summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-09-07 11:59:42 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-07 11:59:42 -0700
commita0725ab0c7536076d5477264420ef420ebb64501 (patch)
tree5c972d46c7f58f634ad74c6e4bc7a2bee24e5956 /fs
parent3ee31b89d9b12c01aa03dda7a923ef07a800eedd (diff)
parentef13ecbc134d7e0ca4ab4834d08bd20885b53c62 (diff)
Merge branch 'for-4.14/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe: "This is the first pull request for 4.14, containing most of the code changes. It's a quiet series this round, which I think we needed after the churn of the last few series. This contains: - Fix for a registration race in loop, from Anton Volkov. - Overflow complaint fix from Arnd for DAC960. - Series of drbd changes from the usual suspects. - Conversion of the stec/skd driver to blk-mq. From Bart. - A few BFQ improvements/fixes from Paolo. - CFQ improvement from Ritesh, allowing idling for group idle. - A few fixes found by Dan's smatch, courtesy of Dan. - A warning fixup for a race between changing the IO scheduler and device remova. From David Jeffery. - A few nbd fixes from Josef. - Support for cgroup info in blktrace, from Shaohua. - Also from Shaohua, new features in the null_blk driver to allow it to actually hold data, among other things. - Various corner cases and error handling fixes from Weiping Zhang. - Improvements to the IO stats tracking for blk-mq from me. Can drastically improve performance for fast devices and/or big machines. - Series from Christoph removing bi_bdev as being needed for IO submission, in preparation for nvme multipathing code. - Series from Bart, including various cleanups and fixes for switch fall through case complaints" * 'for-4.14/block' of git://git.kernel.dk/linux-block: (162 commits) kernfs: checking for IS_ERR() instead of NULL drbd: remove BIOSET_NEED_RESCUER flag from drbd_{md_,}io_bio_set drbd: Fix allyesconfig build, fix recent commit drbd: switch from kmalloc() to kmalloc_array() drbd: abort drbd_start_resync if there is no connection drbd: move global variables to drbd namespace and make some static drbd: rename "usermode_helper" to "drbd_usermode_helper" drbd: fix race between handshake and admin disconnect/down drbd: fix potential deadlock when trying to detach during handshake drbd: A single dot should be put into a sequence. drbd: fix rmmod cleanup, remove _all_ debugfs entries drbd: Use setup_timer() instead of init_timer() to simplify the code. drbd: fix potential get_ldev/put_ldev refcount imbalance during attach drbd: new disk-option disable-write-same drbd: Fix resource role for newly created resources in events2 drbd: mark symbols static where possible drbd: Send P_NEG_ACK upon write error in protocol != C drbd: add explicit plugging when submitting batches drbd: change list_for_each_safe to while(list_first_entry_or_null) drbd: introduce drbd_recv_header_maybe_unplug ...
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c5
-rw-r--r--fs/btrfs/check-integrity.c41
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/extent_io.c6
-rw-r--r--fs/btrfs/raid56.c8
-rw-r--r--fs/btrfs/scrub.c12
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/buffer.c4
-rw-r--r--fs/crypto/bio.c2
-rw-r--r--fs/direct-io.c8
-rw-r--r--fs/exofs/ore.c2
-rw-r--r--fs/ext4/page-io.c4
-rw-r--r--fs/ext4/readpage.c2
-rw-r--r--fs/f2fs/data.c5
-rw-r--r--fs/f2fs/segment.c2
-rw-r--r--fs/gfs2/lops.c2
-rw-r--r--fs/gfs2/meta_io.c2
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/iomap.c4
-rw-r--r--fs/jfs/jfs_logmgr.c4
-rw-r--r--fs/jfs/jfs_metapage.c4
-rw-r--r--fs/kernfs/dir.c111
-rw-r--r--fs/kernfs/file.c10
-rw-r--r--fs/kernfs/inode.c9
-rw-r--r--fs/kernfs/kernfs-internal.h9
-rw-r--r--fs/kernfs/mount.c94
-rw-r--r--fs/kernfs/symlink.c6
-rw-r--r--fs/mpage.c2
-rw-r--r--fs/nfs/blocklayout/blocklayout.c2
-rw-r--r--fs/nilfs2/segbuf.c2
-rw-r--r--fs/ocfs2/cluster/heartbeat.c2
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_buf.c2
34 files changed, 265 insertions, 111 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 9941dc8342df..bb715b2fcfb8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -223,7 +223,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
}
bio_init(&bio, vecs, nr_pages);
- bio.bi_bdev = bdev;
+ bio_set_dev(&bio, bdev);
bio.bi_iter.bi_sector = pos >> 9;
bio.bi_write_hint = iocb->ki_hint;
bio.bi_private = current;
@@ -362,7 +362,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
blk_start_plug(&plug);
for (;;) {
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = pos >> 9;
bio->bi_write_hint = iocb->ki_hint;
bio->bi_private = dio;
@@ -1451,6 +1451,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
bdev->bd_disk = disk;
bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
+ bdev->bd_partno = partno;
if (!partno) {
ret = -ENXIO;
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 11d37c94ce05..fb07e3c22b9a 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -296,8 +296,7 @@ static void btrfsic_dev_state_hashtable_add(
struct btrfsic_dev_state *ds,
struct btrfsic_dev_state_hashtable *h);
static void btrfsic_dev_state_hashtable_remove(struct btrfsic_dev_state *ds);
-static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(
- struct block_device *bdev,
+static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev,
struct btrfsic_dev_state_hashtable *h);
static struct btrfsic_stack_frame *btrfsic_stack_frame_alloc(void);
static void btrfsic_stack_frame_free(struct btrfsic_stack_frame *sf);
@@ -385,8 +384,7 @@ static int btrfsic_process_superblock_dev_mirror(
int superblock_mirror_num,
struct btrfsic_dev_state **selected_dev_state,
struct btrfs_super_block *selected_super);
-static struct btrfsic_dev_state *btrfsic_dev_state_lookup(
- struct block_device *bdev);
+static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev);
static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state,
u64 bytenr,
struct btrfsic_dev_state *dev_state,
@@ -626,17 +624,15 @@ static void btrfsic_dev_state_hashtable_remove(struct btrfsic_dev_state *ds)
list_del(&ds->collision_resolving_node);
}
-static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(
- struct block_device *bdev,
+static struct btrfsic_dev_state *btrfsic_dev_state_hashtable_lookup(dev_t dev,
struct btrfsic_dev_state_hashtable *h)
{
const unsigned int hashval =
- (((unsigned int)((uintptr_t)bdev)) &
- (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1));
+ dev & (BTRFSIC_DEV2STATE_HASHTABLE_SIZE - 1);
struct btrfsic_dev_state *ds;
list_for_each_entry(ds, h->table + hashval, collision_resolving_node) {
- if (ds->bdev == bdev)
+ if (ds->bdev->bd_dev == dev)
return ds;
}
@@ -668,7 +664,7 @@ static int btrfsic_process_superblock(struct btrfsic_state *state,
if (!device->bdev || !device->name)
continue;
- dev_state = btrfsic_dev_state_lookup(device->bdev);
+ dev_state = btrfsic_dev_state_lookup(device->bdev->bd_dev);
BUG_ON(NULL == dev_state);
for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
ret = btrfsic_process_superblock_dev_mirror(
@@ -1556,7 +1552,7 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
}
device = multi->stripes[0].dev;
- block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev);
+ block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev->bd_dev);
block_ctx_out->dev_bytenr = multi->stripes[0].physical;
block_ctx_out->start = bytenr;
block_ctx_out->len = len;
@@ -1639,7 +1635,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
unsigned int j;
bio = btrfs_io_bio_alloc(num_pages - i);
- bio->bi_bdev = block_ctx->dev->bdev;
+ bio_set_dev(bio, block_ctx->dev->bdev);
bio->bi_iter.bi_sector = dev_bytenr >> 9;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
@@ -2654,7 +2650,7 @@ static struct btrfsic_block *btrfsic_block_lookup_or_add(
pr_info("btrfsic: error, kmalloc failed!\n");
return NULL;
}
- dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev);
+ dev_state = btrfsic_dev_state_lookup(block_ctx->dev->bdev->bd_dev);
if (NULL == dev_state) {
pr_info("btrfsic: error, lookup dev_state failed!\n");
btrfsic_block_free(block);
@@ -2734,10 +2730,9 @@ static void btrfsic_cmp_log_and_dev_bytenr(struct btrfsic_state *state,
}
}
-static struct btrfsic_dev_state *btrfsic_dev_state_lookup(
- struct block_device *bdev)
+static struct btrfsic_dev_state *btrfsic_dev_state_lookup(dev_t dev)
{
- return btrfsic_dev_state_hashtable_lookup(bdev,
+ return btrfsic_dev_state_hashtable_lookup(dev,
&btrfsic_dev_state_hashtable);
}
@@ -2751,7 +2746,7 @@ int btrfsic_submit_bh(int op, int op_flags, struct buffer_head *bh)
mutex_lock(&btrfsic_mutex);
/* since btrfsic_submit_bh() might also be called before
* btrfsic_mount(), this might return NULL */
- dev_state = btrfsic_dev_state_lookup(bh->b_bdev);
+ dev_state = btrfsic_dev_state_lookup(bh->b_bdev->bd_dev);
/* Only called to write the superblock (incl. FLUSH/FUA) */
if (NULL != dev_state &&
@@ -2808,7 +2803,7 @@ static void __btrfsic_submit_bio(struct bio *bio)
mutex_lock(&btrfsic_mutex);
/* since btrfsic_submit_bio() is also called before
* btrfsic_mount(), this might return NULL */
- dev_state = btrfsic_dev_state_lookup(bio->bi_bdev);
+ dev_state = btrfsic_dev_state_lookup(bio_dev(bio));
if (NULL != dev_state &&
(bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
unsigned int i = 0;
@@ -2824,10 +2819,10 @@ static void __btrfsic_submit_bio(struct bio *bio)
bio_is_patched = 0;
if (dev_state->state->print_mask &
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
- pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
+ pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_disk=%p)\n",
bio_op(bio), bio->bi_opf, segs,
(unsigned long long)bio->bi_iter.bi_sector,
- dev_bytenr, bio->bi_bdev);
+ dev_bytenr, bio->bi_disk);
mapped_datav = kmalloc_array(segs,
sizeof(*mapped_datav), GFP_NOFS);
@@ -2856,8 +2851,8 @@ static void __btrfsic_submit_bio(struct bio *bio)
} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
if (dev_state->state->print_mask &
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
- pr_info("submit_bio(rw=%d,0x%x FLUSH, bdev=%p)\n",
- bio_op(bio), bio->bi_opf, bio->bi_bdev);
+ pr_info("submit_bio(rw=%d,0x%x FLUSH, disk=%p)\n",
+ bio_op(bio), bio->bi_opf, bio->bi_disk);
if (!dev_state->dummy_block_for_bio_bh_flush.is_iodone) {
if ((dev_state->state->print_mask &
(BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH |
@@ -2998,7 +2993,7 @@ void btrfsic_unmount(struct btrfs_fs_devices *fs_devices)
continue;
ds = btrfsic_dev_state_hashtable_lookup(
- device->bdev,
+ device->bdev->bd_dev,
&btrfsic_dev_state_hashtable);
if (NULL != ds) {
state = ds->state;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f45b61fe9a9a..4f428a48d513 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3499,7 +3499,7 @@ static void write_dev_flush(struct btrfs_device *device)
bio_reset(bio);
bio->bi_end_io = btrfs_end_empty_barrier;
- bio->bi_bdev = device->bdev;
+ bio_set_dev(bio, device->bdev);
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
init_completion(&device->flush_wait);
bio->bi_private = &device->flush_wait;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0aff9b278c19..42b12a85ab49 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2033,7 +2033,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
bio_put(bio);
return -EIO;
}
- bio->bi_bdev = dev->bdev;
+ bio_set_dev(bio, dev->bdev);
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
bio_add_page(bio, page, length, pg_offset);
@@ -2335,7 +2335,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
bio = btrfs_io_bio_alloc(1);
bio->bi_end_io = endio_func;
bio->bi_iter.bi_sector = failrec->logical >> 9;
- bio->bi_bdev = fs_info->fs_devices->latest_bdev;
+ bio_set_dev(bio, fs_info->fs_devices->latest_bdev);
bio->bi_iter.bi_size = 0;
bio->bi_private = data;
@@ -2675,7 +2675,7 @@ struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte)
struct bio *bio;
bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset);
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = first_byte >> 9;
btrfs_io_bio_init(btrfs_io_bio(bio));
return bio;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 2cf6ba40f7c4..24a62224b24b 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1090,7 +1090,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
*/
if (last_end == disk_start && stripe->dev->bdev &&
!last->bi_status &&
- last->bi_bdev == stripe->dev->bdev) {
+ last->bi_disk == stripe->dev->bdev->bd_disk &&
+ last->bi_partno == stripe->dev->bdev->bd_partno) {
ret = bio_add_page(last, page, PAGE_SIZE, 0);
if (ret == PAGE_SIZE)
return 0;
@@ -1100,7 +1101,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
/* put a new bio on the list */
bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
bio->bi_iter.bi_size = 0;
- bio->bi_bdev = stripe->dev->bdev;
+ bio_set_dev(bio, stripe->dev->bdev);
bio->bi_iter.bi_sector = disk_start >> 9;
bio_add_page(bio, page, PAGE_SIZE, 0);
@@ -1347,7 +1348,8 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
stripe_start = stripe->physical;
if (physical >= stripe_start &&
physical < stripe_start + rbio->stripe_len &&
- bio->bi_bdev == stripe->dev->bdev) {
+ bio->bi_disk == stripe->dev->bdev->bd_disk &&
+ bio->bi_partno == stripe->dev->bdev->bd_partno) {
return i;
}
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6f1e4c984b94..b0b71e8e4c36 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1738,7 +1738,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
WARN_ON(!page->page);
bio = btrfs_io_bio_alloc(1);
- bio->bi_bdev = page->dev->bdev;
+ bio_set_dev(bio, page->dev->bdev);
bio_add_page(bio, page->page, PAGE_SIZE, 0);
if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) {
@@ -1826,7 +1826,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
}
bio = btrfs_io_bio_alloc(1);
- bio->bi_bdev = page_bad->dev->bdev;
+ bio_set_dev(bio, page_bad->dev->bdev);
bio->bi_iter.bi_sector = page_bad->physical >> 9;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
@@ -1921,7 +1921,7 @@ again:
bio->bi_private = sbio;
bio->bi_end_io = scrub_wr_bio_end_io;
- bio->bi_bdev = sbio->dev->bdev;
+ bio_set_dev(bio, sbio->dev->bdev);
bio->bi_iter.bi_sector = sbio->physical >> 9;
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
sbio->status = 0;
@@ -1964,7 +1964,7 @@ static void scrub_wr_submit(struct scrub_ctx *sctx)
sbio = sctx->wr_curr_bio;
sctx->wr_curr_bio = NULL;
- WARN_ON(!sbio->bio->bi_bdev);
+ WARN_ON(!sbio->bio->bi_disk);
scrub_pending_bio_inc(sctx);
/* process all writes in a single worker thread. Then the block layer
* orders the requests before sending them to the driver which
@@ -2321,7 +2321,7 @@ again:
bio->bi_private = sbio;
bio->bi_end_io = scrub_bio_end_io;
- bio->bi_bdev = sbio->dev->bdev;
+ bio_set_dev(bio, sbio->dev->bdev);
bio->bi_iter.bi_sector = sbio->physical >> 9;
bio_set_op_attrs(bio, REQ_OP_READ, 0);
sbio->status = 0;
@@ -4627,7 +4627,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
bio = btrfs_io_bio_alloc(1);
bio->bi_iter.bi_size = 0;
bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
- bio->bi_bdev = dev->bdev;
+ bio_set_dev(bio, dev->bdev);
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
ret = bio_add_page(bio, page, PAGE_SIZE, 0);
if (ret != PAGE_SIZE) {
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bd679bc7a1a9..002aa318da67 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6188,7 +6188,7 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
rcu_read_unlock();
}
#endif
- bio->bi_bdev = dev->bdev;
+ bio_set_dev(bio, dev->bdev);
btrfs_bio_counter_inc_noblocked(fs_info);
diff --git a/fs/buffer.c b/fs/buffer.c
index 50da0e102ca0..170df856bdb9 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3056,7 +3056,7 @@ void guard_bio_eod(int op, struct bio *bio)
struct bio_vec *bvec = &bio->bi_io_vec[bio->bi_vcnt - 1];
unsigned truncated_bytes;
- maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
+ maxsector = get_capacity(bio->bi_disk);
if (!maxsector)
return;
@@ -3115,7 +3115,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
}
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
+ bio_set_dev(bio, bh->b_bdev);
bio->bi_write_hint = write_hint;
bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
index 6181e9526860..483784d5eb73 100644
--- a/fs/crypto/bio.c
+++ b/fs/crypto/bio.c
@@ -115,7 +115,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
err = -ENOMEM;
goto errout;
}
- bio->bi_bdev = inode->i_sb->s_bdev;
+ bio_set_dev(bio, inode->i_sb->s_bdev);
bio->bi_iter.bi_sector =
pblk << (inode->i_sb->s_blocksize_bits - 9);
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 08cf27811e5a..5fa2211e49ae 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -111,7 +111,7 @@ struct dio {
int op;
int op_flags;
blk_qc_t bio_cookie;
- struct block_device *bio_bdev;
+ struct gendisk *bio_disk;
struct inode *inode;
loff_t i_size; /* i_size when submitted */
dio_iodone_t *end_io; /* IO completion function */
@@ -377,7 +377,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
*/
bio = bio_alloc(GFP_KERNEL, nr_vecs);
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = first_sector;
bio_set_op_attrs(bio, dio->op, dio->op_flags);
if (dio->is_async)
@@ -412,7 +412,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio)
if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty)
bio_set_pages_dirty(bio);
- dio->bio_bdev = bio->bi_bdev;
+ dio->bio_disk = bio->bi_disk;
if (sdio->submit_io) {
sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio);
@@ -458,7 +458,7 @@ static struct bio *dio_await_one(struct dio *dio)
dio->waiter = current;
spin_unlock_irqrestore(&dio->bio_lock, flags);
if (!(dio->iocb->ki_flags & IOCB_HIPRI) ||
- !blk_mq_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie))
+ !blk_mq_poll(dio->bio_disk->queue, dio->bio_cookie))
io_schedule();
/* wake up sets us TASK_RUNNING */
spin_lock_irqsave(&dio->bio_lock, flags);
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 8bb72807e70d..3c6a9c156b7a 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -869,7 +869,7 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
goto out;
}
- bio->bi_bdev = NULL;
+ bio->bi_disk = NULL;
bio->bi_next = NULL;
per_dev->offset = master_dev->offset;
per_dev->length = master_dev->length;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index c2fce4478cca..55ad7dd149d0 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -300,7 +300,7 @@ static void ext4_end_bio(struct bio *bio)
char b[BDEVNAME_SIZE];
if (WARN_ONCE(!io_end, "io_end is NULL: %s: sector %Lu len %u err %d\n",
- bdevname(bio->bi_bdev, b),
+ bio_devname(bio, b),
(long long) bio->bi_iter.bi_sector,
(unsigned) bio_sectors(bio),
bio->bi_status)) {
@@ -375,7 +375,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
return -ENOMEM;
wbc_init_bio(io->io_wbc, bio);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
+ bio_set_dev(bio, bh->b_bdev);
bio->bi_end_io = ext4_end_bio;
bio->bi_private = ext4_get_io_end(io->io_end);
io->io_bio = bio;
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 40a5497b0f60..04c90643af7a 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -254,7 +254,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
fscrypt_release_ctx(ctx);
goto set_error_page;
}
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = blocks[0] << (blkbits - 9);
bio->bi_end_io = mpage_end_io;
bio->bi_private = ctx;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 87c1f4150c64..a791aac4c5af 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -142,7 +142,7 @@ struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
}
}
if (bio) {
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(blk_addr);
}
return bdev;
@@ -161,7 +161,8 @@ int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr)
static bool __same_bdev(struct f2fs_sb_info *sbi,
block_t blk_addr, struct bio *bio)
{
- return f2fs_target_device(sbi, blk_addr, NULL) == bio->bi_bdev;
+ struct block_device *b = f2fs_target_device(sbi, blk_addr, NULL);
+ return bio->bi_disk == b->bd_disk && bio->bi_partno == b->bd_partno;
}
/*
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index f964b68718c1..6f8fc4a6e701 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -447,7 +447,7 @@ static int __submit_flush_wait(struct f2fs_sb_info *sbi,
int ret;
bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
ret = submit_bio_wait(bio);
bio_put(bio);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 7dabbe721dba..c8ff7b7954f0 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -268,7 +268,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
- bio->bi_bdev = sb->s_bdev;
+ bio_set_dev(bio, sb->s_bdev);
bio->bi_end_io = gfs2_end_log_write;
bio->bi_private = sdp;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 61ef6c9be816..52de1036d9f9 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -221,7 +221,7 @@ static void gfs2_submit_bhs(int op, int op_flags, struct buffer_head *bhs[],
bio = bio_alloc(GFP_NOIO, num);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
+ bio_set_dev(bio, bh->b_bdev);
while (num > 0) {
bh = *bhs;
if (!bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh))) {
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c0a4b3778f3f..84593587691d 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -242,7 +242,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9);
- bio->bi_bdev = sb->s_bdev;
+ bio_set_dev(bio, sb->s_bdev);
bio_add_page(bio, page, PAGE_SIZE, 0);
bio->bi_end_io = end_bio_io_page;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index e254fa0f0697..10032b919a85 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -65,7 +65,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
bio = bio_alloc(GFP_NOIO, 1);
bio->bi_iter.bi_sector = sector;
- bio->bi_bdev = sb->s_bdev;
+ bio_set_dev(bio, sb->s_bdev);
bio_set_op_attrs(bio, op, op_flags);
if (op != WRITE && data)
diff --git a/fs/iomap.c b/fs/iomap.c
index 8554a8d75281..269b24a01f32 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -805,7 +805,7 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
struct bio *bio;
bio = bio_alloc(GFP_KERNEL, 1);
- bio->bi_bdev = iomap->bdev;
+ bio_set_dev(bio, iomap->bdev);
bio->bi_iter.bi_sector =
iomap->blkno + ((pos - iomap->offset) >> 9);
bio->bi_private = dio;
@@ -884,7 +884,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
return 0;
bio = bio_alloc(GFP_KERNEL, nr_pages);
- bio->bi_bdev = iomap->bdev;
+ bio_set_dev(bio, iomap->bdev);
bio->bi_iter.bi_sector =
iomap->blkno + ((pos - iomap->offset) >> 9);
bio->bi_write_hint = dio->iocb->ki_hint;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index a21f0e9eecd4..0e5d412c0b01 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1995,7 +1995,7 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
- bio->bi_bdev = log->bdev;
+ bio_set_dev(bio, log->bdev);
bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
@@ -2139,7 +2139,7 @@ static void lbmStartIO(struct lbuf * bp)
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
- bio->bi_bdev = log->bdev;
+ bio_set_dev(bio, log->bdev);
bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset);
BUG_ON(bio->bi_iter.bi_size != LOGPSIZE);
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 65120a471729..1c4b9ad4d7ab 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -430,7 +430,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
len = min(xlen, (int)JFS_SBI(inode->i_sb)->nbperpage);
bio = bio_alloc(GFP_NOFS, 1);
- bio->bi_bdev = inode->i_sb->s_bdev;
+ bio_set_dev(bio, inode->i_sb->s_bdev);
bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9);
bio->bi_end_io = metapage_write_end_io;
bio->bi_private = page;
@@ -510,7 +510,7 @@ static int metapage_readpage(struct file *fp, struct page *page)
submit_bio(bio);
bio = bio_alloc(GFP_NOFS, 1);
- bio->bi_bdev = inode->i_sb->s_bdev;
+ bio_set_dev(bio, inode->i_sb->s_bdev);
bio->bi_iter.bi_sector =
pblock << (inode->i_blkbits - 9);
bio->bi_end_io = metapage_read_end_io;
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index db5900aaa55a..89d1dc19340b 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -21,6 +21,7 @@
DEFINE_MUTEX(kernfs_mutex);
static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */
static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */
+static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */
#define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
@@ -507,6 +508,10 @@ void kernfs_put(struct kernfs_node *kn)
struct kernfs_node *parent;
struct kernfs_root *root;
+ /*
+ * kernfs_node is freed with ->count 0, kernfs_find_and_get_node_by_ino
+ * depends on this to filter reused stale node
+ */
if (!kn || !atomic_dec_and_test(&kn->count))
return;
root = kernfs_root(kn);
@@ -533,7 +538,9 @@ void kernfs_put(struct kernfs_node *kn)
simple_xattrs_free(&kn->iattr->xattrs);
}
kfree(kn->iattr);
- ida_simple_remove(&root->ino_ida, kn->ino);
+ spin_lock(&kernfs_idr_lock);
+ idr_remove(&root->ino_idr, kn->id.ino);
+ spin_unlock(&kernfs_idr_lock);
kmem_cache_free(kernfs_node_cache, kn);
kn = parent;
@@ -542,7 +549,7 @@ void kernfs_put(struct kernfs_node *kn)
goto repeat;
} else {
/* just released the root kn, free @root too */
- ida_destroy(&root->ino_ida);
+ idr_destroy(&root->ino_idr);
kfree(root);
}
}
@@ -559,7 +566,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
if (d_really_is_negative(dentry))
goto out_bad_unlocked;
- kn = dentry->d_fsdata;
+ kn = kernfs_dentry_node(dentry);
mutex_lock(&kernfs_mutex);
/* The kernfs node has been deactivated */
@@ -567,7 +574,7 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
goto out_bad;
/* The kernfs node has been moved? */
- if (dentry->d_parent->d_fsdata != kn->parent)
+ if (kernfs_dentry_node(dentry->d_parent) != kn->parent)
goto out_bad;
/* The kernfs node has been renamed */
@@ -587,14 +594,8 @@ out_bad_unlocked:
return 0;
}
-static void kernfs_dop_release(struct dentry *dentry)
-{
- kernfs_put(dentry->d_fsdata);
-}
-
const struct dentry_operations kernfs_dops = {
.d_revalidate = kernfs_dop_revalidate,
- .d_release = kernfs_dop_release,
};
/**
@@ -610,8 +611,9 @@ const struct dentry_operations kernfs_dops = {
*/
struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
{
- if (dentry->d_sb->s_op == &kernfs_sops)
- return dentry->d_fsdata;
+ if (dentry->d_sb->s_op == &kernfs_sops &&
+ !d_really_is_negative(dentry))
+ return kernfs_dentry_node(dentry);
return NULL;
}
@@ -620,6 +622,8 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
unsigned flags)
{
struct kernfs_node *kn;
+ u32 gen;
+ int cursor;
int ret;
name = kstrdup_const(name, GFP_KERNEL);
@@ -630,11 +634,25 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
if (!kn)
goto err_out1;
- ret = ida_simple_get(&root->ino_ida, 1, 0, GFP_KERNEL);
+ idr_preload(GFP_KERNEL);
+ spin_lock(&kernfs_idr_lock);
+ cursor = idr_get_cursor(&root->ino_idr);
+ ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC);
+ if (ret >= 0 && ret < cursor)
+ root->next_generation++;
+ gen = root->next_generation;
+ spin_unlock(&kernfs_idr_lock);
+ idr_preload_end();
if (ret < 0)
goto err_out2;
- kn->ino = ret;
+ kn->id.ino = ret;
+ kn->id.generation = gen;
+ /*
+ * set ino first. This barrier is paired with atomic_inc_not_zero in
+ * kernfs_find_and_get_node_by_ino
+ */
+ smp_mb__before_atomic();
atomic_set(&kn->count, 1);
atomic_set(&kn->active, KN_DEACTIVATED_BIAS);
RB_CLEAR_NODE(&kn->rb);
@@ -666,6 +684,54 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
return kn;
}
+/*
+ * kernfs_find_and_get_node_by_ino - get kernfs_node from inode number
+ * @root: the kernfs root
+ * @ino: inode number
+ *
+ * RETURNS:
+ * NULL on failure. Return a kernfs node with reference counter incremented
+ */
+struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
+ unsigned int ino)
+{
+ struct kernfs_node *kn;
+
+ rcu_read_lock();
+ kn = idr_find(&root->ino_idr, ino);
+ if (!kn)
+ goto out;
+
+ /*
+ * Since kernfs_node is freed in RCU, it's possible an old node for ino
+ * is freed, but reused before RCU grace period. But a freed node (see
+ * kernfs_put) or an incompletedly initialized node (see
+ * __kernfs_new_node) should have 'count' 0. We can use this fact to
+ * filter out such node.
+ */
+ if (!atomic_inc_not_zero(&kn->count)) {
+ kn = NULL;
+ goto out;
+ }
+
+ /*
+ * The node could be a new node or a reused node. If it's a new node,
+ * we are ok. If it's reused because of RCU (because of
+ * SLAB_TYPESAFE_BY_RCU), the __kernfs_new_node always sets its 'ino'
+ * before 'count'. So if 'count' is uptodate, 'ino' should be uptodate,
+ * hence we can use 'ino' to filter stale node.
+ */
+ if (kn->id.ino != ino)
+ goto out;
+ rcu_read_unlock();
+
+ return kn;
+out:
+ rcu_read_unlock();
+ kernfs_put(kn);
+ return NULL;
+}
+
/**
* kernfs_add_one - add kernfs_node to parent without warning
* @kn: kernfs_node to be added
@@ -875,13 +941,14 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
if (!root)
return ERR_PTR(-ENOMEM);
- ida_init(&root->ino_ida);
+ idr_init(&root->ino_idr);
INIT_LIST_HEAD(&root->supers);
+ root->next_generation = 1;
kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
KERNFS_DIR);
if (!kn) {
- ida_destroy(&root->ino_ida);
+ idr_destroy(&root->ino_idr);
kfree(root);
return ERR_PTR(-ENOMEM);
}
@@ -984,7 +1051,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
unsigned int flags)
{
struct dentry *ret;
- struct kernfs_node *parent = dentry->d_parent->d_fsdata;
+ struct kernfs_node *parent = dir->i_private;
struct kernfs_node *kn;
struct inode *inode;
const void *ns = NULL;
@@ -1001,8 +1068,6 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
ret = NULL;
goto out_unlock;
}
- kernfs_get(kn);
- dentry->d_fsdata = kn;
/* attach dentry and inode */
inode = kernfs_get_inode(dir->i_sb, kn);
@@ -1039,7 +1104,7 @@ static int kernfs_iop_mkdir(struct inode *dir, struct dentry *dentry,
static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry)
{
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = kernfs_dentry_node(dentry);
struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
int ret;
@@ -1059,7 +1124,7 @@ static int kernfs_iop_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- struct kernfs_node *kn = old_dentry->d_fsdata;
+ struct kernfs_node *kn = kernfs_dentry_node(old_dentry);
struct kernfs_node *new_parent = new_dir->i_private;
struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops;
int ret;
@@ -1572,7 +1637,7 @@ static struct kernfs_node *kernfs_dir_next_pos(const void *ns,
static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file->f_path.dentry;
- struct kernfs_node *parent = dentry->d_fsdata;
+ struct kernfs_node *parent = kernfs_dentry_node(dentry);
struct kernfs_node *pos = file->private_data;
const void *ns = NULL;
@@ -1589,7 +1654,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
const char *name = pos->name;
unsigned int type = dt_type(pos);
int len = strlen(name);
- ino_t ino = pos->ino;
+ ino_t ino = pos->id.ino;
ctx->pos = pos->hash;
file->private_data = pos;
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e6c8954a4e89..9698e51656b1 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -616,7 +616,7 @@ static void kernfs_put_open_node(struct kernfs_node *kn,
static int kernfs_fop_open(struct inode *inode, struct file *file)
{
- struct kernfs_node *kn = file->f_path.dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
struct kernfs_root *root = kernfs_root(kn);
const struct kernfs_ops *ops;
struct kernfs_open_file *of;
@@ -768,7 +768,7 @@ static void kernfs_release_file(struct kernfs_node *kn,
static int kernfs_fop_release(struct inode *inode, struct file *filp)
{
- struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
struct kernfs_open_file *of = kernfs_of(filp);
if (kn->flags & KERNFS_HAS_RELEASE) {
@@ -835,7 +835,7 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
static unsigned int kernfs_fop_poll(struct file *filp, poll_table *wait)
{
struct kernfs_open_file *of = kernfs_of(filp);
- struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
+ struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
struct kernfs_open_node *on = kn->attr.open;
if (!kernfs_get_active(kn))
@@ -895,7 +895,7 @@ repeat:
* have the matching @file available. Look up the inodes
* and generate the events manually.
*/
- inode = ilookup(info->sb, kn->ino);
+ inode = ilookup(info->sb, kn->id.ino);
if (!inode)
continue;
@@ -903,7 +903,7 @@ repeat:
if (parent) {
struct inode *p_inode;
- p_inode = ilookup(info->sb, parent->ino);
+ p_inode = ilookup(info->sb, parent->id.ino);
if (p_inode) {
fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD,
inode, FSNOTIFY_EVENT_INODE, kn->name, 0);
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index fb4b4a79a0d6..a34303981deb 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -112,7 +112,7 @@ int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
int error;
if (!kn)
@@ -154,7 +154,7 @@ static int kernfs_node_setsecdata(struct kernfs_iattrs *attrs, void **secdata,
ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size)
{
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = kernfs_dentry_node(dentry);
struct kernfs_iattrs *attrs;
attrs = kernfs_iattrs(kn);
@@ -203,8 +203,8 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
- struct kernfs_node *kn = path->dentry->d_fsdata;
struct inode *inode = d_inode(path->dentry);
+ struct kernfs_node *kn = inode->i_private;
mutex_lock(&kernfs_mutex);
kernfs_refresh_inode(kn, inode);
@@ -220,6 +220,7 @@ static void kernfs_init_inode(struct kernfs_node *kn, struct inode *inode)
inode->i_private = kn;
inode->i_mapping->a_ops = &kernfs_aops;
inode->i_op = &kernfs_iops;
+ inode->i_generation = kn->id.generation;
set_default_inode_attr(inode, kn->mode);
kernfs_refresh_inode(kn, inode);
@@ -265,7 +266,7 @@ struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn)
{
struct inode *inode;
- inode = iget_locked(sb, kn->ino);
+ inode = iget_locked(sb, kn->id.ino);
if (inode && (inode->i_state & I_NEW))
kernfs_init_inode(kn, inode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 2d5144ab4251..0f260dcca177 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -70,6 +70,13 @@ struct kernfs_super_info {
};
#define kernfs_info(SB) ((struct kernfs_super_info *)(SB->s_fs_info))
+static inline struct kernfs_node *kernfs_dentry_node(struct dentry *dentry)
+{
+ if (d_really_is_negative(dentry))
+ return NULL;
+ return d_inode(dentry)->i_private;
+}
+
extern const struct super_operations kernfs_sops;
extern struct kmem_cache *kernfs_node_cache;
@@ -98,6 +105,8 @@ int kernfs_add_one(struct kernfs_node *kn);
struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
const char *name, umode_t mode,
unsigned flags);
+struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
+ unsigned int ino);
/*
* file.c
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index d5b149a45be1..95a7c88baed9 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -16,6 +16,7 @@
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/seq_file.h>
+#include <linux/exportfs.h>
#include "kernfs-internal.h"
@@ -33,7 +34,7 @@ static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
{
- struct kernfs_root *root = kernfs_root(dentry->d_fsdata);
+ struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
struct kernfs_syscall_ops *scops = root->syscall_ops;
if (scops && scops->show_options)
@@ -43,7 +44,7 @@ static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
static int kernfs_sop_show_path(struct seq_file *sf, struct dentry *dentry)
{
- struct kernfs_node *node = dentry->d_fsdata;
+ struct kernfs_node *node = kernfs_dentry_node(dentry);
struct kernfs_root *root = kernfs_root(node);
struct kernfs_syscall_ops *scops = root->syscall_ops;
@@ -64,6 +65,78 @@ const struct super_operations kernfs_sops = {
.show_path = kernfs_sop_show_path,
};
+/*
+ * Similar to kernfs_fh_get_inode, this one gets kernfs node from inode
+ * number and generation
+ */
+struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
+ const union kernfs_node_id *id)
+{
+ struct kernfs_node *kn;
+
+ kn = kernfs_find_and_get_node_by_ino(root, id->ino);
+ if (!kn)
+ return NULL;
+ if (kn->id.generation != id->generation) {
+ kernfs_put(kn);
+ return NULL;
+ }
+ return kn;
+}
+
+static struct inode *kernfs_fh_get_inode(struct super_block *sb,
+ u64 ino, u32 generation)
+{
+ struct kernfs_super_info *info = kernfs_info(sb);
+ struct inode *inode;
+ struct kernfs_node *kn;
+
+ if (ino == 0)
+ return ERR_PTR(-ESTALE);
+
+ kn = kernfs_find_and_get_node_by_ino(info->root, ino);
+ if (!kn)
+ return ERR_PTR(-ESTALE);
+ inode = kernfs_get_inode(sb, kn);
+ kernfs_put(kn);
+ if (!inode)
+ return ERR_PTR(-ESTALE);
+
+ if (generation && inode->i_generation != generation) {
+ /* we didn't find the right inode.. */
+ iput(inode);
+ return ERR_PTR(-ESTALE);
+ }
+ return inode;
+}
+
+static struct dentry *kernfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+ kernfs_fh_get_inode);
+}
+
+static struct dentry *kernfs_fh_to_parent(struct super_block *sb, struct fid *fid,
+ int fh_len, int fh_type)
+{
+ return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+ kernfs_fh_get_inode);
+}
+
+static struct dentry *kernfs_get_parent_dentry(struct dentry *child)
+{
+ struct kernfs_node *kn = kernfs_dentry_node(child);
+
+ return d_obtain_alias(kernfs_get_inode(child->d_sb, kn->parent));
+}
+
+static const struct export_operations kernfs_export_ops = {
+ .fh_to_dentry = kernfs_fh_to_dentry,
+ .fh_to_parent = kernfs_fh_to_parent,
+ .get_parent = kernfs_get_parent_dentry,
+};
+
/**
* kernfs_root_from_sb - determine kernfs_root associated with a super_block
* @sb: the super_block in question
@@ -159,6 +232,8 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
sb->s_magic = magic;
sb->s_op = &kernfs_sops;
sb->s_xattr = kernfs_xattr_handlers;
+ if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
+ sb->s_export_op = &kernfs_export_ops;
sb->s_time_gran = 1;
/* get root inode, initialize and unlock it */
@@ -176,8 +251,6 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
pr_debug("%s: could not get root dentry!\n", __func__);
return -ENOMEM;
}
- kernfs_get(info->root->kn);
- root->d_fsdata = info->root->kn;
sb->s_root = root;
sb->s_d_op = &kernfs_dops;
return 0;
@@ -283,7 +356,6 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
void kernfs_kill_sb(struct super_block *sb)
{
struct kernfs_super_info *info = kernfs_info(sb);
- struct kernfs_node *root_kn = sb->s_root->d_fsdata;
mutex_lock(&kernfs_mutex);
list_del(&info->node);
@@ -295,7 +367,6 @@ void kernfs_kill_sb(struct super_block *sb)
*/
kill_anon_super(sb);
kfree(info);
- kernfs_put(root_kn);
}
/**
@@ -330,7 +401,16 @@ struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns)
void __init kernfs_init(void)
{
+
+ /*
+ * the slab is freed in RCU context, so kernfs_find_and_get_node_by_ino
+ * can access the slab lock free. This could introduce stale nodes,
+ * please see how kernfs_find_and_get_node_by_ino filters out stale
+ * nodes.
+ */
kernfs_node_cache = kmem_cache_create("kernfs_node_cache",
sizeof(struct kernfs_node),
- 0, SLAB_PANIC, NULL);
+ 0,
+ SLAB_PANIC | SLAB_TYPESAFE_BY_RCU,
+ NULL);
}
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 1684af4a8b9b..08ccabd7047f 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -98,9 +98,9 @@ static int kernfs_get_target_path(struct kernfs_node *parent,
return 0;
}
-static int kernfs_getlink(struct dentry *dentry, char *path)
+static int kernfs_getlink(struct inode *inode, char *path)
{
- struct kernfs_node *kn = dentry->d_fsdata;
+ struct kernfs_node *kn = inode->i_private;
struct kernfs_node *parent = kn->parent;
struct kernfs_node *target = kn->symlink.target_kn;
int error;
@@ -124,7 +124,7 @@ static const char *kernfs_iop_get_link(struct dentry *dentry,
body = kzalloc(PAGE_SIZE, GFP_KERNEL);
if (!body)
return ERR_PTR(-ENOMEM);
- error = kernfs_getlink(dentry, body);
+ error = kernfs_getlink(inode, body);
if (unlikely(error < 0)) {
kfree(body);
return ERR_PTR(error);
diff --git a/fs/mpage.c b/fs/mpage.c
index 2e4c41ccb5c9..37bb77c1302c 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -83,7 +83,7 @@ mpage_alloc(struct block_device *bdev,
}
if (bio) {
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = first_sector;
}
return bio;
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index d8863a804b15..995d707537da 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -130,7 +130,7 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector,
if (bio) {
bio->bi_iter.bi_sector = disk_sector;
- bio->bi_bdev = bdev;
+ bio_set_dev(bio, bdev);
bio->bi_end_io = end_io;
bio->bi_private = par;
}
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index e73c86d9855c..6c5009cc4e6f 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -400,7 +400,7 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start,
bio = bio_alloc(GFP_NOIO, nr_vecs);
}
if (likely(bio)) {
- bio->bi_bdev = nilfs->ns_bdev;
+ bio_set_dev(bio, nilfs->ns_bdev);
bio->bi_iter.bi_sector =
start << (nilfs->ns_blocksize_bits - 9);
}
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 56ac07cd35f6..d0206042d068 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -553,7 +553,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
/* Must put everything in 512 byte sectors for the bio... */
bio->bi_iter.bi_sector = (reg->hr_start_block + cs) << (bits - 9);
- bio->bi_bdev = reg->hr_bdev;
+ bio_set_dev(bio, reg->hr_bdev);
bio->bi_private = wc;
bio->bi_end_io = o2hb_bio_end_io;
bio_set_op_attrs(bio, op, op_flags);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f9efd67f6fa1..fffae1390d7f 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -540,7 +540,7 @@ xfs_init_bio_from_bh(
struct buffer_head *bh)
{
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
- bio->bi_bdev = bh->b_bdev;
+ bio_set_dev(bio, bh->b_bdev);
}
static struct xfs_ioend *
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 72f038492ba8..b1c9711e79a4 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1281,7 +1281,7 @@ next_chunk:
nr_pages = min(total_nr_pages, BIO_MAX_PAGES);
bio = bio_alloc(GFP_NOIO, nr_pages);
- bio->bi_bdev = bp->b_target->bt_bdev;
+ bio_set_dev(bio, bp->b_target->bt_bdev);
bio->bi_iter.bi_sector = sector;
bio->bi_end_io = xfs_buf_bio_end_io;
bio->bi_private = bp;