aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl2
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl2
-rw-r--r--fs/cachefiles/daemon.c13
-rw-r--r--fs/cachefiles/interface.c11
-rw-r--r--fs/cachefiles/internal.h4
-rw-r--r--fs/cachefiles/namei.c28
-rw-r--r--fs/direct-io.c3
-rw-r--r--fs/jffs2/dir.c11
-rw-r--r--fs/ncpfs/dir.c2
-rw-r--r--fs/nfsd/vfs.c4
-rw-r--r--fs/proc_namespace.c2
-rw-r--r--fs/read_write.c197
-rw-r--r--fs/splice.c5
-rw-r--r--include/linux/blkdev.h3
-rw-r--r--include/linux/compat.h6
-rw-r--r--include/linux/fs.h5
-rw-r--r--include/linux/syscalls.h6
-rw-r--r--include/uapi/linux/fs.h3
18 files changed, 231 insertions, 76 deletions
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index cb713df81180..b30dd8154cc2 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -384,3 +384,5 @@
375 i386 membarrier sys_membarrier
376 i386 mlock2 sys_mlock2
377 i386 copy_file_range sys_copy_file_range
+378 i386 preadv2 sys_preadv2
+379 i386 pwritev2 sys_pwritev2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index dc1040a50bdc..31cec929eb8d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -333,6 +333,8 @@
324 common membarrier sys_membarrier
325 common mlock2 sys_mlock2
326 common copy_file_range sys_copy_file_range
+327 64 preadv2 sys_preadv2
+328 64 pwritev2 sys_pwritev2
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
index 452e98dd7560..1ee54ffd3a24 100644
--- a/fs/cachefiles/daemon.c
+++ b/fs/cachefiles/daemon.c
@@ -162,6 +162,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
size_t buflen, loff_t *pos)
{
struct cachefiles_cache *cache = file->private_data;
+ unsigned long long b_released;
+ unsigned f_released;
char buffer[256];
int n;
@@ -174,6 +176,8 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
cachefiles_has_space(cache, 0, 0);
/* summarise */
+ f_released = atomic_xchg(&cache->f_released, 0);
+ b_released = atomic_long_xchg(&cache->b_released, 0);
clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
n = snprintf(buffer, sizeof(buffer),
@@ -183,15 +187,18 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
" fstop=%llx"
" brun=%llx"
" bcull=%llx"
- " bstop=%llx",
+ " bstop=%llx"
+ " freleased=%x"
+ " breleased=%llx",
test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
(unsigned long long) cache->frun,
(unsigned long long) cache->fcull,
(unsigned long long) cache->fstop,
(unsigned long long) cache->brun,
(unsigned long long) cache->bcull,
- (unsigned long long) cache->bstop
- );
+ (unsigned long long) cache->bstop,
+ f_released,
+ b_released);
if (n > buflen)
return -EMSGSIZE;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 675a3332d72f..861d611b8c05 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -291,15 +291,8 @@ static void cachefiles_drop_object(struct fscache_object *_object)
}
/* note that the object is now inactive */
- if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
- write_lock(&cache->active_lock);
- if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
- &object->flags))
- BUG();
- rb_erase(&object->active_node, &cache->active_nodes);
- wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
- write_unlock(&cache->active_lock);
- }
+ if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+ cachefiles_mark_object_inactive(cache, object);
dput(object->dentry);
object->dentry = NULL;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 9c4b737a54df..2fcde1a34b7c 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -66,6 +66,8 @@ struct cachefiles_cache {
struct rb_root active_nodes; /* active nodes (can't be culled) */
rwlock_t active_lock; /* lock for active_nodes */
atomic_t gravecounter; /* graveyard uniquifier */
+ atomic_t f_released; /* number of objects released lately */
+ atomic_long_t b_released; /* number of blocks released lately */
unsigned frun_percent; /* when to stop culling (% files) */
unsigned fcull_percent; /* when to start culling (% files) */
unsigned fstop_percent; /* when to stop allocating (% files) */
@@ -157,6 +159,8 @@ extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
/*
* namei.c
*/
+extern void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+ struct cachefiles_object *object);
extern int cachefiles_delete_object(struct cachefiles_cache *cache,
struct cachefiles_object *object);
extern int cachefiles_walk_to_object(struct cachefiles_object *parent,
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 1c2334c163dd..4ae75006e73b 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -258,6 +258,28 @@ requeue:
}
/*
+ * Mark an object as being inactive.
+ */
+void cachefiles_mark_object_inactive(struct cachefiles_cache *cache,
+ struct cachefiles_object *object)
+{
+ write_lock(&cache->active_lock);
+ rb_erase(&object->active_node, &cache->active_nodes);
+ clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+ write_unlock(&cache->active_lock);
+
+ wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+
+ /* This object can now be culled, so we need to let the daemon know
+ * that there is something it can remove if it needs to.
+ */
+ atomic_long_add(d_backing_inode(object->dentry)->i_blocks,
+ &cache->b_released);
+ if (atomic_inc_return(&cache->f_released))
+ cachefiles_state_changed(cache);
+}
+
+/*
* delete an object representation from the cache
* - file backed objects are unlinked
* - directory backed objects are stuffed into the graveyard for userspace to
@@ -684,11 +706,7 @@ mark_active_timed_out:
check_error:
_debug("check error %d", ret);
- write_lock(&cache->active_lock);
- rb_erase(&object->active_node, &cache->active_nodes);
- clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
- wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
- write_unlock(&cache->active_lock);
+ cachefiles_mark_object_inactive(cache, object);
release_dentry:
dput(object->dentry);
object->dentry = NULL;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 1b2f7ffc8b84..85463171053b 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -445,7 +445,8 @@ static struct bio *dio_await_one(struct dio *dio)
__set_current_state(TASK_UNINTERRUPTIBLE);
dio->waiter = current;
spin_unlock_irqrestore(&dio->bio_lock, flags);
- if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
+ if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
+ !blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
io_schedule();
/* wake up sets us TASK_RUNNING */
spin_lock_irqsave(&dio->bio_lock, flags);
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index d211b8e18566..30c4c9ebb693 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n",
__func__, ret);
- /* Might as well let the VFS know */
- d_instantiate(new_dentry, d_inode(old_dentry));
- ihold(d_inode(old_dentry));
+ /*
+ * We can't keep the target in dcache after that.
+ * For one thing, we can't afford dentry aliases for directories.
+ * For another, if there was a victim, we _can't_ set new inode
+ * for that sucker and we have to trigger mount eviction - the
+ * caller won't do it on its own since we are returning an error.
+ */
+ d_invalidate(new_dentry);
new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
return ret;
}
diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c
index 26c2de2de13f..b7f8eaeea5d8 100644
--- a/fs/ncpfs/dir.c
+++ b/fs/ncpfs/dir.c
@@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx,
d_rehash(newdent);
} else {
spin_lock(&dentry->d_lock);
- NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE;
+ NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE;
spin_unlock(&dentry->d_lock);
}
} else {
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 5d2a57e4c03a..d40010e4f1a9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -870,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
oldfs = get_fs();
set_fs(KERNEL_DS);
- host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset);
+ host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0);
set_fs(oldfs);
return nfsd_finish_read(file, count, host_err);
}
@@ -957,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
/* Write the data. */
oldfs = get_fs(); set_fs(KERNEL_DS);
- host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos);
+ host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0);
set_fs(oldfs);
if (host_err < 0)
goto out_nfserr;
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 2256e7e23e67..3f1190d18991 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -199,6 +199,8 @@ static int show_vfsstat(struct seq_file *m, struct vfsmount *mnt)
if (sb->s_op->show_devname) {
seq_puts(m, "device ");
err = sb->s_op->show_devname(m, mnt_path.dentry);
+ if (err)
+ goto out;
} else {
if (r->mnt_devname) {
seq_puts(m, "device ");
diff --git a/fs/read_write.c b/fs/read_write.c
index dadf24e5c95b..cf377cf9dfe3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -693,12 +693,17 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
EXPORT_SYMBOL(iov_shorten);
static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
- loff_t *ppos, iter_fn_t fn)
+ loff_t *ppos, iter_fn_t fn, int flags)
{
struct kiocb kiocb;
ssize_t ret;
+ if (flags & ~RWF_HIPRI)
+ return -EOPNOTSUPP;
+
init_sync_kiocb(&kiocb, filp);
+ if (flags & RWF_HIPRI)
+ kiocb.ki_flags |= IOCB_HIPRI;
kiocb.ki_pos = *ppos;
ret = fn(&kiocb, iter);
@@ -709,10 +714,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
/* Do it by hand, with file-ops */
static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
- loff_t *ppos, io_fn_t fn)
+ loff_t *ppos, io_fn_t fn, int flags)
{
ssize_t ret = 0;
+ if (flags & ~RWF_HIPRI)
+ return -EOPNOTSUPP;
+
while (iov_iter_count(iter)) {
struct iovec iovec = iov_iter_iovec(iter);
ssize_t nr;
@@ -813,7 +821,8 @@ out:
static ssize_t do_readv_writev(int type, struct file *file,
const struct iovec __user * uvector,
- unsigned long nr_segs, loff_t *pos)
+ unsigned long nr_segs, loff_t *pos,
+ int flags)
{
size_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
@@ -845,9 +854,9 @@ static ssize_t do_readv_writev(int type, struct file *file,
}
if (iter_fn)
- ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+ ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
else
- ret = do_loop_readv_writev(file, &iter, pos, fn);
+ ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
if (type != READ)
file_end_write(file);
@@ -864,40 +873,40 @@ out:
}
ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
if (!(file->f_mode & FMODE_READ))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_READ))
return -EINVAL;
- return do_readv_writev(READ, file, vec, vlen, pos);
+ return do_readv_writev(READ, file, vec, vlen, pos, flags);
}
EXPORT_SYMBOL(vfs_readv);
ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
if (!(file->f_mode & FMODE_WRITE))
return -EBADF;
if (!(file->f_mode & FMODE_CAN_WRITE))
return -EINVAL;
- return do_readv_writev(WRITE, file, vec, vlen, pos);
+ return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
}
EXPORT_SYMBOL(vfs_writev);
-SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen)
+static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
- ret = vfs_readv(f.file, vec, vlen, &pos);
+ ret = vfs_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
@@ -909,15 +918,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}
-SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen)
+static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret = -EBADF;
if (f.file) {
loff_t pos = file_pos_read(f.file);
- ret = vfs_writev(f.file, vec, vlen, &pos);
+ ret = vfs_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
file_pos_write(f.file, pos);
fdput_pos(f);
@@ -935,10 +944,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
}
-SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, loff_t pos, int flags)
{
- loff_t pos = pos_from_hilo(pos_h, pos_l);
struct fd f;
ssize_t ret = -EBADF;
@@ -949,7 +957,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
- ret = vfs_readv(f.file, vec, vlen, &pos);
+ ret = vfs_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
}
@@ -959,10 +967,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}
-SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
- unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, loff_t pos, int flags)
{
- loff_t pos = pos_from_hilo(pos_h, pos_l);
struct fd f;
ssize_t ret = -EBADF;
@@ -973,7 +980,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
if (f.file) {
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
- ret = vfs_writev(f.file, vec, vlen, &pos);
+ ret = vfs_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
}
@@ -983,11 +990,64 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
return ret;
}
+SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
+{
+ return do_readv(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen)
+{
+ return do_writev(fd, vec, vlen, 0);
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ return do_preadv(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+ int, flags)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ if (pos == -1)
+ return do_readv(fd, vec, vlen, flags);
+
+ return do_preadv(fd, vec, vlen, pos, flags);
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ return do_pwritev(fd, vec, vlen, pos, 0);
+}
+
+SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
+ unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h,
+ int, flags)
+{
+ loff_t pos = pos_from_hilo(pos_h, pos_l);
+
+ if (pos == -1)
+ return do_writev(fd, vec, vlen, flags);
+
+ return do_pwritev(fd, vec, vlen, pos, flags);
+}
+
#ifdef CONFIG_COMPAT
static ssize_t compat_do_readv_writev(int type, struct file *file,
const struct compat_iovec __user *uvector,
- unsigned long nr_segs, loff_t *pos)
+ unsigned long nr_segs, loff_t *pos,
+ int flags)
{
compat_ssize_t tot_len;
struct iovec iovstack[UIO_FASTIOV];
@@ -1019,9 +1079,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file,
}
if (iter_fn)
- ret = do_iter_readv_writev(file, &iter, pos, iter_fn);
+ ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
else
- ret = do_loop_readv_writev(file, &iter, pos, fn);
+ ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
if (type != READ)
file_end_write(file);
@@ -1039,7 +1099,7 @@ out:
static size_t compat_readv(struct file *file,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
ssize_t ret = -EBADF;
@@ -1050,7 +1110,7 @@ static size_t compat_readv(struct file *file,
if (!(file->f_mode & FMODE_CAN_READ))
goto out;
- ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
+ ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);
out:
if (ret > 0)
@@ -1059,9 +1119,9 @@ out:
return ret;
}
-COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
- const struct compat_iovec __user *,vec,
- compat_ulong_t, vlen)
+static size_t do_compat_readv(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
@@ -1070,16 +1130,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
- ret = compat_readv(f.file, vec, vlen, &pos);
+ ret = compat_readv(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
+
+}
+
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen)
+{
+ return do_compat_readv(fd, vec, vlen, 0);
}
-static long __compat_sys_preadv64(unsigned long fd,
+static long do_compat_preadv64(unsigned long fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t pos)
+ unsigned long vlen, loff_t pos, int flags)
{
struct fd f;
ssize_t ret;
@@ -1091,7 +1159,7 @@ static long __compat_sys_preadv64(unsigned long fd,
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PREAD)
- ret = compat_readv(f.file, vec, vlen, &pos);
+ ret = compat_readv(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
@@ -1101,7 +1169,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
- return __compat_sys_preadv64(fd, vec, vlen, pos);
+ return do_compat_preadv64(fd, vec, vlen, pos, 0);
}
#endif
@@ -1111,12 +1179,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
- return __compat_sys_preadv64(fd, vec, vlen, pos);
+ return do_compat_preadv64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high,
+ int, flags)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+ if (pos == -1)
+ return do_compat_readv(fd, vec, vlen, flags);
+
+ return do_compat_preadv64(fd, vec, vlen, pos, flags);
}
static size_t compat_writev(struct file *file,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t *pos)
+ unsigned long vlen, loff_t *pos, int flags)
{
ssize_t ret = -EBADF;
@@ -1127,7 +1208,7 @@ static size_t compat_writev(struct file *file,
if (!(file->f_mode & FMODE_CAN_WRITE))
goto out;
- ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
+ ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0);
out:
if (ret > 0)
@@ -1136,9 +1217,9 @@ out:
return ret;
}
-COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
- const struct compat_iovec __user *, vec,
- compat_ulong_t, vlen)
+static size_t do_compat_writev(compat_ulong_t fd,
+ const struct compat_iovec __user* vec,
+ compat_ulong_t vlen, int flags)
{
struct fd f = fdget_pos(fd);
ssize_t ret;
@@ -1147,16 +1228,23 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
if (!f.file)
return -EBADF;
pos = f.file->f_pos;
- ret = compat_writev(f.file, vec, vlen, &pos);
+ ret = compat_writev(f.file, vec, vlen, &pos, flags);
if (ret >= 0)
f.file->f_pos = pos;
fdput_pos(f);
return ret;
}
-static long __compat_sys_pwritev64(unsigned long fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
+ const struct compat_iovec __user *, vec,
+ compat_ulong_t, vlen)
+{
+ return do_compat_writev(fd, vec, vlen, 0);
+}
+
+static long do_compat_pwritev64(unsigned long fd,
const struct compat_iovec __user *vec,
- unsigned long vlen, loff_t pos)
+ unsigned long vlen, loff_t pos, int flags)
{
struct fd f;
ssize_t ret;
@@ -1168,7 +1256,7 @@ static long __compat_sys_pwritev64(unsigned long fd,
return -EBADF;
ret = -ESPIPE;
if (f.file->f_mode & FMODE_PWRITE)
- ret = compat_writev(f.file, vec, vlen, &pos);
+ ret = compat_writev(f.file, vec, vlen, &pos, flags);
fdput(f);
return ret;
}
@@ -1178,7 +1266,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
const struct compat_iovec __user *,vec,
unsigned long, vlen, loff_t, pos)
{
- return __compat_sys_pwritev64(fd, vec, vlen, pos);
+ return do_compat_pwritev64(fd, vec, vlen, pos, 0);
}
#endif
@@ -1188,8 +1276,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
- return __compat_sys_pwritev64(fd, vec, vlen, pos);
+ return do_compat_pwritev64(fd, vec, vlen, pos, 0);
+}
+
+COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd,
+ const struct compat_iovec __user *,vec,
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags)
+{
+ loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+
+ if (pos == -1)
+ return do_compat_writev(fd, vec, vlen, flags);
+
+ return do_compat_pwritev64(fd, vec, vlen, pos, flags);
}
+
#endif
static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
diff --git a/fs/splice.c b/fs/splice.c
index 82bc0d64fc38..9947b5c69664 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -185,6 +185,9 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
unsigned int spd_pages = spd->nr_pages;
int ret, do_wakeup, page_nr;
+ if (!spd_pages)
+ return 0;
+
ret = 0;
do_wakeup = 0;
page_nr = 0;
@@ -577,7 +580,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec,
old_fs = get_fs();
set_fs(get_ds());
/* The cast to a user pointer is valid due to the set_fs() */
- res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos);
+ res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0);
set_fs(old_fs);
return res;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4571ef1a12a9..458f6efe3a21 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -499,7 +499,8 @@ struct request_queue {
#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \
(1 << QUEUE_FLAG_STACKABLE) | \
- (1 << QUEUE_FLAG_SAME_COMP))
+ (1 << QUEUE_FLAG_SAME_COMP) | \
+ (1 << QUEUE_FLAG_POLL))
static inline void queue_lockdep_assert_held(struct request_queue *q)
{
diff --git a/include/linux/compat.h b/include/linux/compat.h
index a76c9172b2eb..fe4ccd0c748a 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -340,6 +340,12 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd,
const struct compat_iovec __user *vec,
compat_ulong_t vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);
+asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd,
+ const struct compat_iovec __user *vec,
+ compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags);
#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64
asmlinkage long compat_sys_preadv64(unsigned long fd,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c577923cd400..3a0d6e54208d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -320,6 +320,7 @@ struct writeback_control;
#define IOCB_EVENTFD (1 << 0)
#define IOCB_APPEND (1 << 1)
#define IOCB_DIRECT (1 << 2)
+#define IOCB_HIPRI (1 << 3)
struct kiocb {
struct file *ki_filp;
@@ -1704,9 +1705,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *)
extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
- unsigned long, loff_t *);
+ unsigned long, loff_t *, int);
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
- unsigned long, loff_t *);
+ unsigned long, loff_t *, int);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
loff_t, size_t, unsigned int);
extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 185815c96433..d795472c54d8 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -575,8 +575,14 @@ asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
size_t count, loff_t pos);
asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
+ int flags);
asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec,
+ unsigned long vlen, unsigned long pos_l, unsigned long pos_h,
+ int flags);
asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode);
asmlinkage long sys_chdir(const char __user *filename);
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 149bec83a907..d2463396125c 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -304,4 +304,7 @@ struct fsxattr {
#define SYNC_FILE_RANGE_WRITE 2
#define SYNC_FILE_RANGE_WAIT_AFTER 4
+/* flags for preadv2/pwritev2: */
+#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */
+
#endif /* _UAPI_LINUX_FS_H */