summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile2
-rw-r--r--fs/char_dev.c87
-rw-r--r--fs/dcache.c50
-rw-r--r--fs/ext2/file.c2
-rw-r--r--fs/ext3/file.c2
-rw-r--r--fs/hppfs/hppfs_kern.c14
-rw-r--r--fs/locks.c45
-rw-r--r--fs/msdos/namei.c15
-rw-r--r--fs/namei.c3
-rw-r--r--fs/pipe.c41
-rw-r--r--fs/proc/base.c13
-rw-r--r--fs/proc/proc_misc.c163
-rw-r--r--fs/reiserfs/file.c2
-rw-r--r--fs/select.c8
-rw-r--r--fs/splice.c663
-rw-r--r--fs/sync.c164
-rw-r--r--fs/vfat/namei.c18
17 files changed, 989 insertions, 303 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 080b3867be4d..83bf478e786b 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o buffer.o bio.o super.o \
ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \
attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \
seq_file.o xattr.o libfs.o fs-writeback.o mpage.o direct-io.o \
- ioprio.o pnode.o drop_caches.o
+ ioprio.o pnode.o drop_caches.o splice.o sync.o
obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_EPOLL) += eventpoll.o
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 4e1b849f912f..f3418f7a6e9d 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <linux/devfs_fs_kernel.h>
+#include <linux/seq_file.h>
#include <linux/kobject.h>
#include <linux/kobj_map.h>
@@ -27,8 +28,6 @@
static struct kobj_map *cdev_map;
-#define MAX_PROBE_HASH 255 /* random */
-
static DEFINE_MUTEX(chrdevs_lock);
static struct char_device_struct {
@@ -39,93 +38,29 @@ static struct char_device_struct {
char name[64];
struct file_operations *fops;
struct cdev *cdev; /* will die */
-} *chrdevs[MAX_PROBE_HASH];
+} *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
/* index in the above */
static inline int major_to_index(int major)
{
- return major % MAX_PROBE_HASH;
-}
-
-struct chrdev_info {
- int index;
- struct char_device_struct *cd;
-};
-
-void *get_next_chrdev(void *dev)
-{
- struct chrdev_info *info;
-
- if (dev == NULL) {
- info = kmalloc(sizeof(*info), GFP_KERNEL);
- if (!info)
- goto out;
- info->index=0;
- info->cd = chrdevs[info->index];
- if (info->cd)
- goto out;
- } else {
- info = dev;
- }
-
- while (info->index < ARRAY_SIZE(chrdevs)) {
- if (info->cd)
- info->cd = info->cd->next;
- if (info->cd)
- goto out;
- /*
- * No devices on this chain, move to the next
- */
- info->index++;
- info->cd = (info->index < ARRAY_SIZE(chrdevs)) ?
- chrdevs[info->index] : NULL;
- if (info->cd)
- goto out;
- }
-
-out:
- return info;
-}
-
-void *acquire_chrdev_list(void)
-{
- mutex_lock(&chrdevs_lock);
- return get_next_chrdev(NULL);
-}
-
-void release_chrdev_list(void *dev)
-{
- mutex_unlock(&chrdevs_lock);
- kfree(dev);
+ return major % CHRDEV_MAJOR_HASH_SIZE;
}
+#ifdef CONFIG_PROC_FS
-int count_chrdev_list(void)
+void chrdev_show(struct seq_file *f, off_t offset)
{
struct char_device_struct *cd;
- int i, count;
-
- count = 0;
- for (i = 0; i < ARRAY_SIZE(chrdevs) ; i++) {
- for (cd = chrdevs[i]; cd; cd = cd->next)
- count++;
+ if (offset < CHRDEV_MAJOR_HASH_SIZE) {
+ mutex_lock(&chrdevs_lock);
+ for (cd = chrdevs[offset]; cd; cd = cd->next)
+ seq_printf(f, "%3d %s\n", cd->major, cd->name);
+ mutex_unlock(&chrdevs_lock);
}
-
- return count;
}
-int get_chrdev_info(void *dev, int *major, char **name)
-{
- struct chrdev_info *info = dev;
-
- if (info->cd == NULL)
- return 1;
-
- *major = info->cd->major;
- *name = info->cd->name;
- return 0;
-}
+#endif /* CONFIG_PROC_FS */
/*
* Register a single major with a specified minor range.
diff --git a/fs/dcache.c b/fs/dcache.c
index 19458d399502..940d188e5d14 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1101,6 +1101,32 @@ next:
}
/**
+ * d_hash_and_lookup - hash the qstr then search for a dentry
+ * @dir: Directory to search in
+ * @name: qstr of name we wish to find
+ *
+ * On hash failure or on lookup failure NULL is returned.
+ */
+struct dentry *d_hash_and_lookup(struct dentry *dir, struct qstr *name)
+{
+ struct dentry *dentry = NULL;
+
+ /*
+ * Check for a fs-specific hash function. Note that we must
+ * calculate the standard hash first, as the d_op->d_hash()
+ * routine may choose to leave the hash value unchanged.
+ */
+ name->hash = full_name_hash(name->name, name->len);
+ if (dir->d_op && dir->d_op->d_hash) {
+ if (dir->d_op->d_hash(dir, name) < 0)
+ goto out;
+ }
+ dentry = d_lookup(dir, name);
+out:
+ return dentry;
+}
+
+/**
* d_validate - verify dentry provided from insecure source
* @dentry: The dentry alleged to be valid child of @dparent
* @dparent: The parent dentry (known to be valid)
@@ -1172,11 +1198,11 @@ void d_delete(struct dentry * dentry)
spin_lock(&dentry->d_lock);
isdir = S_ISDIR(dentry->d_inode->i_mode);
if (atomic_read(&dentry->d_count) == 1) {
- /* remove this and other inotify debug checks after 2.6.18 */
- dentry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED;
-
dentry_iput(dentry);
fsnotify_nameremove(dentry, isdir);
+
+ /* remove this and other inotify debug checks after 2.6.18 */
+ dentry->d_flags &= ~DCACHE_INOTIFY_PARENT_WATCHED;
return;
}
@@ -1616,26 +1642,12 @@ ino_t find_inode_number(struct dentry *dir, struct qstr *name)
struct dentry * dentry;
ino_t ino = 0;
- /*
- * Check for a fs-specific hash function. Note that we must
- * calculate the standard hash first, as the d_op->d_hash()
- * routine may choose to leave the hash value unchanged.
- */
- name->hash = full_name_hash(name->name, name->len);
- if (dir->d_op && dir->d_op->d_hash)
- {
- if (dir->d_op->d_hash(dir, name) != 0)
- goto out;
- }
-
- dentry = d_lookup(dir, name);
- if (dentry)
- {
+ dentry = d_hash_and_lookup(dir, name);
+ if (dentry) {
if (dentry->d_inode)
ino = dentry->d_inode->i_ino;
dput(dentry);
}
-out:
return ino;
}
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 509cceca04db..23e2c7ccec1d 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -53,6 +53,8 @@ const struct file_operations ext2_file_operations = {
.readv = generic_file_readv,
.writev = generic_file_writev,
.sendfile = generic_file_sendfile,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
};
#ifdef CONFIG_EXT2_FS_XIP
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 783a796220bb..1efefb630ea9 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -119,6 +119,8 @@ const struct file_operations ext3_file_operations = {
.release = ext3_release_file,
.fsync = ext3_sync_file,
.sendfile = generic_file_sendfile,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
};
struct inode_operations ext3_file_inode_operations = {
diff --git a/fs/hppfs/hppfs_kern.c b/fs/hppfs/hppfs_kern.c
index 2ba20cdb5baa..5e6363be246f 100644
--- a/fs/hppfs/hppfs_kern.c
+++ b/fs/hppfs/hppfs_kern.c
@@ -216,10 +216,10 @@ static struct dentry *hppfs_lookup(struct inode *ino, struct dentry *dentry,
static struct inode_operations hppfs_file_iops = {
};
-static ssize_t read_proc(struct file *file, char *buf, ssize_t count,
+static ssize_t read_proc(struct file *file, char __user *buf, ssize_t count,
loff_t *ppos, int is_user)
{
- ssize_t (*read)(struct file *, char *, size_t, loff_t *);
+ ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
ssize_t n;
read = file->f_dentry->d_inode->i_fop->read;
@@ -236,7 +236,7 @@ static ssize_t read_proc(struct file *file, char *buf, ssize_t count,
return n;
}
-static ssize_t hppfs_read_file(int fd, char *buf, ssize_t count)
+static ssize_t hppfs_read_file(int fd, char __user *buf, ssize_t count)
{
ssize_t n;
int cur, err;
@@ -274,7 +274,7 @@ static ssize_t hppfs_read_file(int fd, char *buf, ssize_t count)
return n;
}
-static ssize_t hppfs_read(struct file *file, char *buf, size_t count,
+static ssize_t hppfs_read(struct file *file, char __user *buf, size_t count,
loff_t *ppos)
{
struct hppfs_private *hppfs = file->private_data;
@@ -313,12 +313,12 @@ static ssize_t hppfs_read(struct file *file, char *buf, size_t count,
return(count);
}
-static ssize_t hppfs_write(struct file *file, const char *buf, size_t len,
+static ssize_t hppfs_write(struct file *file, const char __user *buf, size_t len,
loff_t *ppos)
{
struct hppfs_private *data = file->private_data;
struct file *proc_file = data->proc_file;
- ssize_t (*write)(struct file *, const char *, size_t, loff_t *);
+ ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
int err;
write = proc_file->f_dentry->d_inode->i_fop->write;
@@ -658,7 +658,7 @@ static struct super_operations hppfs_sbops = {
.statfs = hppfs_statfs,
};
-static int hppfs_readlink(struct dentry *dentry, char *buffer, int buflen)
+static int hppfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
{
struct file *proc_file;
struct dentry *proc_dentry;
diff --git a/fs/locks.c b/fs/locks.c
index 4d9e71d43e7e..dda83d6cd48b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -168,18 +168,9 @@ static void locks_release_private(struct file_lock *fl)
/* Free a lock which is not in use. */
static void locks_free_lock(struct file_lock *fl)
{
- if (fl == NULL) {
- BUG();
- return;
- }
- if (waitqueue_active(&fl->fl_wait))
- panic("Attempting to free lock with active wait queue");
-
- if (!list_empty(&fl->fl_block))
- panic("Attempting to free lock with active block list");
-
- if (!list_empty(&fl->fl_link))
- panic("Attempting to free lock on active lock list");
+ BUG_ON(waitqueue_active(&fl->fl_wait));
+ BUG_ON(!list_empty(&fl->fl_block));
+ BUG_ON(!list_empty(&fl->fl_link));
locks_release_private(fl);
kmem_cache_free(filelock_cache, fl);
@@ -735,8 +726,9 @@ EXPORT_SYMBOL(posix_locks_deadlock);
* at the head of the list, but that's secret knowledge known only to
* flock_lock_file and posix_lock_file.
*/
-static int flock_lock_file(struct file *filp, struct file_lock *new_fl)
+static int flock_lock_file(struct file *filp, struct file_lock *request)
{
+ struct file_lock *new_fl = NULL;
struct file_lock **before;
struct inode * inode = filp->f_dentry->d_inode;
int error = 0;
@@ -751,17 +743,19 @@ static int flock_lock_file(struct file *filp, struct file_lock *new_fl)
continue;
if (filp != fl->fl_file)
continue;
- if (new_fl->fl_type == fl->fl_type)
+ if (request->fl_type == fl->fl_type)
goto out;
found = 1;
locks_delete_lock(before);
break;
}
- unlock_kernel();
- if (new_fl->fl_type == F_UNLCK)
- return 0;
+ if (request->fl_type == F_UNLCK)
+ goto out;
+ new_fl = locks_alloc_lock();
+ if (new_fl == NULL)
+ goto out;
/*
* If a higher-priority process was blocked on the old file lock,
* give it the opportunity to lock the file.
@@ -769,26 +763,27 @@ static int flock_lock_file(struct file *filp, struct file_lock *new_fl)
if (found)
cond_resched();
- lock_kernel();
for_each_lock(inode, before) {
struct file_lock *fl = *before;
if (IS_POSIX(fl))
break;
if (IS_LEASE(fl))
continue;
- if (!flock_locks_conflict(new_fl, fl))
+ if (!flock_locks_conflict(request, fl))
continue;
error = -EAGAIN;
- if (new_fl->fl_flags & FL_SLEEP) {
- locks_insert_block(fl, new_fl);
- }
+ if (request->fl_flags & FL_SLEEP)
+ locks_insert_block(fl, request);
goto out;
}
+ locks_copy_lock(new_fl, request);
locks_insert_lock(&inode->i_flock, new_fl);
- error = 0;
+ new_fl = NULL;
out:
unlock_kernel();
+ if (new_fl)
+ locks_free_lock(new_fl);
return error;
}
@@ -1569,9 +1564,7 @@ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd)
error = flock_lock_file_wait(filp, lock);
out_free:
- if (list_empty(&lock->fl_link)) {
- locks_free_lock(lock);
- }
+ locks_free_lock(lock);
out_putf:
fput(filp);
diff --git a/fs/msdos/namei.c b/fs/msdos/namei.c
index 626a367bcd81..5b76ccd19e3f 100644
--- a/fs/msdos/namei.c
+++ b/fs/msdos/namei.c
@@ -12,14 +12,6 @@
#include <linux/msdos_fs.h>
#include <linux/smp_lock.h>
-/* MS-DOS "device special files" */
-static const unsigned char *reserved_names[] = {
- "CON ", "PRN ", "NUL ", "AUX ",
- "LPT1 ", "LPT2 ", "LPT3 ", "LPT4 ",
- "COM1 ", "COM2 ", "COM3 ", "COM4 ",
- NULL
-};
-
/* Characters that are undesirable in an MS-DOS file name */
static unsigned char bad_chars[] = "*?<>|\"";
static unsigned char bad_if_strict_pc[] = "+=,; ";
@@ -40,7 +32,6 @@ static int msdos_format_name(const unsigned char *name, int len,
*/
{
unsigned char *walk;
- const unsigned char **reserved;
unsigned char c;
int space;
@@ -127,11 +118,7 @@ static int msdos_format_name(const unsigned char *name, int len,
}
while (walk - res < MSDOS_NAME)
*walk++ = ' ';
- if (!opts->atari)
- /* GEMDOS is less stupid and has no reserved names */
- for (reserved = reserved_names; *reserved; reserved++)
- if (!strncmp(res, *reserved, 8))
- return -EINVAL;
+
return 0;
}
diff --git a/fs/namei.c b/fs/namei.c
index 22f6e8d16aa8..96723ae83c89 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1254,7 +1254,7 @@ out:
return dentry;
}
-struct dentry * lookup_hash(struct nameidata *nd)
+static struct dentry *lookup_hash(struct nameidata *nd)
{
return __lookup_hash(&nd->last, nd->dentry, nd);
}
@@ -2697,7 +2697,6 @@ EXPORT_SYMBOL(follow_up);
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
EXPORT_SYMBOL(getname);
EXPORT_SYMBOL(lock_rename);
-EXPORT_SYMBOL(lookup_hash);
EXPORT_SYMBOL(lookup_one_len);
EXPORT_SYMBOL(page_follow_link_light);
EXPORT_SYMBOL(page_put_link);
diff --git a/fs/pipe.c b/fs/pipe.c
index e2f4f1d9ffc2..109a102c150d 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -15,6 +15,7 @@
#include <linux/pipe_fs_i.h>
#include <linux/uio.h>
#include <linux/highmem.h>
+#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
@@ -94,11 +95,20 @@ static void anon_pipe_buf_release(struct pipe_inode_info *info, struct pipe_buff
{
struct page *page = buf->page;
- if (info->tmp_page) {
- __free_page(page);
+ /*
+ * If nobody else uses this page, and we don't already have a
+ * temporary page, let's keep track of it as a one-deep
+ * allocation cache
+ */
+ if (page_count(page) == 1 && !info->tmp_page) {
+ info->tmp_page = page;
return;
}
- info->tmp_page = page;
+
+ /*
+ * Otherwise just release our reference to it
+ */
+ page_cache_release(page);
}
static void *anon_pipe_buf_map(struct file *file, struct pipe_inode_info *info, struct pipe_buffer *buf)
@@ -111,11 +121,19 @@ static void anon_pipe_buf_unmap(struct pipe_inode_info *info, struct pipe_buffer
kunmap(buf->page);
}
+static int anon_pipe_buf_steal(struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
+{
+ buf->stolen = 1;
+ return 0;
+}
+
static struct pipe_buf_operations anon_pipe_buf_ops = {
.can_merge = 1,
.map = anon_pipe_buf_map,
.unmap = anon_pipe_buf_unmap,
.release = anon_pipe_buf_release,
+ .steal = anon_pipe_buf_steal,
};
static ssize_t
@@ -152,6 +170,11 @@ pipe_readv(struct file *filp, const struct iovec *_iov,
chars = total_len;
addr = ops->map(filp, info, buf);
+ if (IS_ERR(addr)) {
+ if (!ret)
+ ret = PTR_ERR(addr);
+ break;
+ }
error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars);
ops->unmap(info, buf);
if (unlikely(error)) {
@@ -254,8 +277,16 @@ pipe_writev(struct file *filp, const struct iovec *_iov,
struct pipe_buf_operations *ops = buf->ops;
int offset = buf->offset + buf->len;
if (ops->can_merge && offset + chars <= PAGE_SIZE) {
- void *addr = ops->map(filp, info, buf);
- int error = pipe_iov_copy_from_user(offset + addr, iov, chars);
+ void *addr;
+ int error;
+
+ addr = ops->map(filp, info, buf);
+ if (IS_ERR(addr)) {
+ error = PTR_ERR(addr);
+ goto out;
+ }
+ error = pipe_iov_copy_from_user(offset + addr, iov,
+ chars);
ops->unmap(info, buf);
ret = error;
do_wakeup = 1;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8f1f49ceebec..a3a3eecef689 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -534,12 +534,15 @@ static int proc_oom_score(struct task_struct *task, char *buffer)
/* If the process being read is separated by chroot from the reading process,
* don't let the reader access the threads.
+ *
+ * note: this does dput(root) and mntput(vfsmnt) on exit.
*/
static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt)
{
struct dentry *de, *base;
struct vfsmount *our_vfsmnt, *mnt;
int res = 0;
+
read_lock(&current->fs->lock);
our_vfsmnt = mntget(current->fs->rootmnt);
base = dget(current->fs->root);
@@ -549,11 +552,11 @@ static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt)
de = root;
mnt = vfsmnt;
- while (vfsmnt != our_vfsmnt) {
- if (vfsmnt == vfsmnt->mnt_parent)
+ while (mnt != our_vfsmnt) {
+ if (mnt == mnt->mnt_parent)
goto out;
- de = vfsmnt->mnt_mountpoint;
- vfsmnt = vfsmnt->mnt_parent;
+ de = mnt->mnt_mountpoint;
+ mnt = mnt->mnt_parent;
}
if (!is_subdir(de, base))
@@ -564,7 +567,7 @@ exit:
dput(base);
mntput(our_vfsmnt);
dput(root);
- mntput(mnt);
+ mntput(vfsmnt);
return res;
out:
spin_unlock(&vfsmount_lock);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index ef5a3323f4b5..5c10ea157425 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -249,144 +249,60 @@ static int cpuinfo_open(struct inode *inode, struct file *file)
return seq_open(file, &cpuinfo_op);
}
-enum devinfo_states {
- CHR_HDR,
- CHR_LIST,
- BLK_HDR,
- BLK_LIST,
- DEVINFO_DONE
-};
-
-struct devinfo_state {
- void *chrdev;
- void *blkdev;
- unsigned int num_records;
- unsigned int cur_record;
- enum devinfo_states state;
+static struct file_operations proc_cpuinfo_operations = {
+ .open = cpuinfo_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
};
-static void *devinfo_start(struct seq_file *f, loff_t *pos)
+static int devinfo_show(struct seq_file *f, void *v)
{
- struct devinfo_state *info = f->private;
+ int i = *(loff_t *) v;
- if (*pos) {
- if ((info) && (*pos <= info->num_records))
- return info;
- return NULL;
+ if (i < CHRDEV_MAJOR_HASH_SIZE) {
+ if (i == 0)
+ seq_printf(f, "Character devices:\n");
+ chrdev_show(f, i);
+ } else {
+ i -= CHRDEV_MAJOR_HASH_SIZE;
+ if (i == 0)
+ seq_printf(f, "\nBlock devices:\n");
+ blkdev_show(f, i);
}
- info = kmalloc(sizeof(*info), GFP_KERNEL);
- f->private = info;
- info->chrdev = acquire_chrdev_list();
- info->blkdev = acquire_blkdev_list();
- info->state = CHR_HDR;
- info->num_records = count_chrdev_list();
- info->num_records += count_blkdev_list();
- info->num_records += 2; /* Character and Block headers */
- *pos = 1;
- info->cur_record = *pos;
- return info;
+ return 0;
}
-static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos)
+static void *devinfo_start(struct seq_file *f, loff_t *pos)
{
- int idummy;
- char *ndummy;
- struct devinfo_state *info = f->private;
-
- switch (info->state) {
- case CHR_HDR:
- info->state = CHR_LIST;
- (*pos)++;
- /*fallthrough*/
- case CHR_LIST:
- if (get_chrdev_info(info->chrdev,&idummy,&ndummy)) {
- /*
- * The character dev list is complete
- */
- info->state = BLK_HDR;
- } else {
- info->chrdev = get_next_chrdev(info->chrdev);
- }
- (*pos)++;
- break;
- case BLK_HDR:
- info->state = BLK_LIST;
- (*pos)++;
- /*fallthrough*/
- case BLK_LIST:
- if (get_blkdev_info(info->blkdev,&idummy,&ndummy)) {
- /*
- * The block dev list is complete
- */
- info->state = DEVINFO_DONE;
- } else {
- info->blkdev = get_next_blkdev(info->blkdev);
- }
- (*pos)++;
- break;
- case DEVINFO_DONE:
- (*pos)++;
- info->cur_record = *pos;
- info = NULL;
- break;
- default:
- break;
- }
- if (info)
- info->cur_record = *pos;
- return info;
+ if (*pos < (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
+ return pos;
+ return NULL;
}
-static void devinfo_stop(struct seq_file *f, void *v)
+static void *devinfo_next(struct seq_file *f, void *v, loff_t *pos)
{
- struct devinfo_state *info = f->private;
-
- if (info) {
- release_chrdev_list(info->chrdev);
- release_blkdev_list(info->blkdev);
- f->private = NULL;
- kfree(info);
- }
+ (*pos)++;
+ if (*pos >= (BLKDEV_MAJOR_HASH_SIZE + CHRDEV_MAJOR_HASH_SIZE))
+ return NULL;
+ return pos;
}
-static int devinfo_show(struct seq_file *f, void *arg)
-{
- int major;
- char *name;
- struct devinfo_state *info = f->private;
-
- switch(info->state) {
- case CHR_HDR:
- seq_printf(f,"Character devices:\n");
- /* fallthrough */
- case CHR_LIST:
- if (!get_chrdev_info(info->chrdev,&major,&name))
- seq_printf(f,"%3d %s\n",major,name);
- break;
- case BLK_HDR:
- seq_printf(f,"\nBlock devices:\n");
- /* fallthrough */
- case BLK_LIST:
- if (!get_blkdev_info(info->blkdev,&major,&name))
- seq_printf(f,"%3d %s\n",major,name);
- break;
- default:
- break;
- }
-
- return 0;
+static void devinfo_stop(struct seq_file *f, void *v)
+{
+ /* Nothing to do */
}
-static struct seq_operations devinfo_op = {
- .start = devinfo_start,
- .next = devinfo_next,
- .stop = devinfo_stop,
- .show = devinfo_show,
+static struct seq_operations devinfo_ops = {
+ .start = devinfo_start,
+ .next = devinfo_next,
+ .stop = devinfo_stop,
+ .show = devinfo_show
};
-static int devinfo_open(struct inode *inode, struct file *file)
+static int devinfo_open(struct inode *inode, struct file *filp)
{
- return seq_open(file, &devinfo_op);
+ return seq_open(filp, &devinfo_ops);
}
static struct file_operations proc_devinfo_operations = {
@@ -396,13 +312,6 @@ static struct file_operations proc_devinfo_operations = {
.release = seq_release,
};
-static struct file_operations proc_cpuinfo_operations = {
- .open = cpuinfo_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release,
-};
-
extern struct seq_operations vmstat_op;
static int vmstat_open(struct inode *inode, struct file *file)
{
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 010094d14da6..cf6e1cf40351 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -1576,6 +1576,8 @@ const struct file_operations reiserfs_file_operations = {
.sendfile = generic_file_sendfile,
.aio_read = generic_file_aio_read,
.aio_write = reiserfs_aio_write,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
};
struct inode_operations reiserfs_file_inode_operations = {
diff --git a/fs/select.c b/fs/select.c
index b3a3a1326af6..071660fa7b01 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -314,7 +314,7 @@ static int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
int ret, size, max_fdset;
struct fdtable *fdt;
/* Allocate small arguments on the stack to save memory and be faster */
- char stack_fds[SELECT_STACK_ALLOC];
+ long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
ret = -EINVAL;
if (n < 0)
@@ -639,8 +639,10 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout)
struct poll_list *walk;
struct fdtable *fdt;
int max_fdset;
- /* Allocate small arguments on the stack to save memory and be faster */
- char stack_pps[POLL_STACK_ALLOC];
+ /* Allocate small arguments on the stack to save memory and be
+ faster - use long to make sure the buffer is aligned properly
+ on 64 bit archs to avoid unaligned access */
+ long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
struct poll_list *stack_pp = NULL;
/* Do a sanity check on nfds ... */
diff --git a/fs/splice.c b/fs/splice.c
new file mode 100644
index 000000000000..7c2bbf18d7a7
--- /dev/null
+++ b/fs/splice.c
@@ -0,0 +1,663 @@
+/*
+ * "splice": joining two ropes together by interweaving their strands.
+ *
+ * This is the "extended pipe" functionality, where a pipe is used as
+ * an arbitrary in-memory buffer. Think of a pipe as a small kernel
+ * buffer that you can use to transfer data from one end to the other.
+ *
+ * The traditional unix read/write is extended with a "splice()" operation
+ * that transfers data buffers to or from a pipe buffer.
+ *
+ * Named by Larry McVoy, original implementation from Linus, extended by
+ * Jens to support splicing to files and fixing the initial implementation
+ * bugs.
+ *
+ * Copyright (C) 2005 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2005 Linus Torvalds <torvalds@osdl.org>
+ *
+ */
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/pagemap.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/mm_inline.h>
+#include <linux/swap.h>
+#include <linux/module.h>
+
+/*
+ * Passed to the actors
+ */
+struct splice_desc {
+ unsigned int len, total_len; /* current and remaining length */
+ unsigned int flags; /* splice flags */
+ struct file *file; /* file to read/write */
+ loff_t pos; /* file position */
+};
+
+static int page_cache_pipe_buf_steal(struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
+{
+ struct page *page = buf->page;
+
+ WARN_ON(!PageLocked(page));
+ WARN_ON(!PageUptodate(page));
+
+ if (!remove_mapping(page_mapping(page), page))
+ return 1;
+
+ if (PageLRU(page)) {
+ struct zone *zone = page_zone(page);
+
+ spin_lock_irq(&zone->lru_lock);
+ BUG_ON(!PageLRU(page));
+ __ClearPageLRU(page);
+ del_page_from_lru(zone, page);
+ spin_unlock_irq(&zone->lru_lock);
+ }
+
+ buf->stolen = 1;
+ return 0;
+}
+
+static void page_cache_pipe_buf_release(struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
+{
+ page_cache_release(buf->page);
+ buf->page = NULL;
+ buf->stolen = 0;
+}
+
+static void *page_cache_pipe_buf_map(struct file *file,
+ struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
+{
+ struct page *page = buf->page;
+
+ lock_page(page);
+
+ if (!PageUptodate(page)) {
+ unlock_page(page);
+ return ERR_PTR(-EIO);
+ }
+
+ if (!page->mapping) {
+ unlock_page(page);
+ return ERR_PTR(-ENODATA);
+ }
+
+ return kmap(buf->page);
+}
+
+static void page_cache_pipe_buf_unmap(struct pipe_inode_info *info,
+ struct pipe_buffer *buf)
+{
+ if (!buf->stolen)
+ unlock_page(buf->page);
+ kunmap(buf->page);
+}
+
+static struct pipe_buf_operations page_cache_pipe_buf_ops = {
+ .can_merge = 0,
+ .map = page_cache_pipe_buf_map,
+ .unmap = page_cache_pipe_buf_unmap,
+ .release = page_cache_pipe_buf_release,
+ .steal = page_cache_pipe_buf_steal,
+};
+
+static ssize_t move_to_pipe(struct inode *inode, struct page **pages,
+ int nr_pages, unsigned long offset,
+ unsigned long len)
+{
+ struct pipe_inode_info *info;
+ int ret, do_wakeup, i;
+
+ ret = 0;
+ do_wakeup = 0;
+ i = 0;
+
+ mutex_lock(PIPE_MUTEX(*inode));
+
+ info = inode->i_pipe;
+ for (;;) {
+ int bufs;
+
+ if (!PIPE_READERS(*inode)) {
+ send_sig(SIGPIPE, current, 0);
+ if (!ret)
+ ret = -EPIPE;
+ break;
+ }
+
+ bufs = info->nrbufs;
+ if (bufs < PIPE_BUFFERS) {
+ int newbuf = (info->curbuf + bufs) & (PIPE_BUFFERS - 1);
+ struct pipe_buffer *buf = info->bufs + newbuf;
+ struct page *page = pages[i++];
+ unsigned long this_len;
+
+ this_len = PAGE_CACHE_SIZE - offset;
+ if (this_len > len)
+ this_len = len;
+
+ buf->page = page;
+ buf->offset = offset;
+ buf->len = this_len;
+ buf->ops = &page_cache_pipe_buf_ops;
+ info->nrbufs = ++bufs;
+ do_wakeup = 1;
+
+ ret += this_len;
+ len -= this_len;
+ offset = 0;
+ if (!--nr_pages)
+ break;
+ if (!len)
+ break;
+ if (bufs < PIPE_BUFFERS)
+ continue;
+
+ break;
+ }
+
+ if (signal_pending(current)) {
+ if (!ret)
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ if (do_wakeup) {
+ wake_up_interruptible_sync(PIPE_WAIT(*inode));
+ kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO,
+ POLL_IN);
+ do_wakeup = 0;
+ }
+
+ PIPE_WAITING_WRITERS(*inode)++;
+ pipe_wait(inode);
+ PIPE_WAITING_WRITERS(*inode)--;
+ }
+
+ mutex_unlock(PIPE_MUTEX(*inode));
+
+ if (do_wakeup) {
+ wake_up_interruptible(PIPE_WAIT(*inode));
+ kill_fasync(PIPE_FASYNC_READERS(*inode), SIGIO, POLL_IN);
+ }
+
+ while (i < nr_pages)
+ page_cache_release(pages[i++]);
+
+ return ret;
+}
+
+static int __generic_file_splice_read(struct file *in, struct inode *pipe,
+ size_t len)
+{
+ struct address_space *mapping = in->f_mapping;
+ unsigned int offset, nr_pages;
+ struct page *pages[PIPE_BUFFERS], *shadow[PIPE_BUFFERS];
+ struct page *page;
+ pgoff_t index, pidx;
+ int i, j;
+
+ index = in->f_pos >> PAGE_CACHE_SHIFT;
+ offset = in->f_pos & ~PAGE_CACHE_MASK;
+ nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ if (nr_pages > PIPE_BUFFERS)
+ nr_pages = PIPE_BUFFERS;
+
+ /*
+ * initiate read-ahead on this page range
+ */
+ do_page_cache_readahead(mapping, in, index, nr_pages);
+
+ /*
+ * Get as many pages from the page cache as possible..
+ * Start IO on the page cache entries we create (we
+ * can assume that any pre-existing ones we find have
+ * already had IO started on them).
+ */
+ i = find_get_pages(mapping, index, nr_pages, pages);
+
+ /*
+ * common case - we found all pages and they are contiguous,
+ * kick them off
+ */
+ if (i && (pages[i - 1]->index == index + i - 1))
+ goto splice_them;
+
+ /*
+ * fill shadow[] with pages at the right locations, so we only
+ * have to fill holes
+ */
+ memset(shadow, 0, i * sizeof(struct page *));
+ for (j = 0, pidx = index; j < i; pidx++, j++)
+ shadow[pages[j]->index - pidx] = pages[j];
+
+ /*
+ * now fill in the holes
+ */
+ for (i = 0, pidx = index; i < nr_pages; pidx++, i++) {
+ int error;
+
+ if (shadow[i])
+ continue;
+
+ /*
+ * no page there, look one up / create it
+ */
+ page = find_or_create_page(mapping, pidx,
+ mapping_gfp_mask(mapping));
+ if (!page)
+ break;
+
+ if (PageUptodate(page))
+ unlock_page(page);
+ else {
+ error = mapping->a_ops->readpage(in, page);
+
+ if (unlikely(error)) {
+ page_cache_release(page);
+ break;
+ }
+ }
+ shadow[i] = page;
+ }
+
+ if (!i) {
+ for (i = 0; i < nr_pages; i++) {
+ if (shadow[i])
+ page_cache_release(shadow[i]);
+ }
+ return 0;
+ }
+
+ memcpy(pages, shadow, i * sizeof(struct page *));
+
+ /*
+ * Now we splice them into the pipe..
+ */
+splice_them:
+ return move_to_pipe(pipe, pages, i, offset, len);
+}
+
+ssize_t generic_file_splice_read(struct file *in, struct inode *pipe,
+ size_t len, unsigned int flags)
+{
+ ssize_t spliced;
+ int ret;
+
+ ret = 0;
+ spliced = 0;
+ while (len) {
+ ret = __generic_file_splice_read(in, pipe, len);
+
+ if (ret <= 0)
+ break;
+
+ in->f_pos += ret;
+ len -= ret;
+ spliced += ret;
+ }
+
+ if (spliced)
+ return spliced;
+
+ return ret;
+}
+
+/*
+ * Send 'len' bytes to socket from 'file' at position 'pos' using sendpage().
+ */
+static int pipe_to_sendpage(struct pipe_inode_info *info,
+ struct pipe_buffer *buf, struct splice_desc *sd)
+{
+ struct file *file = sd->file;
+ loff_t pos = sd->pos;
+ unsigned int offset;
+ ssize_t ret;
+ void *ptr;
+
+ /*
+ * sub-optimal, but we are limited by the pipe ->map. we don't
+ * need a kmap'ed buffer here, we just want to make sure we
+ * have the page pinned if the pipe page originates from the
+ * page cache
+ */
+ ptr = buf->ops->map(file, info, buf);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ offset = pos & ~PAGE_CACHE_MASK;
+
+ ret = file->f_op->sendpage(file, buf->page, offset, sd->len, &pos,
+ sd->len < sd->total_len);
+
+ buf->ops->unmap(info, buf);
+ if (ret == sd->len)
+ return 0;
+
+ return -EIO;
+}
+
+/*
+ * This is a little more tricky than the file -> pipe splicing. There are
+ * basically three cases:
+ *
+ * - Destination page already exists in the address space and there
+ * are users of it. For that case we have no other option that
+ * copying the data. Tough luck.
+ * - Destination page already exists in the address space, but there
+ * are no users of it. Make sure it's uptodate, then drop it. Fall
+ * through to last case.
+ * - Destination page does not exist, we can add the pipe page to
+ * the page cache and avoid the copy.
+ *
+ * For now we just do the slower thing and always copy pages over, it's
+ * easier than migrating pages from the pipe to the target file. For the
+ * case of doing file | file splicing, the migrate approach had some LRU
+ * nastiness...
+ */
+static int pipe_to_file(struct pipe_inode_info *info, struct pipe_buffer *buf,
+ struct splice_desc *sd)
+{
+ struct file *file = sd->file;
+ struct address_space *mapping = file->f_mapping;
+ unsigned int offset;
+ struct page *page;
+ pgoff_t index;
+ char *src;
+ int ret;
+
+ /*
+ * after this, page will be locked and unmapped
+ */
+ src = buf->ops->map(file, info, buf);
+ if (IS_ERR(src))
+ return PTR_ERR(src);
+
+ index = sd->pos >> PAGE_CACHE_SHIFT;
+ offset = sd->pos & ~PAGE_CACHE_MASK;
+
+ /*
+ * reuse buf page, if SPLICE_F_MOVE is set
+ */
+ if (sd->flags & SPLICE_F_MOVE) {
+ if (buf->ops->steal(info, buf))
+ goto find_page;
+
+ page = buf->page;
+ if (add_to_page_cache_lru(page, mapping, index,
+ mapping_gfp_mask(mapping)))
+ goto find_page;
+ } else {
+find_page:
+ ret = -ENOMEM;
+ page = find_or_create_page(mapping, index,
+ mapping_gfp_mask(mapping));
+ if (!page)
+ goto out;
+
+ /*
+ * If the page is uptodate, it is also locked. If it isn't
+ * uptodate, we can mark it uptodate if we are filling the
+ * full page. Otherwise we need to read it in first...
+ */
+ if (!PageUptodate(page)) {
+ if (sd->len < PAGE_CACHE_SIZE) {
+ ret = mapping->a_ops->readpage(file, page);
+ if (unlikely(ret))
+ goto out;
+
+ lock_page(page);
+
+ if (!PageUptodate(page)) {
+ /*
+ * page got invalidated, repeat
+ */
+ if (!page->mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto find_page;
+ }
+ ret = -EIO;
+ goto out;
+ }
+ } else {
+ WARN_ON(!PageLocked(page));
+ SetPageUptodate(page);
+ }
+ }
+ }
+
+ ret = mapping->a_ops->prepare_write(file, page, 0, sd->len);
+ if (ret)
+ goto out;
+
+ if (!buf->stolen) {
+ char *dst = kmap_atomic(page, KM_USER0);
+
+ memcpy(dst + offset, src + buf->offset, sd->len);
+ flush_dcache_page(page);
+ kunmap_atomic(dst, KM_USER0);
+ }
+
+ ret = mapping->a_ops->commit_write(file, page, 0, sd->len);
+ if (ret < 0)
+ goto out;
+
+ set_page_dirty(page);
+ ret = write_one_page(page, 0);
+out:
+ if (ret < 0)
+ unlock_page(page);
+ if (!buf->stolen)
+ page_cache_release(page);
+ buf->ops->unmap(info, buf);
+ return ret;
+}
+
+typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *,
+ struct splice_desc *);
+
+static ssize_t move_from_pipe(struct inode *inode, struct file *out,
+ size_t len, unsigned int flags,
+ splice_actor *actor)
+{
+ struct pipe_inode_info *info;
+ int ret, do_wakeup, err;
+ struct splice_desc sd;
+
+ ret = 0;
+ do_wakeup = 0;
+
+ sd.total_len = len;
+ sd.flags = flags;
+ sd.file = out;
+ sd.pos = out->f_pos;
+
+ mutex_lock(PIPE_MUTEX(*inode));
+
+ info = inode->i_pipe;
+ for (;;) {
+ int bufs = info->nrbufs;
+
+ if (bufs) {
+ int curbuf = info->curbuf;
+ struct pipe_buffer *buf = info->bufs + curbuf;
+ struct pipe_buf_operations *ops = buf->ops;
+
+ sd.len = buf->len;
+ if (sd.len > sd.total_len)
+ sd.len = sd.total_len;
+
+ err = actor(info, buf, &sd);
+ if (err) {
+ if (!ret && err != -ENODATA)
+ ret = err;
+
+ break;
+ }
+
+ ret += sd.len;
+ buf->offset += sd.len;
+ buf->len -= sd.len;
+ if (!buf->len) {
+ buf->ops = NULL;
+ ops->release(info, buf);
+ curbuf = (curbuf + 1) & (PIPE_BUFFERS - 1);
+ info->curbuf = curbuf;
+ info->nrbufs = --bufs;
+ do_wakeup = 1;
+ }
+
+ sd.pos += sd.len;
+ sd.total_len -= sd.len;
+ if (!sd.total_len)
+ break;
+ }
+
+ if (bufs)
+ continue;
+ if (!PIPE_WRITERS(*inode))
+ break;
+ if (!PIPE_WAITING_WRITERS(*inode)) {
+ if (ret)
+ break;
+ }
+
+ if (signal_pending(current)) {
+ if (!ret)
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ if (do_wakeup) {
+ wake_up_interruptible_sync(PIPE_WAIT(*inode));
+ kill_fasync(PIPE_FASYNC_WRITERS(*inode),SIGIO,POLL_OUT);
+ do_wakeup = 0;
+ }
+
+ pipe_wait(inode);
+ }
+
+ mutex_unlock(PIPE_MUTEX(*inode));
+
+ if (do_wakeup) {
+ wake_up_interruptible(PIPE_WAIT(*inode));
+ kill_fasync(PIPE_FASYNC_WRITERS(*inode), SIGIO, POLL_OUT);
+ }
+
+ mutex_lock(&out->f_mapping->host->i_mutex);
+ out->f_pos = sd.pos;
+ mutex_unlock(&out->f_mapping->host->i_mutex);
+ return ret;
+
+}
+
+ssize_t generic_file_splice_write(struct inode *inode, struct file *out,
+ size_t len, unsigned int flags)
+{
+ return move_from_pipe(inode, out, len, flags, pipe_to_file);
+}
+
+ssize_t generic_splice_sendpage(struct inode *inode, struct file *out,
+ size_t len, unsigned int flags)
+{
+ return move_from_pipe(inode, out, len, flags, pipe_to_sendpage);
+}
+
+EXPORT_SYMBOL(generic_file_splice_write);
+EXPORT_SYMBOL(generic_file_splice_read);
+
+static long do_splice_from(struct inode *pipe, struct file *out, size_t len,
+ unsigned int flags)
+{
+ loff_t pos;
+ int ret;
+
+ if (!out->f_op || !out->f_op->splice_write)
+ return -EINVAL;
+
+ if (!(out->f_mode & FMODE_WRITE))
+ return -EBADF;
+
+ pos = out->f_pos;
+ ret = rw_verify_area(WRITE, out, &pos, len);
+ if (unlikely(ret < 0))
+ return ret;
+
+ return out->f_op->splice_write(pipe, out, len, flags);
+}
+
+static long do_splice_to(struct file *in, struct inode *pipe, size_t len,
+ unsigned int flags)
+{
+ loff_t pos, isize, left;
+ int ret;
+
+ if (!in->f_op || !in->f_op->splice_read)
+ return -EINVAL;
+
+ if (!(in->f_mode & FMODE_READ))
+ return -EBADF;
+
+ pos = in->f_pos;
+ ret = rw_verify_area(READ, in, &pos, len);
+ if (unlikely(ret < 0))
+ return ret;
+
+ isize = i_size_read(in->f_mapping->host);
+ if (unlikely(in->f_pos >= isize))
+ return 0;
+
+ left = isize - in->f_pos;
+ if (left < len)
+ len = left;
+
+ return in->f_op->splice_read(in, pipe, len, flags);
+}
+
+static long do_splice(struct file *in, struct file *out, size_t len,
+ unsigned int flags)
+{
+ struct inode *pipe;
+
+ pipe = in->f_dentry->d_inode;
+ if (pipe->i_pipe)
+ return do_splice_from(pipe, out, len, flags);
+
+ pipe = out->f_dentry->d_inode;
+ if (pipe->i_pipe)
+ return do_splice_to(in, pipe, len, flags);
+
+ return -EINVAL;
+}
+
+asmlinkage long sys_splice(int fdin, int fdout, size_t len, unsigned int flags)
+{
+ long error;
+ struct file *in, *out;
+ int fput_in, fput_out;
+
+ if (unlikely(!len))
+ return 0;
+
+ error = -EBADF;
+ in = fget_light(fdin, &fput_in);
+ if (in) {
+ if (in->f_mode & FMODE_READ) {
+ out = fget_light(fdout, &fput_out);
+ if (out) {
+ if (out->f_mode & FMODE_WRITE)
+ error = do_splice(in, out, len, flags);
+ fput_light(out, fput_out);
+ }
+ }
+
+ fput_light(in, fput_in);
+ }
+
+ return error;
+}
diff --git a/fs/sync.c b/fs/sync.c
new file mode 100644
index 000000000000..8616006d2094
--- /dev/null
+++ b/fs/sync.c
@@ -0,0 +1,164 @@
+/*
+ * High-level sync()-related operations
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/writeback.h>
+#include <linux/syscalls.h>
+#include <linux/linkage.h>
+#include <linux/pagemap.h>
+
+#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
+ SYNC_FILE_RANGE_WAIT_AFTER)
+
+/*
+ * sys_sync_file_range() permits finely controlled syncing over a segment of
+ * a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is
+ * zero then sys_sync_file_range() will operate from offset out to EOF.
+ *
+ * The flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
+ * before performing the write.
+ *
+ * SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
+ * range which are not presently under writeback.
+ *
+ * SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
+ * after performing the write.
+ *
+ * Useful combinations of the flag bits are:
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
+ * in the range which were dirty on entry to sys_sync_file_range() are placed
+ * under writeout. This is a start-write-for-data-integrity operation.
+ *
+ * SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
+ * are not presently under writeout. This is an asynchronous flush-to-disk
+ * operation. Not suitable for data integrity operations.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
+ * completion of writeout of all pages in the range. This will be used after an
+ * earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
+ * for that operation to complete and to return the result.
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
+ * a traditional sync() operation. This is a write-for-data-integrity operation
+ * which will ensure that all pages in the range which were dirty on entry to
+ * sys_sync_file_range() are committed to disk.
+ *
+ *
+ * SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
+ * I/O errors or ENOSPC conditions and will return those to the caller, after
+ * clearing the EIO and ENOSPC flags in the address_space.
+ *
+ * It should be noted that none of these operations write out the file's
+ * metadata. So unless the application is strictly performing overwrites of
+ * already-instantiated disk blocks, there are no guarantees here that the data
+ * will be available after a crash.
+ */
+asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
+ int flags)
+{
+ int ret;
+ struct file *file;
+ loff_t endbyte; /* inclusive */
+ int fput_needed;
+ umode_t i_mode;
+
+ ret = -EINVAL;
+ if (flags & ~VALID_FLAGS)
+ goto out;
+
+ endbyte = offset + nbytes;
+
+ if ((s64)offset < 0)
+ goto out;
+ if ((s64)endbyte < 0)
+ goto out;
+ if (endbyte < offset)
+ goto out;
+
+ if (sizeof(pgoff_t) == 4) {
+ if (offset >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+ /*
+ * The range starts outside a 32 bit machine's
+ * pagecache addressing capabilities. Let it "succeed"
+ */
+ ret = 0;
+ goto out;
+ }
+ if (endbyte >= (0x100000000ULL << PAGE_CACHE_SHIFT)) {
+ /*
+ * Out to EOF
+ */
+ nbytes = 0;
+ }
+ }
+
+ if (nbytes == 0)
+ endbyte = -1;
+ else
+ endbyte--; /* inclusive */
+
+ ret = -EBADF;
+ file = fget_light(fd, &fput_needed);
+ if (!file)
+ goto out;
+
+ i_mode = file->f_dentry->d_inode->i_mode;
+ ret = -ESPIPE;
+ if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
+ !S_ISLNK(i_mode))
+ goto out_put;
+
+ ret = do_sync_file_range(file, offset, endbyte, flags);
+out_put:
+ fput_light(file, fput_needed);
+out:
+ return ret;
+}
+
+/*
+ * `endbyte' is inclusive
+ */
+int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte,
+ int flags)
+{
+ int ret;
+ struct address_space *mapping;
+
+ mapping = file->f_mapping;
+ if (!mapping) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = 0;
+ if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
+ ret = wait_on_page_writeback_range(mapping,
+ offset >> PAGE_CACHE_SHIFT,
+ endbyte >> PAGE_CACHE_SHIFT);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (flags & SYNC_FILE_RANGE_WRITE) {
+ ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
+ WB_SYNC_NONE);
+ if (ret < 0)
+ goto out;
+ }
+
+ if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
+ ret = wait_on_page_writeback_range(mapping,
+ offset >> PAGE_CACHE_SHIFT,
+ endbyte >> PAGE_CACHE_SHIFT);
+ }
+out:
+ return ret;
+}
+EXPORT_SYMBOL_GPL(do_sync_file_range);
diff --git a/fs/vfat/namei.c b/fs/vfat/namei.c
index ef46939c0c1a..a56cec3be5f0 100644
--- a/fs/vfat/namei.c
+++ b/fs/vfat/namei.c
@@ -185,24 +185,6 @@ static int vfat_valid_longname(const unsigned char *name, unsigned int len)
return -EINVAL;
if (len >= 256)
return -ENAMETOOLONG;
-
- /* MS-DOS "device special files" */
- if (len == 3 || (len > 3 && name[3] == '.')) { /* basename == 3 */
- if (!strnicmp(name, "aux", 3) ||
- !strnicmp(name, "con", 3) ||
- !strnicmp(name, "nul", 3) ||
- !strnicmp(name, "prn", 3))
- return -EINVAL;
- }
- if (len == 4 || (len > 4 && name[4] == '.')) { /* basename == 4 */
- /* "com1", "com2", ... */
- if ('1' <= name[3] && name[3] <= '9') {
- if (!strnicmp(name, "com", 3) ||
- !strnicmp(name, "lpt", 3))
- return -EINVAL;
- }
- }
-
return 0;
}
OpenPOWER on IntegriCloud