summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/anon_inodes.c11
-rw-r--r--fs/autofs4/autofs_i.h28
-rw-r--r--fs/autofs4/expire.c91
-rw-r--r--fs/autofs4/inode.c33
-rw-r--r--fs/autofs4/root.c589
-rw-r--r--fs/autofs4/waitq.c267
-rw-r--r--fs/binfmt_elf.c1
-rw-r--r--fs/binfmt_misc.c20
-rw-r--r--fs/coda/psdev.c5
-rw-r--r--fs/compat.c22
-rw-r--r--fs/compat_ioctl.c2
-rw-r--r--fs/dcache.c335
-rw-r--r--fs/debugfs/inode.c114
-rw-r--r--fs/ecryptfs/Makefile2
-rw-r--r--fs/ecryptfs/crypto.c37
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h23
-rw-r--r--fs/ecryptfs/file.c17
-rw-r--r--fs/ecryptfs/inode.c31
-rw-r--r--fs/ecryptfs/keystore.c9
-rw-r--r--fs/ecryptfs/kthread.c203
-rw-r--r--fs/ecryptfs/main.c79
-rw-r--r--fs/ecryptfs/miscdev.c59
-rw-r--r--fs/ecryptfs/mmap.c11
-rw-r--r--fs/eventfd.c17
-rw-r--r--fs/eventpoll.c30
-rw-r--r--fs/exec.c4
-rw-r--r--fs/fcntl.c15
-rw-r--r--fs/hugetlbfs/inode.c101
-rw-r--r--fs/inotify_user.c18
-rw-r--r--fs/nfs/nfsroot.c2
-rw-r--r--fs/open.c3
-rw-r--r--fs/partitions/check.c2
-rw-r--r--fs/pipe.c35
-rw-r--r--fs/proc/proc_misc.c19
-rw-r--r--fs/proc/proc_net.c11
-rw-r--r--fs/proc/task_mmu.c2
-rw-r--r--fs/signalfd.c19
-rw-r--r--fs/super.c1
-rw-r--r--fs/sync.c3
-rw-r--r--fs/sysfs/dir.c37
-rw-r--r--fs/sysfs/file.c5
-rw-r--r--fs/sysfs/symlink.c41
-rw-r--r--fs/sysfs/sysfs.h1
-rw-r--r--fs/timerfd.c9
-rw-r--r--fs/ufs/super.c2
45 files changed, 1429 insertions, 937 deletions
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 977ef208c05..3662dd44896 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -58,8 +58,9 @@ static struct dentry_operations anon_inodefs_dentry_operations = {
* of the file
*
* @name: [in] name of the "class" of the new file
- * @fops [in] file operations for the new file
- * @priv [in] private data for the new file (will be file's private_data)
+ * @fops: [in] file operations for the new file
+ * @priv: [in] private data for the new file (will be file's private_data)
+ * @flags: [in] flags
*
* Creates a new file by hooking it on a single inode. This is useful for files
* that do not need to have a full-fledged inode in order to operate correctly.
@@ -68,7 +69,7 @@ static struct dentry_operations anon_inodefs_dentry_operations = {
* setup. Returns new descriptor or -error.
*/
int anon_inode_getfd(const char *name, const struct file_operations *fops,
- void *priv)
+ void *priv, int flags)
{
struct qstr this;
struct dentry *dentry;
@@ -78,7 +79,7 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
if (IS_ERR(anon_inode_inode))
return -ENODEV;
- error = get_unused_fd();
+ error = get_unused_fd_flags(flags);
if (error < 0)
return error;
fd = error;
@@ -115,7 +116,7 @@ int anon_inode_getfd(const char *name, const struct file_operations *fops,
file->f_mapping = anon_inode_inode->i_mapping;
file->f_pos = 0;
- file->f_flags = O_RDWR;
+ file->f_flags = O_RDWR | (flags & O_NONBLOCK);
file->f_version = 0;
file->private_data = priv;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c3d352d7fa9..69a2f5c9231 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -52,7 +52,10 @@ struct autofs_info {
int flags;
- struct list_head rehash;
+ struct completion expire_complete;
+
+ struct list_head active;
+ struct list_head expiring;
struct autofs_sb_info *sbi;
unsigned long last_used;
@@ -68,15 +71,14 @@ 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 */
struct autofs_wait_queue {
wait_queue_head_t queue;
struct autofs_wait_queue *next;
autofs_wqt_t wait_queue_token;
/* We use the following to see what we are waiting for */
- unsigned int hash;
- unsigned int len;
- char *name;
+ struct qstr name;
u32 dev;
u64 ino;
uid_t uid;
@@ -85,7 +87,7 @@ struct autofs_wait_queue {
pid_t tgid;
/* This is for status reporting upon return */
int status;
- atomic_t wait_ctr;
+ unsigned int wait_ctr;
};
#define AUTOFS_SBI_MAGIC 0x6d4a556d
@@ -112,8 +114,9 @@ struct autofs_sb_info {
struct mutex wq_mutex;
spinlock_t fs_lock;
struct autofs_wait_queue *queues; /* Wait queue pointer */
- spinlock_t rehash_lock;
- struct list_head rehash_list;
+ spinlock_t lookup_lock;
+ struct list_head active_list;
+ struct list_head expiring_list;
};
static inline struct autofs_sb_info *autofs4_sbi(struct super_block *sb)
@@ -138,18 +141,14 @@ static inline int autofs4_oz_mode(struct autofs_sb_info *sbi) {
static inline int autofs4_ispending(struct dentry *dentry)
{
struct autofs_info *inf = autofs4_dentry_ino(dentry);
- int pending = 0;
if (dentry->d_flags & DCACHE_AUTOFS_PENDING)
return 1;
- if (inf) {
- spin_lock(&inf->sbi->fs_lock);
- pending = inf->flags & AUTOFS_INF_EXPIRING;
- spin_unlock(&inf->sbi->fs_lock);
- }
+ if (inf->flags & AUTOFS_INF_EXPIRING)
+ return 1;
- return pending;
+ return 0;
}
static inline void autofs4_copy_atime(struct file *src, struct file *dst)
@@ -164,6 +163,7 @@ void autofs4_free_ino(struct autofs_info *);
/* Expiration */
int is_autofs4_dentry(struct dentry *);
+int autofs4_expire_wait(struct dentry *dentry);
int autofs4_expire_run(struct super_block *, struct vfsmount *,
struct autofs_sb_info *,
struct autofs_packet_expire __user *);
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 894fee54d4d..cdabb796ff0 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -259,13 +259,15 @@ static struct dentry *autofs4_expire_direct(struct super_block *sb,
now = jiffies;
timeout = sbi->exp_timeout;
- /* Lock the tree as we must expire as a whole */
spin_lock(&sbi->fs_lock);
if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
struct autofs_info *ino = autofs4_dentry_ino(root);
-
- /* Set this flag early to catch sys_chdir and the like */
+ if (d_mountpoint(root)) {
+ ino->flags |= AUTOFS_INF_MOUNTPOINT;
+ root->d_mounted--;
+ }
ino->flags |= AUTOFS_INF_EXPIRING;
+ init_completion(&ino->expire_complete);
spin_unlock(&sbi->fs_lock);
return root;
}
@@ -292,6 +294,8 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
struct list_head *next;
int do_now = how & AUTOFS_EXP_IMMEDIATE;
int exp_leaves = how & AUTOFS_EXP_LEAVES;
+ struct autofs_info *ino;
+ unsigned int ino_count;
if (!root)
return NULL;
@@ -316,6 +320,9 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
dentry = dget(dentry);
spin_unlock(&dcache_lock);
+ spin_lock(&sbi->fs_lock);
+ ino = autofs4_dentry_ino(dentry);
+
/*
* Case 1: (i) indirect mount or top level pseudo direct mount
* (autofs-4.1).
@@ -326,6 +333,11 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
DPRINTK("checking mountpoint %p %.*s",
dentry, (int)dentry->d_name.len, dentry->d_name.name);
+ /* Path walk currently on this dentry? */
+ ino_count = atomic_read(&ino->count) + 2;
+ if (atomic_read(&dentry->d_count) > ino_count)
+ goto next;
+
/* Can we umount this guy */
if (autofs4_mount_busy(mnt, dentry))
goto next;
@@ -343,23 +355,25 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
/* Case 2: tree mount, expire iff entire tree is not busy */
if (!exp_leaves) {
- /* Lock the tree as we must expire as a whole */
- spin_lock(&sbi->fs_lock);
- if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
- struct autofs_info *inf = autofs4_dentry_ino(dentry);
+ /* Path walk currently on this dentry? */
+ ino_count = atomic_read(&ino->count) + 1;
+ if (atomic_read(&dentry->d_count) > ino_count)
+ goto next;
- /* Set this flag early to catch sys_chdir and the like */
- inf->flags |= AUTOFS_INF_EXPIRING;
- spin_unlock(&sbi->fs_lock);
+ if (!autofs4_tree_busy(mnt, dentry, timeout, do_now)) {
expired = dentry;
goto found;
}
- spin_unlock(&sbi->fs_lock);
/*
* Case 3: pseudo direct mount, expire individual leaves
* (autofs-4.1).
*/
} else {
+ /* Path walk currently on this dentry? */
+ ino_count = atomic_read(&ino->count) + 1;
+ if (atomic_read(&dentry->d_count) > ino_count)
+ goto next;
+
expired = autofs4_check_leaves(mnt, dentry, timeout, do_now);
if (expired) {
dput(dentry);
@@ -367,6 +381,7 @@ static struct dentry *autofs4_expire_indirect(struct super_block *sb,
}
}
next:
+ spin_unlock(&sbi->fs_lock);
dput(dentry);
spin_lock(&dcache_lock);
next = next->next;
@@ -377,12 +392,45 @@ next:
found:
DPRINTK("returning %p %.*s",
expired, (int)expired->d_name.len, expired->d_name.name);
+ ino = autofs4_dentry_ino(expired);
+ ino->flags |= AUTOFS_INF_EXPIRING;
+ init_completion(&ino->expire_complete);
+ spin_unlock(&sbi->fs_lock);
spin_lock(&dcache_lock);
list_move(&expired->d_parent->d_subdirs, &expired->d_u.d_child);
spin_unlock(&dcache_lock);
return expired;
}
+int autofs4_expire_wait(struct dentry *dentry)
+{
+ struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+ struct autofs_info *ino = autofs4_dentry_ino(dentry);
+ int status;
+
+ /* Block on any pending expire */
+ spin_lock(&sbi->fs_lock);
+ if (ino->flags & AUTOFS_INF_EXPIRING) {
+ spin_unlock(&sbi->fs_lock);
+
+ DPRINTK("waiting for expire %p name=%.*s",
+ dentry, dentry->d_name.len, dentry->d_name.name);
+
+ status = autofs4_wait(sbi, dentry, NFY_NONE);
+ wait_for_completion(&ino->expire_complete);
+
+ DPRINTK("expire done status=%d", status);
+
+ if (d_unhashed(dentry))
+ return -EAGAIN;
+
+ return status;
+ }
+ spin_unlock(&sbi->fs_lock);
+
+ return 0;
+}
+
/* Perform an expiry operation */
int autofs4_expire_run(struct super_block *sb,
struct vfsmount *mnt,
@@ -390,7 +438,9 @@ int autofs4_expire_run(struct super_block *sb,
struct autofs_packet_expire __user *pkt_p)
{
struct autofs_packet_expire pkt;
+ struct autofs_info *ino;
struct dentry *dentry;
+ int ret = 0;
memset(&pkt,0,sizeof pkt);
@@ -406,9 +456,15 @@ int autofs4_expire_run(struct super_block *sb,
dput(dentry);
if ( copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire)) )
- return -EFAULT;
+ ret = -EFAULT;
- return 0;
+ spin_lock(&sbi->fs_lock);
+ ino = autofs4_dentry_ino(dentry);
+ ino->flags &= ~AUTOFS_INF_EXPIRING;
+ complete_all(&ino->expire_complete);
+ spin_unlock(&sbi->fs_lock);
+
+ return ret;
}
/* Call repeatedly until it returns -EAGAIN, meaning there's nothing
@@ -433,9 +489,16 @@ int autofs4_expire_multi(struct super_block *sb, struct vfsmount *mnt,
/* This is synchronous because it makes the daemon a
little easier */
- ino->flags |= AUTOFS_INF_EXPIRING;
ret = autofs4_wait(sbi, dentry, NFY_EXPIRE);
+
+ spin_lock(&sbi->fs_lock);
+ if (ino->flags & AUTOFS_INF_MOUNTPOINT) {
+ sb->s_root->d_mounted++;
+ ino->flags &= ~AUTOFS_INF_MOUNTPOINT;
+ }
ino->flags &= ~AUTOFS_INF_EXPIRING;
+ 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 2fdcf5e1d23..7bb3e5ba053 100644
--- a/fs/autofs4/inode.c
+++ b/fs/autofs4/inode.c
@@ -24,8 +24,10 @@
static void ino_lnkfree(struct autofs_info *ino)
{
- kfree(ino->u.symlink);
- ino->u.symlink = NULL;
+ if (ino->u.symlink) {
+ kfree(ino->u.symlink);
+ ino->u.symlink = NULL;
+ }
}
struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
@@ -41,16 +43,18 @@ struct autofs_info *autofs4_init_ino(struct autofs_info *ino,
if (ino == NULL)
return NULL;
- ino->flags = 0;
- ino->mode = mode;
- ino->inode = NULL;
- ino->dentry = NULL;
- ino->size = 0;
-
- INIT_LIST_HEAD(&ino->rehash);
+ if (!reinit) {
+ ino->flags = 0;
+ ino->inode = NULL;
+ ino->dentry = NULL;
+ ino->size = 0;
+ INIT_LIST_HEAD(&ino->active);
+ INIT_LIST_HEAD(&ino->expiring);
+ atomic_set(&ino->count, 0);
+ }
+ ino->mode = mode;
ino->last_used = jiffies;
- atomic_set(&ino->count, 0);
ino->sbi = sbi;
@@ -159,8 +163,8 @@ void autofs4_kill_sb(struct super_block *sb)
if (!sbi)
goto out_kill_sb;
- if (!sbi->catatonic)
- autofs4_catatonic_mode(sbi); /* Free wait queues, close pipe */
+ /* Free wait queues, close pipe */
+ autofs4_catatonic_mode(sbi);
/* Clean up and release dangling references */
autofs4_force_release(sbi);
@@ -338,8 +342,9 @@ int autofs4_fill_super(struct super_block *s, void *data, int silent)
mutex_init(&sbi->wq_mutex);
spin_lock_init(&sbi->fs_lock);
sbi->queues = NULL;
- spin_lock_init(&sbi->rehash_lock);
- INIT_LIST_HEAD(&sbi->rehash_list);
+ spin_lock_init(&sbi->lookup_lock);
+ INIT_LIST_HEAD(&sbi->active_list);
+ INIT_LIST_HEAD(&sbi->expiring_list);
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = AUTOFS_SUPER_MAGIC;
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index edf5b6bddb5..bcfb2dc0a61 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -25,25 +25,25 @@ static int autofs4_dir_rmdir(struct inode *,struct dentry *);
static int autofs4_dir_mkdir(struct inode *,struct dentry *,int);
static int autofs4_root_ioctl(struct inode *, struct file *,unsigned int,unsigned long);
static int autofs4_dir_open(struct inode *inode, struct file *file);
-static int autofs4_dir_close(struct inode *inode, struct file *file);
-static int autofs4_dir_readdir(struct file * filp, void * dirent, filldir_t filldir);
-static int autofs4_root_readdir(struct file * filp, void * dirent, filldir_t filldir);
static struct dentry *autofs4_lookup(struct inode *,struct dentry *, struct nameidata *);
static void *autofs4_follow_link(struct dentry *, struct nameidata *);
+#define TRIGGER_FLAGS (LOOKUP_CONTINUE | LOOKUP_DIRECTORY)
+#define TRIGGER_INTENTS (LOOKUP_OPEN | LOOKUP_CREATE)
+
const struct file_operations autofs4_root_operations = {
.open = dcache_dir_open,
.release = dcache_dir_close,
.read = generic_read_dir,
- .readdir = autofs4_root_readdir,
+ .readdir = dcache_readdir,
.ioctl = autofs4_root_ioctl,
};
const struct file_operations autofs4_dir_operations = {
.open = autofs4_dir_open,
- .release = autofs4_dir_close,
+ .release = dcache_dir_close,
.read = generic_read_dir,
- .readdir = autofs4_dir_readdir,
+ .readdir = dcache_readdir,
};
const struct inode_operations autofs4_indirect_root_inode_operations = {
@@ -70,42 +70,10 @@ const struct inode_operations autofs4_dir_inode_operations = {
.rmdir = autofs4_dir_rmdir,
};
-static int autofs4_root_readdir(struct file *file, void *dirent,
- filldir_t filldir)
-{
- struct autofs_sb_info *sbi = autofs4_sbi(file->f_path.dentry->d_sb);
- int oz_mode = autofs4_oz_mode(sbi);
-
- DPRINTK("called, filp->f_pos = %lld", file->f_pos);
-
- /*
- * Don't set reghost flag if:
- * 1) f_pos is larger than zero -- we've already been here.
- * 2) we haven't even enabled reghosting in the 1st place.
- * 3) this is the daemon doing a readdir
- */
- if (oz_mode && file->f_pos == 0 && sbi->reghost_enabled)
- sbi->needs_reghost = 1;
-
- DPRINTK("needs_reghost = %d", sbi->needs_reghost);
-
- return dcache_readdir(file, dirent, filldir);
-}
-
static int autofs4_dir_open(struct inode *inode, struct file *file)
{
struct dentry *dentry = file->f_path.dentry;
- struct vfsmount *mnt = file->f_path.mnt;
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
- struct dentry *cursor;
- int status;
-
- status = dcache_dir_open(inode, file);
- if (status)
- goto out;
-
- cursor = file->private_data;
- cursor->d_fsdata = NULL;
DPRINTK("file=%p dentry=%p %.*s",
file, dentry, dentry->d_name.len, dentry->d_name.name);
@@ -113,159 +81,32 @@ static int autofs4_dir_open(struct inode *inode, struct file *file)
if (autofs4_oz_mode(sbi))
goto out;
- if (autofs4_ispending(dentry)) {
- DPRINTK("dentry busy");
- dcache_dir_close(inode, file);
- status = -EBUSY;
- goto out;
- }
-
- status = -ENOENT;
- if (!d_mountpoint(dentry) && dentry->d_op && dentry->d_op->d_revalidate) {
- struct nameidata nd;
- int empty, ret;
-
- /* In case there are stale directory dentrys from a failed mount */
- spin_lock(&dcache_lock);
- empty = list_empty(&dentry->d_subdirs);
+ /*
+ * An empty directory in an autofs file system is always a
+ * mount point. The daemon must have failed to mount this
+ * during lookup so it doesn't exist. This can happen, for
+ * example, if user space returns an incorrect status for a
+ * mount request. Otherwise we're doing a readdir on the
+ * autofs file system so just let the libfs routines handle
+ * it.
+ */
+ spin_lock(&dcache_lock);
+ if (!d_mountpoint(dentry) && __simple_empty(dentry)) {
spin_unlock(&dcache_lock);
-
- if (!empty)
- d_invalidate(dentry);
-
- nd.flags = LOOKUP_DIRECTORY;
- ret = (dentry->d_op->d_revalidate)(dentry, &nd);
-
- if (ret <= 0) {
- if (ret < 0)
- status = ret;
- dcache_dir_close(inode, file);
- goto out;
- }
+ return -ENOENT;
}
+ spin_unlock(&dcache_lock);
- if (d_mountpoint(dentry)) {
- struct file *fp = NULL;
- struct path fp_path = { .dentry = dentry, .mnt = mnt };
-
- path_get(&fp_path);
-
- if (!autofs4_follow_mount(&fp_path.mnt, &fp_path.dentry)) {
- path_put(&fp_path);
- dcache_dir_close(inode, file);
- goto out;
- }
-
- fp = dentry_open(fp_path.dentry, fp_path.mnt, file->f_flags);
- status = PTR_ERR(fp);
- if (IS_ERR(fp)) {
- dcache_dir_close(inode, file);
- goto out;
- }
- cursor->d_fsdata = fp;
- }
- return 0;
-out:
- return status;
-}
-
-static int autofs4_dir_close(struct inode *inode, struct file *file)
-{
- struct dentry *dentry = file->f_path.dentry;
- struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
- struct dentry *cursor = file->private_data;
- int status = 0;
-
- DPRINTK("file=%p dentry=%p %.*s",
- file, dentry, dentry->d_name.len, dentry->d_name.name);
-
- if (autofs4_oz_mode(sbi))
- goto out;
-
- if (autofs4_ispending(dentry)) {
- DPRINTK("dentry busy");
- status = -EBUSY;
- goto out;
- }
-
- if (d_mountpoint(dentry)) {
- struct file *fp = cursor->d_fsdata;
- if (!fp) {
- status = -ENOENT;
- goto out;
- }
- filp_close(fp, current->files);
- }
-out:
- dcache_dir_close(inode, file);
- return status;
-}
-
-static int autofs4_dir_readdir(struct file *file, void *dirent, filldir_t filldir)
-{
- struct dentry *dentry = file->f_path.dentry;
- struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
- struct dentry *cursor = file->private_data;
- int status;
-
- DPRINTK("file=%p dentry=%p %.*s",
- file, dentry, dentry->d_name.len, dentry->d_name.name);
-
- if (autofs4_oz_mode(sbi))
- goto out;
-
- if (autofs4_ispending(dentry)) {
- DPRINTK("dentry busy");
- return -EBUSY;
- }
-
- if (d_mountpoint(dentry)) {
- struct file *fp = cursor->d_fsdata;
-
- if (!fp)
- return -ENOENT;
-
- if (!fp->f_op || !fp->f_op->readdir)
- goto out;
-
- status = vfs_readdir(fp, filldir, dirent);
- file->f_pos = fp->f_pos;
- if (status)
- autofs4_copy_atime(file, fp);
- return status;
- }
out:
- return dcache_readdir(file, dirent, filldir);
+ return dcache_dir_open(inode, file);
}
static int try_to_fill_dentry(struct dentry *dentry, int flags)
{
struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
struct autofs_info *ino = autofs4_dentry_ino(dentry);
- struct dentry *new;
int status;
- /* Block on any pending expiry here; invalidate the dentry
- when expiration is done to trigger mount request with a new
- dentry */
- if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
- DPRINTK("waiting for expire %p name=%.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
-
- status = autofs4_wait(sbi, dentry, NFY_NONE);
-
- DPRINTK("expire done status=%d", status);
-
- /*
- * If the directory still exists the mount request must
- * continue otherwise it can't be followed at the right
- * time during the walk.
- */
- status = d_invalidate(dentry);
- if (status != -EBUSY)
- return -EAGAIN;
- }
-
DPRINTK("dentry=%p %.*s ino=%p",
dentry, dentry->d_name.len, dentry->d_name.name, dentry->d_inode);
@@ -292,7 +133,8 @@ static int try_to_fill_dentry(struct dentry *dentry, int flags)
return status;
}
/* Trigger mount for path component or follow link */
- } else if (flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY) ||
+ } 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);
@@ -320,26 +162,6 @@ static int try_to_fill_dentry(struct dentry *dentry, int flags)
dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
spin_unlock(&dentry->d_lock);
- /*
- * The dentry that is passed in from lookup may not be the one
- * we end up using, as mkdir can create a new one. If this
- * happens, and another process tries the lookup at the same time,
- * it will set the PENDING flag on this new dentry, but add itself
- * to our waitq. Then, if after the lookup succeeds, the first
- * process that requested the mount performs another lookup of the
- * same directory, it will show up as still pending! So, we need
- * to redo the lookup here and clear pending on that dentry.
- */
- if (d_unhashed(dentry)) {
- new = d_lookup(dentry->d_parent, &dentry->d_name);
- if (new) {
- spin_lock(&new->d_lock);
- new->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&new->d_lock);
- dput(new);
- }
- }
-
return 0;
}
@@ -355,51 +177,63 @@ static void *autofs4_follow_link(struct dentry *dentry, struct nameidata *nd)
DPRINTK("dentry=%p %.*s oz_mode=%d nd->flags=%d",
dentry, dentry->d_name.len, dentry->d_name.name, oz_mode,
nd->flags);
-
- /* If it's our master or we shouldn't trigger a mount we're done */
- lookup_type = nd->flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY);
- if (oz_mode || !lookup_type)
+ /*
+ * For an expire of a covered direct or offset mount we need
+ * to beeak out of follow_down() at the autofs mount trigger
+ * (d_mounted--), so we can see the expiring flag, and manage
+ * the blocking and following here until the expire is completed.
+ */
+ if (oz_mode) {
+ spin_lock(&sbi->fs_lock);
+ if (ino->flags & AUTOFS_INF_EXPIRING) {
+ spin_unlock(&sbi->fs_lock);
+ /* Follow down to our covering mount. */
+ if (!follow_down(&nd->path.mnt, &nd->path.dentry))
+ goto done;
+ goto follow;
+ }
+ spin_unlock(&sbi->fs_lock);
goto done;
+ }
- /* If an expire request is pending wait for it. */
- if (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
- DPRINTK("waiting for active request %p name=%.*s",
- dentry, dentry->d_name.len, dentry->d_name.name);
-
- status = autofs4_wait(sbi, dentry, NFY_NONE);
+ /* If an expire request is pending everyone must wait. */
+ autofs4_expire_wait(dentry);
- DPRINTK("request done status=%d", status);
- }
+ /* 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))
+ 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.
+ * 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 (!d_mountpoint(dentry) && __simple_empty(dentry)) {
+ if (dentry->d_flags & DCACHE_AUTOFS_PENDING ||
+ (!d_mountpoint(dentry) && __simple_empty(dentry))) {
spin_unlock(&dcache_lock);
status = try_to_fill_dentry(dentry, 0);
if (status)
goto out_error;
- /*
- * The mount succeeded but if there is no root mount
- * it must be an autofs multi-mount with no root offset
- * so we don't need to follow the mount.
- */
- if (d_mountpoint(dentry)) {
- if (!autofs4_follow_mount(&nd->path.mnt,
- &nd->path.dentry)) {
- status = -ENOENT;
- goto out_error;
- }
- }
-
- goto done;
+ goto follow;
}
spin_unlock(&dcache_lock);
+follow:
+ /*
+ * If there is no root mount it must be an autofs
+ * multi-mount with no root offset so we don't need
+ * to follow it.
+ */
+ if (d_mountpoint(dentry)) {
+ if (!autofs4_follow_mount(&nd->path.mnt,
+ &nd->path.dentry)) {
+ status = -ENOENT;
+ goto out_error;
+ }
+ }
done:
return NULL;
@@ -424,12 +258,23 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
int status = 1;
/* Pending dentry */
+ spin_lock(&sbi->fs_lock);
if (autofs4_ispending(dentry)) {
/* The daemon never causes a mount to trigger */
+ spin_unlock(&sbi->fs_lock);
+
if (oz_mode)
return 1;
/*
+ * If the directory has gone away due to an expire
+ * we have been called as ->d_revalidate() and so
+ * we need to return false and proceed to ->lookup().
+ */
+ if (autofs4_expire_wait(dentry) == -EAGAIN)
+ return 0;
+
+ /*
* A zero status is success otherwise we have a
* negative error code.
*/
@@ -437,17 +282,9 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
if (status == 0)
return 1;
- /*
- * A status of EAGAIN here means that the dentry has gone
- * away while waiting for an expire to complete. If we are
- * racing with expire lookup will wait for it so this must
- * be a revalidate and we need to send it to lookup.
- */
- if (status == -EAGAIN)
- return 0;
-
return status;
}
+ spin_unlock(&sbi->fs_lock);
/* Negative dentry.. invalidate if "old" */
if (dentry->d_inode == NULL)
@@ -461,6 +298,7 @@ static int autofs4_revalidate(struct dentry *dentry, struct nameidata *nd)
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;
@@ -493,10 +331,12 @@ void autofs4_dentry_release(struct dentry *de)
struct autofs_sb_info *sbi = autofs4_sbi(de->d_sb);
if (sbi) {
- spin_lock(&sbi->rehash_lock);
- if (!list_empty(&inf->rehash))
- list_del(&inf->rehash);
- spin_unlock(&sbi->rehash_lock);
+ spin_lock(&sbi->lookup_lock);
+ if (!list_empty(&inf->active))
+ list_del(&inf->active);
+ if (!list_empty(&inf->expiring))
+ list_del(&inf->expiring);
+ spin_unlock(&sbi->lookup_lock);
}
inf->dentry = NULL;
@@ -518,7 +358,7 @@ static struct dentry_operations autofs4_dentry_operations = {
.d_release = autofs4_dentry_release,
};
-static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+static struct dentry *autofs4_lookup_active(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
{
unsigned int len = name->len;
unsigned int hash = name->hash;
@@ -526,14 +366,66 @@ static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct
struct list_head *p, *head;
spin_lock(&dcache_lock);
- spin_lock(&sbi->rehash_lock);
- head = &sbi->rehash_list;
+ spin_lock(&sbi->lookup_lock);
+ head = &sbi->active_list;
list_for_each(p, head) {
struct autofs_info *ino;
struct dentry *dentry;
struct qstr *qstr;
- ino = list_entry(p, struct autofs_info, rehash);
+ ino = list_entry(p, struct autofs_info, active);
+ dentry = ino->dentry;
+
+ spin_lock(&dentry->d_lock);
+
+ /* Already gone? */
+ if (atomic_read(&dentry->d_count) == 0)
+ goto next;
+
+ qstr = &dentry->d_name;
+
+ if (dentry->d_name.hash != hash)
+ goto next;
+ if (dentry->d_parent != parent)
+ goto next;
+
+ if (qstr->len != len)
+ goto next;
+ 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;
+ }
+next:
+ spin_unlock(&dentry->d_lock);
+ }
+ spin_unlock(&sbi->lookup_lock);
+ spin_unlock(&dcache_lock);
+
+ return NULL;
+}
+
+static struct dentry *autofs4_lookup_expiring(struct autofs_sb_info *sbi, struct dentry *parent, struct qstr *name)
+{
+ unsigned int len = name->len;
+ unsigned int hash = name->hash;
+ const unsigned char *str = name->name;
+ struct list_head *p, *head;
+
+ spin_lock(&dcache_lock);
+ spin_lock(&sbi->lookup_lock);
+ head = &sbi->expiring_list;
+ list_for_each(p, head) {
+ struct autofs_info *ino;
+ struct dentry *dentry;
+ struct qstr *qstr;
+
+ ino = list_entry(p, struct autofs_info, expiring);
dentry = ino->dentry;
spin_lock(&dentry->d_lock);
@@ -555,33 +447,16 @@ static struct dentry *autofs4_lookup_unhashed(struct autofs_sb_info *sbi, struct
goto next;
if (d_unhashed(dentry)) {
- struct inode *inode = dentry->d_inode;
-
- ino = autofs4_dentry_ino(dentry);
- list_del_init(&ino->rehash);
dget(dentry);
- /*
- * Make the rehashed dentry negative so the VFS
- * behaves as it should.
- */
- if (inode) {
- dentry->d_inode = NULL;
- list_del_init(&dentry->d_alias);
- spin_unlock(&dentry->d_lock);
- spin_unlock(&sbi->rehash_lock);
- spin_unlock(&dcache_lock);
- iput(inode);
- return dentry;
- }
spin_unlock(&dentry->d_lock);
- spin_unlock(&sbi->rehash_lock);
+ spin_unlock(&sbi->lookup_lock);
spin_unlock(&dcache_lock);
return dentry;
}
next:
spin_unlock(&dentry->d_lock);
}
- spin_unlock(&sbi->rehash_lock);
+ spin_unlock(&sbi->lookup_lock);
spin_unlock(&dcache_lock);
return NULL;
@@ -591,7 +466,8 @@ next:
static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
{
struct autofs_sb_info *sbi;
- struct dentry *unhashed;
+ struct autofs_info *ino;
+ struct dentry *expiring, *unhashed;
int oz_mode;
DPRINTK("name = %.*s",
@@ -607,8 +483,26 @@ 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_unhashed(sbi, dentry->d_parent, &dentry->d_name);
- if (!unhashed) {
+ 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);
+ }
+
+ 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
@@ -622,39 +516,34 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
*/
dentry->d_op = &autofs4_root_dentry_operations;
- dentry->d_fsdata = NULL;
- d_instantiate(dentry, NULL);
- } else {
- struct autofs_info *ino = autofs4_dentry_ino(unhashed);
- DPRINTK("rehash %p with %p", dentry, unhashed);
/*
- * 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.
- * We need to ensure the AUTOFS_INF_EXPIRING flag is clear
- * before continuing as revalidate may fail when calling
- * try_to_fill_dentry (returning EAGAIN) if we don't.
+ * 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.
*/
- while (ino && (ino->flags & AUTOFS_INF_EXPIRING)) {
- DPRINTK("wait for incomplete expire %p name=%.*s",
- unhashed, unhashed->d_name.len,
- unhashed->d_name.name);
- autofs4_wait(sbi, unhashed, NFY_NONE);
- DPRINTK("request completed");
- }
- dentry = unhashed;
+ 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);
}
if (!oz_mode) {
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) {
- mutex_unlock(&dir->i_mutex);
- (dentry->d_op->d_revalidate)(dentry, nd);
- mutex_lock(&dir->i_mutex);
+ if (dentry->d_op && dentry->d_op->d_revalidate) {
+ mutex_unlock(&dir->i_mutex);
+ (dentry->d_op->d_revalidate)(dentry, nd);
+ mutex_lock(&dir->i_mutex);
+ }
}
/*
@@ -673,9 +562,11 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
return ERR_PTR(-ERESTARTNOINTR);
}
}
- spin_lock(&dentry->d_lock);
- dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
- spin_unlock(&dentry->d_lock);
+ if (!oz_mode) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags &= ~DCACHE_AUTOFS_PENDING;
+ spin_unlock(&dentry->d_lock);
+ }
}
/*
@@ -706,7 +597,7 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, s
}
if (unhashed)
- return dentry;
+ return unhashed;
return NULL;
}
@@ -728,20 +619,31 @@ static int autofs4_dir_symlink(struct inode *dir,
return -EACCES;
ino = autofs4_init_ino(ino, sbi, S_IFLNK | 0555);
- if (ino == NULL)
- return -ENOSPC;
+ if (!ino)
+ return -ENOMEM;
- ino->size = strlen(symname);
- ino->u.symlink = cp = kmalloc(ino->size + 1, GFP_KERNEL);
+ spin_lock(&sbi->lookup_lock);
+ if (!list_empty(&ino->active))
+ list_del_init(&ino->active);
+ spin_unlock(&sbi->lookup_lock);
- if (cp == NULL) {
- kfree(ino);
- return -ENOSPC;
+ ino->size = strlen(symname);
+ cp = kmalloc(ino->size + 1, GFP_KERNEL);
+ if (!cp) {
+ if (!dentry->d_fsdata)
+ kfree(ino);
+ return -ENOMEM;
}
strcpy(cp, symname);
inode = autofs4_get_inode(dir->i_sb, ino);
+ if (!inode) {
+ kfree(cp);
+ if (!dentry->d_fsdata)
+ kfree(ino);
+ return -ENOMEM;
+ }
d_add(dentry, inode);
if (dir == dir->i_sb->s_root->d_inode)
@@ -757,6 +659,7 @@ static int autofs4_dir_symlink(struct inode *dir,
atomic_inc(&p_ino->count);
ino->inode = inode;
+ ino->u.symlink = cp;
dir->i_mtime = CURRENT_TIME;
return 0;
@@ -769,9 +672,8 @@ static int autofs4_dir_symlink(struct inode *dir,
* that the file no longer exists. However, doing that means that the
* VFS layer can turn the dentry into a negative dentry. We don't want
* this, because the unlink is probably the result of an expire.
- * We simply d_drop it and add it to a rehash candidates list in the
- * super block, which allows the dentry lookup to reuse it retaining
- * the flags, such as expire in progress, in case we're racing with expire.
+ * We simply d_drop it and add it to a expiring list in the super block,
+ * which allows the dentry lookup to check for an incomplete expire.
*
* If a process is blocked on the dentry waiting for the expire to finish,
* it will invalidate the dentry and try to mount with a new one.
@@ -801,9 +703,10 @@ static int autofs4_dir_unlink(struct inode *dir, struct dentry *dentry)
dir->i_mtime = CURRENT_TIME;
spin_lock(&dcache_lock);
- spin_lock(&sbi->rehash_lock);
- list_add(&ino->rehash, &sbi->rehash_list);
- spin_unlock(&sbi->rehash_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);
@@ -829,9 +732,10 @@ static int autofs4_dir_rmdir(struct inode *dir, struct dentry *dentry)
spin_unlock(&dcache_lock);
return -ENOTEMPTY;
}
- spin_lock(&sbi->rehash_lock);
- list_add(&ino->rehash, &sbi->rehash_list);
- spin_unlock(&sbi->rehash_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);
@@ -866,10 +770,20 @@ static int autofs4_dir_mkdir(struct inode *dir, struct dentry *dentry, int mode)
dentry, dentry->d_name.len, dentry->d_name.name);
ino = autofs4_init_ino(ino, sbi, S_IFDIR | 0555);
- if (ino == NULL)
- return -ENOSPC;
+ 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)
+ kfree(ino);
+ return -ENOMEM;
+ }
d_add(dentry, inode);
if (dir == dir->i_sb->s_root->d_inode)
@@ -922,44 +836,6 @@ static inline int autofs4_get_protosubver(struct autofs_sb_info *sbi, int __user
}
/*
- * Tells the daemon whether we need to reghost or not. Also, clears
- * the reghost_needed flag.
- */
-static inline int autofs4_ask_reghost(struct autofs_sb_info *sbi, int __user *p)
-{
- int status;
-
- DPRINTK("returning %d", sbi->needs_reghost);
-
- status = put_user(sbi->needs_reghost, p);
- if (status)
- return status;
-
- sbi->needs_reghost = 0;
- return 0;
-}
-
-/*
- * Enable / Disable reghosting ioctl() operation
- */
-static inline int autofs4_toggle_reghost(struct autofs_sb_info *sbi, int __user *p)
-{
- int status;
- int val;
-
- status = get_user(val, p);
-
- DPRINTK("reghost = %d", val);
-
- if (status)
- return status;
-
- /* turn on/off reghosting, with the val */
- sbi->reghost_enabled = val;
- return 0;
-}
-
-/*
* Tells the daemon whether it can umount the autofs mount.
*/
static inline int autofs4_ask_umount(struct vfsmount *mnt, int __user *p)
@@ -1023,11 +899,6 @@ static int autofs4_root_ioctl(struct inode *inode, struct file *filp,
case AUTOFS_IOC_SETTIMEOUT:
return autofs4_get_set_timeout(sbi, p);
- case AUTOFS_IOC_TOGGLEREGHOST:
- return autofs4_toggle_reghost(sbi, p);
- case AUTOFS_IOC_ASKREGHOST:
- return autofs4_ask_reghost(sbi, p);
-
case AUTOFS_IOC_ASKUMOUNT:
return autofs4_ask_umount(filp->f_path.mnt, p);
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 75e5955c3f6..35216d18d8b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -28,6 +28,12 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
{
struct autofs_wait_queue *wq, *nwq;
+ mutex_lock(&sbi->wq_mutex);
+ if (sbi->catatonic) {
+ mutex_unlock(&sbi->wq_mutex);
+ return;
+ }
+
DPRINTK("entering catatonic mode");
sbi->catatonic = 1;
@@ -36,13 +42,18 @@ void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
while (wq) {
nwq = wq->next;
wq->status = -ENOENT; /* Magic is gone - report failure */
- kfree(wq->name);
- wq->name = NULL;
+ if (wq->name.name) {
+ kfree(wq->name.name);
+ wq->name.name = NULL;
+ }
+ wq->wait_ctr--;
wake_up_interruptible(&wq->queue);
wq = nwq;
}
fput(sbi->pipe); /* Close the pipe */
sbi->pipe = NULL;
+ sbi->pipefd = -1;
+ mutex_unlock(&sbi->wq_mutex);
}
static int autofs4_write(struct file *file, const void *addr, int bytes)
@@ -89,10 +100,11 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
union autofs_packet_union v4_pkt;
union autofs_v5_packet_union v5_pkt;
} pkt;
+ struct file *pipe = NULL;
size_t pktsz;
DPRINTK("wait id = 0x%08lx, name = %.*s, type=%d",
- wq->wait_queue_token, wq->len, wq->name, type);
+ wq->wait_queue_token, wq->name.len, wq->name.name, type);
memset(&pkt,0,sizeof pkt); /* For security reasons */
@@ -107,9 +119,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
pktsz = sizeof(*mp);
mp->wait_queue_token = wq->wait_queue_token;
- mp->len = wq->len;
- memcpy(mp->name, wq->name, wq->len);
- mp->name[wq->len] = '\0';
+ mp->len = wq->name.len;
+ memcpy(mp->name, wq->name.name, wq->name.len);
+ mp->name[wq->name.len] = '\0';
break;
}
case autofs_ptype_expire_multi:
@@ -119,9 +131,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
pktsz = sizeof(*ep);
ep->wait_queue_token = wq->wait_queue_token;
- ep->len = wq->len;
- memcpy(ep->name, wq->name, wq->len);
- ep->name[wq->len] = '\0';
+ ep->len = wq->name.len;
+ memcpy(ep->name, wq->name.name, wq->name.len);
+ ep->name[wq->name.len] = '\0';
break;
}
/*
@@ -138,9 +150,9 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
pktsz = sizeof(*packet);
packet->wait_queue_token = wq->wait_queue_token;
- packet->len = wq->len;
- memcpy(packet->name, wq->name, wq->len);
- packet->name[wq->len] = '\0';
+ packet->len = wq->name.len;
+ memcpy(packet->name, wq->name.name, wq->name.len);
+ packet->name[wq->name.len] = '\0';
packet->dev = wq->dev;
packet->ino = wq->ino;
packet->uid = wq->uid;
@@ -154,8 +166,19 @@ static void autofs4_notify_daemon(struct autofs_sb_info *sbi,
return;
}
- if (autofs4_write(sbi->pipe, &pkt, pktsz))
- autofs4_catatonic_mode(sbi);
+ /* Check if we have become catatonic */
+ mutex_lock(&sbi->wq_mutex);
+ if (!sbi->catatonic) {
+ pipe = sbi->pipe;
+ get_file(pipe);
+ }
+ mutex_unlock(&sbi->wq_mutex);
+
+ if (pipe) {
+ if (autofs4_write(pipe, &pkt, pktsz))
+ autofs4_catatonic_mode(sbi);
+ fput(pipe);
+ }
}
static int autofs4_getpath(struct autofs_sb_info *sbi,
@@ -191,58 +214,55 @@ static int autofs4_getpath(struct autofs_sb_info *sbi,
}
static struct autofs_wait_queue *
-autofs4_find_wait(struct autofs_sb_info *sbi,
- char *name, unsigned int hash, unsigned int len)
+autofs4_find_wait(struct autofs_sb_info *sbi, struct qstr *qstr)
{
struct autofs_wait_queue *wq;
for (wq = sbi->queues; wq; wq = wq->next) {
- if (wq->hash == hash &&
- wq->len == len &&
- wq->name && !memcmp(wq->name, name, len))
+ if (wq->name.hash == qstr->hash &&
+ wq->name.len == qstr->len &&
+ wq->name.name &&
+ !memcmp(wq->name.name, qstr->name, qstr->len))
break;
}
return wq;
}
-int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
- enum autofs_notify notify)
+/*
+ * Check if we have a valid request.
+ * Returns
+ * 1 if the request should continue.
+ * In this case we can return an autofs_wait_queue entry if one is
+ * found or NULL to idicate a new wait needs to be created.
+ * 0 or a negative errno if the request shouldn't continue.
+ */
+static int validate_request(struct autofs_wait_queue **wait,
+ struct autofs_sb_info *sbi,
+ struct qstr *qstr,
+ struct dentry*dentry, enum autofs_notify notify)
{
- struct autofs_info *ino;
struct autofs_wait_queue *wq;
- char *name;
- unsigned int len = 0;
- unsigned int hash = 0;
- int status, type;
-
- /* In catatonic mode, we don't wait for nobody */
- if (sbi->catatonic)
- return -ENOENT;
-
- name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
- if (!name)
- return -ENOMEM;
+ struct autofs_info *ino;
- /* If this is a direct mount request create a dummy name */
- if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT))
- len = sprintf(name, "%p", dentry);
- else {
- len = autofs4_getpath(sbi, dentry, &name);
- if (!len) {
- kfree(name);
- return -ENOENT;
- }
+ /* Wait in progress, continue; */
+ wq = autofs4_find_wait(sbi, qstr);
+ if (wq) {
+ *wait = wq;
+ return 1;
}
- hash = full_name_hash(name, len);
- if (mutex_lock_interruptible(&sbi->wq_mutex)) {
- kfree(name);
- return -EINTR;
- }
+ *wait = NULL;
- wq = autofs4_find_wait(sbi, name, hash, len);
+ /* If we don't yet have any info this is a new request */
ino = autofs4_dentry_ino(dentry);
- if (!wq && ino && notify == NFY_NONE) {
+ if (!ino)
+ return 1;
+
+ /*
+ * If we've been asked to wait on an existing expire (NFY_NONE)
+ * but there is no wait in the queue ...
+ */
+ if (notify == NFY_NONE) {
/*
* Either we've betean the pending expire to post it's
* wait or it finished while we waited on the mutex.
@@ -253,13 +273,14 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
while (ino->flags & AUTOFS_INF_EXPIRING) {
mutex_unlock(&sbi->wq_mutex);
schedule_timeout_interruptible(HZ/10);
- if (mutex_lock_interruptible(&sbi->wq_mutex)) {
- kfree(name);
+ if (mutex_lock_interruptible(&sbi->wq_mutex))
return -EINTR;
+
+ wq = autofs4_find_wait(sbi, qstr);
+ if (wq) {
+ *wait = wq;
+ return 1;
}
- wq = autofs4_find_wait(sbi, name, hash, len);
- if (wq)
- break;
}
/*
@@ -267,18 +288,96 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
* cases where we wait on NFY_NONE neither depend on the
* return status of the wait.
*/
- if (!wq) {
+ return 0;
+ }
+
+ /*
+ * If we've been asked to trigger a mount and the request
+ * completed while we waited on the mutex ...
+ */
+ if (notify == NFY_MOUNT) {
+ /*
+ * If the dentry isn't hashed just go ahead and try the
+ * mount again with a new wait (not much else we can do).
+ */
+ if (!d_unhashed(dentry)) {
+ /*
+ * But if the dentry is hashed, that means that we
+ * got here through the revalidate path. Thus, we
+ * need to check if the dentry has been mounted
+ * while we waited on the wq_mutex. If it has,
+ * simply return success.
+ */
+ if (d_mountpoint(dentry))
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
+int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
+ enum autofs_notify notify)
+{
+ struct autofs_wait_queue *wq;
+ struct qstr qstr;
+ char *name;
+ int status, ret, type;
+
+ /* In catatonic mode, we don't wait for nobody */
+ if (sbi->catatonic)
+ return -ENOENT;
+
+ if (!dentry->d_inode) {
+ /*
+ * A wait for a negative dentry is invalid for certain
+ * cases. A direct or offset mount "always" has its mount
+ * point directory created and so the request dentry must
+ * be positive or the map key doesn't exist. The situation
+ * is very similar for indirect mounts except only dentrys
+ * in the root of the autofs file system may be negative.
+ */
+ if (sbi->type & (AUTOFS_TYPE_DIRECT|AUTOFS_TYPE_OFFSET))
+ return -ENOENT;
+ else if (!IS_ROOT(dentry->d_parent))
+ return -ENOENT;
+ }
+
+ name = kmalloc(NAME_MAX + 1, GFP_KERNEL);
+ if (!name)
+ return -ENOMEM;
+
+ /* If this is a direct mount request create a dummy name */
+ if (IS_ROOT(dentry) && (sbi->type & AUTOFS_TYPE_DIRECT))
+ qstr.len = sprintf(name, "%p", dentry);
+ else {
+ qstr.len = autofs4_getpath(sbi, dentry, &name);
+ if (!qstr.len) {
kfree(name);
- mutex_unlock(&sbi->wq_mutex);
- return 0;
+ return -ENOENT;
}
}
+ qstr.name = name;
+ qstr.hash = full_name_hash(name, qstr.len);
+
+ if (mutex_lock_interruptible(&sbi->wq_mutex)) {
+ kfree(qstr.name);
+ return -EINTR;
+ }
+
+ ret = validate_request(&wq, sbi, &qstr, dentry, notify);
+ if (ret <= 0) {
+ if (ret == 0)
+ mutex_unlock(&sbi->wq_mutex);
+ kfree(qstr.name);
+ return ret;
+ }
if (!wq) {
/* Create a new wait queue */
wq = kmalloc(sizeof(struct autofs_wait_queue),GFP_KERNEL);
if (!wq) {
- kfree(name);
+ kfree(qstr.name);
mutex_unlock(&sbi->wq_mutex);
return -ENOMEM;
}
@@ -289,9 +388,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
wq->next = sbi->queues;
sbi->queues = wq;
init_waitqueue_head(&wq->queue);
- wq->hash = hash;
- wq->name = name;
- wq->len = len;
+ memcpy(&wq->name, &qstr, sizeof(struct qstr));
wq->dev = autofs4_get_dev(sbi);
wq->ino = autofs4_get_ino(sbi);
wq->uid = current->uid;
@@ -299,7 +396,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
wq->pid = current->pid;
wq->tgid = current->tgid;
wq->status = -EINTR; /* Status return if interrupted */
- atomic_set(&wq->wait_ctr, 2);
+ wq->wait_ctr = 2;
mutex_unlock(&sbi->wq_mutex);
if (sbi->version < 5) {
@@ -319,28 +416,25 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
}
DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
- (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
+ (unsigned long) wq->wait_queue_token, wq->name.len,
+ wq->name.name, notify);
/* autofs4_notify_daemon() may block */
autofs4_notify_daemon(sbi, wq, type);
} else {
- atomic_inc(&wq->wait_ctr);
+ wq->wait_ctr++;
mutex_unlock(&sbi->wq_mutex);
- kfree(name);
+ kfree(qstr.name);
DPRINTK("existing wait id = 0x%08lx, name = %.*s, nfy=%d",
- (unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
- }
-
- /* wq->name is NULL if and only if the lock is already released */
-
- if (sbi->catatonic) {
- /* We might have slept, so check again for catatonic mode */
- wq->status = -ENOENT;
- kfree(wq->name);
- wq->name = NULL;
+ (unsigned long) wq->wait_queue_token, wq->name.len,
+ wq->name.name, notify);
}
- if (wq->name) {
+ /*
+ * wq->name.name is NULL iff the lock is already released
+ * or the mount has been made catatonic.
+ */
+ if (wq->name.name) {
/* Block all but "shutdown" signals while waiting */
sigset_t oldset;
unsigned long irqflags;
@@ -351,7 +445,7 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
recalc_sigpending();
spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
- wait_event_interruptible(wq->queue, wq->name == NULL);
+ wait_event_interruptible(wq->queue, wq->name.name == NULL);
spin_lock_irqsave(&current->sighand->siglock, irqflags);
current->blocked = oldset;
@@ -364,8 +458,10 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
status = wq->status;
/* Are we the last process to need status? */
- if (atomic_dec_and_test(&wq->wait_ctr))
+ mutex_lock(&sbi->wq_mutex);
+ if (!--wq->wait_ctr)
kfree(wq);
+ mutex_unlock(&sbi->wq_mutex);
return status;
}
@@ -387,16 +483,13 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
}
*wql = wq->next; /* Unlink from chain */
- mutex_unlock(&sbi->wq_mutex);
- kfree(wq->name);
- wq->name = NULL; /* Do not wait on this queue */
-
+ kfree(wq->name.name);
+ wq->name.name = NULL; /* Do not wait on this queue */
wq->status = status;
-
- if (atomic_dec_and_test(&wq->wait_ctr)) /* Is anyone still waiting for this guy? */
+ wake_up_interruptible(&wq->queue);
+ if (!--wq->wait_ctr)
kfree(wq);
- else
- wake_up_interruptible(&wq->queue);
+ mutex_unlock(&sbi->wq_mutex);
return 0;
}
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d48ff5f370f..639d2d8b571 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -204,6 +204,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
NEW_AUX_ENT(AT_GID, tsk->gid);
NEW_AUX_ENT(AT_EGID, tsk->egid);
NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
+ NEW_AUX_ENT(AT_EXECFN, bprm->exec);
if (k_platform) {
NEW_AUX_ENT(AT_PLATFORM,
(elf_addr_t)(unsigned long)u_platform);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 7191306367c..756205314c2 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -27,6 +27,7 @@
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/syscalls.h>
+#include <linux/fs.h>
#include <asm/uaccess.h>
@@ -535,31 +536,16 @@ static ssize_t
bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
{
Node *e = file->f_path.dentry->d_inode->i_private;
- loff_t pos = *ppos;
ssize_t res;
char *page;
- int len;
if (!(page = (char*) __get_free_page(GFP_KERNEL)))
return -ENOMEM;
entry_status(e, page);
- len = strlen(page);
- res = -EINVAL;
- if (pos < 0)
- goto out;
- res = 0;
- if (pos >= len)
- goto out;
- if (len < pos + nbytes)
- nbytes = len - pos;
- res = -EFAULT;
- if (copy_to_user(buf, page + pos, nbytes))
- goto out;
- *ppos = pos + nbytes;
- res = nbytes;
-out:
+ res = simple_read_from_buffer(buf, nbytes, ppos, page, strlen(page));
+
free_page((unsigned long) page);
return res;
}
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index e3eb3556622..40c36f7352a 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -362,8 +362,9 @@ static int init_coda_psdev(void)
goto out_chrdev;
}
for (i = 0; i < MAX_CODADEVS; i++)
- device_create(coda_psdev_class, NULL,
- MKDEV(CODA_PSDEV_MAJOR,i), "cfs%d", i);
+ device_create_drvdata(coda_psdev_class, NULL,
+ MKDEV(CODA_PSDEV_MAJOR, i),
+ NULL, "cfs%d", i);
coda_sysctl_init();
goto out;
diff --git a/fs/compat.c b/fs/compat.c
index ed43e17a5dc..106eba28ec5 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -197,8 +197,8 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *
{
if (sizeof ubuf->f_blocks == 4) {
- if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
- 0xffffffff00000000ULL)
+ if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+ kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
return -EOVERFLOW;
/* f_files and f_ffree may be -1; it's okay
* to stuff that into 32 bits */
@@ -271,8 +271,8 @@ out:
static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
{
if (sizeof ubuf->f_blocks == 4) {
- if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) &
- 0xffffffff00000000ULL)
+ if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+ kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
return -EOVERFLOW;
/* f_files and f_ffree may be -1; it's okay
* to stuff that into 32 bits */
@@ -2131,9 +2131,9 @@ asmlinkage long compat_sys_epoll_pwait(int epfd,
#ifdef CONFIG_SIGNALFD
-asmlinkage long compat_sys_signalfd(int ufd,
- const compat_sigset_t __user *sigmask,
- compat_size_t sigsetsize)
+asmlinkage long compat_sys_signalfd4(int ufd,
+ const compat_sigset_t __user *sigmask,
+ compat_size_t sigsetsize, int flags)
{
compat_sigset_t ss32;
sigset_t tmp;
@@ -2148,9 +2148,15 @@ asmlinkage long compat_sys_signalfd(int ufd,
if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t)))
return -EFAULT;
- return sys_signalfd(ufd, ksigmask, sizeof(sigset_t));
+ return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags);
}
+asmlinkage long compat_sys_signalfd(int ufd,
+ const compat_sigset_t __user *sigmask,
+ compat_size_t sigsetsize)
+{
+ return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0);
+}
#endif /* CONFIG_SIGNALFD */
#ifdef CONFIG_TIMERFD
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 7b3a03c7c6a..18e2c548161 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -2297,8 +2297,6 @@ COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOVER)
COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE)
COMPATIBLE_IOCTL(AUTOFS_IOC_EXPIRE_MULTI)
COMPATIBLE_IOCTL(AUTOFS_IOC_PROTOSUBVER)
-COMPATIBLE_IOCTL(AUTOFS_IOC_ASKREGHOST)
-COMPATIBLE_IOCTL(AUTOFS_IOC_TOGGLEREGHOST)
COMPATIBLE_IOCTL(AUTOFS_IOC_ASKUMOUNT)
/* Raw devices */
COMPATIBLE_IOCTL(RAW_SETBIND)
diff --git a/fs/dcache.c b/fs/dcache.c
index 6068c25b393..3818d6ab76c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -61,7 +61,6 @@ static struct kmem_cache *dentry_cache __read_mostly;
static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
static struct hlist_head *dentry_hashtable __read_mostly;
-static LIST_HEAD(dentry_unused);
/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
@@ -96,14 +95,6 @@ static void d_free(struct dentry *dentry)
call_rcu(&dentry->d_u.d_rcu, d_callback);
}
-static void dentry_lru_remove(struct dentry *dentry)
-{
- if (!list_empty(&dentry->d_lru)) {
- list_del_init(&dentry->d_lru);
- dentry_stat.nr_unused--;
- }
-}
-
/*
* Release the dentry's inode, using the filesystem
* d_iput() operation if defined.
@@ -130,6 +121,41 @@ static void dentry_iput(struct dentry * dentry)
}
}
+/*
+ * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held.
+ */
+static void dentry_lru_add(struct dentry *dentry)
+{
+ list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+ dentry->d_sb->s_nr_dentry_unused++;
+ dentry_stat.nr_unused++;
+}
+
+static void dentry_lru_add_tail(struct dentry *dentry)
+{
+ list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+ dentry->d_sb->s_nr_dentry_unused++;
+ dentry_stat.nr_unused++;
+}
+
+static void dentry_lru_del(struct dentry *dentry)
+{
+ if (!list_empty(&dentry->d_lru)) {
+ list_del(&dentry->d_lru);
+ dentry->d_sb->s_nr_dentry_unused--;
+ dentry_stat.nr_unused--;
+ }
+}
+
+static void dentry_lru_del_init(struct dentry *dentry)
+{
+ if (likely(!list_empty(&dentry->d_lru))) {
+ list_del_init(&dentry->d_lru);
+ dentry->d_sb->s_nr_dentry_unused--;
+ dentry_stat.nr_unused--;
+ }
+}
+
/**
* d_kill - kill dentry and return parent
* @dentry: dentry to kill
@@ -212,8 +238,7 @@ repeat:
goto kill_it;
if (list_empty(&dentry->d_lru)) {
dentry->d_flags |= DCACHE_REFERENCED;
- list_add(&dentry->d_lru, &dentry_unused);
- dentry_stat.nr_unused++;
+ dentry_lru_add(dentry);
}
spin_unlock(&dentry->d_lock);
spin_unlock(&dcache_lock);
@@ -222,7 +247,8 @@ repeat:
unhash_it:
__d_drop(dentry);
kill_it:
- dentry_lru_remove(dentry);
+ /* if dentry was on the d_lru list delete it from there */
+ dentry_lru_del(dentry);
dentry = d_kill(dentry);
if (dentry)
goto repeat;
@@ -290,7 +316,7 @@ int d_invalidate(struct dentry * dentry)
static inline struct dentry * __dget_locked(struct dentry *dentry)
{
atomic_inc(&dentry->d_count);
- dentry_lru_remove(dentry);
+ dentry_lru_del_init(dentry);
return dentry;
}
@@ -406,133 +432,167 @@ static void prune_one_dentry(struct dentry * dentry)
if (dentry->d_op && dentry->d_op->d_delete)
dentry->d_op->d_delete(dentry);
- dentry_lru_remove(dentry);
+ dentry_lru_del_init(dentry);
__d_drop(dentry);
dentry = d_kill(dentry);
spin_lock(&dcache_lock);
}
}
-/**
- * prune_dcache - shrink the dcache
- * @count: number of entries to try and free
- * @sb: if given, ignore dentries for other superblocks
- * which are being unmounted.
- *
- * Shrink the dcache. This is done when we need
- * more memory, or simply when we need to unmount
- * something (at which point we need to unuse
- * all dentries).
- *
- * This function may fail to free any resources if
- * all the dentries are in use.
+/*
+ * Shrink the dentry LRU on a given superblock.
+ * @sb : superblock to shrink dentry LRU.
+ * @count: If count is NULL, we prune all dentries on superblock.
+ * @flags: If flags is non-zero, we need to do special processing based on
+ * which flags are set. This means we don't need to maintain multiple
+ * similar copies of this loop.
*/
-
-static void prune_dcache(int count, struct super_block *sb)
+static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
{
- spin_lock(&dcache_lock);
- for (; count ; count--) {
- struct dentry *dentry;
- struct list_head *tmp;
- struct rw_semaphore *s_umount;
-
- cond_resched_lock(&dcache_lock);
+ LIST_HEAD(referenced);
+ LIST_HEAD(tmp);
+ struct dentry *dentry;
+ int cnt = 0;
- tmp = dentry_unused.prev;
- if (sb) {
- /* Try to find a dentry for this sb, but don't try
- * too hard, if they aren't near the tail they will
- * be moved down again soon
+ BUG_ON(!sb);
+ BUG_ON((flags & DCACHE_REFERENCED) && count == NULL);
+ spin_lock(&dcache_lock);
+ if (count != NULL)
+ /* called from prune_dcache() and shrink_dcache_parent() */
+ cnt = *count;
+restart:
+ if (count == NULL)
+ list_splice_init(&sb->s_dentry_lru, &tmp);
+ else {
+ while (!list_empty(&sb->s_dentry_lru)) {
+ dentry = list_entry(sb->s_dentry_lru.prev,
+ struct dentry, d_lru);
+ BUG_ON(dentry->d_sb != sb);
+
+ spin_lock(&dentry->d_lock);
+ /*
+ * If we are honouring the DCACHE_REFERENCED flag and
+ * the dentry has this flag set, don't free it. Clear
+ * the flag and put it back on the LRU.
*/
- int skip = count;
- while (skip && tmp != &dentry_unused &&
- list_entry(tmp, struct dentry, d_lru)->d_sb != sb) {
- skip--;
- tmp = tmp->prev;
+ if ((flags & DCACHE_REFERENCED)
+ && (dentry->d_flags & DCACHE_REFERENCED)) {
+ dentry->d_flags &= ~DCACHE_REFERENCED;
+ list_move_tail(&dentry->d_lru, &referenced);
+ spin_unlock(&dentry->d_lock);
+ } else {
+ list_move_tail(&dentry->d_lru, &tmp);
+ spin_unlock(&dentry->d_lock);
+ cnt--;
+ if (!cnt)
+ break;
}
}
- if (tmp == &dentry_unused)
- break;
- list_del_init(tmp);
- prefetch(dentry_unused.prev);
- dentry_stat.nr_unused--;
- dentry = list_entry(tmp, struct dentry, d_lru);
-
- spin_lock(&dentry->d_lock);
+ }
+ while (!list_empty(&tmp)) {
+ dentry = list_entry(tmp.prev, struct dentry, d_lru);
+ dentry_lru_del_init(dentry);
+ spin_lock(&dentry->d_lock);
/*
* We found an inuse dentry which was not removed from
- * dentry_unused because of laziness during lookup. Do not free
- * it - just keep it off the dentry_unused list.
+ * the LRU because of laziness during lookup. Do not free
+ * it - just keep it off the LRU list.
*/
- if (atomic_read(&dentry->d_count)) {
- spin_unlock(&dentry->d_lock);
+ if (atomic_read(&dentry->d_count)) {
+ spin_unlock(&dentry->d_lock);
continue;
}
- /* If the dentry was recently referenced, don't free it. */
- if (dentry->d_flags & DCACHE_REFERENCED) {
- dentry->d_flags &= ~DCACHE_REFERENCED;
- list_add(&dentry->d_lru, &dentry_unused);
- dentry_stat.nr_unused++;
- spin_unlock(&dentry->d_lock);
+ prune_one_dentry(dentry);
+ /* dentry->d_lock was dropped in prune_one_dentry() */
+ cond_resched_lock(&dcache_lock);
+ }
+ if (count == NULL && !list_empty(&sb->s_dentry_lru))
+ goto restart;
+ if (count != NULL)
+ *count = cnt;
+ if (!list_empty(&referenced))
+ list_splice(&referenced, &sb->s_dentry_lru);
+ spin_unlock(&dcache_lock);
+}
+
+/**
+ * prune_dcache - shrink the dcache
+ * @count: number of entries to try to free
+ *
+ * Shrink the dcache. This is done when we need more memory, or simply when we
+ * need to unmount something (at which point we need to unuse all dentries).
+ *
+ * This function may fail to free any resources if all the dentries are in use.
+ */
+static void prune_dcache(int count)
+{
+ struct super_block *sb;
+ int w_count;
+ int unused = dentry_stat.nr_unused;
+ int prune_ratio;
+ int pruned;
+
+ if (unused == 0 || count == 0)
+ return;
+ spin_lock(&dcache_lock);
+restart:
+ if (count >= unused)
+ prune_ratio = 1;
+ else
+ prune_ratio = unused / count;
+ spin_lock(&sb_lock);
+ list_for_each_entry(sb, &super_blocks, s_list) {
+ if (sb->s_nr_dentry_unused == 0)
continue;
- }
- /*
- * If the dentry is not DCACHED_REFERENCED, it is time
- * to remove it from the dcache, provided the super block is
- * NULL (which means we are trying to reclaim memory)
- * or this dentry belongs to the same super block that
- * we want to shrink.
- */
- /*
- * If this dentry is for "my" filesystem, then I can prune it
- * without taking the s_umount lock (I already hold it).
+ sb->s_count++;
+ /* Now, we reclaim unused dentrins with fairness.
+ * We reclaim them same percentage from each superblock.
+ * We calculate number of dentries to scan on this sb
+ * as follows, but the implementation is arranged to avoid
+ * overflows:
+ * number of dentries to scan on this sb =
+ * count * (number of dentries on this sb /
+ * number of dentries in the machine)
*/
- if (sb && dentry->d_sb == sb) {
- prune_one_dentry(dentry);
- continue;
- }
+ spin_unlock(&sb_lock);
+ if (prune_ratio != 1)
+ w_count = (sb->s_nr_dentry_unused / prune_ratio) + 1;
+ else
+ w_count = sb->s_nr_dentry_unused;
+ pruned = w_count;
/*
- * ...otherwise we need to be sure this filesystem isn't being
- * unmounted, otherwise we could race with
- * generic_shutdown_super(), and end up holding a reference to
- * an inode while the filesystem is unmounted.
- * So we try to get s_umount, and make sure s_root isn't NULL.
- * (Take a local copy of s_umount to avoid a use-after-free of
- * `dentry').
+ * We need to be sure this filesystem isn't being unmounted,
+ * otherwise we could race with generic_shutdown_super(), and
+ * end up holding a reference to an inode while the filesystem
+ * is unmounted. So we try to get s_umount, and make sure
+ * s_root isn't NULL.
*/
- s_umount = &dentry->d_sb->s_umount;
- if (down_read_trylock(s_umount)) {
- if (dentry->d_sb->s_root != NULL) {
- prune_one_dentry(dentry);
- up_read(s_umount);
- continue;
+ if (down_read_trylock(&sb->s_umount)) {
+ if ((sb->s_root != NULL) &&
+ (!list_empty(&sb->s_dentry_lru))) {
+ spin_unlock(&dcache_lock);
+ __shrink_dcache_sb(sb, &w_count,
+ DCACHE_REFERENCED);
+ pruned -= w_count;
+ spin_lock(&dcache_lock);
}
- up_read(s_umount);
+ up_read(&sb->s_umount);
}
- spin_unlock(&dentry->d_lock);
+ spin_lock(&sb_lock);
+ count -= pruned;
/*
- * Insert dentry at the head of the list as inserting at the
- * tail leads to a cycle.
+ * restart only when sb is no longer on the list and
+ * we have more work to do.
*/
- list_add(&dentry->d_lru, &dentry_unused);
- dentry_stat.nr_unused++;
+ if (__put_super_and_need_restart(sb) && count > 0) {
+ spin_unlock(&sb_lock);
+ goto restart;
+ }
}
+ spin_unlock(&sb_lock);
spin_unlock(&dcache_lock);
}
-/*
- * Shrink the dcache for the specified super block.
- * This allows us to unmount a device without disturbing
- * the dcache for the other devices.
- *
- * This implementation makes just two traversals of the
- * unused list. On the first pass we move the selected
- * dentries to the most recent end, and on the second
- * pass we free them. The second pass must restart after
- * each dput(), but since the target dentries are all at
- * the end, it's really just a single traversal.
- */
-
/**
* shrink_dcache_sb - shrink dcache for a superblock
* @sb: superblock
@@ -541,44 +601,9 @@ static void prune_dcache(int count, struct super_block *sb)
* is used to free the dcache before unmounting a file
* system
*/
-
void shrink_dcache_sb(struct super_block * sb)
{
- struct list_head *tmp, *next;
- struct dentry *dentry;
-
- /*
- * Pass one ... move the dentries for the specified
- * superblock to the most recent end of the unused list.
- */
- spin_lock(&dcache_lock);
- list_for_each_prev_safe(tmp, next, &dentry_unused) {
- dentry = list_entry(tmp, struct dentry, d_lru);
- if (dentry->d_sb != sb)
- continue;
- list_move_tail(tmp, &dentry_unused);
- }
-
- /*
- * Pass two ... free the dentries for this superblock.
- */
-repeat:
- list_for_each_prev_safe(tmp, next, &dentry_unused) {
- dentry = list_entry(tmp, struct dentry, d_lru);
- if (dentry->d_sb != sb)
- continue;
- dentry_stat.nr_unused--;
- list_del_init(tmp);
- spin_lock(&dentry->d_lock);
- if (atomic_read(&dentry->d_count)) {
- spin_unlock(&dentry->d_lock);
- continue;
- }
- prune_one_dentry(dentry);
- cond_resched_lock(&dcache_lock);
- goto repeat;
- }
- spin_unlock(&dcache_lock);
+ __shrink_dcache_sb(sb, NULL, 0);
}
/*
@@ -595,7 +620,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
/* detach this root from the system */
spin_lock(&dcache_lock);
- dentry_lru_remove(dentry);
+ dentry_lru_del_init(dentry);
__d_drop(dentry);
spin_unlock(&dcache_lock);
@@ -609,7 +634,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
spin_lock(&dcache_lock);
list_for_each_entry(loop, &dentry->d_subdirs,
d_u.d_child) {
- dentry_lru_remove(loop);
+ dentry_lru_del_init(loop);
__d_drop(loop);
cond_resched_lock(&dcache_lock);
}
@@ -791,14 +816,13 @@ resume:
struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
next = tmp->next;
- dentry_lru_remove(dentry);
+ dentry_lru_del_init(dentry);
/*
* move only zero ref count dentries to the end
* of the unused list for prune_dcache
*/
if (!atomic_read(&dentry->d_count)) {
- list_add_tail(&dentry->d_lru, &dentry_unused);
- dentry_stat.nr_unused++;
+ dentry_lru_add_tail(dentry);
found++;
}
@@ -840,10 +864,11 @@ out:
void shrink_dcache_parent(struct dentry * parent)
{
+ struct super_block *sb = parent->d_sb;
int found;
while ((found = select_parent(parent)) != 0)
- prune_dcache(found, parent->d_sb);
+ __shrink_dcache_sb(sb, &found, 0);
}
/*
@@ -863,7 +888,7 @@ static int shrink_dcache_memory(int nr, gfp_t gfp_mask)
if (nr) {
if (!(gfp_mask & __GFP_FS))
return -1;
- prune_dcache(nr, NULL);
+ prune_dcache(nr);
}
return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
@@ -1215,7 +1240,7 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
* rcu_read_lock() and rcu_read_unlock() are used to disable preemption while
* lookup is going on.
*
- * dentry_unused list is not updated even if lookup finds the required dentry
+ * The dentry unused LRU is not updated even if lookup finds the required dentry
* in there. It is updated in places such as prune_dcache, shrink_dcache_sb,
* select_parent and __dget_locked. This laziness saves lookup from dcache_lock
* acquisition.
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index e9602d85c11..08e28c9bb41 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -309,6 +309,31 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
}
EXPORT_SYMBOL_GPL(debugfs_create_symlink);
+static void __debugfs_remove(struct dentry *dentry, struct dentry *parent)
+{
+ int ret = 0;
+
+ if (debugfs_positive(dentry)) {
+ if (dentry->d_inode) {
+ dget(dentry);
+ switch (dentry->d_inode->i_mode & S_IFMT) {
+ case S_IFDIR:
+ ret = simple_rmdir(parent->d_inode, dentry);
+ break;
+ case S_IFLNK:
+ kfree(dentry->d_inode->i_private);
+ /* fall through */
+ default:
+ simple_unlink(parent->d_inode, dentry);
+ break;
+ }
+ if (!ret)
+ d_delete(dentry);
+ dput(dentry);
+ }
+ }
+}
+
/**
* debugfs_remove - removes a file or directory from the debugfs filesystem
* @dentry: a pointer to a the dentry of the file or directory to be
@@ -325,7 +350,6 @@ EXPORT_SYMBOL_GPL(debugfs_create_symlink);
void debugfs_remove(struct dentry *dentry)
{
struct dentry *parent;
- int ret = 0;
if (!dentry)
return;
@@ -335,29 +359,83 @@ void debugfs_remove(struct dentry *dentry)
return;
mutex_lock(&parent->d_inode->i_mutex);
- if (debugfs_positive(dentry)) {
- if (dentry->d_inode) {
- dget(dentry);
- switch (dentry->d_inode->i_mode & S_IFMT) {
- case S_IFDIR:
- ret = simple_rmdir(parent->d_inode, dentry);
- break;
- case S_IFLNK:
- kfree(dentry->d_inode->i_private);
- /* fall through */
- default:
- simple_unlink(parent->d_inode, dentry);
+ __debugfs_remove(dentry, parent);
+ mutex_unlock(&parent->d_inode->i_mutex);
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+}
+EXPORT_SYMBOL_GPL(debugfs_remove);
+
+/**
+ * debugfs_remove_recursive - recursively removes a directory
+ * @dentry: a pointer to a the dentry of the directory to be removed.
+ *
+ * This function recursively removes a directory tree in debugfs that
+ * was previously created with a call to another debugfs function
+ * (like debugfs_create_file() or variants thereof.)
+ *
+ * This function is required to be called in order for the file to be
+ * removed, no automatic cleanup of files will happen when a module is
+ * removed, you are responsible here.
+ */
+void debugfs_remove_recursive(struct dentry *dentry)
+{
+ struct dentry *child;
+ struct dentry *parent;
+
+ if (!dentry)
+ return;
+
+ parent = dentry->d_parent;
+ if (!parent || !parent->d_inode)
+ return;
+
+ parent = dentry;
+ mutex_lock(&parent->d_inode->i_mutex);
+
+ while (1) {
+ /*
+ * When all dentries under "parent" has been removed,
+ * walk up the tree until we reach our starting point.
+ */
+ if (list_empty(&parent->d_subdirs)) {
+ mutex_unlock(&parent->d_inode->i_mutex);
+ if (parent == dentry)
break;
- }
- if (!ret)
- d_delete(dentry);
- dput(dentry);
+ parent = parent->d_parent;
+ mutex_lock(&parent->d_inode->i_mutex);
+ }
+ child = list_entry(parent->d_subdirs.next, struct dentry,
+ d_u.d_child);
+
+ /*
+ * If "child" isn't empty, walk down the tree and
+ * remove all its descendants first.
+ */
+ if (!list_empty(&child->d_subdirs)) {
+ mutex_unlock(&parent->d_inode->i_mutex);
+ parent = child;
+ mutex_lock(&parent->d_inode->i_mutex);
+ continue;
}
+ __debugfs_remove(child, parent);
+ if (parent->d_subdirs.next == &child->d_u.d_child) {
+ /*
+ * Avoid infinite loop if we fail to remove
+ * one dentry.
+ */
+ mutex_unlock(&parent->d_inode->i_mutex);
+ break;
+ }
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
+
+ parent = dentry->d_parent;
+ mutex_lock(&parent->d_inode->i_mutex);
+ __debugfs_remove(dentry, parent);
mutex_unlock(&parent->d_inode->i_mutex);
simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
-EXPORT_SYMBOL_GPL(debugfs_remove);
+EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
/**
* debugfs_rename - rename a file/directory in the debugfs filesystem
diff --git a/fs/ecryptfs/Makefile b/fs/ecryptfs/Makefile
index 1e34a7fd488..b4755a85996 100644
--- a/fs/ecryptfs/Makefile
+++ b/fs/ecryptfs/Makefile
@@ -4,4 +4,4 @@
obj-$(CONFIG_ECRYPT_FS) += ecryptfs.o
-ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o debug.o
+ecryptfs-objs := dentry.o file.o inode.o main.o super.o mmap.o read_write.o crypto.o keystore.o messaging.o netlink.o miscdev.o kthread.o debug.o
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index e2832bc7869..7b99917ffad 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -33,6 +33,7 @@
#include <linux/crypto.h>
#include <linux/file.h>
#include <linux/scatterlist.h>
+#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
static int
@@ -1032,10 +1033,8 @@ static int contains_ecryptfs_marker(char *data)
{
u32 m_1, m_2;
- memcpy(&m_1, data, 4);
- m_1 = be32_to_cpu(m_1);
- memcpy(&m_2, (data + 4), 4);
- m_2 = be32_to_cpu(m_2);
+ m_1 = get_unaligned_be32(data);
+ m_2 = get_unaligned_be32(data + 4);
if ((m_1 ^ MAGIC_ECRYPTFS_MARKER) == m_2)
return 1;
ecryptfs_printk(KERN_DEBUG, "m_1 = [0x%.8x]; m_2 = [0x%.8x]; "
@@ -1073,8 +1072,7 @@ static int ecryptfs_process_flags(struct ecryptfs_crypt_stat *crypt_stat,
int i;
u32 flags;
- memcpy(&flags, page_virt, 4);
- flags = be32_to_cpu(flags);
+ flags = get_unaligned_be32(page_virt);
for (i = 0; i < ((sizeof(ecryptfs_flag_map)
/ sizeof(struct ecryptfs_flag_map_elem))); i++)
if (flags & ecryptfs_flag_map[i].file_flag) {
@@ -1100,11 +1098,9 @@ static void write_ecryptfs_marker(char *page_virt, size_t *written)
get_random_bytes(&m_1, (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
m_2 = (m_1 ^ MAGIC_ECRYPTFS_MARKER);
- m_1 = cpu_to_be32(m_1);
- memcpy(page_virt, &m_1, (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
- m_2 = cpu_to_be32(m_2);
- memcpy(page_virt + (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2), &m_2,
- (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2));
+ put_unaligned_be32(m_1, page_virt);
+ page_virt += (MAGIC_ECRYPTFS_MARKER_SIZE_BYTES / 2);
+ put_unaligned_be32(m_2, page_virt);
(*written) = MAGIC_ECRYPTFS_MARKER_SIZE_BYTES;
}
@@ -1121,8 +1117,7 @@ write_ecryptfs_flags(char *page_virt, struct ecryptfs_crypt_stat *crypt_stat,
flags |= ecryptfs_flag_map[i].file_flag;
/* Version is in top 8 bits of the 32-bit flag vector */
flags |= ((((u8)crypt_stat->file_version) << 24) & 0xFF000000);
- flags = cpu_to_be32(flags);
- memcpy(page_virt, &flags, 4);
+ put_unaligned_be32(flags, page_virt);
(*written) = 4;
}
@@ -1238,11 +1233,9 @@ ecryptfs_write_header_metadata(char *virt,
num_header_extents_at_front =
(u16)(crypt_stat->num_header_bytes_at_front
/ crypt_stat->extent_size);
- header_extent_size = cpu_to_be32(header_extent_size);
- memcpy(virt, &header_extent_size, 4);
+ put_unaligned_be32(header_extent_size, virt);
virt += 4;
- num_header_extents_at_front = cpu_to_be16(num_header_extents_at_front);
- memcpy(virt, &num_header_extents_at_front, 2);
+ put_unaligned_be16(num_header_extents_at_front, virt);
(*written) = 6;
}
@@ -1410,15 +1403,13 @@ static int parse_header_metadata(struct ecryptfs_crypt_stat *crypt_stat,
u32 header_extent_size;
u16 num_header_extents_at_front;
- memcpy(&header_extent_size, virt, sizeof(u32));
- header_extent_size = be32_to_cpu(header_extent_size);
- virt += sizeof(u32);
- memcpy(&num_header_extents_at_front, virt, sizeof(u16));
- num_header_extents_at_front = be16_to_cpu(num_header_extents_at_front);
+ header_extent_size = get_unaligned_be32(virt);
+ virt += sizeof(__be32);
+ num_header_extents_at_front = get_unaligned_be16(virt);
crypt_stat->num_header_bytes_at_front =
(((size_t)num_header_extents_at_front
* (size_t)header_extent_size));
- (*bytes_read) = (sizeof(u32) + sizeof(u16));
+ (*bytes_read) = (sizeof(__be32) + sizeof(__be16));
if ((validate_header_size == ECRYPTFS_VALIDATE_HEADER_SIZE)
&& (crypt_stat->num_header_bytes_at_front
< ECRYPTFS_MINIMUM_HEADER_EXTENT_SIZE)) {
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index c15c25745e0..b73fb752c5f 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -559,10 +559,25 @@ extern struct kmem_cache *ecryptfs_key_record_cache;
extern struct kmem_cache *ecryptfs_key_sig_cache;
extern struct kmem_cache *ecryptfs_global_auth_tok_cache;
extern struct kmem_cache *ecryptfs_key_tfm_cache;
+extern struct kmem_cache *ecryptfs_open_req_cache;
+struct ecryptfs_open_req {
+#define ECRYPTFS_REQ_PROCESSED 0x00000001
+#define ECRYPTFS_REQ_DROPPED 0x00000002
+#define ECRYPTFS_REQ_ZOMBIE 0x00000004
+ u32 flags;
+ struct file **lower_file;
+ struct dentry *lower_dentry;
+ struct vfsmount *lower_mnt;
+ wait_queue_head_t wait;
+ struct mutex mux;
+ struct list_head kthread_ctl_list;
+};
+
+#define ECRYPTFS_INTERPOSE_FLAG_D_ADD 0x00000001
int ecryptfs_interpose(struct dentry *hidden_dentry,
struct dentry *this_dentry, struct super_block *sb,
- int flag);
+ u32 flags);
int ecryptfs_fill_zeros(struct file *file, loff_t new_length);
int ecryptfs_decode_filename(struct ecryptfs_crypt_stat *crypt_stat,
const char *name, int length,
@@ -690,5 +705,11 @@ void ecryptfs_msg_ctx_alloc_to_free(struct ecryptfs_msg_ctx *msg_ctx);
int
ecryptfs_spawn_daemon(struct ecryptfs_daemon **daemon, uid_t euid,
struct user_namespace *user_ns, struct pid *pid);
+int ecryptfs_init_kthread(void);
+void ecryptfs_destroy_kthread(void);
+int ecryptfs_privileged_open(struct file **lower_file,
+ struct dentry *lower_dentry,
+ struct vfsmount *lower_mnt);
+int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry);
#endif /* #ifndef ECRYPTFS_KERNEL_H */
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 24749bf0668..9244d653743 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -192,6 +192,23 @@ static int ecryptfs_open(struct inode *inode, struct file *file)
| ECRYPTFS_ENCRYPTED);
}
mutex_unlock(&crypt_stat->cs_mutex);
+ if ((ecryptfs_inode_to_private(inode)->lower_file->f_flags & O_RDONLY)
+ && !(file->f_flags & O_RDONLY)) {
+ rc = -EPERM;
+ printk(KERN_WARNING "%s: Lower persistent file is RO; eCryptfs "
+ "file must hence be opened RO\n", __func__);
+ goto out;
+ }
+ if (!ecryptfs_inode_to_private(inode)->lower_file) {
+ rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+ if (rc) {
+ printk(KERN_ERR "%s: Error attempting to initialize "
+ "the persistent file for the dentry with name "
+ "[%s]; rc = [%d]\n", __func__,
+ ecryptfs_dentry->d_name.name, rc);
+ goto out;
+ }
+ }
ecryptfs_set_file_lower(
file, ecryptfs_inode_to_private(inode)->lower_file);
if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index c92cc1c00aa..d755455e3bf 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -31,6 +31,7 @@
#include <linux/mount.h>
#include <linux/crypto.h>
#include <linux/fs_stack.h>
+#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
static struct dentry *lock_parent(struct dentry *dentry)
@@ -188,6 +189,16 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
"context; rc = [%d]\n", rc);
goto out;
}
+ if (!ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->lower_file) {
+ rc = ecryptfs_init_persistent_file(ecryptfs_dentry);
+ if (rc) {
+ printk(KERN_ERR "%s: Error attempting to initialize "
+ "the persistent file for the dentry with name "
+ "[%s]; rc = [%d]\n", __func__,
+ ecryptfs_dentry->d_name.name, rc);
+ goto out;
+ }
+ }
rc = ecryptfs_write_metadata(ecryptfs_dentry);
if (rc) {
printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
@@ -307,10 +318,11 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
d_add(dentry, NULL);
goto out;
}
- rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb, 1);
+ rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb,
+ ECRYPTFS_INTERPOSE_FLAG_D_ADD);
if (rc) {
ecryptfs_printk(KERN_ERR, "Error interposing\n");
- goto out_dput;
+ goto out;
}
if (S_ISDIR(lower_inode->i_mode)) {
ecryptfs_printk(KERN_DEBUG, "Is a directory; returning\n");
@@ -336,11 +348,21 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
rc = -ENOMEM;
ecryptfs_printk(KERN_ERR,
"Cannot ecryptfs_kmalloc a page\n");
- goto out_dput;
+ goto out;
}
crypt_stat = &ecryptfs_inode_to_private(dentry->d_inode)->crypt_stat;
if (!(crypt_stat->flags & ECRYPTFS_POLICY_APPLIED))
ecryptfs_set_default_sizes(crypt_stat);
+ if (!ecryptfs_inode_to_private(dentry->d_inode)->lower_file) {
+ rc = ecryptfs_init_persistent_file(dentry);
+ if (rc) {
+ printk(KERN_ERR "%s: Error attempting to initialize "
+ "the persistent file for the dentry with name "
+ "[%s]; rc = [%d]\n", __func__,
+ dentry->d_name.name, rc);
+ goto out;
+ }
+ }
rc = ecryptfs_read_and_validate_header_region(page_virt,
dentry->d_inode);
if (rc) {
@@ -364,8 +386,7 @@ static struct dentry *ecryptfs_lookup(struct inode *dir, struct dentry *dentry,
else
file_size = i_size_read(lower_dentry->d_inode);
} else {
- memcpy(&file_size, page_virt, sizeof(file_size));
- file_size = be64_to_cpu(file_size);
+ file_size = get_unaligned_be64(page_virt);
}
i_size_write(dentry->d_inode, (loff_t)file_size);
kmem_cache_free(ecryptfs_header_cache_2, page_virt);
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index e82b457180b..f5b76a331b9 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -44,15 +44,15 @@ static int process_request_key_err(long err_code)
int rc = 0;
switch (err_code) {
- case ENOKEY:
+ case -ENOKEY:
ecryptfs_printk(KERN_WARNING, "No key\n");
rc = -ENOENT;
break;
- case EKEYEXPIRED:
+ case -EKEYEXPIRED:
ecryptfs_printk(KERN_WARNING, "Key expired\n");
rc = -ETIME;
break;
- case EKEYREVOKED:
+ case -EKEYREVOKED:
ecryptfs_printk(KERN_WARNING, "Key revoked\n");
rc = -EINVAL;
break;
@@ -963,8 +963,7 @@ int ecryptfs_keyring_auth_tok_for_sig(struct key **auth_tok_key,
if (!(*auth_tok_key) || IS_ERR(*auth_tok_key)) {
printk(KERN_ERR "Could not find key with description: [%s]\n",
sig);
- process_request_key_err(PTR_ERR(*auth_tok_key));
- rc = -EINVAL;
+ rc = process_request_key_err(PTR_ERR(*auth_tok_key));
goto out;
}
(*auth_tok) = ecryptfs_get_key_payload_data(*auth_tok_key);
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
new file mode 100644
index 00000000000..c440c6b58b2
--- /dev/null
+++ b/fs/ecryptfs/kthread.c
@@ -0,0 +1,203 @@
+/**
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 2008 International Business Machines Corp.
+ * Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
+ * 02111-1307, USA.
+ */
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
+#include <linux/mount.h>
+#include "ecryptfs_kernel.h"
+
+struct kmem_cache *ecryptfs_open_req_cache;
+
+static struct ecryptfs_kthread_ctl {
+#define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
+ u32 flags;
+ struct mutex mux;
+ struct list_head req_list;
+ wait_queue_head_t wait;
+} ecryptfs_kthread_ctl;
+
+static struct task_struct *ecryptfs_kthread;
+
+/**
+ * ecryptfs_threadfn
+ * @ignored: ignored
+ *
+ * The eCryptfs kernel thread that has the responsibility of getting
+ * the lower persistent file with RW permissions.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_threadfn(void *ignored)
+{
+ set_freezable();
+ while (1) {
+ struct ecryptfs_open_req *req;
+
+ wait_event_freezable(
+ ecryptfs_kthread_ctl.wait,
+ (!list_empty(&ecryptfs_kthread_ctl.req_list)
+ || kthread_should_stop()));
+ mutex_lock(&ecryptfs_kthread_ctl.mux);
+ if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+ mutex_unlock(&ecryptfs_kthread_ctl.mux);
+ goto out;
+ }
+ while (!list_empty(&ecryptfs_kthread_ctl.req_list)) {
+ req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
+ struct ecryptfs_open_req,
+ kthread_ctl_list);
+ mutex_lock(&req->mux);
+ list_del(&req->kthread_ctl_list);
+ if (!(req->flags & ECRYPTFS_REQ_ZOMBIE)) {
+ dget(req->lower_dentry);
+ mntget(req->lower_mnt);
+ (*req->lower_file) = dentry_open(
+ req->lower_dentry, req->lower_mnt,
+ (O_RDWR | O_LARGEFILE));
+ req->flags |= ECRYPTFS_REQ_PROCESSED;
+ }
+ wake_up(&req->wait);
+ mutex_unlock(&req->mux);
+ }
+ mutex_unlock(&ecryptfs_kthread_ctl.mux);
+ }
+out:
+ return 0;
+}
+
+int ecryptfs_init_kthread(void)
+{
+ int rc = 0;
+
+ mutex_init(&ecryptfs_kthread_ctl.mux);
+ init_waitqueue_head(&ecryptfs_kthread_ctl.wait);
+ INIT_LIST_HEAD(&ecryptfs_kthread_ctl.req_list);
+ ecryptfs_kthread = kthread_run(&ecryptfs_threadfn, NULL,
+ "ecryptfs-kthread");
+ if (IS_ERR(ecryptfs_kthread)) {
+ rc = PTR_ERR(ecryptfs_kthread);
+ printk(KERN_ERR "%s: Failed to create kernel thread; rc = [%d]"
+ "\n", __func__, rc);
+ }
+ return rc;
+}
+
+void ecryptfs_destroy_kthread(void)
+{
+ struct ecryptfs_open_req *req;
+
+ mutex_lock(&ecryptfs_kthread_ctl.mux);
+ ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
+ list_for_each_entry(req, &ecryptfs_kthread_ctl.req_list,
+ kthread_ctl_list) {
+ mutex_lock(&req->mux);
+ req->flags |= ECRYPTFS_REQ_ZOMBIE;
+ wake_up(&req->wait);
+ mutex_unlock(&req->mux);
+ }
+ mutex_unlock(&ecryptfs_kthread_ctl.mux);
+ kthread_stop(ecryptfs_kthread);
+ wake_up(&ecryptfs_kthread_ctl.wait);
+}
+
+/**
+ * ecryptfs_privileged_open
+ * @lower_file: Result of dentry_open by root on lower dentry
+ * @lower_dentry: Lower dentry for file to open
+ * @lower_mnt: Lower vfsmount for file to open
+ *
+ * This function gets a r/w file opened againt the lower dentry.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_privileged_open(struct file **lower_file,
+ struct dentry *lower_dentry,
+ struct vfsmount *lower_mnt)
+{
+ struct ecryptfs_open_req *req;
+ int rc = 0;
+
+ /* Corresponding dput() and mntput() are done when the
+ * persistent file is fput() when the eCryptfs inode is
+ * destroyed. */
+ dget(lower_dentry);
+ mntget(lower_mnt);
+ (*lower_file) = dentry_open(lower_dentry, lower_mnt,
+ (O_RDWR | O_LARGEFILE));
+ if (!IS_ERR(*lower_file))
+ goto out;
+ req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL);
+ if (!req) {
+ rc = -ENOMEM;
+ goto out;
+ }
+ mutex_init(&req->mux);
+ req->lower_file = lower_file;
+ req->lower_dentry = lower_dentry;
+ req->lower_mnt = lower_mnt;
+ init_waitqueue_head(&req->wait);
+ req->flags = 0;
+ mutex_lock(&ecryptfs_kthread_ctl.mux);
+ if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+ rc = -EIO;
+ mutex_unlock(&ecryptfs_kthread_ctl.mux);
+ printk(KERN_ERR "%s: We are in the middle of shutting down; "
+ "aborting privileged request to open lower file\n",
+ __func__);
+ goto out_free;
+ }
+ list_add_tail(&req->kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+ mutex_unlock(&ecryptfs_kthread_ctl.mux);
+ wake_up(&ecryptfs_kthread_ctl.wait);
+ wait_event(req->wait, (req->flags != 0));
+ mutex_lock(&req->mux);
+ BUG_ON(req->flags == 0);
+ if (req->flags & ECRYPTFS_REQ_DROPPED
+ || req->flags & ECRYPTFS_REQ_ZOMBIE) {
+ rc = -EIO;
+ printk(KERN_WARNING "%s: Privileged open request dropped\n",
+ __func__);
+ goto out_unlock;
+ }
+ if (IS_ERR(*req->lower_file)) {
+ rc = PTR_ERR(*req->lower_file);
+ dget(lower_dentry);
+ mntget(lower_mnt);
+ (*lower_file) = dentry_open(lower_dentry, lower_mnt,
+ (O_RDONLY | O_LARGEFILE));
+ if (IS_ERR(*lower_file)) {
+ rc = PTR_ERR(*req->lower_file);
+ (*lower_file) = NULL;
+ printk(KERN_WARNING "%s: Error attempting privileged "
+ "open of lower file with either RW or RO "
+ "perms; rc = [%d]. Giving up.\n",
+ __func__, rc);
+ }
+ }
+out_unlock:
+ mutex_unlock(&req->mux);
+out_free:
+ kmem_cache_free(ecryptfs_open_req_cache, req);
+out:
+ return rc;
+}
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index d603631601e..6f403cfba14 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -117,7 +117,7 @@ void __ecryptfs_printk(const char *fmt, ...)
*
* Returns zero on success; non-zero otherwise
*/
-static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
+int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
{
struct ecryptfs_inode_info *inode_info =
ecryptfs_inode_to_private(ecryptfs_dentry->d_inode);
@@ -130,26 +130,12 @@ static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
ecryptfs_dentry_to_lower_mnt(ecryptfs_dentry);
lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
- /* Corresponding dput() and mntput() are done when the
- * persistent file is fput() when the eCryptfs inode
- * is destroyed. */
- dget(lower_dentry);
- mntget(lower_mnt);
- inode_info->lower_file = dentry_open(lower_dentry,
- lower_mnt,
- (O_RDWR | O_LARGEFILE));
- if (IS_ERR(inode_info->lower_file)) {
- dget(lower_dentry);
- mntget(lower_mnt);
- inode_info->lower_file = dentry_open(lower_dentry,
- lower_mnt,
- (O_RDONLY
- | O_LARGEFILE));
- }
- if (IS_ERR(inode_info->lower_file)) {
+ rc = ecryptfs_privileged_open(&inode_info->lower_file,
+ lower_dentry, lower_mnt);
+ if (rc || IS_ERR(inode_info->lower_file)) {
printk(KERN_ERR "Error opening lower persistent file "
- "for lower_dentry [0x%p] and lower_mnt [0x%p]\n",
- lower_dentry, lower_mnt);
+ "for lower_dentry [0x%p] and lower_mnt [0x%p]; "
+ "rc = [%d]\n", lower_dentry, lower_mnt, rc);
rc = PTR_ERR(inode_info->lower_file);
inode_info->lower_file = NULL;
}
@@ -163,14 +149,14 @@ static int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry)
* @lower_dentry: Existing dentry in the lower filesystem
* @dentry: ecryptfs' dentry
* @sb: ecryptfs's super_block
- * @flag: If set to true, then d_add is called, else d_instantiate is called
+ * @flags: flags to govern behavior of interpose procedure
*
* Interposes upper and lower dentries.
*
* Returns zero on success; non-zero otherwise
*/
int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
- struct super_block *sb, int flag)
+ struct super_block *sb, u32 flags)
{
struct inode *lower_inode;
struct inode *inode;
@@ -207,7 +193,7 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
init_special_inode(inode, lower_inode->i_mode,
lower_inode->i_rdev);
dentry->d_op = &ecryptfs_dops;
- if (flag)
+ if (flags & ECRYPTFS_INTERPOSE_FLAG_D_ADD)
d_add(dentry, inode);
else
d_instantiate(dentry, inode);
@@ -215,13 +201,6 @@ int ecryptfs_interpose(struct dentry *lower_dentry, struct dentry *dentry,
/* This size will be overwritten for real files w/ headers and
* other metadata */
fsstack_copy_inode_size(inode, lower_inode);
- rc = ecryptfs_init_persistent_file(dentry);
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to initialize the "
- "persistent file for the dentry with name [%s]; "
- "rc = [%d]\n", __func__, dentry->d_name.name, rc);
- goto out;
- }
out:
return rc;
}
@@ -262,10 +241,11 @@ static int ecryptfs_init_global_auth_toks(
"session keyring for sig specified in mount "
"option: [%s]\n", global_auth_tok->sig);
global_auth_tok->flags |= ECRYPTFS_AUTH_TOK_INVALID;
- rc = 0;
+ goto out;
} else
global_auth_tok->flags &= ~ECRYPTFS_AUTH_TOK_INVALID;
}
+out:
return rc;
}
@@ -314,7 +294,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
char *cipher_name_dst;
char *cipher_name_src;
char *cipher_key_bytes_src;
- int cipher_name_len;
if (!options) {
rc = -EINVAL;
@@ -395,17 +374,12 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
goto out;
}
if (!cipher_name_set) {
- cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
- if (unlikely(cipher_name_len
- >= ECRYPTFS_MAX_CIPHER_NAME_SIZE)) {
- rc = -EINVAL;
- BUG();
- goto out;
- }
- memcpy(mount_crypt_stat->global_default_cipher_name,
- ECRYPTFS_DEFAULT_CIPHER, cipher_name_len);
- mount_crypt_stat->global_default_cipher_name[cipher_name_len]
- = '\0';
+ int cipher_name_len = strlen(ECRYPTFS_DEFAULT_CIPHER);
+
+ BUG_ON(cipher_name_len >= ECRYPTFS_MAX_CIPHER_NAME_SIZE);
+
+ strcpy(mount_crypt_stat->global_default_cipher_name,
+ ECRYPTFS_DEFAULT_CIPHER);
}
if (!cipher_key_bytes_set) {
mount_crypt_stat->global_default_cipher_key_size = 0;
@@ -430,7 +404,6 @@ static int ecryptfs_parse_options(struct super_block *sb, char *options)
printk(KERN_WARNING "One or more global auth toks could not "
"properly register; rc = [%d]\n", rc);
}
- rc = 0;
out:
return rc;
}
@@ -679,6 +652,11 @@ static struct ecryptfs_cache_info {
.name = "ecryptfs_key_tfm_cache",
.size = sizeof(struct ecryptfs_key_tfm),
},
+ {
+ .cache = &ecryptfs_open_req_cache,
+ .name = "ecryptfs_open_req_cache",
+ .size = sizeof(struct ecryptfs_open_req),
+ },
};
static void ecryptfs_free_kmem_caches(void)
@@ -795,11 +773,17 @@ static int __init ecryptfs_init(void)
printk(KERN_ERR "sysfs registration failed\n");
goto out_unregister_filesystem;
}
+ rc = ecryptfs_init_kthread();
+ if (rc) {
+ printk(KERN_ERR "%s: kthread initialization failed; "
+ "rc = [%d]\n", __func__, rc);
+ goto out_do_sysfs_unregistration;
+ }
rc = ecryptfs_init_messaging(ecryptfs_transport);
if (rc) {
- ecryptfs_printk(KERN_ERR, "Failure occured while attempting to "
+ printk(KERN_ERR "Failure occured while attempting to "
"initialize the eCryptfs netlink socket\n");
- goto out_do_sysfs_unregistration;
+ goto out_destroy_kthread;
}
rc = ecryptfs_init_crypto();
if (rc) {
@@ -814,6 +798,8 @@ static int __init ecryptfs_init(void)
goto out;
out_release_messaging:
ecryptfs_release_messaging(ecryptfs_transport);
+out_destroy_kthread:
+ ecryptfs_destroy_kthread();
out_do_sysfs_unregistration:
do_sysfs_unregistration();
out_unregister_filesystem:
@@ -833,6 +819,7 @@ static void __exit ecryptfs_exit(void)
printk(KERN_ERR "Failure whilst attempting to destroy crypto; "
"rc = [%d]\n", rc);
ecryptfs_release_messaging(ecryptfs_transport);
+ ecryptfs_destroy_kthread();
do_sysfs_unregistration();
unregister_filesystem(&ecryptfs_fs_type);
ecryptfs_free_kmem_caches();
diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c
index 09a4522f65e..b484792a099 100644
--- a/fs/ecryptfs/miscdev.c
+++ b/fs/ecryptfs/miscdev.c
@@ -358,46 +358,6 @@ out_unlock_daemon:
}
/**
- * ecryptfs_miscdev_helo
- * @euid: effective user id of miscdevess sending helo packet
- * @user_ns: The namespace in which @euid applies
- * @pid: miscdevess id of miscdevess sending helo packet
- *
- * Returns zero on success; non-zero otherwise
- */
-static int ecryptfs_miscdev_helo(uid_t euid, struct user_namespace *user_ns,
- struct pid *pid)
-{
- int rc;
-
- rc = ecryptfs_process_helo(ECRYPTFS_TRANSPORT_MISCDEV, euid, user_ns,
- pid);
- if (rc)
- printk(KERN_WARNING "Error processing HELO; rc = [%d]\n", rc);
- return rc;
-}
-
-/**
- * ecryptfs_miscdev_quit
- * @euid: effective user id of miscdevess sending quit packet
- * @user_ns: The namespace in which @euid applies
- * @pid: miscdevess id of miscdevess sending quit packet
- *
- * Returns zero on success; non-zero otherwise
- */
-static int ecryptfs_miscdev_quit(uid_t euid, struct user_namespace *user_ns,
- struct pid *pid)
-{
- int rc;
-
- rc = ecryptfs_process_quit(euid, user_ns, pid);
- if (rc)
- printk(KERN_WARNING
- "Error processing QUIT message; rc = [%d]\n", rc);
- return rc;
-}
-
-/**
* ecryptfs_miscdev_response - miscdevess response to message previously sent to daemon
* @data: Bytes comprising struct ecryptfs_message
* @data_size: sizeof(struct ecryptfs_message) + data len
@@ -512,26 +472,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf,
__func__, rc);
break;
case ECRYPTFS_MSG_HELO:
- rc = ecryptfs_miscdev_helo(current->euid,
- current->nsproxy->user_ns,
- task_pid(current));
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to process "
- "helo from pid [0x%p]; rc = [%d]\n", __func__,
- task_pid(current), rc);
- goto out_free;
- }
- break;
case ECRYPTFS_MSG_QUIT:
- rc = ecryptfs_miscdev_quit(current->euid,
- current->nsproxy->user_ns,
- task_pid(current));
- if (rc) {
- printk(KERN_ERR "%s: Error attempting to process "
- "quit from pid [0x%p]; rc = [%d]\n", __func__,
- task_pid(current), rc);
- goto out_free;
- }
break;
default:
ecryptfs_printk(KERN_WARNING, "Dropping miscdev "
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 2b6fe1e6e8b..245c2dc02d5 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -32,6 +32,7 @@
#include <linux/file.h>
#include <linux/crypto.h>
#include <linux/scatterlist.h>
+#include <asm/unaligned.h>
#include "ecryptfs_kernel.h"
/**
@@ -372,7 +373,6 @@ out:
*/
static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
{
- u64 file_size;
char *file_size_virt;
int rc;
@@ -381,9 +381,7 @@ static int ecryptfs_write_inode_size_to_header(struct inode *ecryptfs_inode)
rc = -ENOMEM;
goto out;
}
- file_size = (u64)i_size_read(ecryptfs_inode);
- file_size = cpu_to_be64(file_size);
- memcpy(file_size_virt, &file_size, sizeof(u64));
+ put_unaligned_be64(i_size_read(ecryptfs_inode), file_size_virt);
rc = ecryptfs_write_lower(ecryptfs_inode, file_size_virt, 0,
sizeof(u64));
kfree(file_size_virt);
@@ -403,7 +401,6 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
struct dentry *lower_dentry =
ecryptfs_inode_to_private(ecryptfs_inode)->lower_file->f_dentry;
struct inode *lower_inode = lower_dentry->d_inode;
- u64 file_size;
int rc;
if (!lower_inode->i_op->getxattr || !lower_inode->i_op->setxattr) {
@@ -424,9 +421,7 @@ static int ecryptfs_write_inode_size_to_xattr(struct inode *ecryptfs_inode)
xattr_virt, PAGE_CACHE_SIZE);
if (size < 0)
size = 8;
- file_size = (u64)i_size_read(ecryptfs_inode);
- file_size = cpu_to_be64(file_size);
- memcpy(xattr_virt, &file_size, sizeof(u64));
+ put_unaligned_be64(i_size_read(ecryptfs_inode), xattr_virt);
rc = lower_inode->i_op->setxattr(lower_dentry, ECRYPTFS_XATTR_NAME,
xattr_virt, size, 0);
mutex_unlock(&lower_inode->i_mutex);
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 343942deeec..08bf558d040 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -198,11 +198,18 @@ struct file *eventfd_fget(int fd)
return file;
}
-asmlinkage long sys_eventfd(unsigned int count)
+asmlinkage long sys_eventfd2(unsigned int count, int flags)
{
int fd;
struct eventfd_ctx *ctx;
+ /* Check the EFD_* constants for consistency. */
+ BUILD_BUG_ON(EFD_CLOEXEC != O_CLOEXEC);
+ BUILD_BUG_ON(EFD_NONBLOCK != O_NONBLOCK);
+
+ if (flags & ~(EFD_CLOEXEC | EFD_NONBLOCK))
+ return -EINVAL;
+
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return -ENOMEM;
@@ -214,9 +221,15 @@ asmlinkage long sys_eventfd(unsigned int count)
* When we call this, the initialization must be complete, since
* anon_inode_getfd() will install the fd.
*/
- fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx);
+ fd = anon_inode_getfd("[eventfd]", &eventfd_fops, ctx,
+ flags & (O_CLOEXEC | O_NONBLOCK));
if (fd < 0)
kfree(ctx);
return fd;
}
+asmlinkage long sys_eventfd(unsigned int count)
+{
+ return sys_eventfd2(count, 0);
+}
+
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 990c01d2d66..0c87474f791 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1046,20 +1046,25 @@ retry:
* RB tree. With the current implementation, the "size" parameter is ignored
* (besides sanity checks).
*/
-asmlinkage long sys_epoll_create(int size)
+asmlinkage long sys_epoll_create1(int flags)
{
int error, fd = -1;
struct eventpoll *ep;
+ /* Check the EPOLL_* constant for consistency. */
+ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);
+
+ if (flags & ~EPOLL_CLOEXEC)
+ return -EINVAL;
+
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d)\n",
- current, size));
+ current, flags));
/*
- * Sanity check on the size parameter, and create the internal data
- * structure ( "struct eventpoll" ).
+ * Create the internal data structure ( "struct eventpoll" ).
*/
- error = -EINVAL;
- if (size <= 0 || (error = ep_alloc(&ep)) < 0) {
+ error = ep_alloc(&ep);
+ if (error < 0) {
fd = error;
goto error_return;
}
@@ -1068,17 +1073,26 @@ asmlinkage long sys_epoll_create(int size)
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
- fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep);
+ fd = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
+ flags & O_CLOEXEC);
if (fd < 0)
ep_free(ep);
error_return:
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n",
- current, size, fd));
+ current, flags, fd));
return fd;
}
+asmlinkage long sys_epoll_create(int size)
+{
+ if (size < 0)
+ return -EINVAL;
+
+ return sys_epoll_create1(0);
+}
+
/*
* The following function implements the controller interface for
* the eventpoll file that enables the insertion/removal/change of
diff --git a/fs/exec.c b/fs/exec.c
index fd9234379e8..190ed1f9277 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -541,7 +541,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
/*
* when the old and new regions overlap clear from new_end.
*/
- free_pgd_range(&tlb, new_end, old_end, new_end,
+ free_pgd_range(tlb, new_end, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : 0);
} else {
/*
@@ -550,7 +550,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
* have constraints on va-space that make this illegal (IA64) -
* for the others its just a little faster.
*/
- free_pgd_range(&tlb, old_start, old_end, new_end,
+ free_pgd_range(tlb, old_start, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : 0);
}
tlb_finish_mmu(tlb, new_end, old_end);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 330a7d78259..9679fcbdeaa 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -125,13 +125,16 @@ static int dupfd(struct file *file, unsigned int start, int cloexec)
return fd;
}
-asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
+asmlinkage long sys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
{
int err = -EBADF;
struct file * file, *tofree;
struct files_struct * files = current->files;
struct fdtable *fdt;
+ if ((flags & ~O_CLOEXEC) != 0)
+ return -EINVAL;
+
spin_lock(&files->file_lock);
if (!(file = fcheck(oldfd)))
goto out_unlock;
@@ -163,7 +166,10 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
rcu_assign_pointer(fdt->fd[newfd], file);
FD_SET(newfd, fdt->open_fds);
- FD_CLR(newfd, fdt->close_on_exec);
+ if (flags & O_CLOEXEC)
+ FD_SET(newfd, fdt->close_on_exec);
+ else
+ FD_CLR(newfd, fdt->close_on_exec);
spin_unlock(&files->file_lock);
if (tofree)
@@ -181,6 +187,11 @@ out_fput:
goto out;
}
+asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd)
+{
+ return sys_dup3(oldfd, newfd, 0);
+}
+
asmlinkage long sys_dup(unsigned int fildes)
{
int ret = -EBADF;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index aeabf80f81a..dbd01d262ca 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -53,6 +53,7 @@ int sysctl_hugetlb_shm_group;
enum {
Opt_size, Opt_nr_inodes,
Opt_mode, Opt_uid, Opt_gid,
+ Opt_pagesize,
Opt_err,
};
@@ -62,6 +63,7 @@ static match_table_t tokens = {
{Opt_mode, "mode=%o"},
{Opt_uid, "uid=%u"},
{Opt_gid, "gid=%u"},
+ {Opt_pagesize, "pagesize=%s"},
{Opt_err, NULL},
};
@@ -80,6 +82,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
struct inode *inode = file->f_path.dentry->d_inode;
loff_t len, vma_len;
int ret;
+ struct hstate *h = hstate_file(file);
/*
* vma address alignment (but not the pgoff alignment) has
@@ -92,7 +95,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
vma->vm_ops = &hugetlb_vm_ops;
- if (vma->vm_pgoff & ~(HPAGE_MASK >> PAGE_SHIFT))
+ if (vma->vm_pgoff & ~(huge_page_mask(h) >> PAGE_SHIFT))
return -EINVAL;
vma_len = (loff_t)(vma->vm_end - vma->vm_start);
@@ -103,9 +106,9 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
ret = -ENOMEM;
len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
- if (vma->vm_flags & VM_MAYSHARE &&
- hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
- len >> HPAGE_SHIFT))
+ if (hugetlb_reserve_pages(inode,
+ vma->vm_pgoff >> huge_page_order(h),
+ len >> huge_page_shift(h), vma))
goto out;
ret = 0;
@@ -130,20 +133,21 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long start_addr;
+ struct hstate *h = hstate_file(file);
- if (len & ~HPAGE_MASK)
+ if (len & ~huge_page_mask(h))
return -EINVAL;
if (len > TASK_SIZE)
return -ENOMEM;
if (flags & MAP_FIXED) {
- if (prepare_hugepage_range(addr, len))
+ if (prepare_hugepage_range(file, addr, len))
return -EINVAL;
return addr;
}
if (addr) {
- addr = ALIGN(addr, HPAGE_SIZE);
+ addr = ALIGN(addr, huge_page_size(h));
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
(!vma || addr + len <= vma->vm_start))
@@ -156,7 +160,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
start_addr = TASK_UNMAPPED_BASE;
full_search:
- addr = ALIGN(start_addr, HPAGE_SIZE);
+ addr = ALIGN(start_addr, huge_page_size(h));
for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
/* At this point: (!vma || addr < vma->vm_end). */
@@ -174,7 +178,7 @@ full_search:
if (!vma || addr + len <= vma->vm_start)
return addr;
- addr = ALIGN(vma->vm_end, HPAGE_SIZE);
+ addr = ALIGN(vma->vm_end, huge_page_size(h));
}
}
#endif
@@ -225,10 +229,11 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
size_t len, loff_t *ppos)
{
+ struct hstate *h = hstate_file(filp);
struct address_space *mapping = filp->f_mapping;
struct inode *inode = mapping->host;
- unsigned long index = *ppos >> HPAGE_SHIFT;
- unsigned long offset = *ppos & ~HPAGE_MASK;
+ unsigned long index = *ppos >> huge_page_shift(h);
+ unsigned long offset = *ppos & ~huge_page_mask(h);
unsigned long end_index;
loff_t isize;
ssize_t retval = 0;
@@ -243,17 +248,17 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
if (!isize)
goto out;
- end_index = (isize - 1) >> HPAGE_SHIFT;
+ end_index = (isize - 1) >> huge_page_shift(h);
for (;;) {
struct page *page;
- int nr, ret;
+ unsigned long nr, ret;
/* nr is the maximum number of bytes to copy from this page */
- nr = HPAGE_SIZE;
+ nr = huge_page_size(h);
if (index >= end_index) {
if (index > end_index)
goto out;
- nr = ((isize - 1) & ~HPAGE_MASK) + 1;
+ nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
if (nr <= offset) {
goto out;
}
@@ -287,8 +292,8 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
offset += ret;
retval += ret;
len -= ret;
- index += offset >> HPAGE_SHIFT;
- offset &= ~HPAGE_MASK;
+ index += offset >> huge_page_shift(h);
+ offset &= ~huge_page_mask(h);
if (page)
page_cache_release(page);
@@ -298,7 +303,7 @@ static ssize_t hugetlbfs_read(struct file *filp, char __user *buf,
break;
}
out:
- *ppos = ((loff_t)index << HPAGE_SHIFT) + offset;
+ *ppos = ((loff_t)index << huge_page_shift(h)) + offset;
mutex_unlock(&inode->i_mutex);
return retval;
}
@@ -339,8 +344,9 @@ static void truncate_huge_page(struct page *page)
static void truncate_hugepages(struct inode *inode, loff_t lstart)
{
+ struct hstate *h = hstate_inode(inode);
struct address_space *mapping = &inode->i_data;
- const pgoff_t start = lstart >> HPAGE_SHIFT;
+ const pgoff_t start = lstart >> huge_page_shift(h);
struct pagevec pvec;
pgoff_t next;
int i, freed = 0;
@@ -441,7 +447,7 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, pgoff_t pgoff)
v_offset = 0;
__unmap_hugepage_range(vma,
- vma->vm_start + v_offset, vma->vm_end);
+ vma->vm_start + v_offset, vma->vm_end, NULL);
}
}
@@ -449,8 +455,9 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
pgoff_t pgoff;
struct address_space *mapping = inode->i_mapping;
+ struct hstate *h = hstate_inode(inode);
- BUG_ON(offset & ~HPAGE_MASK);
+ BUG_ON(offset & ~huge_page_mask(h));
pgoff = offset >> PAGE_SHIFT;
i_size_write(inode, offset);
@@ -465,6 +472,7 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
+ struct hstate *h = hstate_inode(inode);
int error;
unsigned int ia_valid = attr->ia_valid;
@@ -476,7 +484,7 @@ static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
if (ia_valid & ATTR_SIZE) {
error = -EINVAL;
- if (!(attr->ia_size & ~HPAGE_MASK))
+ if (!(attr->ia_size & ~huge_page_mask(h)))
error = hugetlb_vmtruncate(inode, attr->ia_size);
if (error)
goto out;
@@ -610,9 +618,10 @@ static int hugetlbfs_set_page_dirty(struct page *page)
static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
+ struct hstate *h = hstate_inode(dentry->d_inode);
buf->f_type = HUGETLBFS_MAGIC;
- buf->f_bsize = HPAGE_SIZE;
+ buf->f_bsize = huge_page_size(h);
if (sbinfo) {
spin_lock(&sbinfo->stat_lock);
/* If no limits set, just report 0 for max/free/used
@@ -743,6 +752,8 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
char *p, *rest;
substring_t args[MAX_OPT_ARGS];
int option;
+ unsigned long long size = 0;
+ enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;
if (!options)
return 0;
@@ -773,17 +784,13 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
break;
case Opt_size: {
- unsigned long long size;
/* memparse() will accept a K/M/G without a digit */
if (!isdigit(*args[0].from))
goto bad_val;
size = memparse(args[0].from, &rest);
- if (*rest == '%') {
- size <<= HPAGE_SHIFT;
- size *= max_huge_pages;
- do_div(size, 100);
- }
- pconfig->nr_blocks = (size >> HPAGE_SHIFT);
+ setsize = SIZE_STD;
+ if (*rest == '%')
+ setsize = SIZE_PERCENT;
break;
}
@@ -794,6 +801,19 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
pconfig->nr_inodes = memparse(args[0].from, &rest);
break;
+ case Opt_pagesize: {
+ unsigned long ps;
+ ps = memparse(args[0].from, &rest);
+ pconfig->hstate = size_to_hstate(ps);
+ if (!pconfig->hstate) {
+ printk(KERN_ERR
+ "hugetlbfs: Unsupported page size %lu MB\n",
+ ps >> 20);
+ return -EINVAL;
+ }
+ break;
+ }
+
default:
printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
p);
@@ -801,6 +821,18 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
break;
}
}
+
+ /* Do size after hstate is set up */
+ if (setsize > NO_SIZE) {
+ struct hstate *h = pconfig->hstate;
+ if (setsize == SIZE_PERCENT) {
+ size <<= huge_page_shift(h);
+ size *= h->max_huge_pages;
+ do_div(size, 100);
+ }
+ pconfig->nr_blocks = (size >> huge_page_shift(h));
+ }
+
return 0;
bad_val:
@@ -825,6 +857,7 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
config.uid = current->fsuid;
config.gid = current->fsgid;
config.mode = 0755;
+ config.hstate = &default_hstate;
ret = hugetlbfs_parse_options(data, &config);
if (ret)
return ret;
@@ -833,14 +866,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
if (!sbinfo)
return -ENOMEM;
sb->s_fs_info = sbinfo;
+ sbinfo->hstate = config.hstate;
spin_lock_init(&sbinfo->stat_lock);
sbinfo->max_blocks = config.nr_blocks;
sbinfo->free_blocks = config.nr_blocks;
sbinfo->max_inodes = config.nr_inodes;
sbinfo->free_inodes = config.nr_inodes;
sb->s_maxbytes = MAX_LFS_FILESIZE;
- sb->s_blocksize = HPAGE_SIZE;
- sb->s_blocksize_bits = HPAGE_SHIFT;
+ sb->s_blocksize = huge_page_size(config.hstate);
+ sb->s_blocksize_bits = huge_page_shift(config.hstate);
sb->s_magic = HUGETLBFS_MAGIC;
sb->s_op = &hugetlbfs_ops;
sb->s_time_gran = 1;
@@ -942,7 +976,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size)
goto out_dentry;
error = -ENOMEM;
- if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT))
+ if (hugetlb_reserve_pages(inode, 0,
+ size >> huge_page_shift(hstate_inode(inode)), NULL))
goto out_inode;
d_instantiate(dentry, inode);
diff --git a/fs/inotify_user.c b/fs/inotify_user.c
index 6676c06bb7c..fe79c25d95d 100644
--- a/fs/inotify_user.c
+++ b/fs/inotify_user.c
@@ -566,7 +566,7 @@ static const struct inotify_operations inotify_user_ops = {
.destroy_watch = free_inotify_user_watch,
};
-asmlinkage long sys_inotify_init(void)
+asmlinkage long sys_inotify_init1(int flags)
{
struct inotify_device *dev;
struct inotify_handle *ih;
@@ -574,7 +574,14 @@ asmlinkage long sys_inotify_init(void)
struct file *filp;
int fd, ret;
- fd = get_unused_fd();
+ /* Check the IN_* constants for consistency. */
+ BUILD_BUG_ON(IN_CLOEXEC != O_CLOEXEC);
+ BUILD_BUG_ON(IN_NONBLOCK != O_NONBLOCK);
+
+ if (flags & ~(IN_CLOEXEC | IN_NONBLOCK))
+ return -EINVAL;
+
+ fd = get_unused_fd_flags(flags & O_CLOEXEC);
if (fd < 0)
return fd;
@@ -610,7 +617,7 @@ asmlinkage long sys_inotify_init(void)
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;
- filp->f_flags = O_RDONLY;
+ filp->f_flags = O_RDONLY | (flags & O_NONBLOCK);
filp->private_data = dev;
INIT_LIST_HEAD(&dev->events);
@@ -638,6 +645,11 @@ out_put_fd:
return ret;
}
+asmlinkage long sys_inotify_init(void)
+{
+ return sys_inotify_init1(0);
+}
+
asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
{
struct inode *inode;
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 46763d1cd39..8478fc25dae 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -127,7 +127,7 @@ enum {
Opt_err
};
-static match_table_t __initdata tokens = {
+static match_table_t __initconst tokens = {
{Opt_port, "port=%u"},
{Opt_rsize, "rsize=%u"},
{Opt_wsize, "wsize=%u"},
diff --git a/fs/open.c b/fs/open.c
index a99ad09c319..bb98d2fe809 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -64,7 +64,8 @@ static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
memcpy(buf, &st, sizeof(st));
else {
if (sizeof buf->f_blocks == 4) {
- if ((st.f_blocks | st.f_bfree | st.f_bavail) &
+ if ((st.f_blocks | st.f_bfree | st.f_bavail |
+ st.f_bsize | st.f_frsize) &
0xffffffff00000000ULL)
return -EOVERFLOW;
/*
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 6149e4b58c8..efef715135d 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -401,7 +401,7 @@ void register_disk(struct gendisk *disk)
disk->dev.parent = disk->driverfs_dev;
disk->dev.devt = MKDEV(disk->major, disk->first_minor);
- strlcpy(disk->dev.bus_id, disk->disk_name, KOBJ_NAME_LEN);
+ strlcpy(disk->dev.bus_id, disk->disk_name, BUS_ID_SIZE);
/* ewww... some of these buggers have / in the name... */
s = strchr(disk->dev.bus_id, '/');
if (s)
diff --git a/fs/pipe.c b/fs/pipe.c
index 700f4e0d957..10c4e9aa5c4 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -950,7 +950,7 @@ fail_inode:
return NULL;
}
-struct file *create_write_pipe(void)
+struct file *create_write_pipe(int flags)
{
int err;
struct inode *inode;
@@ -983,7 +983,7 @@ struct file *create_write_pipe(void)
goto err_dentry;
f->f_mapping = inode->i_mapping;
- f->f_flags = O_WRONLY;
+ f->f_flags = O_WRONLY | (flags & O_NONBLOCK);
f->f_version = 0;
return f;
@@ -1007,7 +1007,7 @@ void free_write_pipe(struct file *f)
put_filp(f);
}
-struct file *create_read_pipe(struct file *wrf)
+struct file *create_read_pipe(struct file *wrf, int flags)
{
struct file *f = get_empty_filp();
if (!f)
@@ -1019,7 +1019,7 @@ struct file *create_read_pipe(struct file *wrf)
f->f_mapping = wrf->f_path.dentry->d_inode->i_mapping;
f->f_pos = 0;
- f->f_flags = O_RDONLY;
+ f->f_flags = O_RDONLY | (flags & O_NONBLOCK);
f->f_op = &read_pipe_fops;
f->f_mode = FMODE_READ;
f->f_version = 0;
@@ -1027,26 +1027,29 @@ struct file *create_read_pipe(struct file *wrf)
return f;
}
-int do_pipe(int *fd)
+int do_pipe_flags(int *fd, int flags)
{
struct file *fw, *fr;
int error;
int fdw, fdr;
- fw = create_write_pipe();
+ if (flags & ~(O_CLOEXEC | O_NONBLOCK))
+ return -EINVAL;
+
+ fw = create_write_pipe(flags);
if (IS_ERR(fw))
return PTR_ERR(fw);
- fr = create_read_pipe(fw);
+ fr = create_read_pipe(fw, flags);
error = PTR_ERR(fr);
if (IS_ERR(fr))
goto err_write_pipe;
- error = get_unused_fd();
+ error = get_unused_fd_flags(flags);
if (error < 0)
goto err_read_pipe;
fdr = error;
- error = get_unused_fd();
+ error = get_unused_fd_flags(flags);
if (error < 0)
goto err_fdr;
fdw = error;
@@ -1074,16 +1077,21 @@ int do_pipe(int *fd)
return error;
}
+int do_pipe(int *fd)
+{
+ return do_pipe_flags(fd, 0);
+}
+
/*
* sys_pipe() is the normal C calling standard for creating
* a pipe. It's not the way Unix traditionally does this, though.
*/
-asmlinkage long __weak sys_pipe(int __user *fildes)
+asmlinkage long __weak sys_pipe2(int __user *fildes, int flags)
{
int fd[2];
int error;
- error = do_pipe(fd);
+ error = do_pipe_flags(fd, flags);
if (!error) {
if (copy_to_user(fildes, fd, sizeof(fd))) {
sys_close(fd[0]);
@@ -1094,6 +1102,11 @@ asmlinkage long __weak sys_pipe(int __user *fildes)
return error;
}
+asmlinkage long __weak sys_pipe(int __user *fildes)
+{
+ return sys_pipe2(fildes, 0);
+}
+
/*
* pipefs should _never_ be mounted by userland - too much of security hassle,
* no real gain from having the whole whorehouse mounted. So we don't need
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index c652d469dc0..ded96986296 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -232,7 +232,6 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
#undef K
}
-extern const struct seq_operations fragmentation_op;
static int fragmentation_open(struct inode *inode, struct file *file)
{
(void)inode;
@@ -246,7 +245,6 @@ static const struct file_operations fragmentation_file_operations = {
.release = seq_release,
};
-extern const struct seq_operations pagetypeinfo_op;
static int pagetypeinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &pagetypeinfo_op);
@@ -259,7 +257,6 @@ static const struct file_operations pagetypeinfo_file_ops = {
.release = seq_release,
};
-extern const struct seq_operations zoneinfo_op;
static int zoneinfo_open(struct inode *inode, struct file *file)
{
return seq_open(file, &zoneinfo_op);
@@ -356,7 +353,6 @@ static const struct file_operations proc_devinfo_operations = {
.release = seq_release,
};
-extern const struct seq_operations vmstat_op;
static int vmstat_open(struct inode *inode, struct file *file)
{
return seq_open(file, &vmstat_op);
@@ -468,14 +464,25 @@ static const struct file_operations proc_slabstats_operations = {
#ifdef CONFIG_MMU
static int vmalloc_open(struct inode *inode, struct file *file)
{
- return seq_open(file, &vmalloc_op);
+ unsigned int *ptr = NULL;
+ int ret;
+
+ if (NUMA_BUILD)
+ ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
+ ret = seq_open(file, &vmalloc_op);
+ if (!ret) {
+ struct seq_file *m = file->private_data;
+ m->private = ptr;
+ } else
+ kfree(ptr);
+ return ret;
}
static const struct file_operations proc_vmalloc_operations = {
.open = vmalloc_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release,
+ .release = seq_release_private,
};
#endif
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index b224a28e0c1..7bc296f424a 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -27,6 +27,11 @@
#include "internal.h"
+static struct net *get_proc_net(const struct inode *inode)
+{
+ return maybe_get_net(PDE_NET(PDE(inode)));
+}
+
int seq_open_net(struct inode *ino, struct file *f,
const struct seq_operations *ops, int size)
{
@@ -185,12 +190,6 @@ void proc_net_remove(struct net *net, const char *name)
}
EXPORT_SYMBOL_GPL(proc_net_remove);
-struct net *get_proc_net(const struct inode *inode)
-{
- return maybe_get_net(PDE_NET(PDE(inode)));
-}
-EXPORT_SYMBOL_GPL(get_proc_net);
-
static __net_init int proc_net_ns_init(struct net *net)
{
struct proc_dir_entry *netd, *net_statd;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 164bd9f9ede..7546a918f79 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -636,7 +636,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
struct pagemapread pm;
int pagecount;
int ret = -ESRCH;
- struct mm_walk pagemap_walk;
+ struct mm_walk pagemap_walk = {};
unsigned long src;
unsigned long svpfn;
unsigned long start_vaddr;
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 619725644c7..9c39bc7f843 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -205,11 +205,19 @@ static const struct file_operations signalfd_fops = {
.read = signalfd_read,
};
-asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask)
+asmlinkage long sys_signalfd4(int ufd, sigset_t __user *user_mask,
+ size_t sizemask, int flags)
{
sigset_t sigmask;
struct signalfd_ctx *ctx;
+ /* Check the SFD_* constants for consistency. */
+ BUILD_BUG_ON(SFD_CLOEXEC != O_CLOEXEC);
+ BUILD_BUG_ON(SFD_NONBLOCK != O_NONBLOCK);
+
+ if (flags & ~(SFD_CLOEXEC | SFD_NONBLOCK))
+ return -EINVAL;
+
if (sizemask != sizeof(sigset_t) ||
copy_from_user(&sigmask, user_mask, sizeof(sigmask)))
return -EINVAL;
@@ -227,7 +235,8 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
* When we call this, the initialization must be complete, since
* anon_inode_getfd() will install the fd.
*/
- ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx);
+ ufd = anon_inode_getfd("[signalfd]", &signalfd_fops, ctx,
+ flags & (O_CLOEXEC | O_NONBLOCK));
if (ufd < 0)
kfree(ctx);
} else {
@@ -249,3 +258,9 @@ asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemas
return ufd;
}
+
+asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask,
+ size_t sizemask)
+{
+ return sys_signalfd4(ufd, user_mask, sizemask, 0);
+}
diff --git a/fs/super.c b/fs/super.c
index 453877c5697..e931ae9511f 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -70,6 +70,7 @@ static struct super_block *alloc_super(struct file_system_type *type)
INIT_LIST_HEAD(&s->s_instances);
INIT_HLIST_HEAD(&s->s_anon);
INIT_LIST_HEAD(&s->s_inodes);
+ INIT_LIST_HEAD(&s->s_dentry_lru);
init_rwsem(&s->s_umount);
mutex_init(&s->s_lock);
lockdep_set_class(&s->s_umount, &type->s_umount_key);
diff --git a/fs/sync.c b/fs/sync.c
index 228e17b5e9e..2967562d416 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -139,7 +139,8 @@ asmlinkage long sys_fdatasync(unsigned int fd)
* before performing the write.
*
* SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
- * range which are not presently under writeback.
+ * range which are not presently under writeback. Note that this may block for
+ * significant periods due to exhaustion of disk request structures.
*
* SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
* after performing the write.
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 8c0e4b92574..c1a7efb310b 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -398,7 +398,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
}
/**
- * sysfs_add_one - add sysfs_dirent to parent
+ * __sysfs_add_one - add sysfs_dirent to parent without warning
* @acxt: addrm context to use
* @sd: sysfs_dirent to be added
*
@@ -417,7 +417,7 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
* 0 on success, -EEXIST if entry with the given name already
* exists.
*/
-int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
{
if (sysfs_find_dirent(acxt->parent_sd, sd->s_name))
return -EEXIST;
@@ -435,6 +435,39 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
}
/**
+ * sysfs_add_one - add sysfs_dirent to parent
+ * @acxt: addrm context to use
+ * @sd: sysfs_dirent to be added
+ *
+ * Get @acxt->parent_sd and set sd->s_parent to it and increment
+ * nlink of parent inode if @sd is a directory and link into the
+ * children list of the parent.
+ *
+ * This function should be called between calls to
+ * sysfs_addrm_start() and sysfs_addrm_finish() and should be
+ * passed the same @acxt as passed to sysfs_addrm_start().
+ *
+ * LOCKING:
+ * Determined by sysfs_addrm_start().
+ *
+ * RETURNS:
+ * 0 on success, -EEXIST if entry with the given name already
+ * exists.
+ */
+int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
+{
+ int ret;
+
+ ret = __sysfs_add_one(acxt, sd);
+ if (ret == -EEXIST) {
+ printk(KERN_WARNING "sysfs: duplicate filename '%s' "
+ "can not be created\n", sd->s_name);
+ WARN_ON(1);
+ }
+ return ret;
+}
+
+/**
* sysfs_remove_one - remove sysfs_dirent from parent
* @acxt: addrm context to use
* @sd: sysfs_dirent to be removed
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index e7735f643cd..3f07893ff89 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -14,6 +14,7 @@
#include <linux/kobject.h>
#include <linux/kallsyms.h>
#include <linux/slab.h>
+#include <linux/fsnotify.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/list.h>
@@ -585,9 +586,11 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode)
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
- rc = notify_change(victim, &newattrs);
+ newattrs.ia_ctime = current_fs_time(inode->i_sb);
+ rc = sysfs_setattr(victim, &newattrs);
if (rc == 0) {
+ fsnotify_change(victim, newattrs.ia_valid);
mutex_lock(&sysfs_mutex);
victim_sd->s_mode = newattrs.ia_mode;
mutex_unlock(&sysfs_mutex);
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 817f5966edc..a3ba217fbe7 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -19,13 +19,8 @@
#include "sysfs.h"
-/**
- * sysfs_create_link - create symlink between two objects.
- * @kobj: object whose directory we're creating the link in.
- * @target: object we're pointing to.
- * @name: name of the symlink.
- */
-int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char * name)
+static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target,
+ const char *name, int warn)
{
struct sysfs_dirent *parent_sd = NULL;
struct sysfs_dirent *target_sd = NULL;
@@ -65,7 +60,10 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
target_sd = NULL; /* reference is now owned by the symlink */
sysfs_addrm_start(&acxt, parent_sd);
- error = sysfs_add_one(&acxt, sd);
+ if (warn)
+ error = sysfs_add_one(&acxt, sd);
+ else
+ error = __sysfs_add_one(&acxt, sd);
sysfs_addrm_finish(&acxt);
if (error)
@@ -80,6 +78,33 @@ int sysfs_create_link(struct kobject * kobj, struct kobject * target, const char
}
/**
+ * sysfs_create_link - create symlink between two objects.
+ * @kobj: object whose directory we're creating the link in.
+ * @target: object we're pointing to.
+ * @name: name of the symlink.
+ */
+int sysfs_create_link(struct kobject *kobj, struct kobject *target,
+ const char *name)
+{
+ return sysfs_do_create_link(kobj, target, name, 1);
+}
+
+/**
+ * sysfs_create_link_nowarn - create symlink between two objects.
+ * @kobj: object whose directory we're creating the link in.
+ * @target: object we're pointing to.
+ * @name: name of the symlink.
+ *
+ * This function does the same as sysf_create_link(), but it
+ * doesn't warn if the link already exists.
+ */
+int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target,
+ const char *name)
+{
+ return sysfs_do_create_link(kobj, target, name, 0);
+}
+
+/**
* sysfs_remove_link - remove symlink in object's directory.
* @kobj: object we're acting for.
* @name: name of the symlink to remove.
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index ce4e15f8aae..a5db496f71c 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -107,6 +107,7 @@ struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd);
void sysfs_put_active_two(struct sysfs_dirent *sd);
void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
struct sysfs_dirent *parent_sd);
+int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd);
void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index d87d354ec42..c502c60e4f5 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -184,7 +184,11 @@ asmlinkage long sys_timerfd_create(int clockid, int flags)
int ufd;
struct timerfd_ctx *ctx;
- if (flags)
+ /* Check the TFD_* constants for consistency. */
+ BUILD_BUG_ON(TFD_CLOEXEC != O_CLOEXEC);
+ BUILD_BUG_ON(TFD_NONBLOCK != O_NONBLOCK);
+
+ if (flags & ~(TFD_CLOEXEC | TFD_NONBLOCK))
return -EINVAL;
if (clockid != CLOCK_MONOTONIC &&
clockid != CLOCK_REALTIME)
@@ -198,7 +202,8 @@ asmlinkage long sys_timerfd_create(int clockid, int flags)
ctx->clockid = clockid;
hrtimer_init(&ctx->tmr, clockid, HRTIMER_MODE_ABS);
- ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx);
+ ufd = anon_inode_getfd("[timerfd]", &timerfd_fops, ctx,
+ flags & (O_CLOEXEC | O_NONBLOCK));
if (ufd < 0)
kfree(ctx);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 85b22b5977f..506f724055c 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1232,7 +1232,7 @@ static int ufs_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
struct ufs_sb_info *sbi = UFS_SB(vfs->mnt_sb);
unsigned mval = sbi->s_mount_opt & UFS_MOUNT_UFSTYPE;
- struct match_token *tp = tokens;
+ const struct match_token *tp = tokens;
while (tp->token != Opt_onerror_panic && tp->token != mval)
++tp;