summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 22:47:20 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2023-06-26 22:47:20 +0300
commita0433f8cae3ac51f59b4b1863032822aaa2d8164 (patch)
tree9eb7b096aa9f7fa53921e6ff247488f3a55471f5 /fs
parent0aa69d53ac7c30f6184f88f2e310d808b32b35a5 (diff)
parentfcaa174a9c995cf0af3967e55644a1543ea07e36 (diff)
downloadlinux-a0433f8cae3ac51f59b4b1863032822aaa2d8164.tar.xz
Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux
Pull block updates from Jens Axboe: - NVMe pull request via Keith: - Various cleanups all around (Irvin, Chaitanya, Christophe) - Better struct packing (Christophe JAILLET) - Reduce controller error logs for optional commands (Keith) - Support for >=64KiB block sizes (Daniel Gomez) - Fabrics fixes and code organization (Max, Chaitanya, Daniel Wagner) - bcache updates via Coly: - Fix a race at init time (Mingzhe Zou) - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye) - use page pinning in the block layer for dio (David) - convert old block dio code to page pinning (David, Christoph) - cleanups for pktcdvd (Andy) - cleanups for rnbd (Guoqing) - use the unchecked __bio_add_page() for the initial single page additions (Johannes) - fix overflows in the Amiga partition handling code (Michael) - improve mq-deadline zoned device support (Bart) - keep passthrough requests out of the IO schedulers (Christoph, Ming) - improve support for flush requests, making them less special to deal with (Christoph) - add bdev holder ops and shutdown methods (Christoph) - fix the name_to_dev_t() situation and use cases (Christoph) - decouple the block open flags from fmode_t (Christoph) - ublk updates and cleanups, including adding user copy support (Ming) - BFQ sanity checking (Bart) - convert brd from radix to xarray (Pankaj) - constify various structures (Thomas, Ivan) - more fine grained persistent reservation ioctl capability checks (Jingbo) - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan, Jordy, Li, Min, Yu, Zhong, Waiman) * tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits) scsi/sg: don't grab scsi host module reference ext4: Fix warning in blkdev_put() block: don't return -EINVAL for not found names in devt_from_devname cdrom: Fix spectre-v1 gadget block: Improve kernel-doc headers blk-mq: don't insert passthrough request into sw queue bsg: make bsg_class a static const structure ublk: make ublk_chr_class a static const structure aoe: make aoe_class a static const structure block/rnbd: make all 'class' structures const block: fix the exclusive open mask in disk_scan_partitions block: add overflow checks for Amiga partition support block: change all __u32 annotations to __be32 in affs_hardblocks.h block: fix signed int overflow in Amiga partition support block: add capacity validation in bdev_add_partition() block: fine-granular CAP_SYS_ADMIN for Persistent Reservation block: disallow Persistent Reservation on partitions reiserfs: fix blkdev_put() warning from release_journal_dev() block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions() block: document the holder argument to blkdev_get_by_path ...
Diffstat (limited to 'fs')
-rw-r--r--fs/Makefile10
-rw-r--r--fs/btrfs/dev-replace.c8
-rw-r--r--fs/btrfs/ioctl.c12
-rw-r--r--fs/btrfs/super.c21
-rw-r--r--fs/btrfs/volumes.c59
-rw-r--r--fs/btrfs/volumes.h11
-rw-r--r--fs/buffer.c3
-rw-r--r--fs/direct-io.c71
-rw-r--r--fs/erofs/super.c7
-rw-r--r--fs/ext4/ext4.h1
-rw-r--r--fs/ext4/ioctl.c24
-rw-r--r--fs/ext4/super.c27
-rw-r--r--fs/f2fs/super.c12
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/inode.c3
-rw-r--r--fs/iomap/buffered-io.c6
-rw-r--r--fs/iomap/direct-io.c1
-rw-r--r--fs/jfs/jfs_logmgr.c12
-rw-r--r--fs/nfs/blocklayout/dev.c10
-rw-r--r--fs/nilfs2/super.c12
-rw-r--r--fs/no-block.c19
-rw-r--r--fs/ocfs2/cluster/heartbeat.c7
-rw-r--r--fs/pstore/blk.c4
-rw-r--r--fs/reiserfs/journal.c25
-rw-r--r--fs/reiserfs/reiserfs.h1
-rw-r--r--fs/splice.c15
-rw-r--r--fs/super.c48
-rw-r--r--fs/xfs/xfs_fsops.c3
-rw-r--r--fs/xfs/xfs_mount.h4
-rw-r--r--fs/xfs/xfs_super.c34
-rw-r--r--fs/zonefs/super.c2
31 files changed, 254 insertions, 220 deletions
diff --git a/fs/Makefile b/fs/Makefile
index 5bfdbf0d7037..e513aaee0603 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -17,14 +17,8 @@ obj-y := open.o read_write.o file_table.o super.o \
fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
kernel_read_file.o mnt_idmapping.o remap_range.o
-ifeq ($(CONFIG_BLOCK),y)
-obj-y += buffer.o mpage.o
-else
-obj-y += no-block.o
-endif
-
-obj-$(CONFIG_PROC_FS) += proc_namespace.o
-
+obj-$(CONFIG_BLOCK) += buffer.o mpage.o
+obj-$(CONFIG_PROC_FS) += proc_namespace.o
obj-$(CONFIG_LEGACY_DIRECT_IO) += direct-io.o
obj-y += notify/
obj-$(CONFIG_EPOLL) += eventpoll.o
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5e86bea0a950..5f10965fd72b 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -257,8 +257,8 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
return -EINVAL;
}
- bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
- fs_info->bdev_holder);
+ bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
+ fs_info->bdev_holder, NULL);
if (IS_ERR(bdev)) {
btrfs_err(fs_info, "target device %s is invalid!", device_path);
return PTR_ERR(bdev);
@@ -315,7 +315,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
device->bdev = bdev;
set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
set_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
- device->mode = FMODE_EXCL;
+ device->holder = fs_info->bdev_holder;
device->dev_stats_valid = 1;
set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
device->fs_devices = fs_devices;
@@ -334,7 +334,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
return 0;
error:
- blkdev_put(bdev, FMODE_EXCL);
+ blkdev_put(bdev, fs_info->bdev_holder);
return ret;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index edbbd5cf23fc..a895d105464b 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2671,7 +2671,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ioctl_vol_args_v2 *vol_args;
struct block_device *bdev = NULL;
- fmode_t mode;
+ void *holder;
int ret;
bool cancel = false;
@@ -2708,7 +2708,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
goto err_drop;
/* Exclusive operation is now claimed */
- ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
+ ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
btrfs_exclop_finish(fs_info);
@@ -2723,7 +2723,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
err_drop:
mnt_drop_write_file(file);
if (bdev)
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, holder);
out:
btrfs_put_dev_args_from_path(&args);
kfree(vol_args);
@@ -2737,7 +2737,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ioctl_vol_args *vol_args;
struct block_device *bdev = NULL;
- fmode_t mode;
+ void *holder;
int ret;
bool cancel = false;
@@ -2764,7 +2764,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
ret = exclop_start_or_cancel_reloc(fs_info, BTRFS_EXCLOP_DEV_REMOVE,
cancel);
if (ret == 0) {
- ret = btrfs_rm_device(fs_info, &args, &bdev, &mode);
+ ret = btrfs_rm_device(fs_info, &args, &bdev, &holder);
if (!ret)
btrfs_info(fs_info, "disk deleted %s", vol_args->name);
btrfs_exclop_finish(fs_info);
@@ -2772,7 +2772,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
mnt_drop_write_file(file);
if (bdev)
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, holder);
out:
btrfs_put_dev_args_from_path(&args);
kfree(vol_args);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8b1c1225245e..f1dd172d8d5b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -849,8 +849,7 @@ out:
* All other options will be parsed on much later in the mount process and
* only when we need to allocate a new super block.
*/
-static int btrfs_parse_device_options(const char *options, fmode_t flags,
- void *holder)
+static int btrfs_parse_device_options(const char *options, blk_mode_t flags)
{
substring_t args[MAX_OPT_ARGS];
char *device_name, *opts, *orig, *p;
@@ -884,8 +883,7 @@ static int btrfs_parse_device_options(const char *options, fmode_t flags,
error = -ENOMEM;
goto out;
}
- device = btrfs_scan_one_device(device_name, flags,
- holder);
+ device = btrfs_scan_one_device(device_name, flags);
kfree(device_name);
if (IS_ERR(device)) {
error = PTR_ERR(device);
@@ -1442,12 +1440,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
struct btrfs_fs_devices *fs_devices = NULL;
struct btrfs_fs_info *fs_info = NULL;
void *new_sec_opts = NULL;
- fmode_t mode = FMODE_READ;
+ blk_mode_t mode = sb_open_mode(flags);
int error = 0;
- if (!(flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
if (data) {
error = security_sb_eat_lsm_opts(data, &new_sec_opts);
if (error)
@@ -1477,13 +1472,13 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
}
mutex_lock(&uuid_mutex);
- error = btrfs_parse_device_options(data, mode, fs_type);
+ error = btrfs_parse_device_options(data, mode);
if (error) {
mutex_unlock(&uuid_mutex);
goto error_fs_info;
}
- device = btrfs_scan_one_device(device_name, mode, fs_type);
+ device = btrfs_scan_one_device(device_name, mode);
if (IS_ERR(device)) {
mutex_unlock(&uuid_mutex);
error = PTR_ERR(device);
@@ -2195,8 +2190,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
switch (cmd) {
case BTRFS_IOC_SCAN_DEV:
mutex_lock(&uuid_mutex);
- device = btrfs_scan_one_device(vol->name, FMODE_READ,
- &btrfs_root_fs_type);
+ device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ);
ret = PTR_ERR_OR_ZERO(device);
mutex_unlock(&uuid_mutex);
break;
@@ -2210,8 +2204,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
break;
case BTRFS_IOC_DEVICES_READY:
mutex_lock(&uuid_mutex);
- device = btrfs_scan_one_device(vol->name, FMODE_READ,
- &btrfs_root_fs_type);
+ device = btrfs_scan_one_device(vol->name, BLK_OPEN_READ);
if (IS_ERR(device)) {
mutex_unlock(&uuid_mutex);
ret = PTR_ERR(device);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4193ace3fb5a..73f9ea7672db 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -510,13 +510,13 @@ static struct btrfs_fs_devices *find_fsid_with_metadata_uuid(
static int
-btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
+btrfs_get_bdev_and_sb(const char *device_path, blk_mode_t flags, void *holder,
int flush, struct block_device **bdev,
struct btrfs_super_block **disk_super)
{
int ret;
- *bdev = blkdev_get_by_path(device_path, flags, holder);
+ *bdev = blkdev_get_by_path(device_path, flags, holder, NULL);
if (IS_ERR(*bdev)) {
ret = PTR_ERR(*bdev);
@@ -527,14 +527,14 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
sync_blockdev(*bdev);
ret = set_blocksize(*bdev, BTRFS_BDEV_BLOCKSIZE);
if (ret) {
- blkdev_put(*bdev, flags);
+ blkdev_put(*bdev, holder);
goto error;
}
invalidate_bdev(*bdev);
*disk_super = btrfs_read_dev_super(*bdev);
if (IS_ERR(*disk_super)) {
ret = PTR_ERR(*disk_super);
- blkdev_put(*bdev, flags);
+ blkdev_put(*bdev, holder);
goto error;
}
@@ -610,7 +610,7 @@ static int btrfs_free_stale_devices(dev_t devt, struct btrfs_device *skip_device
* fs_devices->device_list_mutex here.
*/
static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
- struct btrfs_device *device, fmode_t flags,
+ struct btrfs_device *device, blk_mode_t flags,
void *holder)
{
struct block_device *bdev;
@@ -662,7 +662,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
device->bdev = bdev;
clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
- device->mode = flags;
+ device->holder = holder;
fs_devices->open_devices++;
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) &&
@@ -676,7 +676,7 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices,
error_free_page:
btrfs_release_disk_super(disk_super);
- blkdev_put(bdev, flags);
+ blkdev_put(bdev, holder);
return -EINVAL;
}
@@ -1067,7 +1067,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
continue;
if (device->bdev) {
- blkdev_put(device->bdev, device->mode);
+ blkdev_put(device->bdev, device->holder);
device->bdev = NULL;
fs_devices->open_devices--;
}
@@ -1113,7 +1113,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
invalidate_bdev(device->bdev);
}
- blkdev_put(device->bdev, device->mode);
+ blkdev_put(device->bdev, device->holder);
}
static void btrfs_close_one_device(struct btrfs_device *device)
@@ -1217,14 +1217,12 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
}
static int open_fs_devices(struct btrfs_fs_devices *fs_devices,
- fmode_t flags, void *holder)
+ blk_mode_t flags, void *holder)
{
struct btrfs_device *device;
struct btrfs_device *latest_dev = NULL;
struct btrfs_device *tmp_device;
- flags |= FMODE_EXCL;
-
list_for_each_entry_safe(device, tmp_device, &fs_devices->devices,
dev_list) {
int ret;
@@ -1267,7 +1265,7 @@ static int devid_cmp(void *priv, const struct list_head *a,
}
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
- fmode_t flags, void *holder)
+ blk_mode_t flags, void *holder)
{
int ret;
@@ -1358,8 +1356,7 @@ int btrfs_forget_devices(dev_t devt)
* and we are not allowed to call set_blocksize during the scan. The superblock
* is read via pagecache
*/
-struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
- void *holder)
+struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags)
{
struct btrfs_super_block *disk_super;
bool new_device_added = false;
@@ -1378,16 +1375,16 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
*/
/*
- * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may
- * initiate the device scan which may race with the user's mount
- * or mkfs command, resulting in failure.
- * Since the device scan is solely for reading purposes, there is
- * no need for FMODE_EXCL. Additionally, the devices are read again
+ * Avoid an exclusive open here, as the systemd-udev may initiate the
+ * device scan which may race with the user's mount or mkfs command,
+ * resulting in failure.
+ * Since the device scan is solely for reading purposes, there is no
+ * need for an exclusive open. Additionally, the devices are read again
* during the mount process. It is ok to get some inconsistent
* values temporarily, as the device paths of the fsid are the only
* required information for assembling the volume.
*/
- bdev = blkdev_get_by_path(path, flags, holder);
+ bdev = blkdev_get_by_path(path, flags, NULL, NULL);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
@@ -1411,7 +1408,7 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
btrfs_release_disk_super(disk_super);
error_bdev_put:
- blkdev_put(bdev, flags);
+ blkdev_put(bdev, NULL);
return device;
}
@@ -2098,7 +2095,7 @@ void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
int btrfs_rm_device(struct btrfs_fs_info *fs_info,
struct btrfs_dev_lookup_args *args,
- struct block_device **bdev, fmode_t *mode)
+ struct block_device **bdev, void **holder)
{
struct btrfs_trans_handle *trans;
struct btrfs_device *device;
@@ -2237,7 +2234,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info,
}
*bdev = device->bdev;
- *mode = device->mode;
+ *holder = device->holder;
synchronize_rcu();
btrfs_free_device(device);
@@ -2391,7 +2388,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
return -ENOMEM;
}
- ret = btrfs_get_bdev_and_sb(path, FMODE_READ, fs_info->bdev_holder, 0,
+ ret = btrfs_get_bdev_and_sb(path, BLK_OPEN_READ, NULL, 0,
&bdev, &disk_super);
if (ret) {
btrfs_put_dev_args_from_path(args);
@@ -2405,7 +2402,7 @@ int btrfs_get_dev_args_from_path(struct btrfs_fs_info *fs_info,
else
memcpy(args->fsid, disk_super->fsid, BTRFS_FSID_SIZE);
btrfs_release_disk_super(disk_super);
- blkdev_put(bdev, FMODE_READ);
+ blkdev_put(bdev, NULL);
return 0;
}
@@ -2638,8 +2635,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
if (sb_rdonly(sb) && !fs_devices->seeding)
return -EROFS;
- bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
- fs_info->bdev_holder);
+ bdev = blkdev_get_by_path(device_path, BLK_OPEN_WRITE,
+ fs_info->bdev_holder, NULL);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
@@ -2701,7 +2698,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
device->commit_total_bytes = device->total_bytes;
set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state);
clear_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state);
- device->mode = FMODE_EXCL;
+ device->holder = fs_info->bdev_holder;
device->dev_stats_valid = 1;
set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
@@ -2859,7 +2856,7 @@ error_free_zone:
error_free_device:
btrfs_free_device(device);
error:
- blkdev_put(bdev, FMODE_EXCL);
+ blkdev_put(bdev, fs_info->bdev_holder);
if (locked) {
mutex_unlock(&uuid_mutex);
up_write(&sb->s_umount);
@@ -6898,7 +6895,7 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
if (IS_ERR(fs_devices))
return fs_devices;
- ret = open_fs_devices(fs_devices, FMODE_READ, fs_info->bdev_holder);
+ ret = open_fs_devices(fs_devices, BLK_OPEN_READ, fs_info->bdev_holder);
if (ret) {
free_fs_devices(fs_devices);
return ERR_PTR(ret);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index d44cb9d22d63..b8c51f16ba86 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -94,8 +94,8 @@ struct btrfs_device {
struct btrfs_zoned_device_info *zone_info;
- /* the mode sent to blkdev_get */
- fmode_t mode;
+ /* block device holder for blkdev_get/put */
+ void *holder;
/*
* Device's major-minor number. Must be set even if the device is not
@@ -610,9 +610,8 @@ struct btrfs_block_group *btrfs_create_chunk(struct btrfs_trans_handle *trans,
u64 type);
void btrfs_mapping_tree_free(struct extent_map_tree *tree);
int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
- fmode_t flags, void *holder);
-struct btrfs_device *btrfs_scan_one_device(const char *path,
- fmode_t flags, void *holder);
+ blk_mode_t flags, void *holder);
+struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags);
int btrfs_forget_devices(dev_t devt);
void btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices);
@@ -630,7 +629,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
void btrfs_put_dev_args_from_path(struct btrfs_dev_lookup_args *args);
int btrfs_rm_device(struct btrfs_fs_info *fs_info,
struct btrfs_dev_lookup_args *args,
- struct block_device **bdev, fmode_t *mode);
+ struct block_device **bdev, void **holder);
void __exit btrfs_cleanup_fs_uuids(void);
int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
int btrfs_grow_device(struct btrfs_trans_handle *trans,
diff --git a/fs/buffer.c b/fs/buffer.c
index fe64356e89b8..93c7446d9221 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2759,8 +2759,7 @@ static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
- BUG_ON(bio->bi_iter.bi_size != bh->b_size);
+ __bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0b380bb8a81e..2ceb378b93c0 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -42,8 +42,8 @@
#include "internal.h"
/*
- * How many user pages to map in one call to get_user_pages(). This determines
- * the size of a structure in the slab cache
+ * How many user pages to map in one call to iov_iter_extract_pages(). This
+ * determines the size of a structure in the slab cache
*/
#define DIO_PAGES 64
@@ -121,12 +121,13 @@ struct dio {
struct inode *inode;
loff_t i_size; /* i_size when submitted */
dio_iodone_t *end_io; /* IO completion function */
+ bool is_pinned; /* T if we have pins on the pages */
void *private; /* copy from map_bh.b_private */
/* BIO completion state */
spinlock_t bio_lock; /* protects BIO fields below */
- int page_errors; /* errno from get_user_pages() */
+ int page_errors; /* err from iov_iter_extract_pages() */
int is_async; /* is IO async ? */
bool defer_completion; /* defer AIO completion to workqueue? */
bool should_dirty; /* if pages should be dirtied */
@@ -165,14 +166,14 @@ static inline unsigned dio_pages_present(struct dio_submit *sdio)
*/
static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
{
+ struct page **pages = dio->pages;
const enum req_op dio_op = dio->opf & REQ_OP_MASK;
ssize_t ret;
- ret = iov_iter_get_pages2(sdio->iter, dio->pages, LONG_MAX, DIO_PAGES,
- &sdio->from);
+ ret = iov_iter_extract_pages(sdio->iter, &pages, LONG_MAX,
+ DIO_PAGES, 0, &sdio->from);
if (ret < 0 && sdio->blocks_available && dio_op == REQ_OP_WRITE) {
- struct page *page = ZERO_PAGE(0);
/*
* A memory fault, but the filesystem has some outstanding
* mapped blocks. We need to use those blocks up to avoid
@@ -180,8 +181,7 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
*/
if (dio->page_errors == 0)
dio->page_errors = ret;
- get_page(page);
- dio->pages[0] = page;
+ dio->pages[0] = ZERO_PAGE(0);
sdio->head = 0;
sdio->tail = 1;
sdio->from = 0;
@@ -201,9 +201,9 @@ static inline int dio_refill_pages(struct dio *dio, struct dio_submit *sdio)
/*
* Get another userspace page. Returns an ERR_PTR on error. Pages are
- * buffered inside the dio so that we can call get_user_pages() against a
- * decent number of pages, less frequently. To provide nicer use of the
- * L1 cache.
+ * buffered inside the dio so that we can call iov_iter_extract_pages()
+ * against a decent number of pages, less frequently. To provide nicer use of
+ * the L1 cache.
*/
static inline struct page *dio_get_page(struct dio *dio,
struct dio_submit *sdio)
@@ -219,6 +219,18 @@ static inline struct page *dio_get_page(struct dio *dio,
return dio->pages[sdio->head];
}
+static void dio_pin_page(struct dio *dio, struct page *page)
+{
+ if (dio->is_pinned)
+ folio_add_pin(page_folio(page));
+}
+
+static void dio_unpin_page(struct dio *dio, struct page *page)
+{
+ if (dio->is_pinned)
+ unpin_user_page(page);
+}
+
/*
* dio_complete() - called when all DIO BIO I/O has been completed
*
@@ -402,6 +414,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
bio->bi_end_io = dio_bio_end_aio;
else
bio->bi_end_io = dio_bio_end_io;
+ if (dio->is_pinned)
+ bio_set_flag(bio, BIO_PAGE_PINNED);
sdio->bio = bio;
sdio->logical_offset_in_bio = sdio->cur_page_fs_offset;
}
@@ -442,8 +456,10 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
*/
static inline void dio_cleanup(struct dio *dio, struct dio_submit *sdio)
{
- while (sdio->head < sdio->tail)
- put_page(dio->pages[sdio->head++]);
+ if (dio->is_pinned)
+ unpin_user_pages(dio->pages + sdio->head,
+ sdio->tail - sdio->head);
+ sdio->head = sdio->tail;
}
/*
@@ -674,7 +690,7 @@ out:
*
* Return zero on success. Non-zero means the caller needs to start a new BIO.
*/
-static inline int dio_bio_add_page(struct dio_submit *sdio)
+static inline int dio_bio_add_page(struct dio *dio, struct dio_submit *sdio)
{
int ret;
@@ -686,7 +702,7 @@ static inline int dio_bio_add_page(struct dio_submit *sdio)
*/
if ((sdio->cur_page_len + sdio->cur_page_offset) == PAGE_SIZE)
sdio->pages_in_io--;
- get_page(sdio->cur_page);
+ dio_pin_page(dio, sdio->cur_page);
sdio->final_block_in_bio = sdio->cur_page_block +
(sdio->cur_page_len >> sdio->blkbits);
ret = 0;
@@ -741,11 +757,11 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio,
goto out;
}
- if (dio_bio_add_page(sdio) != 0) {
+ if (dio_bio_add_page(dio, sdio) != 0) {
dio_bio_submit(dio, sdio);
ret = dio_new_bio(dio, sdio, sdio->cur_page_block, map_bh);
if (ret == 0) {
- ret = dio_bio_add_page(sdio);
+ ret = dio_bio_add_page(dio, sdio);
BUG_ON(ret != 0);
}
}
@@ -802,13 +818,13 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page,
*/
if (sdio->cur_page) {
ret = dio_send_cur_page(dio, sdio, map_bh);
- put_page(sdio->cur_page);
+ dio_unpin_page(dio, sdio->cur_page);
sdio->cur_page = NULL;
if (ret)
return ret;
}
- get_page(page); /* It is in dio */
+ dio_pin_page(dio, page); /* It is in dio */
sdio->cur_page = page;
sdio->cur_page_offset = offset;
sdio->cur_page_len = len;
@@ -823,7 +839,7 @@ out:
ret = dio_send_cur_page(dio, sdio, map_bh);
if (sdio->bio)
dio_bio_submit(dio, sdio);
- put_page(sdio->cur_page);
+ dio_unpin_page(dio, sdio->cur_page);
sdio->cur_page = NULL;
}
return ret;
@@ -924,7 +940,7 @@ static int do_direct_IO(struct dio *dio, struct dio_submit *sdio,
ret = get_more_blocks(dio, sdio, map_bh);
if (ret) {
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
if (!buffer_mapped(map_bh))
@@ -969,7 +985,7 @@ do_holes:
/* AKPM: eargh, -ENOTBLK is a hack */
if (dio_op == REQ_OP_WRITE) {
- put_page(page);
+ dio_unpin_page(dio, page);
return -ENOTBLK;
}
@@ -982,7 +998,7 @@ do_holes:
if (sdio->block_in_file >=
i_size_aligned >> blkbits) {
/* We hit eof */
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
zero_user(page, from, 1 << blkbits);
@@ -1022,7 +1038,7 @@ do_holes:
sdio->next_block_for_io,
map_bh);
if (ret) {
- put_page(page);
+ dio_unpin_page(dio, page);
goto out;
}
sdio->next_block_for_io += this_chunk_blocks;
@@ -1037,8 +1053,8 @@ next_block:
break;
}
- /* Drop the ref which was taken in get_user_pages() */
- put_page(page);
+ /* Drop the pin which was taken in get_user_pages() */
+ dio_unpin_page(dio, page);
}
out:
return ret;
@@ -1133,6 +1149,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
/* will be released by direct_io_worker */
inode_lock(inode);
}
+ dio->is_pinned = iov_iter_extract_will_pin(iter);
/* Once we sampled i_size check for reads beyond EOF */
dio->i_size = i_size_read(inode);
@@ -1257,7 +1274,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
ret2 = dio_send_cur_page(dio, &sdio, &map_bh);
if (retval == 0)
retval = ret2;
- put_page(sdio.cur_page);
+ dio_unpin_page(dio, sdio.cur_page);
sdio.cur_page = NULL;
}
if (sdio.bio)
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index ff18f6b14de5..9d6a3c6158bd 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -19,6 +19,7 @@
#include <trace/events/erofs.h>
static struct kmem_cache *erofs_inode_cachep __read_mostly;
+struct file_system_type erofs_fs_type;
void _erofs_err(struct super_block *sb, const char *function,
const char *fmt, ...)
@@ -253,8 +254,8 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb,
return PTR_ERR(fscache);
dif->fscache = fscache;
} else if (!sbi->devs->flatdev) {
- bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL,
- sb->s_type);
+ bdev = blkdev_get_by_path(dif->path, BLK_OPEN_READ, sb->s_type,
+ NULL);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
dif->bdev = bdev;
@@ -815,7 +816,7 @@ static int erofs_release_device_info(int id, void *ptr, void *data)
fs_put_dax(dif->dax_dev, NULL);
if (dif->bdev)
- blkdev_put(dif->bdev, FMODE_READ | FMODE_EXCL);
+ blkdev_put(dif->bdev, &erofs_fs_type);
erofs_fscache_unregister_cookie(dif->fscache);
dif->fscache = NULL;
kfree(dif->path);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8104a21b001a..02fa8a64dc3f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2968,6 +2968,7 @@ int ext4_fileattr_set(struct mnt_idmap *idmap,
int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
extern void ext4_reset_inode_seed(struct inode *inode);
int ext4_update_overhead(struct super_block *sb, bool force);
+int ext4_force_shutdown(struct super_block *sb, u32 flags);
/* migrate.c */
extern int ext4_ext_migrate(struct inode *);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index f9a430152063..961284cc9b65 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -793,16 +793,9 @@ static int ext4_ioctl_setproject(struct inode *inode, __u32 projid)
}
#endif
-static int ext4_shutdown(struct super_block *sb, unsigned long arg)
+int ext4_force_shutdown(struct super_block *sb, u32 flags)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- __u32 flags;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (get_user(flags, (__u32 __user *)arg))
- return -EFAULT;
if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
return -EINVAL;
@@ -838,6 +831,19 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
return 0;
}
+static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg)
+{
+ u32 flags;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(flags, (__u32 __user *)arg))
+ return -EFAULT;
+
+ return ext4_force_shutdown(sb, flags);
+}
+
struct getfsmap_info {
struct super_block *gi_sb;
struct fsmap_head __user *gi_data;
@@ -1566,7 +1572,7 @@ resizefs_out:
return ext4_ioctl_get_es_cache(filp, arg);
case EXT4_IOC_SHUTDOWN:
- return ext4_shutdown(sb, arg);
+ return ext4_ioctl_shutdown(sb, arg);
case FS_IOC_ENABLE_VERITY:
if (!ext4_has_feature_verity(sb))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 05fcecc36244..eaa5858d5285 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1096,6 +1096,15 @@ void ext4_update_dynamic_rev(struct super_block *sb)
*/
}
+static void ext4_bdev_mark_dead(struct block_device *bdev)
+{
+ ext4_force_shutdown(bdev->bd_holder, EXT4_GOING_FLAGS_NOLOGFLUSH);
+}
+
+static const struct blk_holder_ops ext4_holder_ops = {
+ .mark_dead = ext4_bdev_mark_dead,
+};
+
/*
* Open the external journal device
*/
@@ -1103,7 +1112,8 @@ static struct block_device *ext4_blkdev_get(dev_t dev, struct super_block *sb)
{
struct block_device *bdev;
- bdev = blkdev_get_by_dev(dev, FMODE_READ|FMODE_WRITE|FMODE_EXCL, sb);
+ bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, sb,
+ &ext4_holder_ops);
if (IS_ERR(bdev))
goto fail;
return bdev;
@@ -1118,17 +1128,12 @@ fail:
/*
* Release the journal device
*/
-static void ext4_blkdev_put(struct block_device *bdev)
-{
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
-}
-
static void ext4_blkdev_remove(struct ext4_sb_info *sbi)
{
struct block_device *bdev;
bdev = sbi->s_journal_bdev;
if (bdev) {
- ext4_blkdev_put(bdev);
+ blkdev_put(bdev, sbi->s_sb);
sbi->s_journal_bdev = NULL;
}
}
@@ -1449,6 +1454,11 @@ static void ext4_destroy_inode(struct inode *inode)
EXT4_I(inode)->i_reserved_data_blocks);
}
+static void ext4_shutdown(struct super_block *sb)
+{
+ ext4_force_shutdown(sb, EXT4_GOING_FLAGS_NOLOGFLUSH);
+}
+
static void init_once(void *foo)
{
struct ext4_inode_info *ei = foo;
@@ -1609,6 +1619,7 @@ static const struct super_operations ext4_sops = {
.unfreeze_fs = ext4_unfreeze,
.statfs = ext4_statfs,
.show_options = ext4_show_options,
+ .shutdown = ext4_shutdown,
#ifdef CONFIG_QUOTA
.quota_read = ext4_quota_read,
.quota_write = ext4_quota_write,
@@ -5899,7 +5910,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
- ext4_blkdev_put(bdev);
+ blkdev_put(bdev, sb);
return NULL;
}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 9f15b03037db..e34197a70dc1 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1538,7 +1538,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
int i;
for (i = 0; i < sbi->s_ndevs; i++) {
- blkdev_put(FDEV(i).bdev, FMODE_EXCL);
+ blkdev_put(FDEV(i).bdev, sbi->sb->s_type);
#ifdef CONFIG_BLK_DEV_ZONED
kvfree(FDEV(i).blkz_seq);
#endif
@@ -3993,6 +3993,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
unsigned int max_devices = MAX_DEVICES;
unsigned int logical_blksize;
+ blk_mode_t mode = sb_open_mode(sbi->sb->s_flags);
int i;
/* Initialize single device information */
@@ -4024,8 +4025,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
if (max_devices == 1) {
/* Single zoned block device mount */
FDEV(0).bdev =
- blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev,
- sbi->sb->s_mode, sbi->sb->s_type);
+ blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev, mode,
+ sbi->sb->s_type, NULL);
} else {
/* Multi-device mount */
memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
@@ -4043,8 +4044,9 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
(FDEV(i).total_segments <<
sbi->log_blocks_per_seg) - 1;
}
- FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
- sbi->sb->s_mode, sbi->sb->s_type);
+ FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path, mode,
+ sbi->sb->s_type,
+ NULL);
}
if (IS_ERR(FDEV(i).bdev))
return PTR_ERR(FDEV(i).bdev);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 9af9ddb61ca0..cd962985b058 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -254,7 +254,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
bio = bio_alloc(sb->s_bdev, 1, REQ_OP_READ | REQ_META, GFP_NOFS);
bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9);
- bio_add_page(bio, page, PAGE_SIZE, 0);
+ __bio_add_page(bio, page, PAGE_SIZE, 0);
bio->bi_end_io = end_bio_io_page;
bio->bi_private = page;
diff --git a/fs/inode.c b/fs/inode.c
index 53ae3b76d232..d37fad91c8da 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -2306,7 +2306,8 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
inode->i_fop = &def_chr_fops;
inode->i_rdev = rdev;
} else if (S_ISBLK(mode)) {
- inode->i_fop = &def_blk_fops;
+ if (IS_ENABLED(CONFIG_BLOCK))
+ inode->i_fop = &def_blk_fops;
inode->i_rdev = rdev;
} else if (S_ISFIFO(mode))
inode->i_fop = &pipefifo_fops;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 063133ec77f4..0edab9deae2a 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -312,7 +312,7 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
ctx->bio->bi_opf |= REQ_RAHEAD;
ctx->bio->bi_iter.bi_sector = sector;
ctx->bio->bi_end_io = iomap_read_end_io;
- bio_add_folio(ctx->bio, folio, plen, poff);
+ bio_add_folio_nofail(ctx->bio, folio, plen, poff);
}
done:
@@ -539,7 +539,7 @@ static int iomap_read_folio_sync(loff_t block_start, struct folio *folio,
bio_init(&bio, iomap->bdev, &bvec, 1, REQ_OP_READ);
bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
- bio_add_folio(&bio, folio, plen, poff);
+ bio_add_folio_nofail(&bio, folio, plen, poff);
return submit_bio_wait(&bio);
}
@@ -1582,7 +1582,7 @@ iomap_add_to_ioend(struct inode *inode, loff_t pos, struct folio *folio,
if (!bio_add_folio(wpc->ioend->io_bio, folio, len, poff)) {
wpc->ioend->io_bio = iomap_chain_bio(wpc->ioend->io_bio);
- bio_add_folio(wpc->ioend->io_bio, folio, len, poff);
+ bio_add_folio_nofail(wpc->ioend->io_bio, folio, len, poff);
}
if (iop)
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index 019cc87d0fb3..08873f0627dd 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -203,7 +203,6 @@ static void iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
- get_page(page);
__bio_add_page(bio, page, len, 0);
iomap_dio_submit_bio(iter, dio, bio, pos);
}
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 695415cbfe98..e855b8fde76c 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1100,8 +1100,8 @@ int lmLogOpen(struct super_block *sb)
* file systems to log may have n-to-1 relationship;
*/
- bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
- log);
+ bdev = blkdev_get_by_dev(sbi->logdev, BLK_OPEN_READ | BLK_OPEN_WRITE,
+ log, NULL);
if (IS_ERR(bdev)) {
rc = PTR_ERR(bdev);
goto free;
@@ -1141,7 +1141,7 @@ journal_found:
lbmLogShutdown(log);
close: /* close external log device */
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, log);
free: /* free log descriptor */
mutex_unlock(&jfs_log_mutex);
@@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb)
bdev = log->bdev;
rc = lmLogShutdown(log);
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, log);
kfree(log);
@@ -1974,7 +1974,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
bio = bio_alloc(log->bdev, 1, REQ_OP_READ, GFP_NOFS);
bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
- bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+ __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
bio->bi_end_io = lbmIODone;
@@ -2115,7 +2115,7 @@ static void lbmStartIO(struct lbuf * bp)
bio = bio_alloc(log->bdev, 1, REQ_OP_WRITE | REQ_SYNC, GFP_NOFS);
bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
- bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
+ __bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
bio->bi_end_io = lbmIODone;
diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c
index fea5f8821da5..70f5563a8e81 100644
--- a/fs/nfs/blocklayout/dev.c
+++ b/fs/nfs/blocklayout/dev.c
@@ -35,7 +35,7 @@ bl_free_device(struct pnfs_block_dev *dev)
}
if (dev->bdev)
- blkdev_put(dev->bdev, FMODE_READ | FMODE_WRITE);
+ blkdev_put(dev->bdev, NULL);
}
}
@@ -243,7 +243,8 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d,
if (!dev)
return -EIO;
- bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_WRITE, NULL);
+ bdev = blkdev_get_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL,
+ NULL);
if (IS_ERR(bdev)) {
printk(KERN_WARNING "pNFS: failed to open device %d:%d (%ld)\n",
MAJOR(dev), MINOR(dev), PTR_ERR(bdev));
@@ -312,7 +313,8 @@ bl_open_path(struct pnfs_block_volume *v, const char *prefix)
if (!devname)
return ERR_PTR(-ENOMEM);
- bdev = blkdev_get_by_path(devname, FMODE_READ | FMODE_WRITE, NULL);
+ bdev = blkdev_get_by_path(devname, BLK_OPEN_READ | BLK_OPEN_WRITE, NULL,
+ NULL);
if (IS_ERR(bdev)) {
pr_warn("pNFS: failed to open device %s (%ld)\n",
devname, PTR_ERR(bdev));
@@ -373,7 +375,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d,
return 0;
out_blkdev_put:
- blkdev_put(d->bdev, FMODE_READ | FMODE_WRITE);
+ blkdev_put(d->bdev, NULL);
return error;
}
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 9ba4933087af..0ef8c71bde8e 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1299,14 +1299,11 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
{
struct nilfs_super_data sd;
struct super_block *s;
- fmode_t mode = FMODE_READ | FMODE_EXCL;
struct dentry *root_dentry;
int err, s_new = false;
- if (!(flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
- sd.bdev = blkdev_get_by_path(dev_name, mode, fs_type);
+ sd.bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type,
+ NULL);
if (IS_ERR(sd.bdev))
return ERR_CAST(sd.bdev);
@@ -1340,7 +1337,6 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
s_new = true;
/* New superblock instance created */
- s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", sd.bdev);
sb_set_blocksize(s, block_size(sd.bdev));
@@ -1378,7 +1374,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
}
if (!s_new)
- blkdev_put(sd.bdev, mode);
+ blkdev_put(sd.bdev, fs_type);
return root_dentry;
@@ -1387,7 +1383,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
failed:
if (!s_new)
- blkdev_put(sd.bdev, mode);
+ blkdev_put(sd.bdev, fs_type);
return ERR_PTR(err);
}
diff --git a/fs/no-block.c b/fs/no-block.c
deleted file mode 100644
index 481c0f0ab4bd..000000000000
--- a/fs/no-block.c
+++ /dev/null
@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/* no-block.c: implementation of routines required for non-BLOCK configuration
- *
- * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- */
-
-#include <linux/kernel.h>
-#include <linux/fs.h>
-
-static int no_blkdev_open(struct inode * inode, struct file * filp)
-{
- return -ENODEV;
-}
-
-const struct file_operations def_blk_fops = {
- .open = no_blkdev_open,
- .llseek = noop_llseek,
-};
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 60b97c92e2b2..21472e3ed182 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1503,7 +1503,7 @@ static void o2hb_region_release(struct config_item *item)
}
if (reg->hr_bdev)
- blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
+ blkdev_put(reg->hr_bdev, NULL);
kfree(reg->hr_slots);
@@ -1786,7 +1786,8 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
goto out2;
reg->hr_bdev = blkdev_get_by_dev(f.file->f_mapping->host->i_rdev,
- FMODE_WRITE | FMODE_READ, NULL);
+ BLK_OPEN_WRITE | BLK_OPEN_READ, NULL,
+ NULL);
if (IS_ERR(reg->hr_bdev)) {
ret = PTR_ERR(reg->hr_bdev);
reg->hr_bdev = NULL;
@@ -1893,7 +1894,7 @@ static ssize_t o2hb_region_dev_store(struct config_item *item,
out3:
if (ret < 0) {
- blkdev_put(reg->hr_bdev, FMODE_READ | FMODE_WRITE);
+ blkdev_put(reg->hr_bdev, NULL);
reg->hr_bdev = NULL;
}
out2:
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
index 4ae0cfcd15f2..de8cf5d75f34 100644
--- a/fs/pstore/blk.c
+++ b/fs/pstore/blk.c
@@ -263,9 +263,9 @@ static __init const char *early_boot_devpath(const char *initial_devname)
* same scheme to find the device that we use for mounting
* the root file system.
*/
- dev_t dev = name_to_dev_t(initial_devname);
+ dev_t dev;
- if (!dev) {
+ if (early_lookup_bdev(initial_devname, &dev)) {
pr_err("failed to resolve '%s'!\n", initial_devname);
return initial_devname;
}
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 4d11d60f493c..479aa4a57602 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2589,7 +2589,12 @@ static void release_journal_dev(struct super_block *super,
struct reiserfs_journal *journal)
{
if (journal->j_dev_bd != NULL) {
- blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
+ void *holder = NULL;
+
+ if (journal->j_dev_bd->bd_dev != super->s_dev)
+ holder = journal;
+
+ blkdev_put(journal->j_dev_bd, holder);
journal->j_dev_bd = NULL;
}
}
@@ -2598,9 +2603,10 @@ static int journal_init_dev(struct super_block *super,
struct reiserfs_journal *journal,
const char *jdev_name)
{
+ blk_mode_t blkdev_mode = BLK_OPEN_READ;
+ void *holder = journal;
int result;
dev_t jdev;
- fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE | FMODE_EXCL;
result = 0;
@@ -2608,16 +2614,15 @@ static int journal_init_dev(struct super_block *super,
jdev = SB_ONDISK_JOURNAL_DEVICE(super) ?
new_decode_dev(SB_ONDISK_JOURNAL_DEVICE(super)) : super->s_dev;
- if (bdev_read_only(super->s_bdev))
- blkdev_mode = FMODE_READ;
+ if (!bdev_read_only(super->s_bdev))
+ blkdev_mode |= BLK_OPEN_WRITE;
/* there is no "jdev" option and journal is on separate device */
if ((!jdev_name || !jdev_name[0])) {
if (jdev == super->s_dev)
- blkdev_mode &= ~FMODE_EXCL;
- journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode,
- journal);
- journal->j_dev_mode = blkdev_mode;
+ holder = NULL;
+ journal->j_dev_bd = blkdev_get_by_dev(jdev, blkdev_mode, holder,
+ NULL);
if (IS_ERR(journal->j_dev_bd)) {
result = PTR_ERR(journal->j_dev_bd);
journal->j_dev_bd = NULL;
@@ -2631,8 +2636,8 @@ static int journal_init_dev(struct super_block *super,
return 0;
}
- journal->j_dev_mode = blkdev_mode;
- journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, journal);
+ journal->j_dev_bd = blkdev_get_by_path(jdev_name, blkdev_mode, holder,
+ NULL);
if (IS_ERR(journal->j_dev_bd)) {
result = PTR_ERR(journal->j_dev_bd);
journal->j_dev_bd = NULL;
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 1bccf6a2e908..55e85256aae8 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -300,7 +300,6 @@ struct reiserfs_journal {
struct reiserfs_journal_cnode *j_first;
struct block_device *j_dev_bd;
- fmode_t j_dev_mode;
/* first block on s_dev of reserved area journal */
int j_1st_reserved_block;
diff --git a/fs/splice.c b/fs/splice.c
index 2420ead610a7..7a9565d8ec4f 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -368,16 +368,15 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
if (ret > 0) {
keep = DIV_ROUND_UP(ret, PAGE_SIZE);
*ppos = kiocb.ki_pos;
- file_accessed(in);
- } else if (ret < 0) {
- /*
- * callers of ->splice_read() expect -EAGAIN on
- * "can't put anything in there", rather than -EFAULT.
- */
- if (ret == -EFAULT)
- ret = -EAGAIN;
}
+ /*
+ * Callers of ->splice_read() expect -EAGAIN on "can't put anything in
+ * there", rather than -EFAULT.
+ */
+ if (ret == -EFAULT)
+ ret = -EAGAIN;
+
/* Free any pages that didn't get touched at all. */
if (keep < npages)
release_pages(pages + keep, npages - keep);
diff --git a/fs/super.c b/fs/super.c
index 48c29954d487..05ff6abddd3c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1210,6 +1210,22 @@ int get_tree_keyed(struct fs_context *fc,
EXPORT_SYMBOL(get_tree_keyed);
#ifdef CONFIG_BLOCK
+static void fs_mark_dead(struct block_device *bdev)
+{
+ struct super_block *sb;
+
+ sb = get_super(bdev);
+ if (!sb)
+ return;
+
+ if (sb->s_op->shutdown)
+ sb->s_op->shutdown(sb);
+ drop_super(sb);
+}
+
+static const struct blk_holder_ops fs_holder_ops = {
+ .mark_dead = fs_mark_dead,
+};
static int set_bdev_super(struct super_block *s, void *data)
{
@@ -1243,16 +1259,13 @@ int get_tree_bdev(struct fs_context *fc,
{
struct block_device *bdev;
struct super_block *s;
- fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
- if (!(fc->sb_flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
if (!fc->source)
return invalf(fc, "No source specified");
- bdev = blkdev_get_by_path(fc->source, mode, fc->fs_type);
+ bdev = blkdev_get_by_path(fc->source, sb_open_mode(fc->sb_flags),
+ fc->fs_type, &fs_holder_ops);
if (IS_ERR(bdev)) {
errorf(fc, "%s: Can't open blockdev", fc->source);
return PTR_ERR(bdev);
@@ -1266,7 +1279,7 @@ int get_tree_bdev(struct fs_context *fc,
if (bdev->bd_fsfreeze_count > 0) {
mutex_unlock(&bdev->bd_fsfreeze_mutex);
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return -EBUSY;
}
@@ -1275,7 +1288,7 @@ int get_tree_bdev(struct fs_context *fc,
s = sget_fc(fc, test_bdev_super_fc, set_bdev_super_fc);
mutex_unlock(&bdev->bd_fsfreeze_mutex);
if (IS_ERR(s)) {
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return PTR_ERR(s);
}
@@ -1284,7 +1297,7 @@ int get_tree_bdev(struct fs_context *fc,
if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
warnf(fc, "%pg: Can't mount, would change RO state", bdev);
deactivate_locked_super(s);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
return -EBUSY;
}
@@ -1296,10 +1309,9 @@ int get_tree_bdev(struct fs_context *fc,
* holding an active reference.
*/
up_write(&s->s_umount);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fc->fs_type);
down_write(&s->s_umount);
} else {
- s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
fc->fs_type->name, s->s_id);
@@ -1331,13 +1343,10 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
{
struct block_device *bdev;
struct super_block *s;
- fmode_t mode = FMODE_READ | FMODE_EXCL;
int error = 0;
- if (!(flags & SB_RDONLY))
- mode |= FMODE_WRITE;
-
- bdev = blkdev_get_by_path(dev_name, mode, fs_type);
+ bdev = blkdev_get_by_path(dev_name, sb_open_mode(flags), fs_type,
+ &fs_holder_ops);
if (IS_ERR(bdev))
return ERR_CAST(bdev);
@@ -1373,10 +1382,9 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
* holding an active reference.
*/
up_write(&s->s_umount);
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fs_type);
down_write(&s->s_umount);
} else {
- s->s_mode = mode;
snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s",
fs_type->name, s->s_id);
@@ -1396,7 +1404,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
error_s:
error = PTR_ERR(s);
error_bdev:
- blkdev_put(bdev, mode);
+ blkdev_put(bdev, fs_type);
error:
return ERR_PTR(error);
}
@@ -1405,13 +1413,11 @@ EXPORT_SYMBOL(mount_bdev);
void kill_block_super(struct super_block *sb)
{
struct block_device *bdev = sb->s_bdev;
- fmode_t mode = sb->s_mode;
bdev->bd_super = NULL;
generic_shutdown_super(sb);
sync_blockdev(bdev);
- WARN_ON_ONCE(!(mode & FMODE_EXCL));
- blkdev_put(bdev, mode | FMODE_EXCL);
+ blkdev_put(bdev, sb->s_type);
}
EXPORT_SYMBOL(kill_block_super);
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 13851c0d640b..9ebb8333a308 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -534,6 +534,9 @@ xfs_do_force_shutdown(
} else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
tag = XFS_PTAG_SHUTDOWN_CORRUPT;
why = "Corruption of on-disk metadata";
+ } else if (flags & SHUTDOWN_DEVICE_REMOVED) {
+ tag = XFS_PTAG_SHUTDOWN_IOERROR;
+ why = "Block device removal";
} else {
tag = XFS_PTAG_SHUTDOWN_IOERROR;
why = "Metadata I/O Error";
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 6c09f89534d3..e2866e7fa60c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -458,12 +458,14 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, uint32_t flags, char *fname,
#define SHUTDOWN_FORCE_UMOUNT (1u << 2) /* shutdown from a forced unmount */
#define SHUTDOWN_CORRUPT_INCORE (1u << 3) /* corrupt in-memory structures */
#define SHUTDOWN_CORRUPT_ONDISK (1u << 4) /* corrupt metadata on device */
+#define SHUTDOWN_DEVICE_REMOVED (1u << 5) /* device removed underneath us */
#define XFS_SHUTDOWN_STRINGS \
{ SHUTDOWN_META_IO_ERROR, "metadata_io" }, \
{ SHUTDOWN_LOG_IO_ERROR, "log_io" }, \
{ SHUTDOWN_FORCE_UMOUNT, "force_umount" }, \
- { SHUTDOWN_CORRUPT_INCORE, "corruption" }
+ { SHUTDOWN_CORRUPT_INCORE, "corruption" }, \
+ { SHUTDOWN_DEVICE_REMOVED, "device_removed" }
/*
* Flags for xfs_mountfs
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 4120bd1cba90..d910b141d52e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -377,6 +377,17 @@ disable_dax:
return 0;
}
+static void
+xfs_bdev_mark_dead(
+ struct block_device *bdev)
+{
+ xfs_force_shutdown(bdev->bd_holder, SHUTDOWN_DEVICE_REMOVED);
+}
+
+static const struct blk_holder_ops xfs_holder_ops = {
+ .mark_dead = xfs_bdev_mark_dead,
+};
+
STATIC int
xfs_blkdev_get(
xfs_mount_t *mp,
@@ -385,8 +396,8 @@ xfs_blkdev_get(
{
int error = 0;
- *bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
- mp);
+ *bdevp = blkdev_get_by_path(name, BLK_OPEN_READ | BLK_OPEN_WRITE, mp,
+ &xfs_holder_ops);
if (IS_ERR(*bdevp)) {
error = PTR_ERR(*bdevp);
xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
@@ -397,10 +408,11 @@ xfs_blkdev_get(
STATIC void
xfs_blkdev_put(
+ struct xfs_mount *mp,
struct block_device *bdev)
{
if (bdev)
- blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
+ blkdev_put(bdev, mp);
}
STATIC void
@@ -411,13 +423,13 @@ xfs_close_devices(
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
xfs_free_buftarg(mp->m_logdev_targp);
- xfs_blkdev_put(logdev);
+ xfs_blkdev_put(mp, logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
xfs_free_buftarg(mp->m_rtdev_targp);
- xfs_blkdev_put(rtdev);
+ xfs_blkdev_put(mp, rtdev);
}
xfs_free_buftarg(mp->m_ddev_targp);
}
@@ -492,10 +504,10 @@ xfs_open_devices(
out_free_ddev_targ:
xfs_free_buftarg(mp->m_ddev_targp);
out_close_rtdev:
- xfs_blkdev_put(rtdev);
+ xfs_blkdev_put(mp, rtdev);
out_close_logdev:
if (logdev && logdev != ddev)
- xfs_blkdev_put(logdev);
+ xfs_blkdev_put(mp, logdev);
return error;
}
@@ -1160,6 +1172,13 @@ xfs_fs_free_cached_objects(
return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
}
+static void
+xfs_fs_shutdown(
+ struct super_block *sb)
+{
+ xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED);
+}
+
static const struct super_operations xfs_super_operations = {
.alloc_inode = xfs_fs_alloc_inode,
.destroy_inode = xfs_fs_destroy_inode,
@@ -1173,6 +1192,7 @@ static const struct super_operations xfs_super_operations = {
.show_options = xfs_fs_show_options,
.nr_cached_objects = xfs_fs_nr_cached_objects,
.free_cached_objects = xfs_fs_free_cached_objects,
+ .shutdown = xfs_fs_shutdown,
};
static int
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 56c00111966a..bbe44a26a8e5 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -1128,7 +1128,7 @@ static int zonefs_read_super(struct super_block *sb)
bio_init(&bio, sb->s_bdev, &bio_vec, 1, REQ_OP_READ);
bio.bi_iter.bi_sector = 0;
- bio_add_page(&bio, page, PAGE_SIZE, 0);
+ __bio_add_page(&bio, page, PAGE_SIZE, 0);
ret = submit_bio_wait(&bio);
if (ret)