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+ nfs4_verifier verf; /* EXCLUSIVE4 */
+ clientid_t op_clientid; /* request */
+ struct xdr_netobj op_owner; /* request */
+ u32 op_seqid; /* request */
+ u32 op_share_access; /* request */
+ u32 op_share_deny; /* request */
+ stateid_t op_stateid; /* response */
+ u32 op_recall; /* recall */
+ struct nfsd4_change_info op_cinfo; /* response */
+ u32 op_rflags; /* response */
+ int op_truncate; /* used during processing */
+ struct nfs4_stateowner *op_stateowner; /* used during processing */
+ struct nfs4_acl *op_acl;
+};
+#define op_iattr iattr
+#define op_verf verf
+
+struct nfsd4_open_confirm {
+ stateid_t oc_req_stateid /* request */;
+ u32 oc_seqid /* request */;
+ stateid_t oc_resp_stateid /* response */;
+ struct nfs4_stateowner * oc_stateowner; /* response */
+};
+
+struct nfsd4_open_downgrade {
+ stateid_t od_stateid;
+ u32 od_seqid;
+ u32 od_share_access;
+ u32 od_share_deny;
+ struct nfs4_stateowner *od_stateowner;
+};
+
+
+struct nfsd4_read {
+ stateid_t rd_stateid; /* request */
+ u64 rd_offset; /* request */
+ u32 rd_length; /* request */
+ int rd_vlen;
+ struct file *rd_filp;
+
+ struct svc_rqst *rd_rqstp; /* response */
+ struct svc_fh * rd_fhp; /* response */
+};
+
+struct nfsd4_readdir {
+ u64 rd_cookie; /* request */
+ nfs4_verifier rd_verf; /* request */
+ u32 rd_dircount; /* request */
+ u32 rd_maxcount; /* request */
+ u32 rd_bmval[3]; /* request */
+ struct svc_rqst *rd_rqstp; /* response */
+ struct svc_fh * rd_fhp; /* response */
+
+ struct readdir_cd common;
+ __be32 * buffer;
+ int buflen;
+ __be32 * offset;
+};
+
+struct nfsd4_release_lockowner {
+ clientid_t rl_clientid;
+ struct xdr_netobj rl_owner;
+};
+struct nfsd4_readlink {
+ struct svc_rqst *rl_rqstp; /* request */
+ struct svc_fh * rl_fhp; /* request */
+};
+
+struct nfsd4_remove {
+ u32 rm_namelen; /* request */
+ char * rm_name; /* request */
+ struct nfsd4_change_info rm_cinfo; /* response */
+};
+
+struct nfsd4_rename {
+ u32 rn_snamelen; /* request */
+ char * rn_sname; /* request */
+ u32 rn_tnamelen; /* request */
+ char * rn_tname; /* request */
+ struct nfsd4_change_info rn_sinfo; /* response */
+ struct nfsd4_change_info rn_tinfo; /* response */
+};
+
+struct nfsd4_secinfo {
+ u32 si_namelen; /* request */
+ char *si_name; /* request */
+ struct svc_export *si_exp; /* response */
+};
+
+struct nfsd4_setattr {
+ stateid_t sa_stateid; /* request */
+ u32 sa_bmval[3]; /* request */
+ struct iattr sa_iattr; /* request */
+ struct nfs4_acl *sa_acl;
+};
+
+struct nfsd4_setclientid {
+ nfs4_verifier se_verf; /* request */
+ u32 se_namelen; /* request */
+ char * se_name; /* request */
+ u32 se_callback_prog; /* request */
+ u32 se_callback_netid_len; /* request */
+ char * se_callback_netid_val; /* request */
+ u32 se_callback_addr_len; /* request */
+ char * se_callback_addr_val; /* request */
+ u32 se_callback_ident; /* request */
+ clientid_t se_clientid; /* response */
+ nfs4_verifier se_confirm; /* response */
+};
+
+struct nfsd4_setclientid_confirm {
+ clientid_t sc_clientid;
+ nfs4_verifier sc_confirm;
+};
+
+/* also used for NVERIFY */
+struct nfsd4_verify {
+ u32 ve_bmval[3]; /* request */
+ u32 ve_attrlen; /* request */
+ char * ve_attrval; /* request */
+};
+
+struct nfsd4_write {
+ stateid_t wr_stateid; /* request */
+ u64 wr_offset; /* request */
+ u32 wr_stable_how; /* request */
+ u32 wr_buflen; /* request */
+ int wr_vlen;
+
+ u32 wr_bytes_written; /* response */
+ u32 wr_how_written; /* response */
+ nfs4_verifier wr_verifier; /* response */
+};
+
+struct nfsd4_exchange_id {
+ nfs4_verifier verifier;
+ struct xdr_netobj clname;
+ u32 flags;
+ clientid_t clientid;
+ u32 seqid;
+ int spa_how;
+};
+
+struct nfsd4_sequence {
+ struct nfs4_sessionid sessionid; /* request/response */
+ u32 seqid; /* request/response */
+ u32 slotid; /* request/response */
+ u32 maxslots; /* request/response */
+ u32 cachethis; /* request */
+#if 0
+ u32 target_maxslots; /* response */
+ u32 status_flags; /* response */
+#endif /* not yet */
+};
+
+struct nfsd4_destroy_session {
+ struct nfs4_sessionid sessionid;
+};
+
+struct nfsd4_op {
+ int opnum;
+ __be32 status;
+ union {
+ struct nfsd4_access access;
+ struct nfsd4_close close;
+ struct nfsd4_commit commit;
+ struct nfsd4_create create;
+ struct nfsd4_delegreturn delegreturn;
+ struct nfsd4_getattr getattr;
+ struct svc_fh * getfh;
+ struct nfsd4_link link;
+ struct nfsd4_lock lock;
+ struct nfsd4_lockt lockt;
+ struct nfsd4_locku locku;
+ struct nfsd4_lookup lookup;
+ struct nfsd4_verify nverify;
+ struct nfsd4_open open;
+ struct nfsd4_open_confirm open_confirm;
+ struct nfsd4_open_downgrade open_downgrade;
+ struct nfsd4_putfh putfh;
+ struct nfsd4_read read;
+ struct nfsd4_readdir readdir;
+ struct nfsd4_readlink readlink;
+ struct nfsd4_remove remove;
+ struct nfsd4_rename rename;
+ clientid_t renew;
+ struct nfsd4_secinfo secinfo;
+ struct nfsd4_setattr setattr;
+ struct nfsd4_setclientid setclientid;
+ struct nfsd4_setclientid_confirm setclientid_confirm;
+ struct nfsd4_verify verify;
+ struct nfsd4_write write;
+ struct nfsd4_release_lockowner release_lockowner;
+
+ /* NFSv4.1 */
+ struct nfsd4_exchange_id exchange_id;
+ struct nfsd4_create_session create_session;
+ struct nfsd4_destroy_session destroy_session;
+ struct nfsd4_sequence sequence;
+ } u;
+ struct nfs4_replay * replay;
+};
+
+struct nfsd4_compoundargs {
+ /* scratch variables for XDR decode */
+ __be32 * p;
+ __be32 * end;
+ struct page ** pagelist;
+ int pagelen;
+ __be32 tmp[8];
+ __be32 * tmpp;
+ struct tmpbuf {
+ struct tmpbuf *next;
+ void (*release)(const void *);
+ void *buf;
+ } *to_free;
+
+ struct svc_rqst *rqstp;
+
+ u32 taglen;
+ char * tag;
+ u32 minorversion;
+ u32 opcnt;
+ struct nfsd4_op *ops;
+ struct nfsd4_op iops[8];
+};
+
+struct nfsd4_compoundres {
+ /* scratch variables for XDR encode */
+ __be32 * p;
+ __be32 * end;
+ struct xdr_buf * xbuf;
+ struct svc_rqst * rqstp;
+
+ u32 taglen;
+ char * tag;
+ u32 opcnt;
+ __be32 * tagp; /* tag, opcount encode location */
+ struct nfsd4_compound_state cstate;
+};
+
+static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
+{
+ struct nfsd4_compoundargs *args = resp->rqstp->rq_argp;
+ return resp->opcnt == 1 && args->ops[0].opnum == OP_SEQUENCE;
+}
+
+static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
+{
+ return !resp->cstate.slot->sl_cachethis || nfsd4_is_solo_sequence(resp);
+}
+
+#define NFS4_SVC_XDRSIZE sizeof(struct nfsd4_compoundargs)
+
+static inline void
+set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
+{
+ BUG_ON(!fhp->fh_pre_saved || !fhp->fh_post_saved);
+ cinfo->atomic = 1;
+ cinfo->change_supported = IS_I_VERSION(fhp->fh_dentry->d_inode);
+ if (cinfo->change_supported) {
+ cinfo->before_change = fhp->fh_pre_change;
+ cinfo->after_change = fhp->fh_post_change;
+ } else {
+ cinfo->before_ctime_sec = fhp->fh_pre_ctime.tv_sec;
+ cinfo->before_ctime_nsec = fhp->fh_pre_ctime.tv_nsec;
+ cinfo->after_ctime_sec = fhp->fh_post_attr.ctime.tv_sec;
+ cinfo->after_ctime_nsec = fhp->fh_post_attr.ctime.tv_nsec;
+ }
+}
+
+int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
+int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
+ struct nfsd4_compoundargs *);
+int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
+ struct nfsd4_compoundres *);
+void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
+void nfsd4_encode_replay(struct nfsd4_compoundres *resp, struct nfsd4_op *op);
+__be32 nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
+ struct dentry *dentry, __be32 *buffer, int *countp,
+ u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_setclientid *setclid);
+extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_setclientid_confirm *setclientid_confirm);
+extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp);
+extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
+ struct nfsd4_sequence *seq);
+extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+struct nfsd4_exchange_id *);
+ extern __be32 nfsd4_create_session(struct svc_rqst *,
+ struct nfsd4_compound_state *,
+ struct nfsd4_create_session *);
+extern __be32 nfsd4_sequence(struct svc_rqst *,
+ struct nfsd4_compound_state *,
+ struct nfsd4_sequence *);
+extern __be32 nfsd4_destroy_session(struct svc_rqst *,
+ struct nfsd4_compound_state *,
+ struct nfsd4_destroy_session *);
+extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
+ struct nfsd4_open *open);
+extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
+ struct svc_fh *current_fh, struct nfsd4_open *open);
+extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc);
+extern __be32 nfsd4_close(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_close *close);
+extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_open_downgrade *od);
+extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+ struct nfsd4_lock *lock);
+extern __be32 nfsd4_lockt(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_lockt *lockt);
+extern __be32 nfsd4_locku(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_locku *locku);
+extern __be32
+nfsd4_release_lockowner(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *,
+ struct nfsd4_release_lockowner *rlockowner);
+extern void nfsd4_release_compoundargs(struct nfsd4_compoundargs *);
+extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr);
+extern __be32 nfsd4_renew(struct svc_rqst *rqstp,
+ struct nfsd4_compound_state *, clientid_t *clid);
+#endif
+
+/*
+ * Local variables:
+ * c-basic-offset: 8
+ * End:
+ */
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 5403b3ef3a4..8173faee31e 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1118,8 +1118,7 @@ nilfs_get_sb(struct file_system_type *fs_type, int flags,
/* Abandoning the newly allocated superblock */
mutex_unlock(&nilfs->ns_mount_mutex);
put_nilfs(nilfs);
- up_write(&s->s_umount);
- deactivate_super(s);
+ deactivate_locked_super(s);
/*
* deactivate_super() invokes close_bdev_exclusive().
* We must finish all post-cleaning before this call;
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 5ef5f365a5c..8271cf05c95 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -646,6 +646,7 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
struct fsnotify_group *group;
struct user_struct *user;
struct file *filp;
+ struct path path;
int fd, ret;
/* Check the IN_* constants for consistency. */
@@ -659,12 +660,6 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
if (fd < 0)
return fd;
- filp = get_empty_filp();
- if (!filp) {
- ret = -ENFILE;
- goto out_put_fd;
- }
-
user = get_current_user();
if (unlikely(atomic_read(&user->inotify_devs) >=
inotify_max_user_instances)) {
@@ -679,24 +674,28 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
goto out_free_uid;
}
- filp->f_op = &inotify_fops;
- filp->f_path.mnt = mntget(inotify_mnt);
- filp->f_path.dentry = dget(inotify_mnt->mnt_root);
- filp->f_mapping = filp->f_path.dentry->d_inode->i_mapping;
- filp->f_mode = FMODE_READ;
+ atomic_inc(&user->inotify_devs);
+
+ path.mnt = inotify_mnt;
+ path.dentry = inotify_mnt->mnt_root;
+ path_get(&path);
+ filp = alloc_file(&path, FMODE_READ, &inotify_fops);
+ if (!filp)
+ goto Enfile;
+
filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
filp->private_data = group;
- atomic_inc(&user->inotify_devs);
-
fd_install(fd, filp);
return fd;
+Enfile:
+ ret = -ENFILE;
+ path_put(&path);
+ atomic_dec(&user->inotify_devs);
out_free_uid:
free_uid(user);
- put_filp(filp);
-out_put_fd:
put_unused_fd(fd);
return ret;
}
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index fbeaec76210..e3e47415d85 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -331,13 +331,14 @@ cleanup:
return ret;
}
-static size_t ocfs2_xattr_list_acl_access(struct inode *inode,
+static size_t ocfs2_xattr_list_acl_access(struct dentry *dentry,
char *list,
size_t list_len,
const char *name,
- size_t name_len)
+ size_t name_len,
+ int type)
{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
@@ -348,13 +349,14 @@ static size_t ocfs2_xattr_list_acl_access(struct inode *inode,
return size;
}
-static size_t ocfs2_xattr_list_acl_default(struct inode *inode,
+static size_t ocfs2_xattr_list_acl_default(struct dentry *dentry,
char *list,
size_t list_len,
const char *name,
- size_t name_len)
+ size_t name_len,
+ int type)
{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
@@ -365,19 +367,19 @@ static size_t ocfs2_xattr_list_acl_default(struct inode *inode,
return size;
}
-static int ocfs2_xattr_get_acl(struct inode *inode,
- int type,
- void *buffer,
- size_t size)
+static int ocfs2_xattr_get_acl(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
struct posix_acl *acl;
int ret;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
return -EOPNOTSUPP;
- acl = ocfs2_get_acl(inode, type);
+ acl = ocfs2_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -388,35 +390,16 @@ static int ocfs2_xattr_get_acl(struct inode *inode,
return ret;
}
-static int ocfs2_xattr_get_acl_access(struct inode *inode,
- const char *name,
- void *buffer,
- size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ocfs2_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int ocfs2_xattr_get_acl_default(struct inode *inode,
- const char *name,
- void *buffer,
- size_t size)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ocfs2_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int ocfs2_xattr_set_acl(struct inode *inode,
- int type,
- const void *value,
- size_t size)
+static int ocfs2_xattr_set_acl(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct posix_acl *acl;
int ret = 0;
+ if (strcmp(name, "") != 0)
+ return -EINVAL;
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
return -EOPNOTSUPP;
@@ -442,38 +425,18 @@ cleanup:
return ret;
}
-static int ocfs2_xattr_set_acl_access(struct inode *inode,
- const char *name,
- const void *value,
- size_t size,
- int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ocfs2_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static int ocfs2_xattr_set_acl_default(struct inode *inode,
- const char *name,
- const void *value,
- size_t size,
- int flags)
-{
- if (strcmp(name, "") != 0)
- return -EINVAL;
- return ocfs2_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
struct xattr_handler ocfs2_xattr_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
.list = ocfs2_xattr_list_acl_access,
- .get = ocfs2_xattr_get_acl_access,
- .set = ocfs2_xattr_set_acl_access,
+ .get = ocfs2_xattr_get_acl,
+ .set = ocfs2_xattr_set_acl,
};
struct xattr_handler ocfs2_xattr_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
.list = ocfs2_xattr_list_acl_default,
- .get = ocfs2_xattr_get_acl_default,
- .set = ocfs2_xattr_set_acl_default,
+ .get = ocfs2_xattr_get_acl,
+ .set = ocfs2_xattr_set_acl,
};
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 7c7198a5bc9..fb4e672579b 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7190,8 +7190,8 @@ int ocfs2_zero_range_for_truncate(struct inode *inode, handle_t *handle,
* wait on them - the truncate_inode_pages() call later will
* do that for us.
*/
- ret = do_sync_mapping_range(inode->i_mapping, range_start,
- range_end - 1, SYNC_FILE_RANGE_WRITE);
+ ret = filemap_fdatawrite_range(inode->i_mapping, range_start,
+ range_end - 1);
if (ret)
mlog_errno(ret);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index deb2b132ae5..3dae4a13f6e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -547,6 +547,9 @@ bail:
*
* called like this: dio->get_blocks(dio->inode, fs_startblk,
* fs_count, map_bh, dio->rw == WRITE);
+ *
+ * Note that we never bother to allocate blocks here, and thus ignore the
+ * create argument.
*/
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
@@ -563,14 +566,6 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
- /*
- * Any write past EOF is not allowed because we'd be extending.
- */
- if (create && (iblock + max_blocks) > inode_blocks) {
- ret = -EIO;
- goto bail;
- }
-
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
@@ -582,15 +577,6 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
goto bail;
}
- if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)) && !p_blkno && create) {
- ocfs2_error(inode->i_sb,
- "Inode %llu has a hole at block %llu\n",
- (unsigned long long)OCFS2_I(inode)->ip_blkno,
- (unsigned long long)iblock);
- ret = -EROFS;
- goto bail;
- }
-
/* We should already CoW the refcounted extent. */
BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED);
/*
@@ -601,20 +587,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
- else {
- /*
- * ocfs2_prepare_inode_for_write() should have caught
- * the case where we'd be filling a hole and triggered
- * a buffered write instead.
- */
- if (create) {
- ret = -EIO;
- mlog_errno(ret);
- goto bail;
- }
-
+ else
clear_buffer_mapped(bh_result);
- }
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index fe3419068df..43c114831c0 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -205,8 +205,6 @@ static int ocfs2_get_xattr_tree_value_root(struct super_block *sb,
int offset,
struct ocfs2_xattr_value_root **xv,
struct buffer_head **bh);
-static int ocfs2_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags);
static inline u16 ocfs2_xattr_buckets_per_cluster(struct ocfs2_super *osb)
{
@@ -6978,9 +6976,9 @@ int ocfs2_init_security_and_acl(struct inode *dir,
ret = ocfs2_init_security_get(inode, dir, &si);
if (!ret) {
- ret = ocfs2_xattr_security_set(inode, si.name,
- si.value, si.value_len,
- XATTR_CREATE);
+ ret = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY,
+ si.name, si.value, si.value_len,
+ XATTR_CREATE);
if (ret) {
mlog_errno(ret);
goto leave;
@@ -7008,9 +7006,9 @@ leave:
/*
* 'security' attributes support
*/
-static size_t ocfs2_xattr_security_list(struct inode *inode, char *list,
+static size_t ocfs2_xattr_security_list(struct dentry *dentry, char *list,
size_t list_size, const char *name,
- size_t name_len)
+ size_t name_len, int type)
{
const size_t prefix_len = XATTR_SECURITY_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -7023,23 +7021,23 @@ static size_t ocfs2_xattr_security_list(struct inode *inode, char *list,
return total_len;
}
-static int ocfs2_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int ocfs2_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_SECURITY, name,
- buffer, size);
+ return ocfs2_xattr_get(dentry->d_inode, OCFS2_XATTR_INDEX_SECURITY,
+ name, buffer, size);
}
-static int ocfs2_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int ocfs2_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, name, value,
- size, flags);
+ return ocfs2_xattr_set(dentry->d_inode, OCFS2_XATTR_INDEX_SECURITY,
+ name, value, size, flags);
}
int ocfs2_init_security_get(struct inode *inode,
@@ -7076,9 +7074,9 @@ struct xattr_handler ocfs2_xattr_security_handler = {
/*
* 'trusted' attributes support
*/
-static size_t ocfs2_xattr_trusted_list(struct inode *inode, char *list,
+static size_t ocfs2_xattr_trusted_list(struct dentry *dentry, char *list,
size_t list_size, const char *name,
- size_t name_len)
+ size_t name_len, int type)
{
const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
@@ -7091,23 +7089,23 @@ static size_t ocfs2_xattr_trusted_list(struct inode *inode, char *list,
return total_len;
}
-static int ocfs2_xattr_trusted_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int ocfs2_xattr_trusted_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_TRUSTED, name,
- buffer, size);
+ return ocfs2_xattr_get(dentry->d_inode, OCFS2_XATTR_INDEX_TRUSTED,
+ name, buffer, size);
}
-static int ocfs2_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int ocfs2_xattr_trusted_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_TRUSTED, name, value,
- size, flags);
+ return ocfs2_xattr_set(dentry->d_inode, OCFS2_XATTR_INDEX_TRUSTED,
+ name, value, size, flags);
}
struct xattr_handler ocfs2_xattr_trusted_handler = {
@@ -7120,13 +7118,13 @@ struct xattr_handler ocfs2_xattr_trusted_handler = {
/*
* 'user' attributes support
*/
-static size_t ocfs2_xattr_user_list(struct inode *inode, char *list,
+static size_t ocfs2_xattr_user_list(struct dentry *dentry, char *list,
size_t list_size, const char *name,
- size_t name_len)
+ size_t name_len, int type)
{
const size_t prefix_len = XATTR_USER_PREFIX_LEN;
const size_t total_len = prefix_len + name_len + 1;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
return 0;
@@ -7139,31 +7137,31 @@ static size_t ocfs2_xattr_user_list(struct inode *inode, char *list,
return total_len;
}
-static int ocfs2_xattr_user_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int ocfs2_xattr_user_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int type)
{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
if (strcmp(name, "") == 0)
return -EINVAL;
if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
return -EOPNOTSUPP;
- return ocfs2_xattr_get(inode, OCFS2_XATTR_INDEX_USER, name,
+ return ocfs2_xattr_get(dentry->d_inode, OCFS2_XATTR_INDEX_USER, name,
buffer, size);
}
-static int ocfs2_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int ocfs2_xattr_user_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
if (strcmp(name, "") == 0)
return -EINVAL;
if (osb->s_mount_opt & OCFS2_MOUNT_NOUSERXATTR)
return -EOPNOTSUPP;
- return ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_USER, name, value,
- size, flags);
+ return ocfs2_xattr_set(dentry->d_inode, OCFS2_XATTR_INDEX_USER,
+ name, value, size, flags);
}
struct xattr_handler ocfs2_xattr_user_handler = {
diff --git a/fs/open.c b/fs/open.c
index b4b31d277f3..ca69241796b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -30,6 +30,9 @@
#include <linux/audit.h>
#include <linux/falloc.h>
#include <linux/fs_struct.h>
+#include <linux/ima.h>
+
+#include "internal.h"
int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
@@ -855,6 +858,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
if (error)
goto cleanup_all;
}
+ ima_counts_get(f);
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
diff --git a/fs/pipe.c b/fs/pipe.c
index ae17d026aaa..43d79da5c57 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -974,7 +974,7 @@ struct file *create_write_pipe(int flags)
int err;
struct inode *inode;
struct file *f;
- struct dentry *dentry;
+ struct path path;
struct qstr name = { .name = "" };
err = -ENFILE;
@@ -983,21 +983,22 @@ struct file *create_write_pipe(int flags)
goto err;
err = -ENOMEM;
- dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name);
- if (!dentry)
+ path.dentry = d_alloc(pipe_mnt->mnt_sb->s_root, &name);
+ if (!path.dentry)
goto err_inode;
+ path.mnt = mntget(pipe_mnt);
- dentry->d_op = &pipefs_dentry_operations;
+ path.dentry->d_op = &pipefs_dentry_operations;
/*
* We dont want to publish this dentry into global dentry hash table.
* We pretend dentry is already hashed, by unsetting DCACHE_UNHASHED
* This permits a working /proc/$pid/fd/XXX on pipes
*/
- dentry->d_flags &= ~DCACHE_UNHASHED;
- d_instantiate(dentry, inode);
+ path.dentry->d_flags &= ~DCACHE_UNHASHED;
+ d_instantiate(path.dentry, inode);
err = -ENFILE;
- f = alloc_file(pipe_mnt, dentry, FMODE_WRITE, &write_pipefifo_fops);
+ f = alloc_file(&path, FMODE_WRITE, &write_pipefifo_fops);
if (!f)
goto err_dentry;
f->f_mapping = inode->i_mapping;
@@ -1009,7 +1010,7 @@ struct file *create_write_pipe(int flags)
err_dentry:
free_pipe_info(inode);
- dput(dentry);
+ path_put(&path);
return ERR_PTR(err);
err_inode:
@@ -1028,20 +1029,14 @@ void free_write_pipe(struct file *f)
struct file *create_read_pipe(struct file *wrf, int flags)
{
- struct file *f = get_empty_filp();
+ /* Grab pipe from the writer */
+ struct file *f = alloc_file(&wrf->f_path, FMODE_READ,
+ &read_pipefifo_fops);
if (!f)
return ERR_PTR(-ENFILE);
- /* Grab pipe from the writer */
- f->f_path = wrf->f_path;
path_get(&wrf->f_path);
- f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
-
- f->f_pos = 0;
f->f_flags = O_RDONLY | (flags & O_NONBLOCK);
- f->f_op = &read_pipefifo_fops;
- f->f_mode = FMODE_READ;
- f->f_version = 0;
return f;
}
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4df4a464a91..18d5cc62d8e 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2266,7 +2266,7 @@ static const struct inode_operations proc_attr_dir_inode_operations = {
#endif
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
@@ -2623,7 +2623,7 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_FAULT_INJECTION
REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
#endif
-#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
+#ifdef CONFIG_ELF_CORE
REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index fa678abc9db..480cb1065ee 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -429,7 +429,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
unsigned int ino;
ino = de->low_ino;
- de_get(de);
+ pde_get(de);
spin_unlock(&proc_subdir_lock);
error = -EINVAL;
inode = proc_get_inode(dir->i_sb, ino, de);
@@ -445,7 +445,7 @@ out_unlock:
return NULL;
}
if (de)
- de_put(de);
+ pde_put(de);
return ERR_PTR(error);
}
@@ -509,17 +509,17 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
struct proc_dir_entry *next;
/* filldir passes info to user space */
- de_get(de);
+ pde_get(de);
spin_unlock(&proc_subdir_lock);
if (filldir(dirent, de->name, de->namelen, filp->f_pos,
de->low_ino, de->mode >> 12) < 0) {
- de_put(de);
+ pde_put(de);
goto out;
}
spin_lock(&proc_subdir_lock);
filp->f_pos++;
next = de->next;
- de_put(de);
+ pde_put(de);
de = next;
} while (de);
spin_unlock(&proc_subdir_lock);
@@ -763,7 +763,7 @@ out:
return NULL;
}
-void free_proc_entry(struct proc_dir_entry *de)
+static void free_proc_entry(struct proc_dir_entry *de)
{
unsigned int ino = de->low_ino;
@@ -777,6 +777,12 @@ void free_proc_entry(struct proc_dir_entry *de)
kfree(de);
}
+void pde_put(struct proc_dir_entry *pde)
+{
+ if (atomic_dec_and_test(&pde->count))
+ free_proc_entry(pde);
+}
+
/*
* Remove a /proc entry and free it if it's not currently in use.
*/
@@ -845,6 +851,5 @@ continue_removing:
WARN(de->subdir, KERN_WARNING "%s: removing non-empty directory "
"'%s/%s', leaking at least '%s'\n", __func__,
de->parent->name, de->name, de->subdir->name);
- if (atomic_dec_and_test(&de->count))
- free_proc_entry(de);
+ pde_put(de);
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d78ade30554..445a02bcaab 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -24,29 +24,6 @@
#include "internal.h"
-struct proc_dir_entry *de_get(struct proc_dir_entry *de)
-{
- atomic_inc(&de->count);
- return de;
-}
-
-/*
- * Decrements the use count and checks for deferred deletion.
- */
-void de_put(struct proc_dir_entry *de)
-{
- if (!atomic_read(&de->count)) {
- printk("de_put: entry %s already free!\n", de->name);
- return;
- }
-
- if (atomic_dec_and_test(&de->count))
- free_proc_entry(de);
-}
-
-/*
- * Decrement the use count of the proc_dir_entry.
- */
static void proc_delete_inode(struct inode *inode)
{
struct proc_dir_entry *de;
@@ -59,7 +36,7 @@ static void proc_delete_inode(struct inode *inode)
/* Let go of any associated proc directory entry */
de = PROC_I(inode)->pde;
if (de)
- de_put(de);
+ pde_put(de);
if (PROC_I(inode)->sysctl)
sysctl_head_put(PROC_I(inode)->sysctl);
clear_inode(inode);
@@ -480,7 +457,7 @@ struct inode *proc_get_inode(struct super_block *sb, unsigned int ino,
}
unlock_new_inode(inode);
} else
- de_put(de);
+ pde_put(de);
return inode;
}
@@ -495,7 +472,7 @@ int proc_fill_super(struct super_block *s)
s->s_op = &proc_sops;
s->s_time_gran = 1;
- de_get(&proc_root);
+ pde_get(&proc_root);
root_inode = proc_get_inode(s, PROC_ROOT_INO, &proc_root);
if (!root_inode)
goto out_no_root;
@@ -509,6 +486,6 @@ int proc_fill_super(struct super_block *s)
out_no_root:
printk("proc_read_super: get root inode failed\n");
iput(root_inode);
- de_put(&proc_root);
+ pde_put(&proc_root);
return -ENOMEM;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 753ca37002c..1f24a3eddd1 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -61,8 +61,6 @@ extern const struct file_operations proc_pagemap_operations;
extern const struct file_operations proc_net_operations;
extern const struct inode_operations proc_net_inode_operations;
-void free_proc_entry(struct proc_dir_entry *de);
-
void proc_init_inodecache(void);
static inline struct pid *proc_pid(struct inode *inode)
@@ -101,8 +99,12 @@ unsigned long task_vsize(struct mm_struct *);
int task_statm(struct mm_struct *, int *, int *, int *, int *);
void task_mem(struct seq_file *, struct mm_struct *);
-struct proc_dir_entry *de_get(struct proc_dir_entry *de);
-void de_put(struct proc_dir_entry *de);
+static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
+{
+ atomic_inc(&pde->count);
+ return pde;
+}
+void pde_put(struct proc_dir_entry *pde);
extern struct vfsmount *proc_mnt;
int proc_fill_super(struct super_block *);
diff --git a/fs/qnx4/bitmap.c b/fs/qnx4/bitmap.c
index 32f5d131a64..22e0d60e53e 100644
--- a/fs/qnx4/bitmap.c
+++ b/fs/qnx4/bitmap.c
@@ -17,13 +17,6 @@
#include <linux/bitops.h>
#include "qnx4.h"
-#if 0
-int qnx4_new_block(struct super_block *sb)
-{
- return 0;
-}
-#endif /* 0 */
-
static void count_bits(register const char *bmPart, register int size,
int *const tf)
{
@@ -35,22 +28,7 @@ static void count_bits(register const char *bmPart, register int size,
}
do {
b = *bmPart++;
- if ((b & 1) == 0)
- tot++;
- if ((b & 2) == 0)
- tot++;
- if ((b & 4) == 0)
- tot++;
- if ((b & 8) == 0)
- tot++;
- if ((b & 16) == 0)
- tot++;
- if ((b & 32) == 0)
- tot++;
- if ((b & 64) == 0)
- tot++;
- if ((b & 128) == 0)
- tot++;
+ tot += 8 - hweight8(b);
size--;
} while (size != 0);
*tf = tot;
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 449f5a66dd3..ebf3440d28c 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -64,25 +64,7 @@ static struct buffer_head *qnx4_getblk(struct inode *inode, int nr,
result = sb_getblk(inode->i_sb, nr);
return result;
}
- if (!create) {
- return NULL;
- }
-#if 0
- tmp = qnx4_new_block(inode->i_sb);
- if (!tmp) {
- return NULL;
- }
- result = sb_getblk(inode->i_sb, tmp);
- if (tst) {
- qnx4_free_block(inode->i_sb, tmp);
- brelse(result);
- goto repeat;
- }
- tst = tmp;
-#endif
- inode->i_ctime = CURRENT_TIME_SEC;
- mark_inode_dirty(inode);
- return result;
+ return NULL;
}
struct buffer_head *qnx4_bread(struct inode *inode, int block, int create)
@@ -113,8 +95,6 @@ static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_h
if ( phys ) {
// logical block is before EOF
map_bh(bh, inode->i_sb, phys);
- } else if ( create ) {
- // to be done.
}
return 0;
}
diff --git a/fs/reiserfs/Makefile b/fs/reiserfs/Makefile
index 6a9e30c041d..792b3cb2cd1 100644
--- a/fs/reiserfs/Makefile
+++ b/fs/reiserfs/Makefile
@@ -7,7 +7,11 @@ obj-$(CONFIG_REISERFS_FS) += reiserfs.o
reiserfs-objs := bitmap.o do_balan.o namei.o inode.o file.o dir.o fix_node.o \
super.o prints.o objectid.o lbalance.o ibalance.o stree.o \
hashes.o tail_conversion.o journal.o resize.o \
- item_ops.o ioctl.o procfs.o xattr.o lock.o
+ item_ops.o ioctl.o xattr.o lock.o
+
+ifeq ($(CONFIG_REISERFS_PROC_INFO),y)
+reiserfs-objs += procfs.o
+endif
ifeq ($(CONFIG_REISERFS_FS_XATTR),y)
reiserfs-objs += xattr_user.o xattr_trusted.o
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 9229e5514a4..7a9981196c1 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -17,8 +17,6 @@
#include <linux/init.h>
#include <linux/proc_fs.h>
-#ifdef CONFIG_REISERFS_PROC_INFO
-
/*
* LOCKING:
*
@@ -48,14 +46,6 @@ static int show_version(struct seq_file *m, struct super_block *sb)
return 0;
}
-int reiserfs_global_version_in_proc(char *buffer, char **start, off_t offset,
- int count, int *eof, void *data)
-{
- *start = buffer;
- *eof = 1;
- return 0;
-}
-
#define SF( x ) ( r -> x )
#define SFP( x ) SF( s_proc_info_data.x )
#define SFPL( x ) SFP( x[ level ] )
@@ -538,19 +528,6 @@ int reiserfs_proc_info_done(struct super_block *sb)
return 0;
}
-struct proc_dir_entry *reiserfs_proc_register_global(char *name,
- read_proc_t * func)
-{
- return (proc_info_root) ? create_proc_read_entry(name, 0,
- proc_info_root,
- func, NULL) : NULL;
-}
-
-void reiserfs_proc_unregister_global(const char *name)
-{
- remove_proc_entry(name, proc_info_root);
-}
-
int reiserfs_proc_info_global_init(void)
{
if (proc_info_root == NULL) {
@@ -572,48 +549,6 @@ int reiserfs_proc_info_global_done(void)
}
return 0;
}
-
-/* REISERFS_PROC_INFO */
-#else
-
-int reiserfs_proc_info_init(struct super_block *sb)
-{
- return 0;
-}
-int reiserfs_proc_info_done(struct super_block *sb)
-{
- return 0;
-}
-
-struct proc_dir_entry *reiserfs_proc_register_global(char *name,
- read_proc_t * func)
-{
- return NULL;
-}
-
-void reiserfs_proc_unregister_global(const char *name)
-{;
-}
-
-int reiserfs_proc_info_global_init(void)
-{
- return 0;
-}
-int reiserfs_proc_info_global_done(void)
-{
- return 0;
-}
-
-int reiserfs_global_version_in_proc(char *buffer, char **start,
- off_t offset,
- int count, int *eof, void *data)
-{
- return 0;
-}
-
-/* REISERFS_PROC_INFO */
-#endif
-
/*
* Revision 1.1.8.2 2001/07/15 17:08:42 god
* . use get_super() in procfs.c
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 339b0baf2af..b4a7dd03bdb 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2222,8 +2222,6 @@ static int __init init_reiserfs_fs(void)
}
reiserfs_proc_info_global_init();
- reiserfs_proc_register_global("version",
- reiserfs_global_version_in_proc);
ret = register_filesystem(&reiserfs_fs_type);
@@ -2231,7 +2229,6 @@ static int __init init_reiserfs_fs(void)
return 0;
}
- reiserfs_proc_unregister_global("version");
reiserfs_proc_info_global_done();
destroy_inodecache();
@@ -2240,7 +2237,6 @@ static int __init init_reiserfs_fs(void)
static void __exit exit_reiserfs_fs(void)
{
- reiserfs_proc_unregister_global("version");
reiserfs_proc_info_global_done();
unregister_filesystem(&reiserfs_fs_type);
destroy_inodecache();
diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c
index 58aa8e75f7f..8c7033a8b67 100644
--- a/fs/reiserfs/xattr.c
+++ b/fs/reiserfs/xattr.c
@@ -48,6 +48,7 @@
#include <net/checksum.h>
#include <linux/stat.h>
#include <linux/quotaops.h>
+#include <linux/security.h>
#define PRIVROOT_NAME ".reiserfs_priv"
#define XAROOT_NAME "xattrs"
@@ -726,15 +727,14 @@ ssize_t
reiserfs_getxattr(struct dentry * dentry, const char *name, void *buffer,
size_t size)
{
- struct inode *inode = dentry->d_inode;
struct xattr_handler *handler;
- handler = find_xattr_handler_prefix(inode->i_sb->s_xattr, name);
+ handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
- if (!handler || get_inode_sd_version(inode) == STAT_DATA_V1)
+ if (!handler || get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
- return handler->get(inode, name, buffer, size);
+ return handler->get(dentry, name, buffer, size, handler->flags);
}
/*
@@ -746,15 +746,14 @@ int
reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags)
{
- struct inode *inode = dentry->d_inode;
struct xattr_handler *handler;
- handler = find_xattr_handler_prefix(inode->i_sb->s_xattr, name);
+ handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
- if (!handler || get_inode_sd_version(inode) == STAT_DATA_V1)
+ if (!handler || get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
- return handler->set(inode, name, value, size, flags);
+ return handler->set(dentry, name, value, size, flags, handler->flags);
}
/*
@@ -764,21 +763,20 @@ reiserfs_setxattr(struct dentry *dentry, const char *name, const void *value,
*/
int reiserfs_removexattr(struct dentry *dentry, const char *name)
{
- struct inode *inode = dentry->d_inode;
struct xattr_handler *handler;
- handler = find_xattr_handler_prefix(inode->i_sb->s_xattr, name);
+ handler = find_xattr_handler_prefix(dentry->d_sb->s_xattr, name);
- if (!handler || get_inode_sd_version(inode) == STAT_DATA_V1)
+ if (!handler || get_inode_sd_version(dentry->d_inode) == STAT_DATA_V1)
return -EOPNOTSUPP;
- return handler->set(inode, name, NULL, 0, XATTR_REPLACE);
+ return handler->set(dentry, name, NULL, 0, XATTR_REPLACE, handler->flags);
}
struct listxattr_buf {
size_t size;
size_t pos;
char *buf;
- struct inode *inode;
+ struct dentry *dentry;
};
static int listxattr_filler(void *buf, const char *name, int namelen,
@@ -789,17 +787,19 @@ static int listxattr_filler(void *buf, const char *name, int namelen,
if (name[0] != '.' ||
(namelen != 1 && (name[1] != '.' || namelen != 2))) {
struct xattr_handler *handler;
- handler = find_xattr_handler_prefix(b->inode->i_sb->s_xattr,
+ handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr,
name);
if (!handler) /* Unsupported xattr name */
return 0;
if (b->buf) {
- size = handler->list(b->inode, b->buf + b->pos,
- b->size, name, namelen);
+ size = handler->list(b->dentry, b->buf + b->pos,
+ b->size, name, namelen,
+ handler->flags);
if (size > b->size)
return -ERANGE;
} else {
- size = handler->list(b->inode, NULL, 0, name, namelen);
+ size = handler->list(b->dentry, NULL, 0, name,
+ namelen, handler->flags);
}
b->pos += size;
@@ -820,7 +820,7 @@ ssize_t reiserfs_listxattr(struct dentry * dentry, char *buffer, size_t size)
int err = 0;
loff_t pos = 0;
struct listxattr_buf buf = {
- .inode = dentry->d_inode,
+ .dentry = dentry,
.buf = buffer,
.size = buffer ? size : 0,
};
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 35d6e672a27..cc32e6ada67 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -15,8 +15,10 @@ static int reiserfs_set_acl(struct reiserfs_transaction_handle *th,
struct posix_acl *acl);
static int
-xattr_set_acl(struct inode *inode, int type, const void *value, size_t size)
+posix_acl_set(struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
struct posix_acl *acl;
int error, error2;
struct reiserfs_transaction_handle th;
@@ -60,15 +62,16 @@ xattr_set_acl(struct inode *inode, int type, const void *value, size_t size)
}
static int
-xattr_get_acl(struct inode *inode, int type, void *buffer, size_t size)
+posix_acl_get(struct dentry *dentry, const char *name, void *buffer,
+ size_t size, int type)
{
struct posix_acl *acl;
int error;
- if (!reiserfs_posixacl(inode->i_sb))
+ if (!reiserfs_posixacl(dentry->d_sb))
return -EOPNOTSUPP;
- acl = reiserfs_get_acl(inode, type);
+ acl = reiserfs_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -482,30 +485,12 @@ int reiserfs_acl_chmod(struct inode *inode)
return error;
}
-static int
-posix_acl_access_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS) - 1)
- return -EINVAL;
- return xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
-}
-
-static int
-posix_acl_access_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strlen(name) != sizeof(POSIX_ACL_XATTR_ACCESS) - 1)
- return -EINVAL;
- return xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
-}
-
-static size_t posix_acl_access_list(struct inode *inode, char *list,
+static size_t posix_acl_access_list(struct dentry *dentry, char *list,
size_t list_size, const char *name,
- size_t name_len)
+ size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
- if (!reiserfs_posixacl(inode->i_sb))
+ if (!reiserfs_posixacl(dentry->d_sb))
return 0;
if (list && size <= list_size)
memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
@@ -514,35 +499,18 @@ static size_t posix_acl_access_list(struct inode *inode, char *list,
struct xattr_handler reiserfs_posix_acl_access_handler = {
.prefix = POSIX_ACL_XATTR_ACCESS,
- .get = posix_acl_access_get,
- .set = posix_acl_access_set,
+ .flags = ACL_TYPE_ACCESS,
+ .get = posix_acl_get,
+ .set = posix_acl_set,
.list = posix_acl_access_list,
};
-static int
-posix_acl_default_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
-{
- if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT) - 1)
- return -EINVAL;
- return xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
-}
-
-static int
-posix_acl_default_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- if (strlen(name) != sizeof(POSIX_ACL_XATTR_DEFAULT) - 1)
- return -EINVAL;
- return xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
-}
-
-static size_t posix_acl_default_list(struct inode *inode, char *list,
+static size_t posix_acl_default_list(struct dentry *dentry, char *list,
size_t list_size, const char *name,
- size_t name_len)
+ size_t name_len, int type)
{
const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
- if (!reiserfs_posixacl(inode->i_sb))
+ if (!reiserfs_posixacl(dentry->d_sb))
return 0;
if (list && size <= list_size)
memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
@@ -551,7 +519,8 @@ static size_t posix_acl_default_list(struct inode *inode, char *list,
struct xattr_handler reiserfs_posix_acl_default_handler = {
.prefix = POSIX_ACL_XATTR_DEFAULT,
- .get = posix_acl_default_get,
- .set = posix_acl_default_set,
+ .flags = ACL_TYPE_DEFAULT,
+ .get = posix_acl_get,
+ .set = posix_acl_set,
.list = posix_acl_default_list,
};
diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c
index a92c8792c0f..d8b5bfcbdd3 100644
--- a/fs/reiserfs/xattr_security.c
+++ b/fs/reiserfs/xattr_security.c
@@ -8,36 +8,37 @@
#include <asm/uaccess.h>
static int
-security_get(struct inode *inode, const char *name, void *buffer, size_t size)
+security_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
+ int handler_flags)
{
if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
return -EINVAL;
- if (IS_PRIVATE(inode))
+ if (IS_PRIVATE(dentry->d_inode))
return -EPERM;
- return reiserfs_xattr_get(inode, name, buffer, size);
+ return reiserfs_xattr_get(dentry->d_inode, name, buffer, size);
}
static int
-security_set(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+security_set(struct dentry *dentry, const char *name, const void *buffer,
+ size_t size, int flags, int handler_flags)
{
if (strlen(name) < sizeof(XATTR_SECURITY_PREFIX))
return -EINVAL;
- if (IS_PRIVATE(inode))
+ if (IS_PRIVATE(dentry->d_inode))
return -EPERM;
- return reiserfs_xattr_set(inode, name, buffer, size, flags);
+ return reiserfs_xattr_set(dentry->d_inode, name, buffer, size, flags);
}
-static size_t security_list(struct inode *inode, char *list, size_t list_len,
- const char *name, size_t namelen)
+static size_t security_list(struct dentry *dentry, char *list, size_t list_len,
+ const char *name, size_t namelen, int handler_flags)
{
const size_t len = namelen + 1;
- if (IS_PRIVATE(inode))
+ if (IS_PRIVATE(dentry->d_inode))
return 0;
if (list && len <= list_len) {
diff --git a/fs/reiserfs/xattr_trusted.c b/fs/reiserfs/xattr_trusted.c
index a865042f75e..5b08aaca3da 100644
--- a/fs/reiserfs/xattr_trusted.c
+++ b/fs/reiserfs/xattr_trusted.c
@@ -8,36 +8,37 @@
#include <asm/uaccess.h>
static int
-trusted_get(struct inode *inode, const char *name, void *buffer, size_t size)
+trusted_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
+ int handler_flags)
{
if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
return -EINVAL;
- if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+ if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(dentry->d_inode))
return -EPERM;
- return reiserfs_xattr_get(inode, name, buffer, size);
+ return reiserfs_xattr_get(dentry->d_inode, name, buffer, size);
}
static int
-trusted_set(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+trusted_set(struct dentry *dentry, const char *name, const void *buffer,
+ size_t size, int flags, int handler_flags)
{
if (strlen(name) < sizeof(XATTR_TRUSTED_PREFIX))
return -EINVAL;
- if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+ if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(dentry->d_inode))
return -EPERM;
- return reiserfs_xattr_set(inode, name, buffer, size, flags);
+ return reiserfs_xattr_set(dentry->d_inode, name, buffer, size, flags);
}
-static size_t trusted_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t trusted_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int handler_flags)
{
const size_t len = name_len + 1;
- if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(inode))
+ if (!capable(CAP_SYS_ADMIN) || IS_PRIVATE(dentry->d_inode))
return 0;
if (list && len <= list_size) {
diff --git a/fs/reiserfs/xattr_user.c b/fs/reiserfs/xattr_user.c
index e3238dc4f3d..75d59c49b91 100644
--- a/fs/reiserfs/xattr_user.c
+++ b/fs/reiserfs/xattr_user.c
@@ -7,34 +7,35 @@
#include <asm/uaccess.h>
static int
-user_get(struct inode *inode, const char *name, void *buffer, size_t size)
+user_get(struct dentry *dentry, const char *name, void *buffer, size_t size,
+ int handler_flags)
{
if (strlen(name) < sizeof(XATTR_USER_PREFIX))
return -EINVAL;
- if (!reiserfs_xattrs_user(inode->i_sb))
+ if (!reiserfs_xattrs_user(dentry->d_sb))
return -EOPNOTSUPP;
- return reiserfs_xattr_get(inode, name, buffer, size);
+ return reiserfs_xattr_get(dentry->d_inode, name, buffer, size);
}
static int
-user_set(struct inode *inode, const char *name, const void *buffer,
- size_t size, int flags)
+user_set(struct dentry *dentry, const char *name, const void *buffer,
+ size_t size, int flags, int handler_flags)
{
if (strlen(name) < sizeof(XATTR_USER_PREFIX))
return -EINVAL;
- if (!reiserfs_xattrs_user(inode->i_sb))
+ if (!reiserfs_xattrs_user(dentry->d_sb))
return -EOPNOTSUPP;
- return reiserfs_xattr_set(inode, name, buffer, size, flags);
+ return reiserfs_xattr_set(dentry->d_inode, name, buffer, size, flags);
}
-static size_t user_list(struct inode *inode, char *list, size_t list_size,
- const char *name, size_t name_len)
+static size_t user_list(struct dentry *dentry, char *list, size_t list_size,
+ const char *name, size_t name_len, int handler_flags)
{
const size_t len = name_len + 1;
- if (!reiserfs_xattrs_user(inode->i_sb))
+ if (!reiserfs_xattrs_user(dentry->d_sb))
return 0;
if (list && len <= list_size) {
memcpy(list, name, name_len);
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 6f671f1ac27..22af68f8b68 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -70,13 +70,13 @@ static inline unsigned long ufs_dir_pages(struct inode *inode)
return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
}
-ino_t ufs_inode_by_name(struct inode *dir, struct dentry *dentry)
+ino_t ufs_inode_by_name(struct inode *dir, struct qstr *qstr)
{
ino_t res = 0;
struct ufs_dir_entry *de;
struct page *page;
- de = ufs_find_entry(dir, dentry, &page);
+ de = ufs_find_entry(dir, qstr, &page);
if (de) {
res = fs32_to_cpu(dir->i_sb, de->d_ino);
ufs_put_page(page);
@@ -249,12 +249,12 @@ struct ufs_dir_entry *ufs_dotdot(struct inode *dir, struct page **p)
* (as a parameter - res_dir). Page is returned mapped and unlocked.
* Entry is guaranteed to be valid.
*/
-struct ufs_dir_entry *ufs_find_entry(struct inode *dir, struct dentry *dentry,
+struct ufs_dir_entry *ufs_find_entry(struct inode *dir, struct qstr *qstr,
struct page **res_page)
{
struct super_block *sb = dir->i_sb;
- const char *name = dentry->d_name.name;
- int namelen = dentry->d_name.len;
+ const char *name = qstr->name;
+ int namelen = qstr->len;
unsigned reclen = UFS_DIR_REC_LEN(namelen);
unsigned long start, n;
unsigned long npages = ufs_dir_pages(dir);
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 23119fe7ad6..4c26d9e8bc9 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -56,7 +56,7 @@ static struct dentry *ufs_lookup(struct inode * dir, struct dentry *dentry, stru
return ERR_PTR(-ENAMETOOLONG);
lock_kernel();
- ino = ufs_inode_by_name(dir, dentry);
+ ino = ufs_inode_by_name(dir, &dentry->d_name);
if (ino) {
inode = ufs_iget(dir->i_sb, ino);
if (IS_ERR(inode)) {
@@ -237,7 +237,7 @@ static int ufs_unlink(struct inode *dir, struct dentry *dentry)
struct page *page;
int err = -ENOENT;
- de = ufs_find_entry(dir, dentry, &page);
+ de = ufs_find_entry(dir, &dentry->d_name, &page);
if (!de)
goto out;
@@ -281,7 +281,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct ufs_dir_entry *old_de;
int err = -ENOENT;
- old_de = ufs_find_entry(old_dir, old_dentry, &old_page);
+ old_de = ufs_find_entry(old_dir, &old_dentry->d_name, &old_page);
if (!old_de)
goto out;
@@ -301,7 +301,7 @@ static int ufs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_dir;
err = -ENOENT;
- new_de = ufs_find_entry(new_dir, new_dentry, &new_page);
+ new_de = ufs_find_entry(new_dir, &new_dentry->d_name, &new_page);
if (!new_de)
goto out_dir;
inode_inc_link_count(old_inode);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 5faed7954d0..143c20bfb04 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -66,6 +66,7 @@
*/
+#include <linux/exportfs.h>
#include <linux/module.h>
#include <linux/bitops.h>
@@ -96,6 +97,56 @@
#include "swab.h"
#include "util.h"
+static struct inode *ufs_nfs_get_inode(struct super_block *sb, u64 ino, u32 generation)
+{
+ struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+ struct inode *inode;
+
+ if (ino < UFS_ROOTINO || ino > uspi->s_ncg * uspi->s_ipg)
+ return ERR_PTR(-ESTALE);
+
+ inode = ufs_iget(sb, ino);
+ if (IS_ERR(inode))
+ return ERR_CAST(inode);
+ if (generation && inode->i_generation != generation) {
+ iput(inode);
+ return ERR_PTR(-ESTALE);
+ }
+ return inode;
+}
+
+static struct dentry *ufs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_dentry(sb, fid, fh_len, fh_type, ufs_nfs_get_inode);
+}
+
+static struct dentry *ufs_fh_to_parent(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_parent(sb, fid, fh_len, fh_type, ufs_nfs_get_inode);
+}
+
+static struct dentry *ufs_get_parent(struct dentry *child)
+{
+ struct qstr dot_dot = {
+ .name = "..",
+ .len = 2,
+ };
+ ino_t ino;
+
+ ino = ufs_inode_by_name(child->d_inode, &dot_dot);
+ if (!ino)
+ return ERR_PTR(-ENOENT);
+ return d_obtain_alias(ufs_iget(child->d_inode->i_sb, ino));
+}
+
+static const struct export_operations ufs_export_ops = {
+ .fh_to_dentry = ufs_fh_to_dentry,
+ .fh_to_parent = ufs_fh_to_parent,
+ .get_parent = ufs_get_parent,
+};
+
#ifdef CONFIG_UFS_DEBUG
/*
* Print contents of ufs_super_block, useful for debugging
@@ -990,6 +1041,7 @@ magic_found:
* Read ufs_super_block into internal data structures
*/
sb->s_op = &ufs_super_ops;
+ sb->s_export_op = &ufs_export_ops;
sb->dq_op = NULL; /***/
sb->s_magic = fs32_to_cpu(sb, usb3->fs_magic);
diff --git a/fs/ufs/ufs.h b/fs/ufs/ufs.h
index 644e77e1359..0b4c39bc0d9 100644
--- a/fs/ufs/ufs.h
+++ b/fs/ufs/ufs.h
@@ -86,9 +86,9 @@ extern void ufs_put_cylinder (struct super_block *, unsigned);
/* dir.c */
extern const struct inode_operations ufs_dir_inode_operations;
extern int ufs_add_link (struct dentry *, struct inode *);
-extern ino_t ufs_inode_by_name(struct inode *, struct dentry *);
+extern ino_t ufs_inode_by_name(struct inode *, struct qstr *);
extern int ufs_make_empty(struct inode *, struct inode *);
-extern struct ufs_dir_entry *ufs_find_entry(struct inode *, struct dentry *, struct page **);
+extern struct ufs_dir_entry *ufs_find_entry(struct inode *, struct qstr *, struct page **);
extern int ufs_delete_entry(struct inode *, struct ufs_dir_entry *, struct page *);
extern int ufs_empty_dir (struct inode *);
extern struct ufs_dir_entry *ufs_dotdot(struct inode *, struct page **);
diff --git a/fs/xattr.c b/fs/xattr.c
index 6d4f6d3449f..46f87e828b4 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -615,12 +615,11 @@ ssize_t
generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t size)
{
struct xattr_handler *handler;
- struct inode *inode = dentry->d_inode;
- handler = xattr_resolve_name(inode->i_sb->s_xattr, &name);
+ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (!handler)
return -EOPNOTSUPP;
- return handler->get(inode, name, buffer, size);
+ return handler->get(dentry, name, buffer, size, handler->flags);
}
/*
@@ -630,18 +629,20 @@ generic_getxattr(struct dentry *dentry, const char *name, void *buffer, size_t s
ssize_t
generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
- struct inode *inode = dentry->d_inode;
- struct xattr_handler *handler, **handlers = inode->i_sb->s_xattr;
+ struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr;
unsigned int size = 0;
if (!buffer) {
- for_each_xattr_handler(handlers, handler)
- size += handler->list(inode, NULL, 0, NULL, 0);
+ for_each_xattr_handler(handlers, handler) {
+ size += handler->list(dentry, NULL, 0, NULL, 0,
+ handler->flags);
+ }
} else {
char *buf = buffer;
for_each_xattr_handler(handlers, handler) {
- size = handler->list(inode, buf, buffer_size, NULL, 0);
+ size = handler->list(dentry, buf, buffer_size,
+ NULL, 0, handler->flags);
if (size > buffer_size)
return -ERANGE;
buf += size;
@@ -659,14 +660,13 @@ int
generic_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags)
{
struct xattr_handler *handler;
- struct inode *inode = dentry->d_inode;
if (size == 0)
value = ""; /* empty EA, do not remove */
- handler = xattr_resolve_name(inode->i_sb->s_xattr, &name);
+ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (!handler)
return -EOPNOTSUPP;
- return handler->set(inode, name, value, size, flags);
+ return handler->set(dentry, name, value, size, 0, handler->flags);
}
/*
@@ -677,12 +677,12 @@ int
generic_removexattr(struct dentry *dentry, const char *name)
{
struct xattr_handler *handler;
- struct inode *inode = dentry->d_inode;
- handler = xattr_resolve_name(inode->i_sb->s_xattr, &name);
+ handler = xattr_resolve_name(dentry->d_sb->s_xattr, &name);
if (!handler)
return -EOPNOTSUPP;
- return handler->set(inode, name, NULL, 0, XATTR_REPLACE);
+ return handler->set(dentry, name, NULL, 0,
+ XATTR_REPLACE, handler->flags);
}
EXPORT_SYMBOL(generic_getxattr);
diff --git a/fs/xfs/linux-2.6/xfs_acl.c b/fs/xfs/linux-2.6/xfs_acl.c
index 69e598b6986..2512125dfa7 100644
--- a/fs/xfs/linux-2.6/xfs_acl.c
+++ b/fs/xfs/linux-2.6/xfs_acl.c
@@ -354,37 +354,14 @@ xfs_acl_chmod(struct inode *inode)
return error;
}
-/*
- * System xattr handlers.
- *
- * Currently Posix ACLs are the only system namespace extended attribute
- * handlers supported by XFS, so we just implement the handlers here.
- * If we ever support other system extended attributes this will need
- * some refactoring.
- */
-
static int
-xfs_decode_acl(const char *name)
-{
- if (strcmp(name, "posix_acl_access") == 0)
- return ACL_TYPE_ACCESS;
- else if (strcmp(name, "posix_acl_default") == 0)
- return ACL_TYPE_DEFAULT;
- return -EINVAL;
-}
-
-static int
-xfs_xattr_system_get(struct inode *inode, const char *name,
- void *value, size_t size)
+xfs_xattr_acl_get(struct dentry *dentry, const char *name,
+ void *value, size_t size, int type)
{
struct posix_acl *acl;
- int type, error;
-
- type = xfs_decode_acl(name);
- if (type < 0)
- return type;
+ int error;
- acl = xfs_get_acl(inode, type);
+ acl = xfs_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl == NULL)
@@ -397,15 +374,13 @@ xfs_xattr_system_get(struct inode *inode, const char *name,
}
static int
-xfs_xattr_system_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+xfs_xattr_acl_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int type)
{
+ struct inode *inode = dentry->d_inode;
struct posix_acl *acl = NULL;
- int error = 0, type;
+ int error = 0;
- type = xfs_decode_acl(name);
- if (type < 0)
- return type;
if (flags & XATTR_CREATE)
return -EINVAL;
if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
@@ -462,8 +437,16 @@ xfs_xattr_system_set(struct inode *inode, const char *name,
return error;
}
-struct xattr_handler xfs_xattr_system_handler = {
- .prefix = XATTR_SYSTEM_PREFIX,
- .get = xfs_xattr_system_get,
- .set = xfs_xattr_system_set,
+struct xattr_handler xfs_xattr_acl_access_handler = {
+ .prefix = POSIX_ACL_XATTR_ACCESS,
+ .flags = ACL_TYPE_ACCESS,
+ .get = xfs_xattr_acl_get,
+ .set = xfs_xattr_acl_set,
+};
+
+struct xattr_handler xfs_xattr_acl_default_handler = {
+ .prefix = POSIX_ACL_XATTR_DEFAULT,
+ .flags = ACL_TYPE_DEFAULT,
+ .get = xfs_xattr_acl_get,
+ .set = xfs_xattr_acl_set,
};
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index d798c54296e..66abe36c121 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1474,19 +1474,13 @@ xfs_vm_direct_IO(
bdev = xfs_find_bdev_for_inode(XFS_I(inode));
- if (rw == WRITE) {
- iocb->private = xfs_alloc_ioend(inode, IOMAP_UNWRITTEN);
- ret = blockdev_direct_IO_own_locking(rw, iocb, inode,
- bdev, iov, offset, nr_segs,
- xfs_get_blocks_direct,
- xfs_end_io_direct);
- } else {
- iocb->private = xfs_alloc_ioend(inode, IOMAP_READ);
- ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
- bdev, iov, offset, nr_segs,
- xfs_get_blocks_direct,
- xfs_end_io_direct);
- }
+ iocb->private = xfs_alloc_ioend(inode, rw == WRITE ?
+ IOMAP_UNWRITTEN : IOMAP_READ);
+
+ ret = blockdev_direct_IO_no_locking(rw, iocb, inode, bdev, iov,
+ offset, nr_segs,
+ xfs_get_blocks_direct,
+ xfs_end_io_direct);
if (unlikely(ret != -EIOCBQUEUED && iocb->private))
xfs_destroy_ioend(iocb->private);
diff --git a/fs/xfs/linux-2.6/xfs_xattr.c b/fs/xfs/linux-2.6/xfs_xattr.c
index 497c7fb75cc..0b1878857fc 100644
--- a/fs/xfs/linux-2.6/xfs_xattr.c
+++ b/fs/xfs/linux-2.6/xfs_xattr.c
@@ -30,10 +30,10 @@
static int
-__xfs_xattr_get(struct inode *inode, const char *name,
+xfs_xattr_get(struct dentry *dentry, const char *name,
void *value, size_t size, int xflags)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(dentry->d_inode);
int error, asize = size;
if (strcmp(name, "") == 0)
@@ -52,10 +52,10 @@ __xfs_xattr_get(struct inode *inode, const char *name,
}
static int
-__xfs_xattr_set(struct inode *inode, const char *name, const void *value,
+xfs_xattr_set(struct dentry *dentry, const char *name, const void *value,
size_t size, int flags, int xflags)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(dentry->d_inode);
if (strcmp(name, "") == 0)
return -EINVAL;
@@ -71,75 +71,34 @@ __xfs_xattr_set(struct inode *inode, const char *name, const void *value,
return -xfs_attr_set(ip, name, (void *)value, size, xflags);
}
-static int
-xfs_xattr_user_get(struct inode *inode, const char *name,
- void *value, size_t size)
-{
- return __xfs_xattr_get(inode, name, value, size, 0);
-}
-
-static int
-xfs_xattr_user_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return __xfs_xattr_set(inode, name, value, size, flags, 0);
-}
-
static struct xattr_handler xfs_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
- .get = xfs_xattr_user_get,
- .set = xfs_xattr_user_set,
+ .flags = 0, /* no flags implies user namespace */
+ .get = xfs_xattr_get,
+ .set = xfs_xattr_set,
};
-
-static int
-xfs_xattr_trusted_get(struct inode *inode, const char *name,
- void *value, size_t size)
-{
- return __xfs_xattr_get(inode, name, value, size, ATTR_ROOT);
-}
-
-static int
-xfs_xattr_trusted_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return __xfs_xattr_set(inode, name, value, size, flags, ATTR_ROOT);
-}
-
static struct xattr_handler xfs_xattr_trusted_handler = {
.prefix = XATTR_TRUSTED_PREFIX,
- .get = xfs_xattr_trusted_get,
- .set = xfs_xattr_trusted_set,
+ .flags = ATTR_ROOT,
+ .get = xfs_xattr_get,
+ .set = xfs_xattr_set,
};
-
-static int
-xfs_xattr_secure_get(struct inode *inode, const char *name,
- void *value, size_t size)
-{
- return __xfs_xattr_get(inode, name, value, size, ATTR_SECURE);
-}
-
-static int
-xfs_xattr_secure_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- return __xfs_xattr_set(inode, name, value, size, flags, ATTR_SECURE);
-}
-
static struct xattr_handler xfs_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
- .get = xfs_xattr_secure_get,
- .set = xfs_xattr_secure_set,
+ .flags = ATTR_SECURE,
+ .get = xfs_xattr_get,
+ .set = xfs_xattr_set,
};
-
struct xattr_handler *xfs_xattr_handlers[] = {
&xfs_xattr_user_handler,
&xfs_xattr_trusted_handler,
&xfs_xattr_security_handler,
#ifdef CONFIG_XFS_POSIX_ACL
- &xfs_xattr_system_handler,
+ &xfs_xattr_acl_access_handler,
+ &xfs_xattr_acl_default_handler,
#endif
NULL
};
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 947b150df8e..00fd357c3e4 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -49,7 +49,8 @@ extern int xfs_acl_chmod(struct inode *inode);
extern int posix_acl_access_exists(struct inode *inode);
extern int posix_acl_default_exists(struct inode *inode);
-extern struct xattr_handler xfs_xattr_system_handler;
+extern struct xattr_handler xfs_xattr_acl_access_handler;
+extern struct xattr_handler xfs_xattr_acl_default_handler;
#else
# define xfs_check_acl NULL
# define xfs_get_acl(inode, type) NULL