summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/afs/proc.c4
-rw-r--r--fs/bio-integrity.c184
-rw-r--r--fs/bio.c507
-rw-r--r--fs/btrfs/Kconfig3
-rw-r--r--fs/btrfs/Makefile2
-rw-r--r--fs/btrfs/backref.c195
-rw-r--r--fs/btrfs/btrfs_inode.h4
-rw-r--r--fs/btrfs/check-integrity.c24
-rw-r--r--fs/btrfs/compression.c41
-rw-r--r--fs/btrfs/ctree.c552
-rw-r--r--fs/btrfs/ctree.h134
-rw-r--r--fs/btrfs/delayed-inode.c208
-rw-r--r--fs/btrfs/delayed-inode.h8
-rw-r--r--fs/btrfs/delayed-ref.c300
-rw-r--r--fs/btrfs/delayed-ref.h26
-rw-r--r--fs/btrfs/dev-replace.c56
-rw-r--r--fs/btrfs/dir-item.c8
-rw-r--r--fs/btrfs/disk-io.c269
-rw-r--r--fs/btrfs/extent-tree.c618
-rw-r--r--fs/btrfs/extent_io.c277
-rw-r--r--fs/btrfs/extent_io.h9
-rw-r--r--fs/btrfs/extent_map.c74
-rw-r--r--fs/btrfs/file-item.c23
-rw-r--r--fs/btrfs/file.c216
-rw-r--r--fs/btrfs/free-space-cache.c23
-rw-r--r--fs/btrfs/hash.c50
-rw-r--r--fs/btrfs/hash.h11
-rw-r--r--fs/btrfs/inode-item.c65
-rw-r--r--fs/btrfs/inode.c485
-rw-r--r--fs/btrfs/ioctl.c334
-rw-r--r--fs/btrfs/lzo.c6
-rw-r--r--fs/btrfs/ordered-data.c15
-rw-r--r--fs/btrfs/orphan.c20
-rw-r--r--fs/btrfs/print-tree.c4
-rw-r--r--fs/btrfs/props.c427
-rw-r--r--fs/btrfs/props.h42
-rw-r--r--fs/btrfs/qgroup.c57
-rw-r--r--fs/btrfs/raid56.c22
-rw-r--r--fs/btrfs/reada.c9
-rw-r--r--fs/btrfs/relocation.c105
-rw-r--r--fs/btrfs/root-tree.c19
-rw-r--r--fs/btrfs/scrub.c146
-rw-r--r--fs/btrfs/send.c973
-rw-r--r--fs/btrfs/super.c254
-rw-r--r--fs/btrfs/sysfs.c623
-rw-r--r--fs/btrfs/sysfs.h64
-rw-r--r--fs/btrfs/tests/btrfs-tests.h2
-rw-r--r--fs/btrfs/transaction.c55
-rw-r--r--fs/btrfs/transaction.h3
-rw-r--r--fs/btrfs/tree-log.c209
-rw-r--r--fs/btrfs/ulist.c117
-rw-r--r--fs/btrfs/ulist.h39
-rw-r--r--fs/btrfs/uuid-tree.c13
-rw-r--r--fs/btrfs/volumes.c108
-rw-r--r--fs/btrfs/xattr.c12
-rw-r--r--fs/btrfs/zlib.c8
-rw-r--r--fs/buffer.c20
-rw-r--r--fs/ceph/acl.c79
-rw-r--r--fs/ceph/dir.c24
-rw-r--r--fs/ceph/file.c1
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/super.c32
-rw-r--r--fs/ceph/super.h9
-rw-r--r--fs/ceph/xattr.c54
-rw-r--r--fs/cifs/cifsacl.c101
-rw-r--r--fs/cifs/cifsglob.h25
-rw-r--r--fs/cifs/cifsproto.h31
-rw-r--r--fs/cifs/cifssmb.c173
-rw-r--r--fs/cifs/dir.c61
-rw-r--r--fs/cifs/file.c76
-rw-r--r--fs/cifs/inode.c193
-rw-r--r--fs/cifs/link.c323
-rw-r--r--fs/cifs/readdir.c2
-rw-r--r--fs/cifs/smb1ops.c135
-rw-r--r--fs/cifs/smb2glob.h3
-rw-r--r--fs/cifs/smb2ops.c14
-rw-r--r--fs/cifs/smb2pdu.c9
-rw-r--r--fs/cifs/smb2proto.h3
-rw-r--r--fs/cifs/xattr.c64
-rw-r--r--fs/dcookies.c2
-rw-r--r--fs/direct-io.c4
-rw-r--r--fs/exec.c45
-rw-r--r--fs/ext4/ext4.h2
-rw-r--r--fs/ext4/extents.c1
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/ioctl.c3
-rw-r--r--fs/ext4/page-io.c8
-rw-r--r--fs/ext4/resize.c34
-rw-r--r--fs/ext4/super.c20
-rw-r--r--fs/f2fs/data.c35
-rw-r--r--fs/file.c2
-rw-r--r--fs/fs-writeback.c33
-rw-r--r--fs/fscache/object-list.c5
-rw-r--r--fs/fscache/object.c3
-rw-r--r--fs/gfs2/lops.c2
-rw-r--r--fs/gfs2/ops_fstype.c2
-rw-r--r--fs/hfsplus/dir.c2
-rw-r--r--fs/hfsplus/inode.c2
-rw-r--r--fs/hfsplus/options.c2
-rw-r--r--fs/hfsplus/wrapper.c2
-rw-r--r--fs/hfsplus/xattr.c60
-rw-r--r--fs/hfsplus/xattr.h2
-rw-r--r--fs/hpfs/alloc.c66
-rw-r--r--fs/hpfs/buffer.c96
-rw-r--r--fs/hpfs/hpfs_fn.h2
-rw-r--r--fs/hpfs/super.c29
-rw-r--r--fs/jbd2/transaction.c6
-rw-r--r--fs/jfs/acl.c2
-rw-r--r--fs/jfs/jfs_logmgr.c12
-rw-r--r--fs/jfs/jfs_metapage.c9
-rw-r--r--fs/jfs/xattr.c29
-rw-r--r--fs/kernfs/dir.c12
-rw-r--r--fs/kernfs/mount.c8
-rw-r--r--fs/lockd/svclock.c8
-rw-r--r--fs/logfs/dev_bdev.c38
-rw-r--r--fs/mpage.c19
-rw-r--r--fs/namei.c36
-rw-r--r--fs/nfs/blocklayout/blocklayout.c43
-rw-r--r--fs/nfs/delegation.c11
-rw-r--r--fs/nfs/dir.c18
-rw-r--r--fs/nfs/inode.c65
-rw-r--r--fs/nfs/internal.h12
-rw-r--r--fs/nfs/nfs3acl.c34
-rw-r--r--fs/nfs/nfs3proc.c5
-rw-r--r--fs/nfs/nfs4_fs.h1
-rw-r--r--fs/nfs/nfs4client.c14
-rw-r--r--fs/nfs/nfs4filelayout.c18
-rw-r--r--fs/nfs/nfs4namespace.c12
-rw-r--r--fs/nfs/nfs4proc.c63
-rw-r--r--fs/nfs/nfs4session.c25
-rw-r--r--fs/nfs/nfs4session.h2
-rw-r--r--fs/nfs/nfs4state.c19
-rw-r--r--fs/nfs/nfs4xdr.c2
-rw-r--r--fs/nfs/nfstrace.h1
-rw-r--r--fs/nfs/write.c7
-rw-r--r--fs/nfsd/acl.h2
-rw-r--r--fs/nfsd/cache.h8
-rw-r--r--fs/nfsd/idmap.h4
-rw-r--r--fs/nfsd/netns.h1
-rw-r--r--fs/nfsd/nfs3xdr.c14
-rw-r--r--fs/nfsd/nfs4acl.c29
-rw-r--r--fs/nfsd/nfs4idmap.c50
-rw-r--r--fs/nfsd/nfs4proc.c57
-rw-r--r--fs/nfsd/nfs4state.c40
-rw-r--r--fs/nfsd/nfs4xdr.c178
-rw-r--r--fs/nfsd/nfscache.c36
-rw-r--r--fs/nfsd/nfssvc.c30
-rw-r--r--fs/nfsd/nfsxdr.c2
-rw-r--r--fs/nfsd/vfs.c40
-rw-r--r--fs/nfsd/vfs.h2
-rw-r--r--fs/nfsd/xdr3.h3
-rw-r--r--fs/nfsd/xdr4.h4
-rw-r--r--fs/nilfs2/segbuf.c3
-rw-r--r--fs/notify/dnotify/dnotify.c2
-rw-r--r--fs/notify/fanotify/fanotify.c44
-rw-r--r--fs/notify/fanotify/fanotify.h7
-rw-r--r--fs/notify/fanotify/fanotify_user.c20
-rw-r--r--fs/notify/fsnotify.c2
-rw-r--r--fs/notify/group.c8
-rw-r--r--fs/notify/inotify/inotify.h2
-rw-r--r--fs/notify/inotify/inotify_fsnotify.c22
-rw-r--r--fs/notify/inotify/inotify_user.c14
-rw-r--r--fs/notify/notification.c40
-rw-r--r--fs/ntfs/file.c2
-rw-r--r--fs/ocfs2/alloc.c40
-rw-r--r--fs/ocfs2/cluster/heartbeat.c2
-rw-r--r--fs/ocfs2/file.c52
-rw-r--r--fs/ocfs2/localalloc.c42
-rw-r--r--fs/ocfs2/localalloc.h6
-rw-r--r--fs/ocfs2/namei.c17
-rw-r--r--fs/ocfs2/quota_global.c27
-rw-r--r--fs/ocfs2/quota_local.c4
-rw-r--r--fs/posix_acl.c18
-rw-r--r--fs/proc/page.c5
-rw-r--r--fs/proc/vmcore.c26
-rw-r--r--fs/quota/dquot.c14
-rw-r--r--fs/read_write.c16
-rw-r--r--fs/reiserfs/do_balan.c895
-rw-r--r--fs/super.c3
-rw-r--r--fs/sync.c32
-rw-r--r--fs/sysfs/mount.c5
-rw-r--r--fs/udf/file.c14
-rw-r--r--fs/udf/inode.c1
-rw-r--r--fs/xfs/xfs_aops.c2
-rw-r--r--fs/xfs/xfs_buf.c4
-rw-r--r--fs/xfs/xfs_file.c2
-rw-r--r--fs/xfs/xfs_iops.c16
-rw-r--r--fs/xfs/xfs_log_cil.c19
-rw-r--r--fs/xfs/xfs_mount.c24
-rw-r--r--fs/xfs/xfs_sb.c10
-rw-r--r--fs/xfs/xfs_super.c2
191 files changed, 7763 insertions, 4694 deletions
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index bddc5120ed40..24a905b076fd 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -130,8 +130,8 @@ int afs_proc_init(void)
if (!proc_afs)
goto error_dir;
- if (!proc_create("cells", 0, proc_afs, &afs_proc_cells_fops) ||
- !proc_create("rootcell", 0, proc_afs, &afs_proc_rootcell_fops))
+ if (!proc_create("cells", 0644, proc_afs, &afs_proc_cells_fops) ||
+ !proc_create("rootcell", 0644, proc_afs, &afs_proc_rootcell_fops))
goto error_tree;
_leave(" = 0");
diff --git a/fs/bio-integrity.c b/fs/bio-integrity.c
index fc60b31453ee..4f70f383132c 100644
--- a/fs/bio-integrity.c
+++ b/fs/bio-integrity.c
@@ -114,6 +114,14 @@ void bio_integrity_free(struct bio *bio)
}
EXPORT_SYMBOL(bio_integrity_free);
+static inline unsigned int bip_integrity_vecs(struct bio_integrity_payload *bip)
+{
+ if (bip->bip_slab == BIO_POOL_NONE)
+ return BIP_INLINE_VECS;
+
+ return bvec_nr_vecs(bip->bip_slab);
+}
+
/**
* bio_integrity_add_page - Attach integrity metadata
* @bio: bio to update
@@ -129,13 +137,12 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
struct bio_integrity_payload *bip = bio->bi_integrity;
struct bio_vec *iv;
- if (bip->bip_vcnt >= bvec_nr_vecs(bip->bip_slab)) {
+ if (bip->bip_vcnt >= bip_integrity_vecs(bip)) {
printk(KERN_ERR "%s: bip_vec full\n", __func__);
return 0;
}
- iv = bip_vec_idx(bip, bip->bip_vcnt);
- BUG_ON(iv == NULL);
+ iv = bip->bip_vec + bip->bip_vcnt;
iv->bv_page = page;
iv->bv_len = len;
@@ -203,6 +210,12 @@ static inline unsigned int bio_integrity_hw_sectors(struct blk_integrity *bi,
return sectors;
}
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+ unsigned int sectors)
+{
+ return bio_integrity_hw_sectors(bi, sectors) * bi->tuple_size;
+}
+
/**
* bio_integrity_tag_size - Retrieve integrity tag space
* @bio: bio to inspect
@@ -215,13 +228,14 @@ unsigned int bio_integrity_tag_size(struct bio *bio)
{
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- BUG_ON(bio->bi_size == 0);
+ BUG_ON(bio->bi_iter.bi_size == 0);
- return bi->tag_size * (bio->bi_size / bi->sector_size);
+ return bi->tag_size * (bio->bi_iter.bi_size / bi->sector_size);
}
EXPORT_SYMBOL(bio_integrity_tag_size);
-int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set)
+static int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len,
+ int set)
{
struct bio_integrity_payload *bip = bio->bi_integrity;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -235,9 +249,9 @@ int bio_integrity_tag(struct bio *bio, void *tag_buf, unsigned int len, int set)
nr_sectors = bio_integrity_hw_sectors(bi,
DIV_ROUND_UP(len, bi->tag_size));
- if (nr_sectors * bi->tuple_size > bip->bip_size) {
- printk(KERN_ERR "%s: tag too big for bio: %u > %u\n",
- __func__, nr_sectors * bi->tuple_size, bip->bip_size);
+ if (nr_sectors * bi->tuple_size > bip->bip_iter.bi_size) {
+ printk(KERN_ERR "%s: tag too big for bio: %u > %u\n", __func__,
+ nr_sectors * bi->tuple_size, bip->bip_iter.bi_size);
return -1;
}
@@ -299,29 +313,30 @@ static void bio_integrity_generate(struct bio *bio)
{
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
struct blk_integrity_exchg bix;
- struct bio_vec *bv;
- sector_t sector = bio->bi_sector;
- unsigned int i, sectors, total;
+ struct bio_vec bv;
+ struct bvec_iter iter;
+ sector_t sector = bio->bi_iter.bi_sector;
+ unsigned int sectors, total;
void *prot_buf = bio->bi_integrity->bip_buf;
total = 0;
bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
bix.sector_size = bi->sector_size;
- bio_for_each_segment(bv, bio, i) {
- void *kaddr = kmap_atomic(bv->bv_page);
- bix.data_buf = kaddr + bv->bv_offset;
- bix.data_size = bv->bv_len;
+ bio_for_each_segment(bv, bio, iter) {
+ void *kaddr = kmap_atomic(bv.bv_page);
+ bix.data_buf = kaddr + bv.bv_offset;
+ bix.data_size = bv.bv_len;
bix.prot_buf = prot_buf;
bix.sector = sector;
bi->generate_fn(&bix);
- sectors = bv->bv_len / bi->sector_size;
+ sectors = bv.bv_len / bi->sector_size;
sector += sectors;
prot_buf += sectors * bi->tuple_size;
total += sectors * bi->tuple_size;
- BUG_ON(total > bio->bi_integrity->bip_size);
+ BUG_ON(total > bio->bi_integrity->bip_iter.bi_size);
kunmap_atomic(kaddr);
}
@@ -386,8 +401,8 @@ int bio_integrity_prep(struct bio *bio)
bip->bip_owns_buf = 1;
bip->bip_buf = buf;
- bip->bip_size = len;
- bip->bip_sector = bio->bi_sector;
+ bip->bip_iter.bi_size = len;
+ bip->bip_iter.bi_sector = bio->bi_iter.bi_sector;
/* Map it */
offset = offset_in_page(buf);
@@ -442,16 +457,17 @@ static int bio_integrity_verify(struct bio *bio)
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
struct blk_integrity_exchg bix;
struct bio_vec *bv;
- sector_t sector = bio->bi_integrity->bip_sector;
- unsigned int i, sectors, total, ret;
+ sector_t sector = bio->bi_integrity->bip_iter.bi_sector;
+ unsigned int sectors, ret = 0;
void *prot_buf = bio->bi_integrity->bip_buf;
+ int i;
- ret = total = 0;
bix.disk_name = bio->bi_bdev->bd_disk->disk_name;
bix.sector_size = bi->sector_size;
- bio_for_each_segment(bv, bio, i) {
+ bio_for_each_segment_all(bv, bio, i) {
void *kaddr = kmap_atomic(bv->bv_page);
+
bix.data_buf = kaddr + bv->bv_offset;
bix.data_size = bv->bv_len;
bix.prot_buf = prot_buf;
@@ -467,8 +483,6 @@ static int bio_integrity_verify(struct bio *bio)
sectors = bv->bv_len / bi->sector_size;
sector += sectors;
prot_buf += sectors * bi->tuple_size;
- total += sectors * bi->tuple_size;
- BUG_ON(total > bio->bi_integrity->bip_size);
kunmap_atomic(kaddr);
}
@@ -495,7 +509,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
/* Restore original bio completion handler */
bio->bi_end_io = bip->bip_end_io;
- bio_endio(bio, error);
+ bio_endio_nodec(bio, error);
}
/**
@@ -533,56 +547,6 @@ void bio_integrity_endio(struct bio *bio, int error)
EXPORT_SYMBOL(bio_integrity_endio);
/**
- * bio_integrity_mark_head - Advance bip_vec skip bytes
- * @bip: Integrity vector to advance
- * @skip: Number of bytes to advance it
- */
-void bio_integrity_mark_head(struct bio_integrity_payload *bip,
- unsigned int skip)
-{
- struct bio_vec *iv;
- unsigned int i;
-
- bip_for_each_vec(iv, bip, i) {
- if (skip == 0) {
- bip->bip_idx = i;
- return;
- } else if (skip >= iv->bv_len) {
- skip -= iv->bv_len;
- } else { /* skip < iv->bv_len) */
- iv->bv_offset += skip;
- iv->bv_len -= skip;
- bip->bip_idx = i;
- return;
- }
- }
-}
-
-/**
- * bio_integrity_mark_tail - Truncate bip_vec to be len bytes long
- * @bip: Integrity vector to truncate
- * @len: New length of integrity vector
- */
-void bio_integrity_mark_tail(struct bio_integrity_payload *bip,
- unsigned int len)
-{
- struct bio_vec *iv;
- unsigned int i;
-
- bip_for_each_vec(iv, bip, i) {
- if (len == 0) {
- bip->bip_vcnt = i;
- return;
- } else if (len >= iv->bv_len) {
- len -= iv->bv_len;
- } else { /* len < iv->bv_len) */
- iv->bv_len = len;
- len = 0;
- }
- }
-}
-
-/**
* bio_integrity_advance - Advance integrity vector
* @bio: bio whose integrity vector to update
* @bytes_done: number of data bytes that have been completed
@@ -595,13 +559,9 @@ void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
{
struct bio_integrity_payload *bip = bio->bi_integrity;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- unsigned int nr_sectors;
-
- BUG_ON(bip == NULL);
- BUG_ON(bi == NULL);
+ unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
- nr_sectors = bio_integrity_hw_sectors(bi, bytes_done >> 9);
- bio_integrity_mark_head(bip, nr_sectors * bi->tuple_size);
+ bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
}
EXPORT_SYMBOL(bio_integrity_advance);
@@ -621,64 +581,13 @@ void bio_integrity_trim(struct bio *bio, unsigned int offset,
{
struct bio_integrity_payload *bip = bio->bi_integrity;
struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
- unsigned int nr_sectors;
-
- BUG_ON(bip == NULL);
- BUG_ON(bi == NULL);
- BUG_ON(!bio_flagged(bio, BIO_CLONED));
- nr_sectors = bio_integrity_hw_sectors(bi, sectors);
- bip->bip_sector = bip->bip_sector + offset;
- bio_integrity_mark_head(bip, offset * bi->tuple_size);
- bio_integrity_mark_tail(bip, sectors * bi->tuple_size);
+ bio_integrity_advance(bio, offset << 9);
+ bip->bip_iter.bi_size = bio_integrity_bytes(bi, sectors);
}
EXPORT_SYMBOL(bio_integrity_trim);
/**
- * bio_integrity_split - Split integrity metadata
- * @bio: Protected bio
- * @bp: Resulting bio_pair
- * @sectors: Offset
- *
- * Description: Splits an integrity page into a bio_pair.
- */
-void bio_integrity_split(struct bio *bio, struct bio_pair *bp, int sectors)
-{
- struct blk_integrity *bi;
- struct bio_integrity_payload *bip = bio->bi_integrity;
- unsigned int nr_sectors;
-
- if (bio_integrity(bio) == 0)
- return;
-
- bi = bdev_get_integrity(bio->bi_bdev);
- BUG_ON(bi == NULL);
- BUG_ON(bip->bip_vcnt != 1);
-
- nr_sectors = bio_integrity_hw_sectors(bi, sectors);
-
- bp->bio1.bi_integrity = &bp->bip1;
- bp->bio2.bi_integrity = &bp->bip2;
-
- bp->iv1 = bip->bip_vec[bip->bip_idx];
- bp->iv2 = bip->bip_vec[bip->bip_idx];
-
- bp->bip1.bip_vec = &bp->iv1;
- bp->bip2.bip_vec = &bp->iv2;
-
- bp->iv1.bv_len = sectors * bi->tuple_size;
- bp->iv2.bv_offset += sectors * bi->tuple_size;
- bp->iv2.bv_len -= sectors * bi->tuple_size;
-
- bp->bip1.bip_sector = bio->bi_integrity->bip_sector;
- bp->bip2.bip_sector = bio->bi_integrity->bip_sector + nr_sectors;
-
- bp->bip1.bip_vcnt = bp->bip2.bip_vcnt = 1;
- bp->bip1.bip_idx = bp->bip2.bip_idx = 0;
-}
-EXPORT_SYMBOL(bio_integrity_split);
-
-/**
* bio_integrity_clone - Callback for cloning bios with integrity metadata
* @bio: New bio
* @bio_src: Original bio
@@ -702,9 +611,8 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
memcpy(bip->bip_vec, bip_src->bip_vec,
bip_src->bip_vcnt * sizeof(struct bio_vec));
- bip->bip_sector = bip_src->bip_sector;
bip->bip_vcnt = bip_src->bip_vcnt;
- bip->bip_idx = bip_src->bip_idx;
+ bip->bip_iter = bip_src->bip_iter;
return 0;
}
diff --git a/fs/bio.c b/fs/bio.c
index 33d79a4eb92d..8754e7b6eb49 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -38,8 +38,6 @@
*/
#define BIO_INLINE_VECS 4
-static mempool_t *bio_split_pool __read_mostly;
-
/*
* if you change this list, also change bvec_alloc or things will
* break badly! cannot be bigger than what you can fit into an
@@ -273,6 +271,7 @@ void bio_init(struct bio *bio)
{
memset(bio, 0, sizeof(*bio));
bio->bi_flags = 1 << BIO_UPTODATE;
+ atomic_set(&bio->bi_remaining, 1);
atomic_set(&bio->bi_cnt, 1);
}
EXPORT_SYMBOL(bio_init);
@@ -295,9 +294,35 @@ void bio_reset(struct bio *bio)
memset(bio, 0, BIO_RESET_BYTES);
bio->bi_flags = flags|(1 << BIO_UPTODATE);
+ atomic_set(&bio->bi_remaining, 1);
}
EXPORT_SYMBOL(bio_reset);
+static void bio_chain_endio(struct bio *bio, int error)
+{
+ bio_endio(bio->bi_private, error);
+ bio_put(bio);
+}
+
+/**
+ * bio_chain - chain bio completions
+ *
+ * The caller won't have a bi_end_io called when @bio completes - instead,
+ * @parent's bi_end_io won't be called until both @parent and @bio have
+ * completed; the chained bio will also be freed when it completes.
+ *
+ * The caller must not set bi_private or bi_end_io in @bio.
+ */
+void bio_chain(struct bio *bio, struct bio *parent)
+{
+ BUG_ON(bio->bi_private || bio->bi_end_io);
+
+ bio->bi_private = parent;
+ bio->bi_end_io = bio_chain_endio;
+ atomic_inc(&parent->bi_remaining);
+}
+EXPORT_SYMBOL(bio_chain);
+
static void bio_alloc_rescue(struct work_struct *work)
{
struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
@@ -473,13 +498,13 @@ EXPORT_SYMBOL(bio_alloc_bioset);
void zero_fill_bio(struct bio *bio)
{
unsigned long flags;
- struct bio_vec *bv;
- int i;
+ struct bio_vec bv;
+ struct bvec_iter iter;
- bio_for_each_segment(bv, bio, i) {
- char *data = bvec_kmap_irq(bv, &flags);
- memset(data, 0, bv->bv_len);
- flush_dcache_page(bv->bv_page);
+ bio_for_each_segment(bv, bio, iter) {
+ char *data = bvec_kmap_irq(&bv, &flags);
+ memset(data, 0, bv.bv_len);
+ flush_dcache_page(bv.bv_page);
bvec_kunmap_irq(data, &flags);
}
}
@@ -515,51 +540,49 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
EXPORT_SYMBOL(bio_phys_segments);
/**
- * __bio_clone - clone a bio
+ * __bio_clone_fast - clone a bio that shares the original bio's biovec
* @bio: destination bio
* @bio_src: bio to clone
*
* Clone a &bio. Caller will own the returned bio, but not
* the actual data it points to. Reference count of returned
* bio will be one.
+ *
+ * Caller must ensure that @bio_src is not freed before @bio.
*/
-void __bio_clone(struct bio *bio, struct bio *bio_src)
+void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
{
- memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
- bio_src->bi_max_vecs * sizeof(struct bio_vec));
+ BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);
/*
* most users will be overriding ->bi_bdev with a new target,
* so we don't set nor calculate new physical/hw segment counts here
*/
- bio->bi_sector = bio_src->bi_sector;
bio->bi_bdev = bio_src->bi_bdev;
bio->bi_flags |= 1 << BIO_CLONED;
bio->bi_rw = bio_src->bi_rw;
- bio->bi_vcnt = bio_src->bi_vcnt;
- bio->bi_size = bio_src->bi_size;
- bio->bi_idx = bio_src->bi_idx;
+ bio->bi_iter = bio_src->bi_iter;
+ bio->bi_io_vec = bio_src->bi_io_vec;
}
-EXPORT_SYMBOL(__bio_clone);
+EXPORT_SYMBOL(__bio_clone_fast);
/**
- * bio_clone_bioset - clone a bio
+ * bio_clone_fast - clone a bio that shares the original bio's biovec
* @bio: bio to clone
* @gfp_mask: allocation priority
* @bs: bio_set to allocate from
*
- * Like __bio_clone, only also allocates the returned bio
+ * Like __bio_clone_fast, only also allocates the returned bio
*/
-struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
- struct bio_set *bs)
+struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
{
struct bio *b;
- b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, bs);
+ b = bio_alloc_bioset(gfp_mask, 0, bs);
if (!b)
return NULL;
- __bio_clone(b, bio);
+ __bio_clone_fast(b, bio);
if (bio_integrity(bio)) {
int ret;
@@ -574,6 +597,79 @@ struct bio *bio_clone_bioset(struct bio *bio, gfp_t gfp_mask,
return b;
}
+EXPORT_SYMBOL(bio_clone_fast);
+
+/**
+ * bio_clone_bioset - clone a bio
+ * @bio_src: bio to clone
+ * @gfp_mask: allocation priority
+ * @bs: bio_set to allocate from
+ *
+ * Clone bio. Caller will own the returned bio, but not the actual data it
+ * points to. Reference count of returned bio will be one.
+ */
+struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
+ struct bio_set *bs)
+{
+ struct bvec_iter iter;
+ struct bio_vec bv;
+ struct bio *bio;
+
+ /*
+ * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
+ * bio_src->bi_io_vec to bio->bi_io_vec.
+ *
+ * We can't do that anymore, because:
+ *
+ * - The point of cloning the biovec is to produce a bio with a biovec
+ * the caller can modify: bi_idx and bi_bvec_done should be 0.
+ *
+ * - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+ * we tried to clone the whole thing bio_alloc_bioset() would fail.
+ * But the clone should succeed as long as the number of biovecs we
+ * actually need to allocate is fewer than BIO_MAX_PAGES.
+ *
+ * - Lastly, bi_vcnt should not be looked at or relied upon by code
+ * that does not own the bio - reason being drivers don't use it for
+ * iterating over the biovec anymore, so expecting it to be kept up
+ * to date (i.e. for clones that share the parent biovec) is just
+ * asking for trouble and would force extra work on
+ * __bio_clone_fast() anyways.
+ */
+
+ bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
+ if (!bio)
+ return NULL;
+
+ bio->bi_bdev = bio_src->bi_bdev;
+ bio->bi_rw = bio_src->bi_rw;
+ bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector;
+ bio->bi_iter.bi_size = bio_src->bi_iter.bi_size;
+
+ if (bio->bi_rw & REQ_DISCARD)
+ goto integrity_clone;
+
+ if (bio->bi_rw & REQ_WRITE_SAME) {
+ bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+ goto integrity_clone;
+ }
+
+ bio_for_each_segment(bv, bio_src, iter)
+ bio->bi_io_vec[bio->bi_vcnt++] = bv;
+
+integrity_clone:
+ if (bio_integrity(bio_src)) {
+ int ret;
+
+ ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+ if (ret < 0) {
+ bio_put(bio);
+ return NULL;
+ }
+ }
+
+ return bio;
+}
EXPORT_SYMBOL(bio_clone_bioset);
/**
@@ -612,7 +708,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
if (unlikely(bio_flagged(bio, BIO_CLONED)))
return 0;
- if (((bio->bi_size + len) >> 9) > max_sectors)
+ if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
return 0;
/*
@@ -635,8 +731,9 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
simulate merging updated prev_bvec
as new bvec. */
.bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_sector,
- .bi_size = bio->bi_size - prev_bv_len,
+ .bi_sector = bio->bi_iter.bi_sector,
+ .bi_size = bio->bi_iter.bi_size -
+ prev_bv_len,
.bi_rw = bio->bi_rw,
};
@@ -684,8 +781,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
if (q->merge_bvec_fn) {
struct bvec_merge_data bvm = {
.bi_bdev = bio->bi_bdev,
- .bi_sector = bio->bi_sector,
- .bi_size = bio->bi_size,
+ .bi_sector = bio->bi_iter.bi_sector,
+ .bi_size = bio->bi_iter.bi_size,
.bi_rw = bio->bi_rw,
};
@@ -708,7 +805,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
bio->bi_vcnt++;
bio->bi_phys_segments++;
done:
- bio->bi_size += len;
+ bio->bi_iter.bi_size += len;
return len;
}
@@ -807,28 +904,7 @@ void bio_advance(struct bio *bio, unsigned bytes)
if (bio_integrity(bio))
bio_integrity_advance(bio, bytes);
- bio->bi_sector += bytes >> 9;
- bio->bi_size -= bytes;
-
- if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK)
- return;
-
- while (bytes) {
- if (unlikely(bio->bi_idx >= bio->bi_vcnt)) {
- WARN_ONCE(1, "bio idx %d >= vcnt %d\n",
- bio->bi_idx, bio->bi_vcnt);
- break;
- }
-
- if (bytes >= bio_iovec(bio)->bv_len) {
- bytes -= bio_iovec(bio)->bv_len;
- bio->bi_idx++;
- } else {
- bio_iovec(bio)->bv_len -= bytes;
- bio_iovec(bio)->bv_offset += bytes;
- bytes = 0;
- }
- }
+ bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(bio_advance);
@@ -874,117 +950,80 @@ EXPORT_SYMBOL(bio_alloc_pages);
*/
void bio_copy_data(struct bio *dst, struct bio *src)
{
- struct bio_vec *src_bv, *dst_bv;
- unsigned src_offset, dst_offset, bytes;
+ struct bvec_iter src_iter, dst_iter;
+ struct bio_vec src_bv, dst_bv;
void *src_p, *dst_p;
+ unsigned bytes;
- src_bv = bio_iovec(src);
- dst_bv = bio_iovec(dst);
-
- src_offset = src_bv->bv_offset;
- dst_offset = dst_bv->bv_offset;
+ src_iter = src->bi_iter;
+ dst_iter = dst->bi_iter;
while (1) {
- if (src_offset == src_bv->bv_offset + src_bv->bv_len) {
- src_bv++;
- if (src_bv == bio_iovec_idx(src, src->bi_vcnt)) {
- src = src->bi_next;
- if (!src)
- break;
-
- src_bv = bio_iovec(src);
- }
+ if (!src_iter.bi_size) {
+ src = src->bi_next;
+ if (!src)
+ break;
- src_offset = src_bv->bv_offset;
+ src_iter = src->bi_iter;
}
- if (dst_offset == dst_bv->bv_offset + dst_bv->bv_len) {
- dst_bv++;
- if (dst_bv == bio_iovec_idx(dst, dst->bi_vcnt)) {
- dst = dst->bi_next;
- if (!dst)
- break;
-
- dst_bv = bio_iovec(dst);
- }
+ if (!dst_iter.bi_size) {
+ dst = dst->bi_next;
+ if (!dst)
+ break;
- dst_offset = dst_bv->bv_offset;
+ dst_iter = dst->bi_iter;
}
- bytes = min(dst_bv->bv_offset + dst_bv->bv_len - dst_offset,
- src_bv->bv_offset + src_bv->bv_len - src_offset);
+ src_bv = bio_iter_iovec(src, src_iter);
+ dst_bv = bio_iter_iovec(dst, dst_iter);
- src_p = kmap_atomic(src_bv->bv_page);
- dst_p = kmap_atomic(dst_bv->bv_page);
+ bytes = min(src_bv.bv_len, dst_bv.bv_len);
- memcpy(dst_p + dst_offset,
- src_p + src_offset,
+ src_p = kmap_atomic(src_bv.bv_page);
+ dst_p = kmap_atomic(dst_bv.bv_page);
+
+ memcpy(dst_p + dst_bv.bv_offset,
+ src_p + src_bv.bv_offset,
bytes);
kunmap_atomic(dst_p);
kunmap_atomic(src_p);
- src_offset += bytes;
- dst_offset += bytes;
+ bio_advance_iter(src, &src_iter, bytes);
+ bio_advance_iter(dst, &dst_iter, bytes);
}
}
EXPORT_SYMBOL(bio_copy_data);
struct bio_map_data {
- struct bio_vec *iovecs;
- struct sg_iovec *sgvecs;
int nr_sgvecs;
int is_our_pages;
+ struct sg_iovec sgvecs[];
};
static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
struct sg_iovec *iov, int iov_count,
int is_our_pages)
{
- memcpy(bmd->iovecs, bio->bi_io_vec, sizeof(struct bio_vec) * bio->bi_vcnt);
memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
bmd->nr_sgvecs = iov_count;
bmd->is_our_pages = is_our_pages;
bio->bi_private = bmd;
}
-static void bio_free_map_data(struct bio_map_data *bmd)
-{
- kfree(bmd->iovecs);
- kfree(bmd->sgvecs);
- kfree(bmd);
-}
-
static struct bio_map_data *bio_alloc_map_data(int nr_segs,
unsigned int iov_count,
gfp_t gfp_mask)
{
- struct bio_map_data *bmd;
-
if (iov_count > UIO_MAXIOV)
return NULL;
- bmd = kmalloc(sizeof(*bmd), gfp_mask);
- if (!bmd)
- return NULL;
-
- bmd->iovecs = kmalloc(sizeof(struct bio_vec) * nr_segs, gfp_mask);
- if (!bmd->iovecs) {
- kfree(bmd);
- return NULL;
- }
-
- bmd->sgvecs = kmalloc(sizeof(struct sg_iovec) * iov_count, gfp_mask);
- if (bmd->sgvecs)
- return bmd;
-
- kfree(bmd->iovecs);
- kfree(bmd);
- return NULL;
+ return kmalloc(sizeof(struct bio_map_data) +
+ sizeof(struct sg_iovec) * iov_count, gfp_mask);
}
-static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
- struct sg_iovec *iov, int iov_count,
+static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
int to_user, int from_user, int do_free_page)
{
int ret = 0, i;
@@ -994,7 +1033,7 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
bio_for_each_segment_all(bvec, bio, i) {
char *bv_addr = page_address(bvec->bv_page);
- unsigned int bv_len = iovecs[i].bv_len;
+ unsigned int bv_len = bvec->bv_len;
while (bv_len && iov_idx < iov_count) {
unsigned int bytes;
@@ -1054,14 +1093,14 @@ int bio_uncopy_user(struct bio *bio)
* don't copy into a random user address space, just free.
*/
if (current->mm)
- ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
- bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+ ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
+ bio_data_dir(bio) == READ,
0, bmd->is_our_pages);
else if (bmd->is_our_pages)
bio_for_each_segment_all(bvec, bio, i)
__free_page(bvec->bv_page);
}
- bio_free_map_data(bmd);
+ kfree(bmd);
bio_put(bio);
return ret;
}
@@ -1175,7 +1214,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
*/
if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
(map_data && map_data->from_user)) {
- ret = __bio_copy_iov(bio, bio->bi_io_vec, iov, iov_count, 0, 1, 0);
+ ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
if (ret)
goto cleanup;
}
@@ -1189,7 +1228,7 @@ cleanup:
bio_put(bio);
out_bmd:
- bio_free_map_data(bmd);
+ kfree(bmd);
return ERR_PTR(ret);
}
@@ -1485,7 +1524,7 @@ struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
if (IS_ERR(bio))
return bio;
- if (bio->bi_size == len)
+ if (bio->bi_iter.bi_size == len)
return bio;
/*
@@ -1506,16 +1545,15 @@ static void bio_copy_kern_endio(struct bio *bio, int err)
bio_for_each_segment_all(bvec, bio, i) {
char *addr = page_address(bvec->bv_page);
- int len = bmd->iovecs[i].bv_len;
if (read)
- memcpy(p, addr, len);
+ memcpy(p, addr, bvec->bv_len);
__free_page(bvec->bv_page);
- p += len;
+ p += bvec->bv_len;
}
- bio_free_map_data(bmd);
+ kfree(bmd);
bio_put(bio);
}
@@ -1686,11 +1724,11 @@ void bio_check_pages_dirty(struct bio *bio)
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
void bio_flush_dcache_pages(struct bio *bi)
{
- int i;
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
- bio_for_each_segment(bvec, bi, i)
- flush_dcache_page(bvec->bv_page);
+ bio_for_each_segment(bvec, bi, iter)
+ flush_dcache_page(bvec.bv_page);
}
EXPORT_SYMBOL(bio_flush_dcache_pages);
#endif
@@ -1711,96 +1749,86 @@ EXPORT_SYMBOL(bio_flush_dcache_pages);
**/
void bio_endio(struct bio *bio, int error)
{
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
+ while (bio) {
+ BUG_ON(atomic_read(&bio->bi_remaining) <= 0);
- if (bio->bi_end_io)
- bio->bi_end_io(bio, error);
-}
-EXPORT_SYMBOL(bio_endio);
+ if (error)
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = -EIO;
-void bio_pair_release(struct bio_pair *bp)
-{
- if (atomic_dec_and_test(&bp->cnt)) {
- struct bio *master = bp->bio1.bi_private;
+ if (!atomic_dec_and_test(&bio->bi_remaining))
+ return;
- bio_endio(master, bp->error);
- mempool_free(bp, bp->bio2.bi_private);
+ /*
+ * Need to have a real endio function for chained bios,
+ * otherwise various corner cases will break (like stacking
+ * block devices that save/restore bi_end_io) - however, we want
+ * to avoid unbounded recursion and blowing the stack. Tail call
+ * optimization would handle this, but compiling with frame
+ * pointers also disables gcc's sibling call optimization.
+ */
+ if (bio->bi_end_io == bio_chain_endio) {
+ struct bio *parent = bio->bi_private;
+ bio_put(bio);
+ bio = parent;
+ } else {
+ if (bio->bi_end_io)
+ bio->bi_end_io(bio, error);
+ bio = NULL;
+ }
}
}
-EXPORT_SYMBOL(bio_pair_release);
-
-static void bio_pair_end_1(struct bio *bi, int err)
-{
- struct bio_pair *bp = container_of(bi, struct bio_pair, bio1);
-
- if (err)
- bp->error = err;
-
- bio_pair_release(bp);
-}
+EXPORT_SYMBOL(bio_endio);
-static void bio_pair_end_2(struct bio *bi, int err)
+/**
+ * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
+ * @bio: bio
+ * @error: error, if any
+ *
+ * For code that has saved and restored bi_end_io; thing hard before using this
+ * function, probably you should've cloned the entire bio.
+ **/
+void bio_endio_nodec(struct bio *bio, int error)
{
- struct bio_pair *bp = container_of(bi, struct bio_pair, bio2);
-
- if (err)
- bp->error = err;
-
- bio_pair_release(bp);
+ atomic_inc(&bio->bi_remaining);
+ bio_endio(bio, error);
}
+EXPORT_SYMBOL(bio_endio_nodec);
-/*
- * split a bio - only worry about a bio with a single page in its iovec
+/**
+ * bio_split - split a bio
+ * @bio: bio to split
+ * @sectors: number of sectors to split from the front of @bio
+ * @gfp: gfp mask
+ * @bs: bio set to allocate from
+ *
+ * Allocates and returns a new bio which represents @sectors from the start of
+ * @bio, and updates @bio to represent the remaining sectors.
+ *
+ * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
+ * responsibility to ensure that @bio is not freed before the split.
*/
-struct bio_pair *bio_split(struct bio *bi, int first_sectors)
+struct bio *bio_split(struct bio *bio, int sectors,
+ gfp_t gfp, struct bio_set *bs)
{
- struct bio_pair *bp = mempool_alloc(bio_split_pool, GFP_NOIO);
-
- if (!bp)
- return bp;
-
- trace_block_split(bdev_get_queue(bi->bi_bdev), bi,
- bi->bi_sector + first_sectors);
-
- BUG_ON(bio_segments(bi) > 1);
- atomic_set(&bp->cnt, 3);
- bp->error = 0;
- bp->bio1 = *bi;
- bp->bio2 = *bi;
- bp->bio2.bi_sector += first_sectors;
- bp->bio2.bi_size -= first_sectors << 9;
- bp->bio1.bi_size = first_sectors << 9;
-
- if (bi->bi_vcnt != 0) {
- bp->bv1 = *bio_iovec(bi);
- bp->bv2 = *bio_iovec(bi);
-
- if (bio_is_rw(bi)) {
- bp->bv2.bv_offset += first_sectors << 9;
- bp->bv2.bv_len -= first_sectors << 9;
- bp->bv1.bv_len = first_sectors << 9;
- }
+ struct bio *split = NULL;
- bp->bio1.bi_io_vec = &bp->bv1;
- bp->bio2.bi_io_vec = &bp->bv2;
+ BUG_ON(sectors <= 0);
+ BUG_ON(sectors >= bio_sectors(bio));
- bp->bio1.bi_max_vecs = 1;
- bp->bio2.bi_max_vecs = 1;
- }
+ split = bio_clone_fast(bio, gfp, bs);
+ if (!split)
+ return NULL;
- bp->bio1.bi_end_io = bio_pair_end_1;
- bp->bio2.bi_end_io = bio_pair_end_2;
+ split->bi_iter.bi_size = sectors << 9;
- bp->bio1.bi_private = bi;
- bp->bio2.bi_private = bio_split_pool;
+ if (bio_integrity(split))
+ bio_integrity_trim(split, 0, sectors);
- if (bio_integrity(bi))
- bio_integrity_split(bi, bp, first_sectors);
+ bio_advance(bio, split->bi_iter.bi_size);
- return bp;
+ return split;
}
EXPORT_SYMBOL(bio_split);
@@ -1814,80 +1842,20 @@ void bio_trim(struct bio *bio, int offset, int size)
{
/* 'bio' is a cloned bio which we need to trim to match
* the given offset and size.
- * This requires adjusting bi_sector, bi_size, and bi_io_vec
*/
- int i;
- struct bio_vec *bvec;
- int sofar = 0;
size <<= 9;
- if (offset == 0 && size == bio->bi_size)
+ if (offset == 0 && size == bio->bi_iter.bi_size)
return;
clear_bit(BIO_SEG_VALID, &bio->bi_flags);
bio_advance(bio, offset << 9);
- bio->bi_size = size;
-
- /* avoid any complications with bi_idx being non-zero*/
- if (bio->bi_idx) {
- memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
- (bio->bi_vcnt - bio->bi_idx) * sizeof(struct bio_vec));
- bio->bi_vcnt -= bio->bi_idx;
- bio->bi_idx = 0;
- }
- /* Make sure vcnt and last bv are not too big */
- bio_for_each_segment(bvec, bio, i) {
- if (sofar + bvec->bv_len > size)
- bvec->bv_len = size - sofar;
- if (bvec->bv_len == 0) {
- bio->bi_vcnt = i;
- break;
- }
- sofar += bvec->bv_len;
- }
+ bio->bi_iter.bi_size = size;
}
EXPORT_SYMBOL_GPL(bio_trim);
-/**
- * bio_sector_offset - Find hardware sector offset in bio
- * @bio: bio to inspect
- * @index: bio_vec index
- * @offset: offset in bv_page
- *
- * Return the number of hardware sectors between beginning of bio
- * and an end point indicated by a bio_vec index and an offset
- * within that vector's page.
- */
-sector_t bio_sector_offset(struct bio *bio, unsigned short index,
- unsigned int offset)
-{
- unsigned int sector_sz;
- struct bio_vec *bv;
- sector_t sectors;
- int i;
-
- sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue);
- sectors = 0;
-
- if (index >= bio->bi_idx)
- index = bio->bi_vcnt - 1;
-
- bio_for_each_segment_all(bv, bio, i) {
- if (i == index) {
- if (offset > bv->bv_offset)
- sectors += (offset - bv->bv_offset) / sector_sz;
- break;
- }
-
- sectors += bv->bv_len / sector_sz;
- }
-
- return sectors;
-}
-EXPORT_SYMBOL(bio_sector_offset);
-
/*
* create memory pools for biovec's in a bio_set.
* use the global biovec slabs created for general use.
@@ -2065,11 +2033,6 @@ static int __init init_bio(void)
if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
panic("bio: can't create integrity pool\n");
- bio_split_pool = mempool_create_kmalloc_pool(BIO_SPLIT_ENTRIES,
- sizeof(struct bio_pair));
- if (!bio_split_pool)
- panic("bio: can't create split pool\n");
-
return 0;
}
subsys_initcall(init_bio);
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index aa976eced2d2..a66768ebc8d1 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -1,6 +1,7 @@
config BTRFS_FS
tristate "Btrfs filesystem support"
- select LIBCRC32C
+ select CRYPTO
+ select CRYPTO_CRC32C
select ZLIB_INFLATE
select ZLIB_DEFLATE
select LZO_COMPRESS
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 1a44e42d602a..f341a98031d2 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -9,7 +9,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
export.o tree-log.o free-space-cache.o zlib.o lzo.o \
compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
reada.o backref.o ulist.o qgroup.o send.o dev-replace.o raid56.o \
- uuid-tree.o
+ uuid-tree.o props.o hash.o
btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o
btrfs-$(CONFIG_BTRFS_FS_CHECK_INTEGRITY) += check-integrity.o
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 3775947429b2..aded3ef3d3d4 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -66,6 +66,16 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
return 0;
}
+static void free_inode_elem_list(struct extent_inode_elem *eie)
+{
+ struct extent_inode_elem *eie_next;
+
+ for (; eie; eie = eie_next) {
+ eie_next = eie->next;
+ kfree(eie);
+ }
+}
+
static int find_extent_in_eb(struct extent_buffer *eb, u64 wanted_disk_byte,
u64 extent_item_pos,
struct extent_inode_elem **eie)
@@ -209,18 +219,19 @@ static int __add_prelim_ref(struct list_head *head, u64 root_id,
}
static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
- struct ulist *parents, int level,
- struct btrfs_key *key_for_search, u64 time_seq,
- u64 wanted_disk_byte,
- const u64 *extent_item_pos)
+ struct ulist *parents, struct __prelim_ref *ref,
+ int level, u64 time_seq, const u64 *extent_item_pos)
{
int ret = 0;
int slot;
struct extent_buffer *eb;
struct btrfs_key key;
+ struct btrfs_key *key_for_search = &ref->key_for_search;
struct btrfs_file_extent_item *fi;
struct extent_inode_elem *eie = NULL, *old = NULL;
u64 disk_byte;
+ u64 wanted_disk_byte = ref->wanted_disk_byte;
+ u64 count = 0;
if (level != 0) {
eb = path->nodes[level];
@@ -238,7 +249,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (path->slots[0] >= btrfs_header_nritems(path->nodes[0]))
ret = btrfs_next_old_leaf(root, path, time_seq);
- while (!ret) {
+ while (!ret && count < ref->count) {
eb = path->nodes[0];
slot = path->slots[0];
@@ -254,6 +265,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (disk_byte == wanted_disk_byte) {
eie = NULL;
old = NULL;
+ count++;
if (extent_item_pos) {
ret = check_extent_in_eb(&key, eb, fi,
*extent_item_pos,
@@ -273,6 +285,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
old = old->next;
old->next = eie;
}
+ eie = NULL;
}
next:
ret = btrfs_next_old_item(root, path, time_seq);
@@ -280,6 +293,8 @@ next:
if (ret > 0)
ret = 0;
+ else if (ret < 0)
+ free_inode_elem_list(eie);
return ret;
}
@@ -299,23 +314,34 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
int ret = 0;
int root_level;
int level = ref->level;
+ int index;
root_key.objectid = ref->root_id;
root_key.type = BTRFS_ROOT_ITEM_KEY;
root_key.offset = (u64)-1;
+
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
root = btrfs_read_fs_root_no_name(fs_info, &root_key);
if (IS_ERR(root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(root);
goto out;
}
root_level = btrfs_old_root_level(root, time_seq);
- if (root_level + 1 == level)
+ if (root_level + 1 == level) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
goto out;
+ }
path->lowest_level = level;
ret = btrfs_search_old_slot(root, &ref->key_for_search, path, time_seq);
+
+ /* root node has been locked, we can release @subvol_srcu safely here */
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+
pr_debug("search slot in root %llu (level %d, ref count %d) returned "
"%d for key (%llu %u %llu)\n",
ref->root_id, level, ref->count, ret,
@@ -334,9 +360,8 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
eb = path->nodes[level];
}
- ret = add_all_parents(root, path, parents, level, &ref->key_for_search,
- time_seq, ref->wanted_disk_byte,
- extent_item_pos);
+ ret = add_all_parents(root, path, parents, ref, level, time_seq,
+ extent_item_pos);
out:
path->lowest_level = 0;
btrfs_release_path(path);
@@ -376,10 +401,16 @@ static int __resolve_indirect_refs(struct btrfs_fs_info *fs_info,
continue;
err = __resolve_indirect_ref(fs_info, path, time_seq, ref,
parents, extent_item_pos);
- if (err == -ENOMEM)
- goto out;
- if (err)
+ /*
+ * we can only tolerate ENOENT,otherwise,we should catch error
+ * and return directly.
+ */
+ if (err == -ENOENT) {
continue;
+ } else if (err) {
+ ret = err;
+ goto out;
+ }
/* we put the first parent into the ref at hand */
ULIST_ITER_INIT(&uiter);
@@ -538,14 +569,13 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
if (extent_op && extent_op->update_key)
btrfs_disk_key_to_cpu(&op_key, &extent_op->key);
- while ((n = rb_prev(n))) {
+ spin_lock(&head->lock);
+ n = rb_first(&head->ref_root);
+ while (n) {
struct btrfs_delayed_ref_node *node;
node = rb_entry(n, struct btrfs_delayed_ref_node,
rb_node);
- if (node->bytenr != head->node.bytenr)
- break;
- WARN_ON(node->is_head);
-
+ n = rb_next(n);
if (node->seq > seq)
continue;
@@ -612,10 +642,10 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
WARN_ON(1);
}
if (ret)
- return ret;
+ break;
}
-
- return 0;
+ spin_unlock(&head->lock);
+ return ret;
}
/*
@@ -828,6 +858,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
struct list_head prefs_delayed;
struct list_head prefs;
struct __prelim_ref *ref;
+ struct extent_inode_elem *eie = NULL;
INIT_LIST_HEAD(&prefs);
INIT_LIST_HEAD(&prefs_delayed);
@@ -882,15 +913,15 @@ again:
btrfs_put_delayed_ref(&head->node);
goto again;
}
+ spin_unlock(&delayed_refs->lock);
ret = __add_delayed_refs(head, time_seq,
&prefs_delayed);
mutex_unlock(&head->mutex);
- if (ret) {
- spin_unlock(&delayed_refs->lock);
+ if (ret)
goto out;
- }
+ } else {
+ spin_unlock(&delayed_refs->lock);
}
- spin_unlock(&delayed_refs->lock);
}
if (path->slots[0]) {
@@ -941,7 +972,6 @@ again:
goto out;
}
if (ref->count && ref->parent) {
- struct extent_inode_elem *eie = NULL;
if (extent_item_pos && !ref->inode_list) {
u32 bsz;
struct extent_buffer *eb;
@@ -976,6 +1006,7 @@ again:
eie = eie->next;
eie->next = ref->inode_list;
}
+ eie = NULL;
}
list_del(&ref->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref);
@@ -994,7 +1025,8 @@ out:
list_del(&ref->list);
kmem_cache_free(btrfs_prelim_ref_cache, ref);
}
-
+ if (ret < 0)
+ free_inode_elem_list(eie);
return ret;
}
@@ -1002,7 +1034,6 @@ static void free_leaf_list(struct ulist *blocks)
{
struct ulist_node *node = NULL;
struct extent_inode_elem *eie;
- struct extent_inode_elem *eie_next;
struct ulist_iterator uiter;
ULIST_ITER_INIT(&uiter);
@@ -1010,10 +1041,7 @@ static void free_leaf_list(struct ulist *blocks)
if (!node->aux)
continue;
eie = (struct extent_inode_elem *)(uintptr_t)node->aux;
- for (; eie; eie = eie_next) {
- eie_next = eie->next;
- kfree(eie);
- }
+ free_inode_elem_list(eie);
node->aux = 0;
}
@@ -1101,44 +1129,13 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
if (!node)
break;
bytenr = node->val;
+ cond_resched();
}
ulist_free(tmp);
return 0;
}
-
-static int __inode_info(u64 inum, u64 ioff, u8 key_type,
- struct btrfs_root *fs_root, struct btrfs_path *path,
- struct btrfs_key *found_key)
-{
- int ret;
- struct btrfs_key key;
- struct extent_buffer *eb;
-
- key.type = key_type;
- key.objectid = inum;
- key.offset = ioff;
-
- ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
- if (ret < 0)
- return ret;
-
- eb = path->nodes[0];
- if (ret && path->slots[0] >= btrfs_header_nritems(eb)) {
- ret = btrfs_next_leaf(fs_root, path);
- if (ret)
- return ret;
- eb = path->nodes[0];
- }
-
- btrfs_item_key_to_cpu(eb, found_key, path->slots[0]);
- if (found_key->type != key.type || found_key->objectid != key.objectid)
- return 1;
-
- return 0;
-}
-
/*
* this makes the path point to (inum INODE_ITEM ioff)
*/
@@ -1146,16 +1143,16 @@ int inode_item_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
struct btrfs_path *path)
{
struct btrfs_key key;
- return __inode_info(inum, ioff, BTRFS_INODE_ITEM_KEY, fs_root, path,
- &key);
+ return btrfs_find_item(fs_root, path, inum, ioff,
+ BTRFS_INODE_ITEM_KEY, &key);
}
static int inode_ref_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
struct btrfs_path *path,
struct btrfs_key *found_key)
{
- return __inode_info(inum, ioff, BTRFS_INODE_REF_KEY, fs_root, path,
- found_key);
+ return btrfs_find_item(fs_root, path, inum, ioff,
+ BTRFS_INODE_REF_KEY, found_key);
}
int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
@@ -1335,20 +1332,45 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, path, 0, 0);
if (ret < 0)
return ret;
- ret = btrfs_previous_item(fs_info->extent_root, path,
- 0, BTRFS_EXTENT_ITEM_KEY);
- if (ret < 0)
- return ret;
- btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]);
+ while (1) {
+ u32 nritems;
+ if (path->slots[0] == 0) {
+ btrfs_set_path_blocking(path);
+ ret = btrfs_prev_leaf(fs_info->extent_root, path);
+ if (ret != 0) {
+ if (ret > 0) {
+ pr_debug("logical %llu is not within "
+ "any extent\n", logical);
+ ret = -ENOENT;
+ }
+ return ret;
+ }
+ } else {
+ path->slots[0]--;
+ }
+ nritems = btrfs_header_nritems(path->nodes[0]);
+ if (nritems == 0) {
+ pr_debug("logical %llu is not within any extent\n",
+ logical);
+ return -ENOENT;
+ }
+ if (path->slots[0] == nritems)
+ path->slots[0]--;
+
+ btrfs_item_key_to_cpu(path->nodes[0], found_key,
+ path->slots[0]);
+ if (found_key->type == BTRFS_EXTENT_ITEM_KEY ||
+ found_key->type == BTRFS_METADATA_ITEM_KEY)
+ break;
+ }
+
if (found_key->type == BTRFS_METADATA_ITEM_KEY)
size = fs_info->extent_root->leafsize;
else if (found_key->type == BTRFS_EXTENT_ITEM_KEY)
size = found_key->offset;
- if ((found_key->type != BTRFS_EXTENT_ITEM_KEY &&
- found_key->type != BTRFS_METADATA_ITEM_KEY) ||
- found_key->objectid > logical ||
+ if (found_key->objectid > logical ||
found_key->objectid + size <= logical) {
pr_debug("logical %llu is not within any extent\n", logical);
return -ENOENT;
@@ -1601,7 +1623,6 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root,
struct btrfs_key found_key;
while (!ret) {
- path->leave_spinning = 1;
ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path,
&found_key);
if (ret < 0)
@@ -1614,9 +1635,12 @@ static int iterate_inode_refs(u64 inum, struct btrfs_root *fs_root,
parent = found_key.offset;
slot = path->slots[0];
- eb = path->nodes[0];
- /* make sure we can use eb after releasing the path */
- atomic_inc(&eb->refs);
+ eb = btrfs_clone_extent_buffer(path->nodes[0]);
+ if (!eb) {
+ ret = -ENOMEM;
+ break;
+ }
+ extent_buffer_get(eb);
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
btrfs_release_path(path);
@@ -1674,17 +1698,20 @@ static int iterate_inode_extrefs(u64 inum, struct btrfs_root *fs_root,
++found;
slot = path->slots[0];
- eb = path->nodes[0];
- /* make sure we can use eb after releasing the path */
- atomic_inc(&eb->refs);
+ eb = btrfs_clone_extent_buffer(path->nodes[0]);
+ if (!eb) {
+ ret = -ENOMEM;
+ break;
+ }
+ extent_buffer_get(eb);
btrfs_tree_read_lock(eb);
btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
btrfs_release_path(path);
leaf = path->nodes[0];
- item_size = btrfs_item_size_nr(leaf, path->slots[0]);
- ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ item_size = btrfs_item_size_nr(leaf, slot);
+ ptr = btrfs_item_ptr_offset(leaf, slot);
cur_offset = 0;
while (cur_offset < item_size) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index ac0b39db27d1..8fed2125689e 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -43,6 +43,7 @@
#define BTRFS_INODE_COPY_EVERYTHING 8
#define BTRFS_INODE_IN_DELALLOC_LIST 9
#define BTRFS_INODE_READDIO_NEED_LOCK 10
+#define BTRFS_INODE_HAS_PROPS 11
/* in memory btrfs inode */
struct btrfs_inode {
@@ -135,6 +136,9 @@ struct btrfs_inode {
*/
u64 index_cnt;
+ /* Cache the directory index number to speed the dir/file remove */
+ u64 dir_index;
+
/* the fsync log has some corner cases that mean we have to check
* directories to see if any unlinks have been done before
* the directory was logged. See tree-log.c for all the
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 131d82800b3a..0e8388e72d8d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -92,11 +92,11 @@
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/mutex.h>
-#include <linux/crc32c.h>
#include <linux/genhd.h>
#include <linux/blkdev.h>
#include "ctree.h"
#include "disk-io.h"
+#include "hash.h"
#include "transaction.h"
#include "extent_io.h"
#include "volumes.h"
@@ -1456,10 +1456,14 @@ static int btrfsic_handle_extent_data(
btrfsic_read_from_block_data(block_ctx, &file_extent_item,
file_extent_item_offset,
sizeof(struct btrfs_file_extent_item));
- next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item) +
- btrfs_stack_file_extent_offset(&file_extent_item);
- generation = btrfs_stack_file_extent_generation(&file_extent_item);
- num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item);
+ next_bytenr = btrfs_stack_file_extent_disk_bytenr(&file_extent_item);
+ if (btrfs_stack_file_extent_compression(&file_extent_item) ==
+ BTRFS_COMPRESS_NONE) {
+ next_bytenr += btrfs_stack_file_extent_offset(&file_extent_item);
+ num_bytes = btrfs_stack_file_extent_num_bytes(&file_extent_item);
+ } else {
+ num_bytes = btrfs_stack_file_extent_disk_num_bytes(&file_extent_item);
+ }
generation = btrfs_stack_file_extent_generation(&file_extent_item);
if (state->print_mask & BTRFSIC_PRINT_MASK_VERY_VERBOSE)
@@ -1695,7 +1699,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
return -1;
}
bio->bi_bdev = block_ctx->dev->bdev;
- bio->bi_sector = dev_bytenr >> 9;
+ bio->bi_iter.bi_sector = dev_bytenr >> 9;
for (j = i; j < num_pages; j++) {
ret = bio_add_page(bio, block_ctx->pagev[j],
@@ -1819,7 +1823,7 @@ static int btrfsic_test_for_metadata(struct btrfsic_state *state,
size_t sublen = i ? PAGE_CACHE_SIZE :
(PAGE_CACHE_SIZE - BTRFS_CSUM_SIZE);
- crc = crc32c(crc, data, sublen);
+ crc = btrfs_crc32c(crc, data, sublen);
}
btrfs_csum_final(crc, csum);
if (memcmp(csum, h->csum, state->csum_size))
@@ -3013,7 +3017,7 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
int bio_is_patched;
char **mapped_datav;
- dev_bytenr = 512 * bio->bi_sector;
+ dev_bytenr = 512 * bio->bi_iter.bi_sector;
bio_is_patched = 0;
if (dev_state->state->print_mask &
BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
@@ -3021,8 +3025,8 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
"submit_bio(rw=0x%x, bi_vcnt=%u,"
" bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
rw, bio->bi_vcnt,
- (unsigned long long)bio->bi_sector, dev_bytenr,
- bio->bi_bdev);
+ (unsigned long long)bio->bi_iter.bi_sector,
+ dev_bytenr, bio->bi_bdev);
mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt,
GFP_NOFS);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 1499b27b4186..b01fb6c527e3 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -128,11 +128,10 @@ static int check_compressed_csum(struct inode *inode,
kunmap_atomic(kaddr);
if (csum != *cb_sum) {
- printk(KERN_INFO "btrfs csum failed ino %llu "
- "extent %llu csum %u "
- "wanted %u mirror %d\n",
- btrfs_ino(inode), disk_start, csum, *cb_sum,
- cb->mirror_num);
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "csum failed ino %llu extent %llu csum %u wanted %u mirror %d",
+ btrfs_ino(inode), disk_start, csum, *cb_sum,
+ cb->mirror_num);
ret = -EIO;
goto fail;
}
@@ -172,7 +171,8 @@ static void end_compressed_bio_read(struct bio *bio, int err)
goto out;
inode = cb->inode;
- ret = check_compressed_csum(inode, cb, (u64)bio->bi_sector << 9);
+ ret = check_compressed_csum(inode, cb,
+ (u64)bio->bi_iter.bi_sector << 9);
if (ret)
goto csum_failed;
@@ -201,18 +201,16 @@ csum_failed:
if (cb->errors) {
bio_io_error(cb->orig_bio);
} else {
- int bio_index = 0;
- struct bio_vec *bvec = cb->orig_bio->bi_io_vec;
+ int i;
+ struct bio_vec *bvec;
/*
* we have verified the checksum already, set page
* checked so the end_io handlers know about it
*/
- while (bio_index < cb->orig_bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, cb->orig_bio, i)
SetPageChecked(bvec->bv_page);
- bvec++;
- bio_index++;
- }
+
bio_endio(cb->orig_bio, 0);
}
@@ -372,7 +370,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
page = compressed_pages[pg_index];
page->mapping = inode->i_mapping;
- if (bio->bi_size)
+ if (bio->bi_iter.bi_size)
ret = io_tree->ops->merge_bio_hook(WRITE, page, 0,
PAGE_CACHE_SIZE,
bio, 0);
@@ -412,7 +410,8 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
}
if (bytes_left < PAGE_CACHE_SIZE) {
- printk("bytes left %lu compress len %lu nr %lu\n",
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "bytes left %lu compress len %lu nr %lu",
bytes_left, cb->compressed_len, cb->nr_pages);
}
bytes_left -= PAGE_CACHE_SIZE;
@@ -506,7 +505,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
if (!em || last_offset < em->start ||
(last_offset + PAGE_CACHE_SIZE > extent_map_end(em)) ||
- (em->block_start >> 9) != cb->orig_bio->bi_sector) {
+ (em->block_start >> 9) != cb->orig_bio->bi_iter.bi_sector) {
free_extent_map(em);
unlock_extent(tree, last_offset, end);
unlock_page(page);
@@ -552,7 +551,7 @@ next:
* in it. We don't actually do IO on those pages but allocate new ones
* to hold the compressed pages on disk.
*
- * bio->bi_sector points to the compressed extent on disk
+ * bio->bi_iter.bi_sector points to the compressed extent on disk
* bio->bi_io_vec points to all of the inode pages
* bio->bi_vcnt is a count of pages
*
@@ -573,7 +572,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
struct page *page;
struct block_device *bdev;
struct bio *comp_bio;
- u64 cur_disk_byte = (u64)bio->bi_sector << 9;
+ u64 cur_disk_byte = (u64)bio->bi_iter.bi_sector << 9;
u64 em_len;
u64 em_start;
struct extent_map *em;
@@ -659,7 +658,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
page->mapping = inode->i_mapping;
page->index = em_start >> PAGE_CACHE_SHIFT;
- if (comp_bio->bi_size)
+ if (comp_bio->bi_iter.bi_size)
ret = tree->ops->merge_bio_hook(READ, page, 0,
PAGE_CACHE_SIZE,
comp_bio, 0);
@@ -687,8 +686,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
comp_bio, sums);
BUG_ON(ret); /* -ENOMEM */
}
- sums += (comp_bio->bi_size + root->sectorsize - 1) /
- root->sectorsize;
+ sums += (comp_bio->bi_iter.bi_size +
+ root->sectorsize - 1) / root->sectorsize;
ret = btrfs_map_bio(root, READ, comp_bio,
mirror_num, 0);
@@ -1011,6 +1010,8 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
bytes = min(bytes, working_bytes);
kaddr = kmap_atomic(page_out);
memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+ if (*pg_index == (vcnt - 1) && *pg_offset == 0)
+ memset(kaddr + bytes, 0, PAGE_CACHE_SIZE - bytes);
kunmap_atomic(kaddr);
flush_dcache_page(page_out);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 316136bd6dd7..cbd3a7d6fa68 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -39,9 +39,8 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
struct extent_buffer *src_buf);
static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
int level, int slot);
-static void tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+static int tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb);
-static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
struct btrfs_path *btrfs_alloc_path(void)
{
@@ -475,6 +474,8 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
* the index is the shifted logical of the *new* root node for root replace
* operations, or the shifted logical of the affected block for all other
* operations.
+ *
+ * Note: must be called with write lock (tree_mod_log_write_lock).
*/
static noinline int
__tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
@@ -483,24 +484,9 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
struct rb_node **new;
struct rb_node *parent = NULL;
struct tree_mod_elem *cur;
- int ret = 0;
BUG_ON(!tm);
- tree_mod_log_write_lock(fs_info);
- if (list_empty(&fs_info->tree_mod_seq_list)) {
- tree_mod_log_write_unlock(fs_info);
- /*
- * Ok we no longer care about logging modifications, free up tm
- * and return 0. Any callers shouldn't be using tm after
- * calling tree_mod_log_insert, but if they do we can just
- * change this to return a special error code to let the callers
- * do their own thing.
- */
- kfree(tm);
- return 0;
- }
-
spin_lock(&fs_info->tree_mod_seq_lock);
tm->seq = btrfs_inc_tree_mod_seq_minor(fs_info);
spin_unlock(&fs_info->tree_mod_seq_lock);
@@ -518,18 +504,13 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
new = &((*new)->rb_left);
else if (cur->seq > tm->seq)
new = &((*new)->rb_right);
- else {
- ret = -EEXIST;
- kfree(tm);
- goto out;
- }
+ else
+ return -EEXIST;
}
rb_link_node(&tm->node, parent, new);
rb_insert_color(&tm->node, tm_root);
-out:
- tree_mod_log_write_unlock(fs_info);
- return ret;
+ return 0;
}
/*
@@ -545,19 +526,38 @@ static inline int tree_mod_dont_log(struct btrfs_fs_info *fs_info,
return 1;
if (eb && btrfs_header_level(eb) == 0)
return 1;
+
+ tree_mod_log_write_lock(fs_info);
+ if (list_empty(&(fs_info)->tree_mod_seq_list)) {
+ tree_mod_log_write_unlock(fs_info);
+ return 1;
+ }
+
return 0;
}
-static inline int
-__tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb, int slot,
- enum mod_log_op op, gfp_t flags)
+/* Similar to tree_mod_dont_log, but doesn't acquire any locks. */
+static inline int tree_mod_need_log(const struct btrfs_fs_info *fs_info,
+ struct extent_buffer *eb)
+{
+ smp_mb();
+ if (list_empty(&(fs_info)->tree_mod_seq_list))
+ return 0;
+ if (eb && btrfs_header_level(eb) == 0)
+ return 0;
+
+ return 1;
+}
+
+static struct tree_mod_elem *
+alloc_tree_mod_elem(struct extent_buffer *eb, int slot,
+ enum mod_log_op op, gfp_t flags)
{
struct tree_mod_elem *tm;
tm = kzalloc(sizeof(*tm), flags);
if (!tm)
- return -ENOMEM;
+ return NULL;
tm->index = eb->start >> PAGE_CACHE_SHIFT;
if (op != MOD_LOG_KEY_ADD) {
@@ -567,8 +567,9 @@ __tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
tm->op = op;
tm->slot = slot;
tm->generation = btrfs_node_ptr_generation(eb, slot);
+ RB_CLEAR_NODE(&tm->node);
- return __tree_mod_log_insert(fs_info, tm);
+ return tm;
}
static noinline int
@@ -576,10 +577,27 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int slot,
enum mod_log_op op, gfp_t flags)
{
- if (tree_mod_dont_log(fs_info, eb))
+ struct tree_mod_elem *tm;
+ int ret;
+
+ if (!tree_mod_need_log(fs_info, eb))
return 0;
- return __tree_mod_log_insert_key(fs_info, eb, slot, op, flags);
+ tm = alloc_tree_mod_elem(eb, slot, op, flags);
+ if (!tm)
+ return -ENOMEM;
+
+ if (tree_mod_dont_log(fs_info, eb)) {
+ kfree(tm);
+ return 0;
+ }
+
+ ret = __tree_mod_log_insert(fs_info, tm);
+ tree_mod_log_write_unlock(fs_info);
+ if (ret)
+ kfree(tm);
+
+ return ret;
}
static noinline int
@@ -587,53 +605,95 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
struct extent_buffer *eb, int dst_slot, int src_slot,
int nr_items, gfp_t flags)
{
- struct tree_mod_elem *tm;
- int ret;
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int ret = 0;
int i;
+ int locked = 0;
- if (tree_mod_dont_log(fs_info, eb))
+ if (!tree_mod_need_log(fs_info, eb))
return 0;
+ tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags);
+ if (!tm_list)
+ return -ENOMEM;
+
+ tm = kzalloc(sizeof(*tm), flags);
+ if (!tm) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ tm->index = eb->start >> PAGE_CACHE_SHIFT;
+ tm->slot = src_slot;
+ tm->move.dst_slot = dst_slot;
+ tm->move.nr_items = nr_items;
+ tm->op = MOD_LOG_MOVE_KEYS;
+
+ for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
+ tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
+ MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
+ if (tree_mod_dont_log(fs_info, eb))
+ goto free_tms;
+ locked = 1;
+
/*
* When we override something during the move, we log these removals.
* This can only happen when we move towards the beginning of the
* buffer, i.e. dst_slot < src_slot.
*/
for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
- ret = __tree_mod_log_insert_key(fs_info, eb, i + dst_slot,
- MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
- BUG_ON(ret < 0);
+ ret = __tree_mod_log_insert(fs_info, tm_list[i]);
+ if (ret)
+ goto free_tms;
}
- tm = kzalloc(sizeof(*tm), flags);
- if (!tm)
- return -ENOMEM;
+ ret = __tree_mod_log_insert(fs_info, tm);
+ if (ret)
+ goto free_tms;
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
- tm->index = eb->start >> PAGE_CACHE_SHIFT;
- tm->slot = src_slot;
- tm->move.dst_slot = dst_slot;
- tm->move.nr_items = nr_items;
- tm->op = MOD_LOG_MOVE_KEYS;
+ return 0;
+free_tms:
+ for (i = 0; i < nr_items; i++) {
+ if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
+ rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
+ kfree(tm_list[i]);
+ }
+ if (locked)
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
+ kfree(tm);
- return __tree_mod_log_insert(fs_info, tm);
+ return ret;
}
-static inline void
-__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
+static inline int
+__tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
+ struct tree_mod_elem **tm_list,
+ int nritems)
{
- int i;
- u32 nritems;
+ int i, j;
int ret;
- if (btrfs_header_level(eb) == 0)
- return;
-
- nritems = btrfs_header_nritems(eb);
for (i = nritems - 1; i >= 0; i--) {
- ret = __tree_mod_log_insert_key(fs_info, eb, i,
- MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
- BUG_ON(ret < 0);
+ ret = __tree_mod_log_insert(fs_info, tm_list[i]);
+ if (ret) {
+ for (j = nritems - 1; j > i; j--)
+ rb_erase(&tm_list[j]->node,
+ &fs_info->tree_mod_log);
+ return ret;
+ }
}
+
+ return 0;
}
static noinline int
@@ -642,17 +702,38 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
struct extent_buffer *new_root, gfp_t flags,
int log_removal)
{
- struct tree_mod_elem *tm;
+ struct tree_mod_elem *tm = NULL;
+ struct tree_mod_elem **tm_list = NULL;
+ int nritems = 0;
+ int ret = 0;
+ int i;
- if (tree_mod_dont_log(fs_info, NULL))
+ if (!tree_mod_need_log(fs_info, NULL))
return 0;
- if (log_removal)
- __tree_mod_log_free_eb(fs_info, old_root);
+ if (log_removal && btrfs_header_level(old_root) > 0) {
+ nritems = btrfs_header_nritems(old_root);
+ tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
+ flags);
+ if (!tm_list) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ for (i = 0; i < nritems; i++) {
+ tm_list[i] = alloc_tree_mod_elem(old_root, i,
+ MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+ }
tm = kzalloc(sizeof(*tm), flags);
- if (!tm)
- return -ENOMEM;
+ if (!tm) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
tm->index = new_root->start >> PAGE_CACHE_SHIFT;
tm->old_root.logical = old_root->start;
@@ -660,7 +741,30 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
tm->generation = btrfs_header_generation(old_root);
tm->op = MOD_LOG_ROOT_REPLACE;
- return __tree_mod_log_insert(fs_info, tm);
+ if (tree_mod_dont_log(fs_info, NULL))
+ goto free_tms;
+
+ if (tm_list)
+ ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
+ if (!ret)
+ ret = __tree_mod_log_insert(fs_info, tm);
+
+ tree_mod_log_write_unlock(fs_info);
+ if (ret)
+ goto free_tms;
+ kfree(tm_list);
+
+ return ret;
+
+free_tms:
+ if (tm_list) {
+ for (i = 0; i < nritems; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+ }
+ kfree(tm);
+
+ return ret;
}
static struct tree_mod_elem *
@@ -729,31 +833,75 @@ tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq)
return __tree_mod_log_search(fs_info, start, min_seq, 0);
}
-static noinline void
+static noinline int
tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
struct extent_buffer *src, unsigned long dst_offset,
unsigned long src_offset, int nr_items)
{
- int ret;
+ int ret = 0;
+ struct tree_mod_elem **tm_list = NULL;
+ struct tree_mod_elem **tm_list_add, **tm_list_rem;
int i;
+ int locked = 0;
- if (tree_mod_dont_log(fs_info, NULL))
- return;
+ if (!tree_mod_need_log(fs_info, NULL))
+ return 0;
if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
- return;
+ return 0;
+
+ tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *),
+ GFP_NOFS);
+ if (!tm_list)
+ return -ENOMEM;
+ tm_list_add = tm_list;
+ tm_list_rem = tm_list + nr_items;
for (i = 0; i < nr_items; i++) {
- ret = __tree_mod_log_insert_key(fs_info, src,
- i + src_offset,
- MOD_LOG_KEY_REMOVE, GFP_NOFS);
- BUG_ON(ret < 0);
- ret = __tree_mod_log_insert_key(fs_info, dst,
- i + dst_offset,
- MOD_LOG_KEY_ADD,
- GFP_NOFS);
- BUG_ON(ret < 0);
+ tm_list_rem[i] = alloc_tree_mod_elem(src, i + src_offset,
+ MOD_LOG_KEY_REMOVE, GFP_NOFS);
+ if (!tm_list_rem[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+
+ tm_list_add[i] = alloc_tree_mod_elem(dst, i + dst_offset,
+ MOD_LOG_KEY_ADD, GFP_NOFS);
+ if (!tm_list_add[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
}
+
+ if (tree_mod_dont_log(fs_info, NULL))
+ goto free_tms;
+ locked = 1;
+
+ for (i = 0; i < nr_items; i++) {
+ ret = __tree_mod_log_insert(fs_info, tm_list_rem[i]);
+ if (ret)
+ goto free_tms;
+ ret = __tree_mod_log_insert(fs_info, tm_list_add[i]);
+ if (ret)
+ goto free_tms;
+ }
+
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
+
+ return 0;
+
+free_tms:
+ for (i = 0; i < nr_items * 2; i++) {
+ if (tm_list[i] && !RB_EMPTY_NODE(&tm_list[i]->node))
+ rb_erase(&tm_list[i]->node, &fs_info->tree_mod_log);
+ kfree(tm_list[i]);
+ }
+ if (locked)
+ tree_mod_log_write_unlock(fs_info);
+ kfree(tm_list);
+
+ return ret;
}
static inline void
@@ -772,18 +920,58 @@ tree_mod_log_set_node_key(struct btrfs_fs_info *fs_info,
{
int ret;
- ret = __tree_mod_log_insert_key(fs_info, eb, slot,
+ ret = tree_mod_log_insert_key(fs_info, eb, slot,
MOD_LOG_KEY_REPLACE,
atomic ? GFP_ATOMIC : GFP_NOFS);
BUG_ON(ret < 0);
}
-static noinline void
+static noinline int
tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
{
+ struct tree_mod_elem **tm_list = NULL;
+ int nritems = 0;
+ int i;
+ int ret = 0;
+
+ if (btrfs_header_level(eb) == 0)
+ return 0;
+
+ if (!tree_mod_need_log(fs_info, NULL))
+ return 0;
+
+ nritems = btrfs_header_nritems(eb);
+ tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
+ GFP_NOFS);
+ if (!tm_list)
+ return -ENOMEM;
+
+ for (i = 0; i < nritems; i++) {
+ tm_list[i] = alloc_tree_mod_elem(eb, i,
+ MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
+ if (!tm_list[i]) {
+ ret = -ENOMEM;
+ goto free_tms;
+ }
+ }
+
if (tree_mod_dont_log(fs_info, eb))
- return;
- __tree_mod_log_free_eb(fs_info, eb);
+ goto free_tms;
+
+ ret = __tree_mod_log_free_eb(fs_info, tm_list, nritems);
+ tree_mod_log_write_unlock(fs_info);
+ if (ret)
+ goto free_tms;
+ kfree(tm_list);
+
+ return 0;
+
+free_tms:
+ for (i = 0; i < nritems; i++)
+ kfree(tm_list[i]);
+ kfree(tm_list);
+
+ return ret;
}
static noinline void
@@ -1041,8 +1229,13 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
btrfs_set_node_ptr_generation(parent, parent_slot,
trans->transid);
btrfs_mark_buffer_dirty(parent);
- if (last_ref)
- tree_mod_log_free_eb(root->fs_info, buf);
+ if (last_ref) {
+ ret = tree_mod_log_free_eb(root->fs_info, buf);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
+ }
+ }
btrfs_free_tree_block(trans, root, buf, parent_start,
last_ref);
}
@@ -1287,8 +1480,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
old = read_tree_block(root, logical, blocksize, 0);
if (WARN_ON(!old || !extent_buffer_uptodate(old))) {
free_extent_buffer(old);
- pr_warn("btrfs: failed to read tree block %llu from get_old_root\n",
- logical);
+ btrfs_warn(root->fs_info,
+ "failed to read tree block %llu from get_old_root", logical);
} else {
eb = btrfs_clone_extent_buffer(old);
free_extent_buffer(old);
@@ -2462,6 +2655,49 @@ static int key_search(struct extent_buffer *b, struct btrfs_key *key,
return 0;
}
+int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *found_path,
+ u64 iobjectid, u64 ioff, u8 key_type,
+ struct btrfs_key *found_key)
+{
+ int ret;
+ struct btrfs_key key;
+ struct extent_buffer *eb;
+ struct btrfs_path *path;
+
+ key.type = key_type;
+ key.objectid = iobjectid;
+ key.offset = ioff;
+
+ if (found_path == NULL) {
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ } else
+ path = found_path;
+
+ ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
+ if ((ret < 0) || (found_key == NULL)) {
+ if (path != found_path)
+ btrfs_free_path(path);
+ return ret;
+ }
+
+ eb = path->nodes[0];
+ if (ret && path->slots[0] >= btrfs_header_nritems(eb)) {
+ ret = btrfs_next_leaf(fs_root, path);
+ if (ret)
+ return ret;
+ eb = path->nodes[0];
+ }
+
+ btrfs_item_key_to_cpu(eb, found_key, path->slots[0]);
+ if (found_key->type != key.type ||
+ found_key->objectid != key.objectid)
+ return 1;
+
+ return 0;
+}
+
/*
* look for key in the tree. path is filled in with nodes along the way
* if key is found, we return zero and you can find the item in the leaf
@@ -2495,6 +2731,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
lowest_level = p->lowest_level;
WARN_ON(lowest_level && ins_len > 0);
WARN_ON(p->nodes[0] != NULL);
+ BUG_ON(!cow && ins_len);
if (ins_len < 0) {
lowest_unlock = 2;
@@ -2603,8 +2840,6 @@ again:
}
}
cow_done:
- BUG_ON(!cow && ins_len);
-
p->nodes[level] = b;
btrfs_clear_path_blocking(p, NULL, 0);
@@ -2614,13 +2849,19 @@ cow_done:
* It is safe to drop the lock on our parent before we
* go through the expensive btree search on b.
*
- * If cow is true, then we might be changing slot zero,
- * which may require changing the parent. So, we can't
- * drop the lock until after we know which slot we're
- * operating on.
+ * If we're inserting or deleting (ins_len != 0), then we might
+ * be changing slot zero, which may require changing the parent.
+ * So, we can't drop the lock until after we know which slot
+ * we're operating on.
*/
- if (!cow)
- btrfs_unlock_up_safe(p, level + 1);
+ if (!ins_len && !p->keep_locks) {
+ int u = level + 1;
+
+ if (u < BTRFS_MAX_LEVEL && p->locks[u]) {
+ btrfs_tree_unlock_rw(p->nodes[u], p->locks[u]);
+ p->locks[u] = 0;
+ }
+ }
ret = key_search(b, key, level, &prev_cmp, &slot);
@@ -2648,7 +2889,7 @@ cow_done:
* which means we must have a write lock
* on the parent
*/
- if (slot == 0 && cow &&
+ if (slot == 0 && ins_len &&
write_lock_level < level + 1) {
write_lock_level = level + 1;
btrfs_release_path(p);
@@ -2901,7 +3142,9 @@ again:
if (ret < 0)
return ret;
if (!ret) {
- p->slots[0] = btrfs_header_nritems(leaf) - 1;
+ leaf = p->nodes[0];
+ if (p->slots[0] == btrfs_header_nritems(leaf))
+ p->slots[0]--;
return 0;
}
if (!return_any)
@@ -3022,8 +3265,12 @@ static int push_node_left(struct btrfs_trans_handle *trans,
} else
push_items = min(src_nritems - 8, push_items);
- tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0,
- push_items);
+ ret = tree_mod_log_eb_copy(root->fs_info, dst, src, dst_nritems, 0,
+ push_items);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
+ }
copy_extent_buffer(dst, src,
btrfs_node_key_ptr_offset(dst_nritems),
btrfs_node_key_ptr_offset(0),
@@ -3093,8 +3340,12 @@ static int balance_node_right(struct btrfs_trans_handle *trans,
(dst_nritems) *
sizeof(struct btrfs_key_ptr));
- tree_mod_log_eb_copy(root->fs_info, dst, src, 0,
- src_nritems - push_items, push_items);
+ ret = tree_mod_log_eb_copy(root->fs_info, dst, src, 0,
+ src_nritems - push_items, push_items);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
+ }
copy_extent_buffer(dst, src,
btrfs_node_key_ptr_offset(0),
btrfs_node_key_ptr_offset(src_nritems - push_items),
@@ -3295,7 +3546,12 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
btrfs_header_chunk_tree_uuid(split),
BTRFS_UUID_SIZE);
- tree_mod_log_eb_copy(root->fs_info, split, c, 0, mid, c_nritems - mid);
+ ret = tree_mod_log_eb_copy(root->fs_info, split, c, 0,
+ mid, c_nritems - mid);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
+ }
copy_extent_buffer(split, c,
btrfs_node_key_ptr_offset(0),
btrfs_node_key_ptr_offset(mid),
@@ -3362,8 +3618,8 @@ noinline int btrfs_leaf_free_space(struct btrfs_root *root,
int ret;
ret = BTRFS_LEAF_DATA_SIZE(root) - leaf_space_used(leaf, 0, nritems);
if (ret < 0) {
- printk(KERN_CRIT "leaf free space ret %d, leaf data size %lu, "
- "used %d nritems %d\n",
+ btrfs_crit(root->fs_info,
+ "leaf free space ret %d, leaf data size %lu, used %d nritems %d",
ret, (unsigned long) BTRFS_LEAF_DATA_SIZE(root),
leaf_space_used(leaf, 0, nritems), nritems);
}
@@ -3571,6 +3827,19 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
if (left_nritems == 0)
goto out_unlock;
+ if (path->slots[0] == left_nritems && !empty) {
+ /* Key greater than all keys in the leaf, right neighbor has
+ * enough room for it and we're not emptying our leaf to delete
+ * it, therefore use right neighbor to insert the new item and
+ * no need to touch/dirty our left leaft. */
+ btrfs_tree_unlock(left);
+ free_extent_buffer(left);
+ path->nodes[0] = right;
+ path->slots[0] = 0;
+ path->slots[1]++;
+ return 0;
+ }
+
return __push_leaf_right(trans, root, path, min_data_size, empty,
right, free_space, left_nritems, min_slot);
out_unlock:
@@ -3887,14 +4156,17 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
int progress = 0;
int slot;
u32 nritems;
+ int space_needed = data_size;
slot = path->slots[0];
+ if (slot < btrfs_header_nritems(path->nodes[0]))
+ space_needed -= btrfs_leaf_free_space(root, path->nodes[0]);
/*
* try to push all the items after our slot into the
* right leaf
*/
- ret = push_leaf_right(trans, root, path, 1, data_size, 0, slot);
+ ret = push_leaf_right(trans, root, path, 1, space_needed, 0, slot);
if (ret < 0)
return ret;
@@ -3914,7 +4186,7 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
/* try to push all the items before our slot into the next leaf */
slot = path->slots[0];
- ret = push_leaf_left(trans, root, path, 1, data_size, 0, slot);
+ ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot);
if (ret < 0)
return ret;
@@ -3958,13 +4230,18 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
/* first try to make some room by pushing left and right */
if (data_size && path->nodes[1]) {
- wret = push_leaf_right(trans, root, path, data_size,
- data_size, 0, 0);
+ int space_needed = data_size;
+
+ if (slot < btrfs_header_nritems(l))
+ space_needed -= btrfs_leaf_free_space(root, l);
+
+ wret = push_leaf_right(trans, root, path, space_needed,
+ space_needed, 0, 0);
if (wret < 0)
return wret;
if (wret) {
- wret = push_leaf_left(trans, root, path, data_size,
- data_size, 0, (u32)-1);
+ wret = push_leaf_left(trans, root, path, space_needed,
+ space_needed, 0, (u32)-1);
if (wret < 0)
return wret;
}
@@ -4432,7 +4709,7 @@ void btrfs_extend_item(struct btrfs_root *root, struct btrfs_path *path,
BUG_ON(slot < 0);
if (slot >= nritems) {
btrfs_print_leaf(root, leaf);
- printk(KERN_CRIT "slot %d too large, nritems %d\n",
+ btrfs_crit(root->fs_info, "slot %d too large, nritems %d",
slot, nritems);
BUG_ON(1);
}
@@ -4495,7 +4772,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
if (btrfs_leaf_free_space(root, leaf) < total_size) {
btrfs_print_leaf(root, leaf);
- printk(KERN_CRIT "not enough freespace need %u have %d\n",
+ btrfs_crit(root->fs_info, "not enough freespace need %u have %d",
total_size, btrfs_leaf_free_space(root, leaf));
BUG();
}
@@ -4505,7 +4782,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
if (old_data < data_end) {
btrfs_print_leaf(root, leaf);
- printk(KERN_CRIT "slot %d old_data %d data_end %d\n",
+ btrfs_crit(root->fs_info, "slot %d old_data %d data_end %d",
slot, old_data, data_end);
BUG_ON(1);
}
@@ -4817,7 +5094,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
* This may release the path, and so you may lose any locks held at the
* time you call it.
*/
-static int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
+int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path)
{
struct btrfs_key key;
struct btrfs_disk_key found_key;
@@ -5240,7 +5517,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
if (!left_start_ctransid || !right_start_ctransid) {
WARN(1, KERN_WARNING
- "btrfs: btrfs_compare_tree detected "
+ "BTRFS: btrfs_compare_tree detected "
"a change in one of the trees while "
"iterating. This is probably a "
"bug.\n");
@@ -5680,3 +5957,46 @@ int btrfs_previous_item(struct btrfs_root *root,
}
return 1;
}
+
+/*
+ * search in extent tree to find a previous Metadata/Data extent item with
+ * min objecitd.
+ *
+ * returns 0 if something is found, 1 if nothing was found and < 0 on error
+ */
+int btrfs_previous_extent_item(struct btrfs_root *root,
+ struct btrfs_path *path, u64 min_objectid)
+{
+ struct btrfs_key found_key;
+ struct extent_buffer *leaf;
+ u32 nritems;
+ int ret;
+
+ while (1) {
+ if (path->slots[0] == 0) {
+ btrfs_set_path_blocking(path);
+ ret = btrfs_prev_leaf(root, path);
+ if (ret != 0)
+ return ret;
+ } else {
+ path->slots[0]--;
+ }
+ leaf = path->nodes[0];
+ nritems = btrfs_header_nritems(leaf);
+ if (nritems == 0)
+ return 1;
+ if (path->slots[0] == nritems)
+ path->slots[0]--;
+
+ btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+ if (found_key.objectid < min_objectid)
+ break;
+ if (found_key.type == BTRFS_EXTENT_ITEM_KEY ||
+ found_key.type == BTRFS_METADATA_ITEM_KEY)
+ return 0;
+ if (found_key.objectid == min_objectid &&
+ found_key.type < BTRFS_EXTENT_ITEM_KEY)
+ break;
+ }
+ return 1;
+}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7506825211a2..2c1a42ca519f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -521,9 +521,15 @@ struct btrfs_super_block {
#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6)
#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8)
+#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9)
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
+#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
+#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
#define BTRFS_FEATURE_COMPAT_RO_SUPP 0ULL
+#define BTRFS_FEATURE_COMPAT_RO_SAFE_SET 0ULL
+#define BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR 0ULL
+
#define BTRFS_FEATURE_INCOMPAT_SUPP \
(BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF | \
BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL | \
@@ -532,7 +538,12 @@ struct btrfs_super_block {
BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO | \
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
- BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
+ BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
+ BTRFS_FEATURE_INCOMPAT_NO_HOLES)
+
+#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
+ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
+#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL
/*
* A leaf is full of items. offset and size tell us where to find
@@ -1094,7 +1105,7 @@ struct btrfs_qgroup_limit_item {
} __attribute__ ((__packed__));
struct btrfs_space_info {
- u64 flags;
+ spinlock_t lock;
u64 total_bytes; /* total bytes in the space,
this doesn't take mirrors into account */
@@ -1104,14 +1115,25 @@ struct btrfs_space_info {
transaction finishes */
u64 bytes_reserved; /* total bytes the allocator has reserved for
current allocations */
- u64 bytes_readonly; /* total bytes that are read only */
-
u64 bytes_may_use; /* number of bytes that may be used for
delalloc/allocations */
+ u64 bytes_readonly; /* total bytes that are read only */
+
+ unsigned int full:1; /* indicates that we cannot allocate any more
+ chunks for this space */
+ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
+
+ unsigned int flush:1; /* set if we are trying to make space */
+
+ unsigned int force_alloc; /* set if we need to force a chunk
+ alloc for this space */
+
u64 disk_used; /* total bytes used on disk */
u64 disk_total; /* total bytes on disk, takes mirrors into
account */
+ u64 flags;
+
/*
* bytes_pinned is kept in line with what is actually pinned, as in
* we've called update_block_group and dropped the bytes_used counter
@@ -1124,22 +1146,15 @@ struct btrfs_space_info {
*/
struct percpu_counter total_bytes_pinned;
- unsigned int full:1; /* indicates that we cannot allocate any more
- chunks for this space */
- unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
-
- unsigned int flush:1; /* set if we are trying to make space */
-
- unsigned int force_alloc; /* set if we need to force a chunk
- alloc for this space */
-
struct list_head list;
+ struct rw_semaphore groups_sem;
/* for block groups in our same type */
struct list_head block_groups[BTRFS_NR_RAID_TYPES];
- spinlock_t lock;
- struct rw_semaphore groups_sem;
wait_queue_head_t wait;
+
+ struct kobject kobj;
+ struct kobject block_group_kobjs[BTRFS_NR_RAID_TYPES];
};
#define BTRFS_BLOCK_RSV_GLOBAL 1
@@ -1346,6 +1361,7 @@ struct btrfs_fs_info {
u64 generation;
u64 last_trans_committed;
+ u64 avg_delayed_ref_runtime;
/*
* this is updated to the current trans every time a full commit
@@ -1448,7 +1464,6 @@ struct btrfs_fs_info {
spinlock_t tree_mod_seq_lock;
atomic64_t tree_mod_seq;
struct list_head tree_mod_seq_list;
- struct seq_list tree_mod_seq_elem;
/* this protects tree_mod_log */
rwlock_t tree_mod_log_lock;
@@ -1515,6 +1530,8 @@ struct btrfs_fs_info {
int thread_pool_size;
struct kobject super_kobj;
+ struct kobject *space_info_kobj;
+ struct kobject *device_dir_kobj;
struct completion kobj_unregister;
int do_barriers;
int closing;
@@ -1643,6 +1660,10 @@ struct btrfs_fs_info {
spinlock_t reada_lock;
struct radix_tree_root reada_tree;
+ /* Extent buffer radix tree */
+ spinlock_t buffer_lock;
+ struct radix_tree_root buffer_radix;
+
/* next backup root to be overwritten */
int backup_root_index;
@@ -1795,6 +1816,12 @@ struct btrfs_root {
struct list_head ordered_extents;
struct list_head ordered_root;
u64 nr_ordered_extents;
+
+ /*
+ * Number of currently running SEND ioctls to prevent
+ * manipulation with the read-only status via SUBVOL_SETFLAGS
+ */
+ int send_in_progress;
};
struct btrfs_ioctl_defrag_range_args {
@@ -1997,6 +2024,7 @@ struct btrfs_ioctl_defrag_range_args {
#define BTRFS_MOUNT_CHECK_INTEGRITY_INCLUDING_EXTENT_DATA (1 << 21)
#define BTRFS_MOUNT_PANIC_ON_FATAL_ERROR (1 << 22)
#define BTRFS_MOUNT_RESCAN_UUID_TREE (1 << 23)
+#define BTRFS_MOUNT_CHANGE_INODE_CACHE (1 << 24)
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
@@ -2925,6 +2953,10 @@ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_generation,
struct btrfs_file_extent_item, generation, 64);
BTRFS_SETGET_STACK_FUNCS(stack_file_extent_num_bytes,
struct btrfs_file_extent_item, num_bytes, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_disk_num_bytes,
+ struct btrfs_file_extent_item, disk_num_bytes, 64);
+BTRFS_SETGET_STACK_FUNCS(stack_file_extent_compression,
+ struct btrfs_file_extent_item, compression, 8);
static inline unsigned long
btrfs_file_extent_inline_start(struct btrfs_file_extent_item *e)
@@ -2958,15 +2990,6 @@ BTRFS_SETGET_FUNCS(file_extent_encryption, struct btrfs_file_extent_item,
BTRFS_SETGET_FUNCS(file_extent_other_encoding, struct btrfs_file_extent_item,
other_encoding, 16);
-/* this returns the number of file bytes represented by the inline item.
- * If an item is compressed, this is the uncompressed size
- */
-static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
- struct btrfs_file_extent_item *e)
-{
- return btrfs_file_extent_ram_bytes(eb, e);
-}
-
/*
* this returns the number of bytes used by the item on disk, minus the
* size of any extent headers. If a file is compressed on disk, this is
@@ -2980,6 +3003,32 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb,
return btrfs_item_size(eb, e) - offset;
}
+/* this returns the number of file bytes represented by the inline item.
+ * If an item is compressed, this is the uncompressed size
+ */
+static inline u32 btrfs_file_extent_inline_len(struct extent_buffer *eb,
+ int slot,
+ struct btrfs_file_extent_item *fi)
+{
+ struct btrfs_map_token token;
+
+ btrfs_init_map_token(&token);
+ /*
+ * return the space used on disk if this item isn't
+ * compressed or encoded
+ */
+ if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 &&
+ btrfs_token_file_extent_encryption(eb, fi, &token) == 0 &&
+ btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) {
+ return btrfs_file_extent_inline_item_len(eb,
+ btrfs_item_nr(slot));
+ }
+
+ /* otherwise use the ram bytes field */
+ return btrfs_token_file_extent_ram_bytes(eb, fi, &token);
+}
+
+
/* btrfs_dev_stats_item */
static inline u64 btrfs_dev_stats_value(struct extent_buffer *eb,
struct btrfs_dev_stats_item *ptr,
@@ -3143,6 +3192,8 @@ static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_root *root,
int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
@@ -3163,6 +3214,7 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
struct btrfs_fs_info *info,
u64 bytenr);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
+int get_block_group_index(struct btrfs_block_group_cache *cache);
struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u32 blocksize,
u64 parent, u64 root_objectid,
@@ -3301,6 +3353,8 @@ int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2);
int btrfs_previous_item(struct btrfs_root *root,
struct btrfs_path *path, u64 min_objectid,
int type);
+int btrfs_previous_extent_item(struct btrfs_root *root,
+ struct btrfs_path *path, u64 min_objectid);
void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path,
struct btrfs_key *new_key);
struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
@@ -3350,6 +3404,8 @@ int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
struct btrfs_key *new_key);
+int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
+ u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key);
int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
*root, struct btrfs_key *key, struct btrfs_path *p, int
ins_len, int cow);
@@ -3399,6 +3455,7 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
}
int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path);
+int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path);
int btrfs_next_old_leaf(struct btrfs_root *root, struct btrfs_path *path,
u64 time_seq);
static inline int btrfs_next_old_item(struct btrfs_root *root,
@@ -3563,12 +3620,6 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const char *name, int name_len,
u64 inode_objectid, u64 ref_objectid, u64 *index);
-int btrfs_get_inode_ref_index(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len,
- u64 inode_objectid, u64 ref_objectid, int mod,
- u64 *ret_index);
int btrfs_insert_empty_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path, u64 objectid);
@@ -3676,7 +3727,9 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *new_root, u64 new_dirid);
+ struct btrfs_root *new_root,
+ struct btrfs_root *parent_root,
+ u64 new_dirid);
int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
size_t size, struct bio *bio,
unsigned long bio_flags);
@@ -3745,7 +3798,10 @@ extern const struct file_operations btrfs_file_operations;
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
struct btrfs_path *path, u64 start, u64 end,
- u64 *drop_end, int drop_cache);
+ u64 *drop_end, int drop_cache,
+ int replace_extent,
+ u32 extent_item_size,
+ int *key_inserted);
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode, u64 start,
u64 end, int drop_cache);
@@ -3764,6 +3820,8 @@ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
/* sysfs.c */
int btrfs_init_sysfs(void);
void btrfs_exit_sysfs(void);
+int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info);
+void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info);
/* xattr.c */
ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size);
@@ -3796,14 +3854,20 @@ void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
btrfs_printk(fs_info, KERN_NOTICE fmt, ##args)
#define btrfs_info(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_INFO fmt, ##args)
+
+#ifdef DEBUG
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
+#else
+#define btrfs_debug(fs_info, fmt, args...) \
+ no_printk(KERN_DEBUG fmt, ##args)
+#endif
#ifdef CONFIG_BTRFS_ASSERT
static inline void assfail(char *expr, char *file, int line)
{
- printk(KERN_ERR "BTRFS assertion failed: %s, file: %s, line: %d",
+ pr_err("BTRFS: assertion failed: %s, file: %s, line: %d",
expr, file, line);
BUG();
}
@@ -3841,7 +3905,7 @@ static inline void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info,
if (!(features & flag)) {
features |= flag;
btrfs_set_super_incompat_flags(disk_super, features);
- printk(KERN_INFO "btrfs: setting %llu feature flag\n",
+ btrfs_info(fs_info, "setting %llu feature flag",
flag);
}
spin_unlock(&fs_info->super_lock);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 8d292fbae659..451b00c86f6c 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -55,8 +55,7 @@ static inline void btrfs_init_delayed_node(
delayed_node->inode_id = inode_id;
atomic_set(&delayed_node->refs, 0);
delayed_node->count = 0;
- delayed_node->in_list = 0;
- delayed_node->inode_dirty = 0;
+ delayed_node->flags = 0;
delayed_node->ins_root = RB_ROOT;
delayed_node->del_root = RB_ROOT;
mutex_init(&delayed_node->mutex);
@@ -172,7 +171,7 @@ static void btrfs_queue_delayed_node(struct btrfs_delayed_root *root,
int mod)
{
spin_lock(&root->lock);
- if (node->in_list) {
+ if (test_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags)) {
if (!list_empty(&node->p_list))
list_move_tail(&node->p_list, &root->prepare_list);
else if (mod)
@@ -182,7 +181,7 @@ static void btrfs_queue_delayed_node(struct btrfs_delayed_root *root,
list_add_tail(&node->p_list, &root->prepare_list);
atomic_inc(&node->refs); /* inserted into list */
root->nodes++;
- node->in_list = 1;
+ set_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags);
}
spin_unlock(&root->lock);
}
@@ -192,13 +191,13 @@ static void btrfs_dequeue_delayed_node(struct btrfs_delayed_root *root,
struct btrfs_delayed_node *node)
{
spin_lock(&root->lock);
- if (node->in_list) {
+ if (test_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags)) {
root->nodes--;
atomic_dec(&node->refs); /* not in the list */
list_del_init(&node->n_list);
if (!list_empty(&node->p_list))
list_del_init(&node->p_list);
- node->in_list = 0;
+ clear_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags);
}
spin_unlock(&root->lock);
}
@@ -231,7 +230,8 @@ static struct btrfs_delayed_node *btrfs_next_delayed_node(
delayed_root = node->root->fs_info->delayed_root;
spin_lock(&delayed_root->lock);
- if (!node->in_list) { /* not in the list */
+ if (!test_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags)) {
+ /* not in the list */
if (list_empty(&delayed_root->node_list))
goto out;
p = delayed_root->node_list.next;
@@ -1004,9 +1004,10 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
{
struct btrfs_delayed_root *delayed_root;
- if (delayed_node && delayed_node->inode_dirty) {
+ if (delayed_node &&
+ test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
BUG_ON(!delayed_node->root);
- delayed_node->inode_dirty = 0;
+ clear_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags);
delayed_node->count--;
delayed_root = delayed_node->root->fs_info->delayed_root;
@@ -1014,6 +1015,18 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node)
}
}
+static void btrfs_release_delayed_iref(struct btrfs_delayed_node *delayed_node)
+{
+ struct btrfs_delayed_root *delayed_root;
+
+ ASSERT(delayed_node->root);
+ clear_bit(BTRFS_DELAYED_NODE_DEL_IREF, &delayed_node->flags);
+ delayed_node->count--;
+
+ delayed_root = delayed_node->root->fs_info->delayed_root;
+ finish_one_item(delayed_root);
+}
+
static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
@@ -1022,13 +1035,19 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
struct btrfs_key key;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
+ int mod;
int ret;
key.objectid = node->inode_id;
btrfs_set_key_type(&key, BTRFS_INODE_ITEM_KEY);
key.offset = 0;
- ret = btrfs_lookup_inode(trans, root, path, &key, 1);
+ if (test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags))
+ mod = -1;
+ else
+ mod = 1;
+
+ ret = btrfs_lookup_inode(trans, root, path, &key, mod);
if (ret > 0) {
btrfs_release_path(path);
return -ENOENT;
@@ -1036,19 +1055,58 @@ static int __btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
return ret;
}
- btrfs_unlock_up_safe(path, 1);
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
write_extent_buffer(leaf, &node->inode_item, (unsigned long)inode_item,
sizeof(struct btrfs_inode_item));
btrfs_mark_buffer_dirty(leaf);
- btrfs_release_path(path);
+ if (!test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &node->flags))
+ goto no_iref;
+
+ path->slots[0]++;
+ if (path->slots[0] >= btrfs_header_nritems(leaf))
+ goto search;
+again:
+ btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+ if (key.objectid != node->inode_id)
+ goto out;
+
+ if (key.type != BTRFS_INODE_REF_KEY &&
+ key.type != BTRFS_INODE_EXTREF_KEY)
+ goto out;
+
+ /*
+ * Delayed iref deletion is for the inode who has only one link,
+ * so there is only one iref. The case that several irefs are
+ * in the same item doesn't exist.
+ */
+ btrfs_del_item(trans, root, path);
+out:
+ btrfs_release_delayed_iref(node);
+no_iref:
+ btrfs_release_path(path);
+err_out:
btrfs_delayed_inode_release_metadata(root, node);
btrfs_release_delayed_inode(node);
- return 0;
+ return ret;
+
+search:
+ btrfs_release_path(path);
+
+ btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+ key.offset = -1;
+ ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+ if (ret < 0)
+ goto err_out;
+ ASSERT(ret);
+
+ ret = 0;
+ leaf = path->nodes[0];
+ path->slots[0]--;
+ goto again;
}
static inline int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
@@ -1059,7 +1117,7 @@ static inline int btrfs_update_delayed_inode(struct btrfs_trans_handle *trans,
int ret;
mutex_lock(&node->mutex);
- if (!node->inode_dirty) {
+ if (!test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &node->flags)) {
mutex_unlock(&node->mutex);
return 0;
}
@@ -1203,7 +1261,7 @@ int btrfs_commit_inode_delayed_inode(struct inode *inode)
return 0;
mutex_lock(&delayed_node->mutex);
- if (!delayed_node->inode_dirty) {
+ if (!test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
mutex_unlock(&delayed_node->mutex);
btrfs_release_delayed_node(delayed_node);
return 0;
@@ -1227,7 +1285,7 @@ int btrfs_commit_inode_delayed_inode(struct inode *inode)
trans->block_rsv = &delayed_node->root->fs_info->delayed_block_rsv;
mutex_lock(&delayed_node->mutex);
- if (delayed_node->inode_dirty)
+ if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags))
ret = __btrfs_update_delayed_inode(trans, delayed_node->root,
path, delayed_node);
else
@@ -1300,36 +1358,9 @@ again:
trans->block_rsv = &root->fs_info->delayed_block_rsv;
__btrfs_commit_inode_delayed_items(trans, path, delayed_node);
- /*
- * Maybe new delayed items have been inserted, so we need requeue
- * the work. Besides that, we must dequeue the empty delayed nodes
- * to avoid the race between delayed items balance and the worker.
- * The race like this:
- * Task1 Worker thread
- * count == 0, needn't requeue
- * also needn't insert the
- * delayed node into prepare
- * list again.
- * add lots of delayed items
- * queue the delayed node
- * already in the list,
- * and not in the prepare
- * list, it means the delayed
- * node is being dealt with
- * by the worker.
- * do delayed items balance
- * the delayed node is being
- * dealt with by the worker
- * now, just wait.
- * the worker goto idle.
- * Task1 will sleep until the transaction is commited.
- */
- mutex_lock(&delayed_node->mutex);
- btrfs_dequeue_delayed_node(root->fs_info->delayed_root, delayed_node);
- mutex_unlock(&delayed_node->mutex);
trans->block_rsv = block_rsv;
- btrfs_end_transaction_dmeta(trans, root);
+ btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty_nodelay(root);
release_path:
@@ -1376,52 +1407,41 @@ void btrfs_assert_delayed_root_empty(struct btrfs_root *root)
WARN_ON(btrfs_first_delayed_node(delayed_root));
}
-static int refs_newer(struct btrfs_delayed_root *delayed_root,
- int seq, int count)
+static int could_end_wait(struct btrfs_delayed_root *delayed_root, int seq)
{
int val = atomic_read(&delayed_root->items_seq);
- if (val < seq || val >= seq + count)
+ if (val < seq || val >= seq + BTRFS_DELAYED_BATCH)
+ return 1;
+
+ if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
return 1;
+
return 0;
}
void btrfs_balance_delayed_items(struct btrfs_root *root)
{
struct btrfs_delayed_root *delayed_root;
- int seq;
delayed_root = btrfs_get_delayed_root(root);
if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
return;
- seq = atomic_read(&delayed_root->items_seq);
-
if (atomic_read(&delayed_root->items) >= BTRFS_DELAYED_WRITEBACK) {
+ int seq;
int ret;
- DEFINE_WAIT(__wait);
+
+ seq = atomic_read(&delayed_root->items_seq);
ret = btrfs_wq_run_delayed_node(delayed_root, root, 0);
if (ret)
return;
- while (1) {
- prepare_to_wait(&delayed_root->wait, &__wait,
- TASK_INTERRUPTIBLE);
-
- if (refs_newer(delayed_root, seq,
- BTRFS_DELAYED_BATCH) ||
- atomic_read(&delayed_root->items) <
- BTRFS_DELAYED_BACKGROUND) {
- break;
- }
- if (!signal_pending(current))
- schedule();
- else
- break;
- }
- finish_wait(&delayed_root->wait, &__wait);
+ wait_event_interruptible(delayed_root->wait,
+ could_end_wait(delayed_root, seq));
+ return;
}
btrfs_wq_run_delayed_node(delayed_root, root, BTRFS_DELAYED_BATCH);
@@ -1472,9 +1492,9 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
mutex_lock(&delayed_node->mutex);
ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
if (unlikely(ret)) {
- printk(KERN_ERR "err add delayed dir index item(name: %.*s) "
+ btrfs_err(root->fs_info, "err add delayed dir index item(name: %.*s) "
"into the insertion tree of the delayed node"
- "(root id: %llu, inode id: %llu, errno: %d)\n",
+ "(root id: %llu, inode id: %llu, errno: %d)",
name_len, name, delayed_node->root->objectid,
delayed_node->inode_id, ret);
BUG();
@@ -1544,9 +1564,9 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
mutex_lock(&node->mutex);
ret = __btrfs_add_delayed_deletion_item(node, item);
if (unlikely(ret)) {
- printk(KERN_ERR "err add delayed dir index item(index: %llu) "
+ btrfs_err(root->fs_info, "err add delayed dir index item(index: %llu) "
"into the deletion tree of the delayed node"
- "(root id: %llu, inode id: %llu, errno: %d)\n",
+ "(root id: %llu, inode id: %llu, errno: %d)",
index, node->root->objectid, node->inode_id,
ret);
BUG();
@@ -1759,7 +1779,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
return -ENOENT;
mutex_lock(&delayed_node->mutex);
- if (!delayed_node->inode_dirty) {
+ if (!test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
mutex_unlock(&delayed_node->mutex);
btrfs_release_delayed_node(delayed_node);
return -ENOENT;
@@ -1810,7 +1830,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
return PTR_ERR(delayed_node);
mutex_lock(&delayed_node->mutex);
- if (delayed_node->inode_dirty) {
+ if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
goto release_node;
}
@@ -1821,7 +1841,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
goto release_node;
fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
- delayed_node->inode_dirty = 1;
+ set_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags);
delayed_node->count++;
atomic_inc(&root->fs_info->delayed_root->items);
release_node:
@@ -1830,6 +1850,41 @@ release_node:
return ret;
}
+int btrfs_delayed_delete_inode_ref(struct inode *inode)
+{
+ struct btrfs_delayed_node *delayed_node;
+
+ delayed_node = btrfs_get_or_create_delayed_node(inode);
+ if (IS_ERR(delayed_node))
+ return PTR_ERR(delayed_node);
+
+ /*
+ * We don't reserve space for inode ref deletion is because:
+ * - We ONLY do async inode ref deletion for the inode who has only
+ * one link(i_nlink == 1), it means there is only one inode ref.
+ * And in most case, the inode ref and the inode item are in the
+ * same leaf, and we will deal with them at the same time.
+ * Since we are sure we will reserve the space for the inode item,
+ * it is unnecessary to reserve space for inode ref deletion.
+ * - If the inode ref and the inode item are not in the same leaf,
+ * We also needn't worry about enospc problem, because we reserve
+ * much more space for the inode update than it needs.
+ * - At the worst, we can steal some space from the global reservation.
+ * It is very rare.
+ */
+ mutex_lock(&delayed_node->mutex);
+ if (test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &delayed_node->flags))
+ goto release_node;
+
+ set_bit(BTRFS_DELAYED_NODE_DEL_IREF, &delayed_node->flags);
+ delayed_node->count++;
+ atomic_inc(&BTRFS_I(inode)->root->fs_info->delayed_root->items);
+release_node:
+ mutex_unlock(&delayed_node->mutex);
+ btrfs_release_delayed_node(delayed_node);
+ return 0;
+}
+
static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
{
struct btrfs_root *root = delayed_node->root;
@@ -1852,7 +1907,10 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
btrfs_release_delayed_item(prev_item);
}
- if (delayed_node->inode_dirty) {
+ if (test_bit(BTRFS_DELAYED_NODE_DEL_IREF, &delayed_node->flags))
+ btrfs_release_delayed_iref(delayed_node);
+
+ if (test_bit(BTRFS_DELAYED_NODE_INODE_DIRTY, &delayed_node->flags)) {
btrfs_delayed_inode_release_metadata(root, delayed_node);
btrfs_release_delayed_inode(delayed_node);
}
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index a4b38f934d14..f70119f25421 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -48,6 +48,10 @@ struct btrfs_delayed_root {
wait_queue_head_t wait;
};
+#define BTRFS_DELAYED_NODE_IN_LIST 0
+#define BTRFS_DELAYED_NODE_INODE_DIRTY 1
+#define BTRFS_DELAYED_NODE_DEL_IREF 2
+
struct btrfs_delayed_node {
u64 inode_id;
u64 bytes_reserved;
@@ -65,8 +69,7 @@ struct btrfs_delayed_node {
struct btrfs_inode_item inode_item;
atomic_t refs;
u64 index_cnt;
- bool in_list;
- bool inode_dirty;
+ unsigned long flags;
int count;
};
@@ -125,6 +128,7 @@ int btrfs_commit_inode_delayed_inode(struct inode *inode);
int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode);
int btrfs_fill_inode(struct inode *inode, u32 *rdev);
+int btrfs_delayed_delete_inode_ref(struct inode *inode);
/* Used for drop dead root */
void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index e4d467be2dd4..f3bff89eecf0 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -161,35 +161,61 @@ static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root,
return NULL;
}
+/* insert a new ref to head ref rbtree */
+static struct btrfs_delayed_ref_head *htree_insert(struct rb_root *root,
+ struct rb_node *node)
+{
+ struct rb_node **p = &root->rb_node;
+ struct rb_node *parent_node = NULL;
+ struct btrfs_delayed_ref_head *entry;
+ struct btrfs_delayed_ref_head *ins;
+ u64 bytenr;
+
+ ins = rb_entry(node, struct btrfs_delayed_ref_head, href_node);
+ bytenr = ins->node.bytenr;
+ while (*p) {
+ parent_node = *p;
+ entry = rb_entry(parent_node, struct btrfs_delayed_ref_head,
+ href_node);
+
+ if (bytenr < entry->node.bytenr)
+ p = &(*p)->rb_left;
+ else if (bytenr > entry->node.bytenr)
+ p = &(*p)->rb_right;
+ else
+ return entry;
+ }
+
+ rb_link_node(node, parent_node, p);
+ rb_insert_color(node, root);
+ return NULL;
+}
+
/*
* find an head entry based on bytenr. This returns the delayed ref
* head if it was able to find one, or NULL if nothing was in that spot.
* If return_bigger is given, the next bigger entry is returned if no exact
* match is found.
*/
-static struct btrfs_delayed_ref_node *find_ref_head(struct rb_root *root,
- u64 bytenr,
- struct btrfs_delayed_ref_node **last,
- int return_bigger)
+static struct btrfs_delayed_ref_head *
+find_ref_head(struct rb_root *root, u64 bytenr,
+ struct btrfs_delayed_ref_head **last, int return_bigger)
{
struct rb_node *n;
- struct btrfs_delayed_ref_node *entry;
+ struct btrfs_delayed_ref_head *entry;
int cmp = 0;
again:
n = root->rb_node;
entry = NULL;
while (n) {
- entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
- WARN_ON(!entry->in_tree);
+ entry = rb_entry(n, struct btrfs_delayed_ref_head, href_node);
if (last)
*last = entry;
- if (bytenr < entry->bytenr)
+ if (bytenr < entry->node.bytenr)
cmp = -1;
- else if (bytenr > entry->bytenr)
- cmp = 1;
- else if (!btrfs_delayed_ref_is_head(entry))
+ else if (bytenr > entry->node.bytenr)
cmp = 1;
else
cmp = 0;
@@ -203,12 +229,12 @@ again:
}
if (entry && return_bigger) {
if (cmp > 0) {
- n = rb_next(&entry->rb_node);
+ n = rb_next(&entry->href_node);
if (!n)
n = rb_first(root);
- entry = rb_entry(n, struct btrfs_delayed_ref_node,
- rb_node);
- bytenr = entry->bytenr;
+ entry = rb_entry(n, struct btrfs_delayed_ref_head,
+ href_node);
+ bytenr = entry->node.bytenr;
return_bigger = 0;
goto again;
}
@@ -243,33 +269,38 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *ref)
{
- rb_erase(&ref->rb_node, &delayed_refs->root);
+ if (btrfs_delayed_ref_is_head(ref)) {
+ head = btrfs_delayed_node_to_head(ref);
+ rb_erase(&head->href_node, &delayed_refs->href_root);
+ } else {
+ assert_spin_locked(&head->lock);
+ rb_erase(&ref->rb_node, &head->ref_root);
+ }
ref->in_tree = 0;
btrfs_put_delayed_ref(ref);
- delayed_refs->num_entries--;
+ atomic_dec(&delayed_refs->num_entries);
if (trans->delayed_ref_updates)
trans->delayed_ref_updates--;
}
static int merge_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *ref, u64 seq)
{
struct rb_node *node;
- int merged = 0;
int mod = 0;
int done = 0;
- node = rb_prev(&ref->rb_node);
- while (node) {
+ node = rb_next(&ref->rb_node);
+ while (!done && node) {
struct btrfs_delayed_ref_node *next;
next = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- node = rb_prev(node);
- if (next->bytenr != ref->bytenr)
- break;
+ node = rb_next(node);
if (seq && next->seq >= seq)
break;
if (comp_entry(ref, next, 0))
@@ -289,12 +320,11 @@ static int merge_ref(struct btrfs_trans_handle *trans,
mod = -next->ref_mod;
}
- merged++;
- drop_delayed_ref(trans, delayed_refs, next);
+ drop_delayed_ref(trans, delayed_refs, head, next);
ref->ref_mod += mod;
if (ref->ref_mod == 0) {
- drop_delayed_ref(trans, delayed_refs, ref);
- break;
+ drop_delayed_ref(trans, delayed_refs, head, ref);
+ done = 1;
} else {
/*
* You can't have multiples of the same ref on a tree
@@ -303,13 +333,8 @@ static int merge_ref(struct btrfs_trans_handle *trans,
WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY ||
ref->type == BTRFS_SHARED_BLOCK_REF_KEY);
}
-
- if (done)
- break;
- node = rb_prev(&ref->rb_node);
}
-
- return merged;
+ return done;
}
void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
@@ -320,6 +345,14 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
struct rb_node *node;
u64 seq = 0;
+ assert_spin_locked(&head->lock);
+ /*
+ * We don't have too much refs to merge in the case of delayed data
+ * refs.
+ */
+ if (head->is_data)
+ return;
+
spin_lock(&fs_info->tree_mod_seq_lock);
if (!list_empty(&fs_info->tree_mod_seq_list)) {
struct seq_list *elem;
@@ -330,22 +363,19 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
}
spin_unlock(&fs_info->tree_mod_seq_lock);
- node = rb_prev(&head->node.rb_node);
+ node = rb_first(&head->ref_root);
while (node) {
struct btrfs_delayed_ref_node *ref;
ref = rb_entry(node, struct btrfs_delayed_ref_node,
rb_node);
- if (ref->bytenr != head->node.bytenr)
- break;
-
/* We can't merge refs that are outside of our seq count */
if (seq && ref->seq >= seq)
break;
- if (merge_ref(trans, delayed_refs, ref, seq))
- node = rb_prev(&head->node.rb_node);
+ if (merge_ref(trans, delayed_refs, head, ref, seq))
+ node = rb_first(&head->ref_root);
else
- node = rb_prev(node);
+ node = rb_next(&ref->rb_node);
}
}
@@ -373,71 +403,52 @@ int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
return ret;
}
-int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
- struct list_head *cluster, u64 start)
+struct btrfs_delayed_ref_head *
+btrfs_select_ref_head(struct btrfs_trans_handle *trans)
{
- int count = 0;
struct btrfs_delayed_ref_root *delayed_refs;
- struct rb_node *node;
- struct btrfs_delayed_ref_node *ref;
struct btrfs_delayed_ref_head *head;
+ u64 start;
+ bool loop = false;
delayed_refs = &trans->transaction->delayed_refs;
- if (start == 0) {
- node = rb_first(&delayed_refs->root);
- } else {
- ref = NULL;
- find_ref_head(&delayed_refs->root, start + 1, &ref, 1);
- if (ref) {
- node = &ref->rb_node;
- } else
- node = rb_first(&delayed_refs->root);
- }
+
again:
- while (node && count < 32) {
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- if (btrfs_delayed_ref_is_head(ref)) {
- head = btrfs_delayed_node_to_head(ref);
- if (list_empty(&head->cluster)) {
- list_add_tail(&head->cluster, cluster);
- delayed_refs->run_delayed_start =
- head->node.bytenr;
- count++;
-
- WARN_ON(delayed_refs->num_heads_ready == 0);
- delayed_refs->num_heads_ready--;
- } else if (count) {
- /* the goal of the clustering is to find extents
- * that are likely to end up in the same extent
- * leaf on disk. So, we don't want them spread
- * all over the tree. Stop now if we've hit
- * a head that was already in use
- */
- break;
- }
- }
- node = rb_next(node);
- }
- if (count) {
- return 0;
- } else if (start) {
- /*
- * we've gone to the end of the rbtree without finding any
- * clusters. start from the beginning and try again
- */
+ start = delayed_refs->run_delayed_start;
+ head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
+ if (!head && !loop) {
+ delayed_refs->run_delayed_start = 0;
start = 0;
- node = rb_first(&delayed_refs->root);
- goto again;
+ loop = true;
+ head = find_ref_head(&delayed_refs->href_root, start, NULL, 1);
+ if (!head)
+ return NULL;
+ } else if (!head && loop) {
+ return NULL;
}
- return 1;
-}
-void btrfs_release_ref_cluster(struct list_head *cluster)
-{
- struct list_head *pos, *q;
+ while (head->processing) {
+ struct rb_node *node;
+
+ node = rb_next(&head->href_node);
+ if (!node) {
+ if (loop)
+ return NULL;
+ delayed_refs->run_delayed_start = 0;
+ start = 0;
+ loop = true;
+ goto again;
+ }
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ }
- list_for_each_safe(pos, q, cluster)
- list_del_init(pos);
+ head->processing = 1;
+ WARN_ON(delayed_refs->num_heads_ready == 0);
+ delayed_refs->num_heads_ready--;
+ delayed_refs->run_delayed_start = head->node.bytenr +
+ head->node.num_bytes;
+ return head;
}
/*
@@ -451,6 +462,7 @@ void btrfs_release_ref_cluster(struct list_head *cluster)
static noinline void
update_existing_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head,
struct btrfs_delayed_ref_node *existing,
struct btrfs_delayed_ref_node *update)
{
@@ -463,7 +475,7 @@ update_existing_ref(struct btrfs_trans_handle *trans,
*/
existing->ref_mod--;
if (existing->ref_mod == 0)
- drop_delayed_ref(trans, delayed_refs, existing);
+ drop_delayed_ref(trans, delayed_refs, head, existing);
else
WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY ||
existing->type == BTRFS_SHARED_BLOCK_REF_KEY);
@@ -533,9 +545,13 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
}
}
/*
- * update the reference mod on the head to reflect this new operation
+ * update the reference mod on the head to reflect this new operation,
+ * only need the lock for this case cause we could be processing it
+ * currently, for refs we just added we know we're a-ok.
*/
+ spin_lock(&existing_ref->lock);
existing->ref_mod += update->ref_mod;
+ spin_unlock(&existing_ref->lock);
}
/*
@@ -543,13 +559,13 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
* this does all the dirty work in terms of maintaining the correct
* overall modification count.
*/
-static noinline void add_delayed_ref_head(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_node *ref,
- u64 bytenr, u64 num_bytes,
- int action, int is_data)
+static noinline struct btrfs_delayed_ref_head *
+add_delayed_ref_head(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_node *ref, u64 bytenr,
+ u64 num_bytes, int action, int is_data)
{
- struct btrfs_delayed_ref_node *existing;
+ struct btrfs_delayed_ref_head *existing;
struct btrfs_delayed_ref_head *head_ref = NULL;
struct btrfs_delayed_ref_root *delayed_refs;
int count_mod = 1;
@@ -596,38 +612,43 @@ static noinline void add_delayed_ref_head(struct btrfs_fs_info *fs_info,
head_ref = btrfs_delayed_node_to_head(ref);
head_ref->must_insert_reserved = must_insert_reserved;
head_ref->is_data = is_data;
+ head_ref->ref_root = RB_ROOT;
+ head_ref->processing = 0;
- INIT_LIST_HEAD(&head_ref->cluster);
+ spin_lock_init(&head_ref->lock);
mutex_init(&head_ref->mutex);
trace_add_delayed_ref_head(ref, head_ref, action);
- existing = tree_insert(&delayed_refs->root, &ref->rb_node);
-
+ existing = htree_insert(&delayed_refs->href_root,
+ &head_ref->href_node);
if (existing) {
- update_existing_head_ref(existing, ref);
+ update_existing_head_ref(&existing->node, ref);
/*
* we've updated the existing ref, free the newly
* allocated ref
*/
kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
+ head_ref = existing;
} else {
delayed_refs->num_heads++;
delayed_refs->num_heads_ready++;
- delayed_refs->num_entries++;
+ atomic_inc(&delayed_refs->num_entries);
trans->delayed_ref_updates++;
}
+ return head_ref;
}
/*
* helper to insert a delayed tree ref into the rbtree.
*/
-static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_node *ref,
- u64 bytenr, u64 num_bytes, u64 parent,
- u64 ref_root, int level, int action,
- int for_cow)
+static noinline void
+add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_delayed_ref_node *ref, u64 bytenr,
+ u64 num_bytes, u64 parent, u64 ref_root, int level,
+ int action, int for_cow)
{
struct btrfs_delayed_ref_node *existing;
struct btrfs_delayed_tree_ref *full_ref;
@@ -663,30 +684,33 @@ static noinline void add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
trace_add_delayed_tree_ref(ref, full_ref, action);
- existing = tree_insert(&delayed_refs->root, &ref->rb_node);
-
+ spin_lock(&head_ref->lock);
+ existing = tree_insert(&head_ref->ref_root, &ref->rb_node);
if (existing) {
- update_existing_ref(trans, delayed_refs, existing, ref);
+ update_existing_ref(trans, delayed_refs, head_ref, existing,
+ ref);
/*
* we've updated the existing ref, free the newly
* allocated ref
*/
kmem_cache_free(btrfs_delayed_tree_ref_cachep, full_ref);
} else {
- delayed_refs->num_entries++;
+ atomic_inc(&delayed_refs->num_entries);
trans->delayed_ref_updates++;
}
+ spin_unlock(&head_ref->lock);
}
/*
* helper to insert a delayed data ref into the rbtree.
*/
-static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info,
- struct btrfs_trans_handle *trans,
- struct btrfs_delayed_ref_node *ref,
- u64 bytenr, u64 num_bytes, u64 parent,
- u64 ref_root, u64 owner, u64 offset,
- int action, int for_cow)
+static noinline void
+add_delayed_data_ref(struct btrfs_fs_info *fs_info,
+ struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_head *head_ref,
+ struct btrfs_delayed_ref_node *ref, u64 bytenr,
+ u64 num_bytes, u64 parent, u64 ref_root, u64 owner,
+ u64 offset, int action, int for_cow)
{
struct btrfs_delayed_ref_node *existing;
struct btrfs_delayed_data_ref *full_ref;
@@ -724,19 +748,21 @@ static noinline void add_delayed_data_ref(struct btrfs_fs_info *fs_info,
trace_add_delayed_data_ref(ref, full_ref, action);
- existing = tree_insert(&delayed_refs->root, &ref->rb_node);
-
+ spin_lock(&head_ref->lock);
+ existing = tree_insert(&head_ref->ref_root, &ref->rb_node);
if (existing) {
- update_existing_ref(trans, delayed_refs, existing, ref);
+ update_existing_ref(trans, delayed_refs, head_ref, existing,
+ ref);
/*
* we've updated the existing ref, free the newly
* allocated ref
*/
kmem_cache_free(btrfs_delayed_data_ref_cachep, full_ref);
} else {
- delayed_refs->num_entries++;
+ atomic_inc(&delayed_refs->num_entries);
trans->delayed_ref_updates++;
}
+ spin_unlock(&head_ref->lock);
}
/*
@@ -775,10 +801,10 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
- num_bytes, action, 0);
+ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node,
+ bytenr, num_bytes, action, 0);
- add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr,
+ add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, level, action,
for_cow);
spin_unlock(&delayed_refs->lock);
@@ -823,10 +849,10 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
* insert both the head node and the new ref without dropping
* the spin lock
*/
- add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr,
- num_bytes, action, 1);
+ head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node,
+ bytenr, num_bytes, action, 1);
- add_delayed_data_ref(fs_info, trans, &ref->node, bytenr,
+ add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
num_bytes, parent, ref_root, owner, offset,
action, for_cow);
spin_unlock(&delayed_refs->lock);
@@ -869,14 +895,10 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_head *
btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
{
- struct btrfs_delayed_ref_node *ref;
struct btrfs_delayed_ref_root *delayed_refs;
delayed_refs = &trans->transaction->delayed_refs;
- ref = find_ref_head(&delayed_refs->root, bytenr, NULL, 0);
- if (ref)
- return btrfs_delayed_node_to_head(ref);
- return NULL;
+ return find_ref_head(&delayed_refs->href_root, bytenr, NULL, 0);
}
void btrfs_delayed_ref_exit(void)
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 70b962cc177d..4ba9b93022ff 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -81,7 +81,10 @@ struct btrfs_delayed_ref_head {
*/
struct mutex mutex;
- struct list_head cluster;
+ spinlock_t lock;
+ struct rb_root ref_root;
+
+ struct rb_node href_node;
struct btrfs_delayed_extent_op *extent_op;
/*
@@ -98,6 +101,7 @@ struct btrfs_delayed_ref_head {
*/
unsigned int must_insert_reserved:1;
unsigned int is_data:1;
+ unsigned int processing:1;
};
struct btrfs_delayed_tree_ref {
@@ -116,7 +120,8 @@ struct btrfs_delayed_data_ref {
};
struct btrfs_delayed_ref_root {
- struct rb_root root;
+ /* head ref rbtree */
+ struct rb_root href_root;
/* this spin lock protects the rbtree and the entries inside */
spinlock_t lock;
@@ -124,7 +129,7 @@ struct btrfs_delayed_ref_root {
/* how many delayed ref updates we've queued, used by the
* throttling code
*/
- unsigned long num_entries;
+ atomic_t num_entries;
/* total number of head nodes in tree */
unsigned long num_heads;
@@ -133,15 +138,6 @@ struct btrfs_delayed_ref_root {
unsigned long num_heads_ready;
/*
- * bumped when someone is making progress on the delayed
- * refs, so that other procs know they are just adding to
- * contention intead of helping
- */
- atomic_t procs_running_refs;
- atomic_t ref_seq;
- wait_queue_head_t wait;
-
- /*
* set when the tree is flushing before a transaction commit,
* used by the throttling code to decide if new updates need
* to be run right away
@@ -226,9 +222,9 @@ static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
mutex_unlock(&head->mutex);
}
-int btrfs_find_ref_cluster(struct btrfs_trans_handle *trans,
- struct list_head *cluster, u64 search_start);
-void btrfs_release_ref_cluster(struct list_head *cluster);
+
+struct btrfs_delayed_ref_head *
+btrfs_select_ref_head(struct btrfs_trans_handle *trans);
int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info,
struct btrfs_delayed_ref_root *delayed_refs,
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 2cfc3dfff64f..564c92638b20 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -102,7 +102,8 @@ no_valid_dev_replace_entry_found:
ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_replace_item);
if (item_size != sizeof(struct btrfs_dev_replace_item)) {
- pr_warn("btrfs: dev_replace entry found has unexpected size, ignore entry\n");
+ btrfs_warn(fs_info,
+ "dev_replace entry found has unexpected size, ignore entry");
goto no_valid_dev_replace_entry_found;
}
@@ -145,13 +146,19 @@ no_valid_dev_replace_entry_found:
if (!dev_replace->srcdev &&
!btrfs_test_opt(dev_root, DEGRADED)) {
ret = -EIO;
- pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?\n",
- src_devid);
+ btrfs_warn(fs_info,
+ "cannot mount because device replace operation is ongoing and");
+ btrfs_warn(fs_info,
+ "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
+ src_devid);
}
if (!dev_replace->tgtdev &&
!btrfs_test_opt(dev_root, DEGRADED)) {
ret = -EIO;
- pr_warn("btrfs: cannot mount because device replace operation is ongoing and\n" "tgtdev (devid %llu) is missing, need to run btrfs dev scan?\n",
+ btrfs_warn(fs_info,
+ "cannot mount because device replace operation is ongoing and");
+ btrfs_warn(fs_info,
+ "tgtdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
BTRFS_DEV_REPLACE_DEVID);
}
if (dev_replace->tgtdev) {
@@ -210,7 +217,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
}
ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
if (ret < 0) {
- pr_warn("btrfs: error %d while searching for dev_replace item!\n",
+ btrfs_warn(fs_info, "error %d while searching for dev_replace item!",
ret);
goto out;
}
@@ -230,7 +237,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
*/
ret = btrfs_del_item(trans, dev_root, path);
if (ret != 0) {
- pr_warn("btrfs: delete too small dev_replace item failed %d!\n",
+ btrfs_warn(fs_info, "delete too small dev_replace item failed %d!",
ret);
goto out;
}
@@ -243,7 +250,7 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
ret = btrfs_insert_empty_item(trans, dev_root, path,
&key, sizeof(*ptr));
if (ret < 0) {
- pr_warn("btrfs: insert dev_replace item failed %d!\n",
+ btrfs_warn(fs_info, "insert dev_replace item failed %d!",
ret);
goto out;
}
@@ -305,7 +312,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
struct btrfs_device *src_device = NULL;
if (btrfs_fs_incompat(fs_info, RAID56)) {
- pr_warn("btrfs: dev_replace cannot yet handle RAID5/RAID6\n");
+ btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6");
return -EINVAL;
}
@@ -325,7 +332,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
&tgt_device);
if (ret) {
- pr_err("btrfs: target device %s is invalid!\n",
+ btrfs_err(fs_info, "target device %s is invalid!",
args->start.tgtdev_name);
mutex_unlock(&fs_info->volume_mutex);
return -EINVAL;
@@ -341,7 +348,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
}
if (tgt_device->total_bytes < src_device->total_bytes) {
- pr_err("btrfs: target device is smaller than source device!\n");
+ btrfs_err(fs_info, "target device is smaller than source device!");
ret = -EINVAL;
goto leave_no_lock;
}
@@ -366,7 +373,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root,
dev_replace->tgtdev = tgt_device;
printk_in_rcu(KERN_INFO
- "btrfs: dev_replace from %s (devid %llu) to %s started\n",
+ "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
src_device->devid,
@@ -489,7 +496,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
if (scrub_ret) {
printk_in_rcu(KERN_ERR
- "btrfs: btrfs_scrub_dev(%s, %llu, %s) failed %d\n",
+ "BTRFS: btrfs_scrub_dev(%s, %llu, %s) failed %d\n",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
src_device->devid,
@@ -504,7 +511,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
}
printk_in_rcu(KERN_INFO
- "btrfs: dev_replace from %s (devid %llu) to %s) finished\n",
+ "BTRFS: dev_replace from %s (devid %llu) to %s) finished\n",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
src_device->devid,
@@ -699,7 +706,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
dev_replace->time_stopped = get_seconds();
dev_replace->item_needs_writeback = 1;
- pr_info("btrfs: suspending dev_replace for unmount\n");
+ btrfs_info(fs_info, "suspending dev_replace for unmount");
break;
}
@@ -728,8 +735,9 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
break;
}
if (!dev_replace->tgtdev || !dev_replace->tgtdev->bdev) {
- pr_info("btrfs: cannot continue dev_replace, tgtdev is missing\n"
- "btrfs: you may cancel the operation after 'mount -o degraded'\n");
+ btrfs_info(fs_info, "cannot continue dev_replace, tgtdev is missing");
+ btrfs_info(fs_info,
+ "you may cancel the operation after 'mount -o degraded'");
btrfs_dev_replace_unlock(dev_replace);
return 0;
}
@@ -755,14 +763,14 @@ static int btrfs_dev_replace_kthread(void *data)
kfree(status_args);
do_div(progress, 10);
printk_in_rcu(KERN_INFO
- "btrfs: continuing dev_replace from %s (devid %llu) to %s @%u%%\n",
- dev_replace->srcdev->missing ? "<missing disk>" :
- rcu_str_deref(dev_replace->srcdev->name),
- dev_replace->srcdev->devid,
- dev_replace->tgtdev ?
- rcu_str_deref(dev_replace->tgtdev->name) :
- "<missing target disk>",
- (unsigned int)progress);
+ "BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n",
+ dev_replace->srcdev->missing ? "<missing disk>" :
+ rcu_str_deref(dev_replace->srcdev->name),
+ dev_replace->srcdev->devid,
+ dev_replace->tgtdev ?
+ rcu_str_deref(dev_replace->tgtdev->name) :
+ "<missing target disk>",
+ (unsigned int)progress);
}
btrfs_dev_replace_continue_on_mount(fs_info);
atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index c031ea3fd70f..a0691df5dcea 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -261,7 +261,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
* see if there is room in the item to insert this
* name
*/
- data_size = sizeof(*di) + name_len + sizeof(struct btrfs_item);
+ data_size = sizeof(*di) + name_len;
leaf = path->nodes[0];
slot = path->slots[0];
if (data_size + btrfs_item_size_nr(leaf, slot) +
@@ -459,7 +459,7 @@ int verify_dir_item(struct btrfs_root *root,
u8 type = btrfs_dir_type(leaf, dir_item);
if (type >= BTRFS_FT_MAX) {
- printk(KERN_CRIT "btrfs: invalid dir item type: %d\n",
+ btrfs_crit(root->fs_info, "invalid dir item type: %d",
(int)type);
return 1;
}
@@ -468,7 +468,7 @@ int verify_dir_item(struct btrfs_root *root,
namelen = XATTR_NAME_MAX;
if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
- printk(KERN_CRIT "btrfs: invalid dir item name len: %u\n",
+ btrfs_crit(root->fs_info, "invalid dir item name len: %u",
(unsigned)btrfs_dir_data_len(leaf, dir_item));
return 1;
}
@@ -476,7 +476,7 @@ int verify_dir_item(struct btrfs_root *root,
/* BTRFS_MAX_XATTR_SIZE is the same for all dir items */
if ((btrfs_dir_data_len(leaf, dir_item) +
btrfs_dir_name_len(leaf, dir_item)) > BTRFS_MAX_XATTR_SIZE(root)) {
- printk(KERN_CRIT "btrfs: invalid dir item name + data len: %u + %u\n",
+ btrfs_crit(root->fs_info, "invalid dir item name + data len: %u + %u",
(unsigned)btrfs_dir_name_len(leaf, dir_item),
(unsigned)btrfs_dir_data_len(leaf, dir_item));
return 1;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8072cfa8a3b1..81ea55314b1f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -26,7 +26,6 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
-#include <linux/crc32c.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
@@ -35,6 +34,7 @@
#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
+#include "hash.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
@@ -48,6 +48,7 @@
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
+#include "sysfs.h"
#ifdef CONFIG_X86
#include <asm/cpufeature.h>
@@ -243,7 +244,7 @@ out:
u32 btrfs_csum_data(char *data, u32 seed, size_t len)
{
- return crc32c(seed, data, len);
+ return btrfs_crc32c(seed, data, len);
}
void btrfs_csum_final(u32 crc, char *result)
@@ -299,11 +300,11 @@ static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
memcpy(&found, result, csum_size);
read_extent_buffer(buf, &val, 0, csum_size);
- printk_ratelimited(KERN_INFO "btrfs: %s checksum verify "
- "failed on %llu wanted %X found %X "
- "level %d\n",
- root->fs_info->sb->s_id, buf->start,
- val, found, btrfs_header_level(buf));
+ printk_ratelimited(KERN_INFO
+ "BTRFS: %s checksum verify failed on %llu wanted %X found %X "
+ "level %d\n",
+ root->fs_info->sb->s_id, buf->start,
+ val, found, btrfs_header_level(buf));
if (result != (char *)&inline_result)
kfree(result);
return 1;
@@ -382,13 +383,14 @@ static int btrfs_check_super_csum(char *raw_disk_sb)
ret = 1;
if (ret && btrfs_super_generation(disk_sb) < 10) {
- printk(KERN_WARNING "btrfs: super block crcs don't match, older mkfs detected\n");
+ printk(KERN_WARNING
+ "BTRFS: super block crcs don't match, older mkfs detected\n");
ret = 0;
}
}
if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
- printk(KERN_ERR "btrfs: unsupported checksum algorithm %u\n",
+ printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n",
csum_type);
ret = 1;
}
@@ -464,13 +466,10 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
- struct extent_io_tree *tree;
u64 start = page_offset(page);
u64 found_start;
struct extent_buffer *eb;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
-
eb = (struct extent_buffer *)page->private;
if (page != eb->pages[0])
return 0;
@@ -500,8 +499,8 @@ static int check_tree_block_fsid(struct btrfs_root *root,
}
#define CORRUPT(reason, eb, root, slot) \
- printk(KERN_CRIT "btrfs: corrupt leaf, %s: block=%llu," \
- "root=%llu, slot=%d\n", reason, \
+ btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu," \
+ "root=%llu, slot=%d", reason, \
btrfs_header_bytenr(eb), root->objectid, slot)
static noinline int check_leaf(struct btrfs_root *root,
@@ -569,7 +568,6 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
u64 phy_offset, struct page *page,
u64 start, u64 end, int mirror)
{
- struct extent_io_tree *tree;
u64 found_start;
int found_level;
struct extent_buffer *eb;
@@ -580,7 +578,6 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
if (!page->private)
goto out;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
eb = (struct extent_buffer *)page->private;
/* the pending IO might have been the only thing that kept this buffer
@@ -600,21 +597,21 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
found_start = btrfs_header_bytenr(eb);
if (found_start != eb->start) {
- printk_ratelimited(KERN_INFO "btrfs bad tree block start "
+ printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
"%llu %llu\n",
found_start, eb->start);
ret = -EIO;
goto err;
}
if (check_tree_block_fsid(root, eb)) {
- printk_ratelimited(KERN_INFO "btrfs bad fsid on block %llu\n",
+ printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
eb->start);
ret = -EIO;
goto err;
}
found_level = btrfs_header_level(eb);
if (found_level >= BTRFS_MAX_LEVEL) {
- btrfs_info(root->fs_info, "bad tree block level %d\n",
+ btrfs_info(root->fs_info, "bad tree block level %d",
(int)btrfs_header_level(eb));
ret = -EIO;
goto err;
@@ -842,20 +839,17 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
static int btree_csum_one_bio(struct bio *bio)
{
- struct bio_vec *bvec = bio->bi_io_vec;
- int bio_index = 0;
+ struct bio_vec *bvec;
struct btrfs_root *root;
- int ret = 0;
+ int i, ret = 0;
- WARN_ON(bio->bi_vcnt <= 0);
- while (bio_index < bio->bi_vcnt) {
+ bio_for_each_segment_all(bvec, bio, i) {
root = BTRFS_I(bvec->bv_page->mapping->host)->root;
ret = csum_dirty_buffer(root, bvec->bv_page);
if (ret)
break;
- bio_index++;
- bvec++;
}
+
return ret;
}
@@ -967,11 +961,9 @@ static int btree_migratepage(struct address_space *mapping,
static int btree_writepages(struct address_space *mapping,
struct writeback_control *wbc)
{
- struct extent_io_tree *tree;
struct btrfs_fs_info *fs_info;
int ret;
- tree = &BTRFS_I(mapping->host)->io_tree;
if (wbc->sync_mode == WB_SYNC_NONE) {
if (wbc->for_kupdate)
@@ -1010,8 +1002,9 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
extent_invalidatepage(tree, page, offset);
btree_releasepage(page, GFP_NOFS);
if (PagePrivate(page)) {
- printk(KERN_WARNING "btrfs warning page private not zero "
- "on page %llu\n", (unsigned long long)page_offset(page));
+ btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
+ "page private not zero on page %llu",
+ (unsigned long long)page_offset(page));
ClearPagePrivate(page);
set_page_private(page, 0);
page_cache_release(page);
@@ -1095,21 +1088,13 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
- eb = find_extent_buffer(&BTRFS_I(btree_inode)->io_tree, bytenr);
- return eb;
+ return find_extent_buffer(root->fs_info, bytenr);
}
struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
u64 bytenr, u32 blocksize)
{
- struct inode *btree_inode = root->fs_info->btree_inode;
- struct extent_buffer *eb;
-
- eb = alloc_extent_buffer(&BTRFS_I(btree_inode)->io_tree,
- bytenr, blocksize);
- return eb;
+ return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
}
@@ -1273,7 +1258,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
struct btrfs_root *root;
struct btrfs_key key;
int ret = 0;
- u64 bytenr;
uuid_le uuid;
root = btrfs_alloc_root(fs_info);
@@ -1295,7 +1279,6 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
goto fail;
}
- bytenr = leaf->start;
memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
btrfs_set_header_bytenr(leaf, leaf->start);
btrfs_set_header_generation(leaf, trans->transid);
@@ -1616,7 +1599,8 @@ again:
if (ret)
goto fail;
- ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
+ ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
+ location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
if (ret < 0)
goto fail;
if (ret == 0)
@@ -1684,18 +1668,16 @@ static void end_workqueue_fn(struct btrfs_work *work)
{
struct bio *bio;
struct end_io_wq *end_io_wq;
- struct btrfs_fs_info *fs_info;
int error;
end_io_wq = container_of(work, struct end_io_wq, work);
bio = end_io_wq->bio;
- fs_info = end_io_wq->info;
error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kfree(end_io_wq);
- bio_endio(bio, error);
+ bio_endio_nodec(bio, error);
}
static int cleaner_kthread(void *arg)
@@ -2080,6 +2062,12 @@ static void del_fs_roots(struct btrfs_fs_info *fs_info)
for (i = 0; i < ret; i++)
btrfs_drop_and_free_fs_root(fs_info, gang[i]);
}
+
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ btrfs_free_log_root_tree(NULL, fs_info);
+ btrfs_destroy_pinned_extent(fs_info->tree_root,
+ fs_info->pinned_extents);
+ }
}
int open_ctree(struct super_block *sb,
@@ -2154,6 +2142,7 @@ int open_ctree(struct super_block *sb,
mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
+ INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
INIT_LIST_HEAD(&fs_info->trans_list);
INIT_LIST_HEAD(&fs_info->dead_roots);
INIT_LIST_HEAD(&fs_info->delayed_iputs);
@@ -2167,6 +2156,7 @@ int open_ctree(struct super_block *sb,
spin_lock_init(&fs_info->free_chunk_lock);
spin_lock_init(&fs_info->tree_mod_seq_lock);
spin_lock_init(&fs_info->super_lock);
+ spin_lock_init(&fs_info->buffer_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->reloc_mutex);
seqlock_init(&fs_info->profiles_lock);
@@ -2198,7 +2188,7 @@ int open_ctree(struct super_block *sb,
fs_info->free_chunk_space = 0;
fs_info->tree_mod_log = RB_ROOT;
fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
-
+ fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64);
/* readahead state */
INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
spin_lock_init(&fs_info->reada_lock);
@@ -2337,7 +2327,7 @@ int open_ctree(struct super_block *sb,
* Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/
if (btrfs_check_super_csum(bh->b_data)) {
- printk(KERN_ERR "btrfs: superblock checksum mismatch\n");
+ printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
err = -EINVAL;
goto fail_alloc;
}
@@ -2356,7 +2346,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
if (ret) {
- printk(KERN_ERR "btrfs: superblock contains fatal errors\n");
+ printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
err = -EINVAL;
goto fail_alloc;
}
@@ -2421,7 +2411,7 @@ int open_ctree(struct super_block *sb,
features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
- printk(KERN_ERR "btrfs: has skinny extents\n");
+ printk(KERN_ERR "BTRFS: has skinny extents\n");
/*
* flag our filesystem as having big metadata blocks if
@@ -2429,7 +2419,7 @@ int open_ctree(struct super_block *sb,
*/
if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
- printk(KERN_INFO "btrfs flagging fs with big metadata feature\n");
+ printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
}
@@ -2446,7 +2436,7 @@ int open_ctree(struct super_block *sb,
*/
if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
(sectorsize != leafsize)) {
- printk(KERN_WARNING "btrfs: unequal leaf/node/sector sizes "
+ printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
"are not allowed for mixed block groups on %s\n",
sb->s_id);
goto fail_alloc;
@@ -2583,12 +2573,12 @@ int open_ctree(struct super_block *sb,
sb->s_blocksize_bits = blksize_bits(sectorsize);
if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
- printk(KERN_INFO "btrfs: valid FS not found on %s\n", sb->s_id);
+ printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
goto fail_sb_buffer;
}
if (sectorsize != PAGE_SIZE) {
- printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+ printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
"found on %s\n", (unsigned long)sectorsize, sb->s_id);
goto fail_sb_buffer;
}
@@ -2597,7 +2587,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_sys_array(tree_root);
mutex_unlock(&fs_info->chunk_mutex);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read the system "
+ printk(KERN_WARNING "BTRFS: failed to read the system "
"array on %s\n", sb->s_id);
goto fail_sb_buffer;
}
@@ -2614,7 +2604,7 @@ int open_ctree(struct super_block *sb,
blocksize, generation);
if (!chunk_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read chunk root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2626,7 +2616,7 @@ int open_ctree(struct super_block *sb,
ret = btrfs_read_chunk_tree(chunk_root);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to read chunk tree on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2638,7 +2628,7 @@ int open_ctree(struct super_block *sb,
btrfs_close_extra_devices(fs_info, fs_devices, 0);
if (!fs_devices->latest_bdev) {
- printk(KERN_CRIT "btrfs: failed to read devices on %s\n",
+ printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
sb->s_id);
goto fail_tree_roots;
}
@@ -2653,7 +2643,7 @@ retry_root_backup:
blocksize, generation);
if (!tree_root->node ||
!test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
- printk(KERN_WARNING "btrfs: failed to read tree root on %s\n",
+ printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
sb->s_id);
goto recovery_tree_root;
@@ -2724,50 +2714,56 @@ retry_root_backup:
ret = btrfs_recover_balance(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to recover balance\n");
+ printk(KERN_WARNING "BTRFS: failed to recover balance\n");
goto fail_block_groups;
}
ret = btrfs_init_dev_stats(fs_info);
if (ret) {
- printk(KERN_ERR "btrfs: failed to init dev_stats: %d\n",
+ printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
ret);
goto fail_block_groups;
}
ret = btrfs_init_dev_replace(fs_info);
if (ret) {
- pr_err("btrfs: failed to init dev_replace: %d\n", ret);
+ pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
goto fail_block_groups;
}
btrfs_close_extra_devices(fs_info, fs_devices, 1);
- ret = btrfs_init_space_info(fs_info);
+ ret = btrfs_sysfs_add_one(fs_info);
if (ret) {
- printk(KERN_ERR "Failed to initial space info: %d\n", ret);
+ pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
goto fail_block_groups;
}
+ ret = btrfs_init_space_info(fs_info);
+ if (ret) {
+ printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
+ goto fail_sysfs;
+ }
+
ret = btrfs_read_block_groups(extent_root);
if (ret) {
- printk(KERN_ERR "Failed to read block groups: %d\n", ret);
- goto fail_block_groups;
+ printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
+ goto fail_sysfs;
}
fs_info->num_tolerated_disk_barrier_failures =
btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(sb->s_flags & MS_RDONLY)) {
- printk(KERN_WARNING
- "Btrfs: too many missing devices, writeable mount is not allowed\n");
- goto fail_block_groups;
+ printk(KERN_WARNING "BTRFS: "
+ "too many missing devices, writeable mount is not allowed\n");
+ goto fail_sysfs;
}
fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
"btrfs-cleaner");
if (IS_ERR(fs_info->cleaner_kthread))
- goto fail_block_groups;
+ goto fail_sysfs;
fs_info->transaction_kthread = kthread_run(transaction_kthread,
tree_root,
@@ -2778,11 +2774,15 @@ retry_root_backup:
if (!btrfs_test_opt(tree_root, SSD) &&
!btrfs_test_opt(tree_root, NOSSD) &&
!fs_info->fs_devices->rotating) {
- printk(KERN_INFO "Btrfs detected SSD devices, enabling SSD "
+ printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
"mode\n");
btrfs_set_opt(fs_info->mount_opt, SSD);
}
+ /* Set the real inode map cache flag */
+ if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
+ btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);
+
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
ret = btrfsic_mount(tree_root, fs_devices,
@@ -2791,7 +2791,7 @@ retry_root_backup:
1 : 0,
fs_info->check_integrity_print_mask);
if (ret)
- printk(KERN_WARNING "btrfs: failed to initialize"
+ printk(KERN_WARNING "BTRFS: failed to initialize"
" integrity check module %s\n", sb->s_id);
}
#endif
@@ -2804,7 +2804,7 @@ retry_root_backup:
u64 bytenr = btrfs_super_log_root(disk_super);
if (fs_devices->rw_devices == 0) {
- printk(KERN_WARNING "Btrfs log replay required "
+ printk(KERN_WARNING "BTRFS: log replay required "
"on RO media\n");
err = -EIO;
goto fail_qgroup;
@@ -2827,7 +2827,7 @@ retry_root_backup:
generation + 1);
if (!log_tree_root->node ||
!extent_buffer_uptodate(log_tree_root->node)) {
- printk(KERN_ERR "btrfs: failed to read log tree\n");
+ printk(KERN_ERR "BTRFS: failed to read log tree\n");
free_extent_buffer(log_tree_root->node);
kfree(log_tree_root);
goto fail_trans_kthread;
@@ -2861,7 +2861,7 @@ retry_root_backup:
ret = btrfs_recover_relocation(tree_root);
if (ret < 0) {
printk(KERN_WARNING
- "btrfs: failed to recover relocation\n");
+ "BTRFS: failed to recover relocation\n");
err = -EINVAL;
goto fail_qgroup;
}
@@ -2891,14 +2891,14 @@ retry_root_backup:
ret = btrfs_resume_balance_async(fs_info);
if (ret) {
- printk(KERN_WARNING "btrfs: failed to resume balance\n");
+ printk(KERN_WARNING "BTRFS: failed to resume balance\n");
close_ctree(tree_root);
return ret;
}
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("btrfs: failed to resume dev_replace\n");
+ pr_warn("BTRFS: failed to resume dev_replace\n");
close_ctree(tree_root);
return ret;
}
@@ -2906,20 +2906,20 @@ retry_root_backup:
btrfs_qgroup_rescan_resume(fs_info);
if (create_uuid_tree) {
- pr_info("btrfs: creating UUID tree\n");
+ pr_info("BTRFS: creating UUID tree\n");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to create the UUID tree %d\n",
+ pr_warn("BTRFS: failed to create the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
}
} else if (check_uuid_tree ||
btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
- pr_info("btrfs: checking UUID tree\n");
+ pr_info("BTRFS: checking UUID tree\n");
ret = btrfs_check_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to check the UUID tree %d\n",
+ pr_warn("BTRFS: failed to check the UUID tree %d\n",
ret);
close_ctree(tree_root);
return ret;
@@ -2945,6 +2945,9 @@ fail_cleaner:
*/
filemap_write_and_wait(fs_info->btree_inode->i_mapping);
+fail_sysfs:
+ btrfs_sysfs_remove_one(fs_info);
+
fail_block_groups:
btrfs_put_block_group_cache(fs_info);
btrfs_free_block_groups(fs_info);
@@ -3000,7 +3003,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
struct btrfs_device *device = (struct btrfs_device *)
bh->b_private;
- printk_ratelimited_in_rcu(KERN_WARNING "lost page write due to "
+ printk_ratelimited_in_rcu(KERN_WARNING "BTRFS: lost page write due to "
"I/O error on %s\n",
rcu_str_deref(device->name));
/* note, we dont' set_buffer_write_io_error because we have
@@ -3119,7 +3122,7 @@ static int write_dev_supers(struct btrfs_device *device,
bh = __getblk(device->bdev, bytenr / 4096,
BTRFS_SUPER_INFO_SIZE);
if (!bh) {
- printk(KERN_ERR "btrfs: couldn't get super "
+ printk(KERN_ERR "BTRFS: couldn't get super "
"buffer head for bytenr %Lu\n", bytenr);
errors++;
continue;
@@ -3140,7 +3143,10 @@ static int write_dev_supers(struct btrfs_device *device,
* we fua the first super. The others we allow
* to go down lazy.
*/
- ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ if (i == 0)
+ ret = btrfsic_submit_bh(WRITE_FUA, bh);
+ else
+ ret = btrfsic_submit_bh(WRITE_SYNC, bh);
if (ret)
errors++;
}
@@ -3186,7 +3192,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait)
wait_for_completion(&device->flush_wait);
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
- printk_in_rcu("btrfs: disabling barriers on dev %s\n",
+ printk_in_rcu("BTRFS: disabling barriers on dev %s\n",
rcu_str_deref(device->name));
device->nobarriers = 1;
} else if (!bio_flagged(bio, BIO_UPTODATE)) {
@@ -3407,7 +3413,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
total_errors++;
}
if (total_errors > max_errors) {
- printk(KERN_ERR "btrfs: %d errors while writing supers\n",
+ btrfs_err(root->fs_info, "%d errors while writing supers",
total_errors);
mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
@@ -3455,10 +3461,8 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
if (btrfs_root_refs(&root->root_item) == 0)
synchronize_srcu(&fs_info->subvol_srcu);
- if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_free_log(NULL, root);
- btrfs_free_log_root_tree(NULL, fs_info);
- }
__btrfs_remove_free_space_cache(root->free_ino_pinned);
__btrfs_remove_free_space_cache(root->free_ino_ctl);
@@ -3563,14 +3567,12 @@ int close_ctree(struct btrfs_root *root)
if (!(fs_info->sb->s_flags & MS_RDONLY)) {
ret = btrfs_commit_super(root);
if (ret)
- printk(KERN_ERR "btrfs: commit super ret %d\n", ret);
+ btrfs_err(root->fs_info, "commit super ret %d", ret);
}
if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
btrfs_error_commit_super(root);
- btrfs_put_block_group_cache(fs_info);
-
kthread_stop(fs_info->transaction_kthread);
kthread_stop(fs_info->cleaner_kthread);
@@ -3580,12 +3582,16 @@ int close_ctree(struct btrfs_root *root)
btrfs_free_qgroup_config(root->fs_info);
if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
- printk(KERN_INFO "btrfs: at unmount delalloc count %lld\n",
+ btrfs_info(root->fs_info, "at unmount delalloc count %lld",
percpu_counter_sum(&fs_info->delalloc_bytes));
}
+ btrfs_sysfs_remove_one(fs_info);
+
del_fs_roots(fs_info);
+ btrfs_put_block_group_cache(fs_info);
+
btrfs_free_block_groups(fs_info);
btrfs_stop_all_workers(fs_info);
@@ -3803,55 +3809,54 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
delayed_refs = &trans->delayed_refs;
spin_lock(&delayed_refs->lock);
- if (delayed_refs->num_entries == 0) {
+ if (atomic_read(&delayed_refs->num_entries) == 0) {
spin_unlock(&delayed_refs->lock);
- printk(KERN_INFO "delayed_refs has NO entry\n");
+ btrfs_info(root->fs_info, "delayed_refs has NO entry");
return ret;
}
- while ((node = rb_first(&delayed_refs->root)) != NULL) {
- struct btrfs_delayed_ref_head *head = NULL;
+ while ((node = rb_first(&delayed_refs->href_root)) != NULL) {
+ struct btrfs_delayed_ref_head *head;
bool pin_bytes = false;
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- atomic_set(&ref->refs, 1);
- if (btrfs_delayed_ref_is_head(ref)) {
-
- head = btrfs_delayed_node_to_head(ref);
- if (!mutex_trylock(&head->mutex)) {
- atomic_inc(&ref->refs);
- spin_unlock(&delayed_refs->lock);
-
- /* Need to wait for the delayed ref to run */
- mutex_lock(&head->mutex);
- mutex_unlock(&head->mutex);
- btrfs_put_delayed_ref(ref);
-
- spin_lock(&delayed_refs->lock);
- continue;
- }
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ if (!mutex_trylock(&head->mutex)) {
+ atomic_inc(&head->node.refs);
+ spin_unlock(&delayed_refs->lock);
- if (head->must_insert_reserved)
- pin_bytes = true;
- btrfs_free_delayed_extent_op(head->extent_op);
- delayed_refs->num_heads--;
- if (list_empty(&head->cluster))
- delayed_refs->num_heads_ready--;
- list_del_init(&head->cluster);
- }
-
- ref->in_tree = 0;
- rb_erase(&ref->rb_node, &delayed_refs->root);
- delayed_refs->num_entries--;
- spin_unlock(&delayed_refs->lock);
- if (head) {
- if (pin_bytes)
- btrfs_pin_extent(root, ref->bytenr,
- ref->num_bytes, 1);
+ mutex_lock(&head->mutex);
mutex_unlock(&head->mutex);
+ btrfs_put_delayed_ref(&head->node);
+ spin_lock(&delayed_refs->lock);
+ continue;
+ }
+ spin_lock(&head->lock);
+ while ((node = rb_first(&head->ref_root)) != NULL) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node,
+ rb_node);
+ ref->in_tree = 0;
+ rb_erase(&ref->rb_node, &head->ref_root);
+ atomic_dec(&delayed_refs->num_entries);
+ btrfs_put_delayed_ref(ref);
}
- btrfs_put_delayed_ref(ref);
+ if (head->must_insert_reserved)
+ pin_bytes = true;
+ btrfs_free_delayed_extent_op(head->extent_op);
+ delayed_refs->num_heads--;
+ if (head->processing == 0)
+ delayed_refs->num_heads_ready--;
+ atomic_dec(&delayed_refs->num_entries);
+ head->node.in_tree = 0;
+ rb_erase(&head->href_node, &delayed_refs->href_root);
+ spin_unlock(&head->lock);
+ spin_unlock(&delayed_refs->lock);
+ mutex_unlock(&head->mutex);
+ if (pin_bytes)
+ btrfs_pin_extent(root, head->node.bytenr,
+ head->node.num_bytes, 1);
+ btrfs_put_delayed_ref(&head->node);
cond_resched();
spin_lock(&delayed_refs->lock);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9c01509dd8ab..32312e09f0f5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -35,6 +35,7 @@
#include "locking.h"
#include "free-space-cache.h"
#include "math.h"
+#include "sysfs.h"
#undef SCRAMBLE_DELAYED_REFS
@@ -441,7 +442,8 @@ next:
if (ret)
break;
- if (need_resched()) {
+ if (need_resched() ||
+ rwsem_is_contended(&fs_info->extent_commit_sem)) {
caching_ctl->progress = last;
btrfs_release_path(path);
up_read(&fs_info->extent_commit_sem);
@@ -855,12 +857,14 @@ again:
btrfs_put_delayed_ref(&head->node);
goto search_again;
}
+ spin_lock(&head->lock);
if (head->extent_op && head->extent_op->update_flags)
extent_flags |= head->extent_op->flags_to_set;
else
BUG_ON(num_refs == 0);
num_refs += head->node.ref_mod;
+ spin_unlock(&head->lock);
mutex_unlock(&head->mutex);
}
spin_unlock(&delayed_refs->lock);
@@ -1070,11 +1074,11 @@ static u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset)
__le64 lenum;
lenum = cpu_to_le64(root_objectid);
- high_crc = crc32c(high_crc, &lenum, sizeof(lenum));
+ high_crc = btrfs_crc32c(high_crc, &lenum, sizeof(lenum));
lenum = cpu_to_le64(owner);
- low_crc = crc32c(low_crc, &lenum, sizeof(lenum));
+ low_crc = btrfs_crc32c(low_crc, &lenum, sizeof(lenum));
lenum = cpu_to_le64(offset);
- low_crc = crc32c(low_crc, &lenum, sizeof(lenum));
+ low_crc = btrfs_crc32c(low_crc, &lenum, sizeof(lenum));
return ((u64)high_crc << 31) ^ (u64)low_crc;
}
@@ -2285,64 +2289,62 @@ static noinline struct btrfs_delayed_ref_node *
select_delayed_ref(struct btrfs_delayed_ref_head *head)
{
struct rb_node *node;
- struct btrfs_delayed_ref_node *ref;
- int action = BTRFS_ADD_DELAYED_REF;
-again:
+ struct btrfs_delayed_ref_node *ref, *last = NULL;;
+
/*
* select delayed ref of type BTRFS_ADD_DELAYED_REF first.
* this prevents ref count from going down to zero when
* there still are pending delayed ref.
*/
- node = rb_prev(&head->node.rb_node);
- while (1) {
- if (!node)
- break;
+ node = rb_first(&head->ref_root);
+ while (node) {
ref = rb_entry(node, struct btrfs_delayed_ref_node,
rb_node);
- if (ref->bytenr != head->node.bytenr)
- break;
- if (ref->action == action)
+ if (ref->action == BTRFS_ADD_DELAYED_REF)
return ref;
- node = rb_prev(node);
- }
- if (action == BTRFS_ADD_DELAYED_REF) {
- action = BTRFS_DROP_DELAYED_REF;
- goto again;
+ else if (last == NULL)
+ last = ref;
+ node = rb_next(node);
}
- return NULL;
+ return last;
}
/*
* Returns 0 on success or if called with an already aborted transaction.
* Returns -ENOMEM or -EIO on failure and will abort the transaction.
*/
-static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct list_head *cluster)
+static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ unsigned long nr)
{
struct btrfs_delayed_ref_root *delayed_refs;
struct btrfs_delayed_ref_node *ref;
struct btrfs_delayed_ref_head *locked_ref = NULL;
struct btrfs_delayed_extent_op *extent_op;
struct btrfs_fs_info *fs_info = root->fs_info;
+ ktime_t start = ktime_get();
int ret;
- int count = 0;
+ unsigned long count = 0;
+ unsigned long actual_count = 0;
int must_insert_reserved = 0;
delayed_refs = &trans->transaction->delayed_refs;
while (1) {
if (!locked_ref) {
- /* pick a new head ref from the cluster list */
- if (list_empty(cluster))
+ if (count >= nr)
break;
- locked_ref = list_entry(cluster->next,
- struct btrfs_delayed_ref_head, cluster);
+ spin_lock(&delayed_refs->lock);
+ locked_ref = btrfs_select_ref_head(trans);
+ if (!locked_ref) {
+ spin_unlock(&delayed_refs->lock);
+ break;
+ }
/* grab the lock that says we are going to process
* all the refs for this head */
ret = btrfs_delayed_ref_lock(trans, locked_ref);
-
+ spin_unlock(&delayed_refs->lock);
/*
* we may have dropped the spin lock to get the head
* mutex lock, and that might have given someone else
@@ -2363,6 +2365,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
* finish. If we merged anything we need to re-loop so we can
* get a good ref.
*/
+ spin_lock(&locked_ref->lock);
btrfs_merge_delayed_refs(trans, fs_info, delayed_refs,
locked_ref);
@@ -2374,17 +2377,15 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
if (ref && ref->seq &&
btrfs_check_delayed_seq(fs_info, delayed_refs, ref->seq)) {
- /*
- * there are still refs with lower seq numbers in the
- * process of being added. Don't run this ref yet.
- */
- list_del_init(&locked_ref->cluster);
+ spin_unlock(&locked_ref->lock);
btrfs_delayed_ref_unlock(locked_ref);
- locked_ref = NULL;
+ spin_lock(&delayed_refs->lock);
+ locked_ref->processing = 0;
delayed_refs->num_heads_ready++;
spin_unlock(&delayed_refs->lock);
+ locked_ref = NULL;
cond_resched();
- spin_lock(&delayed_refs->lock);
+ count++;
continue;
}
@@ -2399,6 +2400,8 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
locked_ref->extent_op = NULL;
if (!ref) {
+
+
/* All delayed refs have been processed, Go ahead
* and send the head node to run_one_delayed_ref,
* so that any accounting fixes can happen
@@ -2411,8 +2414,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
}
if (extent_op) {
- spin_unlock(&delayed_refs->lock);
-
+ spin_unlock(&locked_ref->lock);
ret = run_delayed_extent_op(trans, root,
ref, extent_op);
btrfs_free_delayed_extent_op(extent_op);
@@ -2426,19 +2428,39 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
*/
if (must_insert_reserved)
locked_ref->must_insert_reserved = 1;
+ locked_ref->processing = 0;
btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
- spin_lock(&delayed_refs->lock);
btrfs_delayed_ref_unlock(locked_ref);
return ret;
}
+ continue;
+ }
- goto next;
+ /*
+ * Need to drop our head ref lock and re-aqcuire the
+ * delayed ref lock and then re-check to make sure
+ * nobody got added.
+ */
+ spin_unlock(&locked_ref->lock);
+ spin_lock(&delayed_refs->lock);
+ spin_lock(&locked_ref->lock);
+ if (rb_first(&locked_ref->ref_root)) {
+ spin_unlock(&locked_ref->lock);
+ spin_unlock(&delayed_refs->lock);
+ continue;
}
+ ref->in_tree = 0;
+ delayed_refs->num_heads--;
+ rb_erase(&locked_ref->href_node,
+ &delayed_refs->href_root);
+ spin_unlock(&delayed_refs->lock);
+ } else {
+ actual_count++;
+ ref->in_tree = 0;
+ rb_erase(&ref->rb_node, &locked_ref->ref_root);
}
+ atomic_dec(&delayed_refs->num_entries);
- ref->in_tree = 0;
- rb_erase(&ref->rb_node, &delayed_refs->root);
- delayed_refs->num_entries--;
if (!btrfs_delayed_ref_is_head(ref)) {
/*
* when we play the delayed ref, also correct the
@@ -2455,20 +2477,18 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
default:
WARN_ON(1);
}
- } else {
- list_del_init(&locked_ref->cluster);
}
- spin_unlock(&delayed_refs->lock);
+ spin_unlock(&locked_ref->lock);
ret = run_one_delayed_ref(trans, root, ref, extent_op,
must_insert_reserved);
btrfs_free_delayed_extent_op(extent_op);
if (ret) {
+ locked_ref->processing = 0;
btrfs_delayed_ref_unlock(locked_ref);
btrfs_put_delayed_ref(ref);
btrfs_debug(fs_info, "run_one_delayed_ref returned %d", ret);
- spin_lock(&delayed_refs->lock);
return ret;
}
@@ -2484,11 +2504,29 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
}
btrfs_put_delayed_ref(ref);
count++;
-next:
cond_resched();
+ }
+
+ /*
+ * We don't want to include ref heads since we can have empty ref heads
+ * and those will drastically skew our runtime down since we just do
+ * accounting, no actual extent tree updates.
+ */
+ if (actual_count > 0) {
+ u64 runtime = ktime_to_ns(ktime_sub(ktime_get(), start));
+ u64 avg;
+
+ /*
+ * We weigh the current average higher than our current runtime
+ * to avoid large swings in the average.
+ */
spin_lock(&delayed_refs->lock);
+ avg = fs_info->avg_delayed_ref_runtime * 3 + runtime;
+ avg = div64_u64(avg, 4);
+ fs_info->avg_delayed_ref_runtime = avg;
+ spin_unlock(&delayed_refs->lock);
}
- return count;
+ return 0;
}
#ifdef SCRAMBLE_DELAYED_REFS
@@ -2570,16 +2608,6 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
return ret;
}
-static int refs_newer(struct btrfs_delayed_ref_root *delayed_refs, int seq,
- int count)
-{
- int val = atomic_read(&delayed_refs->ref_seq);
-
- if (val < seq || val >= seq + count)
- return 1;
- return 0;
-}
-
static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads)
{
u64 num_bytes;
@@ -2596,7 +2624,7 @@ static inline u64 heads_to_leaves(struct btrfs_root *root, u64 heads)
return div64_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(root));
}
-int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
+int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_block_rsv *global_rsv;
@@ -2625,6 +2653,22 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
return ret;
}
+int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ u64 num_entries =
+ atomic_read(&trans->transaction->delayed_refs.num_entries);
+ u64 avg_runtime;
+
+ smp_mb();
+ avg_runtime = fs_info->avg_delayed_ref_runtime;
+ if (num_entries * avg_runtime >= NSEC_PER_SEC)
+ return 1;
+
+ return btrfs_check_space_for_delayed_refs(trans, root);
+}
+
/*
* this starts processing the delayed reference count updates and
* extent insertions we have queued up so far. count can be
@@ -2640,13 +2684,10 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
{
struct rb_node *node;
struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_delayed_ref_node *ref;
- struct list_head cluster;
+ struct btrfs_delayed_ref_head *head;
int ret;
- u64 delayed_start;
int run_all = count == (unsigned long)-1;
int run_most = 0;
- int loops;
/* We'll clean this up in btrfs_cleanup_transaction */
if (trans->aborted)
@@ -2658,130 +2699,40 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
btrfs_delayed_refs_qgroup_accounting(trans, root->fs_info);
delayed_refs = &trans->transaction->delayed_refs;
- INIT_LIST_HEAD(&cluster);
if (count == 0) {
- count = delayed_refs->num_entries * 2;
+ count = atomic_read(&delayed_refs->num_entries) * 2;
run_most = 1;
}
- if (!run_all && !run_most) {
- int old;
- int seq = atomic_read(&delayed_refs->ref_seq);
-
-progress:
- old = atomic_cmpxchg(&delayed_refs->procs_running_refs, 0, 1);
- if (old) {
- DEFINE_WAIT(__wait);
- if (delayed_refs->flushing ||
- !btrfs_should_throttle_delayed_refs(trans, root))
- return 0;
-
- prepare_to_wait(&delayed_refs->wait, &__wait,
- TASK_UNINTERRUPTIBLE);
-
- old = atomic_cmpxchg(&delayed_refs->procs_running_refs, 0, 1);
- if (old) {
- schedule();
- finish_wait(&delayed_refs->wait, &__wait);
-
- if (!refs_newer(delayed_refs, seq, 256))
- goto progress;
- else
- return 0;
- } else {
- finish_wait(&delayed_refs->wait, &__wait);
- goto again;
- }
- }
-
- } else {
- atomic_inc(&delayed_refs->procs_running_refs);
- }
-
again:
- loops = 0;
- spin_lock(&delayed_refs->lock);
-
#ifdef SCRAMBLE_DELAYED_REFS
delayed_refs->run_delayed_start = find_middle(&delayed_refs->root);
#endif
-
- while (1) {
- if (!(run_all || run_most) &&
- !btrfs_should_throttle_delayed_refs(trans, root))
- break;
-
- /*
- * go find something we can process in the rbtree. We start at
- * the beginning of the tree, and then build a cluster
- * of refs to process starting at the first one we are able to
- * lock
- */
- delayed_start = delayed_refs->run_delayed_start;
- ret = btrfs_find_ref_cluster(trans, &cluster,
- delayed_refs->run_delayed_start);
- if (ret)
- break;
-
- ret = run_clustered_refs(trans, root, &cluster);
- if (ret < 0) {
- btrfs_release_ref_cluster(&cluster);
- spin_unlock(&delayed_refs->lock);
- btrfs_abort_transaction(trans, root, ret);
- atomic_dec(&delayed_refs->procs_running_refs);
- wake_up(&delayed_refs->wait);
- return ret;
- }
-
- atomic_add(ret, &delayed_refs->ref_seq);
-
- count -= min_t(unsigned long, ret, count);
-
- if (count == 0)
- break;
-
- if (delayed_start >= delayed_refs->run_delayed_start) {
- if (loops == 0) {
- /*
- * btrfs_find_ref_cluster looped. let's do one
- * more cycle. if we don't run any delayed ref
- * during that cycle (because we can't because
- * all of them are blocked), bail out.
- */
- loops = 1;
- } else {
- /*
- * no runnable refs left, stop trying
- */
- BUG_ON(run_all);
- break;
- }
- }
- if (ret) {
- /* refs were run, let's reset staleness detection */
- loops = 0;
- }
+ ret = __btrfs_run_delayed_refs(trans, root, count);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, root, ret);
+ return ret;
}
if (run_all) {
- if (!list_empty(&trans->new_bgs)) {
- spin_unlock(&delayed_refs->lock);
+ if (!list_empty(&trans->new_bgs))
btrfs_create_pending_block_groups(trans, root);
- spin_lock(&delayed_refs->lock);
- }
- node = rb_first(&delayed_refs->root);
- if (!node)
+ spin_lock(&delayed_refs->lock);
+ node = rb_first(&delayed_refs->href_root);
+ if (!node) {
+ spin_unlock(&delayed_refs->lock);
goto out;
+ }
count = (unsigned long)-1;
while (node) {
- ref = rb_entry(node, struct btrfs_delayed_ref_node,
- rb_node);
- if (btrfs_delayed_ref_is_head(ref)) {
- struct btrfs_delayed_ref_head *head;
+ head = rb_entry(node, struct btrfs_delayed_ref_head,
+ href_node);
+ if (btrfs_delayed_ref_is_head(&head->node)) {
+ struct btrfs_delayed_ref_node *ref;
- head = btrfs_delayed_node_to_head(ref);
+ ref = &head->node;
atomic_inc(&ref->refs);
spin_unlock(&delayed_refs->lock);
@@ -2795,20 +2746,16 @@ again:
btrfs_put_delayed_ref(ref);
cond_resched();
goto again;
+ } else {
+ WARN_ON(1);
}
node = rb_next(node);
}
spin_unlock(&delayed_refs->lock);
- schedule_timeout(1);
+ cond_resched();
goto again;
}
out:
- atomic_dec(&delayed_refs->procs_running_refs);
- smp_mb();
- if (waitqueue_active(&delayed_refs->wait))
- wake_up(&delayed_refs->wait);
-
- spin_unlock(&delayed_refs->lock);
assert_qgroups_uptodate(trans);
return 0;
}
@@ -2850,12 +2797,13 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
struct rb_node *node;
int ret = 0;
- ret = -ENOENT;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
head = btrfs_find_delayed_ref_head(trans, bytenr);
- if (!head)
- goto out;
+ if (!head) {
+ spin_unlock(&delayed_refs->lock);
+ return 0;
+ }
if (!mutex_trylock(&head->mutex)) {
atomic_inc(&head->node.refs);
@@ -2872,40 +2820,35 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
btrfs_put_delayed_ref(&head->node);
return -EAGAIN;
}
+ spin_unlock(&delayed_refs->lock);
- node = rb_prev(&head->node.rb_node);
- if (!node)
- goto out_unlock;
-
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
-
- if (ref->bytenr != bytenr)
- goto out_unlock;
-
- ret = 1;
- if (ref->type != BTRFS_EXTENT_DATA_REF_KEY)
- goto out_unlock;
+ spin_lock(&head->lock);
+ node = rb_first(&head->ref_root);
+ while (node) {
+ ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
+ node = rb_next(node);
- data_ref = btrfs_delayed_node_to_data_ref(ref);
+ /* If it's a shared ref we know a cross reference exists */
+ if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) {
+ ret = 1;
+ break;
+ }
- node = rb_prev(node);
- if (node) {
- int seq = ref->seq;
+ data_ref = btrfs_delayed_node_to_data_ref(ref);
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
- if (ref->bytenr == bytenr && ref->seq == seq)
- goto out_unlock;
+ /*
+ * If our ref doesn't match the one we're currently looking at
+ * then we have a cross reference.
+ */
+ if (data_ref->root != root->root_key.objectid ||
+ data_ref->objectid != objectid ||
+ data_ref->offset != offset) {
+ ret = 1;
+ break;
+ }
}
-
- if (data_ref->root != root->root_key.objectid ||
- data_ref->objectid != objectid || data_ref->offset != offset)
- goto out_unlock;
-
- ret = 0;
-out_unlock:
+ spin_unlock(&head->lock);
mutex_unlock(&head->mutex);
-out:
- spin_unlock(&delayed_refs->lock);
return ret;
}
@@ -3402,6 +3345,23 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
return readonly;
}
+static const char *alloc_name(u64 flags)
+{
+ switch (flags) {
+ case BTRFS_BLOCK_GROUP_METADATA|BTRFS_BLOCK_GROUP_DATA:
+ return "mixed";
+ case BTRFS_BLOCK_GROUP_METADATA:
+ return "metadata";
+ case BTRFS_BLOCK_GROUP_DATA:
+ return "data";
+ case BTRFS_BLOCK_GROUP_SYSTEM:
+ return "system";
+ default:
+ WARN_ON(1);
+ return "invalid-combination";
+ };
+}
+
static int update_space_info(struct btrfs_fs_info *info, u64 flags,
u64 total_bytes, u64 bytes_used,
struct btrfs_space_info **space_info)
@@ -3439,8 +3399,10 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
return ret;
}
- for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
INIT_LIST_HEAD(&found->block_groups[i]);
+ kobject_init(&found->block_group_kobjs[i], &btrfs_raid_ktype);
+ }
init_rwsem(&found->groups_sem);
spin_lock_init(&found->lock);
found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
@@ -3457,11 +3419,21 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
found->chunk_alloc = 0;
found->flush = 0;
init_waitqueue_head(&found->wait);
+
+ ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
+ info->space_info_kobj, "%s",
+ alloc_name(found->flags));
+ if (ret) {
+ kfree(found);
+ return ret;
+ }
+
*space_info = found;
list_add_rcu(&found->list, &info->space_info);
if (flags & BTRFS_BLOCK_GROUP_DATA)
info->data_sinfo = found;
- return 0;
+
+ return ret;
}
static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
@@ -4637,7 +4609,7 @@ void btrfs_block_rsv_release(struct btrfs_root *root,
u64 num_bytes)
{
struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
- if (global_rsv->full || global_rsv == block_rsv ||
+ if (global_rsv == block_rsv ||
block_rsv->space_info != global_rsv->space_info)
global_rsv = NULL;
block_rsv_release_bytes(root->fs_info, block_rsv, global_rsv,
@@ -5916,24 +5888,16 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
{
struct btrfs_delayed_ref_head *head;
struct btrfs_delayed_ref_root *delayed_refs;
- struct btrfs_delayed_ref_node *ref;
- struct rb_node *node;
int ret = 0;
delayed_refs = &trans->transaction->delayed_refs;
spin_lock(&delayed_refs->lock);
head = btrfs_find_delayed_ref_head(trans, bytenr);
if (!head)
- goto out;
+ goto out_delayed_unlock;
- node = rb_prev(&head->node.rb_node);
- if (!node)
- goto out;
-
- ref = rb_entry(node, struct btrfs_delayed_ref_node, rb_node);
-
- /* there are still entries for this ref, we can't drop it */
- if (ref->bytenr == bytenr)
+ spin_lock(&head->lock);
+ if (rb_first(&head->ref_root))
goto out;
if (head->extent_op) {
@@ -5955,19 +5919,19 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
* ahead and process it.
*/
head->node.in_tree = 0;
- rb_erase(&head->node.rb_node, &delayed_refs->root);
+ rb_erase(&head->href_node, &delayed_refs->href_root);
- delayed_refs->num_entries--;
+ atomic_dec(&delayed_refs->num_entries);
/*
* we don't take a ref on the node because we're removing it from the
* tree, so we just steal the ref the tree was holding.
*/
delayed_refs->num_heads--;
- if (list_empty(&head->cluster))
+ if (head->processing == 0)
delayed_refs->num_heads_ready--;
-
- list_del_init(&head->cluster);
+ head->processing = 0;
+ spin_unlock(&head->lock);
spin_unlock(&delayed_refs->lock);
BUG_ON(head->extent_op);
@@ -5978,6 +5942,9 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
btrfs_put_delayed_ref(&head->node);
return ret;
out:
+ spin_unlock(&head->lock);
+
+out_delayed_unlock:
spin_unlock(&delayed_refs->lock);
return 0;
}
@@ -6145,11 +6112,29 @@ int __get_raid_index(u64 flags)
return BTRFS_RAID_SINGLE; /* BTRFS_BLOCK_GROUP_SINGLE */
}
-static int get_block_group_index(struct btrfs_block_group_cache *cache)
+int get_block_group_index(struct btrfs_block_group_cache *cache)
{
return __get_raid_index(cache->flags);
}
+static const char *btrfs_raid_type_names[BTRFS_NR_RAID_TYPES] = {
+ [BTRFS_RAID_RAID10] = "raid10",
+ [BTRFS_RAID_RAID1] = "raid1",
+ [BTRFS_RAID_DUP] = "dup",
+ [BTRFS_RAID_RAID0] = "raid0",
+ [BTRFS_RAID_SINGLE] = "single",
+ [BTRFS_RAID_RAID5] = "raid5",
+ [BTRFS_RAID_RAID6] = "raid6",
+};
+
+static const char *get_raid_name(enum btrfs_raid_types type)
+{
+ if (type >= BTRFS_NR_RAID_TYPES)
+ return NULL;
+
+ return btrfs_raid_type_names[type];
+}
+
enum btrfs_loop_type {
LOOP_CACHING_NOWAIT = 0,
LOOP_CACHING_WAIT = 1,
@@ -6177,7 +6162,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
struct btrfs_root *root = orig_root->fs_info->extent_root;
struct btrfs_free_cluster *last_ptr = NULL;
struct btrfs_block_group_cache *block_group = NULL;
- struct btrfs_block_group_cache *used_block_group;
u64 search_start = 0;
u64 max_extent_size = 0;
int empty_cluster = 2 * 1024 * 1024;
@@ -6186,7 +6170,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
int index = __get_raid_index(flags);
int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ?
RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC;
- bool found_uncached_bg = false;
bool failed_cluster_refill = false;
bool failed_alloc = false;
bool use_cluster = true;
@@ -6239,7 +6222,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root,
if (search_start == hint_byte) {
block_group = btrfs_lookup_block_group(root->fs_info,
search_start);
- used_block_group = block_group;
/*
* we don't want to use the block group if it doesn't match our
* allocation bits, or if its not cached.
@@ -6276,7 +6258,6 @@ search:
u64 offset;
int cached;
- used_block_group = block_group;
btrfs_get_block_group(block_group);
search_start = block_group->key.objectid;
@@ -6304,7 +6285,6 @@ search:
have_block_group:
cached = block_group_cache_done(block_group);
if (unlikely(!cached)) {
- found_uncached_bg = true;
ret = cache_block_group(block_group, 0);
BUG_ON(ret < 0);
ret = 0;
@@ -6320,6 +6300,7 @@ have_block_group:
* lets look there
*/
if (last_ptr) {
+ struct btrfs_block_group_cache *used_block_group;
unsigned long aligned_cluster;
/*
* the refill lock keeps out other
@@ -6330,10 +6311,8 @@ have_block_group:
if (used_block_group != block_group &&
(!used_block_group ||
used_block_group->ro ||
- !block_group_bits(used_block_group, flags))) {
- used_block_group = block_group;
+ !block_group_bits(used_block_group, flags)))
goto refill_cluster;
- }
if (used_block_group != block_group)
btrfs_get_block_group(used_block_group);
@@ -6347,17 +6326,19 @@ have_block_group:
/* we have a block, we're done */
spin_unlock(&last_ptr->refill_lock);
trace_btrfs_reserve_extent_cluster(root,
- block_group, search_start, num_bytes);
+ used_block_group,
+ search_start, num_bytes);
+ if (used_block_group != block_group) {
+ btrfs_put_block_group(block_group);
+ block_group = used_block_group;
+ }
goto checks;
}
WARN_ON(last_ptr->block_group != used_block_group);
- if (used_block_group != block_group) {
+ if (used_block_group != block_group)
btrfs_put_block_group(used_block_group);
- used_block_group = block_group;
- }
refill_cluster:
- BUG_ON(used_block_group != block_group);
/* If we are on LOOP_NO_EMPTY_SIZE, we can't
* set up a new clusters, so lets just skip it
* and let the allocator find whatever block
@@ -6476,25 +6457,25 @@ unclustered_alloc:
goto loop;
}
checks:
- search_start = stripe_align(root, used_block_group,
+ search_start = stripe_align(root, block_group,
offset, num_bytes);
/* move on to the next group */
if (search_start + num_bytes >
- used_block_group->key.objectid + used_block_group->key.offset) {
- btrfs_add_free_space(used_block_group, offset, num_bytes);
+ block_group->key.objectid + block_group->key.offset) {
+ btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
}
if (offset < search_start)
- btrfs_add_free_space(used_block_group, offset,
+ btrfs_add_free_space(block_group, offset,
search_start - offset);
BUG_ON(offset > search_start);
- ret = btrfs_update_reserved_bytes(used_block_group, num_bytes,
+ ret = btrfs_update_reserved_bytes(block_group, num_bytes,
alloc_type);
if (ret == -EAGAIN) {
- btrfs_add_free_space(used_block_group, offset, num_bytes);
+ btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
}
@@ -6504,16 +6485,12 @@ checks:
trace_btrfs_reserve_extent(orig_root, block_group,
search_start, num_bytes);
- if (used_block_group != block_group)
- btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
break;
loop:
failed_cluster_refill = false;
failed_alloc = false;
BUG_ON(index != get_block_group_index(block_group));
- if (used_block_group != block_group)
- btrfs_put_block_group(used_block_group);
btrfs_put_block_group(block_group);
}
up_read(&space_info->groups_sem);
@@ -6584,12 +6561,12 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
int index = 0;
spin_lock(&info->lock);
- printk(KERN_INFO "space_info %llu has %llu free, is %sfull\n",
+ printk(KERN_INFO "BTRFS: space_info %llu has %llu free, is %sfull\n",
info->flags,
info->total_bytes - info->bytes_used - info->bytes_pinned -
info->bytes_reserved - info->bytes_readonly,
(info->full) ? "" : "not ");
- printk(KERN_INFO "space_info total=%llu, used=%llu, pinned=%llu, "
+ printk(KERN_INFO "BTRFS: space_info total=%llu, used=%llu, pinned=%llu, "
"reserved=%llu, may_use=%llu, readonly=%llu\n",
info->total_bytes, info->bytes_used, info->bytes_pinned,
info->bytes_reserved, info->bytes_may_use,
@@ -6603,7 +6580,9 @@ static void dump_space_info(struct btrfs_space_info *info, u64 bytes,
again:
list_for_each_entry(cache, &info->block_groups[index], list) {
spin_lock(&cache->lock);
- printk(KERN_INFO "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s\n",
+ printk(KERN_INFO "BTRFS: "
+ "block group %llu has %llu bytes, "
+ "%llu used %llu pinned %llu reserved %s\n",
cache->key.objectid, cache->key.offset,
btrfs_block_group_used(&cache->item), cache->pinned,
cache->reserved, cache->ro ? "[readonly]" : "");
@@ -6966,7 +6945,7 @@ again:
/*DEFAULT_RATELIMIT_BURST*/ 1);
if (__ratelimit(&_rs))
WARN(1, KERN_DEBUG
- "btrfs: block rsv returned %d\n", ret);
+ "BTRFS: block rsv returned %d\n", ret);
}
try_reserve:
ret = reserve_metadata_bytes(root, block_rsv, blocksize,
@@ -7714,7 +7693,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
btrfs_end_transaction_throttle(trans, tree_root);
if (!for_reloc && btrfs_need_cleaner_sleep(root)) {
- pr_debug("btrfs: drop snapshot early exit\n");
+ pr_debug("BTRFS: drop snapshot early exit\n");
err = -EAGAIN;
goto out_free;
}
@@ -7779,7 +7758,7 @@ out:
*/
if (!for_reloc && root_dropped == false)
btrfs_add_dead_root(root);
- if (err)
+ if (err && err != -EAGAIN)
btrfs_std_error(root->fs_info, err);
return err;
}
@@ -8333,6 +8312,8 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
release_global_block_rsv(info);
while (!list_empty(&info->space_info)) {
+ int i;
+
space_info = list_entry(info->space_info.next,
struct btrfs_space_info,
list);
@@ -8343,9 +8324,17 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
dump_space_info(space_info, 0, 0);
}
}
- percpu_counter_destroy(&space_info->total_bytes_pinned);
list_del(&space_info->list);
- kfree(space_info);
+ for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
+ struct kobject *kobj;
+ kobj = &space_info->block_group_kobjs[i];
+ if (kobj->parent) {
+ kobject_del(kobj);
+ kobject_put(kobj);
+ }
+ }
+ kobject_del(&space_info->kobj);
+ kobject_put(&space_info->kobj);
}
return 0;
}
@@ -8356,10 +8345,57 @@ static void __link_block_group(struct btrfs_space_info *space_info,
int index = get_block_group_index(cache);
down_write(&space_info->groups_sem);
+ if (list_empty(&space_info->block_groups[index])) {
+ struct kobject *kobj = &space_info->block_group_kobjs[index];
+ int ret;
+
+ kobject_get(&space_info->kobj); /* put in release */
+ ret = kobject_add(kobj, &space_info->kobj, "%s",
+ get_raid_name(index));
+ if (ret) {
+ pr_warn("BTRFS: failed to add kobject for block cache. ignoring.\n");
+ kobject_put(&space_info->kobj);
+ }
+ }
list_add_tail(&cache->list, &space_info->block_groups[index]);
up_write(&space_info->groups_sem);
}
+static struct btrfs_block_group_cache *
+btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size)
+{
+ struct btrfs_block_group_cache *cache;
+
+ cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ if (!cache)
+ return NULL;
+
+ cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
+ GFP_NOFS);
+ if (!cache->free_space_ctl) {
+ kfree(cache);
+ return NULL;
+ }
+
+ cache->key.objectid = start;
+ cache->key.offset = size;
+ cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
+
+ cache->sectorsize = root->sectorsize;
+ cache->fs_info = root->fs_info;
+ cache->full_stripe_len = btrfs_full_stripe_len(root,
+ &root->fs_info->mapping_tree,
+ start);
+ atomic_set(&cache->count, 1);
+ spin_lock_init(&cache->lock);
+ INIT_LIST_HEAD(&cache->list);
+ INIT_LIST_HEAD(&cache->cluster_list);
+ INIT_LIST_HEAD(&cache->new_bg_list);
+ btrfs_init_free_space_ctl(cache);
+
+ return cache;
+}
+
int btrfs_read_block_groups(struct btrfs_root *root)
{
struct btrfs_path *path;
@@ -8395,26 +8431,16 @@ int btrfs_read_block_groups(struct btrfs_root *root)
break;
if (ret != 0)
goto error;
+
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
- cache = kzalloc(sizeof(*cache), GFP_NOFS);
+
+ cache = btrfs_create_block_group_cache(root, found_key.objectid,
+ found_key.offset);
if (!cache) {
ret = -ENOMEM;
goto error;
}
- cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
- GFP_NOFS);
- if (!cache->free_space_ctl) {
- kfree(cache);
- ret = -ENOMEM;
- goto error;
- }
-
- atomic_set(&cache->count, 1);
- spin_lock_init(&cache->lock);
- cache->fs_info = info;
- INIT_LIST_HEAD(&cache->list);
- INIT_LIST_HEAD(&cache->cluster_list);
if (need_clear) {
/*
@@ -8435,16 +8461,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
read_extent_buffer(leaf, &cache->item,
btrfs_item_ptr_offset(leaf, path->slots[0]),
sizeof(cache->item));
- memcpy(&cache->key, &found_key, sizeof(found_key));
+ cache->flags = btrfs_block_group_flags(&cache->item);
key.objectid = found_key.objectid + found_key.offset;
btrfs_release_path(path);
- cache->flags = btrfs_block_group_flags(&cache->item);
- cache->sectorsize = root->sectorsize;
- cache->full_stripe_len = btrfs_full_stripe_len(root,
- &root->fs_info->mapping_tree,
- found_key.objectid);
- btrfs_init_free_space_ctl(cache);
/*
* We need to exclude the super stripes now so that the space
@@ -8458,8 +8478,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
* case.
*/
free_excluded_extents(root, cache);
- kfree(cache->free_space_ctl);
- kfree(cache);
+ btrfs_put_block_group(cache);
goto error;
}
@@ -8590,38 +8609,15 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
root->fs_info->last_trans_log_full_commit = trans->transid;
- cache = kzalloc(sizeof(*cache), GFP_NOFS);
+ cache = btrfs_create_block_group_cache(root, chunk_offset, size);
if (!cache)
return -ENOMEM;
- cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
- GFP_NOFS);
- if (!cache->free_space_ctl) {
- kfree(cache);
- return -ENOMEM;
- }
-
- cache->key.objectid = chunk_offset;
- cache->key.offset = size;
- cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
- cache->sectorsize = root->sectorsize;
- cache->fs_info = root->fs_info;
- cache->full_stripe_len = btrfs_full_stripe_len(root,
- &root->fs_info->mapping_tree,
- chunk_offset);
-
- atomic_set(&cache->count, 1);
- spin_lock_init(&cache->lock);
- INIT_LIST_HEAD(&cache->list);
- INIT_LIST_HEAD(&cache->cluster_list);
- INIT_LIST_HEAD(&cache->new_bg_list);
-
- btrfs_init_free_space_ctl(cache);
btrfs_set_block_group_used(&cache->item, bytes_used);
btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid);
- cache->flags = type;
btrfs_set_block_group_flags(&cache->item, type);
+ cache->flags = type;
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
ret = exclude_super_stripes(root, cache);
@@ -8631,8 +8627,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
* case.
*/
free_excluded_extents(root, cache);
- kfree(cache->free_space_ctl);
- kfree(cache);
+ btrfs_put_block_group(cache);
return ret;
}
@@ -8796,8 +8791,11 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
* are still on the list after taking the semaphore
*/
list_del_init(&block_group->list);
- if (list_empty(&block_group->space_info->block_groups[index]))
+ if (list_empty(&block_group->space_info->block_groups[index])) {
+ kobject_del(&block_group->space_info->block_group_kobjs[index]);
+ kobject_put(&block_group->space_info->block_group_kobjs[index]);
clear_avail_alloc_bits(root->fs_info, block_group->flags);
+ }
up_write(&block_group->space_info->groups_sem);
if (block_group->cached == BTRFS_CACHE_STARTED)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ff43802a7c88..85bbd01f1271 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -59,7 +59,7 @@ void btrfs_leak_debug_check(void)
while (!list_empty(&states)) {
state = list_entry(states.next, struct extent_state, leak_list);
- printk(KERN_ERR "btrfs state leak: start %llu end %llu "
+ printk(KERN_ERR "BTRFS: state leak: start %llu end %llu "
"state %lu in tree %p refs %d\n",
state->start, state->end, state->state, state->tree,
atomic_read(&state->refs));
@@ -69,7 +69,7 @@ void btrfs_leak_debug_check(void)
while (!list_empty(&buffers)) {
eb = list_entry(buffers.next, struct extent_buffer, leak_list);
- printk(KERN_ERR "btrfs buffer leak start %llu len %lu "
+ printk(KERN_ERR "BTRFS: buffer leak start %llu len %lu "
"refs %d\n",
eb->start, eb->len, atomic_read(&eb->refs));
list_del(&eb->leak_list);
@@ -77,16 +77,22 @@ void btrfs_leak_debug_check(void)
}
}
-#define btrfs_debug_check_extent_io_range(inode, start, end) \
- __btrfs_debug_check_extent_io_range(__func__, (inode), (start), (end))
+#define btrfs_debug_check_extent_io_range(tree, start, end) \
+ __btrfs_debug_check_extent_io_range(__func__, (tree), (start), (end))
static inline void __btrfs_debug_check_extent_io_range(const char *caller,
- struct inode *inode, u64 start, u64 end)
+ struct extent_io_tree *tree, u64 start, u64 end)
{
- u64 isize = i_size_read(inode);
+ struct inode *inode;
+ u64 isize;
+
+ if (!tree->mapping)
+ return;
+ inode = tree->mapping->host;
+ isize = i_size_read(inode);
if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
printk_ratelimited(KERN_DEBUG
- "btrfs: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
+ "BTRFS: %s: ino %llu isize %llu odd range [%llu,%llu]\n",
caller, btrfs_ino(inode), isize, start, end);
}
}
@@ -124,6 +130,8 @@ static noinline void flush_write_bio(void *data);
static inline struct btrfs_fs_info *
tree_fs_info(struct extent_io_tree *tree)
{
+ if (!tree->mapping)
+ return NULL;
return btrfs_sb(tree->mapping->host->i_sb);
}
@@ -186,11 +194,9 @@ void extent_io_tree_init(struct extent_io_tree *tree,
struct address_space *mapping)
{
tree->state = RB_ROOT;
- INIT_RADIX_TREE(&tree->buffer, GFP_ATOMIC);
tree->ops = NULL;
tree->dirty_bytes = 0;
spin_lock_init(&tree->lock);
- spin_lock_init(&tree->buffer_lock);
tree->mapping = mapping;
}
@@ -224,12 +230,20 @@ void free_extent_state(struct extent_state *state)
}
static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
- struct rb_node *node)
+ struct rb_node *node,
+ struct rb_node ***p_in,
+ struct rb_node **parent_in)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct tree_entry *entry;
+ if (p_in && parent_in) {
+ p = *p_in;
+ parent = *parent_in;
+ goto do_insert;
+ }
+
while (*p) {
parent = *p;
entry = rb_entry(parent, struct tree_entry, rb_node);
@@ -242,35 +256,43 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
return parent;
}
+do_insert:
rb_link_node(node, parent, p);
rb_insert_color(node, root);
return NULL;
}
static struct rb_node *__etree_search(struct extent_io_tree *tree, u64 offset,
- struct rb_node **prev_ret,
- struct rb_node **next_ret)
+ struct rb_node **prev_ret,
+ struct rb_node **next_ret,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_root *root = &tree->state;
- struct rb_node *n = root->rb_node;
+ struct rb_node **n = &root->rb_node;
struct rb_node *prev = NULL;
struct rb_node *orig_prev = NULL;
struct tree_entry *entry;
struct tree_entry *prev_entry = NULL;
- while (n) {
- entry = rb_entry(n, struct tree_entry, rb_node);
- prev = n;
+ while (*n) {
+ prev = *n;
+ entry = rb_entry(prev, struct tree_entry, rb_node);
prev_entry = entry;
if (offset < entry->start)
- n = n->rb_left;
+ n = &(*n)->rb_left;
else if (offset > entry->end)
- n = n->rb_right;
+ n = &(*n)->rb_right;
else
- return n;
+ return *n;
}
+ if (p_ret)
+ *p_ret = n;
+ if (parent_ret)
+ *parent_ret = prev;
+
if (prev_ret) {
orig_prev = prev;
while (prev && offset > prev_entry->end) {
@@ -292,18 +314,27 @@ static struct rb_node *__etree_search(struct extent_io_tree *tree, u64 offset,
return NULL;
}
-static inline struct rb_node *tree_search(struct extent_io_tree *tree,
- u64 offset)
+static inline struct rb_node *
+tree_search_for_insert(struct extent_io_tree *tree,
+ u64 offset,
+ struct rb_node ***p_ret,
+ struct rb_node **parent_ret)
{
struct rb_node *prev = NULL;
struct rb_node *ret;
- ret = __etree_search(tree, offset, &prev, NULL);
+ ret = __etree_search(tree, offset, &prev, NULL, p_ret, parent_ret);
if (!ret)
return prev;
return ret;
}
+static inline struct rb_node *tree_search(struct extent_io_tree *tree,
+ u64 offset)
+{
+ return tree_search_for_insert(tree, offset, NULL, NULL);
+}
+
static void merge_cb(struct extent_io_tree *tree, struct extent_state *new,
struct extent_state *other)
{
@@ -385,23 +416,25 @@ static void set_state_bits(struct extent_io_tree *tree,
*/
static int insert_state(struct extent_io_tree *tree,
struct extent_state *state, u64 start, u64 end,
+ struct rb_node ***p,
+ struct rb_node **parent,
unsigned long *bits)
{
struct rb_node *node;
if (end < start)
- WARN(1, KERN_ERR "btrfs end < start %llu %llu\n",
+ WARN(1, KERN_ERR "BTRFS: end < start %llu %llu\n",
end, start);
state->start = start;
state->end = end;
set_state_bits(tree, state, bits);
- node = tree_insert(&tree->state, end, &state->rb_node);
+ node = tree_insert(&tree->state, end, &state->rb_node, p, parent);
if (node) {
struct extent_state *found;
found = rb_entry(node, struct extent_state, rb_node);
- printk(KERN_ERR "btrfs found node %llu %llu on insert of "
+ printk(KERN_ERR "BTRFS: found node %llu %llu on insert of "
"%llu %llu\n",
found->start, found->end, start, end);
return -EEXIST;
@@ -444,7 +477,8 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
prealloc->state = orig->state;
orig->start = split;
- node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node);
+ node = tree_insert(&tree->state, prealloc->end, &prealloc->rb_node,
+ NULL, NULL);
if (node) {
free_extent_state(prealloc);
return -EEXIST;
@@ -542,7 +576,7 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
int err;
int clear = 0;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
if (bits & EXTENT_DELALLOC)
bits |= EXTENT_NORESERVE;
@@ -702,7 +736,7 @@ static void wait_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state *state;
struct rb_node *node;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
spin_lock(&tree->lock);
again:
@@ -783,11 +817,13 @@ __set_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
bits |= EXTENT_FIRST_DELALLOC;
again:
@@ -809,14 +845,16 @@ again:
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
BUG_ON(!prealloc);
- err = insert_state(tree, prealloc, start, end, &bits);
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
prealloc = NULL;
goto out;
}
@@ -919,7 +957,7 @@ hit_next:
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
@@ -1005,11 +1043,13 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state *state;
struct extent_state *prealloc = NULL;
struct rb_node *node;
+ struct rb_node **p;
+ struct rb_node *parent;
int err = 0;
u64 last_start;
u64 last_end;
- btrfs_debug_check_extent_io_range(tree->mapping->host, start, end);
+ btrfs_debug_check_extent_io_range(tree, start, end);
again:
if (!prealloc && (mask & __GFP_WAIT)) {
@@ -1032,17 +1072,19 @@ again:
* this search will find all the extents that end after
* our range starts.
*/
- node = tree_search(tree, start);
+ node = tree_search_for_insert(tree, start, &p, &parent);
if (!node) {
prealloc = alloc_extent_state_atomic(prealloc);
if (!prealloc) {
err = -ENOMEM;
goto out;
}
- err = insert_state(tree, prealloc, start, end, &bits);
- prealloc = NULL;
+ err = insert_state(tree, prealloc, start, end,
+ &p, &parent, &bits);
if (err)
extent_io_tree_panic(tree, err);
+ cache_state(prealloc, cached_state);
+ prealloc = NULL;
goto out;
}
state = rb_entry(node, struct extent_state, rb_node);
@@ -1135,7 +1177,7 @@ hit_next:
* the later extent.
*/
err = insert_state(tree, prealloc, start, this_end,
- &bits);
+ NULL, NULL, &bits);
if (err)
extent_io_tree_panic(tree, err);
cache_state(prealloc, cached_state);
@@ -1984,7 +2026,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
if (!bio)
return -EIO;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
map_length = length;
ret = btrfs_map_block(fs_info, WRITE, logical,
@@ -1995,7 +2037,7 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
}
BUG_ON(mirror_num != bbio->mirror_num);
sector = bbio->stripes[mirror_num-1].physical >> 9;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
dev = bbio->stripes[mirror_num-1].dev;
kfree(bbio);
if (!dev || !dev->bdev || !dev->writeable) {
@@ -2012,9 +2054,10 @@ int repair_io_failure(struct btrfs_fs_info *fs_info, u64 start,
return -EIO;
}
- printk_ratelimited_in_rcu(KERN_INFO "btrfs read error corrected: ino %lu off %llu "
- "(dev %s sector %llu)\n", page->mapping->host->i_ino,
- start, rcu_str_deref(dev->name), sector);
+ printk_ratelimited_in_rcu(KERN_INFO
+ "BTRFS: read error corrected: ino %lu off %llu "
+ "(dev %s sector %llu)\n", page->mapping->host->i_ino,
+ start, rcu_str_deref(dev->name), sector);
bio_put(bio);
return 0;
@@ -2156,7 +2199,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
return -EIO;
}
- if (em->start > start || em->start + em->len < start) {
+ if (em->start > start || em->start + em->len <= start) {
free_extent_map(em);
em = NULL;
}
@@ -2268,9 +2311,9 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
return -EIO;
}
bio->bi_end_io = failed_bio->bi_end_io;
- bio->bi_sector = failrec->logical >> 9;
+ bio->bi_iter.bi_sector = failrec->logical >> 9;
bio->bi_bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
btrfs_failed_bio = btrfs_io_bio(failed_bio);
if (btrfs_failed_bio->csum) {
@@ -2332,37 +2375,39 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
*/
static void end_bio_extent_writepage(struct bio *bio, int err)
{
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct extent_io_tree *tree;
+ struct bio_vec *bvec;
u64 start;
u64 end;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- tree = &BTRFS_I(page->mapping->host)->io_tree;
/* We always issue full-page reads, but if some block
* in a page fails to read, blk_update_request() will
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page write in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page write in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page write in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
if (end_extent_writepage(page, err, start, end))
continue;
end_page_writeback(page);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
}
@@ -2392,9 +2437,8 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
*/
static void end_bio_extent_readpage(struct bio *bio, int err)
{
+ struct bio_vec *bvec;
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
u64 offset = 0;
@@ -2405,16 +2449,17 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
u64 extent_len = 0;
int mirror;
int ret;
+ int i;
if (err)
uptodate = 0;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%lu\n", (u64)bio->bi_sector, err,
+ "mirror=%lu\n", (u64)bio->bi_iter.bi_sector, err,
io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
@@ -2423,19 +2468,22 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
* advance bv_offset and adjust bv_len to compensate.
* Print a warning for nonzero offsets, and an error
* if they don't add up to a full page. */
- if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE)
- printk("%s page read in btrfs with offset %u and length %u\n",
- bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE
- ? KERN_ERR "partial" : KERN_INFO "incomplete",
- bvec->bv_offset, bvec->bv_len);
+ if (bvec->bv_offset || bvec->bv_len != PAGE_CACHE_SIZE) {
+ if (bvec->bv_offset + bvec->bv_len != PAGE_CACHE_SIZE)
+ btrfs_err(BTRFS_I(page->mapping->host)->root->fs_info,
+ "partial page read in btrfs with offset %u and length %u",
+ bvec->bv_offset, bvec->bv_len);
+ else
+ btrfs_info(BTRFS_I(page->mapping->host)->root->fs_info,
+ "incomplete page read in btrfs with offset %u and "
+ "length %u",
+ bvec->bv_offset, bvec->bv_len);
+ }
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
len = bvec->bv_len;
- if (++bvec <= bvec_end)
- prefetchw(&bvec->bv_page->flags);
-
mirror = io_bio->mirror_num;
if (likely(uptodate && tree->ops &&
tree->ops->readpage_end_io_hook)) {
@@ -2516,7 +2564,7 @@ readpage_ok:
extent_start = start;
extent_len = end + 1 - start;
}
- } while (bvec <= bvec_end);
+ }
if (extent_len)
endio_readpage_release_extent(tree, extent_start, extent_len,
@@ -2547,9 +2595,8 @@ btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
}
if (bio) {
- bio->bi_size = 0;
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
btrfs_bio = btrfs_io_bio(bio);
btrfs_bio->csum = NULL;
btrfs_bio->csum_allocated = NULL;
@@ -2643,7 +2690,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
if (bio_ret && *bio_ret) {
bio = *bio_ret;
if (old_compressed)
- contig = bio->bi_sector == sector;
+ contig = bio->bi_iter.bi_sector == sector;
else
contig = bio_end_sector(bio) == sector;
@@ -3287,8 +3334,8 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
set_range_writeback(tree, cur, cur + iosize - 1);
if (!PageWriteback(page)) {
- printk(KERN_ERR "btrfs warning page %lu not "
- "writeback, cur %llu end %llu\n",
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "page %lu not writeback, cur %llu end %llu",
page->index, cur, end);
}
@@ -3410,20 +3457,18 @@ static void end_extent_buffer_writeback(struct extent_buffer *eb)
static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
{
- int uptodate = err == 0;
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
struct extent_buffer *eb;
- int done;
+ int i, done;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- bvec--;
eb = (struct extent_buffer *)page->private;
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (!uptodate || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+ if (err || test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
ClearPageUptodate(page);
SetPageError(page);
@@ -3435,10 +3480,9 @@ static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
continue;
end_extent_buffer_writeback(eb);
- } while (bvec >= bio->bi_io_vec);
+ }
bio_put(bio);
-
}
static int write_one_eb(struct extent_buffer *eb,
@@ -3447,6 +3491,7 @@ static int write_one_eb(struct extent_buffer *eb,
struct extent_page_data *epd)
{
struct block_device *bdev = fs_info->fs_devices->latest_bdev;
+ struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
u64 offset = eb->start;
unsigned long i, num_pages;
unsigned long bio_flags = 0;
@@ -3464,7 +3509,7 @@ static int write_one_eb(struct extent_buffer *eb,
clear_page_dirty_for_io(p);
set_page_writeback(p);
- ret = submit_extent_page(rw, eb->tree, p, offset >> 9,
+ ret = submit_extent_page(rw, tree, p, offset >> 9,
PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
-1, end_bio_extent_buffer_writepage,
0, epd->bio_flags, bio_flags);
@@ -4082,12 +4127,10 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
struct extent_map *em = NULL;
struct extent_state *cached_state = NULL;
struct btrfs_path *path;
- struct btrfs_file_extent_item *item;
int end = 0;
u64 em_start = 0;
u64 em_len = 0;
u64 em_end = 0;
- unsigned long emflags;
if (len == 0)
return -EINVAL;
@@ -4112,8 +4155,6 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
}
WARN_ON(!ret);
path->slots[0]--;
- item = btrfs_item_ptr(path->nodes[0], path->slots[0],
- struct btrfs_file_extent_item);
btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
found_type = btrfs_key_type(&found_key);
@@ -4181,7 +4222,6 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
- emflags = em->flags;
disko = 0;
flags = 0;
@@ -4333,10 +4373,9 @@ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
__free_extent_buffer(eb);
}
-static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
- u64 start,
- unsigned long len,
- gfp_t mask)
+static struct extent_buffer *
+__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
+ unsigned long len, gfp_t mask)
{
struct extent_buffer *eb = NULL;
@@ -4345,7 +4384,7 @@ static struct extent_buffer *__alloc_extent_buffer(struct extent_io_tree *tree,
return NULL;
eb->start = start;
eb->len = len;
- eb->tree = tree;
+ eb->fs_info = fs_info;
eb->bflags = 0;
rwlock_init(&eb->lock);
atomic_set(&eb->write_locks, 0);
@@ -4477,13 +4516,14 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb)
}
}
-struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
- u64 start)
+struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
+ u64 start)
{
struct extent_buffer *eb;
rcu_read_lock();
- eb = radix_tree_lookup(&tree->buffer, start >> PAGE_CACHE_SHIFT);
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT);
if (eb && atomic_inc_not_zero(&eb->refs)) {
rcu_read_unlock();
mark_extent_buffer_accessed(eb);
@@ -4494,7 +4534,7 @@ struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
return NULL;
}
-struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
+struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len)
{
unsigned long num_pages = num_extent_pages(start, len);
@@ -4503,16 +4543,15 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
struct extent_buffer *eb;
struct extent_buffer *exists = NULL;
struct page *p;
- struct address_space *mapping = tree->mapping;
+ struct address_space *mapping = fs_info->btree_inode->i_mapping;
int uptodate = 1;
int ret;
-
- eb = find_extent_buffer(tree, start);
+ eb = find_extent_buffer(fs_info, start);
if (eb)
return eb;
- eb = __alloc_extent_buffer(tree, start, len, GFP_NOFS);
+ eb = __alloc_extent_buffer(fs_info, start, len, GFP_NOFS);
if (!eb)
return NULL;
@@ -4567,12 +4606,13 @@ again:
if (ret)
goto free_eb;
- spin_lock(&tree->buffer_lock);
- ret = radix_tree_insert(&tree->buffer, start >> PAGE_CACHE_SHIFT, eb);
- spin_unlock(&tree->buffer_lock);
+ spin_lock(&fs_info->buffer_lock);
+ ret = radix_tree_insert(&fs_info->buffer_radix,
+ start >> PAGE_CACHE_SHIFT, eb);
+ spin_unlock(&fs_info->buffer_lock);
radix_tree_preload_end();
if (ret == -EEXIST) {
- exists = find_extent_buffer(tree, start);
+ exists = find_extent_buffer(fs_info, start);
if (exists)
goto free_eb;
else
@@ -4580,6 +4620,7 @@ again:
}
/* add one reference for the tree */
check_buffer_tree_ref(eb);
+ set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
/*
* there is a race where release page may have
@@ -4623,17 +4664,17 @@ static int release_extent_buffer(struct extent_buffer *eb)
{
WARN_ON(atomic_read(&eb->refs) == 0);
if (atomic_dec_and_test(&eb->refs)) {
- if (test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags)) {
- spin_unlock(&eb->refs_lock);
- } else {
- struct extent_io_tree *tree = eb->tree;
+ if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
+ struct btrfs_fs_info *fs_info = eb->fs_info;
spin_unlock(&eb->refs_lock);
- spin_lock(&tree->buffer_lock);
- radix_tree_delete(&tree->buffer,
+ spin_lock(&fs_info->buffer_lock);
+ radix_tree_delete(&fs_info->buffer_radix,
eb->start >> PAGE_CACHE_SHIFT);
- spin_unlock(&tree->buffer_lock);
+ spin_unlock(&fs_info->buffer_lock);
+ } else {
+ spin_unlock(&eb->refs_lock);
}
/* Should be safe to release our pages at this point */
@@ -5112,12 +5153,12 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu dst len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu dst len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}
@@ -5159,12 +5200,12 @@ void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
unsigned long src_i;
if (src_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus src_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus src_offset %lu move "
"len %lu len %lu\n", src_offset, len, dst->len);
BUG_ON(1);
}
if (dst_offset + len > dst->len) {
- printk(KERN_ERR "btrfs memmove bogus dst_offset %lu move "
+ printk(KERN_ERR "BTRFS: memmove bogus dst_offset %lu move "
"len %lu len %lu\n", dst_offset, len, dst->len);
BUG_ON(1);
}
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 19620c58f096..58b27e5ab521 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -43,6 +43,7 @@
#define EXTENT_BUFFER_WRITEBACK 7
#define EXTENT_BUFFER_IOERR 8
#define EXTENT_BUFFER_DUMMY 9
+#define EXTENT_BUFFER_IN_TREE 10
/* these are flags for extent_clear_unlock_delalloc */
#define PAGE_UNLOCK (1 << 0)
@@ -94,12 +95,10 @@ struct extent_io_ops {
struct extent_io_tree {
struct rb_root state;
- struct radix_tree_root buffer;
struct address_space *mapping;
u64 dirty_bytes;
int track_uptodate;
spinlock_t lock;
- spinlock_t buffer_lock;
struct extent_io_ops *ops;
};
@@ -130,7 +129,7 @@ struct extent_buffer {
unsigned long map_start;
unsigned long map_len;
unsigned long bflags;
- struct extent_io_tree *tree;
+ struct btrfs_fs_info *fs_info;
spinlock_t refs_lock;
atomic_t refs;
atomic_t io_pages;
@@ -266,11 +265,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private);
void set_page_extent_mapped(struct page *page);
-struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
+struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start, unsigned long len);
struct extent_buffer *alloc_dummy_extent_buffer(u64 start, unsigned long len);
struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src);
-struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
+struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info,
u64 start);
void free_extent_buffer(struct extent_buffer *eb);
void free_extent_buffer_stale(struct extent_buffer *eb);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index a4a7a1a8da95..996ad56b57db 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -79,12 +79,21 @@ void free_extent_map(struct extent_map *em)
}
}
-static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
- struct rb_node *node)
+/* simple helper to do math around the end of an extent, handling wrap */
+static u64 range_end(u64 start, u64 len)
+{
+ if (start + len < start)
+ return (u64)-1;
+ return start + len;
+}
+
+static int tree_insert(struct rb_root *root, struct extent_map *em)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
- struct extent_map *entry;
+ struct extent_map *entry = NULL;
+ struct rb_node *orig_parent = NULL;
+ u64 end = range_end(em->start, em->len);
while (*p) {
parent = *p;
@@ -92,19 +101,37 @@ static struct rb_node *tree_insert(struct rb_root *root, u64 offset,
WARN_ON(!entry->in_tree);
- if (offset < entry->start)
+ if (em->start < entry->start)
p = &(*p)->rb_left;
- else if (offset >= extent_map_end(entry))
+ else if (em->start >= extent_map_end(entry))
p = &(*p)->rb_right;
else
- return parent;
+ return -EEXIST;
}
- entry = rb_entry(node, struct extent_map, rb_node);
- entry->in_tree = 1;
- rb_link_node(node, parent, p);
- rb_insert_color(node, root);
- return NULL;
+ orig_parent = parent;
+ while (parent && em->start >= extent_map_end(entry)) {
+ parent = rb_next(parent);
+ entry = rb_entry(parent, struct extent_map, rb_node);
+ }
+ if (parent)
+ if (end > entry->start && em->start < extent_map_end(entry))
+ return -EEXIST;
+
+ parent = orig_parent;
+ entry = rb_entry(parent, struct extent_map, rb_node);
+ while (parent && em->start < entry->start) {
+ parent = rb_prev(parent);
+ entry = rb_entry(parent, struct extent_map, rb_node);
+ }
+ if (parent)
+ if (end > entry->start && em->start < extent_map_end(entry))
+ return -EEXIST;
+
+ em->in_tree = 1;
+ rb_link_node(&em->rb_node, orig_parent, p);
+ rb_insert_color(&em->rb_node, root);
+ return 0;
}
/*
@@ -228,7 +255,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
merge = rb_entry(rb, struct extent_map, rb_node);
if (rb && mergable_maps(em, merge)) {
em->len += merge->len;
- em->block_len += merge->len;
+ em->block_len += merge->block_len;
rb_erase(&merge->rb_node, &tree->map);
merge->in_tree = 0;
em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
@@ -310,20 +337,11 @@ int add_extent_mapping(struct extent_map_tree *tree,
struct extent_map *em, int modified)
{
int ret = 0;
- struct rb_node *rb;
- struct extent_map *exist;
- exist = lookup_extent_mapping(tree, em->start, em->len);
- if (exist) {
- free_extent_map(exist);
- ret = -EEXIST;
- goto out;
- }
- rb = tree_insert(&tree->map, em->start, &em->rb_node);
- if (rb) {
- ret = -EEXIST;
+ ret = tree_insert(&tree->map, em);
+ if (ret)
goto out;
- }
+
atomic_inc(&em->refs);
em->mod_start = em->start;
@@ -337,14 +355,6 @@ out:
return ret;
}
-/* simple helper to do math around the end of an extent, handling wrap */
-static u64 range_end(u64 start, u64 len)
-{
- if (start + len < start)
- return (u64)-1;
- return start + len;
-}
-
static struct extent_map *
__lookup_extent_mapping(struct extent_map_tree *tree,
u64 start, u64 len, int strict)
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 6f3848860283..127555b29f58 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -182,7 +182,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
if (!path)
return -ENOMEM;
- nblocks = bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
if (!dst) {
if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size,
@@ -201,7 +201,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
csum = (u8 *)dst;
}
- if (bio->bi_size > PAGE_CACHE_SIZE * 8)
+ if (bio->bi_iter.bi_size > PAGE_CACHE_SIZE * 8)
path->reada = 2;
WARN_ON(bio->bi_vcnt <= 0);
@@ -217,7 +217,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
path->skip_locking = 1;
}
- disk_bytenr = (u64)bio->bi_sector << 9;
+ disk_bytenr = (u64)bio->bi_iter.bi_sector << 9;
if (dio)
offset = logical_offset;
while (bio_index < bio->bi_vcnt) {
@@ -246,8 +246,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
offset + bvec->bv_len - 1,
EXTENT_NODATASUM, GFP_NOFS);
} else {
- printk(KERN_INFO "btrfs no csum found "
- "for inode %llu start %llu\n",
+ btrfs_info(BTRFS_I(inode)->root->fs_info,
+ "no csum found for inode %llu start %llu",
btrfs_ino(inode), offset);
}
item = NULL;
@@ -302,7 +302,7 @@ int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode,
struct btrfs_dio_private *dip, struct bio *bio,
u64 offset)
{
- int len = (bio->bi_sector << 9) - dip->disk_bytenr;
+ int len = (bio->bi_iter.bi_sector << 9) - dip->disk_bytenr;
u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
int ret;
@@ -447,11 +447,12 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
u64 offset;
WARN_ON(bio->bi_vcnt <= 0);
- sums = kzalloc(btrfs_ordered_sum_size(root, bio->bi_size), GFP_NOFS);
+ sums = kzalloc(btrfs_ordered_sum_size(root, bio->bi_iter.bi_size),
+ GFP_NOFS);
if (!sums)
return -ENOMEM;
- sums->len = bio->bi_size;
+ sums->len = bio->bi_iter.bi_size;
INIT_LIST_HEAD(&sums->list);
if (contig)
@@ -461,7 +462,7 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
ordered = btrfs_lookup_ordered_extent(inode, offset);
BUG_ON(!ordered); /* Logic error */
- sums->bytenr = (u64)bio->bi_sector << 9;
+ sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
index = 0;
while (bio_index < bio->bi_vcnt) {
@@ -476,7 +477,7 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
btrfs_add_ordered_sum(inode, ordered, sums);
btrfs_put_ordered_extent(ordered);
- bytes_left = bio->bi_size - total_bytes;
+ bytes_left = bio->bi_iter.bi_size - total_bytes;
sums = kzalloc(btrfs_ordered_sum_size(root, bytes_left),
GFP_NOFS);
@@ -484,7 +485,7 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode, offset);
BUG_ON(!ordered); /* Logic error */
- sums->bytenr = ((u64)bio->bi_sector << 9) +
+ sums->bytenr = ((u64)bio->bi_iter.bi_sector << 9) +
total_bytes;
index = 0;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 82d0342763c5..0165b8672f09 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -692,7 +692,10 @@ next:
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode,
struct btrfs_path *path, u64 start, u64 end,
- u64 *drop_end, int drop_cache)
+ u64 *drop_end, int drop_cache,
+ int replace_extent,
+ u32 extent_item_size,
+ int *key_inserted)
{
struct extent_buffer *leaf;
struct btrfs_file_extent_item *fi;
@@ -712,6 +715,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
int modify_tree = -1;
int update_refs = (root->ref_cows || root == root->fs_info->tree_root);
int found = 0;
+ int leafs_visited = 0;
if (drop_cache)
btrfs_drop_extent_cache(inode, start, end - 1, 0);
@@ -733,6 +737,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
path->slots[0]--;
}
ret = 0;
+ leafs_visited++;
next_slot:
leaf = path->nodes[0];
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
@@ -744,6 +749,7 @@ next_slot:
ret = 0;
break;
}
+ leafs_visited++;
leaf = path->nodes[0];
recow = 1;
}
@@ -766,7 +772,8 @@ next_slot:
btrfs_file_extent_num_bytes(leaf, fi);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = key.offset +
- btrfs_file_extent_inline_len(leaf, fi);
+ btrfs_file_extent_inline_len(leaf,
+ path->slots[0], fi);
} else {
WARN_ON(1);
extent_end = search_start;
@@ -927,14 +934,44 @@ next_slot:
}
if (!ret && del_nr > 0) {
+ /*
+ * Set path->slots[0] to first slot, so that after the delete
+ * if items are move off from our leaf to its immediate left or
+ * right neighbor leafs, we end up with a correct and adjusted
+ * path->slots[0] for our insertion.
+ */
+ path->slots[0] = del_slot;
ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
if (ret)
btrfs_abort_transaction(trans, root, ret);
+
+ leaf = path->nodes[0];
+ /*
+ * leaf eb has flag EXTENT_BUFFER_STALE if it was deleted (that
+ * is, its contents got pushed to its neighbors), in which case
+ * it means path->locks[0] == 0
+ */
+ if (!ret && replace_extent && leafs_visited == 1 &&
+ path->locks[0] &&
+ btrfs_leaf_free_space(root, leaf) >=
+ sizeof(struct btrfs_item) + extent_item_size) {
+
+ key.objectid = ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = start;
+ setup_items_for_insert(root, path, &key,
+ &extent_item_size,
+ extent_item_size,
+ sizeof(struct btrfs_item) +
+ extent_item_size, 1);
+ *key_inserted = 1;
+ }
}
+ if (!replace_extent || !(*key_inserted))
+ btrfs_release_path(path);
if (drop_end)
*drop_end = found ? min(end, extent_end) : end;
- btrfs_release_path(path);
return ret;
}
@@ -949,7 +986,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
if (!path)
return -ENOMEM;
ret = __btrfs_drop_extents(trans, root, inode, path, start, end, NULL,
- drop_cache);
+ drop_cache, 0, 0, NULL);
btrfs_free_path(path);
return ret;
}
@@ -1235,29 +1272,18 @@ static int prepare_uptodate_page(struct page *page, u64 pos,
}
/*
- * this gets pages into the page cache and locks them down, it also properly
- * waits for data=ordered extents to finish before allowing the pages to be
- * modified.
+ * this just gets pages into the page cache and locks them down.
*/
-static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
- struct page **pages, size_t num_pages,
- loff_t pos, unsigned long first_index,
- size_t write_bytes, bool force_uptodate)
+static noinline int prepare_pages(struct inode *inode, struct page **pages,
+ size_t num_pages, loff_t pos,
+ size_t write_bytes, bool force_uptodate)
{
- struct extent_state *cached_state = NULL;
int i;
unsigned long index = pos >> PAGE_CACHE_SHIFT;
- struct inode *inode = file_inode(file);
gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
int err = 0;
- int faili = 0;
- u64 start_pos;
- u64 last_pos;
-
- start_pos = pos & ~((u64)root->sectorsize - 1);
- last_pos = ((u64)index + num_pages) << PAGE_CACHE_SHIFT;
+ int faili;
-again:
for (i = 0; i < num_pages; i++) {
pages[i] = find_or_create_page(inode->i_mapping, index + i,
mask | __GFP_WRITE);
@@ -1280,57 +1306,85 @@ again:
}
wait_on_page_writeback(pages[i]);
}
- faili = num_pages - 1;
- err = 0;
+
+ return 0;
+fail:
+ while (faili >= 0) {
+ unlock_page(pages[faili]);
+ page_cache_release(pages[faili]);
+ faili--;
+ }
+ return err;
+
+}
+
+/*
+ * This function locks the extent and properly waits for data=ordered extents
+ * to finish before allowing the pages to be modified if need.
+ *
+ * The return value:
+ * 1 - the extent is locked
+ * 0 - the extent is not locked, and everything is OK
+ * -EAGAIN - need re-prepare the pages
+ * the other < 0 number - Something wrong happens
+ */
+static noinline int
+lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
+ size_t num_pages, loff_t pos,
+ u64 *lockstart, u64 *lockend,
+ struct extent_state **cached_state)
+{
+ u64 start_pos;
+ u64 last_pos;
+ int i;
+ int ret = 0;
+
+ start_pos = pos & ~((u64)PAGE_CACHE_SIZE - 1);
+ last_pos = start_pos + ((u64)num_pages << PAGE_CACHE_SHIFT) - 1;
+
if (start_pos < inode->i_size) {
struct btrfs_ordered_extent *ordered;
lock_extent_bits(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1, 0, &cached_state);
- ordered = btrfs_lookup_first_ordered_extent(inode,
- last_pos - 1);
+ start_pos, last_pos, 0, cached_state);
+ ordered = btrfs_lookup_first_ordered_extent(inode, last_pos);
if (ordered &&
ordered->file_offset + ordered->len > start_pos &&
- ordered->file_offset < last_pos) {
+ ordered->file_offset <= last_pos) {
btrfs_put_ordered_extent(ordered);
unlock_extent_cached(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1,
- &cached_state, GFP_NOFS);
+ start_pos, last_pos,
+ cached_state, GFP_NOFS);
for (i = 0; i < num_pages; i++) {
unlock_page(pages[i]);
page_cache_release(pages[i]);
}
- err = btrfs_wait_ordered_range(inode, start_pos,
- last_pos - start_pos);
- if (err)
- goto fail;
- goto again;
+ ret = btrfs_wait_ordered_range(inode, start_pos,
+ last_pos - start_pos + 1);
+ if (ret)
+ return ret;
+ else
+ return -EAGAIN;
}
if (ordered)
btrfs_put_ordered_extent(ordered);
clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
- last_pos - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
+ last_pos, EXTENT_DIRTY | EXTENT_DELALLOC |
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
- 0, 0, &cached_state, GFP_NOFS);
- unlock_extent_cached(&BTRFS_I(inode)->io_tree,
- start_pos, last_pos - 1, &cached_state,
- GFP_NOFS);
+ 0, 0, cached_state, GFP_NOFS);
+ *lockstart = start_pos;
+ *lockend = last_pos;
+ ret = 1;
}
+
for (i = 0; i < num_pages; i++) {
if (clear_page_dirty_for_io(pages[i]))
account_page_redirty(pages[i]);
set_page_extent_mapped(pages[i]);
WARN_ON(!PageLocked(pages[i]));
}
- return 0;
-fail:
- while (faili >= 0) {
- unlock_page(pages[faili]);
- page_cache_release(pages[faili]);
- faili--;
- }
- return err;
+ return ret;
}
static noinline int check_can_nocow(struct inode *inode, loff_t pos,
@@ -1381,13 +1435,17 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
struct inode *inode = file_inode(file);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct page **pages = NULL;
+ struct extent_state *cached_state = NULL;
u64 release_bytes = 0;
+ u64 lockstart;
+ u64 lockend;
unsigned long first_index;
size_t num_written = 0;
int nrptrs;
int ret = 0;
bool only_release_metadata = false;
bool force_page_uptodate = false;
+ bool need_unlock;
nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
@@ -1456,18 +1514,31 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
}
release_bytes = reserve_bytes;
-
+ need_unlock = false;
+again:
/*
* This is going to setup the pages array with the number of
* pages we want, so we don't really need to worry about the
* contents of pages from loop to loop
*/
- ret = prepare_pages(root, file, pages, num_pages,
- pos, first_index, write_bytes,
+ ret = prepare_pages(inode, pages, num_pages,
+ pos, write_bytes,
force_page_uptodate);
if (ret)
break;
+ ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
+ pos, &lockstart, &lockend,
+ &cached_state);
+ if (ret < 0) {
+ if (ret == -EAGAIN)
+ goto again;
+ break;
+ } else if (ret > 0) {
+ need_unlock = true;
+ ret = 0;
+ }
+
copied = btrfs_copy_from_user(pos, num_pages,
write_bytes, pages, i);
@@ -1512,19 +1583,21 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
}
release_bytes = dirty_pages << PAGE_CACHE_SHIFT;
- if (copied > 0) {
+
+ if (copied > 0)
ret = btrfs_dirty_pages(root, inode, pages,
dirty_pages, pos, copied,
NULL);
- if (ret) {
- btrfs_drop_pages(pages, num_pages);
- break;
- }
+ if (need_unlock)
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ lockstart, lockend, &cached_state,
+ GFP_NOFS);
+ if (ret) {
+ btrfs_drop_pages(pages, num_pages);
+ break;
}
release_bytes = 0;
- btrfs_drop_pages(pages, num_pages);
-
if (only_release_metadata && copied > 0) {
u64 lockstart = round_down(pos, root->sectorsize);
u64 lockend = lockstart +
@@ -1536,6 +1609,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
only_release_metadata = false;
}
+ btrfs_drop_pages(pages, num_pages);
+
cond_resched();
balance_dirty_pages_ratelimited(inode->i_mapping);
@@ -1857,12 +1932,24 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (file->private_data)
btrfs_ioctl_trans_end(file);
+ /*
+ * We use start here because we will need to wait on the IO to complete
+ * in btrfs_sync_log, which could require joining a transaction (for
+ * example checking cross references in the nocow path). If we use join
+ * here we could get into a situation where we're waiting on IO to
+ * happen that is blocked on a transaction trying to commit. With start
+ * we inc the extwriter counter, so we wait for all extwriters to exit
+ * before we start blocking join'ers. This comment is to keep somebody
+ * from thinking they are super smart and changing this to
+ * btrfs_join_transaction *cough*Josef*cough*.
+ */
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
mutex_unlock(&inode->i_mutex);
goto out;
}
+ trans->sync = true;
ret = btrfs_log_dentry_safe(trans, root, dentry);
if (ret < 0) {
@@ -1963,11 +2050,13 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
struct btrfs_key key;
int ret;
+ if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
+ goto out;
+
key.objectid = btrfs_ino(inode);
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = offset;
-
ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret < 0)
return ret;
@@ -2064,8 +2153,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
u64 drop_end;
int ret = 0;
int err = 0;
+ int rsv_count;
bool same_page = ((offset >> PAGE_CACHE_SHIFT) ==
((offset + len - 1) >> PAGE_CACHE_SHIFT));
+ bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
ret = btrfs_wait_ordered_range(inode, offset, len);
if (ret)
@@ -2125,7 +2216,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
* we need to try again.
*/
if ((!ordered ||
- (ordered->file_offset + ordered->len < lockstart ||
+ (ordered->file_offset + ordered->len <= lockstart ||
ordered->file_offset > lockend)) &&
!test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
lockend, EXTENT_UPTODATE, 0,
@@ -2163,9 +2254,10 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
/*
* 1 - update the inode
* 1 - removing the extents in the range
- * 1 - adding the hole extent
+ * 1 - adding the hole extent if no_holes isn't set
*/
- trans = btrfs_start_transaction(root, 3);
+ rsv_count = no_holes ? 2 : 3;
+ trans = btrfs_start_transaction(root, rsv_count);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out_free;
@@ -2179,7 +2271,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
while (cur_offset < lockend) {
ret = __btrfs_drop_extents(trans, root, inode, path,
cur_offset, lockend + 1,
- &drop_end, 1);
+ &drop_end, 1, 0, 0, NULL);
if (ret != -ENOSPC)
break;
@@ -2202,7 +2294,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
btrfs_end_transaction(trans, root);
btrfs_btree_balance_dirty(root);
- trans = btrfs_start_transaction(root, 3);
+ trans = btrfs_start_transaction(root, rsv_count);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 057be95b1e1e..73f3de7a083c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -347,8 +347,8 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode,
btrfs_readpage(NULL, page);
lock_page(page);
if (!PageUptodate(page)) {
- printk(KERN_ERR "btrfs: error reading free "
- "space cache\n");
+ btrfs_err(BTRFS_I(inode)->root->fs_info,
+ "error reading free space cache");
io_ctl_drop_pages(io_ctl);
return -EIO;
}
@@ -405,7 +405,7 @@ static int io_ctl_check_generation(struct io_ctl *io_ctl, u64 generation)
gen = io_ctl->cur;
if (le64_to_cpu(*gen) != generation) {
- printk_ratelimited(KERN_ERR "btrfs: space cache generation "
+ printk_ratelimited(KERN_ERR "BTRFS: space cache generation "
"(%Lu) does not match inode (%Lu)\n", *gen,
generation);
io_ctl_unmap_page(io_ctl);
@@ -463,7 +463,7 @@ static int io_ctl_check_crc(struct io_ctl *io_ctl, int index)
PAGE_CACHE_SIZE - offset);
btrfs_csum_final(crc, (char *)&crc);
if (val != crc) {
- printk_ratelimited(KERN_ERR "btrfs: csum mismatch on free "
+ printk_ratelimited(KERN_ERR "BTRFS: csum mismatch on free "
"space cache\n");
io_ctl_unmap_page(io_ctl);
return -EIO;
@@ -1902,7 +1902,7 @@ out:
spin_unlock(&ctl->tree_lock);
if (ret) {
- printk(KERN_CRIT "btrfs: unable to add free space :%d\n", ret);
+ printk(KERN_CRIT "BTRFS: unable to add free space :%d\n", ret);
ASSERT(ret != -EEXIST);
}
@@ -2011,14 +2011,15 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
info = rb_entry(n, struct btrfs_free_space, offset_index);
if (info->bytes >= bytes && !block_group->ro)
count++;
- printk(KERN_CRIT "entry offset %llu, bytes %llu, bitmap %s\n",
- info->offset, info->bytes,
+ btrfs_crit(block_group->fs_info,
+ "entry offset %llu, bytes %llu, bitmap %s",
+ info->offset, info->bytes,
(info->bitmap) ? "yes" : "no");
}
- printk(KERN_INFO "block group has cluster?: %s\n",
+ btrfs_info(block_group->fs_info, "block group has cluster?: %s",
list_empty(&block_group->cluster_list) ? "no" : "yes");
- printk(KERN_INFO "%d blocks of free space at or bigger than bytes is"
- "\n", count);
+ btrfs_info(block_group->fs_info,
+ "%d blocks of free space at or bigger than bytes is", count);
}
void btrfs_init_free_space_ctl(struct btrfs_block_group_cache *block_group)
@@ -2421,7 +2422,6 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_space *entry = NULL;
struct btrfs_free_space *last;
struct rb_node *node;
- u64 window_start;
u64 window_free;
u64 max_extent;
u64 total_size = 0;
@@ -2443,7 +2443,6 @@ setup_cluster_no_bitmap(struct btrfs_block_group_cache *block_group,
entry = rb_entry(node, struct btrfs_free_space, offset_index);
}
- window_start = entry->offset;
window_free = entry->bytes;
max_extent = entry->bytes;
first = entry;
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
new file mode 100644
index 000000000000..85889aa82c62
--- /dev/null
+++ b/fs/btrfs/hash.c
@@ -0,0 +1,50 @@
+/*
+ * Copyright (C) 2014 Filipe David Borba Manana <fdmanana@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <crypto/hash.h>
+#include <linux/err.h>
+#include "hash.h"
+
+static struct crypto_shash *tfm;
+
+int __init btrfs_hash_init(void)
+{
+ tfm = crypto_alloc_shash("crc32c", 0, 0);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ return 0;
+}
+
+void btrfs_hash_exit(void)
+{
+ crypto_free_shash(tfm);
+}
+
+u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length)
+{
+ struct {
+ struct shash_desc shash;
+ char ctx[crypto_shash_descsize(tfm)];
+ } desc;
+ int err;
+
+ desc.shash.tfm = tfm;
+ desc.shash.flags = 0;
+ *(u32 *)desc.ctx = crc;
+
+ err = crypto_shash_update(&desc.shash, address, length);
+ BUG_ON(err);
+
+ return *(u32 *)desc.ctx;
+}
diff --git a/fs/btrfs/hash.h b/fs/btrfs/hash.h
index 1d982812ab67..118a2316e5d3 100644
--- a/fs/btrfs/hash.h
+++ b/fs/btrfs/hash.h
@@ -19,10 +19,15 @@
#ifndef __HASH__
#define __HASH__
-#include <linux/crc32c.h>
+int __init btrfs_hash_init(void);
+
+void btrfs_hash_exit(void);
+
+u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length);
+
static inline u64 btrfs_name_hash(const char *name, int len)
{
- return crc32c((u32)~1, name, len);
+ return btrfs_crc32c((u32)~1, name, len);
}
/*
@@ -31,7 +36,7 @@ static inline u64 btrfs_name_hash(const char *name, int len)
static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name,
int len)
{
- return (u64) crc32c(parent_objectid, name, len);
+ return (u64) btrfs_crc32c(parent_objectid, name, len);
}
#endif
diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index ec82fae07097..2be38df703c9 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -91,32 +91,6 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid,
return 0;
}
-static struct btrfs_inode_ref *
-btrfs_lookup_inode_ref(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len,
- u64 inode_objectid, u64 ref_objectid, int ins_len,
- int cow)
-{
- int ret;
- struct btrfs_key key;
- struct btrfs_inode_ref *ref;
-
- key.objectid = inode_objectid;
- key.type = BTRFS_INODE_REF_KEY;
- key.offset = ref_objectid;
-
- ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow);
- if (ret < 0)
- return ERR_PTR(ret);
- if (ret > 0)
- return NULL;
- if (!find_name_in_backref(path, name, name_len, &ref))
- return NULL;
- return ref;
-}
-
/* Returns NULL if no extref found */
struct btrfs_inode_extref *
btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
@@ -144,45 +118,6 @@ btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
return extref;
}
-int btrfs_get_inode_ref_index(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- struct btrfs_path *path,
- const char *name, int name_len,
- u64 inode_objectid, u64 ref_objectid, int mod,
- u64 *ret_index)
-{
- struct btrfs_inode_ref *ref;
- struct btrfs_inode_extref *extref;
- int ins_len = mod < 0 ? -1 : 0;
- int cow = mod != 0;
-
- ref = btrfs_lookup_inode_ref(trans, root, path, name, name_len,
- inode_objectid, ref_objectid, ins_len,
- cow);
- if (IS_ERR(ref))
- return PTR_ERR(ref);
-
- if (ref != NULL) {
- *ret_index = btrfs_inode_ref_index(path->nodes[0], ref);
- return 0;
- }
-
- btrfs_release_path(path);
-
- extref = btrfs_lookup_inode_extref(trans, root, path, name,
- name_len, inode_objectid,
- ref_objectid, ins_len, cow);
- if (IS_ERR(extref))
- return PTR_ERR(extref);
-
- if (extref) {
- *ret_index = btrfs_inode_extref_index(path->nodes[0], extref);
- return 0;
- }
-
- return -ENOENT;
-}
-
static int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
const char *name, int name_len,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 514b291b1354..d3d44486290b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -58,9 +58,10 @@
#include "inode-map.h"
#include "backref.h"
#include "hash.h"
+#include "props.h"
struct btrfs_iget_args {
- u64 ino;
+ struct btrfs_key *location;
struct btrfs_root *root;
};
@@ -125,13 +126,12 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
* no overlapping inline items exist in the btree
*/
static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_path *path, int extent_inserted,
struct btrfs_root *root, struct inode *inode,
u64 start, size_t size, size_t compressed_size,
int compress_type,
struct page **compressed_pages)
{
- struct btrfs_key key;
- struct btrfs_path *path;
struct extent_buffer *leaf;
struct page *page = NULL;
char *kaddr;
@@ -140,29 +140,29 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
int err = 0;
int ret;
size_t cur_size = size;
- size_t datasize;
unsigned long offset;
if (compressed_size && compressed_pages)
cur_size = compressed_size;
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ inode_add_bytes(inode, size);
- path->leave_spinning = 1;
+ if (!extent_inserted) {
+ struct btrfs_key key;
+ size_t datasize;
- key.objectid = btrfs_ino(inode);
- key.offset = start;
- btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
- datasize = btrfs_file_extent_calc_inline_size(cur_size);
+ key.objectid = btrfs_ino(inode);
+ key.offset = start;
+ btrfs_set_key_type(&key, BTRFS_EXTENT_DATA_KEY);
- inode_add_bytes(inode, size);
- ret = btrfs_insert_empty_item(trans, root, path, &key,
- datasize);
- if (ret) {
- err = ret;
- goto fail;
+ datasize = btrfs_file_extent_calc_inline_size(cur_size);
+ path->leave_spinning = 1;
+ ret = btrfs_insert_empty_item(trans, root, path, &key,
+ datasize);
+ if (ret) {
+ err = ret;
+ goto fail;
+ }
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -203,7 +203,7 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
page_cache_release(page);
}
btrfs_mark_buffer_dirty(leaf);
- btrfs_free_path(path);
+ btrfs_release_path(path);
/*
* we're an inline extent, so nobody can
@@ -219,7 +219,6 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
return ret;
fail:
- btrfs_free_path(path);
return err;
}
@@ -242,6 +241,9 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
u64 aligned_end = ALIGN(end, root->sectorsize);
u64 data_len = inline_len;
int ret;
+ struct btrfs_path *path;
+ int extent_inserted = 0;
+ u32 extent_item_size;
if (compressed_size)
data_len = compressed_size;
@@ -256,12 +258,27 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
return 1;
}
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
trans = btrfs_join_transaction(root);
- if (IS_ERR(trans))
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
return PTR_ERR(trans);
+ }
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
- ret = btrfs_drop_extents(trans, root, inode, start, aligned_end, 1);
+ if (compressed_size && compressed_pages)
+ extent_item_size = btrfs_file_extent_calc_inline_size(
+ compressed_size);
+ else
+ extent_item_size = btrfs_file_extent_calc_inline_size(
+ inline_len);
+
+ ret = __btrfs_drop_extents(trans, root, inode, path,
+ start, aligned_end, NULL,
+ 1, 1, extent_item_size, &extent_inserted);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
goto out;
@@ -269,7 +286,8 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
if (isize > actual_end)
inline_len = min_t(u64, isize, actual_end);
- ret = insert_inline_extent(trans, root, inode, start,
+ ret = insert_inline_extent(trans, path, extent_inserted,
+ root, inode, start,
inline_len, compressed_size,
compress_type, compressed_pages);
if (ret && ret != -ENOSPC) {
@@ -284,6 +302,7 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
out:
+ btrfs_free_path(path);
btrfs_end_transaction(trans, root);
return ret;
}
@@ -1262,7 +1281,8 @@ next_slot:
nocow = 1;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = found_key.offset +
- btrfs_file_extent_inline_len(leaf, fi);
+ btrfs_file_extent_inline_len(leaf,
+ path->slots[0], fi);
extent_end = ALIGN(extent_end, root->sectorsize);
} else {
BUG_ON(1);
@@ -1577,7 +1597,7 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
unsigned long bio_flags)
{
struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
int ret;
@@ -1585,7 +1605,7 @@ int btrfs_merge_bio_hook(int rw, struct page *page, unsigned long offset,
if (bio_flags & EXTENT_BIO_COMPRESSED)
return 0;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
ret = btrfs_map_block(root->fs_info, rw, logical,
&map_length, NULL, 0);
@@ -1841,14 +1861,13 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_key ins;
+ int extent_inserted = 0;
int ret;
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
- path->leave_spinning = 1;
-
/*
* we may be replacing one extent in the tree with another.
* The new extent is pinned in the extent map, and we don't want
@@ -1858,17 +1877,23 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
* the caller is expected to unpin it and allow it to be merged
* with the others.
*/
- ret = btrfs_drop_extents(trans, root, inode, file_pos,
- file_pos + num_bytes, 0);
+ ret = __btrfs_drop_extents(trans, root, inode, path, file_pos,
+ file_pos + num_bytes, NULL, 0,
+ 1, sizeof(*fi), &extent_inserted);
if (ret)
goto out;
- ins.objectid = btrfs_ino(inode);
- ins.offset = file_pos;
- ins.type = BTRFS_EXTENT_DATA_KEY;
- ret = btrfs_insert_empty_item(trans, root, path, &ins, sizeof(*fi));
- if (ret)
- goto out;
+ if (!extent_inserted) {
+ ins.objectid = btrfs_ino(inode);
+ ins.offset = file_pos;
+ ins.type = BTRFS_EXTENT_DATA_KEY;
+
+ path->leave_spinning = 1;
+ ret = btrfs_insert_empty_item(trans, root, path, &ins,
+ sizeof(*fi));
+ if (ret)
+ goto out;
+ }
leaf = path->nodes[0];
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
@@ -2290,7 +2315,7 @@ again:
u64 extent_len;
struct btrfs_key found_key;
- ret = btrfs_search_slot(trans, root, &key, path, 1, 1);
+ ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
if (ret < 0)
goto out_free_path;
@@ -2543,12 +2568,6 @@ out_kfree:
return NULL;
}
-/*
- * helper function for btrfs_finish_ordered_io, this
- * just reads in some of the csum leaves to prime them into ram
- * before we start the transaction. It limits the amount of btree
- * reads required while inside the transaction.
- */
/* as ordered data IO finishes, this gets called so we can finish
* an ordered extent if the range of bytes in the file it covers are
* fully written.
@@ -2610,7 +2629,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
EXTENT_DEFRAG, 1, cached_state);
if (ret) {
u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
- if (last_snapshot >= BTRFS_I(inode)->generation)
+ if (0 && last_snapshot >= BTRFS_I(inode)->generation)
/* the inode is shared */
new = record_old_file_extents(inode, ordered_extent);
@@ -3248,7 +3267,8 @@ out:
* slot is the slot the inode is in, objectid is the objectid of the inode
*/
static noinline int acls_after_inode_item(struct extent_buffer *leaf,
- int slot, u64 objectid)
+ int slot, u64 objectid,
+ int *first_xattr_slot)
{
u32 nritems = btrfs_header_nritems(leaf);
struct btrfs_key found_key;
@@ -3264,6 +3284,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
}
slot++;
+ *first_xattr_slot = -1;
while (slot < nritems) {
btrfs_item_key_to_cpu(leaf, &found_key, slot);
@@ -3273,6 +3294,8 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
/* we found an xattr, assume we've got an acl */
if (found_key.type == BTRFS_XATTR_ITEM_KEY) {
+ if (*first_xattr_slot == -1)
+ *first_xattr_slot = slot;
if (found_key.offset == xattr_access ||
found_key.offset == xattr_default)
return 1;
@@ -3301,6 +3324,8 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf,
* something larger than an xattr. We have to assume the inode
* has acls
*/
+ if (*first_xattr_slot == -1)
+ *first_xattr_slot = slot;
return 1;
}
@@ -3315,10 +3340,12 @@ static void btrfs_read_locked_inode(struct inode *inode)
struct btrfs_timespec *tspec;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_key location;
+ unsigned long ptr;
int maybe_acls;
u32 rdev;
int ret;
bool filled = false;
+ int first_xattr_slot;
ret = btrfs_fill_inode(inode, &rdev);
if (!ret)
@@ -3328,7 +3355,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
if (!path)
goto make_bad;
- path->leave_spinning = 1;
memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
@@ -3338,7 +3364,7 @@ static void btrfs_read_locked_inode(struct inode *inode)
leaf = path->nodes[0];
if (filled)
- goto cache_acl;
+ goto cache_index;
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
@@ -3381,18 +3407,51 @@ static void btrfs_read_locked_inode(struct inode *inode)
BTRFS_I(inode)->index_cnt = (u64)-1;
BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
+
+cache_index:
+ path->slots[0]++;
+ if (inode->i_nlink != 1 ||
+ path->slots[0] >= btrfs_header_nritems(leaf))
+ goto cache_acl;
+
+ btrfs_item_key_to_cpu(leaf, &location, path->slots[0]);
+ if (location.objectid != btrfs_ino(inode))
+ goto cache_acl;
+
+ ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+ if (location.type == BTRFS_INODE_REF_KEY) {
+ struct btrfs_inode_ref *ref;
+
+ ref = (struct btrfs_inode_ref *)ptr;
+ BTRFS_I(inode)->dir_index = btrfs_inode_ref_index(leaf, ref);
+ } else if (location.type == BTRFS_INODE_EXTREF_KEY) {
+ struct btrfs_inode_extref *extref;
+
+ extref = (struct btrfs_inode_extref *)ptr;
+ BTRFS_I(inode)->dir_index = btrfs_inode_extref_index(leaf,
+ extref);
+ }
cache_acl:
/*
* try to precache a NULL acl entry for files that don't have
* any xattrs or acls
*/
maybe_acls = acls_after_inode_item(leaf, path->slots[0],
- btrfs_ino(inode));
+ btrfs_ino(inode), &first_xattr_slot);
+ if (first_xattr_slot != -1) {
+ path->slots[0] = first_xattr_slot;
+ ret = btrfs_load_inode_props(inode, path);
+ if (ret)
+ btrfs_err(root->fs_info,
+ "error loading props for ino %llu (root %llu): %d\n",
+ btrfs_ino(inode),
+ root->root_key.objectid, ret);
+ }
+ btrfs_free_path(path);
+
if (!maybe_acls)
cache_no_acl(inode);
- btrfs_free_path(path);
-
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_mapping->a_ops = &btrfs_aops;
@@ -3496,7 +3555,6 @@ static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans,
goto failed;
}
- btrfs_unlock_up_safe(path, 1);
leaf = path->nodes[0];
inode_item = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_inode_item);
@@ -3593,6 +3651,24 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
goto err;
btrfs_release_path(path);
+ /*
+ * If we don't have dir index, we have to get it by looking up
+ * the inode ref, since we get the inode ref, remove it directly,
+ * it is unnecessary to do delayed deletion.
+ *
+ * But if we have dir index, needn't search inode ref to get it.
+ * Since the inode ref is close to the inode item, it is better
+ * that we delay to delete it, and just do this deletion when
+ * we update the inode item.
+ */
+ if (BTRFS_I(inode)->dir_index) {
+ ret = btrfs_delayed_delete_inode_ref(inode);
+ if (!ret) {
+ index = BTRFS_I(inode)->dir_index;
+ goto skip_backref;
+ }
+ }
+
ret = btrfs_del_inode_ref(trans, root, name, name_len, ino,
dir_ino, &index);
if (ret) {
@@ -3602,7 +3678,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
btrfs_abort_transaction(trans, root, ret);
goto err;
}
-
+skip_backref:
ret = btrfs_delete_delayed_dir_index(trans, root, dir, index);
if (ret) {
btrfs_abort_transaction(trans, root, ret);
@@ -3948,7 +4024,7 @@ search_again:
btrfs_file_extent_num_bytes(leaf, fi);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
item_end += btrfs_file_extent_inline_len(leaf,
- fi);
+ path->slots[0], fi);
}
item_end--;
}
@@ -4018,6 +4094,12 @@ search_again:
inode_sub_bytes(inode, item_end + 1 -
new_size);
}
+
+ /*
+ * update the ram bytes to properly reflect
+ * the new size of our item
+ */
+ btrfs_set_file_extent_ram_bytes(leaf, fi, size);
size =
btrfs_file_extent_calc_inline_size(size);
btrfs_truncate_item(root, path, size, 1);
@@ -4203,6 +4285,49 @@ out:
return ret;
}
+static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
+ u64 offset, u64 len)
+{
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ /*
+ * Still need to make sure the inode looks like it's been updated so
+ * that any holes get logged if we fsync.
+ */
+ if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) {
+ BTRFS_I(inode)->last_trans = root->fs_info->generation;
+ BTRFS_I(inode)->last_sub_trans = root->log_transid;
+ BTRFS_I(inode)->last_log_commit = root->last_log_commit;
+ return 0;
+ }
+
+ /*
+ * 1 - for the one we're dropping
+ * 1 - for the one we're adding
+ * 1 - for updating the inode.
+ */
+ trans = btrfs_start_transaction(root, 3);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ ret = btrfs_drop_extents(trans, root, inode, offset, offset + len, 1);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ btrfs_end_transaction(trans, root);
+ return ret;
+ }
+
+ ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
+ 0, 0, len, 0, len, 0, 0, 0);
+ if (ret)
+ btrfs_abort_transaction(trans, root, ret);
+ else
+ btrfs_update_inode(trans, root, inode);
+ btrfs_end_transaction(trans, root);
+ return ret;
+}
+
/*
* This function puts in dummy file extents for the area we're creating a hole
* for. So if we are truncating this file to a larger size we need to insert
@@ -4211,7 +4336,6 @@ out:
*/
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
{
- struct btrfs_trans_handle *trans;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_map *em = NULL;
@@ -4266,31 +4390,10 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
struct extent_map *hole_em;
hole_size = last_byte - cur_offset;
- trans = btrfs_start_transaction(root, 3);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
- break;
- }
-
- err = btrfs_drop_extents(trans, root, inode,
- cur_offset,
- cur_offset + hole_size, 1);
- if (err) {
- btrfs_abort_transaction(trans, root, err);
- btrfs_end_transaction(trans, root);
- break;
- }
-
- err = btrfs_insert_file_extent(trans, root,
- btrfs_ino(inode), cur_offset, 0,
- 0, hole_size, 0, hole_size,
- 0, 0, 0);
- if (err) {
- btrfs_abort_transaction(trans, root, err);
- btrfs_end_transaction(trans, root);
+ err = maybe_insert_hole(root, inode, cur_offset,
+ hole_size);
+ if (err)
break;
- }
-
btrfs_drop_extent_cache(inode, cur_offset,
cur_offset + hole_size - 1, 0);
hole_em = alloc_extent_map();
@@ -4309,7 +4412,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
hole_em->ram_bytes = hole_size;
hole_em->bdev = root->fs_info->fs_devices->latest_bdev;
hole_em->compress_type = BTRFS_COMPRESS_NONE;
- hole_em->generation = trans->transid;
+ hole_em->generation = root->fs_info->generation;
while (1) {
write_lock(&em_tree->lock);
@@ -4322,17 +4425,14 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
hole_size - 1, 0);
}
free_extent_map(hole_em);
-next:
- btrfs_update_inode(trans, root, inode);
- btrfs_end_transaction(trans, root);
}
+next:
free_extent_map(em);
em = NULL;
cur_offset = last_byte;
if (cur_offset >= block_end)
break;
}
-
free_extent_map(em);
unlock_extent_cached(io_tree, hole_start, block_end - 1, &cached_state,
GFP_NOFS);
@@ -4474,6 +4574,64 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
return err;
}
+/*
+ * While truncating the inode pages during eviction, we get the VFS calling
+ * btrfs_invalidatepage() against each page of the inode. This is slow because
+ * the calls to btrfs_invalidatepage() result in a huge amount of calls to
+ * lock_extent_bits() and clear_extent_bit(), which keep merging and splitting
+ * extent_state structures over and over, wasting lots of time.
+ *
+ * Therefore if the inode is being evicted, let btrfs_invalidatepage() skip all
+ * those expensive operations on a per page basis and do only the ordered io
+ * finishing, while we release here the extent_map and extent_state structures,
+ * without the excessive merging and splitting.
+ */
+static void evict_inode_truncate_pages(struct inode *inode)
+{
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct extent_map_tree *map_tree = &BTRFS_I(inode)->extent_tree;
+ struct rb_node *node;
+
+ ASSERT(inode->i_state & I_FREEING);
+ truncate_inode_pages(&inode->i_data, 0);
+
+ write_lock(&map_tree->lock);
+ while (!RB_EMPTY_ROOT(&map_tree->map)) {
+ struct extent_map *em;
+
+ node = rb_first(&map_tree->map);
+ em = rb_entry(node, struct extent_map, rb_node);
+ clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ clear_bit(EXTENT_FLAG_LOGGING, &em->flags);
+ remove_extent_mapping(map_tree, em);
+ free_extent_map(em);
+ }
+ write_unlock(&map_tree->lock);
+
+ spin_lock(&io_tree->lock);
+ while (!RB_EMPTY_ROOT(&io_tree->state)) {
+ struct extent_state *state;
+ struct extent_state *cached_state = NULL;
+
+ node = rb_first(&io_tree->state);
+ state = rb_entry(node, struct extent_state, rb_node);
+ atomic_inc(&state->refs);
+ spin_unlock(&io_tree->lock);
+
+ lock_extent_bits(io_tree, state->start, state->end,
+ 0, &cached_state);
+ clear_extent_bit(io_tree, state->start, state->end,
+ EXTENT_LOCKED | EXTENT_DIRTY |
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 1,
+ &cached_state, GFP_NOFS);
+ free_extent_state(state);
+
+ spin_lock(&io_tree->lock);
+ }
+ spin_unlock(&io_tree->lock);
+}
+
void btrfs_evict_inode(struct inode *inode)
{
struct btrfs_trans_handle *trans;
@@ -4484,7 +4642,8 @@ void btrfs_evict_inode(struct inode *inode)
trace_btrfs_inode_evict(inode);
- truncate_inode_pages(&inode->i_data, 0);
+ evict_inode_truncate_pages(inode);
+
if (inode->i_nlink &&
((btrfs_root_refs(&root->root_item) != 0 &&
root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
@@ -4659,9 +4818,9 @@ static int fixup_tree_root_location(struct btrfs_root *root,
}
err = -ENOENT;
- ret = btrfs_find_root_ref(root->fs_info->tree_root, path,
- BTRFS_I(dir)->root->root_key.objectid,
- location->objectid);
+ ret = btrfs_find_item(root->fs_info->tree_root, path,
+ BTRFS_I(dir)->root->root_key.objectid,
+ location->objectid, BTRFS_ROOT_REF_KEY, NULL);
if (ret) {
if (ret < 0)
err = ret;
@@ -4822,7 +4981,9 @@ again:
static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
struct btrfs_iget_args *args = p;
- inode->i_ino = args->ino;
+ inode->i_ino = args->location->objectid;
+ memcpy(&BTRFS_I(inode)->location, args->location,
+ sizeof(*args->location));
BTRFS_I(inode)->root = args->root;
return 0;
}
@@ -4830,19 +4991,19 @@ static int btrfs_init_locked_inode(struct inode *inode, void *p)
static int btrfs_find_actor(struct inode *inode, void *opaque)
{
struct btrfs_iget_args *args = opaque;
- return args->ino == btrfs_ino(inode) &&
+ return args->location->objectid == BTRFS_I(inode)->location.objectid &&
args->root == BTRFS_I(inode)->root;
}
static struct inode *btrfs_iget_locked(struct super_block *s,
- u64 objectid,
+ struct btrfs_key *location,
struct btrfs_root *root)
{
struct inode *inode;
struct btrfs_iget_args args;
- unsigned long hashval = btrfs_inode_hash(objectid, root);
+ unsigned long hashval = btrfs_inode_hash(location->objectid, root);
- args.ino = objectid;
+ args.location = location;
args.root = root;
inode = iget5_locked(s, hashval, btrfs_find_actor,
@@ -4859,13 +5020,11 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
{
struct inode *inode;
- inode = btrfs_iget_locked(s, location->objectid, root);
+ inode = btrfs_iget_locked(s, location, root);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
- BTRFS_I(inode)->root = root;
- memcpy(&BTRFS_I(inode)->location, location, sizeof(*location));
btrfs_read_locked_inode(inode);
if (!is_bad_inode(inode)) {
inode_tree_add(inode);
@@ -4921,7 +5080,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
return ERR_PTR(ret);
if (location.objectid == 0)
- return NULL;
+ return ERR_PTR(-ENOENT);
if (location.type == BTRFS_INODE_ITEM_KEY) {
inode = btrfs_iget(dir->i_sb, &location, root, NULL);
@@ -4985,10 +5144,17 @@ static void btrfs_dentry_release(struct dentry *dentry)
static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
- struct dentry *ret;
+ struct inode *inode;
- ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
- return ret;
+ inode = btrfs_lookup_dentry(dir, dentry);
+ if (IS_ERR(inode)) {
+ if (PTR_ERR(inode) == -ENOENT)
+ inode = NULL;
+ else
+ return ERR_CAST(inode);
+ }
+
+ return d_materialise_unique(dentry, inode);
}
unsigned char btrfs_filetype_table[] = {
@@ -5358,7 +5524,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
u32 sizes[2];
unsigned long ptr;
int ret;
- int owner;
path = btrfs_alloc_path();
if (!path)
@@ -5392,6 +5557,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
* number
*/
BTRFS_I(inode)->index_cnt = 2;
+ BTRFS_I(inode)->dir_index = *index;
BTRFS_I(inode)->root = root;
BTRFS_I(inode)->generation = trans->transid;
inode->i_generation = BTRFS_I(inode)->generation;
@@ -5404,11 +5570,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
*/
set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
- if (S_ISDIR(mode))
- owner = 0;
- else
- owner = 1;
-
key[0].objectid = objectid;
btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
key[0].offset = 0;
@@ -5473,6 +5634,12 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
btrfs_update_root_times(trans, root);
+ ret = btrfs_inode_inherit_props(trans, inode, dir);
+ if (ret)
+ btrfs_err(root->fs_info,
+ "error inheriting props for ino %llu (root %llu): %d",
+ btrfs_ino(inode), root->root_key.objectid, ret);
+
return inode;
fail:
if (dir)
@@ -5741,6 +5908,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
goto fail;
}
+ /* There are several dir indexes for this inode, clear the cache. */
+ BTRFS_I(inode)->dir_index = 0ULL;
inc_nlink(inode);
inode_inc_iversion(inode);
inode->i_ctime = CURRENT_TIME;
@@ -6004,7 +6173,7 @@ again:
btrfs_file_extent_num_bytes(leaf, item);
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size_t size;
- size = btrfs_file_extent_inline_len(leaf, item);
+ size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_end = ALIGN(extent_start + size, root->sectorsize);
}
next:
@@ -6073,7 +6242,7 @@ next:
goto out;
}
- size = btrfs_file_extent_inline_len(leaf, item);
+ size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_offset = page_offset(page) + pg_offset - extent_start;
copy_size = min_t(u64, PAGE_CACHE_SIZE - pg_offset,
size - extent_offset);
@@ -6390,6 +6559,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
int slot;
int found_type;
bool nocow = (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW);
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -6433,6 +6603,10 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
if (!nocow && found_type == BTRFS_FILE_EXTENT_REG)
goto out;
+ extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
+ if (extent_end <= offset)
+ goto out;
+
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
if (disk_bytenr == 0)
goto out;
@@ -6450,8 +6624,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
*ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
}
- extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
-
if (btrfs_extent_readonly(root, disk_bytenr))
goto out;
btrfs_release_path(path);
@@ -6783,17 +6955,16 @@ unlock_err:
static void btrfs_endio_direct_read(struct bio *bio, int err)
{
struct btrfs_dio_private *dip = bio->bi_private;
- struct bio_vec *bvec_end = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct bio_vec *bvec = bio->bi_io_vec;
+ struct bio_vec *bvec;
struct inode *inode = dip->inode;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *dio_bio;
u32 *csums = (u32 *)dip->csum;
- int index = 0;
u64 start;
+ int i;
start = dip->logical_offset;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
struct page *page = bvec->bv_page;
char *kaddr;
@@ -6809,18 +6980,16 @@ static void btrfs_endio_direct_read(struct bio *bio, int err)
local_irq_restore(flags);
flush_dcache_page(bvec->bv_page);
- if (csum != csums[index]) {
+ if (csum != csums[i]) {
btrfs_err(root->fs_info, "csum failed ino %llu off %llu csum %u expected csum %u",
btrfs_ino(inode), start, csum,
- csums[index]);
+ csums[i]);
err = -EIO;
}
}
start += bvec->bv_len;
- bvec++;
- index++;
- } while (bvec <= bvec_end);
+ }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
@@ -6898,10 +7067,11 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
struct btrfs_dio_private *dip = bio->bi_private;
if (err) {
- printk(KERN_ERR "btrfs direct IO failed ino %llu rw %lu "
- "sector %#Lx len %u err no %d\n",
+ btrfs_err(BTRFS_I(dip->inode)->root->fs_info,
+ "direct IO failed ino %llu rw %lu sector %#Lx len %u err no %d",
btrfs_ino(dip->inode), bio->bi_rw,
- (unsigned long long)bio->bi_sector, bio->bi_size, err);
+ (unsigned long long)bio->bi_iter.bi_sector,
+ bio->bi_iter.bi_size, err);
dip->errors = 1;
/*
@@ -6992,7 +7162,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
struct bio *bio;
struct bio *orig_bio = dip->orig_bio;
struct bio_vec *bvec = orig_bio->bi_io_vec;
- u64 start_sector = orig_bio->bi_sector;
+ u64 start_sector = orig_bio->bi_iter.bi_sector;
u64 file_offset = dip->logical_offset;
u64 submit_len = 0;
u64 map_length;
@@ -7000,7 +7170,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
int ret = 0;
int async_submit = 0;
- map_length = orig_bio->bi_size;
+ map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw, start_sector << 9,
&map_length, NULL, 0);
if (ret) {
@@ -7008,7 +7178,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
return -EIO;
}
- if (map_length >= orig_bio->bi_size) {
+ if (map_length >= orig_bio->bi_iter.bi_size) {
bio = orig_bio;
goto submit;
}
@@ -7060,7 +7230,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip,
bio->bi_private = dip;
bio->bi_end_io = btrfs_end_dio_bio;
- map_length = orig_bio->bi_size;
+ map_length = orig_bio->bi_iter.bi_size;
ret = btrfs_map_block(root->fs_info, rw,
start_sector << 9,
&map_length, NULL, 0);
@@ -7118,7 +7288,8 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
if (!skip_sum && !write) {
csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
- sum_len = dio_bio->bi_size >> inode->i_sb->s_blocksize_bits;
+ sum_len = dio_bio->bi_iter.bi_size >>
+ inode->i_sb->s_blocksize_bits;
sum_len *= csum_size;
} else {
sum_len = 0;
@@ -7133,8 +7304,8 @@ static void btrfs_submit_direct(int rw, struct bio *dio_bio,
dip->private = dio_bio->bi_private;
dip->inode = inode;
dip->logical_offset = file_offset;
- dip->bytes = dio_bio->bi_size;
- dip->disk_bytenr = (u64)dio_bio->bi_sector << 9;
+ dip->bytes = dio_bio->bi_iter.bi_size;
+ dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
io_bio->bi_private = dip;
dip->errors = 0;
dip->orig_bio = io_bio;
@@ -7371,6 +7542,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
struct extent_state *cached_state = NULL;
u64 page_start = page_offset(page);
u64 page_end = page_start + PAGE_CACHE_SIZE - 1;
+ int inode_evicting = inode->i_state & I_FREEING;
/*
* we have the page locked, so new writeback can't start,
@@ -7386,17 +7558,21 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
btrfs_releasepage(page, GFP_NOFS);
return;
}
- lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode, page_offset(page));
+
+ if (!inode_evicting)
+ lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
+ ordered = btrfs_lookup_ordered_extent(inode, page_start);
if (ordered) {
/*
* IO on this page will never be started, so we need
* to account for any ordered extents now
*/
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 0, &cached_state, GFP_NOFS);
+ if (!inode_evicting)
+ clear_extent_bit(tree, page_start, page_end,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 0, &cached_state,
+ GFP_NOFS);
/*
* whoever cleared the private bit is responsible
* for the finish_ordered_io
@@ -7420,14 +7596,22 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
btrfs_finish_ordered_io(ordered);
}
btrfs_put_ordered_extent(ordered);
- cached_state = NULL;
- lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
+ if (!inode_evicting) {
+ cached_state = NULL;
+ lock_extent_bits(tree, page_start, page_end, 0,
+ &cached_state);
+ }
+ }
+
+ if (!inode_evicting) {
+ clear_extent_bit(tree, page_start, page_end,
+ EXTENT_LOCKED | EXTENT_DIRTY |
+ EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
+ EXTENT_DEFRAG, 1, 1,
+ &cached_state, GFP_NOFS);
+
+ __btrfs_releasepage(page, GFP_NOFS);
}
- clear_extent_bit(tree, page_start, page_end,
- EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
- &cached_state, GFP_NOFS);
- __btrfs_releasepage(page, GFP_NOFS);
ClearPageChecked(page);
if (PagePrivate(page)) {
@@ -7737,7 +7921,9 @@ out:
* create a new subvolume directory/inode (helper for the ioctl).
*/
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
- struct btrfs_root *new_root, u64 new_dirid)
+ struct btrfs_root *new_root,
+ struct btrfs_root *parent_root,
+ u64 new_dirid)
{
struct inode *inode;
int err;
@@ -7755,6 +7941,12 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
set_nlink(inode, 1);
btrfs_i_size_write(inode, 0);
+ err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
+ if (err)
+ btrfs_err(new_root->fs_info,
+ "error inheriting subvolume %llu properties: %d\n",
+ new_root->root_key.objectid, err);
+
err = btrfs_update_inode(trans, new_root, inode);
iput(inode);
@@ -7780,6 +7972,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->flags = 0;
ei->csum_bytes = 0;
ei->index_cnt = (u64)-1;
+ ei->dir_index = 0;
ei->last_unlink_trans = 0;
ei->last_log_commit = 0;
@@ -8067,6 +8260,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (ret)
goto out_fail;
+ BTRFS_I(old_inode)->dir_index = 0ULL;
if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
/* force full log commit if subvolume involved. */
root->fs_info->last_trans_log_full_commit = trans->transid;
@@ -8155,6 +8349,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
goto out_fail;
}
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = index;
+
if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
struct dentry *parent = new_dentry->d_parent;
btrfs_log_new_name(trans, old_inode, old_dir, parent);
@@ -8290,7 +8487,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
{
int ret;
- if (root->fs_info->sb->s_flags & MS_RDONLY)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
return -EROFS;
ret = __start_delalloc_inodes(root, delay_iput);
@@ -8316,7 +8513,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput)
struct list_head splice;
int ret;
- if (fs_info->sb->s_flags & MS_RDONLY)
+ if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
return -EROFS;
INIT_LIST_HEAD(&splice);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ad27dcea319c..a6d8efa46bfe 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -56,6 +56,8 @@
#include "rcu-string.h"
#include "send.h"
#include "dev-replace.h"
+#include "props.h"
+#include "sysfs.h"
static int btrfs_clone(struct inode *src, struct inode *inode,
u64 off, u64 olen, u64 olen_aligned, u64 destoff);
@@ -190,6 +192,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
unsigned int i_oldflags;
umode_t mode;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
if (btrfs_root_readonly(root))
return -EROFS;
@@ -200,9 +205,6 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (ret)
return ret;
- if (!inode_owner_or_capable(inode))
- return -EACCES;
-
ret = mnt_want_write_file(file);
if (ret)
return ret;
@@ -280,9 +282,25 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
if (flags & FS_NOCOMP_FL) {
ip->flags &= ~BTRFS_INODE_COMPRESS;
ip->flags |= BTRFS_INODE_NOCOMPRESS;
+
+ ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
+ if (ret && ret != -ENODATA)
+ goto out_drop;
} else if (flags & FS_COMPR_FL) {
+ const char *comp;
+
ip->flags |= BTRFS_INODE_COMPRESS;
ip->flags &= ~BTRFS_INODE_NOCOMPRESS;
+
+ if (root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
+ comp = "lzo";
+ else
+ comp = "zlib";
+ ret = btrfs_set_prop(inode, "btrfs.compression",
+ comp, strlen(comp), 0);
+ if (ret)
+ goto out_drop;
+
} else {
ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
}
@@ -392,6 +410,7 @@ static noinline int create_subvol(struct inode *dir,
struct btrfs_root *new_root;
struct btrfs_block_rsv block_rsv;
struct timespec cur_time = CURRENT_TIME;
+ struct inode *inode;
int ret;
int err;
u64 objectid;
@@ -417,7 +436,9 @@ static noinline int create_subvol(struct inode *dir,
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- goto out;
+ btrfs_subvolume_release_metadata(root, &block_rsv,
+ qgroup_reserved);
+ return ret;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
@@ -500,7 +521,7 @@ static noinline int create_subvol(struct inode *dir,
btrfs_record_root_in_trans(trans, new_root);
- ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
+ ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid);
if (ret) {
/* We potentially lose an unused inode item here */
btrfs_abort_transaction(trans, root, ret);
@@ -542,6 +563,8 @@ static noinline int create_subvol(struct inode *dir,
fail:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
+ btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
+
if (async_transid) {
*async_transid = trans->transid;
err = btrfs_commit_transaction_async(trans, root, 1);
@@ -553,10 +576,12 @@ fail:
if (err && !ret)
ret = err;
- if (!ret)
- d_instantiate(dentry, btrfs_lookup_dentry(dir, dentry));
-out:
- btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
+ if (!ret) {
+ inode = btrfs_lookup_dentry(dir, dentry);
+ if (IS_ERR(inode))
+ return PTR_ERR(inode);
+ d_instantiate(dentry, inode);
+ }
return ret;
}
@@ -642,7 +667,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
ret = PTR_ERR(inode);
goto fail;
}
- BUG_ON(!inode);
+
d_instantiate(dentry, inode);
ret = 0;
fail:
@@ -1011,7 +1036,7 @@ out:
static int cluster_pages_for_defrag(struct inode *inode,
struct page **pages,
unsigned long start_index,
- int num_pages)
+ unsigned long num_pages)
{
unsigned long file_end;
u64 isize = i_size_read(inode);
@@ -1169,8 +1194,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
int defrag_count = 0;
int compress_type = BTRFS_COMPRESS_ZLIB;
int extent_thresh = range->extent_thresh;
- int max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
- int cluster = max_cluster;
+ unsigned long max_cluster = (256 * 1024) >> PAGE_CACHE_SHIFT;
+ unsigned long cluster = max_cluster;
u64 new_align = ~((u64)128 * 1024 - 1);
struct page **pages = NULL;
@@ -1254,7 +1279,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
break;
if (btrfs_defrag_cancelled(root->fs_info)) {
- printk(KERN_DEBUG "btrfs: defrag_file cancelled\n");
+ printk(KERN_DEBUG "BTRFS: defrag_file cancelled\n");
ret = -EAGAIN;
break;
}
@@ -1416,20 +1441,20 @@ static noinline int btrfs_ioctl_resize(struct file *file,
ret = -EINVAL;
goto out_free;
}
- printk(KERN_INFO "btrfs: resizing devid %llu\n", devid);
+ btrfs_info(root->fs_info, "resizing devid %llu", devid);
}
device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
if (!device) {
- printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
+ btrfs_info(root->fs_info, "resizer unable to find device %llu",
devid);
ret = -ENODEV;
goto out_free;
}
if (!device->writeable) {
- printk(KERN_INFO "btrfs: resizer unable to apply on "
- "readonly device %llu\n",
+ btrfs_info(root->fs_info,
+ "resizer unable to apply on readonly device %llu",
devid);
ret = -EPERM;
goto out_free;
@@ -1466,6 +1491,10 @@ static noinline int btrfs_ioctl_resize(struct file *file,
}
new_size = old_size - new_size;
} else if (mod > 0) {
+ if (new_size > ULLONG_MAX - old_size) {
+ ret = -EINVAL;
+ goto out_free;
+ }
new_size = old_size + new_size;
}
@@ -1481,7 +1510,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
do_div(new_size, root->sectorsize);
new_size *= root->sectorsize;
- printk_in_rcu(KERN_INFO "btrfs: new size for %s is %llu\n",
+ printk_in_rcu(KERN_INFO "BTRFS: new size for %s is %llu\n",
rcu_str_deref(device->name), new_size);
if (new_size > old_size) {
@@ -1542,9 +1571,15 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
src_inode = file_inode(src.file);
if (src_inode->i_sb != file_inode(file)->i_sb) {
- printk(KERN_INFO "btrfs: Snapshot src from "
- "another FS\n");
+ btrfs_info(BTRFS_I(src_inode)->root->fs_info,
+ "Snapshot src from another FS");
ret = -EINVAL;
+ } else if (!inode_owner_or_capable(src_inode)) {
+ /*
+ * Subvolume creation is not restricted, but snapshots
+ * are limited to own subvolumes only
+ */
+ ret = -EPERM;
} else {
ret = btrfs_mksubvol(&file->f_path, name, namelen,
BTRFS_I(src_inode)->root,
@@ -1662,6 +1697,9 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
u64 flags;
int ret = 0;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
ret = mnt_want_write_file(file);
if (ret)
goto out;
@@ -1686,11 +1724,6 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
goto out_drop_write;
}
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out_drop_write;
- }
-
down_write(&root->fs_info->subvol_sem);
/* nothing to do */
@@ -1698,12 +1731,28 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
goto out_drop_sem;
root_flags = btrfs_root_flags(&root->root_item);
- if (flags & BTRFS_SUBVOL_RDONLY)
+ if (flags & BTRFS_SUBVOL_RDONLY) {
btrfs_set_root_flags(&root->root_item,
root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
- else
- btrfs_set_root_flags(&root->root_item,
+ } else {
+ /*
+ * Block RO -> RW transition if this subvolume is involved in
+ * send
+ */
+ spin_lock(&root->root_item_lock);
+ if (root->send_in_progress == 0) {
+ btrfs_set_root_flags(&root->root_item,
root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
+ spin_unlock(&root->root_item_lock);
+ } else {
+ spin_unlock(&root->root_item_lock);
+ btrfs_warn(root->fs_info,
+ "Attempt to set subvolume %llu read-write during send",
+ root->root_key.objectid);
+ ret = -EPERM;
+ goto out_drop_sem;
+ }
+ }
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
@@ -1910,7 +1959,7 @@ static noinline int search_ioctl(struct inode *inode,
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
- printk(KERN_ERR "could not find root %llu\n",
+ printk(KERN_ERR "BTRFS: could not find root %llu\n",
sk->tree_id);
btrfs_free_path(path);
return -ENOENT;
@@ -2000,7 +2049,7 @@ static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
key.offset = (u64)-1;
root = btrfs_read_fs_root_no_name(info, &key);
if (IS_ERR(root)) {
- printk(KERN_ERR "could not find root %llu\n", tree_id);
+ printk(KERN_ERR "BTRFS: could not find root %llu\n", tree_id);
ret = -ENOENT;
goto out;
}
@@ -2838,12 +2887,14 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
* note the key will change type as we walk through the
* tree.
*/
+ path->leave_spinning = 1;
ret = btrfs_search_slot(NULL, BTRFS_I(src)->root, &key, path,
0, 0);
if (ret < 0)
goto out;
nritems = btrfs_header_nritems(path->nodes[0]);
+process_slot:
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(BTRFS_I(src)->root, path);
if (ret < 0)
@@ -2870,11 +2921,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
u8 comp;
u64 endoff;
- size = btrfs_item_size_nr(leaf, slot);
- read_extent_buffer(leaf, buf,
- btrfs_item_ptr_offset(leaf, slot),
- size);
-
extent = btrfs_item_ptr(leaf, slot,
struct btrfs_file_extent_item);
comp = btrfs_file_extent_compression(leaf, extent);
@@ -2893,11 +2939,20 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
datal = btrfs_file_extent_ram_bytes(leaf,
extent);
}
- btrfs_release_path(path);
if (key.offset + datal <= off ||
- key.offset >= off + len - 1)
- goto next;
+ key.offset >= off + len - 1) {
+ path->slots[0]++;
+ goto process_slot;
+ }
+
+ size = btrfs_item_size_nr(leaf, slot);
+ read_extent_buffer(leaf, buf,
+ btrfs_item_ptr_offset(leaf, slot),
+ size);
+
+ btrfs_release_path(path);
+ path->leave_spinning = 0;
memcpy(&new_key, &key, sizeof(new_key));
new_key.objectid = btrfs_ino(inode);
@@ -3068,7 +3123,6 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
}
ret = btrfs_end_transaction(trans, root);
}
-next:
btrfs_release_path(path);
key.offset++;
}
@@ -3196,9 +3250,17 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
unlock_extent(&BTRFS_I(src)->io_tree, off, off + len - 1);
out_unlock:
- mutex_unlock(&src->i_mutex);
- if (!same_inode)
- mutex_unlock(&inode->i_mutex);
+ if (!same_inode) {
+ if (inode < src) {
+ mutex_unlock(&src->i_mutex);
+ mutex_unlock(&inode->i_mutex);
+ } else {
+ mutex_unlock(&inode->i_mutex);
+ mutex_unlock(&src->i_mutex);
+ }
+ } else {
+ mutex_unlock(&src->i_mutex);
+ }
out_fput:
fdput(src_file);
out_drop_write:
@@ -3321,8 +3383,8 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
if (IS_ERR_OR_NULL(di)) {
btrfs_free_path(path);
btrfs_end_transaction(trans, root);
- printk(KERN_ERR "Umm, you don't have the default dir item, "
- "this isn't going to work\n");
+ btrfs_err(new_root->fs_info, "Umm, you don't have the default dir"
+ "item, this isn't going to work");
ret = -ENOENT;
goto out;
}
@@ -4303,6 +4365,9 @@ static long btrfs_ioctl_set_received_subvol(struct file *file,
int ret = 0;
int received_uuid_changed;
+ if (!inode_owner_or_capable(inode))
+ return -EPERM;
+
ret = mnt_want_write_file(file);
if (ret < 0)
return ret;
@@ -4319,11 +4384,6 @@ static long btrfs_ioctl_set_received_subvol(struct file *file,
goto out;
}
- if (!inode_owner_or_capable(inode)) {
- ret = -EACCES;
- goto out;
- }
-
sa = memdup_user(arg, sizeof(*sa));
if (IS_ERR(sa)) {
ret = PTR_ERR(sa);
@@ -4409,8 +4469,8 @@ static int btrfs_ioctl_get_fslabel(struct file *file, void __user *arg)
len = strnlen(label, BTRFS_LABEL_SIZE);
if (len == BTRFS_LABEL_SIZE) {
- pr_warn("btrfs: label is too long, return the first %zu bytes\n",
- --len);
+ btrfs_warn(root->fs_info,
+ "label is too long, return the first %zu bytes", --len);
}
ret = copy_to_user(arg, label, len);
@@ -4433,7 +4493,7 @@ static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg)
return -EFAULT;
if (strnlen(label, BTRFS_LABEL_SIZE) == BTRFS_LABEL_SIZE) {
- pr_err("btrfs: unable to set label with more than %d bytes\n",
+ btrfs_err(root->fs_info, "unable to set label with more than %d bytes",
BTRFS_LABEL_SIZE - 1);
return -EINVAL;
}
@@ -4451,13 +4511,173 @@ static int btrfs_ioctl_set_fslabel(struct file *file, void __user *arg)
spin_lock(&root->fs_info->super_lock);
strcpy(super_block->label, label);
spin_unlock(&root->fs_info->super_lock);
- ret = btrfs_end_transaction(trans, root);
+ ret = btrfs_commit_transaction(trans, root);
out_unlock:
mnt_drop_write_file(file);
return ret;
}
+#define INIT_FEATURE_FLAGS(suffix) \
+ { .compat_flags = BTRFS_FEATURE_COMPAT_##suffix, \
+ .compat_ro_flags = BTRFS_FEATURE_COMPAT_RO_##suffix, \
+ .incompat_flags = BTRFS_FEATURE_INCOMPAT_##suffix }
+
+static int btrfs_ioctl_get_supported_features(struct file *file,
+ void __user *arg)
+{
+ static struct btrfs_ioctl_feature_flags features[3] = {
+ INIT_FEATURE_FLAGS(SUPP),
+ INIT_FEATURE_FLAGS(SAFE_SET),
+ INIT_FEATURE_FLAGS(SAFE_CLEAR)
+ };
+
+ if (copy_to_user(arg, &features, sizeof(features)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int btrfs_ioctl_get_features(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_super_block *super_block = root->fs_info->super_copy;
+ struct btrfs_ioctl_feature_flags features;
+
+ features.compat_flags = btrfs_super_compat_flags(super_block);
+ features.compat_ro_flags = btrfs_super_compat_ro_flags(super_block);
+ features.incompat_flags = btrfs_super_incompat_flags(super_block);
+
+ if (copy_to_user(arg, &features, sizeof(features)))
+ return -EFAULT;
+
+ return 0;
+}
+
+static int check_feature_bits(struct btrfs_root *root,
+ enum btrfs_feature_set set,
+ u64 change_mask, u64 flags, u64 supported_flags,
+ u64 safe_set, u64 safe_clear)
+{
+ const char *type = btrfs_feature_set_names[set];
+ char *names;
+ u64 disallowed, unsupported;
+ u64 set_mask = flags & change_mask;
+ u64 clear_mask = ~flags & change_mask;
+
+ unsupported = set_mask & ~supported_flags;
+ if (unsupported) {
+ names = btrfs_printable_features(set, unsupported);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "this kernel does not support the %s feature bit%s",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "this kernel does not support %s bits 0x%llx",
+ type, unsupported);
+ return -EOPNOTSUPP;
+ }
+
+ disallowed = set_mask & ~safe_set;
+ if (disallowed) {
+ names = btrfs_printable_features(set, disallowed);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "can't set the %s feature bit%s while mounted",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "can't set %s bits 0x%llx while mounted",
+ type, disallowed);
+ return -EPERM;
+ }
+
+ disallowed = clear_mask & ~safe_clear;
+ if (disallowed) {
+ names = btrfs_printable_features(set, disallowed);
+ if (names) {
+ btrfs_warn(root->fs_info,
+ "can't clear the %s feature bit%s while mounted",
+ names, strchr(names, ',') ? "s" : "");
+ kfree(names);
+ } else
+ btrfs_warn(root->fs_info,
+ "can't clear %s bits 0x%llx while mounted",
+ type, disallowed);
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+#define check_feature(root, change_mask, flags, mask_base) \
+check_feature_bits(root, FEAT_##mask_base, change_mask, flags, \
+ BTRFS_FEATURE_ ## mask_base ## _SUPP, \
+ BTRFS_FEATURE_ ## mask_base ## _SAFE_SET, \
+ BTRFS_FEATURE_ ## mask_base ## _SAFE_CLEAR)
+
+static int btrfs_ioctl_set_features(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_super_block *super_block = root->fs_info->super_copy;
+ struct btrfs_ioctl_feature_flags flags[2];
+ struct btrfs_trans_handle *trans;
+ u64 newflags;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (copy_from_user(flags, arg, sizeof(flags)))
+ return -EFAULT;
+
+ /* Nothing to do */
+ if (!flags[0].compat_flags && !flags[0].compat_ro_flags &&
+ !flags[0].incompat_flags)
+ return 0;
+
+ ret = check_feature(root, flags[0].compat_flags,
+ flags[1].compat_flags, COMPAT);
+ if (ret)
+ return ret;
+
+ ret = check_feature(root, flags[0].compat_ro_flags,
+ flags[1].compat_ro_flags, COMPAT_RO);
+ if (ret)
+ return ret;
+
+ ret = check_feature(root, flags[0].incompat_flags,
+ flags[1].incompat_flags, INCOMPAT);
+ if (ret)
+ return ret;
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ spin_lock(&root->fs_info->super_lock);
+ newflags = btrfs_super_compat_flags(super_block);
+ newflags |= flags[0].compat_flags & flags[1].compat_flags;
+ newflags &= ~(flags[0].compat_flags & ~flags[1].compat_flags);
+ btrfs_set_super_compat_flags(super_block, newflags);
+
+ newflags = btrfs_super_compat_ro_flags(super_block);
+ newflags |= flags[0].compat_ro_flags & flags[1].compat_ro_flags;
+ newflags &= ~(flags[0].compat_ro_flags & ~flags[1].compat_ro_flags);
+ btrfs_set_super_compat_ro_flags(super_block, newflags);
+
+ newflags = btrfs_super_incompat_flags(super_block);
+ newflags |= flags[0].incompat_flags & flags[1].incompat_flags;
+ newflags &= ~(flags[0].incompat_flags & ~flags[1].incompat_flags);
+ btrfs_set_super_incompat_flags(super_block, newflags);
+ spin_unlock(&root->fs_info->super_lock);
+
+ return btrfs_commit_transaction(trans, root);
+}
+
long btrfs_ioctl(struct file *file, unsigned int
cmd, unsigned long arg)
{
@@ -4576,6 +4796,12 @@ long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_set_fslabel(file, argp);
case BTRFS_IOC_FILE_EXTENT_SAME:
return btrfs_ioctl_file_extent_same(file, argp);
+ case BTRFS_IOC_GET_SUPPORTED_FEATURES:
+ return btrfs_ioctl_get_supported_features(file, argp);
+ case BTRFS_IOC_GET_FEATURES:
+ return btrfs_ioctl_get_features(file, argp);
+ case BTRFS_IOC_SET_FEATURES:
+ return btrfs_ioctl_set_features(file, argp);
}
return -ENOTTY;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index b6a6f07c5ce2..b47f669aca75 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -141,7 +141,7 @@ static int lzo_compress_pages(struct list_head *ws,
ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
&out_len, workspace->mem);
if (ret != LZO_E_OK) {
- printk(KERN_DEBUG "btrfs deflate in loop returned %d\n",
+ printk(KERN_DEBUG "BTRFS: deflate in loop returned %d\n",
ret);
ret = -1;
goto out;
@@ -357,7 +357,7 @@ cont:
if (need_unmap)
kunmap(pages_in[page_in_index - 1]);
if (ret != LZO_E_OK) {
- printk(KERN_WARNING "btrfs decompress failed\n");
+ printk(KERN_WARNING "BTRFS: decompress failed\n");
ret = -1;
break;
}
@@ -401,7 +401,7 @@ static int lzo_decompress(struct list_head *ws, unsigned char *data_in,
out_len = PAGE_CACHE_SIZE;
ret = lzo1x_decompress_safe(data_in, in_len, workspace->buf, &out_len);
if (ret != LZO_E_OK) {
- printk(KERN_WARNING "btrfs decompress failed!\n");
+ printk(KERN_WARNING "BTRFS: decompress failed!\n");
ret = -1;
goto out;
}
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 69582d5b69d1..b16450b840e7 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -336,13 +336,14 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
entry->len);
*file_offset = dec_end;
if (dec_start > dec_end) {
- printk(KERN_CRIT "bad ordering dec_start %llu end %llu\n",
- dec_start, dec_end);
+ btrfs_crit(BTRFS_I(inode)->root->fs_info,
+ "bad ordering dec_start %llu end %llu", dec_start, dec_end);
}
to_dec = dec_end - dec_start;
if (to_dec > entry->bytes_left) {
- printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
- entry->bytes_left, to_dec);
+ btrfs_crit(BTRFS_I(inode)->root->fs_info,
+ "bad ordered accounting left %llu size %llu",
+ entry->bytes_left, to_dec);
}
entry->bytes_left -= to_dec;
if (!uptodate)
@@ -401,7 +402,8 @@ have_entry:
}
if (io_size > entry->bytes_left) {
- printk(KERN_CRIT "bad ordered accounting left %llu size %llu\n",
+ btrfs_crit(BTRFS_I(inode)->root->fs_info,
+ "bad ordered accounting left %llu size %llu",
entry->bytes_left, io_size);
}
entry->bytes_left -= io_size;
@@ -520,7 +522,8 @@ void btrfs_remove_ordered_extent(struct inode *inode,
spin_lock_irq(&tree->lock);
node = &entry->rb_node;
rb_erase(node, &tree->tree);
- tree->last = NULL;
+ if (tree->last == node)
+ tree->last = NULL;
set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
spin_unlock_irq(&tree->lock);
diff --git a/fs/btrfs/orphan.c b/fs/btrfs/orphan.c
index 24cad1695af7..65793edb38ca 100644
--- a/fs/btrfs/orphan.c
+++ b/fs/btrfs/orphan.c
@@ -69,23 +69,3 @@ out:
btrfs_free_path(path);
return ret;
}
-
-int btrfs_find_orphan_item(struct btrfs_root *root, u64 offset)
-{
- struct btrfs_path *path;
- struct btrfs_key key;
- int ret;
-
- key.objectid = BTRFS_ORPHAN_OBJECTID;
- key.type = BTRFS_ORPHAN_ITEM_KEY;
- key.offset = offset;
-
- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
-
- ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-
- btrfs_free_path(path);
- return ret;
-}
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 417053b17181..6efd70d3b64f 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -154,7 +154,7 @@ static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
u32 item_size)
{
if (!IS_ALIGNED(item_size, sizeof(u64))) {
- pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ pr_warn("BTRFS: uuid item with illegal size %lu!\n",
(unsigned long)item_size);
return;
}
@@ -249,7 +249,7 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
BTRFS_FILE_EXTENT_INLINE) {
printk(KERN_INFO "\t\tinline extent data "
"size %u\n",
- btrfs_file_extent_inline_len(l, fi));
+ btrfs_file_extent_inline_len(l, i, fi));
break;
}
printk(KERN_INFO "\t\textent data disk bytenr %llu "
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
new file mode 100644
index 000000000000..129b1dd28527
--- /dev/null
+++ b/fs/btrfs/props.c
@@ -0,0 +1,427 @@
+/*
+ * Copyright (C) 2014 Filipe David Borba Manana <fdmanana@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#include <linux/hashtable.h>
+#include "props.h"
+#include "btrfs_inode.h"
+#include "hash.h"
+#include "transaction.h"
+#include "xattr.h"
+
+#define BTRFS_PROP_HANDLERS_HT_BITS 8
+static DEFINE_HASHTABLE(prop_handlers_ht, BTRFS_PROP_HANDLERS_HT_BITS);
+
+struct prop_handler {
+ struct hlist_node node;
+ const char *xattr_name;
+ int (*validate)(const char *value, size_t len);
+ int (*apply)(struct inode *inode, const char *value, size_t len);
+ const char *(*extract)(struct inode *inode);
+ int inheritable;
+};
+
+static int prop_compression_validate(const char *value, size_t len);
+static int prop_compression_apply(struct inode *inode,
+ const char *value,
+ size_t len);
+static const char *prop_compression_extract(struct inode *inode);
+
+static struct prop_handler prop_handlers[] = {
+ {
+ .xattr_name = XATTR_BTRFS_PREFIX "compression",
+ .validate = prop_compression_validate,
+ .apply = prop_compression_apply,
+ .extract = prop_compression_extract,
+ .inheritable = 1
+ },
+ {
+ .xattr_name = NULL
+ }
+};
+
+void __init btrfs_props_init(void)
+{
+ struct prop_handler *p;
+
+ hash_init(prop_handlers_ht);
+
+ for (p = &prop_handlers[0]; p->xattr_name; p++) {
+ u64 h = btrfs_name_hash(p->xattr_name, strlen(p->xattr_name));
+
+ hash_add(prop_handlers_ht, &p->node, h);
+ }
+}
+
+static const struct hlist_head *find_prop_handlers_by_hash(const u64 hash)
+{
+ struct hlist_head *h;
+
+ h = &prop_handlers_ht[hash_min(hash, BTRFS_PROP_HANDLERS_HT_BITS)];
+ if (hlist_empty(h))
+ return NULL;
+
+ return h;
+}
+
+static const struct prop_handler *
+find_prop_handler(const char *name,
+ const struct hlist_head *handlers)
+{
+ struct prop_handler *h;
+
+ if (!handlers) {
+ u64 hash = btrfs_name_hash(name, strlen(name));
+
+ handlers = find_prop_handlers_by_hash(hash);
+ if (!handlers)
+ return NULL;
+ }
+
+ hlist_for_each_entry(h, handlers, node)
+ if (!strcmp(h->xattr_name, name))
+ return h;
+
+ return NULL;
+}
+
+static int __btrfs_set_prop(struct btrfs_trans_handle *trans,
+ struct inode *inode,
+ const char *name,
+ const char *value,
+ size_t value_len,
+ int flags)
+{
+ const struct prop_handler *handler;
+ int ret;
+
+ if (strlen(name) <= XATTR_BTRFS_PREFIX_LEN)
+ return -EINVAL;
+
+ handler = find_prop_handler(name, NULL);
+ if (!handler)
+ return -EINVAL;
+
+ if (value_len == 0) {
+ ret = __btrfs_setxattr(trans, inode, handler->xattr_name,
+ NULL, 0, flags);
+ if (ret)
+ return ret;
+
+ ret = handler->apply(inode, NULL, 0);
+ ASSERT(ret == 0);
+
+ return ret;
+ }
+
+ ret = handler->validate(value, value_len);
+ if (ret)
+ return ret;
+ ret = __btrfs_setxattr(trans, inode, handler->xattr_name,
+ value, value_len, flags);
+ if (ret)
+ return ret;
+ ret = handler->apply(inode, value, value_len);
+ if (ret) {
+ __btrfs_setxattr(trans, inode, handler->xattr_name,
+ NULL, 0, flags);
+ return ret;
+ }
+
+ set_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(inode)->runtime_flags);
+
+ return 0;
+}
+
+int btrfs_set_prop(struct inode *inode,
+ const char *name,
+ const char *value,
+ size_t value_len,
+ int flags)
+{
+ return __btrfs_set_prop(NULL, inode, name, value, value_len, flags);
+}
+
+static int iterate_object_props(struct btrfs_root *root,
+ struct btrfs_path *path,
+ u64 objectid,
+ void (*iterator)(void *,
+ const struct prop_handler *,
+ const char *,
+ size_t),
+ void *ctx)
+{
+ int ret;
+ char *name_buf = NULL;
+ char *value_buf = NULL;
+ int name_buf_len = 0;
+ int value_buf_len = 0;
+
+ while (1) {
+ struct btrfs_key key;
+ struct btrfs_dir_item *di;
+ struct extent_buffer *leaf;
+ u32 total_len, cur, this_len;
+ int slot;
+ const struct hlist_head *handlers;
+
+ slot = path->slots[0];
+ leaf = path->nodes[0];
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ else if (ret > 0)
+ break;
+ continue;
+ }
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != objectid)
+ break;
+ if (key.type != BTRFS_XATTR_ITEM_KEY)
+ break;
+
+ handlers = find_prop_handlers_by_hash(key.offset);
+ if (!handlers)
+ goto next_slot;
+
+ di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
+ cur = 0;
+ total_len = btrfs_item_size_nr(leaf, slot);
+
+ while (cur < total_len) {
+ u32 name_len = btrfs_dir_name_len(leaf, di);
+ u32 data_len = btrfs_dir_data_len(leaf, di);
+ unsigned long name_ptr, data_ptr;
+ const struct prop_handler *handler;
+
+ this_len = sizeof(*di) + name_len + data_len;
+ name_ptr = (unsigned long)(di + 1);
+ data_ptr = name_ptr + name_len;
+
+ if (name_len <= XATTR_BTRFS_PREFIX_LEN ||
+ memcmp_extent_buffer(leaf, XATTR_BTRFS_PREFIX,
+ name_ptr,
+ XATTR_BTRFS_PREFIX_LEN))
+ goto next_dir_item;
+
+ if (name_len >= name_buf_len) {
+ kfree(name_buf);
+ name_buf_len = name_len + 1;
+ name_buf = kmalloc(name_buf_len, GFP_NOFS);
+ if (!name_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ read_extent_buffer(leaf, name_buf, name_ptr, name_len);
+ name_buf[name_len] = '\0';
+
+ handler = find_prop_handler(name_buf, handlers);
+ if (!handler)
+ goto next_dir_item;
+
+ if (data_len > value_buf_len) {
+ kfree(value_buf);
+ value_buf_len = data_len;
+ value_buf = kmalloc(data_len, GFP_NOFS);
+ if (!value_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+ read_extent_buffer(leaf, value_buf, data_ptr, data_len);
+
+ iterator(ctx, handler, value_buf, data_len);
+next_dir_item:
+ cur += this_len;
+ di = (struct btrfs_dir_item *)((char *) di + this_len);
+ }
+
+next_slot:
+ path->slots[0]++;
+ }
+
+ ret = 0;
+out:
+ btrfs_release_path(path);
+ kfree(name_buf);
+ kfree(value_buf);
+
+ return ret;
+}
+
+static void inode_prop_iterator(void *ctx,
+ const struct prop_handler *handler,
+ const char *value,
+ size_t len)
+{
+ struct inode *inode = ctx;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ int ret;
+
+ ret = handler->apply(inode, value, len);
+ if (unlikely(ret))
+ btrfs_warn(root->fs_info,
+ "error applying prop %s to ino %llu (root %llu): %d",
+ handler->xattr_name, btrfs_ino(inode),
+ root->root_key.objectid, ret);
+ else
+ set_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(inode)->runtime_flags);
+}
+
+int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path)
+{
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ u64 ino = btrfs_ino(inode);
+ int ret;
+
+ ret = iterate_object_props(root, path, ino, inode_prop_iterator, inode);
+
+ return ret;
+}
+
+static int inherit_props(struct btrfs_trans_handle *trans,
+ struct inode *inode,
+ struct inode *parent)
+{
+ const struct prop_handler *h;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ int ret;
+
+ if (!test_bit(BTRFS_INODE_HAS_PROPS,
+ &BTRFS_I(parent)->runtime_flags))
+ return 0;
+
+ for (h = &prop_handlers[0]; h->xattr_name; h++) {
+ const char *value;
+ u64 num_bytes;
+
+ if (!h->inheritable)
+ continue;
+
+ value = h->extract(parent);
+ if (!value)
+ continue;
+
+ num_bytes = btrfs_calc_trans_metadata_size(root, 1);
+ ret = btrfs_block_rsv_add(root, trans->block_rsv,
+ num_bytes, BTRFS_RESERVE_NO_FLUSH);
+ if (ret)
+ goto out;
+ ret = __btrfs_set_prop(trans, inode, h->xattr_name,
+ value, strlen(value), 0);
+ btrfs_block_rsv_release(root, trans->block_rsv, num_bytes);
+ if (ret)
+ goto out;
+ }
+ ret = 0;
+out:
+ return ret;
+}
+
+int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans,
+ struct inode *inode,
+ struct inode *dir)
+{
+ if (!dir)
+ return 0;
+
+ return inherit_props(trans, inode, dir);
+}
+
+int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_root *parent_root)
+{
+ struct btrfs_key key;
+ struct inode *parent_inode, *child_inode;
+ int ret;
+
+ key.objectid = BTRFS_FIRST_FREE_OBJECTID;
+ key.type = BTRFS_INODE_ITEM_KEY;
+ key.offset = 0;
+
+ parent_inode = btrfs_iget(parent_root->fs_info->sb, &key,
+ parent_root, NULL);
+ if (IS_ERR(parent_inode))
+ return PTR_ERR(parent_inode);
+
+ child_inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
+ if (IS_ERR(child_inode)) {
+ iput(parent_inode);
+ return PTR_ERR(child_inode);
+ }
+
+ ret = inherit_props(trans, child_inode, parent_inode);
+ iput(child_inode);
+ iput(parent_inode);
+
+ return ret;
+}
+
+static int prop_compression_validate(const char *value, size_t len)
+{
+ if (!strncmp("lzo", value, len))
+ return 0;
+ else if (!strncmp("zlib", value, len))
+ return 0;
+
+ return -EINVAL;
+}
+
+static int prop_compression_apply(struct inode *inode,
+ const char *value,
+ size_t len)
+{
+ int type;
+
+ if (len == 0) {
+ BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS;
+ BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
+
+ return 0;
+ }
+
+ if (!strncmp("lzo", value, len))
+ type = BTRFS_COMPRESS_LZO;
+ else if (!strncmp("zlib", value, len))
+ type = BTRFS_COMPRESS_ZLIB;
+ else
+ return -EINVAL;
+
+ BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
+ BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
+ BTRFS_I(inode)->force_compress = type;
+
+ return 0;
+}
+
+static const char *prop_compression_extract(struct inode *inode)
+{
+ switch (BTRFS_I(inode)->force_compress) {
+ case BTRFS_COMPRESS_ZLIB:
+ return "zlib";
+ case BTRFS_COMPRESS_LZO:
+ return "lzo";
+ }
+
+ return NULL;
+}
diff --git a/fs/btrfs/props.h b/fs/btrfs/props.h
new file mode 100644
index 000000000000..100f18829d50
--- /dev/null
+++ b/fs/btrfs/props.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2014 Filipe David Borba Manana <fdmanana@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_PROPS_H
+#define __BTRFS_PROPS_H
+
+#include "ctree.h"
+
+void __init btrfs_props_init(void);
+
+int btrfs_set_prop(struct inode *inode,
+ const char *name,
+ const char *value,
+ size_t value_len,
+ int flags);
+
+int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path);
+
+int btrfs_inode_inherit_props(struct btrfs_trans_handle *trans,
+ struct inode *inode,
+ struct inode *dir);
+
+int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct btrfs_root *parent_root);
+
+#endif
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 4e6ef490619e..472302a2d745 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -301,16 +301,16 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
if (btrfs_qgroup_status_version(l, ptr) !=
BTRFS_QGROUP_STATUS_VERSION) {
- printk(KERN_ERR
- "btrfs: old qgroup version, quota disabled\n");
+ btrfs_err(fs_info,
+ "old qgroup version, quota disabled");
goto out;
}
if (btrfs_qgroup_status_generation(l, ptr) !=
fs_info->generation) {
flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- printk(KERN_ERR
- "btrfs: qgroup generation mismatch, "
- "marked as inconsistent\n");
+ btrfs_err(fs_info,
+ "qgroup generation mismatch, "
+ "marked as inconsistent");
}
fs_info->qgroup_flags = btrfs_qgroup_status_flags(l,
ptr);
@@ -325,7 +325,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
qgroup = find_qgroup_rb(fs_info, found_key.offset);
if ((qgroup && found_key.type == BTRFS_QGROUP_INFO_KEY) ||
(!qgroup && found_key.type == BTRFS_QGROUP_LIMIT_KEY)) {
- printk(KERN_ERR "btrfs: inconsitent qgroup config\n");
+ btrfs_err(fs_info, "inconsitent qgroup config");
flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
}
if (!qgroup) {
@@ -396,8 +396,8 @@ next1:
ret = add_relation_rb(fs_info, found_key.objectid,
found_key.offset);
if (ret == -ENOENT) {
- printk(KERN_WARNING
- "btrfs: orphan qgroup relation 0x%llx->0x%llx\n",
+ btrfs_warn(fs_info,
+ "orphan qgroup relation 0x%llx->0x%llx",
found_key.objectid, found_key.offset);
ret = 0; /* ignore the error */
}
@@ -644,8 +644,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
l = path->nodes[0];
slot = path->slots[0];
- qgroup_limit = btrfs_item_ptr(l, path->slots[0],
- struct btrfs_qgroup_limit_item);
+ qgroup_limit = btrfs_item_ptr(l, slot, struct btrfs_qgroup_limit_item);
btrfs_set_qgroup_limit_flags(l, qgroup_limit, flags);
btrfs_set_qgroup_limit_max_rfer(l, qgroup_limit, max_rfer);
btrfs_set_qgroup_limit_max_excl(l, qgroup_limit, max_excl);
@@ -687,8 +686,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
l = path->nodes[0];
slot = path->slots[0];
- qgroup_info = btrfs_item_ptr(l, path->slots[0],
- struct btrfs_qgroup_info_item);
+ qgroup_info = btrfs_item_ptr(l, slot, struct btrfs_qgroup_info_item);
btrfs_set_qgroup_info_generation(l, qgroup_info, trans->transid);
btrfs_set_qgroup_info_rfer(l, qgroup_info, qgroup->rfer);
btrfs_set_qgroup_info_rfer_cmpr(l, qgroup_info, qgroup->rfer_cmpr);
@@ -1161,7 +1159,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
limit->rsv_excl);
if (ret) {
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- printk(KERN_INFO "unable to update quota limit for %llu\n",
+ btrfs_info(fs_info, "unable to update quota limit for %llu",
qgroupid);
}
@@ -1349,7 +1347,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
struct btrfs_delayed_ref_node *node,
struct btrfs_delayed_extent_op *extent_op)
{
- struct btrfs_key ins;
struct btrfs_root *quota_root;
u64 ref_root;
struct btrfs_qgroup *qgroup;
@@ -1363,10 +1360,6 @@ int btrfs_qgroup_account_ref(struct btrfs_trans_handle *trans,
BUG_ON(!fs_info->quota_root);
- ins.objectid = node->bytenr;
- ins.offset = node->num_bytes;
- ins.type = BTRFS_EXTENT_ITEM_KEY;
-
if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
struct btrfs_delayed_tree_ref *ref;
@@ -1840,7 +1833,9 @@ void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
{
if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq)
return;
- pr_err("btrfs: qgroups not uptodate in trans handle %p: list is%s empty, seq is %#x.%x\n",
+ btrfs_err(trans->root->fs_info,
+ "qgroups not uptodate in trans handle %p: list is%s empty, "
+ "seq is %#x.%x",
trans, list_empty(&trans->qgroup_ref_list) ? "" : " not",
(u32)(trans->delayed_ref_elem.seq >> 32),
(u32)trans->delayed_ref_elem.seq);
@@ -1902,9 +1897,17 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
mutex_unlock(&fs_info->qgroup_rescan_lock);
for (; slot < btrfs_header_nritems(scratch_leaf); ++slot) {
+ u64 num_bytes;
+
btrfs_item_key_to_cpu(scratch_leaf, &found, slot);
- if (found.type != BTRFS_EXTENT_ITEM_KEY)
+ if (found.type != BTRFS_EXTENT_ITEM_KEY &&
+ found.type != BTRFS_METADATA_ITEM_KEY)
continue;
+ if (found.type == BTRFS_METADATA_ITEM_KEY)
+ num_bytes = fs_info->extent_root->leafsize;
+ else
+ num_bytes = found.offset;
+
ret = btrfs_find_all_roots(trans, fs_info, found.objectid,
tree_mod_seq_elem.seq, &roots);
if (ret < 0)
@@ -1949,12 +1952,12 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
struct btrfs_qgroup_list *glist;
qg = (struct btrfs_qgroup *)(uintptr_t) unode->aux;
- qg->rfer += found.offset;
- qg->rfer_cmpr += found.offset;
+ qg->rfer += num_bytes;
+ qg->rfer_cmpr += num_bytes;
WARN_ON(qg->tag >= seq);
if (qg->refcnt - seq == roots->nnodes) {
- qg->excl += found.offset;
- qg->excl_cmpr += found.offset;
+ qg->excl += num_bytes;
+ qg->excl_cmpr += num_bytes;
}
qgroup_dirty(fs_info, qg);
@@ -2037,10 +2040,10 @@ out:
mutex_unlock(&fs_info->qgroup_rescan_lock);
if (err >= 0) {
- pr_info("btrfs: qgroup scan completed%s\n",
+ btrfs_info(fs_info, "qgroup scan completed%s",
err == 2 ? " (inconsistency flag cleared)" : "");
} else {
- pr_err("btrfs: qgroup scan failed with %d\n", err);
+ btrfs_err(fs_info, "qgroup scan failed with %d", err);
}
complete_all(&fs_info->qgroup_rescan_completion);
@@ -2096,7 +2099,7 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
if (ret) {
err:
- pr_info("btrfs: qgroup_rescan_init failed with %d\n", ret);
+ btrfs_info(fs_info, "qgroup_rescan_init failed with %d", ret);
return ret;
}
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 24ac21840a9a..9af0b25d991a 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1032,8 +1032,8 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
/* see if we can add this page onto our existing bio */
if (last) {
- last_end = (u64)last->bi_sector << 9;
- last_end += last->bi_size;
+ last_end = (u64)last->bi_iter.bi_sector << 9;
+ last_end += last->bi_iter.bi_size;
/*
* we can't merge these if they are from different
@@ -1053,9 +1053,9 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
if (!bio)
return -ENOMEM;
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
bio->bi_bdev = stripe->dev->bdev;
- bio->bi_sector = disk_start >> 9;
+ bio->bi_iter.bi_sector = disk_start >> 9;
set_bit(BIO_UPTODATE, &bio->bi_flags);
bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
@@ -1111,7 +1111,7 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
spin_lock_irq(&rbio->bio_list_lock);
bio_list_for_each(bio, &rbio->bio_list) {
- start = (u64)bio->bi_sector << 9;
+ start = (u64)bio->bi_iter.bi_sector << 9;
stripe_offset = start - rbio->raid_map[0];
page_index = stripe_offset >> PAGE_CACHE_SHIFT;
@@ -1272,7 +1272,7 @@ cleanup:
static int find_bio_stripe(struct btrfs_raid_bio *rbio,
struct bio *bio)
{
- u64 physical = bio->bi_sector;
+ u64 physical = bio->bi_iter.bi_sector;
u64 stripe_start;
int i;
struct btrfs_bio_stripe *stripe;
@@ -1298,7 +1298,7 @@ static int find_bio_stripe(struct btrfs_raid_bio *rbio,
static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
struct bio *bio)
{
- u64 logical = bio->bi_sector;
+ u64 logical = bio->bi_iter.bi_sector;
u64 stripe_start;
int i;
@@ -1602,8 +1602,8 @@ static int plug_cmp(void *priv, struct list_head *a, struct list_head *b)
plug_list);
struct btrfs_raid_bio *rb = container_of(b, struct btrfs_raid_bio,
plug_list);
- u64 a_sector = ra->bio_list.head->bi_sector;
- u64 b_sector = rb->bio_list.head->bi_sector;
+ u64 a_sector = ra->bio_list.head->bi_iter.bi_sector;
+ u64 b_sector = rb->bio_list.head->bi_iter.bi_sector;
if (a_sector < b_sector)
return -1;
@@ -1691,7 +1691,7 @@ int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
if (IS_ERR(rbio))
return PTR_ERR(rbio);
bio_list_add(&rbio->bio_list, bio);
- rbio->bio_list_bytes = bio->bi_size;
+ rbio->bio_list_bytes = bio->bi_iter.bi_size;
/*
* don't plug on full rbios, just get them out the door
@@ -2044,7 +2044,7 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
rbio->read_rebuild = 1;
bio_list_add(&rbio->bio_list, bio);
- rbio->bio_list_bytes = bio->bi_size;
+ rbio->bio_list_bytes = bio->bi_iter.bi_size;
rbio->faila = find_logical_bio_stripe(rbio, bio);
if (rbio->faila == -1) {
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 1031b69252c5..31c797c48c3e 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -189,8 +189,8 @@ static int __readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
*/
#ifdef DEBUG
if (rec->generation != generation) {
- printk(KERN_DEBUG "generation mismatch for "
- "(%llu,%d,%llu) %llu != %llu\n",
+ btrfs_debug(root->fs_info,
+ "generation mismatch for (%llu,%d,%llu) %llu != %llu",
key.objectid, key.type, key.offset,
rec->generation, generation);
}
@@ -365,8 +365,9 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
goto error;
if (bbio->num_stripes > BTRFS_MAX_MIRRORS) {
- printk(KERN_ERR "btrfs readahead: more than %d copies not "
- "supported", BTRFS_MAX_MIRRORS);
+ btrfs_err(root->fs_info,
+ "readahead: more than %d copies not supported",
+ BTRFS_MAX_MIRRORS);
goto error;
}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 429c73c374b8..07b3b36f40ee 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -94,6 +94,7 @@ struct backref_edge {
#define LOWER 0
#define UPPER 1
+#define RELOCATION_RESERVED_NODES 256
struct backref_cache {
/* red black tree of all backref nodes in the cache */
@@ -176,6 +177,8 @@ struct reloc_control {
u64 merging_rsv_size;
/* size of relocated tree nodes */
u64 nodes_relocated;
+ /* reserved size for block group relocation*/
+ u64 reserved_bytes;
u64 search_start;
u64 extents_found;
@@ -184,7 +187,6 @@ struct reloc_control {
unsigned int create_reloc_tree:1;
unsigned int merge_reloc_tree:1;
unsigned int found_file_extent:1;
- unsigned int commit_transaction:1;
};
/* stages of data relocation */
@@ -2309,9 +2311,6 @@ void free_reloc_roots(struct list_head *list)
reloc_root = list_entry(list->next, struct btrfs_root,
root_list);
__del_reloc_root(reloc_root);
- free_extent_buffer(reloc_root->node);
- free_extent_buffer(reloc_root->commit_root);
- kfree(reloc_root);
}
}
@@ -2353,10 +2352,9 @@ again:
ret = merge_reloc_root(rc, root);
if (ret) {
- __del_reloc_root(reloc_root);
- free_extent_buffer(reloc_root->node);
- free_extent_buffer(reloc_root->commit_root);
- kfree(reloc_root);
+ if (list_empty(&reloc_root->root_list))
+ list_add_tail(&reloc_root->root_list,
+ &reloc_roots);
goto out;
}
} else {
@@ -2452,7 +2450,7 @@ static noinline_for_stack
struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
struct reloc_control *rc,
struct backref_node *node,
- struct backref_edge *edges[], int *nr)
+ struct backref_edge *edges[])
{
struct backref_node *next;
struct btrfs_root *root;
@@ -2494,7 +2492,6 @@ struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
if (!root)
return NULL;
- *nr = index;
next = node;
/* setup backref node path for btrfs_reloc_cow_block */
while (1) {
@@ -2590,28 +2587,36 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
struct btrfs_root *root = rc->extent_root;
u64 num_bytes;
int ret;
+ u64 tmp;
num_bytes = calcu_metadata_size(rc, node, 1) * 2;
trans->block_rsv = rc->block_rsv;
- ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes,
- BTRFS_RESERVE_FLUSH_ALL);
+ rc->reserved_bytes += num_bytes;
+ ret = btrfs_block_rsv_refill(root, rc->block_rsv, num_bytes,
+ BTRFS_RESERVE_FLUSH_ALL);
if (ret) {
- if (ret == -EAGAIN)
- rc->commit_transaction = 1;
+ if (ret == -EAGAIN) {
+ tmp = rc->extent_root->nodesize *
+ RELOCATION_RESERVED_NODES;
+ while (tmp <= rc->reserved_bytes)
+ tmp <<= 1;
+ /*
+ * only one thread can access block_rsv at this point,
+ * so we don't need hold lock to protect block_rsv.
+ * we expand more reservation size here to allow enough
+ * space for relocation and we will return eailer in
+ * enospc case.
+ */
+ rc->block_rsv->size = tmp + rc->extent_root->nodesize *
+ RELOCATION_RESERVED_NODES;
+ }
return ret;
}
return 0;
}
-static void release_metadata_space(struct reloc_control *rc,
- struct backref_node *node)
-{
- u64 num_bytes = calcu_metadata_size(rc, node, 0) * 2;
- btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, num_bytes);
-}
-
/*
* relocate a block tree, and then update pointers in upper level
* blocks that reference the block to point to the new location.
@@ -2633,7 +2638,6 @@ static int do_relocation(struct btrfs_trans_handle *trans,
u32 blocksize;
u64 bytenr;
u64 generation;
- int nr;
int slot;
int ret;
int err = 0;
@@ -2646,7 +2650,7 @@ static int do_relocation(struct btrfs_trans_handle *trans,
cond_resched();
upper = edge->node[UPPER];
- root = select_reloc_root(trans, rc, upper, edges, &nr);
+ root = select_reloc_root(trans, rc, upper, edges);
BUG_ON(!root);
if (upper->eb && !upper->locked) {
@@ -2898,7 +2902,6 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_path *path)
{
struct btrfs_root *root;
- int release = 0;
int ret = 0;
if (!node)
@@ -2915,7 +2918,6 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
ret = reserve_metadata_space(trans, rc, node);
if (ret)
goto out;
- release = 1;
}
if (root) {
@@ -2940,11 +2942,8 @@ static int relocate_tree_block(struct btrfs_trans_handle *trans,
ret = do_relocation(trans, rc, node, key, path, 1);
}
out:
- if (ret || node->level == 0 || node->cowonly) {
- if (release)
- release_metadata_space(rc, node);
+ if (ret || node->level == 0 || node->cowonly)
remove_backref_node(&rc->backref_cache, node);
- }
return ret;
}
@@ -3867,29 +3866,20 @@ static noinline_for_stack
int prepare_to_relocate(struct reloc_control *rc)
{
struct btrfs_trans_handle *trans;
- int ret;
rc->block_rsv = btrfs_alloc_block_rsv(rc->extent_root,
BTRFS_BLOCK_RSV_TEMP);
if (!rc->block_rsv)
return -ENOMEM;
- /*
- * reserve some space for creating reloc trees.
- * btrfs_init_reloc_root will use them when there
- * is no reservation in transaction handle.
- */
- ret = btrfs_block_rsv_add(rc->extent_root, rc->block_rsv,
- rc->extent_root->nodesize * 256,
- BTRFS_RESERVE_FLUSH_ALL);
- if (ret)
- return ret;
-
memset(&rc->cluster, 0, sizeof(rc->cluster));
rc->search_start = rc->block_group->key.objectid;
rc->extents_found = 0;
rc->nodes_relocated = 0;
rc->merging_rsv_size = 0;
+ rc->reserved_bytes = 0;
+ rc->block_rsv->size = rc->extent_root->nodesize *
+ RELOCATION_RESERVED_NODES;
rc->create_reloc_tree = 1;
set_reloc_control(rc);
@@ -3933,6 +3923,14 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
}
while (1) {
+ rc->reserved_bytes = 0;
+ ret = btrfs_block_rsv_refill(rc->extent_root,
+ rc->block_rsv, rc->block_rsv->size,
+ BTRFS_RESERVE_FLUSH_ALL);
+ if (ret) {
+ err = ret;
+ break;
+ }
progress++;
trans = btrfs_start_transaction(rc->extent_root, 0);
if (IS_ERR(trans)) {
@@ -4011,6 +4009,12 @@ restart:
if (!RB_EMPTY_ROOT(&blocks)) {
ret = relocate_tree_blocks(trans, rc, &blocks);
if (ret < 0) {
+ /*
+ * if we fail to relocate tree blocks, force to update
+ * backref cache when committing transaction.
+ */
+ rc->backref_cache.last_trans = trans->transid - 1;
+
if (ret != -EAGAIN) {
err = ret;
break;
@@ -4020,14 +4024,8 @@ restart:
}
}
- if (rc->commit_transaction) {
- rc->commit_transaction = 0;
- ret = btrfs_commit_transaction(trans, rc->extent_root);
- BUG_ON(ret);
- } else {
- btrfs_end_transaction_throttle(trans, rc->extent_root);
- btrfs_btree_balance_dirty(rc->extent_root);
- }
+ btrfs_end_transaction_throttle(trans, rc->extent_root);
+ btrfs_btree_balance_dirty(rc->extent_root);
trans = NULL;
if (rc->stage == MOVE_DATA_EXTENTS &&
@@ -4247,7 +4245,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
goto out;
}
- printk(KERN_INFO "btrfs: relocating block group %llu flags %llu\n",
+ btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
rc->block_group->key.objectid, rc->block_group->flags);
ret = btrfs_start_delalloc_roots(fs_info, 0);
@@ -4269,7 +4267,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
if (rc->extents_found == 0)
break;
- printk(KERN_INFO "btrfs: found %llu extents\n",
+ btrfs_info(extent_root->fs_info, "found %llu extents",
rc->extents_found);
if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) {
@@ -4285,11 +4283,6 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
}
}
- filemap_write_and_wait_range(fs_info->btree_inode->i_mapping,
- rc->block_group->key.objectid,
- rc->block_group->key.objectid +
- rc->block_group->key.offset - 1);
-
WARN_ON(rc->block_group->pinned > 0);
WARN_ON(rc->block_group->reserved > 0);
WARN_ON(btrfs_block_group_used(&rc->block_group->item) > 0);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index ec71ea44d2b4..1389b69059de 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -44,7 +44,7 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
if (!need_reset && btrfs_root_generation(item)
!= btrfs_root_generation_v2(item)) {
if (btrfs_root_generation_v2(item) != 0) {
- printk(KERN_WARNING "btrfs: mismatching "
+ printk(KERN_WARNING "BTRFS: mismatching "
"generation and generation_v2 "
"found in root item. This root "
"was probably mounted with an "
@@ -154,7 +154,7 @@ int btrfs_update_root(struct btrfs_trans_handle *trans, struct btrfs_root
if (ret != 0) {
btrfs_print_leaf(root, path->nodes[0]);
- printk(KERN_CRIT "unable to update root key %llu %u %llu\n",
+ btrfs_crit(root->fs_info, "unable to update root key %llu %u %llu",
key->objectid, key->type, key->offset);
BUG_ON(1);
}
@@ -400,21 +400,6 @@ out:
return err;
}
-int btrfs_find_root_ref(struct btrfs_root *tree_root,
- struct btrfs_path *path,
- u64 root_id, u64 ref_id)
-{
- struct btrfs_key key;
- int ret;
-
- key.objectid = root_id;
- key.type = BTRFS_ROOT_REF_KEY;
- key.offset = ref_id;
-
- ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
- return ret;
-}
-
/*
* add a btrfs_root_ref item. type is either BTRFS_ROOT_REF_KEY
* or BTRFS_ROOT_BACKREF_KEY.
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 1fd3f33c330a..efba5d1282ee 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
int mirror_num, u64 physical_for_dev_replace);
static void copy_nocow_pages_worker(struct btrfs_work *work);
+static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
+static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
@@ -269,6 +271,29 @@ static void scrub_pending_bio_dec(struct scrub_ctx *sctx)
wake_up(&sctx->list_wait);
}
+static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
+{
+ while (atomic_read(&fs_info->scrub_pause_req)) {
+ mutex_unlock(&fs_info->scrub_lock);
+ wait_event(fs_info->scrub_pause_wait,
+ atomic_read(&fs_info->scrub_pause_req) == 0);
+ mutex_lock(&fs_info->scrub_lock);
+ }
+}
+
+static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
+{
+ atomic_inc(&fs_info->scrubs_paused);
+ wake_up(&fs_info->scrub_pause_wait);
+
+ mutex_lock(&fs_info->scrub_lock);
+ __scrub_blocked_if_needed(fs_info);
+ atomic_dec(&fs_info->scrubs_paused);
+ mutex_unlock(&fs_info->scrub_lock);
+
+ wake_up(&fs_info->scrub_pause_wait);
+}
+
/*
* used for workers that require transaction commits (i.e., for the
* NOCOW case)
@@ -480,7 +505,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
* hold all of the paths here
*/
for (i = 0; i < ipath->fspath->elem_cnt; ++i)
- printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev "
+ printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev "
"%s, sector %llu, root %llu, inode %llu, offset %llu, "
"length %llu, links %u (path: %s)\n", swarn->errstr,
swarn->logical, rcu_str_deref(swarn->dev->name),
@@ -492,7 +517,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
return 0;
err:
- printk_in_rcu(KERN_WARNING "btrfs: %s at logical %llu on dev "
+ printk_in_rcu(KERN_WARNING "BTRFS: %s at logical %llu on dev "
"%s, sector %llu, root %llu, inode %llu, offset %llu: path "
"resolving failed with ret=%d\n", swarn->errstr,
swarn->logical, rcu_str_deref(swarn->dev->name),
@@ -555,7 +580,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_block *sblock)
ret = tree_backref_for_extent(&ptr, eb, ei, item_size,
&ref_root, &ref_level);
printk_in_rcu(KERN_WARNING
- "btrfs: %s at logical %llu on dev %s, "
+ "BTRFS: %s at logical %llu on dev %s, "
"sector %llu: metadata %s (level %d) in tree "
"%llu\n", errstr, swarn.logical,
rcu_str_deref(dev->name),
@@ -704,13 +729,11 @@ static void scrub_fixup_nodatasum(struct btrfs_work *work)
struct scrub_fixup_nodatasum *fixup;
struct scrub_ctx *sctx;
struct btrfs_trans_handle *trans = NULL;
- struct btrfs_fs_info *fs_info;
struct btrfs_path *path;
int uncorrectable = 0;
fixup = container_of(work, struct scrub_fixup_nodatasum, work);
sctx = fixup->sctx;
- fs_info = fixup->root->fs_info;
path = btrfs_alloc_path();
if (!path) {
@@ -759,8 +782,8 @@ out:
btrfs_dev_replace_stats_inc(
&sctx->dev_root->fs_info->dev_replace.
num_uncorrectable_read_errors);
- printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: unable to fixup (nodatasum) error at logical %llu on dev %s\n",
+ printk_ratelimited_in_rcu(KERN_ERR "BTRFS: "
+ "unable to fixup (nodatasum) error at logical %llu on dev %s\n",
fixup->logical, rcu_str_deref(fixup->dev->name));
}
@@ -1161,7 +1184,7 @@ corrected_error:
sctx->stat.corrected_errors++;
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: fixed up error at logical %llu on dev %s\n",
+ "BTRFS: fixed up error at logical %llu on dev %s\n",
logical, rcu_str_deref(dev->name));
}
} else {
@@ -1170,7 +1193,7 @@ did_not_correct_error:
sctx->stat.uncorrectable_errors++;
spin_unlock(&sctx->stat_lock);
printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: unable to fixup (regular) error at logical %llu on dev %s\n",
+ "BTRFS: unable to fixup (regular) error at logical %llu on dev %s\n",
logical, rcu_str_deref(dev->name));
}
@@ -1308,7 +1331,7 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
continue;
}
bio->bi_bdev = page->dev->bdev;
- bio->bi_sector = page->physical >> 9;
+ bio->bi_iter.bi_sector = page->physical >> 9;
bio_add_page(bio, page->page, PAGE_SIZE, 0);
if (btrfsic_submit_bio_wait(READ, bio))
@@ -1418,8 +1441,9 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
int ret;
if (!page_bad->dev->bdev) {
- printk_ratelimited(KERN_WARNING
- "btrfs: scrub_repair_page_from_good_copy(bdev == NULL) is unexpected!\n");
+ printk_ratelimited(KERN_WARNING "BTRFS: "
+ "scrub_repair_page_from_good_copy(bdev == NULL) "
+ "is unexpected!\n");
return -EIO;
}
@@ -1427,7 +1451,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
if (!bio)
return -EIO;
bio->bi_bdev = page_bad->dev->bdev;
- bio->bi_sector = page_bad->physical >> 9;
+ bio->bi_iter.bi_sector = page_bad->physical >> 9;
ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
if (PAGE_SIZE != ret) {
@@ -1520,7 +1544,7 @@ again:
bio->bi_private = sbio;
bio->bi_end_io = scrub_wr_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical_for_dev_replace ||
@@ -1877,7 +1901,7 @@ static void scrub_submit(struct scrub_ctx *sctx)
* This case is handled correctly (but _very_ slowly).
*/
printk_ratelimited(KERN_WARNING
- "btrfs: scrub_submit(bio bdev == NULL) is unexpected!\n");
+ "BTRFS: scrub_submit(bio bdev == NULL) is unexpected!\n");
bio_endio(sbio->bio, -EIO);
} else {
btrfsic_submit_bio(READ, sbio->bio);
@@ -1926,7 +1950,7 @@ again:
bio->bi_private = sbio;
bio->bi_end_io = scrub_bio_end_io;
bio->bi_bdev = sbio->dev->bdev;
- bio->bi_sector = sbio->physical >> 9;
+ bio->bi_iter.bi_sector = sbio->physical >> 9;
sbio->err = 0;
} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
spage->physical ||
@@ -2286,8 +2310,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
/* FIXME it might be better to start readahead at commit root */
key_start.objectid = logical;
@@ -2311,16 +2334,6 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
if (!IS_ERR(reada2))
btrfs_reada_wait(reada2);
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
/*
* collect all data csums for the stripe to avoid seeking during
@@ -2357,22 +2370,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
}
+ if (btrfs_fs_incompat(fs_info, SKINNY_METADATA))
+ key.type = BTRFS_METADATA_ITEM_KEY;
+ else
+ key.type = BTRFS_EXTENT_ITEM_KEY;
key.objectid = logical;
- key.type = BTRFS_EXTENT_ITEM_KEY;
key.offset = (u64)-1;
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -2380,8 +2385,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
goto out;
if (ret > 0) {
- ret = btrfs_previous_item(root, path, 0,
- BTRFS_EXTENT_ITEM_KEY);
+ ret = btrfs_previous_extent_item(root, path, 0);
if (ret < 0)
goto out;
if (ret > 0) {
@@ -2439,9 +2443,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
if (key.objectid < logical &&
(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)) {
- printk(KERN_ERR
- "btrfs scrub: tree block %llu spanning "
- "stripes, ignored. logical=%llu\n",
+ btrfs_err(fs_info,
+ "scrub: tree block %llu spanning "
+ "stripes, ignored. logical=%llu",
key.objectid, logical);
goto next;
}
@@ -2683,21 +2687,9 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
wait_event(sctx->list_wait,
atomic_read(&sctx->bios_in_flight) == 0);
atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
- atomic_inc(&fs_info->scrubs_paused);
- wake_up(&fs_info->scrub_pause_wait);
wait_event(sctx->list_wait,
atomic_read(&sctx->workers_pending) == 0);
-
- mutex_lock(&fs_info->scrub_lock);
- while (atomic_read(&fs_info->scrub_pause_req)) {
- mutex_unlock(&fs_info->scrub_lock);
- wait_event(fs_info->scrub_pause_wait,
- atomic_read(&fs_info->scrub_pause_req) == 0);
- mutex_lock(&fs_info->scrub_lock);
- }
- atomic_dec(&fs_info->scrubs_paused);
- mutex_unlock(&fs_info->scrub_lock);
- wake_up(&fs_info->scrub_pause_wait);
+ scrub_blocked_if_needed(fs_info);
btrfs_put_block_group(cache);
if (ret)
@@ -2823,8 +2815,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
* check some assumptions
*/
if (fs_info->chunk_root->nodesize != fs_info->chunk_root->leafsize) {
- printk(KERN_ERR
- "btrfs_scrub: size assumption nodesize == leafsize (%d == %d) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption nodesize == leafsize (%d == %d) fails",
fs_info->chunk_root->nodesize,
fs_info->chunk_root->leafsize);
return -EINVAL;
@@ -2836,16 +2828,17 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
* the way scrub is implemented. Do not handle this
* situation at all because it won't ever happen.
*/
- printk(KERN_ERR
- "btrfs_scrub: size assumption nodesize <= BTRFS_STRIPE_LEN (%d <= %d) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption nodesize <= BTRFS_STRIPE_LEN (%d <= %d) fails",
fs_info->chunk_root->nodesize, BTRFS_STRIPE_LEN);
return -EINVAL;
}
if (fs_info->chunk_root->sectorsize != PAGE_SIZE) {
/* not supported for data w/o checksums */
- printk(KERN_ERR
- "btrfs_scrub: size assumption sectorsize != PAGE_SIZE (%d != %lu) fails\n",
+ btrfs_err(fs_info,
+ "scrub: size assumption sectorsize != PAGE_SIZE "
+ "(%d != %lu) fails",
fs_info->chunk_root->sectorsize, PAGE_SIZE);
return -EINVAL;
}
@@ -2858,7 +2851,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
* would exhaust the array bounds of pagev member in
* struct scrub_block
*/
- pr_err("btrfs_scrub: size assumption nodesize and sectorsize <= SCRUB_MAX_PAGES_PER_BLOCK (%d <= %d && %d <= %d) fails\n",
+ btrfs_err(fs_info, "scrub: size assumption nodesize and sectorsize "
+ "<= SCRUB_MAX_PAGES_PER_BLOCK (%d <= %d && %d <= %d) fails",
fs_info->chunk_root->nodesize,
SCRUB_MAX_PAGES_PER_BLOCK,
fs_info->chunk_root->sectorsize,
@@ -2908,7 +2902,13 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
}
sctx->readonly = readonly;
dev->scrub_device = sctx;
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ /*
+ * checking @scrub_pause_req here, we can avoid
+ * race between committing transaction and scrubbing.
+ */
+ __scrub_blocked_if_needed(fs_info);
atomic_inc(&fs_info->scrubs_running);
mutex_unlock(&fs_info->scrub_lock);
@@ -2917,9 +2917,10 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
* by holding device list mutex, we can
* kick off writing super in log tree sync.
*/
+ mutex_lock(&fs_info->fs_devices->device_list_mutex);
ret = scrub_supers(sctx, dev);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
}
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
if (!ret)
ret = scrub_enumerate_chunks(sctx, dev, start, end,
@@ -3167,7 +3168,8 @@ static void copy_nocow_pages_worker(struct btrfs_work *work)
ret = iterate_inodes_from_logical(logical, fs_info, path,
record_inode_for_nocow, nocow_ctx);
if (ret != 0 && ret != -ENOENT) {
- pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n",
+ btrfs_warn(fs_info, "iterate_inodes_from_logical() failed: log %llu, "
+ "phys %llu, len %llu, mir %u, ret %d",
logical, physical_for_dev_replace, len, mirror_num,
ret);
not_written = 1;
@@ -3289,7 +3291,7 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
again:
page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
if (!page) {
- pr_err("find_or_create_page() failed\n");
+ btrfs_err(fs_info, "find_or_create_page() failed");
ret = -ENOMEM;
goto out;
}
@@ -3361,7 +3363,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
return -EIO;
if (!dev->bdev) {
printk_ratelimited(KERN_WARNING
- "btrfs: scrub write_page_nocow(bdev == NULL) is unexpected!\n");
+ "BTRFS: scrub write_page_nocow(bdev == NULL) is unexpected!\n");
return -EIO;
}
bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
@@ -3371,8 +3373,8 @@ static int write_page_nocow(struct scrub_ctx *sctx,
spin_unlock(&sctx->stat_lock);
return -ENOMEM;
}
- bio->bi_size = 0;
- bio->bi_sector = physical_for_dev_replace >> 9;
+ bio->bi_iter.bi_size = 0;
+ bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
bio->bi_bdev = dev->bdev;
ret = bio_add_page(bio, page, PAGE_CACHE_SIZE, 0);
if (ret != PAGE_CACHE_SIZE) {
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 945d1db98f26..9dde9717c1b9 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -24,12 +24,12 @@
#include <linux/xattr.h>
#include <linux/posix_acl_xattr.h>
#include <linux/radix-tree.h>
-#include <linux/crc32c.h>
#include <linux/vmalloc.h>
#include <linux/string.h>
#include "send.h"
#include "backref.h"
+#include "hash.h"
#include "locking.h"
#include "disk-io.h"
#include "btrfs_inode.h"
@@ -88,8 +88,6 @@ struct send_ctx {
u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];
u64 flags; /* 'flags' member of btrfs_ioctl_send_args is u64 */
- struct vfsmount *mnt;
-
struct btrfs_root *send_root;
struct btrfs_root *parent_root;
struct clone_root *clone_roots;
@@ -111,6 +109,7 @@ struct send_ctx {
int cur_inode_deleted;
u64 cur_inode_size;
u64 cur_inode_mode;
+ u64 cur_inode_last_extent;
u64 send_progress;
@@ -122,6 +121,74 @@ struct send_ctx {
int name_cache_size;
char *read_buf;
+
+ /*
+ * We process inodes by their increasing order, so if before an
+ * incremental send we reverse the parent/child relationship of
+ * directories such that a directory with a lower inode number was
+ * the parent of a directory with a higher inode number, and the one
+ * becoming the new parent got renamed too, we can't rename/move the
+ * directory with lower inode number when we finish processing it - we
+ * must process the directory with higher inode number first, then
+ * rename/move it and then rename/move the directory with lower inode
+ * number. Example follows.
+ *
+ * Tree state when the first send was performed:
+ *
+ * .
+ * |-- a (ino 257)
+ * |-- b (ino 258)
+ * |
+ * |
+ * |-- c (ino 259)
+ * | |-- d (ino 260)
+ * |
+ * |-- c2 (ino 261)
+ *
+ * Tree state when the second (incremental) send is performed:
+ *
+ * .
+ * |-- a (ino 257)
+ * |-- b (ino 258)
+ * |-- c2 (ino 261)
+ * |-- d2 (ino 260)
+ * |-- cc (ino 259)
+ *
+ * The sequence of steps that lead to the second state was:
+ *
+ * mv /a/b/c/d /a/b/c2/d2
+ * mv /a/b/c /a/b/c2/d2/cc
+ *
+ * "c" has lower inode number, but we can't move it (2nd mv operation)
+ * before we move "d", which has higher inode number.
+ *
+ * So we just memorize which move/rename operations must be performed
+ * later when their respective parent is processed and moved/renamed.
+ */
+
+ /* Indexed by parent directory inode number. */
+ struct rb_root pending_dir_moves;
+
+ /*
+ * Reverse index, indexed by the inode number of a directory that
+ * is waiting for the move/rename of its immediate parent before its
+ * own move/rename can be performed.
+ */
+ struct rb_root waiting_dir_moves;
+};
+
+struct pending_dir_move {
+ struct rb_node node;
+ struct list_head list;
+ u64 parent_ino;
+ u64 ino;
+ u64 gen;
+ struct list_head update_refs;
+};
+
+struct waiting_dir_move {
+ struct rb_node node;
+ u64 ino;
};
struct name_cache_entry {
@@ -145,6 +212,15 @@ struct name_cache_entry {
char name[];
};
+static int is_waiting_for_move(struct send_ctx *sctx, u64 ino);
+
+static int need_send_hole(struct send_ctx *sctx)
+{
+ return (sctx->parent_root && !sctx->cur_inode_new &&
+ !sctx->cur_inode_new_gen && !sctx->cur_inode_deleted &&
+ S_ISREG(sctx->cur_inode_mode));
+}
+
static void fs_path_reset(struct fs_path *p)
{
if (p->reversed) {
@@ -336,16 +412,6 @@ out:
return ret;
}
-#if 0
-static void fs_path_remove(struct fs_path *p)
-{
- BUG_ON(p->reversed);
- while (p->start != p->end && *p->end != '/')
- p->end--;
- *p->end = 0;
-}
-#endif
-
static int fs_path_copy(struct fs_path *p, struct fs_path *from)
{
int ret;
@@ -436,30 +502,15 @@ static int tlv_put(struct send_ctx *sctx, u16 attr, const void *data, int len)
return 0;
}
-#if 0
-static int tlv_put_u8(struct send_ctx *sctx, u16 attr, u8 value)
-{
- return tlv_put(sctx, attr, &value, sizeof(value));
-}
-
-static int tlv_put_u16(struct send_ctx *sctx, u16 attr, u16 value)
-{
- __le16 tmp = cpu_to_le16(value);
- return tlv_put(sctx, attr, &tmp, sizeof(tmp));
-}
-
-static int tlv_put_u32(struct send_ctx *sctx, u16 attr, u32 value)
-{
- __le32 tmp = cpu_to_le32(value);
- return tlv_put(sctx, attr, &tmp, sizeof(tmp));
-}
-#endif
+#define TLV_PUT_DEFINE_INT(bits) \
+ static int tlv_put_u##bits(struct send_ctx *sctx, \
+ u##bits attr, u##bits value) \
+ { \
+ __le##bits __tmp = cpu_to_le##bits(value); \
+ return tlv_put(sctx, attr, &__tmp, sizeof(__tmp)); \
+ }
-static int tlv_put_u64(struct send_ctx *sctx, u16 attr, u64 value)
-{
- __le64 tmp = cpu_to_le64(value);
- return tlv_put(sctx, attr, &tmp, sizeof(tmp));
-}
+TLV_PUT_DEFINE_INT(64)
static int tlv_put_string(struct send_ctx *sctx, u16 attr,
const char *str, int len)
@@ -475,17 +526,6 @@ static int tlv_put_uuid(struct send_ctx *sctx, u16 attr,
return tlv_put(sctx, attr, uuid, BTRFS_UUID_SIZE);
}
-#if 0
-static int tlv_put_timespec(struct send_ctx *sctx, u16 attr,
- struct timespec *ts)
-{
- struct btrfs_timespec bts;
- bts.sec = cpu_to_le64(ts->tv_sec);
- bts.nsec = cpu_to_le32(ts->tv_nsec);
- return tlv_put(sctx, attr, &bts, sizeof(bts));
-}
-#endif
-
static int tlv_put_btrfs_timespec(struct send_ctx *sctx, u16 attr,
struct extent_buffer *eb,
struct btrfs_timespec *ts)
@@ -533,12 +573,6 @@ static int tlv_put_btrfs_timespec(struct send_ctx *sctx, u16 attr,
if (ret < 0) \
goto tlv_put_failure; \
} while (0)
-#define TLV_PUT_TIMESPEC(sctx, attrtype, ts) \
- do { \
- ret = tlv_put_timespec(sctx, attrtype, ts); \
- if (ret < 0) \
- goto tlv_put_failure; \
- } while (0)
#define TLV_PUT_BTRFS_TIMESPEC(sctx, attrtype, eb, ts) \
do { \
ret = tlv_put_btrfs_timespec(sctx, attrtype, eb, ts); \
@@ -586,7 +620,7 @@ static int send_cmd(struct send_ctx *sctx)
hdr->len = cpu_to_le32(sctx->send_size - sizeof(*hdr));
hdr->crc = 0;
- crc = crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
+ crc = btrfs_crc32c(0, (unsigned char *)sctx->send_buf, sctx->send_size);
hdr->crc = cpu_to_le32(crc);
ret = write_buf(sctx->send_filp, sctx->send_buf, sctx->send_size,
@@ -1270,7 +1304,7 @@ static int find_extent_clone(struct send_ctx *sctx,
if (!backref_ctx->found_itself) {
/* found a bug in backref code? */
ret = -EIO;
- printk(KERN_ERR "btrfs: ERROR did not find backref in "
+ btrfs_err(sctx->send_root->fs_info, "did not find backref in "
"send_root. inode=%llu, offset=%llu, "
"disk_byte=%llu found extent=%llu\n",
ino, data_offset, disk_byte, found_key.objectid);
@@ -1298,6 +1332,16 @@ verbose_printk(KERN_DEBUG "btrfs: find_extent_clone: data_offset=%llu, "
}
if (cur_clone_root) {
+ if (compressed != BTRFS_COMPRESS_NONE) {
+ /*
+ * Offsets given by iterate_extent_inodes() are relative
+ * to the start of the extent, we need to add logical
+ * offset from the file extent item.
+ * (See why at backref.c:check_extent_in_eb())
+ */
+ cur_clone_root->offset += btrfs_file_extent_offset(eb,
+ fi);
+ }
*found = cur_clone_root;
ret = 0;
} else {
@@ -1343,7 +1387,7 @@ static int read_symlink(struct btrfs_root *root,
BUG_ON(compression);
off = btrfs_file_extent_inline_start(ei);
- len = btrfs_file_extent_inline_len(path->nodes[0], ei);
+ len = btrfs_file_extent_inline_len(path->nodes[0], path->slots[0], ei);
ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len);
@@ -1372,7 +1416,7 @@ static int gen_unique_name(struct send_ctx *sctx,
return -ENOMEM;
while (1) {
- len = snprintf(tmp, sizeof(tmp) - 1, "o%llu-%llu-%llu",
+ len = snprintf(tmp, sizeof(tmp), "o%llu-%llu-%llu",
ino, gen, idx);
if (len >= sizeof(tmp)) {
/* should really not happen */
@@ -1933,6 +1977,7 @@ static void name_cache_free(struct send_ctx *sctx)
*/
static int __get_cur_name_and_parent(struct send_ctx *sctx,
u64 ino, u64 gen,
+ int skip_name_cache,
u64 *parent_ino,
u64 *parent_gen,
struct fs_path *dest)
@@ -1942,6 +1987,8 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
struct btrfs_path *path = NULL;
struct name_cache_entry *nce = NULL;
+ if (skip_name_cache)
+ goto get_ref;
/*
* First check if we already did a call to this function with the same
* ino/gen. If yes, check if the cache entry is still up-to-date. If yes
@@ -1986,11 +2033,12 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
goto out_cache;
}
+get_ref:
/*
* Depending on whether the inode was already processed or not, use
* send_root or parent_root for ref lookup.
*/
- if (ino < sctx->send_progress)
+ if (ino < sctx->send_progress && !skip_name_cache)
ret = get_first_ref(sctx->send_root, ino,
parent_ino, parent_gen, dest);
else
@@ -2014,6 +2062,8 @@ static int __get_cur_name_and_parent(struct send_ctx *sctx,
goto out;
ret = 1;
}
+ if (skip_name_cache)
+ goto out;
out_cache:
/*
@@ -2081,6 +2131,9 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
u64 parent_inode = 0;
u64 parent_gen = 0;
int stop = 0;
+ u64 start_ino = ino;
+ u64 start_gen = gen;
+ int skip_name_cache = 0;
name = fs_path_alloc();
if (!name) {
@@ -2088,19 +2141,32 @@ static int get_cur_path(struct send_ctx *sctx, u64 ino, u64 gen,
goto out;
}
+ if (is_waiting_for_move(sctx, ino))
+ skip_name_cache = 1;
+
+again:
dest->reversed = 1;
fs_path_reset(dest);
while (!stop && ino != BTRFS_FIRST_FREE_OBJECTID) {
fs_path_reset(name);
- ret = __get_cur_name_and_parent(sctx, ino, gen,
+ ret = __get_cur_name_and_parent(sctx, ino, gen, skip_name_cache,
&parent_inode, &parent_gen, name);
if (ret < 0)
goto out;
if (ret)
stop = 1;
+ if (!skip_name_cache &&
+ is_waiting_for_move(sctx, parent_inode)) {
+ ino = start_ino;
+ gen = start_gen;
+ stop = 0;
+ skip_name_cache = 1;
+ goto again;
+ }
+
ret = fs_path_add_path(dest, name);
if (ret < 0)
goto out;
@@ -2131,7 +2197,7 @@ static int send_subvol_begin(struct send_ctx *sctx)
char *name = NULL;
int namelen;
- path = alloc_path_for_send();
+ path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -2180,12 +2246,12 @@ static int send_subvol_begin(struct send_ctx *sctx)
TLV_PUT_UUID(sctx, BTRFS_SEND_A_UUID,
sctx->send_root->root_item.uuid);
TLV_PUT_U64(sctx, BTRFS_SEND_A_CTRANSID,
- sctx->send_root->root_item.ctransid);
+ le64_to_cpu(sctx->send_root->root_item.ctransid));
if (parent_root) {
TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
sctx->parent_root->root_item.uuid);
TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
- sctx->parent_root->root_item.ctransid);
+ le64_to_cpu(sctx->parent_root->root_item.ctransid));
}
ret = send_cmd(sctx);
@@ -2672,10 +2738,347 @@ out:
return ret;
}
+static int is_waiting_for_move(struct send_ctx *sctx, u64 ino)
+{
+ struct rb_node *n = sctx->waiting_dir_moves.rb_node;
+ struct waiting_dir_move *entry;
+
+ while (n) {
+ entry = rb_entry(n, struct waiting_dir_move, node);
+ if (ino < entry->ino)
+ n = n->rb_left;
+ else if (ino > entry->ino)
+ n = n->rb_right;
+ else
+ return 1;
+ }
+ return 0;
+}
+
+static int add_waiting_dir_move(struct send_ctx *sctx, u64 ino)
+{
+ struct rb_node **p = &sctx->waiting_dir_moves.rb_node;
+ struct rb_node *parent = NULL;
+ struct waiting_dir_move *entry, *dm;
+
+ dm = kmalloc(sizeof(*dm), GFP_NOFS);
+ if (!dm)
+ return -ENOMEM;
+ dm->ino = ino;
+
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct waiting_dir_move, node);
+ if (ino < entry->ino) {
+ p = &(*p)->rb_left;
+ } else if (ino > entry->ino) {
+ p = &(*p)->rb_right;
+ } else {
+ kfree(dm);
+ return -EEXIST;
+ }
+ }
+
+ rb_link_node(&dm->node, parent, p);
+ rb_insert_color(&dm->node, &sctx->waiting_dir_moves);
+ return 0;
+}
+
+static int del_waiting_dir_move(struct send_ctx *sctx, u64 ino)
+{
+ struct rb_node *n = sctx->waiting_dir_moves.rb_node;
+ struct waiting_dir_move *entry;
+
+ while (n) {
+ entry = rb_entry(n, struct waiting_dir_move, node);
+ if (ino < entry->ino) {
+ n = n->rb_left;
+ } else if (ino > entry->ino) {
+ n = n->rb_right;
+ } else {
+ rb_erase(&entry->node, &sctx->waiting_dir_moves);
+ kfree(entry);
+ return 0;
+ }
+ }
+ return -ENOENT;
+}
+
+static int add_pending_dir_move(struct send_ctx *sctx, u64 parent_ino)
+{
+ struct rb_node **p = &sctx->pending_dir_moves.rb_node;
+ struct rb_node *parent = NULL;
+ struct pending_dir_move *entry, *pm;
+ struct recorded_ref *cur;
+ int exists = 0;
+ int ret;
+
+ pm = kmalloc(sizeof(*pm), GFP_NOFS);
+ if (!pm)
+ return -ENOMEM;
+ pm->parent_ino = parent_ino;
+ pm->ino = sctx->cur_ino;
+ pm->gen = sctx->cur_inode_gen;
+ INIT_LIST_HEAD(&pm->list);
+ INIT_LIST_HEAD(&pm->update_refs);
+ RB_CLEAR_NODE(&pm->node);
+
+ while (*p) {
+ parent = *p;
+ entry = rb_entry(parent, struct pending_dir_move, node);
+ if (parent_ino < entry->parent_ino) {
+ p = &(*p)->rb_left;
+ } else if (parent_ino > entry->parent_ino) {
+ p = &(*p)->rb_right;
+ } else {
+ exists = 1;
+ break;
+ }
+ }
+
+ list_for_each_entry(cur, &sctx->deleted_refs, list) {
+ ret = dup_ref(cur, &pm->update_refs);
+ if (ret < 0)
+ goto out;
+ }
+ list_for_each_entry(cur, &sctx->new_refs, list) {
+ ret = dup_ref(cur, &pm->update_refs);
+ if (ret < 0)
+ goto out;
+ }
+
+ ret = add_waiting_dir_move(sctx, pm->ino);
+ if (ret)
+ goto out;
+
+ if (exists) {
+ list_add_tail(&pm->list, &entry->list);
+ } else {
+ rb_link_node(&pm->node, parent, p);
+ rb_insert_color(&pm->node, &sctx->pending_dir_moves);
+ }
+ ret = 0;
+out:
+ if (ret) {
+ __free_recorded_refs(&pm->update_refs);
+ kfree(pm);
+ }
+ return ret;
+}
+
+static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx,
+ u64 parent_ino)
+{
+ struct rb_node *n = sctx->pending_dir_moves.rb_node;
+ struct pending_dir_move *entry;
+
+ while (n) {
+ entry = rb_entry(n, struct pending_dir_move, node);
+ if (parent_ino < entry->parent_ino)
+ n = n->rb_left;
+ else if (parent_ino > entry->parent_ino)
+ n = n->rb_right;
+ else
+ return entry;
+ }
+ return NULL;
+}
+
+static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm)
+{
+ struct fs_path *from_path = NULL;
+ struct fs_path *to_path = NULL;
+ u64 orig_progress = sctx->send_progress;
+ struct recorded_ref *cur;
+ int ret;
+
+ from_path = fs_path_alloc();
+ if (!from_path)
+ return -ENOMEM;
+
+ sctx->send_progress = pm->ino;
+ ret = get_cur_path(sctx, pm->ino, pm->gen, from_path);
+ if (ret < 0)
+ goto out;
+
+ to_path = fs_path_alloc();
+ if (!to_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ sctx->send_progress = sctx->cur_ino + 1;
+ ret = del_waiting_dir_move(sctx, pm->ino);
+ ASSERT(ret == 0);
+
+ ret = get_cur_path(sctx, pm->ino, pm->gen, to_path);
+ if (ret < 0)
+ goto out;
+
+ ret = send_rename(sctx, from_path, to_path);
+ if (ret < 0)
+ goto out;
+
+ ret = send_utimes(sctx, pm->ino, pm->gen);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * After rename/move, need to update the utimes of both new parent(s)
+ * and old parent(s).
+ */
+ list_for_each_entry(cur, &pm->update_refs, list) {
+ ret = send_utimes(sctx, cur->dir, cur->dir_gen);
+ if (ret < 0)
+ goto out;
+ }
+
+out:
+ fs_path_free(from_path);
+ fs_path_free(to_path);
+ sctx->send_progress = orig_progress;
+
+ return ret;
+}
+
+static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m)
+{
+ if (!list_empty(&m->list))
+ list_del(&m->list);
+ if (!RB_EMPTY_NODE(&m->node))
+ rb_erase(&m->node, &sctx->pending_dir_moves);
+ __free_recorded_refs(&m->update_refs);
+ kfree(m);
+}
+
+static void tail_append_pending_moves(struct pending_dir_move *moves,
+ struct list_head *stack)
+{
+ if (list_empty(&moves->list)) {
+ list_add_tail(&moves->list, stack);
+ } else {
+ LIST_HEAD(list);
+ list_splice_init(&moves->list, &list);
+ list_add_tail(&moves->list, stack);
+ list_splice_tail(&list, stack);
+ }
+}
+
+static int apply_children_dir_moves(struct send_ctx *sctx)
+{
+ struct pending_dir_move *pm;
+ struct list_head stack;
+ u64 parent_ino = sctx->cur_ino;
+ int ret = 0;
+
+ pm = get_pending_dir_moves(sctx, parent_ino);
+ if (!pm)
+ return 0;
+
+ INIT_LIST_HEAD(&stack);
+ tail_append_pending_moves(pm, &stack);
+
+ while (!list_empty(&stack)) {
+ pm = list_first_entry(&stack, struct pending_dir_move, list);
+ parent_ino = pm->ino;
+ ret = apply_dir_move(sctx, pm);
+ free_pending_move(sctx, pm);
+ if (ret)
+ goto out;
+ pm = get_pending_dir_moves(sctx, parent_ino);
+ if (pm)
+ tail_append_pending_moves(pm, &stack);
+ }
+ return 0;
+
+out:
+ while (!list_empty(&stack)) {
+ pm = list_first_entry(&stack, struct pending_dir_move, list);
+ free_pending_move(sctx, pm);
+ }
+ return ret;
+}
+
+static int wait_for_parent_move(struct send_ctx *sctx,
+ struct recorded_ref *parent_ref)
+{
+ int ret;
+ u64 ino = parent_ref->dir;
+ u64 parent_ino_before, parent_ino_after;
+ u64 new_gen, old_gen;
+ struct fs_path *path_before = NULL;
+ struct fs_path *path_after = NULL;
+ int len1, len2;
+
+ if (parent_ref->dir <= sctx->cur_ino)
+ return 0;
+
+ if (is_waiting_for_move(sctx, ino))
+ return 1;
+
+ ret = get_inode_info(sctx->parent_root, ino, NULL, &old_gen,
+ NULL, NULL, NULL, NULL);
+ if (ret == -ENOENT)
+ return 0;
+ else if (ret < 0)
+ return ret;
+
+ ret = get_inode_info(sctx->send_root, ino, NULL, &new_gen,
+ NULL, NULL, NULL, NULL);
+ if (ret < 0)
+ return ret;
+
+ if (new_gen != old_gen)
+ return 0;
+
+ path_before = fs_path_alloc();
+ if (!path_before)
+ return -ENOMEM;
+
+ ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
+ NULL, path_before);
+ if (ret == -ENOENT) {
+ ret = 0;
+ goto out;
+ } else if (ret < 0) {
+ goto out;
+ }
+
+ path_after = fs_path_alloc();
+ if (!path_after) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
+ NULL, path_after);
+ if (ret == -ENOENT) {
+ ret = 0;
+ goto out;
+ } else if (ret < 0) {
+ goto out;
+ }
+
+ len1 = fs_path_len(path_before);
+ len2 = fs_path_len(path_after);
+ if ((parent_ino_before != parent_ino_after) && (len1 != len2 ||
+ memcmp(path_before->start, path_after->start, len1))) {
+ ret = 1;
+ goto out;
+ }
+ ret = 0;
+
+out:
+ fs_path_free(path_before);
+ fs_path_free(path_after);
+
+ return ret;
+}
+
/*
* This does all the move/link/unlink/rmdir magic.
*/
-static int process_recorded_refs(struct send_ctx *sctx)
+static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
{
int ret = 0;
struct recorded_ref *cur;
@@ -2824,11 +3227,17 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino);
* dirs, we always have one new and one deleted
* ref. The deleted ref is ignored later.
*/
- ret = send_rename(sctx, valid_path,
- cur->full_path);
- if (ret < 0)
- goto out;
- ret = fs_path_copy(valid_path, cur->full_path);
+ if (wait_for_parent_move(sctx, cur)) {
+ ret = add_pending_dir_move(sctx,
+ cur->dir);
+ *pending_move = 1;
+ } else {
+ ret = send_rename(sctx, valid_path,
+ cur->full_path);
+ if (!ret)
+ ret = fs_path_copy(valid_path,
+ cur->full_path);
+ }
if (ret < 0)
goto out;
} else {
@@ -3197,6 +3606,7 @@ static int process_all_refs(struct send_ctx *sctx,
struct extent_buffer *eb;
int slot;
iterate_inode_ref_t cb;
+ int pending_move = 0;
path = alloc_path_for_send();
if (!path)
@@ -3240,7 +3650,9 @@ static int process_all_refs(struct send_ctx *sctx,
}
btrfs_release_path(path);
- ret = process_recorded_refs(sctx);
+ ret = process_recorded_refs(sctx, &pending_move);
+ /* Only applicable to an incremental send. */
+ ASSERT(pending_move == 0);
out:
btrfs_free_path(path);
@@ -3706,7 +4118,7 @@ verbose_printk("btrfs: send_clone offset=%llu, len=%d, clone_root=%llu, "
TLV_PUT_UUID(sctx, BTRFS_SEND_A_CLONE_UUID,
clone_root->root->root_item.uuid);
TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_CTRANSID,
- clone_root->root->root_item.ctransid);
+ le64_to_cpu(clone_root->root->root_item.ctransid));
TLV_PUT_PATH(sctx, BTRFS_SEND_A_CLONE_PATH, p);
TLV_PUT_U64(sctx, BTRFS_SEND_A_CLONE_OFFSET,
clone_root->offset);
@@ -3752,6 +4164,39 @@ out:
return ret;
}
+static int send_hole(struct send_ctx *sctx, u64 end)
+{
+ struct fs_path *p = NULL;
+ u64 offset = sctx->cur_inode_last_extent;
+ u64 len;
+ int ret = 0;
+
+ p = fs_path_alloc();
+ if (!p)
+ return -ENOMEM;
+ memset(sctx->read_buf, 0, BTRFS_SEND_READ_SIZE);
+ while (offset < end) {
+ len = min_t(u64, end - offset, BTRFS_SEND_READ_SIZE);
+
+ ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE);
+ if (ret < 0)
+ break;
+ ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p);
+ if (ret < 0)
+ break;
+ TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p);
+ TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset);
+ TLV_PUT(sctx, BTRFS_SEND_A_DATA, sctx->read_buf, len);
+ ret = send_cmd(sctx);
+ if (ret < 0)
+ break;
+ offset += len;
+ }
+tlv_put_failure:
+ fs_path_free(p);
+ return ret;
+}
+
static int send_write_or_clone(struct send_ctx *sctx,
struct btrfs_path *path,
struct btrfs_key *key,
@@ -3764,12 +4209,14 @@ static int send_write_or_clone(struct send_ctx *sctx,
u64 len;
u32 l;
u8 type;
+ u64 bs = sctx->send_root->fs_info->sb->s_blocksize;
ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_file_extent_item);
type = btrfs_file_extent_type(path->nodes[0], ei);
if (type == BTRFS_FILE_EXTENT_INLINE) {
- len = btrfs_file_extent_inline_len(path->nodes[0], ei);
+ len = btrfs_file_extent_inline_len(path->nodes[0],
+ path->slots[0], ei);
/*
* it is possible the inline item won't cover the whole page,
* but there may be items after this page. Make
@@ -3787,7 +4234,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
goto out;
}
- if (clone_root) {
+ if (clone_root && IS_ALIGNED(offset + len, bs)) {
ret = send_clone(sctx, offset, len, clone_root);
} else if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA) {
ret = send_update_extent(sctx, offset, len);
@@ -3979,6 +4426,101 @@ out:
return ret;
}
+static int get_last_extent(struct send_ctx *sctx, u64 offset)
+{
+ struct btrfs_path *path;
+ struct btrfs_root *root = sctx->send_root;
+ struct btrfs_file_extent_item *fi;
+ struct btrfs_key key;
+ u64 extent_end;
+ u8 type;
+ int ret;
+
+ path = alloc_path_for_send();
+ if (!path)
+ return -ENOMEM;
+
+ sctx->cur_inode_last_extent = 0;
+
+ key.objectid = sctx->cur_ino;
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = offset;
+ ret = btrfs_search_slot_for_read(root, &key, path, 0, 1);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+ if (key.objectid != sctx->cur_ino || key.type != BTRFS_EXTENT_DATA_KEY)
+ goto out;
+
+ fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(path->nodes[0], fi);
+ if (type == BTRFS_FILE_EXTENT_INLINE) {
+ u64 size = btrfs_file_extent_inline_len(path->nodes[0],
+ path->slots[0], fi);
+ extent_end = ALIGN(key.offset + size,
+ sctx->send_root->sectorsize);
+ } else {
+ extent_end = key.offset +
+ btrfs_file_extent_num_bytes(path->nodes[0], fi);
+ }
+ sctx->cur_inode_last_extent = extent_end;
+out:
+ btrfs_free_path(path);
+ return ret;
+}
+
+static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
+ struct btrfs_key *key)
+{
+ struct btrfs_file_extent_item *fi;
+ u64 extent_end;
+ u8 type;
+ int ret = 0;
+
+ if (sctx->cur_ino != key->objectid || !need_send_hole(sctx))
+ return 0;
+
+ if (sctx->cur_inode_last_extent == (u64)-1) {
+ ret = get_last_extent(sctx, key->offset - 1);
+ if (ret)
+ return ret;
+ }
+
+ fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+ struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(path->nodes[0], fi);
+ if (type == BTRFS_FILE_EXTENT_INLINE) {
+ u64 size = btrfs_file_extent_inline_len(path->nodes[0],
+ path->slots[0], fi);
+ extent_end = ALIGN(key->offset + size,
+ sctx->send_root->sectorsize);
+ } else {
+ extent_end = key->offset +
+ btrfs_file_extent_num_bytes(path->nodes[0], fi);
+ }
+
+ if (path->slots[0] == 0 &&
+ sctx->cur_inode_last_extent < key->offset) {
+ /*
+ * We might have skipped entire leafs that contained only
+ * file extent items for our current inode. These leafs have
+ * a generation number smaller (older) than the one in the
+ * current leaf and the leaf our last extent came from, and
+ * are located between these 2 leafs.
+ */
+ ret = get_last_extent(sctx, key->offset - 1);
+ if (ret)
+ return ret;
+ }
+
+ if (sctx->cur_inode_last_extent < key->offset)
+ ret = send_hole(sctx, key->offset);
+ sctx->cur_inode_last_extent = extent_end;
+ return ret;
+}
+
static int process_extent(struct send_ctx *sctx,
struct btrfs_path *path,
struct btrfs_key *key)
@@ -3995,7 +4537,7 @@ static int process_extent(struct send_ctx *sctx,
goto out;
if (ret) {
ret = 0;
- goto out;
+ goto out_hole;
}
} else {
struct btrfs_file_extent_item *ei;
@@ -4031,7 +4573,10 @@ static int process_extent(struct send_ctx *sctx,
goto out;
ret = send_write_or_clone(sctx, path, key, found_clone);
-
+ if (ret)
+ goto out;
+out_hole:
+ ret = maybe_send_hole(sctx, path, key);
out:
return ret;
}
@@ -4054,17 +4599,25 @@ static int process_all_extents(struct send_ctx *sctx)
key.objectid = sctx->cmp_key->objectid;
key.type = BTRFS_EXTENT_DATA_KEY;
key.offset = 0;
- while (1) {
- ret = btrfs_search_slot_for_read(root, &key, path, 1, 0);
- if (ret < 0)
- goto out;
- if (ret) {
- ret = 0;
- goto out;
- }
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+ while (1) {
eb = path->nodes[0];
slot = path->slots[0];
+
+ if (slot >= btrfs_header_nritems(eb)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0) {
+ goto out;
+ } else if (ret > 0) {
+ ret = 0;
+ break;
+ }
+ continue;
+ }
+
btrfs_item_key_to_cpu(eb, &found_key, slot);
if (found_key.objectid != key.objectid ||
@@ -4077,8 +4630,7 @@ static int process_all_extents(struct send_ctx *sctx)
if (ret < 0)
goto out;
- btrfs_release_path(path);
- key.offset = found_key.offset + 1;
+ path->slots[0]++;
}
out:
@@ -4086,7 +4638,9 @@ out:
return ret;
}
-static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end)
+static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end,
+ int *pending_move,
+ int *refs_processed)
{
int ret = 0;
@@ -4098,17 +4652,11 @@ static int process_recorded_refs_if_needed(struct send_ctx *sctx, int at_end)
if (list_empty(&sctx->new_refs) && list_empty(&sctx->deleted_refs))
goto out;
- ret = process_recorded_refs(sctx);
+ ret = process_recorded_refs(sctx, pending_move);
if (ret < 0)
goto out;
- /*
- * We have processed the refs and thus need to advance send_progress.
- * Now, calls to get_cur_xxx will take the updated refs of the current
- * inode into account.
- */
- sctx->send_progress = sctx->cur_ino + 1;
-
+ *refs_processed = 1;
out:
return ret;
}
@@ -4124,11 +4672,29 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
u64 right_gid;
int need_chmod = 0;
int need_chown = 0;
+ int pending_move = 0;
+ int refs_processed = 0;
- ret = process_recorded_refs_if_needed(sctx, at_end);
+ ret = process_recorded_refs_if_needed(sctx, at_end, &pending_move,
+ &refs_processed);
if (ret < 0)
goto out;
+ /*
+ * We have processed the refs and thus need to advance send_progress.
+ * Now, calls to get_cur_xxx will take the updated refs of the current
+ * inode into account.
+ *
+ * On the other hand, if our current inode is a directory and couldn't
+ * be moved/renamed because its parent was renamed/moved too and it has
+ * a higher inode number, we can only move/rename our current inode
+ * after we moved/renamed its parent. Therefore in this case operate on
+ * the old path (pre move/rename) of our current inode, and the
+ * move/rename will be performed later.
+ */
+ if (refs_processed && !pending_move)
+ sctx->send_progress = sctx->cur_ino + 1;
+
if (sctx->cur_ino == 0 || sctx->cur_inode_deleted)
goto out;
if (!at_end && sctx->cmp_key->objectid == sctx->cur_ino)
@@ -4157,6 +4723,19 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
}
if (S_ISREG(sctx->cur_inode_mode)) {
+ if (need_send_hole(sctx)) {
+ if (sctx->cur_inode_last_extent == (u64)-1) {
+ ret = get_last_extent(sctx, (u64)-1);
+ if (ret)
+ goto out;
+ }
+ if (sctx->cur_inode_last_extent <
+ sctx->cur_inode_size) {
+ ret = send_hole(sctx, sctx->cur_inode_size);
+ if (ret)
+ goto out;
+ }
+ }
ret = send_truncate(sctx, sctx->cur_ino, sctx->cur_inode_gen,
sctx->cur_inode_size);
if (ret < 0)
@@ -4177,9 +4756,21 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
}
/*
- * Need to send that every time, no matter if it actually changed
- * between the two trees as we have done changes to the inode before.
+ * If other directory inodes depended on our current directory
+ * inode's move/rename, now do their move/rename operations.
+ */
+ if (!is_waiting_for_move(sctx, sctx->cur_ino)) {
+ ret = apply_children_dir_moves(sctx);
+ if (ret)
+ goto out;
+ }
+
+ /*
+ * Need to send that every time, no matter if it actually
+ * changed between the two trees as we have done changes to
+ * the inode before.
*/
+ sctx->send_progress = sctx->cur_ino + 1;
ret = send_utimes(sctx, sctx->cur_ino, sctx->cur_inode_gen);
if (ret < 0)
goto out;
@@ -4200,6 +4791,7 @@ static int changed_inode(struct send_ctx *sctx,
sctx->cur_ino = key->objectid;
sctx->cur_inode_new_gen = 0;
+ sctx->cur_inode_last_extent = (u64)-1;
/*
* Set send_progress to current inode. This will tell all get_cur_xxx
@@ -4480,14 +5072,18 @@ static int changed_cb(struct btrfs_root *left_root,
struct send_ctx *sctx = ctx;
if (result == BTRFS_COMPARE_TREE_SAME) {
- if (key->type != BTRFS_INODE_REF_KEY &&
- key->type != BTRFS_INODE_EXTREF_KEY)
- return 0;
- ret = compare_refs(sctx, left_path, key);
- if (!ret)
+ if (key->type == BTRFS_INODE_REF_KEY ||
+ key->type == BTRFS_INODE_EXTREF_KEY) {
+ ret = compare_refs(sctx, left_path, key);
+ if (!ret)
+ return 0;
+ if (ret < 0)
+ return ret;
+ } else if (key->type == BTRFS_EXTENT_DATA_KEY) {
+ return maybe_send_hole(sctx, left_path, key);
+ } else {
return 0;
- if (ret < 0)
- return ret;
+ }
result = BTRFS_COMPARE_TREE_CHANGED;
ret = 0;
}
@@ -4522,7 +5118,6 @@ out:
static int full_send_tree(struct send_ctx *sctx)
{
int ret;
- struct btrfs_trans_handle *trans = NULL;
struct btrfs_root *send_root = sctx->send_root;
struct btrfs_key key;
struct btrfs_key found_key;
@@ -4544,19 +5139,6 @@ static int full_send_tree(struct send_ctx *sctx)
key.type = BTRFS_INODE_ITEM_KEY;
key.offset = 0;
-join_trans:
- /*
- * We need to make sure the transaction does not get committed
- * while we do anything on commit roots. Join a transaction to prevent
- * this.
- */
- trans = btrfs_join_transaction(send_root);
- if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- trans = NULL;
- goto out;
- }
-
/*
* Make sure the tree has not changed after re-joining. We detect this
* by comparing start_ctransid and ctransid. They should always match.
@@ -4566,7 +5148,7 @@ join_trans:
spin_unlock(&send_root->root_item_lock);
if (ctransid != start_ctransid) {
- WARN(1, KERN_WARNING "btrfs: the root that you're trying to "
+ WARN(1, KERN_WARNING "BTRFS: the root that you're trying to "
"send was modified in between. This is "
"probably a bug.\n");
ret = -EIO;
@@ -4580,19 +5162,6 @@ join_trans:
goto out_finish;
while (1) {
- /*
- * When someone want to commit while we iterate, end the
- * joined transaction and rejoin.
- */
- if (btrfs_should_end_transaction(trans, send_root)) {
- ret = btrfs_end_transaction(trans, send_root);
- trans = NULL;
- if (ret < 0)
- goto out;
- btrfs_release_path(path);
- goto join_trans;
- }
-
eb = path->nodes[0];
slot = path->slots[0];
btrfs_item_key_to_cpu(eb, &found_key, slot);
@@ -4620,12 +5189,6 @@ out_finish:
out:
btrfs_free_path(path);
- if (trans) {
- if (!ret)
- ret = btrfs_end_transaction(trans, send_root);
- else
- btrfs_end_transaction(trans, send_root);
- }
return ret;
}
@@ -4662,6 +5225,21 @@ out:
return ret;
}
+static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
+{
+ spin_lock(&root->root_item_lock);
+ root->send_in_progress--;
+ /*
+ * Not much left to do, we don't know why it's unbalanced and
+ * can't blindly reset it to 0.
+ */
+ if (root->send_in_progress < 0)
+ btrfs_err(root->fs_info,
+ "send_in_progres unbalanced %d root %llu\n",
+ root->send_in_progress, root->root_key.objectid);
+ spin_unlock(&root->root_item_lock);
+}
+
long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
{
int ret = 0;
@@ -4673,6 +5251,9 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
struct send_ctx *sctx = NULL;
u32 i;
u64 *clone_sources_tmp = NULL;
+ int clone_sources_to_rollback = 0;
+ int sort_clone_roots = 0;
+ int index;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -4681,38 +5262,26 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
fs_info = send_root->fs_info;
/*
+ * The subvolume must remain read-only during send, protect against
+ * making it RW.
+ */
+ spin_lock(&send_root->root_item_lock);
+ send_root->send_in_progress++;
+ spin_unlock(&send_root->root_item_lock);
+
+ /*
* This is done when we lookup the root, it should already be complete
* by the time we get here.
*/
WARN_ON(send_root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE);
/*
- * If we just created this root we need to make sure that the orphan
- * cleanup has been done and committed since we search the commit root,
- * so check its commit root transid with our otransid and if they match
- * commit the transaction to make sure everything is updated.
+ * Userspace tools do the checks and warn the user if it's
+ * not RO.
*/
- down_read(&send_root->fs_info->extent_commit_sem);
- if (btrfs_header_generation(send_root->commit_root) ==
- btrfs_root_otransid(&send_root->root_item)) {
- struct btrfs_trans_handle *trans;
-
- up_read(&send_root->fs_info->extent_commit_sem);
-
- trans = btrfs_attach_transaction_barrier(send_root);
- if (IS_ERR(trans)) {
- if (PTR_ERR(trans) != -ENOENT) {
- ret = PTR_ERR(trans);
- goto out;
- }
- /* ENOENT means theres no transaction */
- } else {
- ret = btrfs_commit_transaction(trans, send_root);
- if (ret)
- goto out;
- }
- } else {
- up_read(&send_root->fs_info->extent_commit_sem);
+ if (!btrfs_root_readonly(send_root)) {
+ ret = -EPERM;
+ goto out;
}
arg = memdup_user(arg_, sizeof(*arg));
@@ -4753,8 +5322,6 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
goto out;
}
- sctx->mnt = mnt_file->f_path.mnt;
-
sctx->send_root = send_root;
sctx->clone_roots_cnt = arg->clone_sources_count;
@@ -4771,6 +5338,9 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
goto out;
}
+ sctx->pending_dir_moves = RB_ROOT;
+ sctx->waiting_dir_moves = RB_ROOT;
+
sctx->clone_roots = vzalloc(sizeof(struct clone_root) *
(arg->clone_sources_count + 1));
if (!sctx->clone_roots) {
@@ -4798,11 +5368,27 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
key.objectid = clone_sources_tmp[i];
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
+
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
clone_root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(clone_root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(clone_root);
goto out;
}
+ clone_sources_to_rollback = i + 1;
+ spin_lock(&clone_root->root_item_lock);
+ clone_root->send_in_progress++;
+ if (!btrfs_root_readonly(clone_root)) {
+ spin_unlock(&clone_root->root_item_lock);
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ ret = -EPERM;
+ goto out;
+ }
+ spin_unlock(&clone_root->root_item_lock);
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+
sctx->clone_roots[i].root = clone_root;
}
vfree(clone_sources_tmp);
@@ -4813,11 +5399,27 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
key.objectid = arg->parent_root;
key.type = BTRFS_ROOT_ITEM_KEY;
key.offset = (u64)-1;
+
+ index = srcu_read_lock(&fs_info->subvol_srcu);
+
sctx->parent_root = btrfs_read_fs_root_no_name(fs_info, &key);
if (IS_ERR(sctx->parent_root)) {
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
ret = PTR_ERR(sctx->parent_root);
goto out;
}
+
+ spin_lock(&sctx->parent_root->root_item_lock);
+ sctx->parent_root->send_in_progress++;
+ if (!btrfs_root_readonly(sctx->parent_root)) {
+ spin_unlock(&sctx->parent_root->root_item_lock);
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
+ ret = -EPERM;
+ goto out;
+ }
+ spin_unlock(&sctx->parent_root->root_item_lock);
+
+ srcu_read_unlock(&fs_info->subvol_srcu, index);
}
/*
@@ -4831,6 +5433,7 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
sort(sctx->clone_roots, sctx->clone_roots_cnt,
sizeof(*sctx->clone_roots), __clone_root_cmp_sort,
NULL);
+ sort_clone_roots = 1;
ret = send_subvol(sctx);
if (ret < 0)
@@ -4846,6 +5449,48 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
}
out:
+ WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->pending_dir_moves));
+ while (sctx && !RB_EMPTY_ROOT(&sctx->pending_dir_moves)) {
+ struct rb_node *n;
+ struct pending_dir_move *pm;
+
+ n = rb_first(&sctx->pending_dir_moves);
+ pm = rb_entry(n, struct pending_dir_move, node);
+ while (!list_empty(&pm->list)) {
+ struct pending_dir_move *pm2;
+
+ pm2 = list_first_entry(&pm->list,
+ struct pending_dir_move, list);
+ free_pending_move(sctx, pm2);
+ }
+ free_pending_move(sctx, pm);
+ }
+
+ WARN_ON(sctx && !ret && !RB_EMPTY_ROOT(&sctx->waiting_dir_moves));
+ while (sctx && !RB_EMPTY_ROOT(&sctx->waiting_dir_moves)) {
+ struct rb_node *n;
+ struct waiting_dir_move *dm;
+
+ n = rb_first(&sctx->waiting_dir_moves);
+ dm = rb_entry(n, struct waiting_dir_move, node);
+ rb_erase(&dm->node, &sctx->waiting_dir_moves);
+ kfree(dm);
+ }
+
+ if (sort_clone_roots) {
+ for (i = 0; i < sctx->clone_roots_cnt; i++)
+ btrfs_root_dec_send_in_progress(
+ sctx->clone_roots[i].root);
+ } else {
+ for (i = 0; sctx && i < clone_sources_to_rollback; i++)
+ btrfs_root_dec_send_in_progress(
+ sctx->clone_roots[i].root);
+
+ btrfs_root_dec_send_in_progress(send_root);
+ }
+ if (sctx && !IS_ERR_OR_NULL(sctx->parent_root))
+ btrfs_root_dec_send_in_progress(sctx->parent_root);
+
kfree(arg);
vfree(clone_sources_tmp);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d71a11d13dfa..d04db817be5c 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -48,6 +48,8 @@
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
+#include "hash.h"
+#include "props.h"
#include "xattr.h"
#include "volumes.h"
#include "export.h"
@@ -152,11 +154,12 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
vaf.fmt = fmt;
vaf.va = &args;
- printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: errno=%d %s (%pV)\n",
+ printk(KERN_CRIT
+ "BTRFS: error (device %s) in %s:%d: errno=%d %s (%pV)\n",
sb->s_id, function, line, errno, errstr, &vaf);
va_end(args);
} else {
- printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: errno=%d %s\n",
+ printk(KERN_CRIT "BTRFS: error (device %s) in %s:%d: errno=%d %s\n",
sb->s_id, function, line, errno, errstr);
}
@@ -250,7 +253,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
*/
if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED,
&root->fs_info->fs_state)) {
- WARN(1, KERN_DEBUG "btrfs: Transaction aborted (error %d)\n",
+ WARN(1, KERN_DEBUG "BTRFS: Transaction aborted (error %d)\n",
errno);
}
trans->aborted = errno;
@@ -294,8 +297,8 @@ void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n",
s_id, function, line, &vaf, errno, errstr);
- printk(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n",
- s_id, function, line, &vaf, errno, errstr);
+ btrfs_crit(fs_info, "panic in %s:%d: %pV (errno=%d %s)",
+ function, line, &vaf, errno, errstr);
va_end(args);
/* Caller calls BUG() */
}
@@ -322,7 +325,9 @@ enum {
Opt_no_space_cache, Opt_recovery, Opt_skip_balance,
Opt_check_integrity, Opt_check_integrity_including_extent_data,
Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
- Opt_commit_interval,
+ Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
+ Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
+ Opt_datasum, Opt_treelog, Opt_noinode_cache,
Opt_err,
};
@@ -332,8 +337,11 @@ static match_table_t tokens = {
{Opt_subvolid, "subvolid=%s"},
{Opt_device, "device=%s"},
{Opt_nodatasum, "nodatasum"},
+ {Opt_datasum, "datasum"},
{Opt_nodatacow, "nodatacow"},
+ {Opt_datacow, "datacow"},
{Opt_nobarrier, "nobarrier"},
+ {Opt_barrier, "barrier"},
{Opt_max_inline, "max_inline=%s"},
{Opt_alloc_start, "alloc_start=%s"},
{Opt_thread_pool, "thread_pool=%d"},
@@ -344,18 +352,25 @@ static match_table_t tokens = {
{Opt_ssd, "ssd"},
{Opt_ssd_spread, "ssd_spread"},
{Opt_nossd, "nossd"},
+ {Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_notreelog, "notreelog"},
+ {Opt_treelog, "treelog"},
{Opt_flushoncommit, "flushoncommit"},
+ {Opt_noflushoncommit, "noflushoncommit"},
{Opt_ratio, "metadata_ratio=%d"},
{Opt_discard, "discard"},
+ {Opt_nodiscard, "nodiscard"},
{Opt_space_cache, "space_cache"},
{Opt_clear_cache, "clear_cache"},
{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
{Opt_enospc_debug, "enospc_debug"},
+ {Opt_noenospc_debug, "noenospc_debug"},
{Opt_subvolrootid, "subvolrootid=%d"},
{Opt_defrag, "autodefrag"},
+ {Opt_nodefrag, "noautodefrag"},
{Opt_inode_cache, "inode_cache"},
+ {Opt_noinode_cache, "noinode_cache"},
{Opt_no_space_cache, "nospace_cache"},
{Opt_recovery, "recovery"},
{Opt_skip_balance, "skip_balance"},
@@ -368,6 +383,20 @@ static match_table_t tokens = {
{Opt_err, NULL},
};
+#define btrfs_set_and_info(root, opt, fmt, args...) \
+{ \
+ if (!btrfs_test_opt(root, opt)) \
+ btrfs_info(root->fs_info, fmt, ##args); \
+ btrfs_set_opt(root->fs_info->mount_opt, opt); \
+}
+
+#define btrfs_clear_and_info(root, opt, fmt, args...) \
+{ \
+ if (btrfs_test_opt(root, opt)) \
+ btrfs_info(root->fs_info, fmt, ##args); \
+ btrfs_clear_opt(root->fs_info->mount_opt, opt); \
+}
+
/*
* Regular mount options parser. Everything that is needed only when
* reading in a new superblock is parsed here.
@@ -383,6 +412,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
int ret = 0;
char *compress_type;
bool compress_force = false;
+ bool compress = false;
cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
if (cache_gen)
@@ -409,7 +439,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
token = match_token(p, tokens, args);
switch (token) {
case Opt_degraded:
- printk(KERN_INFO "btrfs: allowing degraded mounts\n");
+ btrfs_info(root->fs_info, "allowing degraded mounts");
btrfs_set_opt(info->mount_opt, DEGRADED);
break;
case Opt_subvol:
@@ -422,27 +452,45 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
*/
break;
case Opt_nodatasum:
- printk(KERN_INFO "btrfs: setting nodatasum\n");
- btrfs_set_opt(info->mount_opt, NODATASUM);
+ btrfs_set_and_info(root, NODATASUM,
+ "setting nodatasum");
+ break;
+ case Opt_datasum:
+ if (btrfs_test_opt(root, NODATASUM)) {
+ if (btrfs_test_opt(root, NODATACOW))
+ btrfs_info(root->fs_info, "setting datasum, datacow enabled");
+ else
+ btrfs_info(root->fs_info, "setting datasum");
+ }
+ btrfs_clear_opt(info->mount_opt, NODATACOW);
+ btrfs_clear_opt(info->mount_opt, NODATASUM);
break;
case Opt_nodatacow:
- if (!btrfs_test_opt(root, COMPRESS) ||
- !btrfs_test_opt(root, FORCE_COMPRESS)) {
- printk(KERN_INFO "btrfs: setting nodatacow, compression disabled\n");
- } else {
- printk(KERN_INFO "btrfs: setting nodatacow\n");
+ if (!btrfs_test_opt(root, NODATACOW)) {
+ if (!btrfs_test_opt(root, COMPRESS) ||
+ !btrfs_test_opt(root, FORCE_COMPRESS)) {
+ btrfs_info(root->fs_info,
+ "setting nodatacow, compression disabled");
+ } else {
+ btrfs_info(root->fs_info, "setting nodatacow");
+ }
}
btrfs_clear_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
btrfs_set_opt(info->mount_opt, NODATACOW);
btrfs_set_opt(info->mount_opt, NODATASUM);
break;
+ case Opt_datacow:
+ btrfs_clear_and_info(root, NODATACOW,
+ "setting datacow");
+ break;
case Opt_compress_force:
case Opt_compress_force_type:
compress_force = true;
/* Fallthrough */
case Opt_compress:
case Opt_compress_type:
+ compress = true;
if (token == Opt_compress ||
token == Opt_compress_force ||
strcmp(args[0].from, "zlib") == 0) {
@@ -469,34 +517,36 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
}
if (compress_force) {
- btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
- pr_info("btrfs: force %s compression\n",
- compress_type);
- } else if (btrfs_test_opt(root, COMPRESS)) {
- pr_info("btrfs: use %s compression\n",
- compress_type);
+ btrfs_set_and_info(root, FORCE_COMPRESS,
+ "force %s compression",
+ compress_type);
+ } else if (compress) {
+ if (!btrfs_test_opt(root, COMPRESS))
+ btrfs_info(root->fs_info,
+ "btrfs: use %s compression\n",
+ compress_type);
}
break;
case Opt_ssd:
- printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
- btrfs_set_opt(info->mount_opt, SSD);
+ btrfs_set_and_info(root, SSD,
+ "use ssd allocation scheme");
break;
case Opt_ssd_spread:
- printk(KERN_INFO "btrfs: use spread ssd "
- "allocation scheme\n");
- btrfs_set_opt(info->mount_opt, SSD);
- btrfs_set_opt(info->mount_opt, SSD_SPREAD);
+ btrfs_set_and_info(root, SSD_SPREAD,
+ "use spread ssd allocation scheme");
break;
case Opt_nossd:
- printk(KERN_INFO "btrfs: not using ssd allocation "
- "scheme\n");
- btrfs_set_opt(info->mount_opt, NOSSD);
+ btrfs_clear_and_info(root, NOSSD,
+ "not using ssd allocation scheme");
btrfs_clear_opt(info->mount_opt, SSD);
- btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
+ break;
+ case Opt_barrier:
+ btrfs_clear_and_info(root, NOBARRIER,
+ "turning on barriers");
break;
case Opt_nobarrier:
- printk(KERN_INFO "btrfs: turning off barriers\n");
- btrfs_set_opt(info->mount_opt, NOBARRIER);
+ btrfs_set_and_info(root, NOBARRIER,
+ "turning off barriers");
break;
case Opt_thread_pool:
ret = match_int(&args[0], &intarg);
@@ -516,11 +566,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
kfree(num);
if (info->max_inline) {
- info->max_inline = max_t(u64,
+ info->max_inline = min_t(u64,
info->max_inline,
root->sectorsize);
}
- printk(KERN_INFO "btrfs: max_inline at %llu\n",
+ btrfs_info(root->fs_info, "max_inline at %llu",
info->max_inline);
} else {
ret = -ENOMEM;
@@ -534,24 +584,34 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
info->alloc_start = memparse(num, NULL);
mutex_unlock(&info->chunk_mutex);
kfree(num);
- printk(KERN_INFO
- "btrfs: allocations start at %llu\n",
+ btrfs_info(root->fs_info, "allocations start at %llu",
info->alloc_start);
} else {
ret = -ENOMEM;
goto out;
}
break;
+ case Opt_acl:
+ root->fs_info->sb->s_flags |= MS_POSIXACL;
+ break;
case Opt_noacl:
root->fs_info->sb->s_flags &= ~MS_POSIXACL;
break;
case Opt_notreelog:
- printk(KERN_INFO "btrfs: disabling tree log\n");
- btrfs_set_opt(info->mount_opt, NOTREELOG);
+ btrfs_set_and_info(root, NOTREELOG,
+ "disabling tree log");
+ break;
+ case Opt_treelog:
+ btrfs_clear_and_info(root, NOTREELOG,
+ "enabling tree log");
break;
case Opt_flushoncommit:
- printk(KERN_INFO "btrfs: turning on flush-on-commit\n");
- btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
+ btrfs_set_and_info(root, FLUSHONCOMMIT,
+ "turning on flush-on-commit");
+ break;
+ case Opt_noflushoncommit:
+ btrfs_clear_and_info(root, FLUSHONCOMMIT,
+ "turning off flush-on-commit");
break;
case Opt_ratio:
ret = match_int(&args[0], &intarg);
@@ -559,7 +619,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
goto out;
} else if (intarg >= 0) {
info->metadata_ratio = intarg;
- printk(KERN_INFO "btrfs: metadata ratio %d\n",
+ btrfs_info(root->fs_info, "metadata ratio %d",
info->metadata_ratio);
} else {
ret = -EINVAL;
@@ -567,25 +627,35 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
}
break;
case Opt_discard:
- btrfs_set_opt(info->mount_opt, DISCARD);
+ btrfs_set_and_info(root, DISCARD,
+ "turning on discard");
+ break;
+ case Opt_nodiscard:
+ btrfs_clear_and_info(root, DISCARD,
+ "turning off discard");
break;
case Opt_space_cache:
- btrfs_set_opt(info->mount_opt, SPACE_CACHE);
+ btrfs_set_and_info(root, SPACE_CACHE,
+ "enabling disk space caching");
break;
case Opt_rescan_uuid_tree:
btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
break;
case Opt_no_space_cache:
- printk(KERN_INFO "btrfs: disabling disk space caching\n");
- btrfs_clear_opt(info->mount_opt, SPACE_CACHE);
+ btrfs_clear_and_info(root, SPACE_CACHE,
+ "disabling disk space caching");
break;
case Opt_inode_cache:
- printk(KERN_INFO "btrfs: enabling inode map caching\n");
- btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE);
+ btrfs_set_and_info(root, CHANGE_INODE_CACHE,
+ "enabling inode map caching");
+ break;
+ case Opt_noinode_cache:
+ btrfs_clear_and_info(root, CHANGE_INODE_CACHE,
+ "disabling inode map caching");
break;
case Opt_clear_cache:
- printk(KERN_INFO "btrfs: force clearing of disk cache\n");
- btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
+ btrfs_set_and_info(root, CLEAR_CACHE,
+ "force clearing of disk cache");
break;
case Opt_user_subvol_rm_allowed:
btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
@@ -593,12 +663,19 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
case Opt_enospc_debug:
btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
break;
+ case Opt_noenospc_debug:
+ btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG);
+ break;
case Opt_defrag:
- printk(KERN_INFO "btrfs: enabling auto defrag\n");
- btrfs_set_opt(info->mount_opt, AUTO_DEFRAG);
+ btrfs_set_and_info(root, AUTO_DEFRAG,
+ "enabling auto defrag");
+ break;
+ case Opt_nodefrag:
+ btrfs_clear_and_info(root, AUTO_DEFRAG,
+ "disabling auto defrag");
break;
case Opt_recovery:
- printk(KERN_INFO "btrfs: enabling auto recovery\n");
+ btrfs_info(root->fs_info, "enabling auto recovery");
btrfs_set_opt(info->mount_opt, RECOVERY);
break;
case Opt_skip_balance:
@@ -606,14 +683,14 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
break;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
case Opt_check_integrity_including_extent_data:
- printk(KERN_INFO "btrfs: enabling check integrity"
- " including extent data\n");
+ btrfs_info(root->fs_info,
+ "enabling check integrity including extent data");
btrfs_set_opt(info->mount_opt,
CHECK_INTEGRITY_INCLUDING_EXTENT_DATA);
btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
break;
case Opt_check_integrity:
- printk(KERN_INFO "btrfs: enabling check integrity\n");
+ btrfs_info(root->fs_info, "enabling check integrity");
btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
break;
case Opt_check_integrity_print_mask:
@@ -622,8 +699,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
goto out;
} else if (intarg >= 0) {
info->check_integrity_print_mask = intarg;
- printk(KERN_INFO "btrfs:"
- " check_integrity_print_mask 0x%x\n",
+ btrfs_info(root->fs_info, "check_integrity_print_mask 0x%x",
info->check_integrity_print_mask);
} else {
ret = -EINVAL;
@@ -634,8 +710,8 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
case Opt_check_integrity_including_extent_data:
case Opt_check_integrity:
case Opt_check_integrity_print_mask:
- printk(KERN_ERR "btrfs: support for check_integrity*"
- " not compiled in!\n");
+ btrfs_err(root->fs_info,
+ "support for check_integrity* not compiled in!");
ret = -EINVAL;
goto out;
#endif
@@ -655,28 +731,24 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
intarg = 0;
ret = match_int(&args[0], &intarg);
if (ret < 0) {
- printk(KERN_ERR
- "btrfs: invalid commit interval\n");
+ btrfs_err(root->fs_info, "invalid commit interval");
ret = -EINVAL;
goto out;
}
if (intarg > 0) {
if (intarg > 300) {
- printk(KERN_WARNING
- "btrfs: excessive commit interval %d\n",
+ btrfs_warn(root->fs_info, "excessive commit interval %d",
intarg);
}
info->commit_interval = intarg;
} else {
- printk(KERN_INFO
- "btrfs: using default commit interval %ds\n",
+ btrfs_info(root->fs_info, "using default commit interval %ds",
BTRFS_DEFAULT_COMMIT_INTERVAL);
info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
}
break;
case Opt_err:
- printk(KERN_INFO "btrfs: unrecognized mount option "
- "'%s'\n", p);
+ btrfs_info(root->fs_info, "unrecognized mount option '%s'", p);
ret = -EINVAL;
goto out;
default:
@@ -685,7 +757,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
}
out:
if (!ret && btrfs_test_opt(root, SPACE_CACHE))
- printk(KERN_INFO "btrfs: disk space caching is enabled\n");
+ btrfs_info(root->fs_info, "disk space caching is enabled");
kfree(orig);
return ret;
}
@@ -748,7 +820,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
break;
case Opt_subvolrootid:
printk(KERN_WARNING
- "btrfs: 'subvolrootid' mount option is deprecated and has no effect\n");
+ "BTRFS: 'subvolrootid' mount option is deprecated and has "
+ "no effect\n");
break;
case Opt_device:
device_name = match_strdup(&args[0]);
@@ -782,6 +855,7 @@ static struct dentry *get_default_root(struct super_block *sb,
struct btrfs_path *path;
struct btrfs_key location;
struct inode *inode;
+ struct dentry *dentry;
u64 dir_id;
int new = 0;
@@ -852,7 +926,13 @@ setup_root:
return dget(sb->s_root);
}
- return d_obtain_alias(inode);
+ dentry = d_obtain_alias(inode);
+ if (!IS_ERR(dentry)) {
+ spin_lock(&dentry->d_lock);
+ dentry->d_flags &= ~DCACHE_DISCONNECTED;
+ spin_unlock(&dentry->d_lock);
+ }
+ return dentry;
}
static int btrfs_fill_super(struct super_block *sb,
@@ -877,7 +957,7 @@ static int btrfs_fill_super(struct super_block *sb,
sb->s_flags |= MS_I_VERSION;
err = open_ctree(sb, fs_devices, (char *)data);
if (err) {
- printk("btrfs: open_ctree failed\n");
+ printk(KERN_ERR "BTRFS: open_ctree failed\n");
return err;
}
@@ -1115,7 +1195,7 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
dput(root);
root = ERR_PTR(-EINVAL);
deactivate_locked_super(s);
- printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
+ printk(KERN_ERR "BTRFS: '%s' is not a valid subvolume\n",
subvol_name);
}
@@ -1240,7 +1320,7 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
fs_info->thread_pool_size = new_pool_size;
- printk(KERN_INFO "btrfs: resize thread pool %d -> %d\n",
+ btrfs_info(fs_info, "resize thread pool %d -> %d",
old_pool_size, new_pool_size);
btrfs_set_max_workers(&fs_info->generic_worker, new_pool_size);
@@ -1346,7 +1426,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
} else {
if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
btrfs_err(fs_info,
- "Remounting read-write after error is not allowed\n");
+ "Remounting read-write after error is not allowed");
ret = -EINVAL;
goto restore;
}
@@ -1358,8 +1438,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
if (fs_info->fs_devices->missing_devices >
fs_info->num_tolerated_disk_barrier_failures &&
!(*flags & MS_RDONLY)) {
- printk(KERN_WARNING
- "Btrfs: too many missing devices, writeable remount is not allowed\n");
+ btrfs_warn(fs_info,
+ "too many missing devices, writeable remount is not allowed");
ret = -EACCES;
goto restore;
}
@@ -1384,16 +1464,15 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
ret = btrfs_resume_dev_replace_async(fs_info);
if (ret) {
- pr_warn("btrfs: failed to resume dev_replace\n");
+ btrfs_warn(fs_info, "failed to resume dev_replace");
goto restore;
}
if (!fs_info->uuid_root) {
- pr_info("btrfs: creating UUID tree\n");
+ btrfs_info(fs_info, "creating UUID tree");
ret = btrfs_create_uuid_tree(fs_info);
if (ret) {
- pr_warn("btrfs: failed to create the uuid tree"
- "%d\n", ret);
+ btrfs_warn(fs_info, "failed to create the UUID tree %d", ret);
goto restore;
}
}
@@ -1773,7 +1852,7 @@ static int btrfs_interface_init(void)
static void btrfs_interface_exit(void)
{
if (misc_deregister(&btrfs_misc) < 0)
- printk(KERN_INFO "btrfs: misc_deregister failed for control device\n");
+ printk(KERN_INFO "BTRFS: misc_deregister failed for control device\n");
}
static void btrfs_print_info(void)
@@ -1818,10 +1897,16 @@ static int __init init_btrfs_fs(void)
{
int err;
- err = btrfs_init_sysfs();
+ err = btrfs_hash_init();
if (err)
return err;
+ btrfs_props_init();
+
+ err = btrfs_init_sysfs();
+ if (err)
+ goto free_hash;
+
btrfs_init_compress();
err = btrfs_init_cachep();
@@ -1895,6 +1980,8 @@ free_cachep:
free_compress:
btrfs_exit_compress();
btrfs_exit_sysfs();
+free_hash:
+ btrfs_hash_exit();
return err;
}
@@ -1913,9 +2000,10 @@ static void __exit exit_btrfs_fs(void)
btrfs_exit_sysfs();
btrfs_cleanup_fs_uuids();
btrfs_exit_compress();
+ btrfs_hash_exit();
}
-module_init(init_btrfs_fs)
+late_initcall(init_btrfs_fs);
module_exit(exit_btrfs_fs)
MODULE_LICENSE("GPL");
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 5b326cd60a4a..865f4cf9a769 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -22,24 +22,647 @@
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/kobject.h>
+#include <linux/bug.h>
+#include <linux/genhd.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
+#include "sysfs.h"
+#include "volumes.h"
+
+static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj);
+
+static u64 get_features(struct btrfs_fs_info *fs_info,
+ enum btrfs_feature_set set)
+{
+ struct btrfs_super_block *disk_super = fs_info->super_copy;
+ if (set == FEAT_COMPAT)
+ return btrfs_super_compat_flags(disk_super);
+ else if (set == FEAT_COMPAT_RO)
+ return btrfs_super_compat_ro_flags(disk_super);
+ else
+ return btrfs_super_incompat_flags(disk_super);
+}
+
+static void set_features(struct btrfs_fs_info *fs_info,
+ enum btrfs_feature_set set, u64 features)
+{
+ struct btrfs_super_block *disk_super = fs_info->super_copy;
+ if (set == FEAT_COMPAT)
+ btrfs_set_super_compat_flags(disk_super, features);
+ else if (set == FEAT_COMPAT_RO)
+ btrfs_set_super_compat_ro_flags(disk_super, features);
+ else
+ btrfs_set_super_incompat_flags(disk_super, features);
+}
+
+static int can_modify_feature(struct btrfs_feature_attr *fa)
+{
+ int val = 0;
+ u64 set, clear;
+ switch (fa->feature_set) {
+ case FEAT_COMPAT:
+ set = BTRFS_FEATURE_COMPAT_SAFE_SET;
+ clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR;
+ break;
+ case FEAT_COMPAT_RO:
+ set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET;
+ clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR;
+ break;
+ case FEAT_INCOMPAT:
+ set = BTRFS_FEATURE_INCOMPAT_SAFE_SET;
+ clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR;
+ break;
+ default:
+ printk(KERN_WARNING "btrfs: sysfs: unknown feature set %d\n",
+ fa->feature_set);
+ return 0;
+ }
+
+ if (set & fa->feature_bit)
+ val |= 1;
+ if (clear & fa->feature_bit)
+ val |= 2;
+
+ return val;
+}
+
+static ssize_t btrfs_feature_attr_show(struct kobject *kobj,
+ struct kobj_attribute *a, char *buf)
+{
+ int val = 0;
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a);
+ if (fs_info) {
+ u64 features = get_features(fs_info, fa->feature_set);
+ if (features & fa->feature_bit)
+ val = 1;
+ } else
+ val = can_modify_feature(fa);
+
+ return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t btrfs_feature_attr_store(struct kobject *kobj,
+ struct kobj_attribute *a,
+ const char *buf, size_t count)
+{
+ struct btrfs_fs_info *fs_info;
+ struct btrfs_feature_attr *fa = to_btrfs_feature_attr(a);
+ struct btrfs_trans_handle *trans;
+ u64 features, set, clear;
+ unsigned long val;
+ int ret;
+
+ fs_info = to_fs_info(kobj);
+ if (!fs_info)
+ return -EPERM;
+
+ ret = kstrtoul(skip_spaces(buf), 0, &val);
+ if (ret)
+ return ret;
+
+ if (fa->feature_set == FEAT_COMPAT) {
+ set = BTRFS_FEATURE_COMPAT_SAFE_SET;
+ clear = BTRFS_FEATURE_COMPAT_SAFE_CLEAR;
+ } else if (fa->feature_set == FEAT_COMPAT_RO) {
+ set = BTRFS_FEATURE_COMPAT_RO_SAFE_SET;
+ clear = BTRFS_FEATURE_COMPAT_RO_SAFE_CLEAR;
+ } else {
+ set = BTRFS_FEATURE_INCOMPAT_SAFE_SET;
+ clear = BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR;
+ }
+
+ features = get_features(fs_info, fa->feature_set);
+
+ /* Nothing to do */
+ if ((val && (features & fa->feature_bit)) ||
+ (!val && !(features & fa->feature_bit)))
+ return count;
+
+ if ((val && !(set & fa->feature_bit)) ||
+ (!val && !(clear & fa->feature_bit))) {
+ btrfs_info(fs_info,
+ "%sabling feature %s on mounted fs is not supported.",
+ val ? "En" : "Dis", fa->kobj_attr.attr.name);
+ return -EPERM;
+ }
+
+ btrfs_info(fs_info, "%s %s feature flag",
+ val ? "Setting" : "Clearing", fa->kobj_attr.attr.name);
+
+ trans = btrfs_start_transaction(fs_info->fs_root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ spin_lock(&fs_info->super_lock);
+ features = get_features(fs_info, fa->feature_set);
+ if (val)
+ features |= fa->feature_bit;
+ else
+ features &= ~fa->feature_bit;
+ set_features(fs_info, fa->feature_set, features);
+ spin_unlock(&fs_info->super_lock);
+
+ ret = btrfs_commit_transaction(trans, fs_info->fs_root);
+ if (ret)
+ return ret;
+
+ return count;
+}
+
+static umode_t btrfs_feature_visible(struct kobject *kobj,
+ struct attribute *attr, int unused)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ umode_t mode = attr->mode;
+
+ if (fs_info) {
+ struct btrfs_feature_attr *fa;
+ u64 features;
+
+ fa = attr_to_btrfs_feature_attr(attr);
+ features = get_features(fs_info, fa->feature_set);
+
+ if (can_modify_feature(fa))
+ mode |= S_IWUSR;
+ else if (!(features & fa->feature_bit))
+ mode = 0;
+ }
+
+ return mode;
+}
+
+BTRFS_FEAT_ATTR_INCOMPAT(mixed_backref, MIXED_BACKREF);
+BTRFS_FEAT_ATTR_INCOMPAT(default_subvol, DEFAULT_SUBVOL);
+BTRFS_FEAT_ATTR_INCOMPAT(mixed_groups, MIXED_GROUPS);
+BTRFS_FEAT_ATTR_INCOMPAT(compress_lzo, COMPRESS_LZO);
+BTRFS_FEAT_ATTR_INCOMPAT(big_metadata, BIG_METADATA);
+BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF);
+BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56);
+BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA);
+BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES);
+
+static struct attribute *btrfs_supported_feature_attrs[] = {
+ BTRFS_FEAT_ATTR_PTR(mixed_backref),
+ BTRFS_FEAT_ATTR_PTR(default_subvol),
+ BTRFS_FEAT_ATTR_PTR(mixed_groups),
+ BTRFS_FEAT_ATTR_PTR(compress_lzo),
+ BTRFS_FEAT_ATTR_PTR(big_metadata),
+ BTRFS_FEAT_ATTR_PTR(extended_iref),
+ BTRFS_FEAT_ATTR_PTR(raid56),
+ BTRFS_FEAT_ATTR_PTR(skinny_metadata),
+ BTRFS_FEAT_ATTR_PTR(no_holes),
+ NULL
+};
+
+static const struct attribute_group btrfs_feature_attr_group = {
+ .name = "features",
+ .is_visible = btrfs_feature_visible,
+ .attrs = btrfs_supported_feature_attrs,
+};
+
+static ssize_t btrfs_show_u64(u64 *value_ptr, spinlock_t *lock, char *buf)
+{
+ u64 val;
+ if (lock)
+ spin_lock(lock);
+ val = *value_ptr;
+ if (lock)
+ spin_unlock(lock);
+ return snprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
+static ssize_t global_rsv_size_show(struct kobject *kobj,
+ struct kobj_attribute *ka, char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
+ struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
+ return btrfs_show_u64(&block_rsv->size, &block_rsv->lock, buf);
+}
+BTRFS_ATTR(global_rsv_size, 0444, global_rsv_size_show);
+
+static ssize_t global_rsv_reserved_show(struct kobject *kobj,
+ struct kobj_attribute *a, char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj->parent);
+ struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
+ return btrfs_show_u64(&block_rsv->reserved, &block_rsv->lock, buf);
+}
+BTRFS_ATTR(global_rsv_reserved, 0444, global_rsv_reserved_show);
+
+#define to_space_info(_kobj) container_of(_kobj, struct btrfs_space_info, kobj)
+
+static ssize_t raid_bytes_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf);
+BTRFS_RAID_ATTR(total_bytes, raid_bytes_show);
+BTRFS_RAID_ATTR(used_bytes, raid_bytes_show);
+
+static ssize_t raid_bytes_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+
+{
+ struct btrfs_space_info *sinfo = to_space_info(kobj->parent);
+ struct btrfs_block_group_cache *block_group;
+ int index = kobj - sinfo->block_group_kobjs;
+ u64 val = 0;
+
+ down_read(&sinfo->groups_sem);
+ list_for_each_entry(block_group, &sinfo->block_groups[index], list) {
+ if (&attr->attr == BTRFS_RAID_ATTR_PTR(total_bytes))
+ val += block_group->key.offset;
+ else
+ val += btrfs_block_group_used(&block_group->item);
+ }
+ up_read(&sinfo->groups_sem);
+ return snprintf(buf, PAGE_SIZE, "%llu\n", val);
+}
+
+static struct attribute *raid_attributes[] = {
+ BTRFS_RAID_ATTR_PTR(total_bytes),
+ BTRFS_RAID_ATTR_PTR(used_bytes),
+ NULL
+};
+
+static void release_raid_kobj(struct kobject *kobj)
+{
+ kobject_put(kobj->parent);
+}
+
+struct kobj_type btrfs_raid_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .release = release_raid_kobj,
+ .default_attrs = raid_attributes,
+};
+
+#define SPACE_INFO_ATTR(field) \
+static ssize_t btrfs_space_info_show_##field(struct kobject *kobj, \
+ struct kobj_attribute *a, \
+ char *buf) \
+{ \
+ struct btrfs_space_info *sinfo = to_space_info(kobj); \
+ return btrfs_show_u64(&sinfo->field, &sinfo->lock, buf); \
+} \
+BTRFS_ATTR(field, 0444, btrfs_space_info_show_##field)
+
+static ssize_t btrfs_space_info_show_total_bytes_pinned(struct kobject *kobj,
+ struct kobj_attribute *a,
+ char *buf)
+{
+ struct btrfs_space_info *sinfo = to_space_info(kobj);
+ s64 val = percpu_counter_sum(&sinfo->total_bytes_pinned);
+ return snprintf(buf, PAGE_SIZE, "%lld\n", val);
+}
+
+SPACE_INFO_ATTR(flags);
+SPACE_INFO_ATTR(total_bytes);
+SPACE_INFO_ATTR(bytes_used);
+SPACE_INFO_ATTR(bytes_pinned);
+SPACE_INFO_ATTR(bytes_reserved);
+SPACE_INFO_ATTR(bytes_may_use);
+SPACE_INFO_ATTR(disk_used);
+SPACE_INFO_ATTR(disk_total);
+BTRFS_ATTR(total_bytes_pinned, 0444, btrfs_space_info_show_total_bytes_pinned);
+
+static struct attribute *space_info_attrs[] = {
+ BTRFS_ATTR_PTR(flags),
+ BTRFS_ATTR_PTR(total_bytes),
+ BTRFS_ATTR_PTR(bytes_used),
+ BTRFS_ATTR_PTR(bytes_pinned),
+ BTRFS_ATTR_PTR(bytes_reserved),
+ BTRFS_ATTR_PTR(bytes_may_use),
+ BTRFS_ATTR_PTR(disk_used),
+ BTRFS_ATTR_PTR(disk_total),
+ BTRFS_ATTR_PTR(total_bytes_pinned),
+ NULL,
+};
+
+static void space_info_release(struct kobject *kobj)
+{
+ struct btrfs_space_info *sinfo = to_space_info(kobj);
+ percpu_counter_destroy(&sinfo->total_bytes_pinned);
+ kfree(sinfo);
+}
+
+struct kobj_type space_info_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .release = space_info_release,
+ .default_attrs = space_info_attrs,
+};
+
+static const struct attribute *allocation_attrs[] = {
+ BTRFS_ATTR_PTR(global_rsv_reserved),
+ BTRFS_ATTR_PTR(global_rsv_size),
+ NULL,
+};
+
+static ssize_t btrfs_label_show(struct kobject *kobj,
+ struct kobj_attribute *a, char *buf)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ return snprintf(buf, PAGE_SIZE, "%s\n", fs_info->super_copy->label);
+}
+
+static ssize_t btrfs_label_store(struct kobject *kobj,
+ struct kobj_attribute *a,
+ const char *buf, size_t len)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = fs_info->fs_root;
+ int ret;
+
+ if (len >= BTRFS_LABEL_SIZE) {
+ pr_err("BTRFS: unable to set label with more than %d bytes\n",
+ BTRFS_LABEL_SIZE - 1);
+ return -EINVAL;
+ }
+
+ trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ spin_lock(&root->fs_info->super_lock);
+ strcpy(fs_info->super_copy->label, buf);
+ spin_unlock(&root->fs_info->super_lock);
+ ret = btrfs_commit_transaction(trans, root);
+
+ if (!ret)
+ return len;
+
+ return ret;
+}
+BTRFS_ATTR_RW(label, 0644, btrfs_label_show, btrfs_label_store);
+
+static struct attribute *btrfs_attrs[] = {
+ BTRFS_ATTR_PTR(label),
+ NULL,
+};
+
+static void btrfs_release_super_kobj(struct kobject *kobj)
+{
+ struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+ complete(&fs_info->kobj_unregister);
+}
+
+static struct kobj_type btrfs_ktype = {
+ .sysfs_ops = &kobj_sysfs_ops,
+ .release = btrfs_release_super_kobj,
+ .default_attrs = btrfs_attrs,
+};
+
+static inline struct btrfs_fs_info *to_fs_info(struct kobject *kobj)
+{
+ if (kobj->ktype != &btrfs_ktype)
+ return NULL;
+ return container_of(kobj, struct btrfs_fs_info, super_kobj);
+}
+
+#define NUM_FEATURE_BITS 64
+static char btrfs_unknown_feature_names[3][NUM_FEATURE_BITS][13];
+static struct btrfs_feature_attr btrfs_feature_attrs[3][NUM_FEATURE_BITS];
+
+static u64 supported_feature_masks[3] = {
+ [FEAT_COMPAT] = BTRFS_FEATURE_COMPAT_SUPP,
+ [FEAT_COMPAT_RO] = BTRFS_FEATURE_COMPAT_RO_SUPP,
+ [FEAT_INCOMPAT] = BTRFS_FEATURE_INCOMPAT_SUPP,
+};
+
+static int addrm_unknown_feature_attrs(struct btrfs_fs_info *fs_info, bool add)
+{
+ int set;
+
+ for (set = 0; set < FEAT_MAX; set++) {
+ int i;
+ struct attribute *attrs[2];
+ struct attribute_group agroup = {
+ .name = "features",
+ .attrs = attrs,
+ };
+ u64 features = get_features(fs_info, set);
+ features &= ~supported_feature_masks[set];
+
+ if (!features)
+ continue;
+
+ attrs[1] = NULL;
+ for (i = 0; i < NUM_FEATURE_BITS; i++) {
+ struct btrfs_feature_attr *fa;
+
+ if (!(features & (1ULL << i)))
+ continue;
+
+ fa = &btrfs_feature_attrs[set][i];
+ attrs[0] = &fa->kobj_attr.attr;
+ if (add) {
+ int ret;
+ ret = sysfs_merge_group(&fs_info->super_kobj,
+ &agroup);
+ if (ret)
+ return ret;
+ } else
+ sysfs_unmerge_group(&fs_info->super_kobj,
+ &agroup);
+ }
+
+ }
+ return 0;
+}
+
+static void __btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info)
+{
+ kobject_del(&fs_info->super_kobj);
+ kobject_put(&fs_info->super_kobj);
+ wait_for_completion(&fs_info->kobj_unregister);
+}
+
+void btrfs_sysfs_remove_one(struct btrfs_fs_info *fs_info)
+{
+ if (fs_info->space_info_kobj) {
+ sysfs_remove_files(fs_info->space_info_kobj, allocation_attrs);
+ kobject_del(fs_info->space_info_kobj);
+ kobject_put(fs_info->space_info_kobj);
+ }
+ kobject_del(fs_info->device_dir_kobj);
+ kobject_put(fs_info->device_dir_kobj);
+ addrm_unknown_feature_attrs(fs_info, false);
+ sysfs_remove_group(&fs_info->super_kobj, &btrfs_feature_attr_group);
+ __btrfs_sysfs_remove_one(fs_info);
+}
+
+const char * const btrfs_feature_set_names[3] = {
+ [FEAT_COMPAT] = "compat",
+ [FEAT_COMPAT_RO] = "compat_ro",
+ [FEAT_INCOMPAT] = "incompat",
+};
+
+char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags)
+{
+ size_t bufsize = 4096; /* safe max, 64 names * 64 bytes */
+ int len = 0;
+ int i;
+ char *str;
+
+ str = kmalloc(bufsize, GFP_KERNEL);
+ if (!str)
+ return str;
+
+ for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) {
+ const char *name;
+
+ if (!(flags & (1ULL << i)))
+ continue;
+
+ name = btrfs_feature_attrs[set][i].kobj_attr.attr.name;
+ len += snprintf(str + len, bufsize - len, "%s%s",
+ len ? "," : "", name);
+ }
+
+ return str;
+}
+
+static void init_feature_attrs(void)
+{
+ struct btrfs_feature_attr *fa;
+ int set, i;
+
+ BUILD_BUG_ON(ARRAY_SIZE(btrfs_unknown_feature_names) !=
+ ARRAY_SIZE(btrfs_feature_attrs));
+ BUILD_BUG_ON(ARRAY_SIZE(btrfs_unknown_feature_names[0]) !=
+ ARRAY_SIZE(btrfs_feature_attrs[0]));
+
+ memset(btrfs_feature_attrs, 0, sizeof(btrfs_feature_attrs));
+ memset(btrfs_unknown_feature_names, 0,
+ sizeof(btrfs_unknown_feature_names));
+
+ for (i = 0; btrfs_supported_feature_attrs[i]; i++) {
+ struct btrfs_feature_attr *sfa;
+ struct attribute *a = btrfs_supported_feature_attrs[i];
+ int bit;
+ sfa = attr_to_btrfs_feature_attr(a);
+ bit = ilog2(sfa->feature_bit);
+ fa = &btrfs_feature_attrs[sfa->feature_set][bit];
+
+ fa->kobj_attr.attr.name = sfa->kobj_attr.attr.name;
+ }
+
+ for (set = 0; set < FEAT_MAX; set++) {
+ for (i = 0; i < ARRAY_SIZE(btrfs_feature_attrs[set]); i++) {
+ char *name = btrfs_unknown_feature_names[set][i];
+ fa = &btrfs_feature_attrs[set][i];
+
+ if (fa->kobj_attr.attr.name)
+ continue;
+
+ snprintf(name, 13, "%s:%u",
+ btrfs_feature_set_names[set], i);
+
+ fa->kobj_attr.attr.name = name;
+ fa->kobj_attr.attr.mode = S_IRUGO;
+ fa->feature_set = set;
+ fa->feature_bit = 1ULL << i;
+ }
+ }
+}
+
+static int add_device_membership(struct btrfs_fs_info *fs_info)
+{
+ int error = 0;
+ struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+ struct btrfs_device *dev;
+
+ fs_info->device_dir_kobj = kobject_create_and_add("devices",
+ &fs_info->super_kobj);
+ if (!fs_info->device_dir_kobj)
+ return -ENOMEM;
+
+ list_for_each_entry(dev, &fs_devices->devices, dev_list) {
+ struct hd_struct *disk;
+ struct kobject *disk_kobj;
+
+ if (!dev->bdev)
+ continue;
+
+ disk = dev->bdev->bd_part;
+ disk_kobj = &part_to_dev(disk)->kobj;
+
+ error = sysfs_create_link(fs_info->device_dir_kobj,
+ disk_kobj, disk_kobj->name);
+ if (error)
+ break;
+ }
+
+ return error;
+}
/* /sys/fs/btrfs/ entry */
static struct kset *btrfs_kset;
+int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
+{
+ int error;
+
+ init_completion(&fs_info->kobj_unregister);
+ fs_info->super_kobj.kset = btrfs_kset;
+ error = kobject_init_and_add(&fs_info->super_kobj, &btrfs_ktype, NULL,
+ "%pU", fs_info->fsid);
+ if (error)
+ return error;
+
+ error = sysfs_create_group(&fs_info->super_kobj,
+ &btrfs_feature_attr_group);
+ if (error) {
+ __btrfs_sysfs_remove_one(fs_info);
+ return error;
+ }
+
+ error = addrm_unknown_feature_attrs(fs_info, true);
+ if (error)
+ goto failure;
+
+ error = add_device_membership(fs_info);
+ if (error)
+ goto failure;
+
+ fs_info->space_info_kobj = kobject_create_and_add("allocation",
+ &fs_info->super_kobj);
+ if (!fs_info->space_info_kobj) {
+ error = -ENOMEM;
+ goto failure;
+ }
+
+ error = sysfs_create_files(fs_info->space_info_kobj, allocation_attrs);
+ if (error)
+ goto failure;
+
+ return 0;
+failure:
+ btrfs_sysfs_remove_one(fs_info);
+ return error;
+}
+
int btrfs_init_sysfs(void)
{
+ int ret;
btrfs_kset = kset_create_and_add("btrfs", NULL, fs_kobj);
if (!btrfs_kset)
return -ENOMEM;
+
+ init_feature_attrs();
+
+ ret = sysfs_create_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
+ if (ret) {
+ kset_unregister(btrfs_kset);
+ return ret;
+ }
+
return 0;
}
void btrfs_exit_sysfs(void)
{
+ sysfs_remove_group(&btrfs_kset->kobj, &btrfs_feature_attr_group);
kset_unregister(btrfs_kset);
}
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
new file mode 100644
index 000000000000..f3cea3710d44
--- /dev/null
+++ b/fs/btrfs/sysfs.h
@@ -0,0 +1,64 @@
+#ifndef _BTRFS_SYSFS_H_
+#define _BTRFS_SYSFS_H_
+
+enum btrfs_feature_set {
+ FEAT_COMPAT,
+ FEAT_COMPAT_RO,
+ FEAT_INCOMPAT,
+ FEAT_MAX
+};
+
+#define __INIT_KOBJ_ATTR(_name, _mode, _show, _store) \
+{ \
+ .attr = { .name = __stringify(_name), .mode = _mode }, \
+ .show = _show, \
+ .store = _store, \
+}
+
+#define BTRFS_ATTR_RW(_name, _mode, _show, _store) \
+static struct kobj_attribute btrfs_attr_##_name = \
+ __INIT_KOBJ_ATTR(_name, _mode, _show, _store)
+#define BTRFS_ATTR(_name, _mode, _show) \
+ BTRFS_ATTR_RW(_name, _mode, _show, NULL)
+#define BTRFS_ATTR_PTR(_name) (&btrfs_attr_##_name.attr)
+
+#define BTRFS_RAID_ATTR(_name, _show) \
+static struct kobj_attribute btrfs_raid_attr_##_name = \
+ __INIT_KOBJ_ATTR(_name, 0444, _show, NULL)
+#define BTRFS_RAID_ATTR_PTR(_name) (&btrfs_raid_attr_##_name.attr)
+
+
+struct btrfs_feature_attr {
+ struct kobj_attribute kobj_attr;
+ enum btrfs_feature_set feature_set;
+ u64 feature_bit;
+};
+
+#define BTRFS_FEAT_ATTR(_name, _feature_set, _prefix, _feature_bit) \
+static struct btrfs_feature_attr btrfs_attr_##_name = { \
+ .kobj_attr = __INIT_KOBJ_ATTR(_name, S_IRUGO, \
+ btrfs_feature_attr_show, \
+ btrfs_feature_attr_store), \
+ .feature_set = _feature_set, \
+ .feature_bit = _prefix ##_## _feature_bit, \
+}
+#define BTRFS_FEAT_ATTR_PTR(_name) (&btrfs_attr_##_name.kobj_attr.attr)
+
+#define BTRFS_FEAT_ATTR_COMPAT(name, feature) \
+ BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature)
+#define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \
+ BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature)
+#define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \
+ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature)
+
+/* convert from attribute */
+#define to_btrfs_feature_attr(a) \
+ container_of(a, struct btrfs_feature_attr, kobj_attr)
+#define attr_to_btrfs_attr(a) container_of(a, struct kobj_attribute, attr)
+#define attr_to_btrfs_feature_attr(a) \
+ to_btrfs_feature_attr(attr_to_btrfs_attr(a))
+char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
+extern const char * const btrfs_feature_set_names[3];
+extern struct kobj_type space_info_ktype;
+extern struct kobj_type btrfs_raid_ktype;
+#endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index b353bc806ca0..312560a9123d 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -21,7 +21,7 @@
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-#define test_msg(fmt, ...) pr_info("btrfs: selftest: " fmt, ##__VA_ARGS__)
+#define test_msg(fmt, ...) pr_info("BTRFS: selftest: " fmt, ##__VA_ARGS__)
int btrfs_test_free_space_cache(void);
int btrfs_test_extent_buffer_operations(void);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c6a872a8a468..34cd83184c4a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -62,7 +62,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
WARN_ON(atomic_read(&transaction->use_count) == 0);
if (atomic_dec_and_test(&transaction->use_count)) {
BUG_ON(!list_empty(&transaction->list));
- WARN_ON(transaction->delayed_refs.root.rb_node);
+ WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root));
while (!list_empty(&transaction->pending_chunks)) {
struct extent_map *em;
@@ -183,8 +183,8 @@ loop:
atomic_set(&cur_trans->use_count, 2);
cur_trans->start_time = get_seconds();
- cur_trans->delayed_refs.root = RB_ROOT;
- cur_trans->delayed_refs.num_entries = 0;
+ cur_trans->delayed_refs.href_root = RB_ROOT;
+ atomic_set(&cur_trans->delayed_refs.num_entries, 0);
cur_trans->delayed_refs.num_heads_ready = 0;
cur_trans->delayed_refs.num_heads = 0;
cur_trans->delayed_refs.flushing = 0;
@@ -196,17 +196,14 @@ loop:
*/
smp_mb();
if (!list_empty(&fs_info->tree_mod_seq_list))
- WARN(1, KERN_ERR "btrfs: tree_mod_seq_list not empty when "
+ WARN(1, KERN_ERR "BTRFS: tree_mod_seq_list not empty when "
"creating a fresh transaction\n");
if (!RB_EMPTY_ROOT(&fs_info->tree_mod_log))
- WARN(1, KERN_ERR "btrfs: tree_mod_log rb tree not empty when "
+ WARN(1, KERN_ERR "BTRFS: tree_mod_log rb tree not empty when "
"creating a fresh transaction\n");
atomic64_set(&fs_info->tree_mod_seq, 0);
spin_lock_init(&cur_trans->delayed_refs.lock);
- atomic_set(&cur_trans->delayed_refs.procs_running_refs, 0);
- atomic_set(&cur_trans->delayed_refs.ref_seq, 0);
- init_waitqueue_head(&cur_trans->delayed_refs.wait);
INIT_LIST_HEAD(&cur_trans->pending_snapshots);
INIT_LIST_HEAD(&cur_trans->ordered_operations);
@@ -472,6 +469,7 @@ again:
h->type = type;
h->allocating_chunk = false;
h->reloc_reserved = false;
+ h->sync = false;
INIT_LIST_HEAD(&h->qgroup_ref_list);
INIT_LIST_HEAD(&h->new_bgs);
@@ -647,7 +645,7 @@ static int should_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
if (root->fs_info->global_block_rsv.space_info->full &&
- btrfs_should_throttle_delayed_refs(trans, root))
+ btrfs_check_space_for_delayed_refs(trans, root))
return 1;
return !!btrfs_block_rsv_check(root, &root->fs_info->global_block_rsv, 5);
@@ -711,8 +709,8 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
btrfs_create_pending_block_groups(trans, root);
trans->delayed_ref_updates = 0;
- if (btrfs_should_throttle_delayed_refs(trans, root)) {
- cur = max_t(unsigned long, cur, 1);
+ if (!trans->sync && btrfs_should_throttle_delayed_refs(trans, root)) {
+ cur = max_t(unsigned long, cur, 32);
trans->delayed_ref_updates = 0;
btrfs_run_delayed_refs(trans, root, cur);
}
@@ -788,12 +786,6 @@ int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
return __btrfs_end_transaction(trans, root, 1);
}
-int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
-{
- return __btrfs_end_transaction(trans, root, 1);
-}
-
/*
* when btree blocks are allocated, they have some corresponding bits set for
* them in one of two extent_io trees. This is used to make sure all of
@@ -1105,7 +1097,7 @@ int btrfs_defrag_root(struct btrfs_root *root)
break;
if (btrfs_defrag_cancelled(root->fs_info)) {
- printk(KERN_DEBUG "btrfs: defrag_root cancelled\n");
+ pr_debug("BTRFS: defrag_root cancelled\n");
ret = -EAGAIN;
break;
}
@@ -1746,6 +1738,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
goto cleanup_transaction;
btrfs_wait_delalloc_flush(root->fs_info);
+
+ btrfs_scrub_pause(root);
/*
* Ok now we need to make sure to block out any other joins while we
* commit the transaction. We could have started a join before setting
@@ -1810,7 +1804,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
WARN_ON(cur_trans != trans->transaction);
- btrfs_scrub_pause(root);
/* btrfs_commit_tree_roots is responsible for getting the
* various roots consistent with each other. Every pointer
* in the tree of tree roots has to point to the most up to date
@@ -1833,6 +1826,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
goto cleanup_transaction;
}
+ /*
+ * Since the transaction is done, we should set the inode map cache flag
+ * before any other comming transaction.
+ */
+ if (btrfs_test_opt(root, CHANGE_INODE_CACHE))
+ btrfs_set_opt(root->fs_info->mount_opt, INODE_MAP_CACHE);
+ else
+ btrfs_clear_opt(root->fs_info->mount_opt, INODE_MAP_CACHE);
+
/* commit_fs_roots gets rid of all the tree log roots, it is now
* safe to free the root of tree log roots
*/
@@ -1975,10 +1977,23 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
}
root = list_first_entry(&fs_info->dead_roots,
struct btrfs_root, root_list);
+ /*
+ * Make sure root is not involved in send,
+ * if we fail with first root, we return
+ * directly rather than continue.
+ */
+ spin_lock(&root->root_item_lock);
+ if (root->send_in_progress) {
+ spin_unlock(&fs_info->trans_lock);
+ spin_unlock(&root->root_item_lock);
+ return 0;
+ }
+ spin_unlock(&root->root_item_lock);
+
list_del_init(&root->root_list);
spin_unlock(&fs_info->trans_lock);
- pr_debug("btrfs: cleaner removing %llu\n", root->objectid);
+ pr_debug("BTRFS: cleaner removing %llu\n", root->objectid);
btrfs_kill_all_delayed_nodes(root);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 7657d115067d..6ac037e9f9f0 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -93,6 +93,7 @@ struct btrfs_trans_handle {
short adding_csums;
bool allocating_chunk;
bool reloc_reserved;
+ bool sync;
unsigned int type;
/*
* this root is only needed to validate that the root passed to
@@ -154,8 +155,6 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
int wait_for_unblock);
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
-int btrfs_end_transaction_dmeta(struct btrfs_trans_handle *trans,
- struct btrfs_root *root);
int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
void btrfs_throttle(struct btrfs_root *root);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9f7fc51ca334..39d83da03e03 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -570,7 +570,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
nbytes = 0;
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
- size = btrfs_file_extent_inline_len(eb, item);
+ size = btrfs_file_extent_inline_len(eb, slot, item);
nbytes = btrfs_file_extent_ram_bytes(eb, item);
extent_end = ALIGN(start + size, root->sectorsize);
} else {
@@ -1238,7 +1238,8 @@ static int insert_orphan_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 offset)
{
int ret;
- ret = btrfs_find_orphan_item(root, offset);
+ ret = btrfs_find_item(root, NULL, BTRFS_ORPHAN_OBJECTID,
+ offset, BTRFS_ORPHAN_ITEM_KEY, NULL);
if (ret > 0)
ret = btrfs_insert_orphan_item(trans, root, offset);
return ret;
@@ -3194,7 +3195,7 @@ static int log_inode_item(struct btrfs_trans_handle *trans,
static noinline int copy_items(struct btrfs_trans_handle *trans,
struct inode *inode,
struct btrfs_path *dst_path,
- struct extent_buffer *src,
+ struct btrfs_path *src_path, u64 *last_extent,
int start_slot, int nr, int inode_only)
{
unsigned long src_offset;
@@ -3202,6 +3203,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
struct btrfs_root *log = BTRFS_I(inode)->root->log_root;
struct btrfs_file_extent_item *extent;
struct btrfs_inode_item *inode_item;
+ struct extent_buffer *src = src_path->nodes[0];
+ struct btrfs_key first_key, last_key, key;
int ret;
struct btrfs_key *ins_keys;
u32 *ins_sizes;
@@ -3209,6 +3212,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
int i;
struct list_head ordered_sums;
int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+ bool has_extents = false;
+ bool need_find_last_extent = (*last_extent == 0);
+ bool done = false;
INIT_LIST_HEAD(&ordered_sums);
@@ -3217,6 +3223,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
if (!ins_data)
return -ENOMEM;
+ first_key.objectid = (u64)-1;
+
ins_sizes = (u32 *)ins_data;
ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));
@@ -3237,6 +3245,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
src_offset = btrfs_item_ptr_offset(src, start_slot + i);
+ if ((i == (nr - 1)))
+ last_key = ins_keys[i];
+
if (ins_keys[i].type == BTRFS_INODE_ITEM_KEY) {
inode_item = btrfs_item_ptr(dst_path->nodes[0],
dst_path->slots[0],
@@ -3248,6 +3259,21 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
src_offset, ins_sizes[i]);
}
+ /*
+ * We set need_find_last_extent here in case we know we were
+ * processing other items and then walk into the first extent in
+ * the inode. If we don't hit an extent then nothing changes,
+ * we'll do the last search the next time around.
+ */
+ if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY) {
+ has_extents = true;
+ if (need_find_last_extent &&
+ first_key.objectid == (u64)-1)
+ first_key = ins_keys[i];
+ } else {
+ need_find_last_extent = false;
+ }
+
/* take a reference on file data extents so that truncates
* or deletes of this inode don't have to relog the inode
* again
@@ -3312,6 +3338,128 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
list_del(&sums->list);
kfree(sums);
}
+
+ if (!has_extents)
+ return ret;
+
+ /*
+ * Because we use btrfs_search_forward we could skip leaves that were
+ * not modified and then assume *last_extent is valid when it really
+ * isn't. So back up to the previous leaf and read the end of the last
+ * extent before we go and fill in holes.
+ */
+ if (need_find_last_extent) {
+ u64 len;
+
+ ret = btrfs_prev_leaf(BTRFS_I(inode)->root, src_path);
+ if (ret < 0)
+ return ret;
+ if (ret)
+ goto fill_holes;
+ if (src_path->slots[0])
+ src_path->slots[0]--;
+ src = src_path->nodes[0];
+ btrfs_item_key_to_cpu(src, &key, src_path->slots[0]);
+ if (key.objectid != btrfs_ino(inode) ||
+ key.type != BTRFS_EXTENT_DATA_KEY)
+ goto fill_holes;
+ extent = btrfs_item_ptr(src, src_path->slots[0],
+ struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(src, extent) ==
+ BTRFS_FILE_EXTENT_INLINE) {
+ len = btrfs_file_extent_inline_len(src,
+ src_path->slots[0],
+ extent);
+ *last_extent = ALIGN(key.offset + len,
+ log->sectorsize);
+ } else {
+ len = btrfs_file_extent_num_bytes(src, extent);
+ *last_extent = key.offset + len;
+ }
+ }
+fill_holes:
+ /* So we did prev_leaf, now we need to move to the next leaf, but a few
+ * things could have happened
+ *
+ * 1) A merge could have happened, so we could currently be on a leaf
+ * that holds what we were copying in the first place.
+ * 2) A split could have happened, and now not all of the items we want
+ * are on the same leaf.
+ *
+ * So we need to adjust how we search for holes, we need to drop the
+ * path and re-search for the first extent key we found, and then walk
+ * forward until we hit the last one we copied.
+ */
+ if (need_find_last_extent) {
+ /* btrfs_prev_leaf could return 1 without releasing the path */
+ btrfs_release_path(src_path);
+ ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &first_key,
+ src_path, 0, 0);
+ if (ret < 0)
+ return ret;
+ ASSERT(ret == 0);
+ src = src_path->nodes[0];
+ i = src_path->slots[0];
+ } else {
+ i = start_slot;
+ }
+
+ /*
+ * Ok so here we need to go through and fill in any holes we may have
+ * to make sure that holes are punched for those areas in case they had
+ * extents previously.
+ */
+ while (!done) {
+ u64 offset, len;
+ u64 extent_end;
+
+ if (i >= btrfs_header_nritems(src_path->nodes[0])) {
+ ret = btrfs_next_leaf(BTRFS_I(inode)->root, src_path);
+ if (ret < 0)
+ return ret;
+ ASSERT(ret == 0);
+ src = src_path->nodes[0];
+ i = 0;
+ }
+
+ btrfs_item_key_to_cpu(src, &key, i);
+ if (!btrfs_comp_cpu_keys(&key, &last_key))
+ done = true;
+ if (key.objectid != btrfs_ino(inode) ||
+ key.type != BTRFS_EXTENT_DATA_KEY) {
+ i++;
+ continue;
+ }
+ extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
+ if (btrfs_file_extent_type(src, extent) ==
+ BTRFS_FILE_EXTENT_INLINE) {
+ len = btrfs_file_extent_inline_len(src, i, extent);
+ extent_end = ALIGN(key.offset + len, log->sectorsize);
+ } else {
+ len = btrfs_file_extent_num_bytes(src, extent);
+ extent_end = key.offset + len;
+ }
+ i++;
+
+ if (*last_extent == key.offset) {
+ *last_extent = extent_end;
+ continue;
+ }
+ offset = *last_extent;
+ len = key.offset - *last_extent;
+ ret = btrfs_insert_file_extent(trans, log, btrfs_ino(inode),
+ offset, 0, 0, len, 0, len, 0,
+ 0, 0);
+ if (ret)
+ break;
+ *last_extent = offset + len;
+ }
+ /*
+ * Need to let the callers know we dropped the path so they should
+ * re-search.
+ */
+ if (!ret && need_find_last_extent)
+ ret = 1;
return ret;
}
@@ -3349,21 +3497,27 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
int ret;
int index = log->log_transid % 2;
bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
-
- ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
- em->start + em->len, NULL, 0);
- if (ret)
- return ret;
+ int extent_inserted = 0;
INIT_LIST_HEAD(&ordered_sums);
btrfs_init_map_token(&token);
- key.objectid = btrfs_ino(inode);
- key.type = BTRFS_EXTENT_DATA_KEY;
- key.offset = em->start;
- ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*fi));
+ ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
+ em->start + em->len, NULL, 0, 1,
+ sizeof(*fi), &extent_inserted);
if (ret)
return ret;
+
+ if (!extent_inserted) {
+ key.objectid = btrfs_ino(inode);
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = em->start;
+
+ ret = btrfs_insert_empty_item(trans, log, path, &key,
+ sizeof(*fi));
+ if (ret)
+ return ret;
+ }
leaf = path->nodes[0];
fi = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
@@ -3485,7 +3639,11 @@ again:
* start over after this.
*/
- wait_event(ordered->wait, ordered->csum_bytes_left == 0);
+ if (ordered->csum_bytes_left) {
+ btrfs_start_ordered_extent(inode, ordered, 0);
+ wait_event(ordered->wait,
+ ordered->csum_bytes_left == 0);
+ }
list_for_each_entry(sum, &ordered->list, list) {
ret = btrfs_csum_file_blocks(trans, log, sum);
@@ -3630,6 +3788,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct btrfs_key max_key;
struct btrfs_root *log = root->log_root;
struct extent_buffer *src = NULL;
+ u64 last_extent = 0;
int err = 0;
int ret;
int nritems;
@@ -3745,11 +3904,15 @@ again:
goto next_slot;
}
- ret = copy_items(trans, inode, dst_path, src, ins_start_slot,
- ins_nr, inode_only);
- if (ret) {
+ ret = copy_items(trans, inode, dst_path, path, &last_extent,
+ ins_start_slot, ins_nr, inode_only);
+ if (ret < 0) {
err = ret;
goto out_unlock;
+ } if (ret) {
+ ins_nr = 0;
+ btrfs_release_path(path);
+ continue;
}
ins_nr = 1;
ins_start_slot = path->slots[0];
@@ -3763,13 +3926,14 @@ next_slot:
goto again;
}
if (ins_nr) {
- ret = copy_items(trans, inode, dst_path, src,
- ins_start_slot,
+ ret = copy_items(trans, inode, dst_path, path,
+ &last_extent, ins_start_slot,
ins_nr, inode_only);
- if (ret) {
+ if (ret < 0) {
err = ret;
goto out_unlock;
}
+ ret = 0;
ins_nr = 0;
}
btrfs_release_path(path);
@@ -3784,12 +3948,13 @@ next_slot:
}
}
if (ins_nr) {
- ret = copy_items(trans, inode, dst_path, src, ins_start_slot,
- ins_nr, inode_only);
- if (ret) {
+ ret = copy_items(trans, inode, dst_path, path, &last_extent,
+ ins_start_slot, ins_nr, inode_only);
+ if (ret < 0) {
err = ret;
goto out_unlock;
}
+ ret = 0;
ins_nr = 0;
}
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index b0a523b2c60e..840a38b2778a 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -5,8 +5,8 @@
*/
#include <linux/slab.h>
-#include <linux/export.h>
#include "ulist.h"
+#include "ctree.h"
/*
* ulist is a generic data structure to hold a collection of unique u64
@@ -14,10 +14,6 @@
* enumerating it.
* It is possible to store an auxiliary value along with the key.
*
- * The implementation is preliminary and can probably be sped up
- * significantly. A first step would be to store the values in an rbtree
- * as soon as ULIST_SIZE is exceeded.
- *
* A sample usage for ulists is the enumeration of directed graphs without
* visiting a node twice. The pseudo-code could look like this:
*
@@ -50,12 +46,10 @@
*/
void ulist_init(struct ulist *ulist)
{
- ulist->nnodes = 0;
- ulist->nodes = ulist->int_nodes;
- ulist->nodes_alloced = ULIST_SIZE;
+ INIT_LIST_HEAD(&ulist->nodes);
ulist->root = RB_ROOT;
+ ulist->nnodes = 0;
}
-EXPORT_SYMBOL(ulist_init);
/**
* ulist_fini - free up additionally allocated memory for the ulist
@@ -64,18 +58,17 @@ EXPORT_SYMBOL(ulist_init);
* This is useful in cases where the base 'struct ulist' has been statically
* allocated.
*/
-void ulist_fini(struct ulist *ulist)
+static void ulist_fini(struct ulist *ulist)
{
- /*
- * The first ULIST_SIZE elements are stored inline in struct ulist.
- * Only if more elements are alocated they need to be freed.
- */
- if (ulist->nodes_alloced > ULIST_SIZE)
- kfree(ulist->nodes);
- ulist->nodes_alloced = 0; /* in case ulist_fini is called twice */
+ struct ulist_node *node;
+ struct ulist_node *next;
+
+ list_for_each_entry_safe(node, next, &ulist->nodes, list) {
+ kfree(node);
+ }
ulist->root = RB_ROOT;
+ INIT_LIST_HEAD(&ulist->nodes);
}
-EXPORT_SYMBOL(ulist_fini);
/**
* ulist_reinit - prepare a ulist for reuse
@@ -89,7 +82,6 @@ void ulist_reinit(struct ulist *ulist)
ulist_fini(ulist);
ulist_init(ulist);
}
-EXPORT_SYMBOL(ulist_reinit);
/**
* ulist_alloc - dynamically allocate a ulist
@@ -108,7 +100,6 @@ struct ulist *ulist_alloc(gfp_t gfp_mask)
return ulist;
}
-EXPORT_SYMBOL(ulist_alloc);
/**
* ulist_free - free dynamically allocated ulist
@@ -123,7 +114,6 @@ void ulist_free(struct ulist *ulist)
ulist_fini(ulist);
kfree(ulist);
}
-EXPORT_SYMBOL(ulist_free);
static struct ulist_node *ulist_rbtree_search(struct ulist *ulist, u64 val)
{
@@ -192,63 +182,32 @@ int ulist_add(struct ulist *ulist, u64 val, u64 aux, gfp_t gfp_mask)
int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
u64 *old_aux, gfp_t gfp_mask)
{
- int ret = 0;
- struct ulist_node *node = NULL;
+ int ret;
+ struct ulist_node *node;
+
node = ulist_rbtree_search(ulist, val);
if (node) {
if (old_aux)
*old_aux = node->aux;
return 0;
}
+ node = kmalloc(sizeof(*node), gfp_mask);
+ if (!node)
+ return -ENOMEM;
- if (ulist->nnodes >= ulist->nodes_alloced) {
- u64 new_alloced = ulist->nodes_alloced + 128;
- struct ulist_node *new_nodes;
- void *old = NULL;
- int i;
-
- for (i = 0; i < ulist->nnodes; i++)
- rb_erase(&ulist->nodes[i].rb_node, &ulist->root);
-
- /*
- * if nodes_alloced == ULIST_SIZE no memory has been allocated
- * yet, so pass NULL to krealloc
- */
- if (ulist->nodes_alloced > ULIST_SIZE)
- old = ulist->nodes;
+ node->val = val;
+ node->aux = aux;
+#ifdef CONFIG_BTRFS_DEBUG
+ node->seqnum = ulist->nnodes;
+#endif
- new_nodes = krealloc(old, sizeof(*new_nodes) * new_alloced,
- gfp_mask);
- if (!new_nodes)
- return -ENOMEM;
-
- if (!old)
- memcpy(new_nodes, ulist->int_nodes,
- sizeof(ulist->int_nodes));
-
- ulist->nodes = new_nodes;
- ulist->nodes_alloced = new_alloced;
-
- /*
- * krealloc actually uses memcpy, which does not copy rb_node
- * pointers, so we have to do it ourselves. Otherwise we may
- * be bitten by crashes.
- */
- for (i = 0; i < ulist->nnodes; i++) {
- ret = ulist_rbtree_insert(ulist, &ulist->nodes[i]);
- if (ret < 0)
- return ret;
- }
- }
- ulist->nodes[ulist->nnodes].val = val;
- ulist->nodes[ulist->nnodes].aux = aux;
- ret = ulist_rbtree_insert(ulist, &ulist->nodes[ulist->nnodes]);
- BUG_ON(ret);
- ++ulist->nnodes;
+ ret = ulist_rbtree_insert(ulist, node);
+ ASSERT(!ret);
+ list_add_tail(&node->list, &ulist->nodes);
+ ulist->nnodes++;
return 1;
}
-EXPORT_SYMBOL(ulist_add);
/**
* ulist_next - iterate ulist
@@ -268,11 +227,25 @@ EXPORT_SYMBOL(ulist_add);
*/
struct ulist_node *ulist_next(struct ulist *ulist, struct ulist_iterator *uiter)
{
- if (ulist->nnodes == 0)
+ struct ulist_node *node;
+
+ if (list_empty(&ulist->nodes))
return NULL;
- if (uiter->i < 0 || uiter->i >= ulist->nnodes)
+ if (uiter->cur_list && uiter->cur_list->next == &ulist->nodes)
return NULL;
-
- return &ulist->nodes[uiter->i++];
+ if (uiter->cur_list) {
+ uiter->cur_list = uiter->cur_list->next;
+ } else {
+ uiter->cur_list = ulist->nodes.next;
+#ifdef CONFIG_BTRFS_DEBUG
+ uiter->i = 0;
+#endif
+ }
+ node = list_entry(uiter->cur_list, struct ulist_node, list);
+#ifdef CONFIG_BTRFS_DEBUG
+ ASSERT(node->seqnum == uiter->i);
+ ASSERT(uiter->i >= 0 && uiter->i < ulist->nnodes);
+ uiter->i++;
+#endif
+ return node;
}
-EXPORT_SYMBOL(ulist_next);
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index fb36731074b5..7f78cbf5cf41 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -17,18 +17,12 @@
* enumerating it.
* It is possible to store an auxiliary value along with the key.
*
- * The implementation is preliminary and can probably be sped up
- * significantly. A first step would be to store the values in an rbtree
- * as soon as ULIST_SIZE is exceeded.
*/
-
-/*
- * number of elements statically allocated inside struct ulist
- */
-#define ULIST_SIZE 16
-
struct ulist_iterator {
+#ifdef CONFIG_BTRFS_DEBUG
int i;
+#endif
+ struct list_head *cur_list; /* hint to start search */
};
/*
@@ -37,6 +31,12 @@ struct ulist_iterator {
struct ulist_node {
u64 val; /* value to store */
u64 aux; /* auxiliary value saved along with the val */
+
+#ifdef CONFIG_BTRFS_DEBUG
+ int seqnum; /* sequence number this node is added */
+#endif
+
+ struct list_head list; /* used to link node */
struct rb_node rb_node; /* used to speed up search */
};
@@ -46,28 +46,11 @@ struct ulist {
*/
unsigned long nnodes;
- /*
- * number of nodes we already have room for
- */
- unsigned long nodes_alloced;
-
- /*
- * pointer to the array storing the elements. The first ULIST_SIZE
- * elements are stored inline. In this case the it points to int_nodes.
- * After exceeding ULIST_SIZE, dynamic memory is allocated.
- */
- struct ulist_node *nodes;
-
+ struct list_head nodes;
struct rb_root root;
-
- /*
- * inline storage space for the first ULIST_SIZE entries
- */
- struct ulist_node int_nodes[ULIST_SIZE];
};
void ulist_init(struct ulist *ulist);
-void ulist_fini(struct ulist *ulist);
void ulist_reinit(struct ulist *ulist);
struct ulist *ulist_alloc(gfp_t gfp_mask);
void ulist_free(struct ulist *ulist);
@@ -77,6 +60,6 @@ int ulist_add_merge(struct ulist *ulist, u64 val, u64 aux,
struct ulist_node *ulist_next(struct ulist *ulist,
struct ulist_iterator *uiter);
-#define ULIST_ITER_INIT(uiter) ((uiter)->i = 0)
+#define ULIST_ITER_INIT(uiter) ((uiter)->cur_list = NULL)
#endif
diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c
index fbda90004fe9..f6a4c03ee7d8 100644
--- a/fs/btrfs/uuid-tree.c
+++ b/fs/btrfs/uuid-tree.c
@@ -69,7 +69,7 @@ static int btrfs_uuid_tree_lookup(struct btrfs_root *uuid_root, u8 *uuid,
ret = -ENOENT;
if (!IS_ALIGNED(item_size, sizeof(u64))) {
- pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ btrfs_warn(uuid_root->fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
goto out;
}
@@ -137,7 +137,8 @@ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans,
offset = btrfs_item_ptr_offset(eb, slot);
offset += btrfs_item_size_nr(eb, slot) - sizeof(subid_le);
} else if (ret < 0) {
- pr_warn("btrfs: insert uuid item failed %d (0x%016llx, 0x%016llx) type %u!\n",
+ btrfs_warn(uuid_root->fs_info, "insert uuid item failed %d "
+ "(0x%016llx, 0x%016llx) type %u!",
ret, (unsigned long long)key.objectid,
(unsigned long long)key.offset, type);
goto out;
@@ -183,7 +184,7 @@ int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
ret = btrfs_search_slot(trans, uuid_root, &key, path, -1, 1);
if (ret < 0) {
- pr_warn("btrfs: error %d while searching for uuid item!\n",
+ btrfs_warn(uuid_root->fs_info, "error %d while searching for uuid item!",
ret);
goto out;
}
@@ -197,7 +198,7 @@ int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans,
offset = btrfs_item_ptr_offset(eb, slot);
item_size = btrfs_item_size_nr(eb, slot);
if (!IS_ALIGNED(item_size, sizeof(u64))) {
- pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ btrfs_warn(uuid_root->fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
ret = -ENOENT;
goto out;
@@ -299,7 +300,7 @@ again_search_slot:
offset = btrfs_item_ptr_offset(leaf, slot);
item_size = btrfs_item_size_nr(leaf, slot);
if (!IS_ALIGNED(item_size, sizeof(u64))) {
- pr_warn("btrfs: uuid item with illegal size %lu!\n",
+ btrfs_warn(fs_info, "uuid item with illegal size %lu!",
(unsigned long)item_size);
goto skip;
}
@@ -349,6 +350,6 @@ skip:
out:
btrfs_free_path(path);
if (ret)
- pr_warn("btrfs: btrfs_uuid_tree_iterate failed %d\n", ret);
+ btrfs_warn(fs_info, "btrfs_uuid_tree_iterate failed %d", ret);
return 0;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 92303f42baaa..bab0b84d8f80 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -125,7 +125,7 @@ static void btrfs_kobject_uevent(struct block_device *bdev,
ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action);
if (ret)
- pr_warn("Sending event '%d' to kobject: '%s' (%p): failed\n",
+ pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n",
action,
kobject_name(&disk_to_dev(bdev->bd_disk)->kobj),
&disk_to_dev(bdev->bd_disk)->kobj);
@@ -200,7 +200,7 @@ btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
if (IS_ERR(*bdev)) {
ret = PTR_ERR(*bdev);
- printk(KERN_INFO "btrfs: open %s failed\n", device_path);
+ printk(KERN_INFO "BTRFS: open %s failed\n", device_path);
goto error;
}
@@ -912,9 +912,9 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
if (disk_super->label[0]) {
if (disk_super->label[BTRFS_LABEL_SIZE - 1])
disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0';
- printk(KERN_INFO "btrfs: device label %s ", disk_super->label);
+ printk(KERN_INFO "BTRFS: device label %s ", disk_super->label);
} else {
- printk(KERN_INFO "btrfs: device fsid %pU ", disk_super->fsid);
+ printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid);
}
printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path);
@@ -1813,7 +1813,7 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_root *root,
}
if (!*device) {
- pr_err("btrfs: no missing device found\n");
+ btrfs_err(root->fs_info, "no missing device found");
return -ENOENT;
}
@@ -3052,7 +3052,7 @@ loop:
error:
btrfs_free_path(path);
if (enospc_errors) {
- printk(KERN_INFO "btrfs: %d enospc errors during balance\n",
+ btrfs_info(fs_info, "%d enospc errors during balance",
enospc_errors);
if (!ret)
ret = -ENOSPC;
@@ -3138,8 +3138,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if (!(bctl->flags & BTRFS_BALANCE_DATA) ||
!(bctl->flags & BTRFS_BALANCE_METADATA) ||
memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) {
- printk(KERN_ERR "btrfs: with mixed groups data and "
- "metadata balance options must be the same\n");
+ btrfs_err(fs_info, "with mixed groups data and "
+ "metadata balance options must be the same");
ret = -EINVAL;
goto out;
}
@@ -3165,8 +3165,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->data.target, 1) ||
(bctl->data.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "data profile %llu\n",
+ btrfs_err(fs_info, "unable to start balance with target "
+ "data profile %llu",
bctl->data.target);
ret = -EINVAL;
goto out;
@@ -3174,8 +3174,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->meta.target, 1) ||
(bctl->meta.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "metadata profile %llu\n",
+ btrfs_err(fs_info,
+ "unable to start balance with target metadata profile %llu",
bctl->meta.target);
ret = -EINVAL;
goto out;
@@ -3183,8 +3183,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(!alloc_profile_is_valid(bctl->sys.target, 1) ||
(bctl->sys.target & ~allowed))) {
- printk(KERN_ERR "btrfs: unable to start balance with target "
- "system profile %llu\n",
+ btrfs_err(fs_info,
+ "unable to start balance with target system profile %llu",
bctl->sys.target);
ret = -EINVAL;
goto out;
@@ -3193,7 +3193,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
/* allow dup'ed data chunks only in mixed mode */
if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) &&
(bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) {
- printk(KERN_ERR "btrfs: dup for data is not allowed\n");
+ btrfs_err(fs_info, "dup for data is not allowed");
ret = -EINVAL;
goto out;
}
@@ -3213,11 +3213,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
(fs_info->avail_metadata_alloc_bits & allowed) &&
!(bctl->meta.target & allowed))) {
if (bctl->flags & BTRFS_BALANCE_FORCE) {
- printk(KERN_INFO "btrfs: force reducing metadata "
- "integrity\n");
+ btrfs_info(fs_info, "force reducing metadata integrity");
} else {
- printk(KERN_ERR "btrfs: balance will reduce metadata "
- "integrity, use force if you want this\n");
+ btrfs_err(fs_info, "balance will reduce metadata "
+ "integrity, use force if you want this");
ret = -EINVAL;
goto out;
}
@@ -3303,7 +3302,7 @@ static int balance_kthread(void *data)
mutex_lock(&fs_info->balance_mutex);
if (fs_info->balance_ctl) {
- printk(KERN_INFO "btrfs: continuing balance\n");
+ btrfs_info(fs_info, "continuing balance");
ret = btrfs_balance(fs_info->balance_ctl, NULL);
}
@@ -3325,7 +3324,7 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
spin_unlock(&fs_info->balance_lock);
if (btrfs_test_opt(fs_info->tree_root, SKIP_BALANCE)) {
- printk(KERN_INFO "btrfs: force skipping balance\n");
+ btrfs_info(fs_info, "force skipping balance");
return 0;
}
@@ -3543,7 +3542,7 @@ update_tree:
BTRFS_UUID_KEY_SUBVOL,
key.objectid);
if (ret < 0) {
- pr_warn("btrfs: uuid_tree_add failed %d\n",
+ btrfs_warn(fs_info, "uuid_tree_add failed %d",
ret);
break;
}
@@ -3555,7 +3554,7 @@ update_tree:
BTRFS_UUID_KEY_RECEIVED_SUBVOL,
key.objectid);
if (ret < 0) {
- pr_warn("btrfs: uuid_tree_add failed %d\n",
+ btrfs_warn(fs_info, "uuid_tree_add failed %d",
ret);
break;
}
@@ -3590,7 +3589,7 @@ out:
if (trans && !IS_ERR(trans))
btrfs_end_transaction(trans, fs_info->uuid_root);
if (ret)
- pr_warn("btrfs: btrfs_uuid_scan_kthread failed %d\n", ret);
+ btrfs_warn(fs_info, "btrfs_uuid_scan_kthread failed %d", ret);
else
fs_info->update_uuid_tree_gen = 1;
up(&fs_info->uuid_tree_rescan_sem);
@@ -3654,7 +3653,7 @@ static int btrfs_uuid_rescan_kthread(void *data)
*/
ret = btrfs_uuid_tree_iterate(fs_info, btrfs_check_uuid_tree_entry);
if (ret < 0) {
- pr_warn("btrfs: iterating uuid_tree failed %d\n", ret);
+ btrfs_warn(fs_info, "iterating uuid_tree failed %d", ret);
up(&fs_info->uuid_tree_rescan_sem);
return ret;
}
@@ -3695,7 +3694,7 @@ int btrfs_create_uuid_tree(struct btrfs_fs_info *fs_info)
task = kthread_run(btrfs_uuid_scan_kthread, fs_info, "btrfs-uuid");
if (IS_ERR(task)) {
/* fs_info->update_uuid_tree_gen remains 0 in all error case */
- pr_warn("btrfs: failed to start uuid_scan task\n");
+ btrfs_warn(fs_info, "failed to start uuid_scan task");
up(&fs_info->uuid_tree_rescan_sem);
return PTR_ERR(task);
}
@@ -3711,7 +3710,7 @@ int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
if (IS_ERR(task)) {
/* fs_info->update_uuid_tree_gen remains 0 in all error case */
- pr_warn("btrfs: failed to start uuid_rescan task\n");
+ btrfs_warn(fs_info, "failed to start uuid_rescan task");
up(&fs_info->uuid_tree_rescan_sem);
return PTR_ERR(task);
}
@@ -4033,7 +4032,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
max_stripe_size = 32 * 1024 * 1024;
max_chunk_size = 2 * max_stripe_size;
} else {
- printk(KERN_ERR "btrfs: invalid chunk type 0x%llx requested\n",
+ btrfs_err(info, "invalid chunk type 0x%llx requested\n",
type);
BUG_ON(1);
}
@@ -4065,7 +4064,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
if (!device->writeable) {
WARN(1, KERN_ERR
- "btrfs: read-only device in alloc_list\n");
+ "BTRFS: read-only device in alloc_list\n");
continue;
}
@@ -5193,13 +5192,13 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree,
read_unlock(&em_tree->lock);
if (!em) {
- printk(KERN_ERR "btrfs: couldn't find em for chunk %Lu\n",
+ printk(KERN_ERR "BTRFS: couldn't find em for chunk %Lu\n",
chunk_start);
return -EIO;
}
if (em->start != chunk_start) {
- printk(KERN_ERR "btrfs: bad chunk start, em=%Lu, wanted=%Lu\n",
+ printk(KERN_ERR "BTRFS: bad chunk start, em=%Lu, wanted=%Lu\n",
em->start, chunk_start);
free_extent_map(em);
return -EIO;
@@ -5298,6 +5297,13 @@ static void btrfs_end_bio(struct bio *bio, int err)
bio_put(bio);
bio = bbio->orig_bio;
}
+
+ /*
+ * We have original bio now. So increment bi_remaining to
+ * account for it in endio
+ */
+ atomic_inc(&bio->bi_remaining);
+
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
@@ -5411,7 +5417,7 @@ static int bio_size_ok(struct block_device *bdev, struct bio *bio,
if (!q->merge_bvec_fn)
return 1;
- bvm.bi_size = bio->bi_size - prev->bv_len;
+ bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len;
if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len)
return 0;
return 1;
@@ -5426,7 +5432,7 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio,
bio->bi_private = bbio;
btrfs_io_bio(bio)->stripe_index = dev_nr;
bio->bi_end_io = btrfs_end_bio;
- bio->bi_sector = physical >> 9;
+ bio->bi_iter.bi_sector = physical >> 9;
#ifdef DEBUG
{
struct rcu_string *name;
@@ -5464,7 +5470,7 @@ again:
while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
bvec->bv_offset) < bvec->bv_len) {
- u64 len = bio->bi_size;
+ u64 len = bio->bi_iter.bi_size;
atomic_inc(&bbio->stripes_pending);
submit_stripe_bio(root, bbio, bio, physical, dev_nr,
@@ -5486,7 +5492,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
bio->bi_private = bbio->private;
bio->bi_end_io = bbio->end_io;
btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
- bio->bi_sector = logical >> 9;
+ bio->bi_iter.bi_sector = logical >> 9;
kfree(bbio);
bio_endio(bio, -EIO);
}
@@ -5497,7 +5503,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
{
struct btrfs_device *dev;
struct bio *first_bio = bio;
- u64 logical = (u64)bio->bi_sector << 9;
+ u64 logical = (u64)bio->bi_iter.bi_sector << 9;
u64 length = 0;
u64 map_length;
u64 *raid_map = NULL;
@@ -5506,7 +5512,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio,
int total_devs = 1;
struct btrfs_bio *bbio = NULL;
- length = bio->bi_size;
+ length = bio->bi_iter.bi_size;
map_length = length;
ret = __btrfs_map_block(root->fs_info, rw, logical, &map_length, &bbio,
@@ -6123,7 +6129,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
BUG_ON(!path);
ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "error %d while searching for dev_stats item for device %s!\n",
ret, rcu_str_deref(device->name));
goto out;
}
@@ -6133,7 +6140,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
/* need to delete old one and insert a new one */
ret = btrfs_del_item(trans, dev_root, path);
if (ret != 0) {
- printk_in_rcu(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "delete too small dev_stats item for device %s failed %d!\n",
rcu_str_deref(device->name), ret);
goto out;
}
@@ -6146,7 +6154,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
ret = btrfs_insert_empty_item(trans, dev_root, path,
&key, sizeof(*ptr));
if (ret < 0) {
- printk_in_rcu(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n",
+ printk_in_rcu(KERN_WARNING "BTRFS: "
+ "insert dev_stats item for device %s failed %d!\n",
rcu_str_deref(device->name), ret);
goto out;
}
@@ -6199,16 +6208,14 @@ static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev)
{
if (!dev->dev_stats_valid)
return;
- printk_ratelimited_in_rcu(KERN_ERR
- "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ printk_ratelimited_in_rcu(KERN_ERR "BTRFS: "
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS),
- btrfs_dev_stat_read(dev,
- BTRFS_DEV_STAT_CORRUPTION_ERRS),
- btrfs_dev_stat_read(dev,
- BTRFS_DEV_STAT_GENERATION_ERRS));
+ btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS),
+ btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS));
}
static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
@@ -6221,7 +6228,8 @@ static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev)
if (i == BTRFS_DEV_STAT_VALUES_MAX)
return; /* all values == 0, suppress message */
- printk_in_rcu(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
+ printk_in_rcu(KERN_INFO "BTRFS: "
+ "bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n",
rcu_str_deref(dev->name),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS),
btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS),
@@ -6242,12 +6250,10 @@ int btrfs_get_dev_stats(struct btrfs_root *root,
mutex_unlock(&fs_devices->device_list_mutex);
if (!dev) {
- printk(KERN_WARNING
- "btrfs: get dev_stats failed, device not found\n");
+ btrfs_warn(root->fs_info, "get dev_stats failed, device not found");
return -ENODEV;
} else if (!dev->dev_stats_valid) {
- printk(KERN_WARNING
- "btrfs: get dev_stats failed, not yet valid\n");
+ btrfs_warn(root->fs_info, "get dev_stats failed, not yet valid");
return -ENODEV;
} else if (stats->flags & BTRFS_DEV_STATS_RESET) {
for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) {
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 3d1c301c9260..ad8328d797ea 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -28,6 +28,7 @@
#include "transaction.h"
#include "xattr.h"
#include "disk-io.h"
+#include "props.h"
ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
@@ -332,7 +333,8 @@ static bool btrfs_is_valid_xattr(const char *name)
XATTR_SECURITY_PREFIX_LEN) ||
!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN) ||
!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) ||
- !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN);
+ !strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) ||
+ !strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN);
}
ssize_t btrfs_getxattr(struct dentry *dentry, const char *name,
@@ -374,6 +376,10 @@ int btrfs_setxattr(struct dentry *dentry, const char *name, const void *value,
if (!btrfs_is_valid_xattr(name))
return -EOPNOTSUPP;
+ if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
+ return btrfs_set_prop(dentry->d_inode, name,
+ value, size, flags);
+
if (size == 0)
value = ""; /* empty EA, do not remove */
@@ -403,6 +409,10 @@ int btrfs_removexattr(struct dentry *dentry, const char *name)
if (!btrfs_is_valid_xattr(name))
return -EOPNOTSUPP;
+ if (!strncmp(name, XATTR_BTRFS_PREFIX, XATTR_BTRFS_PREFIX_LEN))
+ return btrfs_set_prop(dentry->d_inode, name,
+ NULL, 0, XATTR_REPLACE);
+
return __btrfs_setxattr(NULL, dentry->d_inode, name, NULL, 0,
XATTR_REPLACE);
}
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 9acb846c3e7f..8e57191950cb 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -97,7 +97,7 @@ static int zlib_compress_pages(struct list_head *ws,
*total_in = 0;
if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) {
- printk(KERN_WARNING "btrfs: deflateInit failed\n");
+ printk(KERN_WARNING "BTRFS: deflateInit failed\n");
ret = -1;
goto out;
}
@@ -125,7 +125,7 @@ static int zlib_compress_pages(struct list_head *ws,
while (workspace->def_strm.total_in < len) {
ret = zlib_deflate(&workspace->def_strm, Z_SYNC_FLUSH);
if (ret != Z_OK) {
- printk(KERN_DEBUG "btrfs: deflate in loop returned %d\n",
+ printk(KERN_DEBUG "BTRFS: deflate in loop returned %d\n",
ret);
zlib_deflateEnd(&workspace->def_strm);
ret = -1;
@@ -252,7 +252,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
}
if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
- printk(KERN_WARNING "btrfs: inflateInit failed\n");
+ printk(KERN_WARNING "BTRFS: inflateInit failed\n");
return -1;
}
while (workspace->inf_strm.total_in < srclen) {
@@ -336,7 +336,7 @@ static int zlib_decompress(struct list_head *ws, unsigned char *data_in,
}
if (Z_OK != zlib_inflateInit2(&workspace->inf_strm, wbits)) {
- printk(KERN_WARNING "btrfs: inflateInit failed\n");
+ printk(KERN_WARNING "BTRFS: inflateInit failed\n");
return -1;
}
diff --git a/fs/buffer.c b/fs/buffer.c
index 6024877335ca..27265a8b43c1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -654,14 +654,16 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
static void __set_page_dirty(struct page *page,
struct address_space *mapping, int warn)
{
- spin_lock_irq(&mapping->tree_lock);
+ unsigned long flags;
+
+ spin_lock_irqsave(&mapping->tree_lock, flags);
if (page->mapping) { /* Race with truncate? */
WARN_ON_ONCE(warn && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
- spin_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
@@ -1312,7 +1314,7 @@ static void bh_lru_install(struct buffer_head *bh)
}
while (out < BH_LRU_SIZE)
bhs[out++] = NULL;
- memcpy(__this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
+ memcpy(this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
}
bh_lru_unlock();
@@ -2982,11 +2984,11 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
* let it through, and the IO layer will turn it into
* an EIO.
*/
- if (unlikely(bio->bi_sector >= maxsector))
+ if (unlikely(bio->bi_iter.bi_sector >= maxsector))
return;
- maxsector -= bio->bi_sector;
- bytes = bio->bi_size;
+ maxsector -= bio->bi_iter.bi_sector;
+ bytes = bio->bi_iter.bi_size;
if (likely((bytes >> 9) <= maxsector))
return;
@@ -2994,7 +2996,7 @@ static void guard_bh_eod(int rw, struct bio *bio, struct buffer_head *bh)
bytes = maxsector << 9;
/* Truncate the bio.. */
- bio->bi_size = bytes;
+ bio->bi_iter.bi_size = bytes;
bio->bi_io_vec[0].bv_len = bytes;
/* ..and clear the end of the buffer for reads */
@@ -3029,14 +3031,14 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
*/
bio = bio_alloc(GFP_NOIO, 1);
- bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
bio->bi_io_vec[0].bv_page = bh->b_page;
bio->bi_io_vec[0].bv_len = bh->b_size;
bio->bi_io_vec[0].bv_offset = bh_offset(bh);
bio->bi_vcnt = 1;
- bio->bi_size = bh->b_size;
+ bio->bi_iter.bi_size = bh->b_size;
bio->bi_end_io = end_bio_bh_io_sync;
bio->bi_private = bh;
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index f6911284c9bd..21887d63dad5 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -54,11 +54,6 @@ static inline struct posix_acl *ceph_get_cached_acl(struct inode *inode,
return acl;
}
-void ceph_forget_all_cached_acls(struct inode *inode)
-{
- forget_all_cached_acls(inode);
-}
-
struct posix_acl *ceph_get_acl(struct inode *inode, int type)
{
int size;
@@ -66,13 +61,6 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type)
char *value = NULL;
struct posix_acl *acl;
- if (!IS_POSIXACL(inode))
- return NULL;
-
- acl = ceph_get_cached_acl(inode, type);
- if (acl != ACL_NOT_CACHED)
- return acl;
-
switch (type) {
case ACL_TYPE_ACCESS:
name = POSIX_ACL_XATTR_ACCESS;
@@ -107,14 +95,14 @@ struct posix_acl *ceph_get_acl(struct inode *inode, int type)
return acl;
}
-static int ceph_set_acl(struct dentry *dentry, struct inode *inode,
- struct posix_acl *acl, int type)
+int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int ret = 0, size = 0;
const char *name = NULL;
char *value = NULL;
struct iattr newattrs;
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
+ struct dentry *dentry;
if (acl) {
ret = posix_acl_valid(acl);
@@ -158,30 +146,29 @@ static int ceph_set_acl(struct dentry *dentry, struct inode *inode,
goto out_free;
}
+ dentry = d_find_alias(inode);
if (new_mode != old_mode) {
newattrs.ia_mode = new_mode;
newattrs.ia_valid = ATTR_MODE;
ret = ceph_setattr(dentry, &newattrs);
if (ret)
- goto out_free;
+ goto out_dput;
}
- if (value)
- ret = __ceph_setxattr(dentry, name, value, size, 0);
- else
- ret = __ceph_removexattr(dentry, name);
-
+ ret = __ceph_setxattr(dentry, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_mode = old_mode;
newattrs.ia_valid = ATTR_MODE;
ceph_setattr(dentry, &newattrs);
}
- goto out_free;
+ goto out_dput;
}
ceph_set_cached_acl(inode, type, acl);
+out_dput:
+ dput(dentry);
out_free:
kfree(value);
out:
@@ -190,42 +177,24 @@ out:
int ceph_init_acl(struct dentry *dentry, struct inode *inode, struct inode *dir)
{
- struct posix_acl *acl = NULL;
- int ret = 0;
-
- if (!S_ISLNK(inode->i_mode)) {
- if (IS_POSIXACL(dir)) {
- acl = ceph_get_acl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(acl)) {
- ret = PTR_ERR(acl);
- goto out;
- }
- }
+ struct posix_acl *default_acl, *acl;
+ int error;
- if (!acl)
- inode->i_mode &= ~current_umask();
- }
+ error = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
+ if (error)
+ return error;
- if (IS_POSIXACL(dir) && acl) {
- if (S_ISDIR(inode->i_mode)) {
- ret = ceph_set_acl(dentry, inode, acl,
- ACL_TYPE_DEFAULT);
- if (ret)
- goto out_release;
- }
- ret = __posix_acl_create(&acl, GFP_NOFS, &inode->i_mode);
- if (ret < 0)
- goto out;
- else if (ret > 0)
- ret = ceph_set_acl(dentry, inode, acl, ACL_TYPE_ACCESS);
- else
- cache_no_acl(inode);
- } else {
+ if (!default_acl && !acl)
cache_no_acl(inode);
- }
-out_release:
- posix_acl_release(acl);
-out:
- return ret;
+ if (default_acl) {
+ error = ceph_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+ posix_acl_release(default_acl);
+ }
+ if (acl) {
+ if (!error)
+ error = ceph_set_acl(inode, acl, ACL_TYPE_ACCESS);
+ posix_acl_release(acl);
+ }
+ return error;
}
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 619616d585b0..45eda6d7a40c 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -100,6 +100,14 @@ static unsigned fpos_off(loff_t p)
return p & 0xffffffff;
}
+static int fpos_cmp(loff_t l, loff_t r)
+{
+ int v = ceph_frag_compare(fpos_frag(l), fpos_frag(r));
+ if (v)
+ return v;
+ return (int)(fpos_off(l) - fpos_off(r));
+}
+
/*
* When possible, we try to satisfy a readdir by peeking at the
* dcache. We make this work by carefully ordering dentries on
@@ -156,7 +164,7 @@ more:
if (!d_unhashed(dentry) && dentry->d_inode &&
ceph_snap(dentry->d_inode) != CEPH_SNAPDIR &&
ceph_ino(dentry->d_inode) != CEPH_INO_CEPH &&
- ctx->pos <= di->offset)
+ fpos_cmp(ctx->pos, di->offset) <= 0)
break;
dout(" skipping %p %.*s at %llu (%llu)%s%s\n", dentry,
dentry->d_name.len, dentry->d_name.name, di->offset,
@@ -695,9 +703,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
ceph_mdsc_put_request(req);
if (!err)
- err = ceph_init_acl(dentry, dentry->d_inode, dir);
-
- if (err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -735,7 +742,9 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
if (!err && !req->r_reply_info.head->is_dentry)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
- if (err)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -776,7 +785,9 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
err = ceph_handle_notrace_create(dir, dentry);
ceph_mdsc_put_request(req);
out:
- if (err < 0)
+ if (!err)
+ ceph_init_acl(dentry, dentry->d_inode, dir);
+ else
d_drop(dentry);
return err;
}
@@ -1303,6 +1314,7 @@ const struct inode_operations ceph_dir_iops = {
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
.get_acl = ceph_get_acl,
+ .set_acl = ceph_set_acl,
.mknod = ceph_mknod,
.symlink = ceph_symlink,
.mkdir = ceph_mkdir,
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index dfd2ce3419f8..09c7afe32e49 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -286,6 +286,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
} else {
dout("atomic_open finish_open on dn %p\n", dn);
if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
+ ceph_init_acl(dentry, dentry->d_inode, dir);
*opened |= FILE_CREATED;
}
err = finish_open(file, dentry, ceph_open, opened);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 8b8b506636cc..32d519d8a2e2 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -97,6 +97,7 @@ const struct inode_operations ceph_file_iops = {
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
.get_acl = ceph_get_acl,
+ .set_acl = ceph_set_acl,
};
@@ -1616,6 +1617,7 @@ static const struct inode_operations ceph_symlink_iops = {
.listxattr = ceph_listxattr,
.removexattr = ceph_removexattr,
.get_acl = ceph_get_acl,
+ .set_acl = ceph_set_acl,
};
/*
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2df963f1cf5a..10a4ccbf38da 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -144,7 +144,11 @@ enum {
Opt_ino32,
Opt_noino32,
Opt_fscache,
- Opt_nofscache
+ Opt_nofscache,
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ Opt_acl,
+#endif
+ Opt_noacl
};
static match_table_t fsopt_tokens = {
@@ -172,6 +176,10 @@ static match_table_t fsopt_tokens = {
{Opt_noino32, "noino32"},
{Opt_fscache, "fsc"},
{Opt_nofscache, "nofsc"},
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ {Opt_acl, "acl"},
+#endif
+ {Opt_noacl, "noacl"},
{-1, NULL}
};
@@ -271,6 +279,14 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_nofscache:
fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
break;
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ case Opt_acl:
+ fsopt->sb_flags |= MS_POSIXACL;
+ break;
+#endif
+ case Opt_noacl:
+ fsopt->sb_flags &= ~MS_POSIXACL;
+ break;
default:
BUG_ON(token);
}
@@ -438,6 +454,13 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
else
seq_puts(m, ",nofsc");
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ if (fsopt->sb_flags & MS_POSIXACL)
+ seq_puts(m, ",acl");
+ else
+ seq_puts(m, ",noacl");
+#endif
+
if (fsopt->wsize)
seq_printf(m, ",wsize=%d", fsopt->wsize);
if (fsopt->rsize != CEPH_RSIZE_DEFAULT)
@@ -819,9 +842,6 @@ static int ceph_set_super(struct super_block *s, void *data)
s->s_flags = fsc->mount_options->sb_flags;
s->s_maxbytes = 1ULL << 40; /* temp value until we get mdsmap */
-#ifdef CONFIG_CEPH_FS_POSIX_ACL
- s->s_flags |= MS_POSIXACL;
-#endif
s->s_xattr = ceph_xattr_handlers;
s->s_fs_info = fsc;
@@ -911,6 +931,10 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
struct ceph_options *opt = NULL;
dout("ceph_mount\n");
+
+#ifdef CONFIG_CEPH_FS_POSIX_ACL
+ flags |= MS_POSIXACL;
+#endif
err = parse_mount_options(&fsopt, &opt, flags, data, dev_name, &path);
if (err < 0) {
res = ERR_PTR(err);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 345933948b6e..d8801a95b685 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -13,6 +13,7 @@
#include <linux/wait.h>
#include <linux/writeback.h>
#include <linux/slab.h>
+#include <linux/posix_acl.h>
#include <linux/ceph/libceph.h>
@@ -741,12 +742,18 @@ extern const struct xattr_handler *ceph_xattr_handlers[];
#ifdef CONFIG_CEPH_FS_POSIX_ACL
struct posix_acl *ceph_get_acl(struct inode *, int);
+int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type);
int ceph_init_acl(struct dentry *, struct inode *, struct inode *);
-void ceph_forget_all_cached_acls(struct inode *inode);
+
+static inline void ceph_forget_all_cached_acls(struct inode *inode)
+{
+ forget_all_cached_acls(inode);
+}
#else
#define ceph_get_acl NULL
+#define ceph_set_acl NULL
static inline int ceph_init_acl(struct dentry *dentry, struct inode *inode,
struct inode *dir)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 898b6565ad3e..a55ec37378c6 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
#define XATTR_CEPH_PREFIX "ceph."
#define XATTR_CEPH_PREFIX_LEN (sizeof (XATTR_CEPH_PREFIX) - 1)
+static int __remove_xattr(struct ceph_inode_info *ci,
+ struct ceph_inode_xattr *xattr);
+
/*
* List of handlers for synthetic system.* attributes. Other
* attributes are handled directly.
@@ -319,8 +322,7 @@ static struct ceph_vxattr *ceph_match_vxattr(struct inode *inode,
static int __set_xattr(struct ceph_inode_info *ci,
const char *name, int name_len,
const char *val, int val_len,
- int dirty,
- int should_free_name, int should_free_val,
+ int flags, int update_xattr,
struct ceph_inode_xattr **newxattr)
{
struct rb_node **p;
@@ -349,12 +351,31 @@ static int __set_xattr(struct ceph_inode_info *ci,
xattr = NULL;
}
+ if (update_xattr) {
+ int err = 0;
+ if (xattr && (flags & XATTR_CREATE))
+ err = -EEXIST;
+ else if (!xattr && (flags & XATTR_REPLACE))
+ err = -ENODATA;
+ if (err) {
+ kfree(name);
+ kfree(val);
+ return err;
+ }
+ if (update_xattr < 0) {
+ if (xattr)
+ __remove_xattr(ci, xattr);
+ kfree(name);
+ return 0;
+ }
+ }
+
if (!xattr) {
new = 1;
xattr = *newxattr;
xattr->name = name;
xattr->name_len = name_len;
- xattr->should_free_name = should_free_name;
+ xattr->should_free_name = update_xattr;
ci->i_xattrs.count++;
dout("__set_xattr count=%d\n", ci->i_xattrs.count);
@@ -364,7 +385,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
if (xattr->should_free_val)
kfree((void *)xattr->val);
- if (should_free_name) {
+ if (update_xattr) {
kfree((void *)name);
name = xattr->name;
}
@@ -379,8 +400,8 @@ static int __set_xattr(struct ceph_inode_info *ci,
xattr->val = "";
xattr->val_len = val_len;
- xattr->dirty = dirty;
- xattr->should_free_val = (val && should_free_val);
+ xattr->dirty = update_xattr;
+ xattr->should_free_val = (val && update_xattr);
if (new) {
rb_link_node(&xattr->node, parent, p);
@@ -442,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci,
struct ceph_inode_xattr *xattr)
{
if (!xattr)
- return -EOPNOTSUPP;
+ return -ENODATA;
rb_erase(&xattr->node, &ci->i_xattrs.index);
@@ -588,7 +609,7 @@ start:
p += len;
err = __set_xattr(ci, name, namelen, val, len,
- 0, 0, 0, &xattrs[numattr]);
+ 0, 0, &xattrs[numattr]);
if (err < 0)
goto bad;
@@ -850,6 +871,9 @@ static int ceph_sync_setxattr(struct dentry *dentry, const char *name,
dout("setxattr value=%.*s\n", (int)size, value);
+ if (!value)
+ flags |= CEPH_XATTR_REMOVE;
+
/* do request */
req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETXATTR,
USE_AUTH_MDS);
@@ -892,7 +916,7 @@ int __ceph_setxattr(struct dentry *dentry, const char *name,
struct ceph_inode_info *ci = ceph_inode(inode);
int issued;
int err;
- int dirty;
+ int dirty = 0;
int name_len = strlen(name);
int val_len = size;
char *newname = NULL;
@@ -953,12 +977,14 @@ retry:
goto retry;
}
- err = __set_xattr(ci, newname, name_len, newval,
- val_len, 1, 1, 1, &xattr);
+ err = __set_xattr(ci, newname, name_len, newval, val_len,
+ flags, value ? 1 : -1, &xattr);
- dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
- ci->i_xattrs.dirty = true;
- inode->i_ctime = CURRENT_TIME;
+ if (!err) {
+ dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_XATTR_EXCL);
+ ci->i_xattrs.dirty = true;
+ inode->i_ctime = CURRENT_TIME;
+ }
spin_unlock(&ci->i_ceph_lock);
if (dirty)
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 51f5e0ee7237..7ff866dbb89e 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -865,8 +865,8 @@ static int build_sec_desc(struct cifs_ntsd *pntsd, struct cifs_ntsd *pnntsd,
return rc;
}
-static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
- __u16 fid, u32 *pacllen)
+struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
+ const struct cifs_fid *cifsfid, u32 *pacllen)
{
struct cifs_ntsd *pntsd = NULL;
unsigned int xid;
@@ -877,7 +877,8 @@ static struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb,
return ERR_CAST(tlink);
xid = get_xid();
- rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), fid, &pntsd, pacllen);
+ rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd,
+ pacllen);
free_xid(xid);
cifs_put_tlink(tlink);
@@ -895,9 +896,10 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
int oplock = 0;
unsigned int xid;
int rc, create_options = 0;
- __u16 fid;
struct cifs_tcon *tcon;
struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
if (IS_ERR(tlink))
return ERR_CAST(tlink);
@@ -908,12 +910,19 @@ static struct cifs_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb,
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
- rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, READ_CONTROL,
- create_options, &fid, &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = READ_CONTROL;
+ oparms.create_options = create_options;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (!rc) {
- rc = CIFSSMBGetCIFSACL(xid, tcon, fid, &pntsd, pacllen);
- CIFSSMBClose(xid, tcon, fid);
+ rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen);
+ CIFSSMBClose(xid, tcon, fid.netfid);
}
cifs_put_tlink(tlink);
@@ -938,7 +947,7 @@ struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb,
if (!open_file)
return get_cifs_acl_by_path(cifs_sb, path, pacllen);
- pntsd = get_cifs_acl_by_fid(cifs_sb, open_file->fid.netfid, pacllen);
+ pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
cifsFileInfo_put(open_file);
return pntsd;
}
@@ -950,10 +959,11 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
int oplock = 0;
unsigned int xid;
int rc, access_flags, create_options = 0;
- __u16 fid;
struct cifs_tcon *tcon;
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
if (IS_ERR(tlink))
return PTR_ERR(tlink);
@@ -969,18 +979,25 @@ int set_cifs_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
else
access_flags = WRITE_DAC;
- rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, access_flags,
- create_options, &fid, &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = access_flags;
+ oparms.create_options = create_options;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc) {
cifs_dbg(VFS, "Unable to open file to set ACL\n");
goto out;
}
- rc = CIFSSMBSetCIFSACL(xid, tcon, fid, pnntsd, acllen, aclflag);
+ rc = CIFSSMBSetCIFSACL(xid, tcon, fid.netfid, pnntsd, acllen, aclflag);
cifs_dbg(NOISY, "SetCIFSACL rc = %d\n", rc);
- CIFSSMBClose(xid, tcon, fid);
+ CIFSSMBClose(xid, tcon, fid.netfid);
out:
free_xid(xid);
cifs_put_tlink(tlink);
@@ -990,19 +1007,31 @@ out:
/* Translate the CIFS ACL (simlar to NTFS ACL) for a file into mode bits */
int
cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
- struct inode *inode, const char *path, const __u16 *pfid)
+ struct inode *inode, const char *path,
+ const struct cifs_fid *pfid)
{
struct cifs_ntsd *pntsd = NULL;
u32 acllen = 0;
int rc = 0;
+ struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_tcon *tcon;
cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
- if (pfid)
- pntsd = get_cifs_acl_by_fid(cifs_sb, *pfid, &acllen);
- else
- pntsd = get_cifs_acl(cifs_sb, inode, path, &acllen);
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
+ if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
+ pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
+ &acllen);
+ else if (tcon->ses->server->ops->get_acl)
+ pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+ &acllen);
+ else {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
/* if we can retrieve the ACL, now parse Access Control Entries, ACEs */
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
@@ -1014,6 +1043,8 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
cifs_dbg(VFS, "parse sec desc failed rc = %d\n", rc);
}
+ cifs_put_tlink(tlink);
+
return rc;
}
@@ -1027,15 +1058,30 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
__u32 secdesclen = 0;
struct cifs_ntsd *pntsd = NULL; /* acl obtained from server */
struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
+ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+ struct cifs_tcon *tcon;
+
+ if (IS_ERR(tlink))
+ return PTR_ERR(tlink);
+ tcon = tlink_tcon(tlink);
cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
/* Get the security descriptor */
- pntsd = get_cifs_acl(CIFS_SB(inode->i_sb), inode, path, &secdesclen);
+
+ if (tcon->ses->server->ops->get_acl == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
+ &secdesclen);
if (IS_ERR(pntsd)) {
rc = PTR_ERR(pntsd);
cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
- goto out;
+ cifs_put_tlink(tlink);
+ return rc;
}
/*
@@ -1048,6 +1094,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
pnntsd = kmalloc(secdesclen, GFP_KERNEL);
if (!pnntsd) {
kfree(pntsd);
+ cifs_put_tlink(tlink);
return -ENOMEM;
}
@@ -1056,14 +1103,18 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
+ if (tcon->ses->server->ops->set_acl == NULL)
+ rc = -EOPNOTSUPP;
+
if (!rc) {
/* Set the security descriptor */
- rc = set_cifs_acl(pnntsd, secdesclen, inode, path, aclflag);
+ rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
+ path, aclflag);
cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
}
+ cifs_put_tlink(tlink);
kfree(pnntsd);
kfree(pntsd);
-out:
return rc;
}
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index f918a998a087..cf32f0393369 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -323,7 +323,8 @@ struct smb_version_operations {
/* async read from the server */
int (*async_readv)(struct cifs_readdata *);
/* async write to the server */
- int (*async_writev)(struct cifs_writedata *);
+ int (*async_writev)(struct cifs_writedata *,
+ void (*release)(struct kref *));
/* sync read from the server */
int (*sync_read)(const unsigned int, struct cifsFileInfo *,
struct cifs_io_parms *, unsigned int *, char **,
@@ -370,8 +371,12 @@ struct smb_version_operations {
void (*new_lease_key)(struct cifs_fid *);
int (*generate_signingkey)(struct cifs_ses *);
int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *);
- int (*query_mf_symlink)(const unsigned char *, char *, unsigned int *,
- struct cifs_sb_info *, unsigned int);
+ int (*query_mf_symlink)(unsigned int, struct cifs_tcon *,
+ struct cifs_sb_info *, const unsigned char *,
+ char *, unsigned int *);
+ int (*create_mf_symlink)(unsigned int, struct cifs_tcon *,
+ struct cifs_sb_info *, const unsigned char *,
+ char *, unsigned int *);
/* if we can do cache read operations */
bool (*is_read_op)(__u32);
/* set oplock level for the inode */
@@ -385,6 +390,18 @@ struct smb_version_operations {
struct cifsFileInfo *target_file, u64 src_off, u64 len,
u64 dest_off);
int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
+ ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
+ const unsigned char *, const unsigned char *, char *,
+ size_t, const struct nls_table *, int);
+ int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
+ const char *, const void *, const __u16,
+ const struct nls_table *, int);
+ struct cifs_ntsd * (*get_acl)(struct cifs_sb_info *, struct inode *,
+ const char *, u32 *);
+ struct cifs_ntsd * (*get_acl_by_fid)(struct cifs_sb_info *,
+ const struct cifs_fid *, u32 *);
+ int (*set_acl)(struct cifs_ntsd *, __u32, struct inode *, const char *,
+ int);
};
struct smb_version_values {
@@ -1054,7 +1071,7 @@ struct cifs_writedata {
unsigned int pagesz;
unsigned int tailsz;
unsigned int nr_pages;
- struct page *pages[1];
+ struct page *pages[];
};
/*
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 2c29db6a247e..acc4ee8ed075 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -151,7 +151,7 @@ extern struct inode *cifs_iget(struct super_block *sb,
extern int cifs_get_inode_info(struct inode **inode, const char *full_path,
FILE_ALL_INFO *data, struct super_block *sb,
- int xid, const __u16 *fid);
+ int xid, const struct cifs_fid *fid);
extern int cifs_get_inode_info_unix(struct inode **pinode,
const unsigned char *search_path,
struct super_block *sb, unsigned int xid);
@@ -162,11 +162,13 @@ extern int cifs_rename_pending_delete(const char *full_path,
const unsigned int xid);
extern int cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb,
struct cifs_fattr *fattr, struct inode *inode,
- const char *path, const __u16 *pfid);
+ const char *path, const struct cifs_fid *pfid);
extern int id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64,
kuid_t, kgid_t);
extern struct cifs_ntsd *get_cifs_acl(struct cifs_sb_info *, struct inode *,
const char *, u32 *);
+extern struct cifs_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *,
+ const struct cifs_fid *, u32 *);
extern int set_cifs_acl(struct cifs_ntsd *, __u32, struct inode *,
const char *, int);
@@ -362,11 +364,8 @@ extern int CIFSSMBQuerySymLink(const unsigned int xid, struct cifs_tcon *tcon,
const struct nls_table *nls_codepage);
extern int CIFSSMB_set_compression(const unsigned int xid,
struct cifs_tcon *tcon, __u16 fid);
-extern int CIFSSMBOpen(const unsigned int xid, struct cifs_tcon *tcon,
- const char *fileName, const int disposition,
- const int access_flags, const int omode,
- __u16 *netfid, int *pOplock, FILE_ALL_INFO *,
- const struct nls_table *nls_codepage, int remap);
+extern int CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms,
+ int *oplock, FILE_ALL_INFO *buf);
extern int SMBLegacyOpen(const unsigned int xid, struct cifs_tcon *tcon,
const char *fileName, const int disposition,
const int access_flags, const int omode,
@@ -476,8 +475,8 @@ extern int CIFSSMBSetPosixACL(const unsigned int xid, struct cifs_tcon *tcon,
extern int CIFSGetExtAttr(const unsigned int xid, struct cifs_tcon *tcon,
const int netfid, __u64 *pExtAttrBits, __u64 *pMask);
extern void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb);
-extern bool CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr);
-extern int CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
+extern bool couldbe_mf_symlink(const struct cifs_fattr *fattr);
+extern int check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
struct cifs_sb_info *cifs_sb,
struct cifs_fattr *fattr,
const unsigned char *path);
@@ -491,12 +490,18 @@ void cifs_readdata_release(struct kref *refcount);
int cifs_async_readv(struct cifs_readdata *rdata);
int cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid);
-int cifs_async_writev(struct cifs_writedata *wdata);
+int cifs_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref));
void cifs_writev_complete(struct work_struct *work);
struct cifs_writedata *cifs_writedata_alloc(unsigned int nr_pages,
work_func_t complete);
void cifs_writedata_release(struct kref *refcount);
-int open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
- unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
- unsigned int xid);
+int cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb,
+ const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_read);
+int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb,
+ const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_written);
#endif /* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d707edb6b852..f3264bd7a83d 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1273,104 +1273,124 @@ OldOpenRetry:
}
int
-CIFSSMBOpen(const unsigned int xid, struct cifs_tcon *tcon,
- const char *fileName, const int openDisposition,
- const int access_flags, const int create_options, __u16 *netfid,
- int *pOplock, FILE_ALL_INFO *pfile_info,
- const struct nls_table *nls_codepage, int remap)
+CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock,
+ FILE_ALL_INFO *buf)
{
int rc = -EACCES;
- OPEN_REQ *pSMB = NULL;
- OPEN_RSP *pSMBr = NULL;
+ OPEN_REQ *req = NULL;
+ OPEN_RSP *rsp = NULL;
int bytes_returned;
int name_len;
__u16 count;
+ struct cifs_sb_info *cifs_sb = oparms->cifs_sb;
+ struct cifs_tcon *tcon = oparms->tcon;
+ int remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
+ const struct nls_table *nls = cifs_sb->local_nls;
+ int create_options = oparms->create_options;
+ int desired_access = oparms->desired_access;
+ int disposition = oparms->disposition;
+ const char *path = oparms->path;
openRetry:
- rc = smb_init(SMB_COM_NT_CREATE_ANDX, 24, tcon, (void **) &pSMB,
- (void **) &pSMBr);
+ rc = smb_init(SMB_COM_NT_CREATE_ANDX, 24, tcon, (void **)&req,
+ (void **)&rsp);
if (rc)
return rc;
- pSMB->AndXCommand = 0xFF; /* none */
+ /* no commands go after this */
+ req->AndXCommand = 0xFF;
- if (pSMB->hdr.Flags2 & SMBFLG2_UNICODE) {
- count = 1; /* account for one byte pad to word boundary */
- name_len =
- cifsConvertToUTF16((__le16 *) (pSMB->fileName + 1),
- fileName, PATH_MAX, nls_codepage, remap);
- name_len++; /* trailing null */
+ if (req->hdr.Flags2 & SMBFLG2_UNICODE) {
+ /* account for one byte pad to word boundary */
+ count = 1;
+ name_len = cifsConvertToUTF16((__le16 *)(req->fileName + 1),
+ path, PATH_MAX, nls, remap);
+ /* trailing null */
+ name_len++;
name_len *= 2;
- pSMB->NameLength = cpu_to_le16(name_len);
- } else { /* BB improve check for buffer overruns BB */
- count = 0; /* no pad */
- name_len = strnlen(fileName, PATH_MAX);
- name_len++; /* trailing null */
- pSMB->NameLength = cpu_to_le16(name_len);
- strncpy(pSMB->fileName, fileName, name_len);
+ req->NameLength = cpu_to_le16(name_len);
+ } else {
+ /* BB improve check for buffer overruns BB */
+ /* no pad */
+ count = 0;
+ name_len = strnlen(path, PATH_MAX);
+ /* trailing null */
+ name_len++;
+ req->NameLength = cpu_to_le16(name_len);
+ strncpy(req->fileName, path, name_len);
}
- if (*pOplock & REQ_OPLOCK)
- pSMB->OpenFlags = cpu_to_le32(REQ_OPLOCK);
- else if (*pOplock & REQ_BATCHOPLOCK)
- pSMB->OpenFlags = cpu_to_le32(REQ_BATCHOPLOCK);
- pSMB->DesiredAccess = cpu_to_le32(access_flags);
- pSMB->AllocationSize = 0;
- /* set file as system file if special file such
- as fifo and server expecting SFU style and
- no Unix extensions */
+
+ if (*oplock & REQ_OPLOCK)
+ req->OpenFlags = cpu_to_le32(REQ_OPLOCK);
+ else if (*oplock & REQ_BATCHOPLOCK)
+ req->OpenFlags = cpu_to_le32(REQ_BATCHOPLOCK);
+
+ req->DesiredAccess = cpu_to_le32(desired_access);
+ req->AllocationSize = 0;
+
+ /*
+ * Set file as system file if special file such as fifo and server
+ * expecting SFU style and no Unix extensions.
+ */
if (create_options & CREATE_OPTION_SPECIAL)
- pSMB->FileAttributes = cpu_to_le32(ATTR_SYSTEM);
+ req->FileAttributes = cpu_to_le32(ATTR_SYSTEM);
else
- pSMB->FileAttributes = cpu_to_le32(ATTR_NORMAL);
+ req->FileAttributes = cpu_to_le32(ATTR_NORMAL);
- /* XP does not handle ATTR_POSIX_SEMANTICS */
- /* but it helps speed up case sensitive checks for other
- servers such as Samba */
+ /*
+ * XP does not handle ATTR_POSIX_SEMANTICS but it helps speed up case
+ * sensitive checks for other servers such as Samba.
+ */
if (tcon->ses->capabilities & CAP_UNIX)
- pSMB->FileAttributes |= cpu_to_le32(ATTR_POSIX_SEMANTICS);
+ req->FileAttributes |= cpu_to_le32(ATTR_POSIX_SEMANTICS);
if (create_options & CREATE_OPTION_READONLY)
- pSMB->FileAttributes |= cpu_to_le32(ATTR_READONLY);
+ req->FileAttributes |= cpu_to_le32(ATTR_READONLY);
+
+ req->ShareAccess = cpu_to_le32(FILE_SHARE_ALL);
+ req->CreateDisposition = cpu_to_le32(disposition);
+ req->CreateOptions = cpu_to_le32(create_options & CREATE_OPTIONS_MASK);
- pSMB->ShareAccess = cpu_to_le32(FILE_SHARE_ALL);
- pSMB->CreateDisposition = cpu_to_le32(openDisposition);
- pSMB->CreateOptions = cpu_to_le32(create_options & CREATE_OPTIONS_MASK);
/* BB Expirement with various impersonation levels and verify */
- pSMB->ImpersonationLevel = cpu_to_le32(SECURITY_IMPERSONATION);
- pSMB->SecurityFlags =
- SECURITY_CONTEXT_TRACKING | SECURITY_EFFECTIVE_ONLY;
+ req->ImpersonationLevel = cpu_to_le32(SECURITY_IMPERSONATION);
+ req->SecurityFlags = SECURITY_CONTEXT_TRACKING|SECURITY_EFFECTIVE_ONLY;
count += name_len;
- inc_rfc1001_len(pSMB, count);
+ inc_rfc1001_len(req, count);
- pSMB->ByteCount = cpu_to_le16(count);
- /* long_op set to 1 to allow for oplock break timeouts */
- rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
- (struct smb_hdr *)pSMBr, &bytes_returned, 0);
+ req->ByteCount = cpu_to_le16(count);
+ rc = SendReceive(xid, tcon->ses, (struct smb_hdr *)req,
+ (struct smb_hdr *)rsp, &bytes_returned, 0);
cifs_stats_inc(&tcon->stats.cifs_stats.num_opens);
if (rc) {
cifs_dbg(FYI, "Error in Open = %d\n", rc);
- } else {
- *pOplock = pSMBr->OplockLevel; /* 1 byte no need to le_to_cpu */
- *netfid = pSMBr->Fid; /* cifs fid stays in le */
- /* Let caller know file was created so we can set the mode. */
- /* Do we care about the CreateAction in any other cases? */
- if (cpu_to_le32(FILE_CREATE) == pSMBr->CreateAction)
- *pOplock |= CIFS_CREATE_ACTION;
- if (pfile_info) {
- memcpy((char *)pfile_info, (char *)&pSMBr->CreationTime,
- 36 /* CreationTime to Attributes */);
- /* the file_info buf is endian converted by caller */
- pfile_info->AllocationSize = pSMBr->AllocationSize;
- pfile_info->EndOfFile = pSMBr->EndOfFile;
- pfile_info->NumberOfLinks = cpu_to_le32(1);
- pfile_info->DeletePending = 0;
- }
+ cifs_buf_release(req);
+ if (rc == -EAGAIN)
+ goto openRetry;
+ return rc;
}
- cifs_buf_release(pSMB);
- if (rc == -EAGAIN)
- goto openRetry;
+ /* 1 byte no need to le_to_cpu */
+ *oplock = rsp->OplockLevel;
+ /* cifs fid stays in le */
+ oparms->fid->netfid = rsp->Fid;
+
+ /* Let caller know file was created so we can set the mode. */
+ /* Do we care about the CreateAction in any other cases? */
+ if (cpu_to_le32(FILE_CREATE) == rsp->CreateAction)
+ *oplock |= CIFS_CREATE_ACTION;
+
+ if (buf) {
+ /* copy from CreationTime to Attributes */
+ memcpy((char *)buf, (char *)&rsp->CreationTime, 36);
+ /* the file_info buf is endian converted by caller */
+ buf->AllocationSize = rsp->AllocationSize;
+ buf->EndOfFile = rsp->EndOfFile;
+ buf->NumberOfLinks = cpu_to_le32(1);
+ buf->DeletePending = 0;
+ }
+
+ cifs_buf_release(req);
return rc;
}
@@ -1890,7 +1910,7 @@ cifs_writev_requeue(struct cifs_writedata *wdata)
do {
server = tlink_tcon(wdata->cfile->tlink)->ses->server;
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata, cifs_writedata_release);
} while (rc == -EAGAIN);
for (i = 0; i < wdata->nr_pages; i++) {
@@ -1942,15 +1962,9 @@ cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
{
struct cifs_writedata *wdata;
- /* this would overflow */
- if (nr_pages == 0) {
- cifs_dbg(VFS, "%s: called with nr_pages == 0!\n", __func__);
- return NULL;
- }
-
/* writedata + number of page pointers */
wdata = kzalloc(sizeof(*wdata) +
- sizeof(struct page *) * (nr_pages - 1), GFP_NOFS);
+ sizeof(struct page *) * nr_pages, GFP_NOFS);
if (wdata != NULL) {
kref_init(&wdata->refcount);
INIT_LIST_HEAD(&wdata->list);
@@ -2011,7 +2025,8 @@ cifs_writev_callback(struct mid_q_entry *mid)
/* cifs_async_writev - send an async write, and set up mid to handle result */
int
-cifs_async_writev(struct cifs_writedata *wdata)
+cifs_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref))
{
int rc = -EACCES;
WRITE_REQ *smb = NULL;
@@ -2085,7 +2100,7 @@ cifs_async_writev(struct cifs_writedata *wdata)
if (rc == 0)
cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
else
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, release);
async_writev_out:
cifs_small_buf_release(smb);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index a514e0a65f69..3db0c5fd9a11 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -378,7 +378,7 @@ cifs_create_get_file_info:
xid);
else {
rc = cifs_get_inode_info(&newinode, full_path, buf, inode->i_sb,
- xid, &fid->netfid);
+ xid, fid);
if (newinode) {
if (server->ops->set_lease_key)
server->ops->set_lease_key(newinode, fid);
@@ -565,12 +565,13 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
int create_options = CREATE_NOT_DIR | CREATE_OPTION_SPECIAL;
struct cifs_sb_info *cifs_sb;
struct tcon_link *tlink;
- struct cifs_tcon *pTcon;
+ struct cifs_tcon *tcon;
struct cifs_io_parms io_parms;
char *full_path = NULL;
struct inode *newinode = NULL;
int oplock = 0;
- u16 fileHandle;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
FILE_ALL_INFO *buf = NULL;
unsigned int bytes_written;
struct win_dev *pdev;
@@ -583,7 +584,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
if (IS_ERR(tlink))
return PTR_ERR(tlink);
- pTcon = tlink_tcon(tlink);
+ tcon = tlink_tcon(tlink);
xid = get_xid();
@@ -593,7 +594,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
goto mknod_out;
}
- if (pTcon->unix_ext) {
+ if (tcon->unix_ext) {
struct cifs_unix_set_info_args args = {
.mode = mode & ~current_umask(),
.ctime = NO_CHANGE_64,
@@ -608,7 +609,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
args.uid = INVALID_UID; /* no change */
args.gid = INVALID_GID; /* no change */
}
- rc = CIFSSMBUnixSetPathInfo(xid, pTcon, full_path, &args,
+ rc = CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
@@ -640,42 +641,44 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode,
if (backup_cred(cifs_sb))
create_options |= CREATE_OPEN_BACKUP_INTENT;
- rc = CIFSSMBOpen(xid, pTcon, full_path, FILE_CREATE,
- GENERIC_WRITE, create_options,
- &fileHandle, &oplock, buf, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = GENERIC_WRITE;
+ oparms.create_options = create_options;
+ oparms.disposition = FILE_CREATE;
+ oparms.path = full_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, buf);
if (rc)
goto mknod_out;
- /* BB Do not bother to decode buf since no local inode yet to put
- * timestamps in, but we can reuse it safely */
+ /*
+ * BB Do not bother to decode buf since no local inode yet to put
+ * timestamps in, but we can reuse it safely.
+ */
pdev = (struct win_dev *)buf;
- io_parms.netfid = fileHandle;
+ io_parms.netfid = fid.netfid;
io_parms.pid = current->tgid;
- io_parms.tcon = pTcon;
+ io_parms.tcon = tcon;
io_parms.offset = 0;
io_parms.length = sizeof(struct win_dev);
if (S_ISCHR(mode)) {
memcpy(pdev->type, "IntxCHR", 8);
- pdev->major =
- cpu_to_le64(MAJOR(device_number));
- pdev->minor =
- cpu_to_le64(MINOR(device_number));
- rc = CIFSSMBWrite(xid, &io_parms,
- &bytes_written, (char *)pdev,
- NULL, 0);
+ pdev->major = cpu_to_le64(MAJOR(device_number));
+ pdev->minor = cpu_to_le64(MINOR(device_number));
+ rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, (char *)pdev,
+ NULL, 0);
} else if (S_ISBLK(mode)) {
memcpy(pdev->type, "IntxBLK", 8);
- pdev->major =
- cpu_to_le64(MAJOR(device_number));
- pdev->minor =
- cpu_to_le64(MINOR(device_number));
- rc = CIFSSMBWrite(xid, &io_parms,
- &bytes_written, (char *)pdev,
- NULL, 0);
+ pdev->major = cpu_to_le64(MAJOR(device_number));
+ pdev->minor = cpu_to_le64(MINOR(device_number));
+ rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, (char *)pdev,
+ NULL, 0);
} /* else if (S_ISFIFO) */
- CIFSSMBClose(xid, pTcon, fileHandle);
+ CIFSSMBClose(xid, tcon, fid.netfid);
d_drop(direntry);
/* FIXME: add code here to set EAs */
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5a5a87240fe2..53c15074bb36 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -244,7 +244,7 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
xid);
else
rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
- xid, &fid->netfid);
+ xid, fid);
out:
kfree(buf);
@@ -678,7 +678,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
/*
* Can not refresh inode by passing in file_info buf to be returned by
- * CIFSSMBOpen and then calling get_inode_info with returned buf since
+ * ops->open and then calling get_inode_info with returned buf since
* file might have write behind data that needs to be flushed and server
* version of file size can be stale. If we knew for sure that inode was
* not dirty locally we could do this.
@@ -2043,7 +2043,8 @@ retry:
}
wdata->pid = wdata->cfile->pid;
server = tlink_tcon(wdata->cfile->tlink)->ses->server;
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata,
+ cifs_writedata_release);
} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);
for (i = 0; i < nr_pages; ++i)
@@ -2331,9 +2332,20 @@ size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
}
static void
-cifs_uncached_writev_complete(struct work_struct *work)
+cifs_uncached_writedata_release(struct kref *refcount)
{
int i;
+ struct cifs_writedata *wdata = container_of(refcount,
+ struct cifs_writedata, refcount);
+
+ for (i = 0; i < wdata->nr_pages; i++)
+ put_page(wdata->pages[i]);
+ cifs_writedata_release(refcount);
+}
+
+static void
+cifs_uncached_writev_complete(struct work_struct *work)
+{
struct cifs_writedata *wdata = container_of(work,
struct cifs_writedata, work);
struct inode *inode = wdata->cfile->dentry->d_inode;
@@ -2347,12 +2359,7 @@ cifs_uncached_writev_complete(struct work_struct *work)
complete(&wdata->done);
- if (wdata->result != -EAGAIN) {
- for (i = 0; i < wdata->nr_pages; i++)
- put_page(wdata->pages[i]);
- }
-
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
/* attempt to send write to server, retry on any -EAGAIN errors */
@@ -2370,7 +2377,8 @@ cifs_uncached_retry_writev(struct cifs_writedata *wdata)
if (rc != 0)
continue;
}
- rc = server->ops->async_writev(wdata);
+ rc = server->ops->async_writev(wdata,
+ cifs_uncached_writedata_release);
} while (rc == -EAGAIN);
return rc;
@@ -2381,7 +2389,7 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
unsigned long nr_segs, loff_t *poffset)
{
unsigned long nr_pages, i;
- size_t copied, len, cur_len;
+ size_t bytes, copied, len, cur_len;
ssize_t total_written = 0;
loff_t offset;
struct iov_iter it;
@@ -2436,14 +2444,45 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
save_len = cur_len;
for (i = 0; i < nr_pages; i++) {
- copied = min_t(const size_t, cur_len, PAGE_SIZE);
+ bytes = min_t(const size_t, cur_len, PAGE_SIZE);
copied = iov_iter_copy_from_user(wdata->pages[i], &it,
- 0, copied);
+ 0, bytes);
cur_len -= copied;
iov_iter_advance(&it, copied);
+ /*
+ * If we didn't copy as much as we expected, then that
+ * may mean we trod into an unmapped area. Stop copying
+ * at that point. On the next pass through the big
+ * loop, we'll likely end up getting a zero-length
+ * write and bailing out of it.
+ */
+ if (copied < bytes)
+ break;
}
cur_len = save_len - cur_len;
+ /*
+ * If we have no data to send, then that probably means that
+ * the copy above failed altogether. That's most likely because
+ * the address in the iovec was bogus. Set the rc to -EFAULT,
+ * free anything we allocated and bail out.
+ */
+ if (!cur_len) {
+ for (i = 0; i < nr_pages; i++)
+ put_page(wdata->pages[i]);
+ kfree(wdata);
+ rc = -EFAULT;
+ break;
+ }
+
+ /*
+ * i + 1 now represents the number of pages we actually used in
+ * the copy phase above. Bring nr_pages down to that, and free
+ * any pages that we didn't use.
+ */
+ for ( ; nr_pages > i + 1; nr_pages--)
+ put_page(wdata->pages[nr_pages - 1]);
+
wdata->sync_mode = WB_SYNC_ALL;
wdata->nr_pages = nr_pages;
wdata->offset = (__u64)offset;
@@ -2454,7 +2493,8 @@ cifs_iovec_write(struct file *file, const struct iovec *iov,
wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
rc = cifs_uncached_retry_writev(wdata);
if (rc) {
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount,
+ cifs_uncached_writedata_release);
break;
}
@@ -2496,7 +2536,7 @@ restart_loop:
}
}
list_del_init(&wdata->list);
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, cifs_uncached_writedata_release);
}
if (total_written > 0)
@@ -2559,8 +2599,8 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
if (rc > 0) {
ssize_t err;
- err = generic_write_sync(file, pos, rc);
- if (err < 0 && rc > 0)
+ err = generic_write_sync(file, iocb->ki_pos - rc, rc);
+ if (err < 0)
rc = err;
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 49719b8228e5..aadc2b68678b 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -383,10 +383,10 @@ int cifs_get_inode_info_unix(struct inode **pinode,
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
- int tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
- full_path);
+ int tmprc = check_mf_symlink(xid, tcon, cifs_sb, &fattr,
+ full_path);
if (tmprc)
- cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
+ cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
}
if (*pinode == NULL) {
@@ -404,18 +404,20 @@ int cifs_get_inode_info_unix(struct inode **pinode,
}
static int
-cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path,
+cifs_sfu_type(struct cifs_fattr *fattr, const char *path,
struct cifs_sb_info *cifs_sb, unsigned int xid)
{
int rc;
int oplock = 0;
- __u16 netfid;
struct tcon_link *tlink;
struct cifs_tcon *tcon;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
struct cifs_io_parms io_parms;
char buf[24];
unsigned int bytes_read;
char *pbuf;
+ int buf_type = CIFS_NO_BUFFER;
pbuf = buf;
@@ -436,62 +438,69 @@ cifs_sfu_type(struct cifs_fattr *fattr, const unsigned char *path,
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
- rc = CIFSSMBOpen(xid, tcon, path, FILE_OPEN, GENERIC_READ,
- CREATE_NOT_DIR, &netfid, &oplock, NULL,
- cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
- if (rc == 0) {
- int buf_type = CIFS_NO_BUFFER;
- /* Read header */
- io_parms.netfid = netfid;
- io_parms.pid = current->tgid;
- io_parms.tcon = tcon;
- io_parms.offset = 0;
- io_parms.length = 24;
- rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf,
- &buf_type);
- if ((rc == 0) && (bytes_read >= 8)) {
- if (memcmp("IntxBLK", pbuf, 8) == 0) {
- cifs_dbg(FYI, "Block device\n");
- fattr->cf_mode |= S_IFBLK;
- fattr->cf_dtype = DT_BLK;
- if (bytes_read == 24) {
- /* we have enough to decode dev num */
- __u64 mjr; /* major */
- __u64 mnr; /* minor */
- mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
- mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
- fattr->cf_rdev = MKDEV(mjr, mnr);
- }
- } else if (memcmp("IntxCHR", pbuf, 8) == 0) {
- cifs_dbg(FYI, "Char device\n");
- fattr->cf_mode |= S_IFCHR;
- fattr->cf_dtype = DT_CHR;
- if (bytes_read == 24) {
- /* we have enough to decode dev num */
- __u64 mjr; /* major */
- __u64 mnr; /* minor */
- mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
- mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
- fattr->cf_rdev = MKDEV(mjr, mnr);
- }
- } else if (memcmp("IntxLNK", pbuf, 7) == 0) {
- cifs_dbg(FYI, "Symlink\n");
- fattr->cf_mode |= S_IFLNK;
- fattr->cf_dtype = DT_LNK;
- } else {
- fattr->cf_mode |= S_IFREG; /* file? */
- fattr->cf_dtype = DT_REG;
- rc = -EOPNOTSUPP;
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = GENERIC_READ;
+ oparms.create_options = CREATE_NOT_DIR;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
+ if (rc) {
+ cifs_put_tlink(tlink);
+ return rc;
+ }
+
+ /* Read header */
+ io_parms.netfid = fid.netfid;
+ io_parms.pid = current->tgid;
+ io_parms.tcon = tcon;
+ io_parms.offset = 0;
+ io_parms.length = 24;
+
+ rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
+ if ((rc == 0) && (bytes_read >= 8)) {
+ if (memcmp("IntxBLK", pbuf, 8) == 0) {
+ cifs_dbg(FYI, "Block device\n");
+ fattr->cf_mode |= S_IFBLK;
+ fattr->cf_dtype = DT_BLK;
+ if (bytes_read == 24) {
+ /* we have enough to decode dev num */
+ __u64 mjr; /* major */
+ __u64 mnr; /* minor */
+ mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
+ mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
+ fattr->cf_rdev = MKDEV(mjr, mnr);
}
+ } else if (memcmp("IntxCHR", pbuf, 8) == 0) {
+ cifs_dbg(FYI, "Char device\n");
+ fattr->cf_mode |= S_IFCHR;
+ fattr->cf_dtype = DT_CHR;
+ if (bytes_read == 24) {
+ /* we have enough to decode dev num */
+ __u64 mjr; /* major */
+ __u64 mnr; /* minor */
+ mjr = le64_to_cpu(*(__le64 *)(pbuf+8));
+ mnr = le64_to_cpu(*(__le64 *)(pbuf+16));
+ fattr->cf_rdev = MKDEV(mjr, mnr);
+ }
+ } else if (memcmp("IntxLNK", pbuf, 7) == 0) {
+ cifs_dbg(FYI, "Symlink\n");
+ fattr->cf_mode |= S_IFLNK;
+ fattr->cf_dtype = DT_LNK;
} else {
- fattr->cf_mode |= S_IFREG; /* then it is a file */
+ fattr->cf_mode |= S_IFREG; /* file? */
fattr->cf_dtype = DT_REG;
- rc = -EOPNOTSUPP; /* or some unknown SFU type */
+ rc = -EOPNOTSUPP;
}
- CIFSSMBClose(xid, tcon, netfid);
+ } else {
+ fattr->cf_mode |= S_IFREG; /* then it is a file */
+ fattr->cf_dtype = DT_REG;
+ rc = -EOPNOTSUPP; /* or some unknown SFU type */
}
+ CIFSSMBClose(xid, tcon, fid.netfid);
cifs_put_tlink(tlink);
return rc;
}
@@ -518,10 +527,15 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
return PTR_ERR(tlink);
tcon = tlink_tcon(tlink);
- rc = CIFSSMBQAllEAs(xid, tcon, path, "SETFILEBITS",
- ea_value, 4 /* size of buf */, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (tcon->ses->server->ops->query_all_EAs == NULL) {
+ cifs_put_tlink(tlink);
+ return -EOPNOTSUPP;
+ }
+
+ rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
+ "SETFILEBITS", ea_value, 4 /* size of buf */,
+ cifs_sb->local_nls,
+ cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
cifs_put_tlink(tlink);
if (rc < 0)
return (int)rc;
@@ -663,7 +677,7 @@ cgfi_exit:
int
cifs_get_inode_info(struct inode **inode, const char *full_path,
FILE_ALL_INFO *data, struct super_block *sb, int xid,
- const __u16 *fid)
+ const struct cifs_fid *fid)
{
bool validinum = false;
__u16 srchflgs;
@@ -800,10 +814,10 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
/* check for Minshall+French symlinks */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) {
- tmprc = CIFSCheckMFSymlink(xid, tcon, cifs_sb, &fattr,
- full_path);
+ tmprc = check_mf_symlink(xid, tcon, cifs_sb, &fattr,
+ full_path);
if (tmprc)
- cifs_dbg(FYI, "CIFSCheckMFSymlink: %d\n", tmprc);
+ cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc);
}
if (!*inode) {
@@ -1032,7 +1046,8 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
{
int oplock = 0;
int rc;
- __u16 netfid;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
struct inode *inode = dentry->d_inode;
struct cifsInodeInfo *cifsInode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -1055,10 +1070,16 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
goto out;
}
- rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
- DELETE|FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR,
- &netfid, &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = DELETE | FILE_WRITE_ATTRIBUTES;
+ oparms.create_options = CREATE_NOT_DIR;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = full_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc != 0)
goto out;
@@ -1079,7 +1100,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
goto out_close;
}
info_buf->Attributes = cpu_to_le32(dosattr);
- rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid,
+ rc = CIFSSMBSetFileInfo(xid, tcon, info_buf, fid.netfid,
current->tgid);
/* although we would like to mark the file hidden
if that fails we will still try to rename it */
@@ -1090,7 +1111,8 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
}
/* rename the file */
- rc = CIFSSMBRenameOpenFile(xid, tcon, netfid, NULL, cifs_sb->local_nls,
+ rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, NULL,
+ cifs_sb->local_nls,
cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
if (rc != 0) {
@@ -1100,7 +1122,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
/* try to set DELETE_ON_CLOSE */
if (!cifsInode->delete_pending) {
- rc = CIFSSMBSetFileDisposition(xid, tcon, true, netfid,
+ rc = CIFSSMBSetFileDisposition(xid, tcon, true, fid.netfid,
current->tgid);
/*
* some samba versions return -ENOENT when we try to set the
@@ -1120,7 +1142,7 @@ cifs_rename_pending_delete(const char *full_path, struct dentry *dentry,
}
out_close:
- CIFSSMBClose(xid, tcon, netfid);
+ CIFSSMBClose(xid, tcon, fid.netfid);
out:
kfree(info_buf);
cifs_put_tlink(tlink);
@@ -1132,13 +1154,13 @@ out:
* them anyway.
*/
undo_rename:
- CIFSSMBRenameOpenFile(xid, tcon, netfid, dentry->d_name.name,
+ CIFSSMBRenameOpenFile(xid, tcon, fid.netfid, dentry->d_name.name,
cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
undo_setattr:
if (dosattr != origattr) {
info_buf->Attributes = cpu_to_le32(origattr);
- if (!CIFSSMBSetFileInfo(xid, tcon, info_buf, netfid,
+ if (!CIFSSMBSetFileInfo(xid, tcon, info_buf, fid.netfid,
current->tgid))
cifsInode->cifsAttrs = origattr;
}
@@ -1549,7 +1571,8 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
struct tcon_link *tlink;
struct cifs_tcon *tcon;
struct TCP_Server_Info *server;
- __u16 srcfid;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
int oplock, rc;
tlink = cifs_sb_tlink(cifs_sb);
@@ -1576,17 +1599,23 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
if (to_dentry->d_parent != from_dentry->d_parent)
goto do_rename_exit;
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
/* open the file to be renamed -- we need DELETE perms */
- rc = CIFSSMBOpen(xid, tcon, from_path, FILE_OPEN, DELETE,
- CREATE_NOT_DIR, &srcfid, &oplock, NULL,
- cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.desired_access = DELETE;
+ oparms.create_options = CREATE_NOT_DIR;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = from_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc == 0) {
- rc = CIFSSMBRenameOpenFile(xid, tcon, srcfid,
+ rc = CIFSSMBRenameOpenFile(xid, tcon, fid.netfid,
(const char *) to_dentry->d_name.name,
cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
CIFS_MOUNT_MAP_SPECIAL_CHR);
- CIFSSMBClose(xid, tcon, srcfid);
+ CIFSSMBClose(xid, tcon, fid.netfid);
}
do_rename_exit:
cifs_put_tlink(tlink);
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 92aee08483a5..264ece71bdb2 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -29,6 +29,10 @@
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
+/*
+ * M-F Symlink Functions - Begin
+ */
+
#define CIFS_MF_SYMLINK_LEN_OFFSET (4+1)
#define CIFS_MF_SYMLINK_MD5_OFFSET (CIFS_MF_SYMLINK_LEN_OFFSET+(4+1))
#define CIFS_MF_SYMLINK_LINK_OFFSET (CIFS_MF_SYMLINK_MD5_OFFSET+(32+1))
@@ -91,10 +95,8 @@ symlink_hash_err:
}
static int
-CIFSParseMFSymlink(const u8 *buf,
- unsigned int buf_len,
- unsigned int *_link_len,
- char **_link_str)
+parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len,
+ char **_link_str)
{
int rc;
unsigned int link_len;
@@ -137,7 +139,7 @@ CIFSParseMFSymlink(const u8 *buf,
}
static int
-CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str)
+format_mf_symlink(u8 *buf, unsigned int buf_len, const char *link_str)
{
int rc;
unsigned int link_len;
@@ -180,190 +182,94 @@ CIFSFormatMFSymlink(u8 *buf, unsigned int buf_len, const char *link_str)
return 0;
}
+bool
+couldbe_mf_symlink(const struct cifs_fattr *fattr)
+{
+ if (!S_ISREG(fattr->cf_mode))
+ /* it's not a symlink */
+ return false;
+
+ if (fattr->cf_eof != CIFS_MF_SYMLINK_FILE_SIZE)
+ /* it's not a symlink */
+ return false;
+
+ return true;
+}
+
static int
-CIFSCreateMFSymLink(const unsigned int xid, struct cifs_tcon *tcon,
- const char *fromName, const char *toName,
- struct cifs_sb_info *cifs_sb)
+create_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, const char *fromName,
+ const char *toName)
{
int rc;
- int oplock = 0;
- int remap;
- int create_options = CREATE_NOT_DIR;
- __u16 netfid = 0;
u8 *buf;
unsigned int bytes_written = 0;
- struct cifs_io_parms io_parms;
- struct nls_table *nls_codepage;
-
- nls_codepage = cifs_sb->local_nls;
- remap = cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR;
buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
if (!buf)
return -ENOMEM;
- rc = CIFSFormatMFSymlink(buf, CIFS_MF_SYMLINK_FILE_SIZE, toName);
- if (rc != 0) {
- kfree(buf);
- return rc;
- }
-
- if (backup_cred(cifs_sb))
- create_options |= CREATE_OPEN_BACKUP_INTENT;
-
- rc = CIFSSMBOpen(xid, tcon, fromName, FILE_CREATE, GENERIC_WRITE,
- create_options, &netfid, &oplock, NULL,
- nls_codepage, remap);
- if (rc != 0) {
- kfree(buf);
- return rc;
- }
-
- io_parms.netfid = netfid;
- io_parms.pid = current->tgid;
- io_parms.tcon = tcon;
- io_parms.offset = 0;
- io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+ rc = format_mf_symlink(buf, CIFS_MF_SYMLINK_FILE_SIZE, toName);
+ if (rc)
+ goto out;
- rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, buf, NULL, 0);
- CIFSSMBClose(xid, tcon, netfid);
- kfree(buf);
- if (rc != 0)
- return rc;
+ rc = tcon->ses->server->ops->create_mf_symlink(xid, tcon, cifs_sb,
+ fromName, buf, &bytes_written);
+ if (rc)
+ goto out;
if (bytes_written != CIFS_MF_SYMLINK_FILE_SIZE)
- return -EIO;
-
- return 0;
+ rc = -EIO;
+out:
+ kfree(buf);
+ return rc;
}
static int
-CIFSQueryMFSymLink(const unsigned int xid, struct cifs_tcon *tcon,
- const unsigned char *searchName, char **symlinkinfo,
- const struct nls_table *nls_codepage, int remap)
+query_mf_symlink(const unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, const unsigned char *path,
+ char **symlinkinfo)
{
int rc;
- int oplock = 0;
- __u16 netfid = 0;
- u8 *buf;
- char *pbuf;
- unsigned int bytes_read = 0;
- int buf_type = CIFS_NO_BUFFER;
+ u8 *buf = NULL;
unsigned int link_len = 0;
- struct cifs_io_parms io_parms;
- FILE_ALL_INFO file_info;
-
- rc = CIFSSMBOpen(xid, tcon, searchName, FILE_OPEN, GENERIC_READ,
- CREATE_NOT_DIR, &netfid, &oplock, &file_info,
- nls_codepage, remap);
- if (rc != 0)
- return rc;
-
- if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
- CIFSSMBClose(xid, tcon, netfid);
- /* it's not a symlink */
- return -EINVAL;
- }
+ unsigned int bytes_read = 0;
buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
if (!buf)
return -ENOMEM;
- pbuf = buf;
- io_parms.netfid = netfid;
- io_parms.pid = current->tgid;
- io_parms.tcon = tcon;
- io_parms.offset = 0;
- io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
-
- rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
- CIFSSMBClose(xid, tcon, netfid);
- if (rc != 0) {
- kfree(buf);
- return rc;
- }
-
- rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, symlinkinfo);
- kfree(buf);
- if (rc != 0)
- return rc;
-
- return 0;
-}
-
-bool
-CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr)
-{
- if (!(fattr->cf_mode & S_IFREG))
- /* it's not a symlink */
- return false;
- if (fattr->cf_eof != CIFS_MF_SYMLINK_FILE_SIZE)
- /* it's not a symlink */
- return false;
-
- return true;
-}
-
-int
-open_query_close_cifs_symlink(const unsigned char *path, char *pbuf,
- unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
- unsigned int xid)
-{
- int rc;
- int oplock = 0;
- __u16 netfid = 0;
- struct tcon_link *tlink;
- struct cifs_tcon *ptcon;
- struct cifs_io_parms io_parms;
- int buf_type = CIFS_NO_BUFFER;
- FILE_ALL_INFO file_info;
-
- tlink = cifs_sb_tlink(cifs_sb);
- if (IS_ERR(tlink))
- return PTR_ERR(tlink);
- ptcon = tlink_tcon(tlink);
+ if (tcon->ses->server->ops->query_mf_symlink)
+ rc = tcon->ses->server->ops->query_mf_symlink(xid, tcon,
+ cifs_sb, path, buf, &bytes_read);
+ else
+ rc = -ENOSYS;
- rc = CIFSSMBOpen(xid, ptcon, path, FILE_OPEN, GENERIC_READ,
- CREATE_NOT_DIR, &netfid, &oplock, &file_info,
- cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
- if (rc != 0) {
- cifs_put_tlink(tlink);
- return rc;
- }
+ if (rc)
+ goto out;
- if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
- CIFSSMBClose(xid, ptcon, netfid);
- cifs_put_tlink(tlink);
- /* it's not a symlink */
- return rc;
+ if (bytes_read == 0) { /* not a symlink */
+ rc = -EINVAL;
+ goto out;
}
- io_parms.netfid = netfid;
- io_parms.pid = current->tgid;
- io_parms.tcon = ptcon;
- io_parms.offset = 0;
- io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
-
- rc = CIFSSMBRead(xid, &io_parms, pbytes_read, &pbuf, &buf_type);
- CIFSSMBClose(xid, ptcon, netfid);
- cifs_put_tlink(tlink);
+ rc = parse_mf_symlink(buf, bytes_read, &link_len, symlinkinfo);
+out:
+ kfree(buf);
return rc;
}
-
int
-CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
- struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
- const unsigned char *path)
+check_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
+ const unsigned char *path)
{
int rc;
u8 *buf = NULL;
unsigned int link_len = 0;
unsigned int bytes_read = 0;
- if (!CIFSCouldBeMFSymlink(fattr))
+ if (!couldbe_mf_symlink(fattr))
/* it's not a symlink */
return 0;
@@ -372,8 +278,8 @@ CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
return -ENOMEM;
if (tcon->ses->server->ops->query_mf_symlink)
- rc = tcon->ses->server->ops->query_mf_symlink(path, buf,
- &bytes_read, cifs_sb, xid);
+ rc = tcon->ses->server->ops->query_mf_symlink(xid, tcon,
+ cifs_sb, path, buf, &bytes_read);
else
rc = -ENOSYS;
@@ -383,7 +289,7 @@ CIFSCheckMFSymlink(unsigned int xid, struct cifs_tcon *tcon,
if (bytes_read == 0) /* not a symlink */
goto out;
- rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, NULL);
+ rc = parse_mf_symlink(buf, bytes_read, &link_len, NULL);
if (rc == -EINVAL) {
/* it's not a symlink */
rc = 0;
@@ -403,6 +309,95 @@ out:
return rc;
}
+/*
+ * SMB 1.0 Protocol specific functions
+ */
+
+int
+cifs_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, const unsigned char *path,
+ char *pbuf, unsigned int *pbytes_read)
+{
+ int rc;
+ int oplock = 0;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
+ struct cifs_io_parms io_parms;
+ int buf_type = CIFS_NO_BUFFER;
+ FILE_ALL_INFO file_info;
+
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = GENERIC_READ;
+ oparms.create_options = CREATE_NOT_DIR;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, &file_info);
+ if (rc)
+ return rc;
+
+ if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE))
+ /* it's not a symlink */
+ goto out;
+
+ io_parms.netfid = fid.netfid;
+ io_parms.pid = current->tgid;
+ io_parms.tcon = tcon;
+ io_parms.offset = 0;
+ io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+
+ rc = CIFSSMBRead(xid, &io_parms, pbytes_read, &pbuf, &buf_type);
+out:
+ CIFSSMBClose(xid, tcon, fid.netfid);
+ return rc;
+}
+
+int
+cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
+ struct cifs_sb_info *cifs_sb, const unsigned char *path,
+ char *pbuf, unsigned int *pbytes_written)
+{
+ int rc;
+ int oplock = 0;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
+ struct cifs_io_parms io_parms;
+ int create_options = CREATE_NOT_DIR;
+
+ if (backup_cred(cifs_sb))
+ create_options |= CREATE_OPEN_BACKUP_INTENT;
+
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = GENERIC_WRITE;
+ oparms.create_options = create_options;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
+ if (rc)
+ return rc;
+
+ io_parms.netfid = fid.netfid;
+ io_parms.pid = current->tgid;
+ io_parms.tcon = tcon;
+ io_parms.offset = 0;
+ io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
+
+ rc = CIFSSMBWrite(xid, &io_parms, pbytes_written, pbuf, NULL, 0);
+ CIFSSMBClose(xid, tcon, fid.netfid);
+ return rc;
+}
+
+/*
+ * M-F Symlink Functions - End
+ */
+
int
cifs_hardlink(struct dentry *old_file, struct inode *inode,
struct dentry *direntry)
@@ -438,8 +433,10 @@ cifs_hardlink(struct dentry *old_file, struct inode *inode,
CIFS_MOUNT_MAP_SPECIAL_CHR);
else {
server = tcon->ses->server;
- if (!server->ops->create_hardlink)
- return -ENOSYS;
+ if (!server->ops->create_hardlink) {
+ rc = -ENOSYS;
+ goto cifs_hl_exit;
+ }
rc = server->ops->create_hardlink(xid, tcon, from_name, to_name,
cifs_sb);
if ((rc == -EIO) || (rc == -EINVAL))
@@ -530,15 +527,10 @@ cifs_follow_link(struct dentry *direntry, struct nameidata *nd)
* and fallback to UNIX Extensions Symlinks.
*/
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
- rc = CIFSQueryMFSymLink(xid, tcon, full_path, &target_path,
- cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ rc = query_mf_symlink(xid, tcon, cifs_sb, full_path,
+ &target_path);
- if ((rc != 0) && cap_unix(tcon->ses))
- rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, &target_path,
- cifs_sb->local_nls);
- else if (rc != 0 && server->ops->query_symlink)
+ if (rc != 0 && server->ops->query_symlink)
rc = server->ops->query_symlink(xid, tcon, full_path,
&target_path, cifs_sb);
@@ -587,8 +579,7 @@ cifs_symlink(struct inode *inode, struct dentry *direntry, const char *symname)
/* BB what if DFS and this volume is on different share? BB */
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS)
- rc = CIFSCreateMFSymLink(xid, pTcon, full_path, symname,
- cifs_sb);
+ rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname);
else if (pTcon->unix_ext)
rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname,
cifs_sb->local_nls);
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 5940ecabbe6a..b15862e0f68c 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -749,7 +749,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
}
if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) &&
- CIFSCouldBeMFSymlink(&fattr))
+ couldbe_mf_symlink(&fattr))
/*
* trying to get the type and mode can be slow,
* so just call those regular files for now, and mark
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 5f5ba0dc2ee1..526fb89f9230 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -560,17 +560,24 @@ cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
if (!rc && (le32_to_cpu(data->Attributes) & ATTR_REPARSE)) {
int tmprc;
int oplock = 0;
- __u16 netfid;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
+
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = FILE_READ_ATTRIBUTES;
+ oparms.create_options = 0;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = full_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
/* Need to check if this is a symbolic link or not */
- tmprc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
- FILE_READ_ATTRIBUTES, 0, &netfid, &oplock,
- NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ tmprc = CIFS_open(xid, &oparms, &oplock, NULL);
if (tmprc == -EOPNOTSUPP)
*symlink = true;
else
- CIFSSMBClose(xid, tcon, netfid);
+ CIFSSMBClose(xid, tcon, fid.netfid);
}
return rc;
@@ -705,12 +712,7 @@ cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
oparms->cifs_sb->local_nls,
oparms->cifs_sb->mnt_cifs_flags
& CIFS_MOUNT_MAP_SPECIAL_CHR);
- return CIFSSMBOpen(xid, oparms->tcon, oparms->path,
- oparms->disposition, oparms->desired_access,
- oparms->create_options, &oparms->fid->netfid, oplock,
- buf, oparms->cifs_sb->local_nls,
- oparms->cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ return CIFS_open(xid, oparms, oplock, buf);
}
static void
@@ -761,8 +763,9 @@ smb_set_file_info(struct inode *inode, const char *full_path,
{
int oplock = 0;
int rc;
- __u16 netfid;
__u32 netpid;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
struct cifsFileInfo *open_file;
struct cifsInodeInfo *cinode = CIFS_I(inode);
struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
@@ -772,7 +775,7 @@ smb_set_file_info(struct inode *inode, const char *full_path,
/* if the file is already open for write, just use that fileid */
open_file = find_writable_file(cinode, true);
if (open_file) {
- netfid = open_file->fid.netfid;
+ fid.netfid = open_file->fid.netfid;
netpid = open_file->pid;
tcon = tlink_tcon(open_file->tlink);
goto set_via_filehandle;
@@ -796,12 +799,17 @@ smb_set_file_info(struct inode *inode, const char *full_path,
goto out;
}
- cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for times not supported by this server\n");
- rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
- SYNCHRONIZE | FILE_WRITE_ATTRIBUTES, CREATE_NOT_DIR,
- &netfid, &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = SYNCHRONIZE | FILE_WRITE_ATTRIBUTES;
+ oparms.create_options = CREATE_NOT_DIR;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = full_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+ cifs_dbg(FYI, "calling SetFileInfo since SetPathInfo for times not supported by this server\n");
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc != 0) {
if (rc == -EIO)
rc = -EINVAL;
@@ -811,12 +819,12 @@ smb_set_file_info(struct inode *inode, const char *full_path,
netpid = current->tgid;
set_via_filehandle:
- rc = CIFSSMBSetFileInfo(xid, tcon, buf, netfid, netpid);
+ rc = CIFSSMBSetFileInfo(xid, tcon, buf, fid.netfid, netpid);
if (!rc)
cinode->cifsAttrs = le32_to_cpu(buf->Attributes);
if (open_file == NULL)
- CIFSSMBClose(xid, tcon, netfid);
+ CIFSSMBClose(xid, tcon, fid.netfid);
else
cifsFileInfo_put(open_file);
out:
@@ -908,33 +916,80 @@ cifs_mand_lock(const unsigned int xid, struct cifsFileInfo *cfile, __u64 offset,
}
static int
+cifs_unix_dfs_readlink(const unsigned int xid, struct cifs_tcon *tcon,
+ const unsigned char *searchName, char **symlinkinfo,
+ const struct nls_table *nls_codepage)
+{
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ int rc;
+ unsigned int num_referrals = 0;
+ struct dfs_info3_param *referrals = NULL;
+
+ rc = get_dfs_path(xid, tcon->ses, searchName, nls_codepage,
+ &num_referrals, &referrals, 0);
+
+ if (!rc && num_referrals > 0) {
+ *symlinkinfo = kstrndup(referrals->node_name,
+ strlen(referrals->node_name),
+ GFP_KERNEL);
+ if (!*symlinkinfo)
+ rc = -ENOMEM;
+ free_dfs_info_array(referrals, num_referrals);
+ }
+ return rc;
+#else /* No DFS support */
+ return -EREMOTE;
+#endif
+}
+
+static int
cifs_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
const char *full_path, char **target_path,
struct cifs_sb_info *cifs_sb)
{
int rc;
int oplock = 0;
- __u16 netfid;
+ struct cifs_fid fid;
+ struct cifs_open_parms oparms;
cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
- rc = CIFSSMBOpen(xid, tcon, full_path, FILE_OPEN,
- FILE_READ_ATTRIBUTES, OPEN_REPARSE_POINT, &netfid,
- &oplock, NULL, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ /* Check for unix extensions */
+ if (cap_unix(tcon->ses)) {
+ rc = CIFSSMBUnixQuerySymLink(xid, tcon, full_path, target_path,
+ cifs_sb->local_nls);
+ if (rc == -EREMOTE)
+ rc = cifs_unix_dfs_readlink(xid, tcon, full_path,
+ target_path,
+ cifs_sb->local_nls);
+
+ goto out;
+ }
+
+ oparms.tcon = tcon;
+ oparms.cifs_sb = cifs_sb;
+ oparms.desired_access = FILE_READ_ATTRIBUTES;
+ oparms.create_options = OPEN_REPARSE_POINT;
+ oparms.disposition = FILE_OPEN;
+ oparms.path = full_path;
+ oparms.fid = &fid;
+ oparms.reconnect = false;
+
+ rc = CIFS_open(xid, &oparms, &oplock, NULL);
if (rc)
- return rc;
+ goto out;
- rc = CIFSSMBQuerySymLink(xid, tcon, netfid, target_path,
+ rc = CIFSSMBQuerySymLink(xid, tcon, fid.netfid, target_path,
cifs_sb->local_nls);
- if (rc) {
- CIFSSMBClose(xid, tcon, netfid);
- return rc;
- }
+ if (rc)
+ goto out_close;
convert_delimiter(*target_path, '/');
- CIFSSMBClose(xid, tcon, netfid);
- cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
+out_close:
+ CIFSSMBClose(xid, tcon, fid.netfid);
+out:
+ if (!rc)
+ cifs_dbg(FYI, "%s: target path: %s\n", __func__, *target_path);
return rc;
}
@@ -1009,8 +1064,18 @@ struct smb_version_operations smb1_operations = {
.mand_lock = cifs_mand_lock,
.mand_unlock_range = cifs_unlock_range,
.push_mand_locks = cifs_push_mandatory_locks,
- .query_mf_symlink = open_query_close_cifs_symlink,
+ .query_mf_symlink = cifs_query_mf_symlink,
+ .create_mf_symlink = cifs_create_mf_symlink,
.is_read_op = cifs_is_read_op,
+#ifdef CONFIG_CIFS_XATTR
+ .query_all_EAs = CIFSSMBQAllEAs,
+ .set_EA = CIFSSMBSetEA,
+#endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+ .get_acl = get_cifs_acl,
+ .get_acl_by_fid = get_cifs_acl_by_fid,
+ .set_acl = set_cifs_acl,
+#endif /* CIFS_ACL */
};
struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index c38350851b08..bc0bb9c34f72 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -57,4 +57,7 @@
#define SMB2_CMACAES_SIZE (16)
#define SMB3_SIGNKEY_SIZE (16)
+/* Maximum buffer size value we can send with 1 credit */
+#define SMB2_MAX_BUFFER_SIZE 65536
+
#endif /* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 757da3e54d3d..192f51a12cf1 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -182,11 +182,8 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
/* start with specified wsize, or default */
wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE;
wsize = min_t(unsigned int, wsize, server->max_write);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- wsize = min_t(unsigned int, wsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE);
return wsize;
}
@@ -200,11 +197,8 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info)
/* start with specified rsize, or default */
rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE;
rsize = min_t(unsigned int, rsize, server->max_read);
- /*
- * limit write size to 2 ** 16, because we don't support multicredit
- * requests now.
- */
- rsize = min_t(unsigned int, rsize, 2 << 15);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ rsize = min_t(unsigned int, rsize, SMB2_MAX_BUFFER_SIZE);
return rsize;
}
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 2013234b73ad..860344701067 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -413,7 +413,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
/* SMB2 only has an extended negflavor */
server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
- server->maxBuf = le32_to_cpu(rsp->MaxTransactSize);
+ /* set it to the maximum buffer size value we can send with 1 credit */
+ server->maxBuf = min_t(unsigned int, le32_to_cpu(rsp->MaxTransactSize),
+ SMB2_MAX_BUFFER_SIZE);
server->max_read = le32_to_cpu(rsp->MaxReadSize);
server->max_write = le32_to_cpu(rsp->MaxWriteSize);
/* BB Do we need to validate the SecurityMode? */
@@ -1890,7 +1892,8 @@ smb2_writev_callback(struct mid_q_entry *mid)
/* smb2_async_writev - send an async write, and set up mid to handle result */
int
-smb2_async_writev(struct cifs_writedata *wdata)
+smb2_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref))
{
int rc = -EACCES;
struct smb2_write_req *req = NULL;
@@ -1938,7 +1941,7 @@ smb2_async_writev(struct cifs_writedata *wdata)
smb2_writev_callback, wdata, 0);
if (rc) {
- kref_put(&wdata->refcount, cifs_writedata_release);
+ kref_put(&wdata->refcount, release);
cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
}
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 93adc64666f3..0ce48db20a65 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -123,7 +123,8 @@ extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon,
extern int smb2_async_readv(struct cifs_readdata *rdata);
extern int SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, char **buf, int *buf_type);
-extern int smb2_async_writev(struct cifs_writedata *wdata);
+extern int smb2_async_writev(struct cifs_writedata *wdata,
+ void (*release)(struct kref *kref));
extern int SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
unsigned int *nbytes, struct kvec *iov, int n_vec);
extern int SMB2_echo(struct TCP_Server_Info *server);
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 09afda4cc58e..5ac836a86b18 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -82,9 +82,11 @@ int cifs_removexattr(struct dentry *direntry, const char *ea_name)
goto remove_ea_exit;
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, NULL,
- (__u16)0, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, NULL, (__u16)0,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
}
remove_ea_exit:
kfree(full_path);
@@ -149,18 +151,22 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
cifs_dbg(FYI, "attempt to set cifs inode metadata\n");
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
- (__u16)value_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, ea_value, (__u16)value_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN)
== 0) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
goto set_ea_exit;
ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- rc = CIFSSMBSetEA(xid, pTcon, full_path, ea_name, ea_value,
- (__u16)value_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->set_EA)
+ rc = pTcon->ses->server->ops->set_EA(xid, pTcon,
+ full_path, ea_name, ea_value, (__u16)value_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, CIFS_XATTR_CIFS_ACL,
strlen(CIFS_XATTR_CIFS_ACL)) == 0) {
#ifdef CONFIG_CIFS_ACL
@@ -170,8 +176,12 @@ int cifs_setxattr(struct dentry *direntry, const char *ea_name,
rc = -ENOMEM;
} else {
memcpy(pacl, ea_value, value_size);
- rc = set_cifs_acl(pacl, value_size,
- direntry->d_inode, full_path, CIFS_ACL_DACL);
+ if (pTcon->ses->server->ops->set_acl)
+ rc = pTcon->ses->server->ops->set_acl(pacl,
+ value_size, direntry->d_inode,
+ full_path, CIFS_ACL_DACL);
+ else
+ rc = -EOPNOTSUPP;
if (rc == 0) /* force revalidate of the inode */
CIFS_I(direntry->d_inode)->time = 0;
kfree(pacl);
@@ -272,17 +282,21 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
/* revalidate/getattr then populate from inode */
} /* BB add else when above is implemented */
ea_name += XATTR_USER_PREFIX_LEN; /* skip past user. prefix */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, ea_name, ea_value, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, XATTR_OS2_PREFIX, XATTR_OS2_PREFIX_LEN) == 0) {
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR)
goto get_ea_exit;
ea_name += XATTR_OS2_PREFIX_LEN; /* skip past os2. prefix */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, ea_name, ea_value,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, ea_name, ea_value, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
} else if (strncmp(ea_name, POSIX_ACL_XATTR_ACCESS,
strlen(POSIX_ACL_XATTR_ACCESS)) == 0) {
#ifdef CONFIG_CIFS_POSIX
@@ -313,8 +327,11 @@ ssize_t cifs_getxattr(struct dentry *direntry, const char *ea_name,
u32 acllen;
struct cifs_ntsd *pacl;
- pacl = get_cifs_acl(cifs_sb, direntry->d_inode,
- full_path, &acllen);
+ if (pTcon->ses->server->ops->get_acl == NULL)
+ goto get_ea_exit; /* rc already EOPNOTSUPP */
+
+ pacl = pTcon->ses->server->ops->get_acl(cifs_sb,
+ direntry->d_inode, full_path, &acllen);
if (IS_ERR(pacl)) {
rc = PTR_ERR(pacl);
cifs_dbg(VFS, "%s: error %zd getting sec desc\n",
@@ -400,11 +417,12 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
/* if proc/fs/cifs/streamstoxattr is set then
search server for EAs or streams to
returns as xattrs */
- rc = CIFSSMBQAllEAs(xid, pTcon, full_path, NULL, data,
- buf_size, cifs_sb->local_nls,
- cifs_sb->mnt_cifs_flags &
- CIFS_MOUNT_MAP_SPECIAL_CHR);
+ if (pTcon->ses->server->ops->query_all_EAs)
+ rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
+ full_path, NULL, data, buf_size,
+ cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
list_ea_exit:
kfree(full_path);
free_xid(xid);
diff --git a/fs/dcookies.c b/fs/dcookies.c
index ab5954b50267..ac44a69fbea9 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -204,7 +204,7 @@ out:
}
#ifdef CONFIG_COMPAT
-COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, size_t, len)
+COMPAT_SYSCALL_DEFINE4(lookup_dcookie, u32, w0, u32, w1, char __user *, buf, compat_size_t, len)
{
#ifdef __BIG_ENDIAN
return sys_lookup_dcookie(((u64)w0 << 32) | w1, buf, len);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0e04142d5962..160a5489a939 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -375,7 +375,7 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
bio = bio_alloc(GFP_KERNEL, nr_vecs);
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
if (dio->is_async)
bio->bi_end_io = dio_bio_end_aio;
else
@@ -719,7 +719,7 @@ static inline int dio_send_cur_page(struct dio *dio, struct dio_submit *sdio,
if (sdio->bio) {
loff_t cur_offset = sdio->cur_page_fs_offset;
loff_t bio_next_offset = sdio->logical_offset_in_bio +
- sdio->bio->bi_size;
+ sdio->bio->bi_iter.bi_size;
/*
* See whether this new request is contiguous with the old.
diff --git a/fs/exec.c b/fs/exec.c
index e1529b4c79b1..3d78fccdd723 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -748,11 +748,10 @@ EXPORT_SYMBOL(setup_arg_pages);
#endif /* CONFIG_MMU */
-struct file *open_exec(const char *name)
+static struct file *do_open_exec(struct filename *name)
{
struct file *file;
int err;
- struct filename tmp = { .name = name };
static const struct open_flags open_exec_flags = {
.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
.acc_mode = MAY_EXEC | MAY_OPEN,
@@ -760,7 +759,7 @@ struct file *open_exec(const char *name)
.lookup_flags = LOOKUP_FOLLOW,
};
- file = do_filp_open(AT_FDCWD, &tmp, &open_exec_flags);
+ file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
if (IS_ERR(file))
goto out;
@@ -784,6 +783,12 @@ exit:
fput(file);
return ERR_PTR(err);
}
+
+struct file *open_exec(const char *name)
+{
+ struct filename tmp = { .name = name };
+ return do_open_exec(&tmp);
+}
EXPORT_SYMBOL(open_exec);
int kernel_read(struct file *file, loff_t offset,
@@ -1162,7 +1167,7 @@ int prepare_bprm_creds(struct linux_binprm *bprm)
return -ENOMEM;
}
-void free_bprm(struct linux_binprm *bprm)
+static void free_bprm(struct linux_binprm *bprm)
{
free_arg_pages(bprm);
if (bprm->cred) {
@@ -1432,7 +1437,7 @@ static int exec_binprm(struct linux_binprm *bprm)
/*
* sys_execve() executes a new program.
*/
-static int do_execve_common(const char *filename,
+static int do_execve_common(struct filename *filename,
struct user_arg_ptr argv,
struct user_arg_ptr envp)
{
@@ -1441,6 +1446,9 @@ static int do_execve_common(const char *filename,
struct files_struct *displaced;
int retval;
+ if (IS_ERR(filename))
+ return PTR_ERR(filename);
+
/*
* We move the actual failure in case of RLIMIT_NPROC excess from
* set*uid() to execve() because too many poorly written programs
@@ -1473,7 +1481,7 @@ static int do_execve_common(const char *filename,
check_unsafe_exec(bprm);
current->in_execve = 1;
- file = open_exec(filename);
+ file = do_open_exec(filename);
retval = PTR_ERR(file);
if (IS_ERR(file))
goto out_unmark;
@@ -1481,8 +1489,7 @@ static int do_execve_common(const char *filename,
sched_exec();
bprm->file = file;
- bprm->filename = filename;
- bprm->interp = filename;
+ bprm->filename = bprm->interp = filename->name;
retval = bprm_mm_init(bprm);
if (retval)
@@ -1523,6 +1530,7 @@ static int do_execve_common(const char *filename,
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
+ putname(filename);
if (displaced)
put_files_struct(displaced);
return retval;
@@ -1544,10 +1552,11 @@ out_files:
if (displaced)
reset_files_struct(displaced);
out_ret:
+ putname(filename);
return retval;
}
-int do_execve(const char *filename,
+int do_execve(struct filename *filename,
const char __user *const __user *__argv,
const char __user *const __user *__envp)
{
@@ -1557,7 +1566,7 @@ int do_execve(const char *filename,
}
#ifdef CONFIG_COMPAT
-static int compat_do_execve(const char *filename,
+static int compat_do_execve(struct filename *filename,
const compat_uptr_t __user *__argv,
const compat_uptr_t __user *__envp)
{
@@ -1607,25 +1616,13 @@ SYSCALL_DEFINE3(execve,
const char __user *const __user *, argv,
const char __user *const __user *, envp)
{
- struct filename *path = getname(filename);
- int error = PTR_ERR(path);
- if (!IS_ERR(path)) {
- error = do_execve(path->name, argv, envp);
- putname(path);
- }
- return error;
+ return do_execve(getname(filename), argv, envp);
}
#ifdef CONFIG_COMPAT
asmlinkage long compat_sys_execve(const char __user * filename,
const compat_uptr_t __user * argv,
const compat_uptr_t __user * envp)
{
- struct filename *path = getname(filename);
- int error = PTR_ERR(path);
- if (!IS_ERR(path)) {
- error = compat_do_execve(path->name, argv, envp);
- putname(path);
- }
- return error;
+ return compat_do_execve(getname(filename), argv, envp);
}
#endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index ece55565b9cd..d3a534fdc5ff 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -771,6 +771,8 @@ do { \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \
(einode)->xtime.tv_sec = \
(signed)le32_to_cpu((raw_inode)->xtime); \
+ else \
+ (einode)->xtime.tv_sec = 0; \
if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime ## _extra)) \
ext4_decode_extra_time(&(einode)->xtime, \
raw_inode->xtime ## _extra); \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 10cff4736b11..74bc2d549c58 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3906,6 +3906,7 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
} else
err = ret;
map->m_flags |= EXT4_MAP_MAPPED;
+ map->m_pblk = newblock;
if (allocated > map->m_len)
allocated = map->m_len;
map->m_len = allocated;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 43e64f6022eb..1a5073959f32 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -152,7 +152,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
if (ret > 0) {
ssize_t err;
- err = generic_write_sync(file, pos, ret);
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0 && ret > 0)
ret = err;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 6bea80614d77..a2a837f00407 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -140,7 +140,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
- goto swap_boot_out;
+ goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
@@ -198,6 +198,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
ext4_double_up_write_data_sem(inode, inode_bl);
+journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index d488f80ee32d..ab95508e3d40 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -65,9 +65,9 @@ static void ext4_finish_bio(struct bio *bio)
{
int i;
int error = !test_bit(BIO_UPTODATE, &bio->bi_flags);
+ struct bio_vec *bvec;
- for (i = 0; i < bio->bi_vcnt; i++) {
- struct bio_vec *bvec = &bio->bi_io_vec[i];
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct buffer_head *bh, *head;
unsigned bio_start = bvec->bv_offset;
@@ -298,7 +298,7 @@ ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end)
static void ext4_end_bio(struct bio *bio, int error)
{
ext4_io_end_t *io_end = bio->bi_private;
- sector_t bi_sector = bio->bi_sector;
+ sector_t bi_sector = bio->bi_iter.bi_sector;
BUG_ON(!io_end);
bio->bi_end_io = NULL;
@@ -366,7 +366,7 @@ static int io_submit_init_bio(struct ext4_io_submit *io,
bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES));
if (!bio)
return -ENOMEM;
- bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
bio->bi_end_io = ext4_end_bio;
bio->bi_private = ext4_get_io_end(io->io_end);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c5adbb318a90..f3b84cd9de56 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -243,6 +243,7 @@ static int ext4_alloc_group_tables(struct super_block *sb,
ext4_group_t group;
ext4_group_t last_group;
unsigned overhead;
+ __u16 uninit_mask = (flexbg_size > 1) ? ~EXT4_BG_BLOCK_UNINIT : ~0;
BUG_ON(flex_gd->count == 0 || group_data == NULL);
@@ -266,7 +267,7 @@ next_group:
src_group++;
for (; src_group <= last_group; src_group++) {
overhead = ext4_group_overhead_blocks(sb, src_group);
- if (overhead != 0)
+ if (overhead == 0)
last_blk += group_data[src_group - group].blocks_count;
else
break;
@@ -280,8 +281,7 @@ next_group:
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode bitmaps */
@@ -292,22 +292,30 @@ next_group:
group = ext4_get_group_number(sb, start_blk - 1);
group -= group_data[0].group;
group_data[group].free_blocks_count--;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ flex_gd->bg_flags[group] &= uninit_mask;
}
/* Allocate inode tables */
for (; it_index < flex_gd->count; it_index++) {
- if (start_blk + EXT4_SB(sb)->s_itb_per_group > last_blk)
+ unsigned int itb = EXT4_SB(sb)->s_itb_per_group;
+ ext4_fsblk_t next_group_start;
+
+ if (start_blk + itb > last_blk)
goto next_group;
group_data[it_index].inode_table = start_blk;
- group = ext4_get_group_number(sb, start_blk - 1);
+ group = ext4_get_group_number(sb, start_blk);
+ next_group_start = ext4_group_first_block_no(sb, group + 1);
group -= group_data[0].group;
- group_data[group].free_blocks_count -=
- EXT4_SB(sb)->s_itb_per_group;
- if (flexbg_size > 1)
- flex_gd->bg_flags[group] &= ~EXT4_BG_BLOCK_UNINIT;
+ if (start_blk + itb > next_group_start) {
+ flex_gd->bg_flags[group + 1] &= uninit_mask;
+ overhead = start_blk + itb - next_group_start;
+ group_data[group + 1].free_blocks_count -= overhead;
+ itb -= overhead;
+ }
+
+ group_data[group].free_blocks_count -= itb;
+ flex_gd->bg_flags[group] &= uninit_mask;
start_blk += EXT4_SB(sb)->s_itb_per_group;
}
@@ -401,7 +409,7 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle,
start = ext4_group_first_block_no(sb, group);
group -= flex_gd->groups[0].group;
- count2 = sb->s_blocksize * 8 - (block - start);
+ count2 = EXT4_BLOCKS_PER_GROUP(sb) - (block - start);
if (count2 > count)
count2 = count;
@@ -620,7 +628,7 @@ handle_ib:
if (err)
goto out;
count = group_table_count[j];
- start = group_data[i].block_bitmap;
+ start = (&group_data[i].block_bitmap)[j];
block = start;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 1f7784de05b6..710fed2377d4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3695,16 +3695,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
for (i = 0; i < 4; i++)
sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
sbi->s_def_hash_version = es->s_def_hash_version;
- i = le32_to_cpu(es->s_flags);
- if (i & EXT2_FLAGS_UNSIGNED_HASH)
- sbi->s_hash_unsigned = 3;
- else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+ if (EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX)) {
+ i = le32_to_cpu(es->s_flags);
+ if (i & EXT2_FLAGS_UNSIGNED_HASH)
+ sbi->s_hash_unsigned = 3;
+ else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
#ifdef __CHAR_UNSIGNED__
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
- sbi->s_hash_unsigned = 3;
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+ sbi->s_hash_unsigned = 3;
#else
- es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+ if (!(sb->s_flags & MS_RDONLY))
+ es->s_flags |=
+ cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
#endif
+ }
}
/* Handle clustersize */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0ae558723506..2261ccdd0b5f 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -26,40 +26,33 @@
static void f2fs_read_end_io(struct bio *bio, int err)
{
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
- if (unlikely(!uptodate)) {
+ if (!err) {
+ SetPageUptodate(page);
+ } else {
ClearPageUptodate(page);
SetPageError(page);
- } else {
- SetPageUptodate(page);
}
unlock_page(page);
- } while (bvec >= bio->bi_io_vec);
-
+ }
bio_put(bio);
}
static void f2fs_write_end_io(struct bio *bio, int err)
{
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
- struct f2fs_sb_info *sbi = F2FS_SB(bvec->bv_page->mapping->host->i_sb);
+ struct f2fs_sb_info *sbi = F2FS_SB(bio->bi_io_vec->bv_page->mapping->host->i_sb);
+ struct bio_vec *bvec;
+ int i;
- do {
+ bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
- if (unlikely(!uptodate)) {
+ if (unlikely(err)) {
SetPageError(page);
set_bit(AS_EIO, &page->mapping->flags);
set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG);
@@ -67,7 +60,7 @@ static void f2fs_write_end_io(struct bio *bio, int err)
}
end_page_writeback(page);
dec_page_count(sbi, F2FS_WRITEBACK);
- } while (bvec >= bio->bi_io_vec);
+ }
if (bio->bi_private)
complete(bio->bi_private);
@@ -91,7 +84,7 @@ static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
bio = bio_alloc(GFP_NOIO, npages);
bio->bi_bdev = sbi->sb->s_bdev;
- bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
return bio;
diff --git a/fs/file.c b/fs/file.c
index 771578b33fb6..db25c2bdfe46 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -34,7 +34,7 @@ static void *alloc_fdmem(size_t size)
* vmalloc() if the allocation size will be considered "large" by the VM.
*/
if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
- void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN);
+ void *data = kmalloc(size, GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY);
if (data != NULL)
return data;
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e0259a163f98..d754e3cf99a8 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -40,18 +40,13 @@
struct wb_writeback_work {
long nr_pages;
struct super_block *sb;
- /*
- * Write only inodes dirtied before this time. Don't forget to set
- * older_than_this_is_set when you set this.
- */
- unsigned long older_than_this;
+ unsigned long *older_than_this;
enum writeback_sync_modes sync_mode;
unsigned int tagged_writepages:1;
unsigned int for_kupdate:1;
unsigned int range_cyclic:1;
unsigned int for_background:1;
unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */
- unsigned int older_than_this_is_set:1;
enum wb_reason reason; /* why was writeback initiated? */
struct list_head list; /* pending work list */
@@ -252,10 +247,10 @@ static int move_expired_inodes(struct list_head *delaying_queue,
int do_sb_sort = 0;
int moved = 0;
- WARN_ON_ONCE(!work->older_than_this_is_set);
while (!list_empty(delaying_queue)) {
inode = wb_inode(delaying_queue->prev);
- if (inode_dirtied_after(inode, work->older_than_this))
+ if (work->older_than_this &&
+ inode_dirtied_after(inode, *work->older_than_this))
break;
list_move(&inode->i_wb_list, &tmp);
moved++;
@@ -742,8 +737,6 @@ static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
.sync_mode = WB_SYNC_NONE,
.range_cyclic = 1,
.reason = reason,
- .older_than_this = jiffies,
- .older_than_this_is_set = 1,
};
spin_lock(&wb->list_lock);
@@ -802,13 +795,12 @@ static long wb_writeback(struct bdi_writeback *wb,
{
unsigned long wb_start = jiffies;
long nr_pages = work->nr_pages;
+ unsigned long oldest_jif;
struct inode *inode;
long progress;
- if (!work->older_than_this_is_set) {
- work->older_than_this = jiffies;
- work->older_than_this_is_set = 1;
- }
+ oldest_jif = jiffies;
+ work->older_than_this = &oldest_jif;
spin_lock(&wb->list_lock);
for (;;) {
@@ -842,10 +834,10 @@ static long wb_writeback(struct bdi_writeback *wb,
* safe.
*/
if (work->for_kupdate) {
- work->older_than_this = jiffies -
+ oldest_jif = jiffies -
msecs_to_jiffies(dirty_expire_interval * 10);
} else if (work->for_background)
- work->older_than_this = jiffies;
+ oldest_jif = jiffies;
trace_writeback_start(wb->bdi, work);
if (list_empty(&wb->b_io))
@@ -1357,21 +1349,18 @@ EXPORT_SYMBOL(try_to_writeback_inodes_sb);
/**
* sync_inodes_sb - sync sb inode pages
- * @sb: the superblock
- * @older_than_this: timestamp
+ * @sb: the superblock
*
* This function writes and waits on any dirty inode belonging to this
- * superblock that has been dirtied before given timestamp.
+ * super_block.
*/
-void sync_inodes_sb(struct super_block *sb, unsigned long older_than_this)
+void sync_inodes_sb(struct super_block *sb)
{
DECLARE_COMPLETION_ONSTACK(done);
struct wb_writeback_work work = {
.sb = sb,
.sync_mode = WB_SYNC_ALL,
.nr_pages = LONG_MAX,
- .older_than_this = older_than_this,
- .older_than_this_is_set = 1,
.range_cyclic = 0,
.done = &done,
.reason = WB_REASON_SYNC,
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index e1959efad64f..b5ebc2d7d80d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -50,6 +50,8 @@ void fscache_objlist_add(struct fscache_object *obj)
struct fscache_object *xobj;
struct rb_node **p = &fscache_object_list.rb_node, *parent = NULL;
+ ASSERT(RB_EMPTY_NODE(&obj->objlist_link));
+
write_lock(&fscache_object_list_lock);
while (*p) {
@@ -75,6 +77,9 @@ void fscache_objlist_add(struct fscache_object *obj)
*/
void fscache_objlist_remove(struct fscache_object *obj)
{
+ if (RB_EMPTY_NODE(&obj->objlist_link))
+ return;
+
write_lock(&fscache_object_list_lock);
BUG_ON(RB_EMPTY_ROOT(&fscache_object_list));
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 53d35c504240..d3b4539f1651 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -314,6 +314,9 @@ void fscache_object_init(struct fscache_object *object,
object->cache = cache;
object->cookie = cookie;
object->parent = NULL;
+#ifdef CONFIG_FSCACHE_OBJECT_LIST
+ RB_CLEAR_NODE(&object->objlist_link);
+#endif
object->oob_event_mask = 0;
for (t = object->oob_table; t->events; t++)
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 58f06400b7b8..76693793cedd 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -273,7 +273,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno)
nrvecs = max(nrvecs/2, 1U);
}
- bio->bi_sector = blkno * (sb->s_blocksize >> 9);
+ bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9);
bio->bi_bdev = sb->s_bdev;
bio->bi_end_io = gfs2_end_log_write;
bio->bi_private = sdp;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 1e712b566d76..c6872d09561a 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -238,7 +238,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
lock_page(page);
bio = bio_alloc(GFP_NOFS, 1);
- bio->bi_sector = sector * (sb->s_blocksize >> 9);
+ bio->bi_iter.bi_sector = sector * (sb->s_blocksize >> 9);
bio->bi_bdev = sb->s_bdev;
bio_add_page(bio, page, PAGE_SIZE, 0);
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 9ee62985e739..bdec66522de3 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -529,7 +529,7 @@ const struct inode_operations hfsplus_dir_inode_operations = {
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
- .removexattr = hfsplus_removexattr,
+ .removexattr = generic_removexattr,
#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
.get_acl = hfsplus_get_posix_acl,
.set_acl = hfsplus_set_posix_acl,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 4551cbd6bd43..fa929f325f87 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -331,7 +331,7 @@ static const struct inode_operations hfsplus_file_inode_operations = {
.setxattr = generic_setxattr,
.getxattr = generic_getxattr,
.listxattr = hfsplus_listxattr,
- .removexattr = hfsplus_removexattr,
+ .removexattr = generic_removexattr,
#ifdef CONFIG_HFSPLUS_FS_POSIX_ACL
.get_acl = hfsplus_get_posix_acl,
.set_acl = hfsplus_set_posix_acl,
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index 968eab5bc1f5..68537e8b7a09 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -75,7 +75,7 @@ int hfsplus_parse_options_remount(char *input, int *force)
int token;
if (!input)
- return 0;
+ return 1;
while ((p = strsep(&input, ",")) != NULL) {
if (!*p)
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index e9a97a0d4314..3f999649587f 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -63,7 +63,7 @@ int hfsplus_submit_bio(struct super_block *sb, sector_t sector,
sector &= ~((io_size >> HFSPLUS_SECTOR_SHIFT) - 1);
bio = bio_alloc(GFP_NOIO, 1);
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
bio->bi_bdev = sb->s_bdev;
if (!(rw & WRITE) && data)
diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
index 0b4a5c9b93c4..4e27edc082a4 100644
--- a/fs/hfsplus/xattr.c
+++ b/fs/hfsplus/xattr.c
@@ -11,6 +11,8 @@
#include "xattr.h"
#include "acl.h"
+static int hfsplus_removexattr(struct inode *inode, const char *name);
+
const struct xattr_handler *hfsplus_xattr_handlers[] = {
&hfsplus_xattr_osx_handler,
&hfsplus_xattr_user_handler,
@@ -274,14 +276,8 @@ int __hfsplus_setxattr(struct inode *inode, const char *name,
HFSPLUS_IS_RSRC(inode))
return -EOPNOTSUPP;
- if (strncmp(name, XATTR_MAC_OSX_PREFIX,
- XATTR_MAC_OSX_PREFIX_LEN) == 0)
- name += XATTR_MAC_OSX_PREFIX_LEN;
-
- if (value == NULL) {
- value = "";
- size = 0;
- }
+ if (value == NULL)
+ return hfsplus_removexattr(inode, name);
err = hfs_find_init(HFSPLUS_SB(inode->i_sb)->cat_tree, &cat_fd);
if (err) {
@@ -399,16 +395,11 @@ end_setxattr:
return err;
}
-static inline int is_osx_xattr(const char *xattr_name)
-{
- return !is_known_namespace(xattr_name);
-}
-
static int name_len(const char *xattr_name, int xattr_name_len)
{
int len = xattr_name_len + 1;
- if (is_osx_xattr(xattr_name))
+ if (!is_known_namespace(xattr_name))
len += XATTR_MAC_OSX_PREFIX_LEN;
return len;
@@ -419,7 +410,7 @@ static int copy_name(char *buffer, const char *xattr_name, int name_len)
int len = name_len;
int offset = 0;
- if (is_osx_xattr(xattr_name)) {
+ if (!is_known_namespace(xattr_name)) {
strncpy(buffer, XATTR_MAC_OSX_PREFIX, XATTR_MAC_OSX_PREFIX_LEN);
offset += XATTR_MAC_OSX_PREFIX_LEN;
len += XATTR_MAC_OSX_PREFIX_LEN;
@@ -497,18 +488,6 @@ ssize_t __hfsplus_getxattr(struct inode *inode, const char *name,
HFSPLUS_IS_RSRC(inode))
return -EOPNOTSUPP;
- if (strncmp(name, XATTR_MAC_OSX_PREFIX,
- XATTR_MAC_OSX_PREFIX_LEN) == 0) {
- /* skip "osx." prefix */
- name += XATTR_MAC_OSX_PREFIX_LEN;
- /*
- * Don't allow retrieving properly prefixed attributes
- * by prepending them with "osx."
- */
- if (is_known_namespace(name))
- return -EOPNOTSUPP;
- }
-
if (!strcmp_xattr_finder_info(name))
return hfsplus_getxattr_finder_info(inode, value, size);
@@ -743,28 +722,18 @@ end_listxattr:
return res;
}
-int hfsplus_removexattr(struct dentry *dentry, const char *name)
+static int hfsplus_removexattr(struct inode *inode, const char *name)
{
int err = 0;
- struct inode *inode = dentry->d_inode;
struct hfs_find_data cat_fd;
u16 flags;
u16 cat_entry_type;
int is_xattr_acl_deleted = 0;
int is_all_xattrs_deleted = 0;
- if ((!S_ISREG(inode->i_mode) &&
- !S_ISDIR(inode->i_mode)) ||
- HFSPLUS_IS_RSRC(inode))
- return -EOPNOTSUPP;
-
if (!HFSPLUS_SB(inode->i_sb)->attr_tree)
return -EOPNOTSUPP;
- if (strncmp(name, XATTR_MAC_OSX_PREFIX,
- XATTR_MAC_OSX_PREFIX_LEN) == 0)
- name += XATTR_MAC_OSX_PREFIX_LEN;
-
if (!strcmp_xattr_finder_info(name))
return -EOPNOTSUPP;
@@ -838,8 +807,12 @@ static int hfsplus_osx_getxattr(struct dentry *dentry, const char *name,
if (len > HFSPLUS_ATTR_MAX_STRLEN)
return -EOPNOTSUPP;
- strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
- strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
+ /*
+ * Don't allow retrieving properly prefixed attributes
+ * by prepending them with "osx."
+ */
+ if (is_known_namespace(name))
+ return -EOPNOTSUPP;
return hfsplus_getxattr(dentry, xattr_name, buffer, size);
}
@@ -857,12 +830,13 @@ static int hfsplus_osx_setxattr(struct dentry *dentry, const char *name,
if (len > HFSPLUS_ATTR_MAX_STRLEN)
return -EOPNOTSUPP;
+ /*
+ * Don't allow setting properly prefixed attributes
+ * by prepending them with "osx."
+ */
if (is_known_namespace(name))
return -EOPNOTSUPP;
- strcpy(xattr_name, XATTR_MAC_OSX_PREFIX);
- strcpy(xattr_name + XATTR_MAC_OSX_PREFIX_LEN, name);
-
return hfsplus_setxattr(dentry, xattr_name, buffer, size, flags);
}
diff --git a/fs/hfsplus/xattr.h b/fs/hfsplus/xattr.h
index 9e214490c313..288530cf80b5 100644
--- a/fs/hfsplus/xattr.h
+++ b/fs/hfsplus/xattr.h
@@ -40,8 +40,6 @@ static inline ssize_t hfsplus_getxattr(struct dentry *dentry,
ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int hfsplus_removexattr(struct dentry *dentry, const char *name);
-
int hfsplus_init_security(struct inode *inode, struct inode *dir,
const struct qstr *qstr);
diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c
index cdb84a838068..58b5106186d0 100644
--- a/fs/hpfs/alloc.c
+++ b/fs/hpfs/alloc.c
@@ -8,6 +8,58 @@
#include "hpfs_fn.h"
+static void hpfs_claim_alloc(struct super_block *s, secno sec)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ if (sbi->sb_n_free != (unsigned)-1) {
+ if (unlikely(!sbi->sb_n_free)) {
+ hpfs_error(s, "free count underflow, allocating sector %08x", sec);
+ sbi->sb_n_free = -1;
+ return;
+ }
+ sbi->sb_n_free--;
+ }
+}
+
+static void hpfs_claim_free(struct super_block *s, secno sec)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ if (sbi->sb_n_free != (unsigned)-1) {
+ if (unlikely(sbi->sb_n_free >= sbi->sb_fs_size)) {
+ hpfs_error(s, "free count overflow, freeing sector %08x", sec);
+ sbi->sb_n_free = -1;
+ return;
+ }
+ sbi->sb_n_free++;
+ }
+}
+
+static void hpfs_claim_dirband_alloc(struct super_block *s, secno sec)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ if (sbi->sb_n_free_dnodes != (unsigned)-1) {
+ if (unlikely(!sbi->sb_n_free_dnodes)) {
+ hpfs_error(s, "dirband free count underflow, allocating sector %08x", sec);
+ sbi->sb_n_free_dnodes = -1;
+ return;
+ }
+ sbi->sb_n_free_dnodes--;
+ }
+}
+
+static void hpfs_claim_dirband_free(struct super_block *s, secno sec)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ if (sbi->sb_n_free_dnodes != (unsigned)-1) {
+ if (unlikely(sbi->sb_n_free_dnodes >= sbi->sb_dirband_size / 4)) {
+ hpfs_error(s, "dirband free count overflow, freeing sector %08x", sec);
+ sbi->sb_n_free_dnodes = -1;
+ return;
+ }
+ sbi->sb_n_free_dnodes++;
+ }
+}
+
/*
* Check if a sector is allocated in bitmap
* This is really slow. Turned on only if chk==2
@@ -203,9 +255,15 @@ secno hpfs_alloc_sector(struct super_block *s, secno near, unsigned n, int forwa
}
sec = 0;
ret:
+ if (sec) {
+ i = 0;
+ do
+ hpfs_claim_alloc(s, sec + i);
+ while (unlikely(++i < n));
+ }
if (sec && f_p) {
for (i = 0; i < forward; i++) {
- if (!hpfs_alloc_if_possible(s, sec + i + 1)) {
+ if (!hpfs_alloc_if_possible(s, sec + n + i)) {
hpfs_error(s, "Prealloc doesn't work! Wanted %d, allocated at %08x, can't allocate %d", forward, sec, i);
sec = 0;
break;
@@ -228,6 +286,7 @@ static secno alloc_in_dirband(struct super_block *s, secno near)
nr >>= 2;
sec = alloc_in_bmp(s, (~0x3fff) | nr, 1, 0);
if (!sec) return 0;
+ hpfs_claim_dirband_alloc(s, sec);
return ((sec & 0x3fff) << 2) + sbi->sb_dirband_start;
}
@@ -242,6 +301,7 @@ int hpfs_alloc_if_possible(struct super_block *s, secno sec)
bmp[(sec & 0x3fff) >> 5] &= cpu_to_le32(~(1 << (sec & 0x1f)));
hpfs_mark_4buffers_dirty(&qbh);
hpfs_brelse4(&qbh);
+ hpfs_claim_alloc(s, sec);
return 1;
}
hpfs_brelse4(&qbh);
@@ -275,6 +335,7 @@ void hpfs_free_sectors(struct super_block *s, secno sec, unsigned n)
return;
}
bmp[(sec & 0x3fff) >> 5] |= cpu_to_le32(1 << (sec & 0x1f));
+ hpfs_claim_free(s, sec);
if (!--n) {
hpfs_mark_4buffers_dirty(&qbh);
hpfs_brelse4(&qbh);
@@ -359,6 +420,7 @@ void hpfs_free_dnode(struct super_block *s, dnode_secno dno)
bmp[ssec >> 5] |= cpu_to_le32(1 << (ssec & 0x1f));
hpfs_mark_4buffers_dirty(&qbh);
hpfs_brelse4(&qbh);
+ hpfs_claim_dirband_free(s, dno);
}
}
@@ -366,7 +428,7 @@ struct dnode *hpfs_alloc_dnode(struct super_block *s, secno near,
dnode_secno *dno, struct quad_buffer_head *qbh)
{
struct dnode *d;
- if (hpfs_count_one_bitmap(s, hpfs_sb(s)->sb_dmap) > FREE_DNODES_ADD) {
+ if (hpfs_get_free_dnodes(s) > FREE_DNODES_ADD) {
if (!(*dno = alloc_in_dirband(s, near)))
if (!(*dno = hpfs_alloc_sector(s, near, 4, 0))) return NULL;
} else {
diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c
index 4d0a1afa058c..139ef1684d07 100644
--- a/fs/hpfs/buffer.c
+++ b/fs/hpfs/buffer.c
@@ -86,7 +86,6 @@ void *hpfs_get_sector(struct super_block *s, unsigned secno, struct buffer_head
void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffer_head *qbh,
int ahead)
{
- struct buffer_head *bh;
char *data;
hpfs_lock_assert(s);
@@ -100,34 +99,32 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe
hpfs_prefetch_sectors(s, secno, 4 + ahead);
+ if (!(qbh->bh[0] = sb_bread(s, secno + 0))) goto bail0;
+ if (!(qbh->bh[1] = sb_bread(s, secno + 1))) goto bail1;
+ if (!(qbh->bh[2] = sb_bread(s, secno + 2))) goto bail2;
+ if (!(qbh->bh[3] = sb_bread(s, secno + 3))) goto bail3;
+
+ if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) &&
+ likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) &&
+ likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) {
+ return qbh->data = qbh->bh[0]->b_data;
+ }
+
qbh->data = data = kmalloc(2048, GFP_NOFS);
if (!data) {
printk("HPFS: hpfs_map_4sectors: out of memory\n");
- goto bail;
+ goto bail4;
}
- qbh->bh[0] = bh = sb_bread(s, secno);
- if (!bh)
- goto bail0;
- memcpy(data, bh->b_data, 512);
-
- qbh->bh[1] = bh = sb_bread(s, secno + 1);
- if (!bh)
- goto bail1;
- memcpy(data + 512, bh->b_data, 512);
-
- qbh->bh[2] = bh = sb_bread(s, secno + 2);
- if (!bh)
- goto bail2;
- memcpy(data + 2 * 512, bh->b_data, 512);
-
- qbh->bh[3] = bh = sb_bread(s, secno + 3);
- if (!bh)
- goto bail3;
- memcpy(data + 3 * 512, bh->b_data, 512);
+ memcpy(data + 0 * 512, qbh->bh[0]->b_data, 512);
+ memcpy(data + 1 * 512, qbh->bh[1]->b_data, 512);
+ memcpy(data + 2 * 512, qbh->bh[2]->b_data, 512);
+ memcpy(data + 3 * 512, qbh->bh[3]->b_data, 512);
return data;
+ bail4:
+ brelse(qbh->bh[3]);
bail3:
brelse(qbh->bh[2]);
bail2:
@@ -135,9 +132,6 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe
bail1:
brelse(qbh->bh[0]);
bail0:
- kfree(data);
- printk("HPFS: hpfs_map_4sectors: read error\n");
- bail:
return NULL;
}
@@ -155,44 +149,54 @@ void *hpfs_get_4sectors(struct super_block *s, unsigned secno,
return NULL;
}
- /*return hpfs_map_4sectors(s, secno, qbh, 0);*/
+ if (!hpfs_get_sector(s, secno + 0, &qbh->bh[0])) goto bail0;
+ if (!hpfs_get_sector(s, secno + 1, &qbh->bh[1])) goto bail1;
+ if (!hpfs_get_sector(s, secno + 2, &qbh->bh[2])) goto bail2;
+ if (!hpfs_get_sector(s, secno + 3, &qbh->bh[3])) goto bail3;
+
+ if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) &&
+ likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) &&
+ likely(qbh->bh[3]->b_data == qbh->bh[0]->b_data + 3 * 512)) {
+ return qbh->data = qbh->bh[0]->b_data;
+ }
+
if (!(qbh->data = kmalloc(2048, GFP_NOFS))) {
printk("HPFS: hpfs_get_4sectors: out of memory\n");
- return NULL;
+ goto bail4;
}
- if (!(hpfs_get_sector(s, secno, &qbh->bh[0]))) goto bail0;
- if (!(hpfs_get_sector(s, secno + 1, &qbh->bh[1]))) goto bail1;
- if (!(hpfs_get_sector(s, secno + 2, &qbh->bh[2]))) goto bail2;
- if (!(hpfs_get_sector(s, secno + 3, &qbh->bh[3]))) goto bail3;
- memcpy(qbh->data, qbh->bh[0]->b_data, 512);
- memcpy(qbh->data + 512, qbh->bh[1]->b_data, 512);
- memcpy(qbh->data + 2*512, qbh->bh[2]->b_data, 512);
- memcpy(qbh->data + 3*512, qbh->bh[3]->b_data, 512);
return qbh->data;
- bail3: brelse(qbh->bh[2]);
- bail2: brelse(qbh->bh[1]);
- bail1: brelse(qbh->bh[0]);
- bail0:
+bail4:
+ brelse(qbh->bh[3]);
+bail3:
+ brelse(qbh->bh[2]);
+bail2:
+ brelse(qbh->bh[1]);
+bail1:
+ brelse(qbh->bh[0]);
+bail0:
return NULL;
}
void hpfs_brelse4(struct quad_buffer_head *qbh)
{
- brelse(qbh->bh[3]);
- brelse(qbh->bh[2]);
- brelse(qbh->bh[1]);
+ if (unlikely(qbh->data != qbh->bh[0]->b_data))
+ kfree(qbh->data);
brelse(qbh->bh[0]);
- kfree(qbh->data);
+ brelse(qbh->bh[1]);
+ brelse(qbh->bh[2]);
+ brelse(qbh->bh[3]);
}
void hpfs_mark_4buffers_dirty(struct quad_buffer_head *qbh)
{
- memcpy(qbh->bh[0]->b_data, qbh->data, 512);
- memcpy(qbh->bh[1]->b_data, qbh->data + 512, 512);
- memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512);
- memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512);
+ if (unlikely(qbh->data != qbh->bh[0]->b_data)) {
+ memcpy(qbh->bh[0]->b_data, qbh->data + 0 * 512, 512);
+ memcpy(qbh->bh[1]->b_data, qbh->data + 1 * 512, 512);
+ memcpy(qbh->bh[2]->b_data, qbh->data + 2 * 512, 512);
+ memcpy(qbh->bh[3]->b_data, qbh->data + 3 * 512, 512);
+ }
mark_buffer_dirty(qbh->bh[0]);
mark_buffer_dirty(qbh->bh[1]);
mark_buffer_dirty(qbh->bh[2]);
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 6797bf80f6e2..3ba49c080e42 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -312,7 +312,7 @@ static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb)
__printf(2, 3)
void hpfs_error(struct super_block *, const char *, ...);
int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *);
-unsigned hpfs_count_one_bitmap(struct super_block *, secno);
+unsigned hpfs_get_free_dnodes(struct super_block *);
/*
* local time (HPFS) to GMT (Unix)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index b8d01ef6f531..4534ff688b76 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -121,7 +121,7 @@ static void hpfs_put_super(struct super_block *s)
call_rcu(&hpfs_sb(s)->rcu, lazy_free_sbi);
}
-unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
+static unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
{
struct quad_buffer_head qbh;
unsigned long *bits;
@@ -129,7 +129,7 @@ unsigned hpfs_count_one_bitmap(struct super_block *s, secno secno)
bits = hpfs_map_4sectors(s, secno, &qbh, 0);
if (!bits)
- return 0;
+ return (unsigned)-1;
count = bitmap_weight(bits, 2048 * BITS_PER_BYTE);
hpfs_brelse4(&qbh);
return count;
@@ -144,30 +144,45 @@ static unsigned count_bitmaps(struct super_block *s)
hpfs_prefetch_bitmap(s, n);
}
for (n = 0; n < n_bands; n++) {
+ unsigned c;
hpfs_prefetch_bitmap(s, n + COUNT_RD_AHEAD);
- count += hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n]));
+ c = hpfs_count_one_bitmap(s, le32_to_cpu(hpfs_sb(s)->sb_bmp_dir[n]));
+ if (c != (unsigned)-1)
+ count += c;
}
return count;
}
+unsigned hpfs_get_free_dnodes(struct super_block *s)
+{
+ struct hpfs_sb_info *sbi = hpfs_sb(s);
+ if (sbi->sb_n_free_dnodes == (unsigned)-1) {
+ unsigned c = hpfs_count_one_bitmap(s, sbi->sb_dmap);
+ if (c == (unsigned)-1)
+ return 0;
+ sbi->sb_n_free_dnodes = c;
+ }
+ return sbi->sb_n_free_dnodes;
+}
+
static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *s = dentry->d_sb;
struct hpfs_sb_info *sbi = hpfs_sb(s);
u64 id = huge_encode_dev(s->s_bdev->bd_dev);
+
hpfs_lock(s);
- /*if (sbi->sb_n_free == -1) {*/
+ if (sbi->sb_n_free == (unsigned)-1)
sbi->sb_n_free = count_bitmaps(s);
- sbi->sb_n_free_dnodes = hpfs_count_one_bitmap(s, sbi->sb_dmap);
- /*}*/
+
buf->f_type = s->s_magic;
buf->f_bsize = 512;
buf->f_blocks = sbi->sb_fs_size;
buf->f_bfree = sbi->sb_n_free;
buf->f_bavail = sbi->sb_n_free;
buf->f_files = sbi->sb_dirband_size / 4;
- buf->f_ffree = sbi->sb_n_free_dnodes;
+ buf->f_ffree = hpfs_get_free_dnodes(s);
buf->f_fsid.val[0] = (u32)id;
buf->f_fsid.val[1] = (u32)(id >> 32);
buf->f_namelen = 254;
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 8360674c85bc..60bb365f54a5 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -514,11 +514,13 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
* similarly constrained call sites
*/
ret = start_this_handle(journal, handle, GFP_NOFS);
- if (ret < 0)
+ if (ret < 0) {
jbd2_journal_free_reserved(handle);
+ return ret;
+ }
handle->h_type = type;
handle->h_line_no = line_no;
- return ret;
+ return 0;
}
EXPORT_SYMBOL(jbd2_journal_start_reserved);
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index e973b85d6afd..5a8ea16eedbc 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -86,6 +86,8 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type,
rc = posix_acl_equiv_mode(acl, &inode->i_mode);
if (rc < 0)
return rc;
+ inode->i_ctime = CURRENT_TIME;
+ mark_inode_dirty(inode);
if (rc == 0)
acl = NULL;
break;
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 360d27c48887..8d811e02b4b9 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1998,20 +1998,20 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp)
bio = bio_alloc(GFP_NOFS, 1);
- bio->bi_sector = bp->l_blkno << (log->l2bsize - 9);
+ bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
bio->bi_bdev = log->bdev;
bio->bi_io_vec[0].bv_page = bp->l_page;
bio->bi_io_vec[0].bv_len = LOGPSIZE;
bio->bi_io_vec[0].bv_offset = bp->l_offset;
bio->bi_vcnt = 1;
- bio->bi_size = LOGPSIZE;
+ bio->bi_iter.bi_size = LOGPSIZE;
bio->bi_end_io = lbmIODone;
bio->bi_private = bp;
/*check if journaling to disk has been disabled*/
if (log->no_integrity) {
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
lbmIODone(bio, 0);
} else {
submit_bio(READ_SYNC, bio);
@@ -2144,21 +2144,21 @@ static void lbmStartIO(struct lbuf * bp)
jfs_info("lbmStartIO\n");
bio = bio_alloc(GFP_NOFS, 1);
- bio->bi_sector = bp->l_blkno << (log->l2bsize - 9);
+ bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9);
bio->bi_bdev = log->bdev;
bio->bi_io_vec[0].bv_page = bp->l_page;
bio->bi_io_vec[0].bv_len = LOGPSIZE;
bio->bi_io_vec[0].bv_offset = bp->l_offset;
bio->bi_vcnt = 1;
- bio->bi_size = LOGPSIZE;
+ bio->bi_iter.bi_size = LOGPSIZE;
bio->bi_end_io = lbmIODone;
bio->bi_private = bp;
/* check if journaling to disk has been disabled */
if (log->no_integrity) {
- bio->bi_size = 0;
+ bio->bi_iter.bi_size = 0;
lbmIODone(bio, 0);
} else {
submit_bio(WRITE_SYNC, bio);
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index d165cde0c68d..49ba7ff1bbb9 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -416,7 +416,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
* count from hitting zero before we're through
*/
inc_io(page);
- if (!bio->bi_size)
+ if (!bio->bi_iter.bi_size)
goto dump_bio;
submit_bio(WRITE, bio);
nr_underway++;
@@ -438,7 +438,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_bdev = inode->i_sb->s_bdev;
- bio->bi_sector = pblock << (inode->i_blkbits - 9);
+ bio->bi_iter.bi_sector = pblock << (inode->i_blkbits - 9);
bio->bi_end_io = metapage_write_end_io;
bio->bi_private = page;
@@ -452,7 +452,7 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
if (bio) {
if (bio_add_page(bio, page, bio_bytes, bio_offset) < bio_bytes)
goto add_failed;
- if (!bio->bi_size)
+ if (!bio->bi_iter.bi_size)
goto dump_bio;
submit_bio(WRITE, bio);
@@ -517,7 +517,8 @@ static int metapage_readpage(struct file *fp, struct page *page)
bio = bio_alloc(GFP_NOFS, 1);
bio->bi_bdev = inode->i_sb->s_bdev;
- bio->bi_sector = pblock << (inode->i_blkbits - 9);
+ bio->bi_iter.bi_sector =
+ pblock << (inode->i_blkbits - 9);
bio->bi_end_io = metapage_read_end_io;
bio->bi_private = page;
len = xlen << inode->i_blkbits;
diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
index 5324e4e2b992..46325d5c34fc 100644
--- a/fs/jfs/xattr.c
+++ b/fs/jfs/xattr.c
@@ -791,6 +791,19 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name,
/* Completely new ea list */
xattr_size = sizeof (struct jfs_ea_list);
+ /*
+ * The size of EA value is limitted by on-disk format up to
+ * __le16, there would be an overflow if the size is equal
+ * to XATTR_SIZE_MAX (65536). In order to avoid this issue,
+ * we can pre-checkup the value size against USHRT_MAX, and
+ * return -E2BIG in this case, which is consistent with the
+ * VFS setxattr interface.
+ */
+ if (value_len >= USHRT_MAX) {
+ rc = -E2BIG;
+ goto release;
+ }
+
ea = (struct jfs_ea *) ((char *) ealist + xattr_size);
ea->flag = 0;
ea->namelen = namelen;
@@ -805,7 +818,7 @@ int __jfs_setxattr(tid_t tid, struct inode *inode, const char *name,
/* DEBUG - If we did this right, these number match */
if (xattr_size != new_size) {
printk(KERN_ERR
- "jfs_xsetattr: xattr_size = %d, new_size = %d\n",
+ "__jfs_setxattr: xattr_size = %d, new_size = %d\n",
xattr_size, new_size);
rc = -EINVAL;
@@ -841,9 +854,6 @@ int jfs_setxattr(struct dentry *dentry, const char *name, const void *value,
int rc;
tid_t tid;
- if ((rc = can_set_xattr(inode, name, value, value_len)))
- return rc;
-
/*
* If this is a request for a synthetic attribute in the system.*
* namespace use the generic infrastructure to resolve a handler
@@ -852,6 +862,9 @@ int jfs_setxattr(struct dentry *dentry, const char *name, const void *value,
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_setxattr(dentry, name, value, value_len, flags);
+ if ((rc = can_set_xattr(inode, name, value, value_len)))
+ return rc;
+
if (value == NULL) { /* empty EA, do not remove */
value = "";
value_len = 0;
@@ -1021,9 +1034,6 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
int rc;
tid_t tid;
- if ((rc = can_set_xattr(inode, name, NULL, 0)))
- return rc;
-
/*
* If this is a request for a synthetic attribute in the system.*
* namespace use the generic infrastructure to resolve a handler
@@ -1032,6 +1042,9 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_removexattr(dentry, name);
+ if ((rc = can_set_xattr(inode, name, NULL, 0)))
+ return rc;
+
tid = txBegin(inode->i_sb, 0);
mutex_lock(&ji->commit_mutex);
rc = __jfs_setxattr(tid, dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
@@ -1048,7 +1061,7 @@ int jfs_removexattr(struct dentry *dentry, const char *name)
* attributes are handled directly.
*/
const struct xattr_handler *jfs_xattr_handlers[] = {
-#ifdef JFS_POSIX_ACL
+#ifdef CONFIG_JFS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5104cf5d25c5..bd6e18be6e1a 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -187,19 +187,23 @@ static void kernfs_deactivate(struct kernfs_node *kn)
kn->u.completion = (void *)&wait;
- rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
+ if (kn->flags & KERNFS_LOCKDEP)
+ rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
/* atomic_add_return() is a mb(), put_active() will always see
* the updated kn->u.completion.
*/
v = atomic_add_return(KN_DEACTIVATED_BIAS, &kn->active);
if (v != KN_DEACTIVATED_BIAS) {
- lock_contended(&kn->dep_map, _RET_IP_);
+ if (kn->flags & KERNFS_LOCKDEP)
+ lock_contended(&kn->dep_map, _RET_IP_);
wait_for_completion(&wait);
}
- lock_acquired(&kn->dep_map, _RET_IP_);
- rwsem_release(&kn->dep_map, 1, _RET_IP_);
+ if (kn->flags & KERNFS_LOCKDEP) {
+ lock_acquired(&kn->dep_map, _RET_IP_);
+ rwsem_release(&kn->dep_map, 1, _RET_IP_);
+ }
}
/**
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 0d6ce895a9ee..0f4152defe7b 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -94,6 +94,7 @@ const void *kernfs_super_ns(struct super_block *sb)
* @fs_type: file_system_type of the fs being mounted
* @flags: mount flags specified for the mount
* @root: kernfs_root of the hierarchy being mounted
+ * @new_sb_created: tell the caller if we allocated a new superblock
* @ns: optional namespace tag of the mount
*
* This is to be called from each kernfs user's file_system_type->mount()
@@ -104,7 +105,8 @@ const void *kernfs_super_ns(struct super_block *sb)
* The return value can be passed to the vfs layer verbatim.
*/
struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
- struct kernfs_root *root, const void *ns)
+ struct kernfs_root *root, bool *new_sb_created,
+ const void *ns)
{
struct super_block *sb;
struct kernfs_super_info *info;
@@ -122,6 +124,10 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
kfree(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
+
+ if (new_sb_created)
+ *new_sb_created = !sb->s_root;
+
if (!sb->s_root) {
error = kernfs_fill_super(sb);
if (error) {
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index e066a3902973..ab798a88ec1d 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -779,6 +779,7 @@ nlmsvc_grant_blocked(struct nlm_block *block)
struct nlm_file *file = block->b_file;
struct nlm_lock *lock = &block->b_call->a_args.lock;
int error;
+ loff_t fl_start, fl_end;
dprintk("lockd: grant blocked lock %p\n", block);
@@ -796,9 +797,16 @@ nlmsvc_grant_blocked(struct nlm_block *block)
}
/* Try the lock operation again */
+ /* vfs_lock_file() can mangle fl_start and fl_end, but we need
+ * them unchanged for the GRANT_MSG
+ */
lock->fl.fl_flags |= FL_SLEEP;
+ fl_start = lock->fl.fl_start;
+ fl_end = lock->fl.fl_end;
error = vfs_lock_file(file->f_file, F_SETLK, &lock->fl, NULL);
lock->fl.fl_flags &= ~FL_SLEEP;
+ lock->fl.fl_start = fl_start;
+ lock->fl.fl_end = fl_end;
switch (error) {
case 0:
diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c
index 0f95f0d0b313..76279e11982d 100644
--- a/fs/logfs/dev_bdev.c
+++ b/fs/logfs/dev_bdev.c
@@ -26,9 +26,9 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw)
bio_vec.bv_len = PAGE_SIZE;
bio_vec.bv_offset = 0;
bio.bi_vcnt = 1;
- bio.bi_size = PAGE_SIZE;
bio.bi_bdev = bdev;
- bio.bi_sector = page->index * (PAGE_SIZE >> 9);
+ bio.bi_iter.bi_sector = page->index * (PAGE_SIZE >> 9);
+ bio.bi_iter.bi_size = PAGE_SIZE;
return submit_bio_wait(rw, &bio);
}
@@ -56,22 +56,18 @@ static DECLARE_WAIT_QUEUE_HEAD(wq);
static void writeseg_end_io(struct bio *bio, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
+ int i;
struct super_block *sb = bio->bi_private;
struct logfs_super *super = logfs_super(sb);
- struct page *page;
BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */
BUG_ON(err);
- BUG_ON(bio->bi_vcnt == 0);
- do {
- page = bvec->bv_page;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
-
- end_page_writeback(page);
- page_cache_release(page);
- } while (bvec >= bio->bi_io_vec);
+
+ bio_for_each_segment_all(bvec, bio, i) {
+ end_page_writeback(bvec->bv_page);
+ page_cache_release(bvec->bv_page);
+ }
bio_put(bio);
if (atomic_dec_and_test(&super->s_pending_writes))
wake_up(&wq);
@@ -96,9 +92,9 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
- bio->bi_size = i * PAGE_SIZE;
+ bio->bi_iter.bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
- bio->bi_sector = ofs >> 9;
+ bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
@@ -123,9 +119,9 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
unlock_page(page);
}
bio->bi_vcnt = nr_pages;
- bio->bi_size = nr_pages * PAGE_SIZE;
+ bio->bi_iter.bi_size = nr_pages * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
- bio->bi_sector = ofs >> 9;
+ bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
@@ -188,9 +184,9 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
- bio->bi_size = i * PAGE_SIZE;
+ bio->bi_iter.bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
- bio->bi_sector = ofs >> 9;
+ bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = erase_end_io;
atomic_inc(&super->s_pending_writes);
@@ -209,9 +205,9 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
bio->bi_io_vec[i].bv_offset = 0;
}
bio->bi_vcnt = nr_pages;
- bio->bi_size = nr_pages * PAGE_SIZE;
+ bio->bi_iter.bi_size = nr_pages * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
- bio->bi_sector = ofs >> 9;
+ bio->bi_iter.bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = erase_end_io;
atomic_inc(&super->s_pending_writes);
diff --git a/fs/mpage.c b/fs/mpage.c
index 0face1c4d4c6..4979ffa60aaa 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -43,16 +43,14 @@
*/
static void mpage_end_io(struct bio *bio, int err)
{
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bv;
+ int i;
- do {
- struct page *page = bvec->bv_page;
+ bio_for_each_segment_all(bv, bio, i) {
+ struct page *page = bv->bv_page;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
if (bio_data_dir(bio) == READ) {
- if (uptodate) {
+ if (!err) {
SetPageUptodate(page);
} else {
ClearPageUptodate(page);
@@ -60,14 +58,15 @@ static void mpage_end_io(struct bio *bio, int err)
}
unlock_page(page);
} else { /* bio_data_dir(bio) == WRITE */
- if (!uptodate) {
+ if (err) {
SetPageError(page);
if (page->mapping)
set_bit(AS_EIO, &page->mapping->flags);
}
end_page_writeback(page);
}
- } while (bvec >= bio->bi_io_vec);
+ }
+
bio_put(bio);
}
@@ -94,7 +93,7 @@ mpage_alloc(struct block_device *bdev,
if (bio) {
bio->bi_bdev = bdev;
- bio->bi_sector = first_sector;
+ bio->bi_iter.bi_sector = first_sector;
}
return bio;
}
diff --git a/fs/namei.c b/fs/namei.c
index bcb838e2e52f..385f7817bfcc 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -196,6 +196,7 @@ recopy:
goto error;
result->uptr = filename;
+ result->aname = NULL;
audit_getname(result);
return result;
@@ -209,7 +210,35 @@ getname(const char __user * filename)
{
return getname_flags(filename, 0, NULL);
}
-EXPORT_SYMBOL(getname);
+
+/*
+ * The "getname_kernel()" interface doesn't do pathnames longer
+ * than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user.
+ */
+struct filename *
+getname_kernel(const char * filename)
+{
+ struct filename *result;
+ char *kname;
+ int len;
+
+ len = strlen(filename);
+ if (len >= EMBEDDED_NAME_MAX)
+ return ERR_PTR(-ENAMETOOLONG);
+
+ result = __getname();
+ if (unlikely(!result))
+ return ERR_PTR(-ENOMEM);
+
+ kname = (char *)result + sizeof(*result);
+ result->name = kname;
+ result->uptr = NULL;
+ result->aname = NULL;
+ result->separate = false;
+
+ strlcpy(kname, filename, EMBEDDED_NAME_MAX);
+ return result;
+}
#ifdef CONFIG_AUDITSYSCALL
void putname(struct filename *name)
@@ -3927,10 +3956,13 @@ out_dput:
done_path_create(&new_path, new_dentry);
if (delegated_inode) {
error = break_deleg_wait(&delegated_inode);
- if (!error)
+ if (!error) {
+ path_put(&old_path);
goto retry;
+ }
}
if (retry_estale(error, how)) {
+ path_put(&old_path);
how |= LOOKUP_REVAL;
goto retry;
}
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index e242bbf72972..56ff823ca82e 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -134,8 +134,8 @@ bl_submit_bio(int rw, struct bio *bio)
if (bio) {
get_parallel(bio->bi_private);
dprintk("%s submitting %s bio %u@%llu\n", __func__,
- rw == READ ? "read" : "write",
- bio->bi_size, (unsigned long long)bio->bi_sector);
+ rw == READ ? "read" : "write", bio->bi_iter.bi_size,
+ (unsigned long long)bio->bi_iter.bi_sector);
submit_bio(rw, bio);
}
return NULL;
@@ -156,7 +156,8 @@ static struct bio *bl_alloc_init_bio(int npg, sector_t isect,
}
if (bio) {
- bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+ bio->bi_iter.bi_sector = isect - be->be_f_offset +
+ be->be_v_offset;
bio->bi_bdev = be->be_mdev;
bio->bi_end_io = end_io;
bio->bi_private = par;
@@ -201,18 +202,14 @@ static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw,
static void bl_end_io_read(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
+ struct bio_vec *bvec;
+ int i;
- do {
- struct page *page = bvec->bv_page;
+ if (!err)
+ bio_for_each_segment_all(bvec, bio, i)
+ SetPageUptodate(bvec->bv_page);
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
- if (uptodate)
- SetPageUptodate(page);
- } while (bvec >= bio->bi_io_vec);
- if (!uptodate) {
+ if (err) {
struct nfs_read_data *rdata = par->data;
struct nfs_pgio_header *header = rdata->header;
@@ -383,20 +380,16 @@ static void mark_extents_written(struct pnfs_block_layout *bl,
static void bl_end_io_write_zero(struct bio *bio, int err)
{
struct parallel_io *par = bio->bi_private;
- const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-
- do {
- struct page *page = bvec->bv_page;
+ struct bio_vec *bvec;
+ int i;
- if (--bvec >= bio->bi_io_vec)
- prefetchw(&bvec->bv_page->flags);
+ bio_for_each_segment_all(bvec, bio, i) {
/* This is the zeroing page we added */
- end_page_writeback(page);
- page_cache_release(page);
- } while (bvec >= bio->bi_io_vec);
+ end_page_writeback(bvec->bv_page);
+ page_cache_release(bvec->bv_page);
+ }
- if (unlikely(!uptodate)) {
+ if (unlikely(err)) {
struct nfs_write_data *data = par->data;
struct nfs_pgio_header *header = data->header;
@@ -519,7 +512,7 @@ bl_do_readpage_sync(struct page *page, struct pnfs_block_extent *be,
isect = (page->index << PAGE_CACHE_SECTOR_SHIFT) +
(offset / SECTOR_SIZE);
- bio->bi_sector = isect - be->be_f_offset + be->be_v_offset;
+ bio->bi_iter.bi_sector = isect - be->be_f_offset + be->be_v_offset;
bio->bi_bdev = be->be_mdev;
bio->bi_end_io = bl_read_single_end_io;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ef792f29f831..5d8ccecf5f5c 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -659,16 +659,19 @@ int nfs_async_inode_return_delegation(struct inode *inode,
rcu_read_lock();
delegation = rcu_dereference(NFS_I(inode)->delegation);
+ if (delegation == NULL)
+ goto out_enoent;
- if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid)) {
- rcu_read_unlock();
- return -ENOENT;
- }
+ if (!clp->cl_mvops->match_stateid(&delegation->stateid, stateid))
+ goto out_enoent;
nfs_mark_return_delegation(server, delegation);
rcu_read_unlock();
nfs_delegation_run_state_manager(clp);
return 0;
+out_enoent:
+ rcu_read_unlock();
+ return -ENOENT;
}
static struct inode *
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b266f734bd53..4a48fe4b84b6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -274,6 +274,15 @@ out_eof:
return -EBADCOOKIE;
}
+static bool
+nfs_readdir_inode_mapping_valid(struct nfs_inode *nfsi)
+{
+ if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))
+ return false;
+ smp_rmb();
+ return !test_bit(NFS_INO_INVALIDATING, &nfsi->flags);
+}
+
static
int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc)
{
@@ -287,8 +296,8 @@ int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_des
struct nfs_open_dir_context *ctx = desc->file->private_data;
new_pos = desc->current_index + i;
- if (ctx->attr_gencount != nfsi->attr_gencount
- || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) {
+ if (ctx->attr_gencount != nfsi->attr_gencount ||
+ !nfs_readdir_inode_mapping_valid(nfsi)) {
ctx->duped = 0;
ctx->attr_gencount = nfsi->attr_gencount;
} else if (new_pos < desc->ctx->pos) {
@@ -1837,6 +1846,11 @@ int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
GFP_KERNEL)) {
SetPageUptodate(page);
unlock_page(page);
+ /*
+ * add_to_page_cache_lru() grabs an extra page refcount.
+ * Drop it here to avoid leaking this page later.
+ */
+ page_cache_release(page);
} else
__free_page(page);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index ea00b34ff071..360114ae8b82 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -164,17 +164,16 @@ static void nfs_zap_caches_locked(struct inode *inode)
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
nfs_fscache_invalidate(inode);
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_DATA
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
} else
nfsi->cache_validity |= NFS_INO_INVALID_ATTR
- | NFS_INO_INVALID_LABEL
| NFS_INO_INVALID_ACCESS
| NFS_INO_INVALID_ACL
| NFS_INO_REVAL_PAGECACHE;
+ nfs_zap_label_cache_locked(nfsi);
}
void nfs_zap_caches(struct inode *inode)
@@ -266,6 +265,13 @@ nfs_init_locked(struct inode *inode, void *opaque)
}
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
+static void nfs_clear_label_invalid(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_LABEL;
+ spin_unlock(&inode->i_lock);
+}
+
void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
struct nfs4_label *label)
{
@@ -283,6 +289,7 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
__func__,
(char *)label->label,
label->len, error);
+ nfs_clear_label_invalid(inode);
}
}
@@ -977,11 +984,11 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
if (ret < 0)
return ret;
}
- spin_lock(&inode->i_lock);
- nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
- if (S_ISDIR(inode->i_mode))
+ if (S_ISDIR(inode->i_mode)) {
+ spin_lock(&inode->i_lock);
memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
- spin_unlock(&inode->i_lock);
+ spin_unlock(&inode->i_lock);
+ }
nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
nfs_fscache_wait_on_invalidate(inode);
@@ -1008,6 +1015,7 @@ static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long *bitlock = &nfsi->flags;
int ret = 0;
/* swapfiles are not supposed to be shared. */
@@ -1019,12 +1027,46 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
if (ret < 0)
goto out;
}
- if (nfsi->cache_validity & NFS_INO_INVALID_DATA) {
- trace_nfs_invalidate_mapping_enter(inode);
- ret = nfs_invalidate_mapping(inode, mapping);
- trace_nfs_invalidate_mapping_exit(inode, ret);
+
+ /*
+ * We must clear NFS_INO_INVALID_DATA first to ensure that
+ * invalidations that come in while we're shooting down the mappings
+ * are respected. But, that leaves a race window where one revalidator
+ * can clear the flag, and then another checks it before the mapping
+ * gets invalidated. Fix that by serializing access to this part of
+ * the function.
+ *
+ * At the same time, we need to allow other tasks to see whether we
+ * might be in the middle of invalidating the pages, so we only set
+ * the bit lock here if it looks like we're going to be doing that.
+ */
+ for (;;) {
+ ret = wait_on_bit(bitlock, NFS_INO_INVALIDATING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (ret)
+ goto out;
+ spin_lock(&inode->i_lock);
+ if (test_bit(NFS_INO_INVALIDATING, bitlock)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+ break;
+ spin_unlock(&inode->i_lock);
+ goto out;
}
+ set_bit(NFS_INO_INVALIDATING, bitlock);
+ smp_wmb();
+ nfsi->cache_validity &= ~NFS_INO_INVALID_DATA;
+ spin_unlock(&inode->i_lock);
+ trace_nfs_invalidate_mapping_enter(inode);
+ ret = nfs_invalidate_mapping(inode, mapping);
+ trace_nfs_invalidate_mapping_exit(inode, ret);
+
+ clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
return ret;
}
@@ -1613,7 +1655,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
inode->i_blocks = fattr->du.nfs2.blocks;
/* Update attrtimeo value if we're out of the unstable period */
- if (invalid & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL)) {
+ if (invalid & NFS_INO_INVALID_ATTR) {
nfs_inc_stats(inode, NFSIOS_ATTRINVALIDATE);
nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
nfsi->attrtimeo_timestamp = now;
@@ -1626,7 +1668,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
}
}
invalid &= ~NFS_INO_INVALID_ATTR;
- invalid &= ~NFS_INO_INVALID_LABEL;
/* Don't invalidate the data if we were to blame */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
|| S_ISLNK(inode->i_mode)))
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8b5cc04a8611..b46cf5a67329 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -176,7 +176,8 @@ extern struct nfs_server *nfs4_create_server(
extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *,
struct nfs_fh *);
extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen);
+ struct sockaddr *sap, size_t salen,
+ struct net *net);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
struct nfs_fh *,
@@ -279,9 +280,18 @@ static inline void nfs4_label_free(struct nfs4_label *label)
}
return;
}
+
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+ if (nfs_server_capable(&nfsi->vfs_inode, NFS_CAP_SECURITY_LABEL))
+ nfsi->cache_validity |= NFS_INO_INVALID_LABEL;
+}
#else
static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; }
static inline void nfs4_label_free(void *label) {}
+static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
+{
+}
#endif /* CONFIG_NFS_V4_SECURITY_LABEL */
/* proc.c */
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 9a5ca03fa539..871d6eda8dba 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -80,7 +80,7 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
}
if (res.acl_access != NULL) {
- if (posix_acl_equiv_mode(res.acl_access, NULL) ||
+ if ((posix_acl_equiv_mode(res.acl_access, NULL) == 0) ||
res.acl_access->a_count == 0) {
posix_acl_release(res.acl_access);
res.acl_access = NULL;
@@ -113,7 +113,7 @@ getout:
return ERR_PTR(status);
}
-int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
struct posix_acl *dfacl)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -198,6 +198,15 @@ out:
return status;
}
+int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
+ struct posix_acl *dfacl)
+{
+ int ret;
+ ret = __nfs3_proc_setacls(inode, acl, dfacl);
+ return (ret == -EOPNOTSUPP) ? 0 : ret;
+
+}
+
int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
struct posix_acl *alloc = NULL, *dfacl = NULL;
@@ -225,7 +234,7 @@ int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type)
if (IS_ERR(alloc))
goto fail;
}
- status = nfs3_proc_setacls(inode, acl, dfacl);
+ status = __nfs3_proc_setacls(inode, acl, dfacl);
posix_acl_release(alloc);
return status;
@@ -233,25 +242,6 @@ fail:
return PTR_ERR(alloc);
}
-int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode,
- umode_t mode)
-{
- struct posix_acl *default_acl, *acl;
- int error;
-
- error = posix_acl_create(dir, &mode, &default_acl, &acl);
- if (error)
- return (error == -EOPNOTSUPP) ? 0 : error;
-
- error = nfs3_proc_setacls(inode, acl, default_acl);
-
- if (acl)
- posix_acl_release(acl);
- if (default_acl)
- posix_acl_release(default_acl);
- return error;
-}
-
const struct xattr_handler *nfs3_xattr_handlers[] = {
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index d2255d705421..a462ef0fb5d6 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -18,6 +18,7 @@
#include <linux/lockd/bind.h>
#include <linux/nfs_mount.h>
#include <linux/freezer.h>
+#include <linux/xattr.h>
#include "iostat.h"
#include "internal.h"
@@ -924,11 +925,11 @@ static const struct inode_operations nfs3_dir_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
+#ifdef CONFIG_NFS_V3_ACL
.listxattr = generic_listxattr,
.getxattr = generic_getxattr,
.setxattr = generic_setxattr,
.removexattr = generic_removexattr,
-#ifdef CONFIG_NFS_V3_ACL
.get_acl = nfs3_get_acl,
.set_acl = nfs3_set_acl,
#endif
@@ -938,11 +939,11 @@ static const struct inode_operations nfs3_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
+#ifdef CONFIG_NFS_V3_ACL
.listxattr = generic_listxattr,
.getxattr = generic_getxattr,
.setxattr = generic_setxattr,
.removexattr = generic_removexattr,
-#ifdef CONFIG_NFS_V3_ACL
.get_acl = nfs3_get_acl,
.set_acl = nfs3_set_acl,
#endif
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 5609edc742a0..a5b27c2d9689 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -270,6 +270,7 @@ static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *ser
extern int nfs41_setup_sequence(struct nfs4_session *session,
struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
struct rpc_task *task);
+extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 73d4ecda1e36..0e46d3d1b6cc 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -170,7 +170,7 @@ void nfs41_shutdown_client(struct nfs_client *clp)
void nfs40_shutdown_client(struct nfs_client *clp)
{
if (clp->cl_slot_tbl) {
- nfs4_release_slot_table(clp->cl_slot_tbl);
+ nfs4_shutdown_slot_table(clp->cl_slot_tbl);
kfree(clp->cl_slot_tbl);
}
}
@@ -372,10 +372,7 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
__set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
- error = -EINVAL;
- if (gssd_running(clp->cl_net))
- error = nfs_create_rpc_client(clp, timeparms,
- RPC_AUTH_GSS_KRB5I);
+ error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_GSS_KRB5I);
if (error == -EINVAL)
error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
if (error < 0)
@@ -1138,6 +1135,7 @@ static int nfs_probe_destination(struct nfs_server *server)
* @hostname: new end-point's hostname
* @sap: new end-point's socket address
* @salen: size of "sap"
+ * @net: net namespace
*
* The nfs_server must be quiescent before this function is invoked.
* Either its session is drained (NFSv4.1+), or its transport is
@@ -1146,13 +1144,13 @@ static int nfs_probe_destination(struct nfs_server *server)
* Returns zero on success, or a negative errno value.
*/
int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen)
+ struct sockaddr *sap, size_t salen, struct net *net)
{
struct nfs_client *clp = server->nfs_client;
struct rpc_clnt *clnt = server->client;
struct xprt_create xargs = {
.ident = clp->cl_proto,
- .net = &init_net,
+ .net = net,
.dstaddr = sap,
.addrlen = salen,
.servername = hostname,
@@ -1192,7 +1190,7 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
error = nfs4_set_client(server, hostname, sap, salen, buf,
clp->cl_rpcclient->cl_auth->au_flavor,
clp->cl_proto, clnt->cl_timeout,
- clp->cl_minorversion, clp->cl_net);
+ clp->cl_minorversion, net);
nfs_put_client(clp);
if (error != 0) {
nfs_server_insert_lists(server);
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 03fd8be8c0c5..b9a35c05b60f 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -324,8 +324,9 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
&rdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
- rdata->args.lock_context, FMODE_READ);
+ if (nfs4_set_rw_stateid(&rdata->args.stateid, rdata->args.context,
+ rdata->args.lock_context, FMODE_READ) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_read_call_done(struct rpc_task *task, void *data)
@@ -335,8 +336,10 @@ static void filelayout_read_call_done(struct rpc_task *task, void *data)
dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
- task->tk_status == 0)
+ task->tk_status == 0) {
+ nfs41_sequence_done(task, &rdata->res.seq_res);
return;
+ }
/* Note this may cause RPC to be resent */
rdata->header->mds_ops->rpc_call_done(task, data);
@@ -433,8 +436,9 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
&wdata->res.seq_res,
task))
return;
- nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
- wdata->args.lock_context, FMODE_WRITE);
+ if (nfs4_set_rw_stateid(&wdata->args.stateid, wdata->args.context,
+ wdata->args.lock_context, FMODE_WRITE) == -EIO)
+ rpc_exit(task, -EIO); /* lost lock, terminate I/O */
}
static void filelayout_write_call_done(struct rpc_task *task, void *data)
@@ -442,8 +446,10 @@ static void filelayout_write_call_done(struct rpc_task *task, void *data)
struct nfs_write_data *wdata = data;
if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
- task->tk_status == 0)
+ task->tk_status == 0) {
+ nfs41_sequence_done(task, &wdata->res.seq_res);
return;
+ }
/* Note this may cause RPC to be resent */
wdata->header->mds_ops->rpc_call_done(task, data);
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 4e7f05d3e9db..3d5dbf80d46a 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,8 @@ static int nfs4_validate_fspath(struct dentry *dentry,
}
static size_t nfs_parse_server_name(char *string, size_t len,
- struct sockaddr *sa, size_t salen, struct nfs_server *server)
+ struct sockaddr *sa, size_t salen, struct net *net)
{
- struct net *net = rpc_net_ns(server->client);
ssize_t ret;
ret = rpc_pton(net, string, len, sa, salen);
@@ -223,6 +222,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(NFS_SB(mountdata->sb)->client);
struct vfsmount *mnt = ERR_PTR(-ENOENT);
char *mnt_path;
unsigned int maxbuflen;
@@ -248,8 +248,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
continue;
mountdata->addrlen = nfs_parse_server_name(buf->data, buf->len,
- mountdata->addr, addr_bufsize,
- NFS_SB(mountdata->sb));
+ mountdata->addr, addr_bufsize, net);
if (mountdata->addrlen == 0)
continue;
@@ -419,6 +418,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
const struct nfs4_fs_location *location)
{
const size_t addr_bufsize = sizeof(struct sockaddr_storage);
+ struct net *net = rpc_net_ns(server->client);
struct sockaddr *sap;
unsigned int s;
size_t salen;
@@ -440,7 +440,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
continue;
salen = nfs_parse_server_name(buf->data, buf->len,
- sap, addr_bufsize, server);
+ sap, addr_bufsize, net);
if (salen == 0)
continue;
rpc_set_port(sap, NFS_PORT);
@@ -450,7 +450,7 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
if (hostname == NULL)
break;
- error = nfs4_update_server(server, hostname, sap, salen);
+ error = nfs4_update_server(server, hostname, sap, salen, net);
kfree(hostname);
if (error == 0)
break;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index a1965329a12c..450bfedbe2f4 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -539,7 +539,7 @@ static int nfs40_sequence_done(struct rpc_task *task,
struct nfs4_slot *slot = res->sr_slot;
struct nfs4_slot_table *tbl;
- if (!RPC_WAS_SENT(task))
+ if (slot == NULL)
goto out;
tbl = slot->table;
@@ -559,15 +559,10 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
struct nfs4_slot_table *tbl;
+ struct nfs4_slot *slot = res->sr_slot;
bool send_new_highest_used_slotid = false;
- if (!res->sr_slot) {
- /* just wake up the next guy waiting since
- * we may have not consumed a slot after all */
- dprintk("%s: No slot\n", __func__);
- return;
- }
- tbl = res->sr_slot->table;
+ tbl = slot->table;
session = tbl->session;
spin_lock(&tbl->slot_tbl_lock);
@@ -577,11 +572,11 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
if (tbl->highest_used_slotid > tbl->target_highest_slotid)
send_new_highest_used_slotid = true;
- if (nfs41_wake_and_assign_slot(tbl, res->sr_slot)) {
+ if (nfs41_wake_and_assign_slot(tbl, slot)) {
send_new_highest_used_slotid = false;
goto out_unlock;
}
- nfs4_free_slot(tbl, res->sr_slot);
+ nfs4_free_slot(tbl, slot);
if (tbl->highest_used_slotid != NFS4_NO_SLOT)
send_new_highest_used_slotid = false;
@@ -592,19 +587,20 @@ out_unlock:
nfs41_server_notify_highest_slotid_update(session->clp);
}
-static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
+int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
{
struct nfs4_session *session;
- struct nfs4_slot *slot;
+ struct nfs4_slot *slot = res->sr_slot;
struct nfs_client *clp;
bool interrupted = false;
int ret = 1;
+ if (slot == NULL)
+ goto out_noaction;
/* don't increment the sequence number if the task wasn't sent */
if (!RPC_WAS_SENT(task))
goto out;
- slot = res->sr_slot;
session = slot->table->session;
if (slot->interrupted) {
@@ -679,6 +675,7 @@ out:
/* The session may be reset by one of the error handlers. */
dprintk("%s: Error %d free the slot \n", __func__, res->sr_status);
nfs41_sequence_free_slot(res);
+out_noaction:
return ret;
retry_nowait:
if (rpc_restart_call_prepare(task)) {
@@ -692,6 +689,7 @@ out_retry:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
return 0;
}
+EXPORT_SYMBOL_GPL(nfs41_sequence_done);
static int nfs4_sequence_done(struct rpc_task *task,
struct nfs4_sequence_res *res)
@@ -1622,15 +1620,15 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
- nfs40_setup_sequence(data->o_arg.server, &data->o_arg.seq_args,
- &data->o_res.seq_res, task);
+ nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
+ &data->c_res.seq_res, task);
}
static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
{
struct nfs4_opendata *data = calldata;
- nfs40_sequence_done(task, &data->o_res.seq_res);
+ nfs40_sequence_done(task, &data->c_res.seq_res);
data->rpc_status = task->tk_status;
if (data->rpc_status == 0) {
@@ -1688,7 +1686,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
};
int status;
- nfs4_init_sequence(&data->o_arg.seq_args, &data->o_res.seq_res, 1);
+ nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
kref_get(&data->kref);
data->rpc_done = 0;
data->rpc_status = 0;
@@ -2400,13 +2398,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
/* Use that stateid */
- } else if (truncate && state != NULL && nfs4_valid_open_stateid(state)) {
+ } else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
.l_owner = current->files,
.l_pid = current->tgid,
};
- nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner);
+ if (!nfs4_valid_open_stateid(state))
+ return -EBADF;
+ if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
+ &lockowner) == -EIO)
+ return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
@@ -2744,7 +2745,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
NFS_CAP_CTIME|NFS_CAP_MTIME|
NFS_CAP_SECURITY_LABEL);
- if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
+ if (res.attr_bitmask[0] & FATTR4_WORD0_ACL &&
+ res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
server->caps |= NFS_CAP_ACLS;
if (res.has_links != 0)
server->caps |= NFS_CAP_HARDLINKS;
@@ -4012,8 +4014,9 @@ static bool nfs4_stateid_is_current(nfs4_stateid *stateid,
{
nfs4_stateid current_stateid;
- if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode))
- return false;
+ /* If the current stateid represents a lost lock, then exit */
+ if (nfs4_set_rw_stateid(&current_stateid, ctx, l_ctx, fmode) == -EIO)
+ return true;
return nfs4_stateid_match(stateid, &current_stateid);
}
@@ -4321,9 +4324,7 @@ static int nfs4_proc_renew(struct nfs_client *clp, struct rpc_cred *cred)
static inline int nfs4_server_supports_acls(struct nfs_server *server)
{
- return (server->caps & NFS_CAP_ACLS)
- && (server->acl_bitmask & ACL4_SUPPORT_ALLOW_ACL)
- && (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL);
+ return server->caps & NFS_CAP_ACLS;
}
/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that
@@ -5831,8 +5832,7 @@ struct nfs_release_lockowner_data {
struct nfs4_lock_state *lsp;
struct nfs_server *server;
struct nfs_release_lockowner_args args;
- struct nfs4_sequence_args seq_args;
- struct nfs4_sequence_res seq_res;
+ struct nfs_release_lockowner_res res;
unsigned long timestamp;
};
@@ -5840,7 +5840,7 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
{
struct nfs_release_lockowner_data *data = calldata;
nfs40_setup_sequence(data->server,
- &data->seq_args, &data->seq_res, task);
+ &data->args.seq_args, &data->res.seq_res, task);
data->timestamp = jiffies;
}
@@ -5849,7 +5849,7 @@ static void nfs4_release_lockowner_done(struct rpc_task *task, void *calldata)
struct nfs_release_lockowner_data *data = calldata;
struct nfs_server *server = data->server;
- nfs40_sequence_done(task, &data->seq_res);
+ nfs40_sequence_done(task, &data->res.seq_res);
switch (task->tk_status) {
case 0:
@@ -5890,7 +5890,6 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data = kmalloc(sizeof(*data), GFP_NOFS);
if (!data)
return -ENOMEM;
- nfs4_init_sequence(&data->seq_args, &data->seq_res, 0);
data->lsp = lsp;
data->server = server;
data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
@@ -5898,6 +5897,8 @@ static int nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_st
data->args.lock_owner.s_dev = server->s_dev;
msg.rpc_argp = &data->args;
+ msg.rpc_resp = &data->res;
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
rpc_call_async(server->client, &msg, 0, &nfs4_release_lockowner_ops, data);
return 0;
}
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index cf883c7ae053..e799dc3c3b1d 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -231,14 +231,23 @@ out:
return ret;
}
+/*
+ * nfs4_release_slot_table - release all slot table entries
+ */
+static void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+{
+ nfs4_shrink_slot_table(tbl, 0);
+}
+
/**
- * nfs4_release_slot_table - release resources attached to a slot table
+ * nfs4_shutdown_slot_table - release resources attached to a slot table
* @tbl: slot table to shut down
*
*/
-void nfs4_release_slot_table(struct nfs4_slot_table *tbl)
+void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl)
{
- nfs4_shrink_slot_table(tbl, 0);
+ nfs4_release_slot_table(tbl);
+ rpc_destroy_wait_queue(&tbl->slot_tbl_waitq);
}
/**
@@ -422,7 +431,7 @@ void nfs41_update_target_slotid(struct nfs4_slot_table *tbl,
spin_unlock(&tbl->slot_tbl_lock);
}
-static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+static void nfs4_release_session_slot_tables(struct nfs4_session *session)
{
nfs4_release_slot_table(&session->fc_slot_table);
nfs4_release_slot_table(&session->bc_slot_table);
@@ -450,7 +459,7 @@ int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
if (status && tbl->slots == NULL)
/* Fore and back channel share a connection so get
* both slot tables or neither */
- nfs4_destroy_session_slot_tables(ses);
+ nfs4_release_session_slot_tables(ses);
return status;
}
@@ -470,6 +479,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
return session;
}
+static void nfs4_destroy_session_slot_tables(struct nfs4_session *session)
+{
+ nfs4_shutdown_slot_table(&session->fc_slot_table);
+ nfs4_shutdown_slot_table(&session->bc_slot_table);
+}
+
void nfs4_destroy_session(struct nfs4_session *session)
{
struct rpc_xprt *xprt;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index 232306100651..b34ada9bc6a2 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -74,7 +74,7 @@ enum nfs4_session_state {
extern int nfs4_setup_slot_table(struct nfs4_slot_table *tbl,
unsigned int max_reqs, const char *queue);
-extern void nfs4_release_slot_table(struct nfs4_slot_table *tbl);
+extern void nfs4_shutdown_slot_table(struct nfs4_slot_table *tbl);
extern struct nfs4_slot *nfs4_alloc_slot(struct nfs4_slot_table *tbl);
extern void nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *slot);
extern void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index e5be72518bd7..0deb32105ccf 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -974,9 +974,6 @@ static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
ret = 0;
- smp_rmb();
- if (!list_empty(&lsp->ls_seqid.list))
- ret = -EWOULDBLOCK;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
@@ -984,10 +981,9 @@ out:
return ret;
}
-static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
+static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
const nfs4_stateid *src;
- int ret;
int seq;
do {
@@ -996,12 +992,7 @@ static int nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
if (test_bit(NFS_OPEN_STATE, &state->flags))
src = &state->open_stateid;
nfs4_stateid_copy(dst, src);
- ret = 0;
- smp_rmb();
- if (!list_empty(&state->owner->so_seqid.list))
- ret = -EWOULDBLOCK;
} while (read_seqretry(&state->seqlock, seq));
- return ret;
}
/*
@@ -1015,15 +1006,19 @@ int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
if (ret == -EIO)
/* A lost lock - don't even consider delegations */
goto out;
- if (nfs4_copy_delegation_stateid(dst, state->inode, fmode))
+ /* returns true if delegation stateid found and copied */
+ if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+ ret = 0;
goto out;
+ }
if (ret != -ENOENT)
/* nfs4_copy_delegation_stateid() didn't over-write
* dst, so it still has the lock stateid which we now
* choose to use.
*/
goto out;
- ret = nfs4_copy_open_stateid(dst, state);
+ nfs4_copy_open_stateid(dst, state);
+ ret = 0;
out:
if (nfs_server_capable(state->inode, NFS_CAP_STATEID_NFSV41))
dst->seqid = 0;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8c21d69a9dc1..72f3bf1754ef 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -3449,7 +3449,7 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint
{
__be32 *p;
- *res = ACL4_SUPPORT_ALLOW_ACL|ACL4_SUPPORT_DENY_ACL;
+ *res = 0;
if (unlikely(bitmap[0] & (FATTR4_WORD0_ACLSUPPORT - 1U)))
return -EIO;
if (likely(bitmap[0] & FATTR4_WORD0_ACLSUPPORT)) {
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 89fe741e58b1..59f838cdc009 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,6 +36,7 @@
__print_flags(v, "|", \
{ 1 << NFS_INO_ADVISE_RDPLUS, "ADVISE_RDPLUS" }, \
{ 1 << NFS_INO_STALE, "STALE" }, \
+ { 1 << NFS_INO_INVALIDATING, "INVALIDATING" }, \
{ 1 << NFS_INO_FLUSHING, "FLUSHING" }, \
{ 1 << NFS_INO_FSCACHE, "FSCACHE" }, \
{ 1 << NFS_INO_COMMIT, "COMMIT" }, \
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index a44a87268a6e..9a3b6a4cd6b9 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -909,9 +909,14 @@ bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx)
*/
static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
{
+ struct nfs_inode *nfsi = NFS_I(inode);
+
if (nfs_have_delegated_attributes(inode))
goto out;
- if (NFS_I(inode)->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ if (nfsi->cache_validity & (NFS_INO_INVALID_DATA|NFS_INO_REVAL_PAGECACHE))
+ return false;
+ smp_rmb();
+ if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
return false;
out:
return PageUptodate(page) != 0;
diff --git a/fs/nfsd/acl.h b/fs/nfsd/acl.h
index 8b68218e2c1c..a812fd1b92a4 100644
--- a/fs/nfsd/acl.h
+++ b/fs/nfsd/acl.h
@@ -45,7 +45,7 @@ struct svc_rqst;
struct nfs4_acl *nfs4_acl_new(int);
int nfs4_acl_get_whotype(char *, u32);
-int nfs4_acl_write_who(int who, char *p);
+__be32 nfs4_acl_write_who(int who, __be32 **p, int *len);
int nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
struct nfs4_acl **acl);
diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h
index d5c5b3e00266..b582f9ab6b2a 100644
--- a/fs/nfsd/cache.h
+++ b/fs/nfsd/cache.h
@@ -84,12 +84,4 @@ int nfsd_cache_lookup(struct svc_rqst *);
void nfsd_cache_update(struct svc_rqst *, int, __be32 *);
int nfsd_reply_cache_stats_open(struct inode *, struct file *);
-#ifdef CONFIG_NFSD_V4
-void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp);
-#else /* CONFIG_NFSD_V4 */
-static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
-{
-}
-#endif /* CONFIG_NFSD_V4 */
-
#endif /* NFSCACHE_H */
diff --git a/fs/nfsd/idmap.h b/fs/nfsd/idmap.h
index bf95f6b817a4..66e58db01936 100644
--- a/fs/nfsd/idmap.h
+++ b/fs/nfsd/idmap.h
@@ -56,7 +56,7 @@ static inline void nfsd_idmap_shutdown(struct net *net)
__be32 nfsd_map_name_to_uid(struct svc_rqst *, const char *, size_t, kuid_t *);
__be32 nfsd_map_name_to_gid(struct svc_rqst *, const char *, size_t, kgid_t *);
-int nfsd_map_uid_to_name(struct svc_rqst *, kuid_t, char *);
-int nfsd_map_gid_to_name(struct svc_rqst *, kgid_t, char *);
+__be32 nfsd4_encode_user(struct svc_rqst *, kuid_t, __be32 **, int *);
+__be32 nfsd4_encode_group(struct svc_rqst *, kgid_t, __be32 **, int *);
#endif /* LINUX_NFSD_IDMAP_H */
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 849a7c3ced22..d32b3aa6600d 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -95,6 +95,7 @@ struct nfsd_net {
time_t nfsd4_grace;
bool nfsd_net_up;
+ bool lockd_up;
/*
* Time of server startup
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 14d9ecb96cff..de6e39e12cb3 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -168,7 +168,7 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
struct kstat *stat)
{
*p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]);
- *p++ = htonl((u32) stat->mode);
+ *p++ = htonl((u32) (stat->mode & S_IALLUGO));
*p++ = htonl((u32) stat->nlink);
*p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
*p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
@@ -842,21 +842,21 @@ out:
static __be32 *encode_entryplus_baggage(struct nfsd3_readdirres *cd, __be32 *p, const char *name, int namlen)
{
- struct svc_fh fh;
+ struct svc_fh *fh = &cd->scratch;
__be32 err;
- fh_init(&fh, NFS3_FHSIZE);
- err = compose_entry_fh(cd, &fh, name, namlen);
+ fh_init(fh, NFS3_FHSIZE);
+ err = compose_entry_fh(cd, fh, name, namlen);
if (err) {
*p++ = 0;
*p++ = 0;
goto out;
}
- p = encode_post_op_attr(cd->rqstp, p, &fh);
+ p = encode_post_op_attr(cd->rqstp, p, fh);
*p++ = xdr_one; /* yes, a file handle follows */
- p = encode_fh(p, &fh);
+ p = encode_fh(p, fh);
out:
- fh_put(&fh);
+ fh_put(fh);
return p;
}
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 649ad7cf2204..d190e33d0ec2 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -38,6 +38,7 @@
#include <linux/nfs_fs.h>
#include <linux/export.h>
#include "nfsfh.h"
+#include "nfsd.h"
#include "acl.h"
#include "vfs.h"
@@ -150,17 +151,15 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
if (IS_ERR(pacl))
return PTR_ERR(pacl);
- /* allocate for worst case: one (deny, allow) pair each: */
- size += 2 * pacl->a_count;
}
+ /* allocate for worst case: one (deny, allow) pair each: */
+ size += 2 * pacl->a_count;
if (S_ISDIR(inode->i_mode)) {
flags = NFS4_ACL_DIR;
dpacl = get_acl(inode, ACL_TYPE_DEFAULT);
if (dpacl)
size += 2 * dpacl->a_count;
- } else {
- dpacl = NULL;
}
*acl = nfs4_acl_new(size);
@@ -169,8 +168,7 @@ nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
goto out;
}
- if (pacl)
- _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+ _posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
if (dpacl)
_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
@@ -916,17 +914,22 @@ nfs4_acl_get_whotype(char *p, u32 len)
return NFS4_ACL_WHO_NAMED;
}
-int
-nfs4_acl_write_who(int who, char *p)
+__be32 nfs4_acl_write_who(int who, __be32 **p, int *len)
{
int i;
+ int bytes;
for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
- if (s2t_map[i].type == who) {
- memcpy(p, s2t_map[i].string, s2t_map[i].stringlen);
- return s2t_map[i].stringlen;
- }
+ if (s2t_map[i].type != who)
+ continue;
+ bytes = 4 + (XDR_QUADLEN(s2t_map[i].stringlen) << 2);
+ if (bytes > *len)
+ return nfserr_resource;
+ *p = xdr_encode_opaque(*p, s2t_map[i].string,
+ s2t_map[i].stringlen);
+ *len -= bytes;
+ return 0;
}
- BUG();
+ WARN_ON_ONCE(1);
return -1;
}
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 4832fd819f88..c0dfde68742e 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -551,27 +551,46 @@ idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen
return 0;
}
-static int
-idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
+static __be32 encode_ascii_id(u32 id, __be32 **p, int *buflen)
+{
+ char buf[11];
+ int len;
+ int bytes;
+
+ len = sprintf(buf, "%u", id);
+ bytes = 4 + (XDR_QUADLEN(len) << 2);
+ if (bytes > *buflen)
+ return nfserr_resource;
+ *p = xdr_encode_opaque(*p, buf, len);
+ *buflen -= bytes;
+ return 0;
+}
+
+static __be32 idmap_id_to_name(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
{
struct ent *item, key = {
.id = id,
.type = type,
};
int ret;
+ int bytes;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
strlcpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
if (ret == -ENOENT)
- return sprintf(name, "%u", id);
+ return encode_ascii_id(id, p, buflen);
if (ret)
- return ret;
+ return nfserrno(ret);
ret = strlen(item->name);
- BUG_ON(ret > IDMAP_NAMESZ);
- memcpy(name, item->name, ret);
+ WARN_ON_ONCE(ret > IDMAP_NAMESZ);
+ bytes = 4 + (XDR_QUADLEN(ret) << 2);
+ if (bytes > *buflen)
+ return nfserr_resource;
+ *p = xdr_encode_opaque(*p, item->name, ret);
+ *buflen -= bytes;
cache_put(&item->h, nn->idtoname_cache);
- return ret;
+ return 0;
}
static bool
@@ -603,12 +622,11 @@ do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u
return idmap_name_to_id(rqstp, type, name, namelen, id);
}
-static int
-do_id_to_name(struct svc_rqst *rqstp, int type, u32 id, char *name)
+static __be32 encode_name_from_id(struct svc_rqst *rqstp, int type, u32 id, __be32 **p, int *buflen)
{
if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
- return sprintf(name, "%u", id);
- return idmap_id_to_name(rqstp, type, id, name);
+ return encode_ascii_id(id, p, buflen);
+ return idmap_id_to_name(rqstp, type, id, p, buflen);
}
__be32
@@ -637,16 +655,14 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
return status;
}
-int
-nfsd_map_uid_to_name(struct svc_rqst *rqstp, kuid_t uid, char *name)
+__be32 nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t uid, __be32 **p, int *buflen)
{
u32 id = from_kuid(&init_user_ns, uid);
- return do_id_to_name(rqstp, IDMAP_TYPE_USER, id, name);
+ return encode_name_from_id(rqstp, IDMAP_TYPE_USER, id, p, buflen);
}
-int
-nfsd_map_gid_to_name(struct svc_rqst *rqstp, kgid_t gid, char *name)
+__be32 nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t gid, __be32 **p, int *buflen)
{
u32 id = from_kgid(&init_user_ns, gid);
- return do_id_to_name(rqstp, IDMAP_TYPE_GROUP, id, name);
+ return encode_name_from_id(rqstp, IDMAP_TYPE_GROUP, id, p, buflen);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 825b8a99b99b..82189b208af3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -231,17 +231,16 @@ static void nfsd4_set_open_owner_reply_cache(struct nfsd4_compound_state *cstate
}
static __be32
-do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct svc_fh **resfh)
{
struct svc_fh *current_fh = &cstate->current_fh;
- struct svc_fh *resfh;
int accmode;
__be32 status;
- resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
- if (!resfh)
+ *resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+ if (!*resfh)
return nfserr_jukebox;
- fh_init(resfh, NFS4_FHSIZE);
+ fh_init(*resfh, NFS4_FHSIZE);
open->op_truncate = 0;
if (open->op_create) {
@@ -266,12 +265,12 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
*/
status = do_nfsd_create(rqstp, current_fh, open->op_fname.data,
open->op_fname.len, &open->op_iattr,
- resfh, open->op_createmode,
+ *resfh, open->op_createmode,
(u32 *)open->op_verf.data,
&open->op_truncate, &open->op_created);
if (!status && open->op_label.len)
- nfsd4_security_inode_setsecctx(resfh, &open->op_label, open->op_bmval);
+ nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);
/*
* Following rfc 3530 14.2.16, use the returned bitmask
@@ -281,31 +280,32 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS |
FATTR4_WORD1_TIME_MODIFY);
- } else {
+ } else
+ /*
+ * Note this may exit with the parent still locked.
+ * We will hold the lock until nfsd4_open's final
+ * lookup, to prevent renames or unlinks until we've had
+ * a chance to an acquire a delegation if appropriate.
+ */
status = nfsd_lookup(rqstp, current_fh,
- open->op_fname.data, open->op_fname.len, resfh);
- fh_unlock(current_fh);
- }
+ open->op_fname.data, open->op_fname.len, *resfh);
if (status)
goto out;
- status = nfsd_check_obj_isreg(resfh);
+ status = nfsd_check_obj_isreg(*resfh);
if (status)
goto out;
if (is_create_with_attrs(open) && open->op_acl != NULL)
- do_set_nfs4_acl(rqstp, resfh, open->op_acl, open->op_bmval);
+ do_set_nfs4_acl(rqstp, *resfh, open->op_acl, open->op_bmval);
- nfsd4_set_open_owner_reply_cache(cstate, open, resfh);
+ nfsd4_set_open_owner_reply_cache(cstate, open, *resfh);
accmode = NFSD_MAY_NOP;
if (open->op_created ||
open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR)
accmode |= NFSD_MAY_OWNER_OVERRIDE;
- status = do_open_permission(rqstp, resfh, open, accmode);
+ status = do_open_permission(rqstp, *resfh, open, accmode);
set_change_info(&open->op_cinfo, current_fh);
- fh_dup2(current_fh, resfh);
out:
- fh_put(resfh);
- kfree(resfh);
return status;
}
@@ -358,6 +358,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_open *open)
{
__be32 status;
+ struct svc_fh *resfh = NULL;
struct nfsd4_compoundres *resp;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -424,7 +425,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
switch (open->op_claim_type) {
case NFS4_OPEN_CLAIM_DELEGATE_CUR:
case NFS4_OPEN_CLAIM_NULL:
- status = do_open_lookup(rqstp, cstate, open);
+ status = do_open_lookup(rqstp, cstate, open, &resfh);
if (status)
goto out;
break;
@@ -440,6 +441,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = do_open_fhandle(rqstp, cstate, open);
if (status)
goto out;
+ resfh = &cstate->current_fh;
break;
case NFS4_OPEN_CLAIM_DELEG_PREV_FH:
case NFS4_OPEN_CLAIM_DELEGATE_PREV:
@@ -459,9 +461,14 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
* successful, it (1) truncates the file if open->op_truncate was
* set, (2) sets open->op_stateid, (3) sets open->op_delegation.
*/
- status = nfsd4_process_open2(rqstp, &cstate->current_fh, open);
+ status = nfsd4_process_open2(rqstp, resfh, open);
WARN_ON(status && open->op_created);
out:
+ if (resfh && resfh != &cstate->current_fh) {
+ fh_dup2(&cstate->current_fh, resfh);
+ fh_put(resfh);
+ kfree(resfh);
+ }
nfsd4_cleanup_open_state(open, status);
if (open->op_openowner && !nfsd4_has_session(cstate))
cstate->replay_owner = &open->op_openowner->oo_owner;
@@ -1070,8 +1077,10 @@ _nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
cstate->current_fh.fh_dentry, &p,
count, verify->ve_bmval,
rqstp, 0);
-
- /* this means that nfsd4_encode_fattr() ran out of space */
+ /*
+ * If nfsd4_encode_fattr() ran out of space, assume that's because
+ * the attributes are longer (hence different) than those given:
+ */
if (status == nfserr_resource)
status = nfserr_not_same;
if (status)
@@ -1525,7 +1534,8 @@ static inline u32 nfsd4_write_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
static inline u32 nfsd4_exchange_id_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
{
return (op_encode_hdr_size + 2 + 1 + /* eir_clientid, eir_sequenceid */\
- 1 + 1 + 2 + /* eir_flags, spr_how, spo_must_enforce & _allow */\
+ 1 + 1 + /* eir_flags, spr_how */\
+ 4 + /* spo_must_enforce & _allow with bitmap */\
2 + /*eir_server_owner.so_minor_id */\
/* eir_server_owner.so_major_id<> */\
XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\
@@ -1882,6 +1892,7 @@ struct svc_version nfsd_version4 = {
.vs_proc = nfsd_procedures4,
.vs_dispatch = nfsd_dispatch,
.vs_xdrsize = NFS4_SVC_XDRSIZE,
+ .vs_rpcb_optnl = 1,
};
/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 105d6fa7c514..d5d070fbeb35 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -832,10 +832,11 @@ static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca)
spin_unlock(&nfsd_drc_lock);
}
-static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *attrs)
+static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
+ struct nfsd4_channel_attrs *battrs)
{
- int numslots = attrs->maxreqs;
- int slotsize = slot_bytes(attrs);
+ int numslots = fattrs->maxreqs;
+ int slotsize = slot_bytes(fattrs);
struct nfsd4_session *new;
int mem, i;
@@ -852,6 +853,10 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *attrs)
if (!new->se_slots[i])
goto out_free;
}
+
+ memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
+ memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs));
+
return new;
out_free:
while (i--)
@@ -997,8 +1002,7 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
list_add(&new->se_perclnt, &clp->cl_sessions);
spin_unlock(&clp->cl_lock);
spin_unlock(&nn->client_lock);
- memcpy(&new->se_fchannel, &cses->fore_channel,
- sizeof(struct nfsd4_channel_attrs));
+
if (cses->flags & SESSION4_BACK_CHAN) {
struct sockaddr *sa = svc_addr(rqstp);
/*
@@ -1851,6 +1855,11 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs
return nfs_ok;
}
+#define NFSD_CB_MAX_REQ_SZ ((NFS4_enc_cb_recall_sz + \
+ RPC_MAX_HEADER_WITH_AUTH) * sizeof(__be32))
+#define NFSD_CB_MAX_RESP_SZ ((NFS4_dec_cb_recall_sz + \
+ RPC_MAX_REPHEADER_WITH_AUTH) * sizeof(__be32))
+
static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
{
ca->headerpadsz = 0;
@@ -1861,9 +1870,9 @@ static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca)
* less than 1k. Tighten up this estimate in the unlikely event
* it turns out to be a problem for some client:
*/
- if (ca->maxreq_sz < NFS4_enc_cb_recall_sz + RPC_MAX_HEADER_WITH_AUTH)
+ if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ)
return nfserr_toosmall;
- if (ca->maxresp_sz < NFS4_dec_cb_recall_sz + RPC_MAX_REPHEADER_WITH_AUTH)
+ if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ)
return nfserr_toosmall;
ca->maxresp_cached = 0;
if (ca->maxops < 2)
@@ -1913,9 +1922,9 @@ nfsd4_create_session(struct svc_rqst *rqstp,
return status;
status = check_backchannel_attrs(&cr_ses->back_channel);
if (status)
- return status;
+ goto out_release_drc_mem;
status = nfserr_jukebox;
- new = alloc_session(&cr_ses->fore_channel);
+ new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel);
if (!new)
goto out_release_drc_mem;
conn = alloc_conn_from_crses(rqstp, cr_ses);
@@ -3034,18 +3043,18 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
if (!fl)
return -ENOMEM;
fl->fl_file = find_readable_file(fp);
- list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
- if (status) {
- list_del_init(&dp->dl_perclnt);
- locks_free_lock(fl);
- return status;
- }
+ if (status)
+ goto out_free;
+ list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
fp->fi_lease = fl;
fp->fi_deleg_file = get_file(fl->fl_file);
atomic_set(&fp->fi_delegees, 1);
list_add(&dp->dl_perfile, &fp->fi_delegations);
return 0;
+out_free:
+ locks_free_lock(fl);
+ return status;
}
static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp)
@@ -3125,6 +3134,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
goto out_no_deleg;
break;
case NFS4_OPEN_CLAIM_NULL:
+ case NFS4_OPEN_CLAIM_FH:
/*
* Let's not give out any delegations till everyone's
* had the chance to reclaim theirs....
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index ee7237f99f54..63f2395c57ed 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -103,11 +103,6 @@ xdr_error: \
(x) = (u64)ntohl(*p++) << 32; \
(x) |= ntohl(*p++); \
} while (0)
-#define READTIME(x) do { \
- p++; \
- (x) = ntohl(*p++); \
- p++; \
-} while (0)
#define READMEM(x,nbytes) do { \
x = (char *)p; \
p += XDR_QUADLEN(nbytes); \
@@ -190,6 +185,15 @@ static int zero_clientid(clientid_t *clid)
return (clid->cl_boot == 0) && (clid->cl_id == 0);
}
+/**
+ * defer_free - mark an allocation as deferred freed
+ * @argp: NFSv4 compound argument structure to be freed with
+ * @release: release callback to free @p, typically kfree()
+ * @p: pointer to be freed
+ *
+ * Marks @p to be freed when processing the compound operation
+ * described in @argp finishes.
+ */
static int
defer_free(struct nfsd4_compoundargs *argp,
void (*release)(const void *), void *p)
@@ -206,6 +210,16 @@ defer_free(struct nfsd4_compoundargs *argp,
return 0;
}
+/**
+ * savemem - duplicate a chunk of memory for later processing
+ * @argp: NFSv4 compound argument structure to be freed with
+ * @p: pointer to be duplicated
+ * @nbytes: length to be duplicated
+ *
+ * Returns a pointer to a copy of @nbytes bytes of memory at @p
+ * that are preserved until processing of the NFSv4 compound
+ * operation described by @argp finishes.
+ */
static char *savemem(struct nfsd4_compoundargs *argp, __be32 *p, int nbytes)
{
if (p == argp->tmp) {
@@ -257,7 +271,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
int expected_len, len = 0;
u32 dummy32;
char *buf;
- int host_err;
DECODE_HEAD;
iattr->ia_valid = 0;
@@ -284,10 +297,9 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
return nfserr_resource;
*acl = nfs4_acl_new(nace);
- if (*acl == NULL) {
- host_err = -ENOMEM;
- goto out_nfserr;
- }
+ if (*acl == NULL)
+ return nfserr_jukebox;
+
defer_free(argp, kfree, *acl);
(*acl)->naces = nace;
@@ -425,10 +437,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
goto xdr_error;
DECODE_TAIL;
-
-out_nfserr:
- status = nfserrno(host_err);
- goto out;
}
static __be32
@@ -1957,56 +1965,16 @@ static u32 nfs4_file_type(umode_t mode)
};
}
-static __be32
-nfsd4_encode_name(struct svc_rqst *rqstp, int whotype, kuid_t uid, kgid_t gid,
- __be32 **p, int *buflen)
-{
- int status;
-
- if (*buflen < (XDR_QUADLEN(IDMAP_NAMESZ) << 2) + 4)
- return nfserr_resource;
- if (whotype != NFS4_ACL_WHO_NAMED)
- status = nfs4_acl_write_who(whotype, (u8 *)(*p + 1));
- else if (gid_valid(gid))
- status = nfsd_map_gid_to_name(rqstp, gid, (u8 *)(*p + 1));
- else
- status = nfsd_map_uid_to_name(rqstp, uid, (u8 *)(*p + 1));
- if (status < 0)
- return nfserrno(status);
- *p = xdr_encode_opaque(*p, NULL, status);
- *buflen -= (XDR_QUADLEN(status) << 2) + 4;
- BUG_ON(*buflen < 0);
- return 0;
-}
-
-static inline __be32
-nfsd4_encode_user(struct svc_rqst *rqstp, kuid_t user, __be32 **p, int *buflen)
-{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, user, INVALID_GID,
- p, buflen);
-}
-
-static inline __be32
-nfsd4_encode_group(struct svc_rqst *rqstp, kgid_t group, __be32 **p, int *buflen)
-{
- return nfsd4_encode_name(rqstp, NFS4_ACL_WHO_NAMED, INVALID_UID, group,
- p, buflen);
-}
-
static inline __be32
nfsd4_encode_aclname(struct svc_rqst *rqstp, struct nfs4_ace *ace,
__be32 **p, int *buflen)
{
- kuid_t uid = INVALID_UID;
- kgid_t gid = INVALID_GID;
-
- if (ace->whotype == NFS4_ACL_WHO_NAMED) {
- if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
- gid = ace->who_gid;
- else
- uid = ace->who_uid;
- }
- return nfsd4_encode_name(rqstp, ace->whotype, uid, gid, p, buflen);
+ if (ace->whotype != NFS4_ACL_WHO_NAMED)
+ return nfs4_acl_write_who(ace->whotype, p, buflen);
+ else if (ace->flag & NFS4_ACE_IDENTIFIER_GROUP)
+ return nfsd4_encode_group(rqstp, ace->who_gid, p, buflen);
+ else
+ return nfsd4_encode_user(rqstp, ace->who_uid, p, buflen);
}
#define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
@@ -2090,7 +2058,7 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
u32 bmval1 = bmval[1];
u32 bmval2 = bmval[2];
struct kstat stat;
- struct svc_fh tempfh;
+ struct svc_fh *tempfh = NULL;
struct kstatfs statfs;
int buflen = count << 2;
__be32 *attrlenp;
@@ -2137,11 +2105,15 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
goto out_nfserr;
}
if ((bmval0 & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) && !fhp) {
- fh_init(&tempfh, NFS4_FHSIZE);
- status = fh_compose(&tempfh, exp, dentry, NULL);
+ tempfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
+ status = nfserr_jukebox;
+ if (!tempfh)
+ goto out;
+ fh_init(tempfh, NFS4_FHSIZE);
+ status = fh_compose(tempfh, exp, dentry, NULL);
if (status)
goto out;
- fhp = &tempfh;
+ fhp = tempfh;
}
if (bmval0 & (FATTR4_WORD0_ACL | FATTR4_WORD0_ACLSUPPORT
| FATTR4_WORD0_SUPPORTED_ATTRS)) {
@@ -2222,8 +2194,10 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
if ((buflen -= 4) < 0)
goto out_resource;
dummy = nfs4_file_type(stat.mode);
- if (dummy == NF4BAD)
- goto out_serverfault;
+ if (dummy == NF4BAD) {
+ status = nfserr_serverfault;
+ goto out;
+ }
WRITE32(dummy);
}
if (bmval0 & FATTR4_WORD0_FH_EXPIRE_TYPE) {
@@ -2317,8 +2291,6 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
WRITE32(ace->flag);
WRITE32(ace->access_mask & NFS4_ACE_MASK_ALL);
status = nfsd4_encode_aclname(rqstp, ace, &p, &buflen);
- if (status == nfserr_resource)
- goto out_resource;
if (status)
goto out;
}
@@ -2379,8 +2351,6 @@ out_acl:
}
if (bmval0 & FATTR4_WORD0_FS_LOCATIONS) {
status = nfsd4_encode_fs_locations(rqstp, exp, &p, &buflen);
- if (status == nfserr_resource)
- goto out_resource;
if (status)
goto out;
}
@@ -2431,15 +2401,11 @@ out_acl:
}
if (bmval1 & FATTR4_WORD1_OWNER) {
status = nfsd4_encode_user(rqstp, stat.uid, &p, &buflen);
- if (status == nfserr_resource)
- goto out_resource;
if (status)
goto out;
}
if (bmval1 & FATTR4_WORD1_OWNER_GROUP) {
status = nfsd4_encode_group(rqstp, stat.gid, &p, &buflen);
- if (status == nfserr_resource)
- goto out_resource;
if (status)
goto out;
}
@@ -2533,8 +2499,8 @@ out:
security_release_secctx(context, contextlen);
#endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
kfree(acl);
- if (fhp == &tempfh)
- fh_put(&tempfh);
+ if (tempfh)
+ fh_put(tempfh);
return status;
out_nfserr:
status = nfserrno(err);
@@ -2542,9 +2508,6 @@ out_nfserr:
out_resource:
status = nfserr_resource;
goto out;
-out_serverfault:
- status = nfserr_serverfault;
- goto out;
}
static inline int attributes_need_mount(u32 *bmval)
@@ -2621,17 +2584,14 @@ out_put:
static __be32 *
nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr)
{
- __be32 *attrlenp;
-
if (buflen < 6)
return NULL;
*p++ = htonl(2);
*p++ = htonl(FATTR4_WORD0_RDATTR_ERROR); /* bmval0 */
*p++ = htonl(0); /* bmval1 */
- attrlenp = p++;
+ *p++ = htonl(4); /* attribute length */
*p++ = nfserr; /* no htonl */
- *attrlenp = htonl((char *)p - (char *)attrlenp - 4);
return p;
}
@@ -3244,7 +3204,7 @@ nfsd4_do_encode_secinfo(struct nfsd4_compoundres *resp,
if (rpcauth_get_gssinfo(pf, &info) == 0) {
supported++;
- RESERVE_SPACE(4 + 4 + info.oid.len + 4 + 4);
+ RESERVE_SPACE(4 + 4 + XDR_LEN(info.oid.len) + 4 + 4);
WRITE32(RPC_AUTH_GSS);
WRITE32(info.oid.len);
WRITEMEM(info.oid.data, info.oid.len);
@@ -3379,35 +3339,43 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
8 /* eir_clientid */ +
4 /* eir_sequenceid */ +
4 /* eir_flags */ +
- 4 /* spr_how */ +
- 8 /* spo_must_enforce, spo_must_allow */ +
- 8 /* so_minor_id */ +
- 4 /* so_major_id.len */ +
- (XDR_QUADLEN(major_id_sz) * 4) +
- 4 /* eir_server_scope.len */ +
- (XDR_QUADLEN(server_scope_sz) * 4) +
- 4 /* eir_server_impl_id.count (0) */);
+ 4 /* spr_how */);
WRITEMEM(&exid->clientid, 8);
WRITE32(exid->seqid);
WRITE32(exid->flags);
WRITE32(exid->spa_how);
+ ADJUST_ARGS();
+
switch (exid->spa_how) {
case SP4_NONE:
break;
case SP4_MACH_CRED:
+ /* spo_must_enforce, spo_must_allow */
+ RESERVE_SPACE(16);
+
/* spo_must_enforce bitmap: */
WRITE32(2);
WRITE32(nfs4_minimal_spo_must_enforce[0]);
WRITE32(nfs4_minimal_spo_must_enforce[1]);
/* empty spo_must_allow bitmap: */
WRITE32(0);
+
+ ADJUST_ARGS();
break;
default:
WARN_ON_ONCE(1);
}
+ RESERVE_SPACE(
+ 8 /* so_minor_id */ +
+ 4 /* so_major_id.len */ +
+ (XDR_QUADLEN(major_id_sz) * 4) +
+ 4 /* eir_server_scope.len */ +
+ (XDR_QUADLEN(server_scope_sz) * 4) +
+ 4 /* eir_server_impl_id.count (0) */);
+
/* The server_owner struct */
WRITE64(minor_id); /* Minor id */
/* major id */
@@ -3474,28 +3442,6 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr,
}
static __be32
-nfsd4_encode_destroy_session(struct nfsd4_compoundres *resp, __be32 nfserr,
- struct nfsd4_destroy_session *destroy_session)
-{
- return nfserr;
-}
-
-static __be32
-nfsd4_encode_free_stateid(struct nfsd4_compoundres *resp, __be32 nfserr,
- struct nfsd4_free_stateid *free_stateid)
-{
- __be32 *p;
-
- if (nfserr)
- return nfserr;
-
- RESERVE_SPACE(4);
- *p++ = nfserr;
- ADJUST_ARGS();
- return nfserr;
-}
-
-static __be32
nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr,
struct nfsd4_sequence *seq)
{
@@ -3593,8 +3539,8 @@ static nfsd4_enc nfsd4_enc_ops[] = {
[OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session,
[OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id,
[OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session,
- [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_destroy_session,
- [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_free_stateid,
+ [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop,
+ [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop,
[OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop,
[OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop,
[OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop,
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index b6af150c96b8..f8f060ffbf4f 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -132,13 +132,6 @@ nfsd_reply_cache_alloc(void)
}
static void
-nfsd_reply_cache_unhash(struct svc_cacherep *rp)
-{
- hlist_del_init(&rp->c_hash);
- list_del_init(&rp->c_lru);
-}
-
-static void
nfsd_reply_cache_free_locked(struct svc_cacherep *rp)
{
if (rp->c_type == RC_REPLBUFF && rp->c_replvec.iov_base) {
@@ -416,22 +409,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
/*
* Since the common case is a cache miss followed by an insert,
- * preallocate an entry. First, try to reuse the first entry on the LRU
- * if it works, then go ahead and prune the LRU list.
+ * preallocate an entry.
*/
- spin_lock(&cache_lock);
- if (!list_empty(&lru_head)) {
- rp = list_first_entry(&lru_head, struct svc_cacherep, c_lru);
- if (nfsd_cache_entry_expired(rp) ||
- num_drc_entries >= max_drc_entries) {
- nfsd_reply_cache_unhash(rp);
- prune_cache_entries();
- goto search_cache;
- }
- }
-
- /* No expired ones available, allocate a new one. */
- spin_unlock(&cache_lock);
rp = nfsd_reply_cache_alloc();
spin_lock(&cache_lock);
if (likely(rp)) {
@@ -439,7 +418,9 @@ nfsd_cache_lookup(struct svc_rqst *rqstp)
drc_mem_usage += sizeof(*rp);
}
-search_cache:
+ /* go ahead and prune the cache */
+ prune_cache_entries();
+
found = nfsd_cache_search(rqstp, csum);
if (found) {
if (likely(rp))
@@ -453,15 +434,6 @@ search_cache:
goto out;
}
- /*
- * We're keeping the one we just allocated. Are we now over the
- * limit? Prune one off the tip of the LRU in trade for the one we
- * just allocated if so.
- */
- if (num_drc_entries >= max_drc_entries)
- nfsd_reply_cache_free_locked(list_first_entry(&lru_head,
- struct svc_cacherep, c_lru));
-
nfsdstats.rcmisses++;
rqstp->rq_cacherep = rp;
rp->c_state = RC_INPROG;
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index 760c85a6f534..9a4a5f9e7468 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -241,6 +241,15 @@ static void nfsd_shutdown_generic(void)
nfsd_racache_shutdown();
}
+static bool nfsd_needs_lockd(void)
+{
+#if defined(CONFIG_NFSD_V3)
+ return (nfsd_versions[2] != NULL) || (nfsd_versions[3] != NULL);
+#else
+ return (nfsd_versions[2] != NULL);
+#endif
+}
+
static int nfsd_startup_net(int nrservs, struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -255,9 +264,14 @@ static int nfsd_startup_net(int nrservs, struct net *net)
ret = nfsd_init_socks(net);
if (ret)
goto out_socks;
- ret = lockd_up(net);
- if (ret)
- goto out_socks;
+
+ if (nfsd_needs_lockd() && !nn->lockd_up) {
+ ret = lockd_up(net);
+ if (ret)
+ goto out_socks;
+ nn->lockd_up = 1;
+ }
+
ret = nfs4_state_start_net(net);
if (ret)
goto out_lockd;
@@ -266,7 +280,10 @@ static int nfsd_startup_net(int nrservs, struct net *net)
return 0;
out_lockd:
- lockd_down(net);
+ if (nn->lockd_up) {
+ lockd_down(net);
+ nn->lockd_up = 0;
+ }
out_socks:
nfsd_shutdown_generic();
return ret;
@@ -277,7 +294,10 @@ static void nfsd_shutdown_net(struct net *net)
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_state_shutdown_net(net);
- lockd_down(net);
+ if (nn->lockd_up) {
+ lockd_down(net);
+ nn->lockd_up = 0;
+ }
nn->nfsd_net_up = false;
nfsd_shutdown_generic();
}
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 9c769a47ac5a..b17d93214d01 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -152,7 +152,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp,
type = (stat->mode & S_IFMT);
*p++ = htonl(nfs_ftypes[type >> 12]);
- *p++ = htonl((u32) stat->mode);
+ *p++ = htonl((u32) (stat->mode & S_IALLUGO));
*p++ = htonl((u32) stat->nlink);
*p++ = htonl((u32) from_kuid(&init_user_ns, stat->uid));
*p++ = htonl((u32) from_kgid(&init_user_ns, stat->gid));
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 1426eb66c8c6..017d3cb5e99b 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -207,7 +207,12 @@ nfsd_lookup_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp,
goto out_nfserr;
}
} else {
- fh_lock(fhp);
+ /*
+ * In the nfsd4_open() case, this may be held across
+ * subsequent open and delegation acquisition which may
+ * need to take the child's i_mutex:
+ */
+ fh_lock_nested(fhp, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dparent, len);
host_err = PTR_ERR(dentry);
if (IS_ERR(dentry))
@@ -273,13 +278,6 @@ out:
return err;
}
-static int nfsd_break_lease(struct inode *inode)
-{
- if (!S_ISREG(inode->i_mode))
- return 0;
- return break_lease(inode, O_WRONLY | O_NONBLOCK);
-}
-
/*
* Commit metadata changes to stable storage.
*/
@@ -348,8 +346,7 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
/* Revoke setuid/setgid on chown */
if (!S_ISDIR(inode->i_mode) &&
- (((iap->ia_valid & ATTR_UID) && !uid_eq(iap->ia_uid, inode->i_uid)) ||
- ((iap->ia_valid & ATTR_GID) && !gid_eq(iap->ia_gid, inode->i_gid)))) {
+ ((iap->ia_valid & ATTR_UID) || (iap->ia_valid & ATTR_GID))) {
iap->ia_valid |= ATTR_KILL_PRIV;
if (iap->ia_valid & ATTR_MODE) {
/* we're setting mode too, just clear the s*id bits */
@@ -449,16 +446,10 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
goto out_put_write_access;
}
- host_err = nfsd_break_lease(inode);
- if (host_err)
- goto out_put_write_access_nfserror;
-
fh_lock(fhp);
host_err = notify_change(dentry, iap, NULL);
fh_unlock(fhp);
-out_put_write_access_nfserror:
- err = nfserrno(host_err);
out_put_write_access:
if (size_change)
put_write_access(inode);
@@ -1609,11 +1600,6 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp,
err = nfserr_noent;
if (!dold->d_inode)
goto out_dput;
- host_err = nfsd_break_lease(dold->d_inode);
- if (host_err) {
- err = nfserrno(host_err);
- goto out_dput;
- }
host_err = vfs_link(dold, dirp, dnew, NULL);
if (!host_err) {
err = nfserrno(commit_metadata(ffhp));
@@ -1707,14 +1693,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry)
goto out_dput_new;
- host_err = nfsd_break_lease(odentry->d_inode);
- if (host_err)
- goto out_dput_new;
- if (ndentry->d_inode) {
- host_err = nfsd_break_lease(ndentry->d_inode);
- if (host_err)
- goto out_dput_new;
- }
host_err = vfs_rename(fdir, odentry, tdir, ndentry, NULL);
if (!host_err) {
host_err = commit_metadata(tfhp);
@@ -1784,16 +1762,12 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
if (!type)
type = rdentry->d_inode->i_mode & S_IFMT;
- host_err = nfsd_break_lease(rdentry->d_inode);
- if (host_err)
- goto out_put;
if (type != S_IFDIR)
host_err = vfs_unlink(dirp, rdentry, NULL);
else
host_err = vfs_rmdir(dirp, rdentry);
if (!host_err)
host_err = commit_metadata(fhp);
-out_put:
dput(rdentry);
out_nfserr:
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 1bc1d440a1a5..fbe90bdb2214 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -86,8 +86,6 @@ __be32 nfsd_link(struct svc_rqst *, struct svc_fh *,
__be32 nfsd_rename(struct svc_rqst *,
struct svc_fh *, char *, int,
struct svc_fh *, char *, int);
-__be32 nfsd_remove(struct svc_rqst *,
- struct svc_fh *, char *, int);
__be32 nfsd_unlink(struct svc_rqst *, struct svc_fh *, int type,
char *name, int len);
__be32 nfsd_readdir(struct svc_rqst *, struct svc_fh *,
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index b6d5542a4ac8..335e04aaf7db 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -174,6 +174,9 @@ struct nfsd3_linkres {
struct nfsd3_readdirres {
__be32 status;
struct svc_fh fh;
+ /* Just to save kmalloc on every readdirplus entry (svc_fh is a
+ * little large for the stack): */
+ struct svc_fh scratch;
int count;
__be32 verf[2];
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index b3ed6446ed8e..d278a0d03496 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -228,7 +228,7 @@ struct nfsd4_open {
u32 op_create; /* request */
u32 op_createmode; /* request */
u32 op_bmval[3]; /* request */
- struct iattr iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+ struct iattr op_iattr; /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
nfs4_verifier op_verf __attribute__((aligned(32)));
/* EXCLUSIVE4 */
clientid_t op_clientid; /* request */
@@ -250,7 +250,6 @@ struct nfsd4_open {
struct nfs4_acl *op_acl;
struct xdr_netobj op_label;
};
-#define op_iattr iattr
struct nfsd4_open_confirm {
stateid_t oc_req_stateid /* request */;
@@ -374,7 +373,6 @@ struct nfsd4_test_stateid {
struct nfsd4_free_stateid {
stateid_t fr_stateid; /* request */
- __be32 fr_status; /* response */
};
/* also used for NVERIFY */
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 2d8be51f90dc..dc3a9efdaab8 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -416,7 +416,8 @@ static struct bio *nilfs_alloc_seg_bio(struct the_nilfs *nilfs, sector_t start,
}
if (likely(bio)) {
bio->bi_bdev = nilfs->ns_bdev;
- bio->bi_sector = start << (nilfs->ns_blocksize_bits - 9);
+ bio->bi_iter.bi_sector =
+ start << (nilfs->ns_blocksize_bits - 9);
}
return bio;
}
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 0b9ff4395e6a..abc8cbcfe90e 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -86,7 +86,7 @@ static int dnotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct dnotify_mark *dn_mark;
struct dnotify_struct *dn;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 58772623f02a..dc638f786d5c 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -16,12 +16,6 @@ static bool should_merge(struct fsnotify_event *old_fsn,
{
struct fanotify_event_info *old, *new;
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
- /* dont merge two permission events */
- if ((old_fsn->mask & FAN_ALL_PERM_EVENTS) &&
- (new_fsn->mask & FAN_ALL_PERM_EVENTS))
- return false;
-#endif
pr_debug("%s: old=%p new=%p\n", __func__, old_fsn, new_fsn);
old = FANOTIFY_E(old_fsn);
new = FANOTIFY_E(new_fsn);
@@ -34,14 +28,23 @@ static bool should_merge(struct fsnotify_event *old_fsn,
}
/* and the list better be locked by something too! */
-static struct fsnotify_event *fanotify_merge(struct list_head *list,
- struct fsnotify_event *event)
+static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
{
struct fsnotify_event *test_event;
bool do_merge = false;
pr_debug("%s: list=%p event=%p\n", __func__, list, event);
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+ /*
+ * Don't merge a permission event with any other event so that we know
+ * the event structure we have created in fanotify_handle_event() is the
+ * one we should check for permission response.
+ */
+ if (event->mask & FAN_ALL_PERM_EVENTS)
+ return 0;
+#endif
+
list_for_each_entry_reverse(test_event, list, list) {
if (should_merge(test_event, event)) {
do_merge = true;
@@ -50,10 +53,10 @@ static struct fsnotify_event *fanotify_merge(struct list_head *list,
}
if (!do_merge)
- return NULL;
+ return 0;
test_event->mask |= event->mask;
- return test_event;
+ return 1;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
@@ -144,12 +147,11 @@ static int fanotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *fanotify_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
int ret = 0;
struct fanotify_event_info *event;
struct fsnotify_event *fsn_event;
- struct fsnotify_event *notify_fsn_event;
BUILD_BUG_ON(FAN_ACCESS != FS_ACCESS);
BUILD_BUG_ON(FAN_MODIFY != FS_MODIFY);
@@ -188,21 +190,21 @@ static int fanotify_handle_event(struct fsnotify_group *group,
event->response = 0;
#endif
- notify_fsn_event = fsnotify_add_notify_event(group, fsn_event,
- fanotify_merge);
- if (notify_fsn_event) {
+ ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
+ if (ret) {
+ /* Permission events shouldn't be merged */
+ BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
- if (IS_ERR(notify_fsn_event))
- return PTR_ERR(notify_fsn_event);
- /* We need to ask about a different events after a merge... */
- event = FANOTIFY_E(notify_fsn_event);
- fsn_event = notify_fsn_event;
+
+ return 0;
}
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
- if (fsn_event->mask & FAN_ALL_PERM_EVENTS)
+ if (mask & FAN_ALL_PERM_EVENTS) {
ret = fanotify_get_response_from_access(group, event);
+ fsnotify_destroy_event(group, fsn_event);
+ }
#endif
return ret;
}
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 0e90174a116a..32a2f034fb94 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -4,6 +4,13 @@
extern struct kmem_cache *fanotify_event_cachep;
+/*
+ * Lifetime of the structure differs for normal and permission events. In both
+ * cases the structure is allocated in fanotify_handle_event(). For normal
+ * events the structure is freed immediately after reporting it to userspace.
+ * For permission events we free it only after we receive response from
+ * userspace.
+ */
struct fanotify_event_info {
struct fsnotify_event fse;
/*
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 1fd66abe5740..287a22c04149 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -319,7 +319,12 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
if (IS_ERR(kevent))
break;
ret = copy_event_to_user(group, kevent, buf);
- fsnotify_destroy_event(group, kevent);
+ /*
+ * Permission events get destroyed after we
+ * receive response
+ */
+ if (!(kevent->mask & FAN_ALL_PERM_EVENTS))
+ fsnotify_destroy_event(group, kevent);
if (ret < 0)
break;
buf += ret;
@@ -693,6 +698,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
struct fsnotify_group *group;
int f_flags, fd;
struct user_struct *user;
+ struct fanotify_event_info *oevent;
pr_debug("%s: flags=%d event_f_flags=%d\n",
__func__, flags, event_f_flags);
@@ -725,8 +731,20 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
group->fanotify_data.user = user;
atomic_inc(&user->fanotify_listeners);
+ oevent = kmem_cache_alloc(fanotify_event_cachep, GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fd = -ENOMEM;
+ goto out_destroy_group;
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->tgid = get_pid(task_tgid(current));
+ oevent->path.mnt = NULL;
+ oevent->path.dentry = NULL;
+
group->fanotify_data.f_flags = event_f_flags;
#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+ oevent->response = 0;
mutex_init(&group->fanotify_data.access_mutex);
init_waitqueue_head(&group->fanotify_data.access_waitq);
INIT_LIST_HEAD(&group->fanotify_data.access_list);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 1d4e1ea2f37c..9d3e9c50066a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -179,7 +179,7 @@ static int send_to_group(struct inode *to_tell,
return group->ops->handle_event(group, to_tell, inode_mark,
vfsmount_mark, mask, data, data_is,
- file_name);
+ file_name, cookie);
}
/*
diff --git a/fs/notify/group.c b/fs/notify/group.c
index ee674fe2cec7..ad1995980456 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -55,6 +55,13 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
/* clear the notification queue of all events */
fsnotify_flush_notify(group);
+ /*
+ * Destroy overflow event (we cannot use fsnotify_destroy_event() as
+ * that deliberately ignores overflow events.
+ */
+ if (group->overflow_event)
+ group->ops->free_event(group->overflow_event);
+
fsnotify_put_group(group);
}
@@ -99,7 +106,6 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
INIT_LIST_HEAD(&group->marks_list);
group->ops = ops;
- fsnotify_init_event(&group->overflow_event, NULL, FS_Q_OVERFLOW);
return group;
}
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index 485eef3f4407..ed855ef6f077 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,6 @@ extern int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name);
+ const unsigned char *file_name, u32 cookie);
extern const struct fsnotify_ops inotify_fsnotify_ops;
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index aad1a35e9af1..43ab1e1a07a2 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -53,15 +53,13 @@ static bool event_compare(struct fsnotify_event *old_fsn,
return false;
}
-static struct fsnotify_event *inotify_merge(struct list_head *list,
- struct fsnotify_event *event)
+static int inotify_merge(struct list_head *list,
+ struct fsnotify_event *event)
{
struct fsnotify_event *last_event;
last_event = list_entry(list->prev, struct fsnotify_event, list);
- if (!event_compare(last_event, event))
- return NULL;
- return last_event;
+ return event_compare(last_event, event);
}
int inotify_handle_event(struct fsnotify_group *group,
@@ -69,13 +67,12 @@ int inotify_handle_event(struct fsnotify_group *group,
struct fsnotify_mark *inode_mark,
struct fsnotify_mark *vfsmount_mark,
u32 mask, void *data, int data_type,
- const unsigned char *file_name)
+ const unsigned char *file_name, u32 cookie)
{
struct inotify_inode_mark *i_mark;
struct inotify_event_info *event;
- struct fsnotify_event *added_event;
struct fsnotify_event *fsn_event;
- int ret = 0;
+ int ret;
int len = 0;
int alloc_len = sizeof(struct inotify_event_info);
@@ -106,22 +103,21 @@ int inotify_handle_event(struct fsnotify_group *group,
fsn_event = &event->fse;
fsnotify_init_event(fsn_event, inode, mask);
event->wd = i_mark->wd;
+ event->sync_cookie = cookie;
event->name_len = len;
if (len)
strcpy(event->name, file_name);
- added_event = fsnotify_add_notify_event(group, fsn_event, inotify_merge);
- if (added_event) {
+ ret = fsnotify_add_notify_event(group, fsn_event, inotify_merge);
+ if (ret) {
/* Our event wasn't used in the end. Free it. */
fsnotify_destroy_event(group, fsn_event);
- if (IS_ERR(added_event))
- ret = PTR_ERR(added_event);
}
if (inode_mark->mask & IN_ONESHOT)
fsnotify_destroy_mark(inode_mark, group);
- return ret;
+ return 0;
}
static void inotify_freeing_mark(struct fsnotify_mark *fsn_mark, struct fsnotify_group *group)
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 497395c8274b..78a2ca3966c3 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -495,7 +495,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
/* Queue ignore event for the watch */
inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
- NULL, FSNOTIFY_EVENT_NONE, NULL);
+ NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
/* remove this mark from the idr */
@@ -633,11 +633,23 @@ static int inotify_update_watch(struct fsnotify_group *group, struct inode *inod
static struct fsnotify_group *inotify_new_group(unsigned int max_events)
{
struct fsnotify_group *group;
+ struct inotify_event_info *oevent;
group = fsnotify_alloc_group(&inotify_fsnotify_ops);
if (IS_ERR(group))
return group;
+ oevent = kmalloc(sizeof(struct inotify_event_info), GFP_KERNEL);
+ if (unlikely(!oevent)) {
+ fsnotify_destroy_group(group);
+ return ERR_PTR(-ENOMEM);
+ }
+ group->overflow_event = &oevent->fse;
+ fsnotify_init_event(group->overflow_event, NULL, FS_Q_OVERFLOW);
+ oevent->wd = -1;
+ oevent->sync_cookie = 0;
+ oevent->name_len = 0;
+
group->max_events = max_events;
spin_lock_init(&group->inotify_data.idr_lock);
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 952237b8e2d2..1e58402171a5 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -79,15 +79,16 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
/*
* Add an event to the group notification queue. The group can later pull this
- * event off the queue to deal with. If the event is successfully added to the
- * group's notification queue, a reference is taken on event.
+ * event off the queue to deal with. The function returns 0 if the event was
+ * added to the queue, 1 if the event was merged with some other queued event,
+ * 2 if the queue of events has overflown.
*/
-struct fsnotify_event *fsnotify_add_notify_event(struct fsnotify_group *group,
- struct fsnotify_event *event,
- struct fsnotify_event *(*merge)(struct list_head *,
- struct fsnotify_event *))
+int fsnotify_add_notify_event(struct fsnotify_group *group,
+ struct fsnotify_event *event,
+ int (*merge)(struct list_head *,
+ struct fsnotify_event *))
{
- struct fsnotify_event *return_event = NULL;
+ int ret = 0;
struct list_head *list = &group->notification_list;
pr_debug("%s: group=%p event=%p\n", __func__, group, event);
@@ -95,27 +96,32 @@ struct fsnotify_event *fsnotify_add_notify_event(struct fsnotify_group *group,
mutex_lock(&group->notification_mutex);
if (group->q_len >= group->max_events) {
+ ret = 2;
/* Queue overflow event only if it isn't already queued */
- if (list_empty(&group->overflow_event.list))
- event = &group->overflow_event;
- return_event = event;
+ if (!list_empty(&group->overflow_event->list)) {
+ mutex_unlock(&group->notification_mutex);
+ return ret;
+ }
+ event = group->overflow_event;
+ goto queue;
}
if (!list_empty(list) && merge) {
- return_event = merge(list, event);
- if (return_event) {
+ ret = merge(list, event);
+ if (ret) {
mutex_unlock(&group->notification_mutex);
- return return_event;
+ return ret;
}
}
+queue:
group->q_len++;
list_add_tail(&event->list, list);
mutex_unlock(&group->notification_mutex);
wake_up(&group->notification_waitq);
kill_fasync(&group->fsn_fa, SIGIO, POLL_IN);
- return return_event;
+ return ret;
}
/*
@@ -132,7 +138,11 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
event = list_first_entry(&group->notification_list,
struct fsnotify_event, list);
- list_del(&event->list);
+ /*
+ * We need to init list head for the case of overflow event so that
+ * check in fsnotify_add_notify_events() works
+ */
+ list_del_init(&event->list);
group->q_len--;
return event;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index ea4ba9daeb47..db9bd8a31725 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -2134,7 +2134,7 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
ret = ntfs_file_aio_write_nolock(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
- int err = generic_write_sync(file, pos, ret);
+ int err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0)
ret = err;
}
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 8750ae1b8636..e2edff38be52 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -4742,6 +4742,7 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
enum ocfs2_alloc_restarted *reason_ret)
{
int status = 0, err = 0;
+ int need_free = 0;
int free_extents;
enum ocfs2_alloc_restarted reason = RESTART_NONE;
u32 bit_off, num_bits;
@@ -4796,7 +4797,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
- goto leave;
+ need_free = 1;
+ goto bail;
}
block = ocfs2_clusters_to_blocks(osb->sb, bit_off);
@@ -4807,7 +4809,8 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
num_bits, flags, meta_ac);
if (status < 0) {
mlog_errno(status);
- goto leave;
+ need_free = 1;
+ goto bail;
}
ocfs2_journal_dirty(handle, et->et_root_bh);
@@ -4821,6 +4824,19 @@ int ocfs2_add_clusters_in_btree(handle_t *handle,
reason = RESTART_TRANS;
}
+bail:
+ if (need_free) {
+ if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+ ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+ bit_off, num_bits);
+ else
+ ocfs2_free_clusters(handle,
+ data_ac->ac_inode,
+ data_ac->ac_bh,
+ ocfs2_clusters_to_blocks(osb->sb, bit_off),
+ num_bits);
+ }
+
leave:
if (reason_ret)
*reason_ret = reason;
@@ -6805,6 +6821,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
struct buffer_head *di_bh)
{
int ret, i, has_data, num_pages = 0;
+ int need_free = 0;
+ u32 bit_off, num;
handle_t *handle;
u64 uninitialized_var(block);
struct ocfs2_inode_info *oi = OCFS2_I(inode);
@@ -6850,7 +6868,6 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
}
if (has_data) {
- u32 bit_off, num;
unsigned int page_end;
u64 phys;
@@ -6886,6 +6903,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
if (ret) {
mlog_errno(ret);
+ need_free = 1;
goto out_commit;
}
@@ -6896,6 +6914,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
if (ret) {
mlog_errno(ret);
+ need_free = 1;
goto out_commit;
}
@@ -6927,6 +6946,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
ret = ocfs2_insert_extent(handle, &et, 0, block, 1, 0, NULL);
if (ret) {
mlog_errno(ret);
+ need_free = 1;
goto out_commit;
}
@@ -6938,6 +6958,18 @@ out_commit:
dquot_free_space_nodirty(inode,
ocfs2_clusters_to_bytes(osb->sb, 1));
+ if (need_free) {
+ if (data_ac->ac_which == OCFS2_AC_USE_LOCAL)
+ ocfs2_free_local_alloc_bits(osb, handle, data_ac,
+ bit_off, num);
+ else
+ ocfs2_free_clusters(handle,
+ data_ac->ac_inode,
+ data_ac->ac_bh,
+ ocfs2_clusters_to_blocks(osb->sb, bit_off),
+ num);
+ }
+
ocfs2_commit_trans(osb, handle);
out_unlock:
@@ -7126,7 +7158,7 @@ int ocfs2_truncate_inline(struct inode *inode, struct buffer_head *di_bh,
if (end > i_size_read(inode))
end = i_size_read(inode);
- BUG_ON(start >= end);
+ BUG_ON(start > end);
if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) ||
!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) ||
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 73920ffda05b..bf482dfed14f 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -413,7 +413,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
}
/* Must put everything in 512 byte sectors for the bio... */
- bio->bi_sector = (reg->hr_start_block + cs) << (bits - 9);
+ bio->bi_iter.bi_sector = (reg->hr_start_block + cs) << (bits - 9);
bio->bi_bdev = reg->hr_bdev;
bio->bi_private = wc;
bio->bi_end_io = o2hb_bio_end_io;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index d77d71ead8d1..8450262bcf2a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -185,6 +185,9 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
file->f_path.dentry->d_name.name,
(unsigned long long)datasync);
+ if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
+ return -EROFS;
+
err = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (err)
return err;
@@ -474,11 +477,6 @@ static int ocfs2_truncate_file(struct inode *inode,
goto bail;
}
- /* lets handle the simple truncate cases before doing any more
- * cluster locking. */
- if (new_i_size == le64_to_cpu(fe->i_size))
- goto bail;
-
down_write(&OCFS2_I(inode)->ip_alloc_sem);
ocfs2_resv_discard(&osb->osb_la_resmap,
@@ -718,7 +716,8 @@ leave:
* While a write will already be ordering the data, a truncate will not.
* Thus, we need to explicitly order the zeroed pages.
*/
-static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
+ struct buffer_head *di_bh)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
@@ -735,7 +734,14 @@ static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
}
ret = ocfs2_jbd2_file_inode(handle, inode);
- if (ret < 0)
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ }
+
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (ret)
mlog_errno(ret);
out:
@@ -751,7 +757,7 @@ out:
* to be too fragile to do exactly what we need without us having to
* worry about recursive locking in ->write_begin() and ->write_end(). */
static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
- u64 abs_to)
+ u64 abs_to, struct buffer_head *di_bh)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
@@ -759,6 +765,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
handle_t *handle = NULL;
int ret = 0;
unsigned zero_from, zero_to, block_start, block_end;
+ struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
BUG_ON(abs_from >= abs_to);
BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
@@ -801,7 +808,8 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
}
if (!handle) {
- handle = ocfs2_zero_start_ordered_transaction(inode);
+ handle = ocfs2_zero_start_ordered_transaction(inode,
+ di_bh);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
@@ -818,8 +826,22 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
ret = 0;
}
- if (handle)
+ if (handle) {
+ /*
+ * fs-writeback will release the dirty pages without page lock
+ * whose offset are over inode size, the release happens at
+ * block_write_full_page_endio().
+ */
+ i_size_write(inode, abs_to);
+ inode->i_blocks = ocfs2_inode_sector_count(inode);
+ di->i_size = cpu_to_le64((u64)i_size_read(inode));
+ inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+ di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
+ di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ di->i_mtime_nsec = di->i_ctime_nsec;
+ ocfs2_journal_dirty(handle, di_bh);
ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+ }
out_unlock:
unlock_page(page);
@@ -915,7 +937,7 @@ out:
* has made sure that the entire range needs zeroing.
*/
static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
- u64 range_end)
+ u64 range_end, struct buffer_head *di_bh)
{
int rc = 0;
u64 next_pos;
@@ -931,7 +953,7 @@ static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
if (next_pos > range_end)
next_pos = range_end;
- rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+ rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
if (rc < 0) {
mlog_errno(rc);
break;
@@ -977,7 +999,7 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
range_end = zero_to_size;
ret = ocfs2_zero_extend_range(inode, range_start,
- range_end);
+ range_end, di_bh);
if (ret) {
mlog_errno(ret);
break;
@@ -1145,14 +1167,14 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
goto bail_unlock_rw;
}
- if (size_change && attr->ia_size != i_size_read(inode)) {
+ if (size_change) {
status = inode_newsize_ok(inode, attr->ia_size);
if (status)
goto bail_unlock;
inode_dio_wait(inode);
- if (i_size_read(inode) > attr->ia_size) {
+ if (i_size_read(inode) >= attr->ia_size) {
if (ocfs2_should_order_data(inode)) {
status = ocfs2_begin_ordered_truncate(inode,
attr->ia_size);
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index cd5496b7a0a3..044013455621 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -781,6 +781,48 @@ bail:
return status;
}
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+ handle_t *handle,
+ struct ocfs2_alloc_context *ac,
+ u32 bit_off,
+ u32 num_bits)
+{
+ int status, start;
+ u32 clear_bits;
+ struct inode *local_alloc_inode;
+ void *bitmap;
+ struct ocfs2_dinode *alloc;
+ struct ocfs2_local_alloc *la;
+
+ BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL);
+
+ local_alloc_inode = ac->ac_inode;
+ alloc = (struct ocfs2_dinode *) osb->local_alloc_bh->b_data;
+ la = OCFS2_LOCAL_ALLOC(alloc);
+
+ bitmap = la->la_bitmap;
+ start = bit_off - le32_to_cpu(la->la_bm_off);
+ clear_bits = num_bits;
+
+ status = ocfs2_journal_access_di(handle,
+ INODE_CACHE(local_alloc_inode),
+ osb->local_alloc_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
+ if (status < 0) {
+ mlog_errno(status);
+ goto bail;
+ }
+
+ while (clear_bits--)
+ ocfs2_clear_bit(start++, bitmap);
+
+ le32_add_cpu(&alloc->id1.bitmap1.i_used, -num_bits);
+ ocfs2_journal_dirty(handle, osb->local_alloc_bh);
+
+bail:
+ return status;
+}
+
static u32 ocfs2_local_alloc_count_bits(struct ocfs2_dinode *alloc)
{
u32 count;
diff --git a/fs/ocfs2/localalloc.h b/fs/ocfs2/localalloc.h
index 1be9b5864460..44a7d1fb2dec 100644
--- a/fs/ocfs2/localalloc.h
+++ b/fs/ocfs2/localalloc.h
@@ -55,6 +55,12 @@ int ocfs2_claim_local_alloc_bits(struct ocfs2_super *osb,
u32 *bit_off,
u32 *num_bits);
+int ocfs2_free_local_alloc_bits(struct ocfs2_super *osb,
+ handle_t *handle,
+ struct ocfs2_alloc_context *ac,
+ u32 bit_off,
+ u32 num_bits);
+
void ocfs2_local_alloc_seen_free_bits(struct ocfs2_super *osb,
unsigned int num_clusters);
void ocfs2_la_enable_worker(struct work_struct *work);
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index f4d609be9400..3683643f3f0e 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -664,6 +664,7 @@ static int ocfs2_link(struct dentry *old_dentry,
struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
struct ocfs2_dir_lookup_result lookup = { NULL, };
sigset_t oldset;
+ u64 old_de_ino;
trace_ocfs2_link((unsigned long long)OCFS2_I(inode)->ip_blkno,
old_dentry->d_name.len, old_dentry->d_name.name,
@@ -686,6 +687,22 @@ static int ocfs2_link(struct dentry *old_dentry,
goto out;
}
+ err = ocfs2_lookup_ino_from_name(dir, old_dentry->d_name.name,
+ old_dentry->d_name.len, &old_de_ino);
+ if (err) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ /*
+ * Check whether another node removed the source inode while we
+ * were in the vfs.
+ */
+ if (old_de_ino != OCFS2_I(inode)->ip_blkno) {
+ err = -ENOENT;
+ goto out;
+ }
+
err = ocfs2_check_dir_for_entry(dir, dentry->d_name.name,
dentry->d_name.len);
if (err)
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index aaa50611ec66..d7b5108789e2 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -717,6 +717,12 @@ static int ocfs2_release_dquot(struct dquot *dquot)
*/
if (status < 0)
mlog_errno(status);
+ /*
+ * Clear dq_off so that we search for the structure in quota file next
+ * time we acquire it. The structure might be deleted and reallocated
+ * elsewhere by another node while our dquot structure is on freelist.
+ */
+ dquot->dq_off = 0;
clear_bit(DQ_ACTIVE_B, &dquot->dq_flags);
out_trans:
ocfs2_commit_trans(osb, handle);
@@ -756,16 +762,17 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
status = ocfs2_lock_global_qf(info, 1);
if (status < 0)
goto out;
- if (!test_bit(DQ_READ_B, &dquot->dq_flags)) {
- status = ocfs2_qinfo_lock(info, 0);
- if (status < 0)
- goto out_dq;
- status = qtree_read_dquot(&info->dqi_gi, dquot);
- ocfs2_qinfo_unlock(info, 0);
- if (status < 0)
- goto out_dq;
- }
- set_bit(DQ_READ_B, &dquot->dq_flags);
+ status = ocfs2_qinfo_lock(info, 0);
+ if (status < 0)
+ goto out_dq;
+ /*
+ * We always want to read dquot structure from disk because we don't
+ * know what happened with it while it was on freelist.
+ */
+ status = qtree_read_dquot(&info->dqi_gi, dquot);
+ ocfs2_qinfo_unlock(info, 0);
+ if (status < 0)
+ goto out_dq;
OCFS2_DQUOT(dquot)->dq_use_count++;
OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 2e4344be3b96..2001862bf2b1 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -1303,10 +1303,6 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
out:
- /* Clear the read bit so that next time someone uses this
- * dquot he reads fresh info from disk and allocates local
- * dquot structure */
- clear_bit(DQ_READ_B, &dquot->dq_flags);
return status;
}
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 38bae5a0ea25..11c54fd51e16 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -521,8 +521,11 @@ posix_acl_chmod(struct inode *inode, umode_t mode)
return -EOPNOTSUPP;
acl = get_acl(inode, ACL_TYPE_ACCESS);
- if (IS_ERR_OR_NULL(acl))
+ if (IS_ERR_OR_NULL(acl)) {
+ if (acl == ERR_PTR(-EOPNOTSUPP))
+ return 0;
return PTR_ERR(acl);
+ }
ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
if (ret)
@@ -544,14 +547,15 @@ posix_acl_create(struct inode *dir, umode_t *mode,
goto no_acl;
p = get_acl(dir, ACL_TYPE_DEFAULT);
- if (IS_ERR(p))
+ if (IS_ERR(p)) {
+ if (p == ERR_PTR(-EOPNOTSUPP))
+ goto apply_umask;
return PTR_ERR(p);
-
- if (!p) {
- *mode &= ~current_umask();
- goto no_acl;
}
+ if (!p)
+ goto apply_umask;
+
*acl = posix_acl_clone(p, GFP_NOFS);
if (!*acl)
return -ENOMEM;
@@ -575,6 +579,8 @@ posix_acl_create(struct inode *dir, umode_t *mode,
}
return 0;
+apply_umask:
+ *mode &= ~current_umask();
no_acl:
*default_acl = NULL;
*acl = NULL;
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 02174a610315..e647c55275d9 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -121,9 +121,8 @@ u64 stable_page_flags(struct page *page)
* just checks PG_head/PG_tail, so we need to check PageLRU/PageAnon
* to make sure a given page is a thp, not a non-huge compound page.
*/
- else if (PageTransCompound(page) &&
- (PageLRU(compound_trans_head(page)) ||
- PageAnon(compound_trans_head(page))))
+ else if (PageTransCompound(page) && (PageLRU(compound_head(page)) ||
+ PageAnon(compound_head(page))))
u |= 1 << KPF_THP;
/*
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2ca7ba047f04..88d4585b30f1 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -468,17 +468,24 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
return rc;
}
nhdr_ptr = notes_section;
- while (real_sz < max_sz) {
- if (nhdr_ptr->n_namesz == 0)
- break;
+ while (nhdr_ptr->n_namesz != 0) {
sz = sizeof(Elf64_Nhdr) +
((nhdr_ptr->n_namesz + 3) & ~3) +
((nhdr_ptr->n_descsz + 3) & ~3);
+ if ((real_sz + sz) > max_sz) {
+ pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+ nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+ break;
+ }
real_sz += sz;
nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
}
kfree(notes_section);
phdr_ptr->p_memsz = real_sz;
+ if (real_sz == 0) {
+ pr_warn("Warning: Zero PT_NOTE entries found\n");
+ return -EINVAL;
+ }
}
return 0;
@@ -648,17 +655,24 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
return rc;
}
nhdr_ptr = notes_section;
- while (real_sz < max_sz) {
- if (nhdr_ptr->n_namesz == 0)
- break;
+ while (nhdr_ptr->n_namesz != 0) {
sz = sizeof(Elf32_Nhdr) +
((nhdr_ptr->n_namesz + 3) & ~3) +
((nhdr_ptr->n_descsz + 3) & ~3);
+ if ((real_sz + sz) > max_sz) {
+ pr_warn("Warning: Exceeded p_memsz, dropping PT_NOTE entry n_namesz=0x%x, n_descsz=0x%x\n",
+ nhdr_ptr->n_namesz, nhdr_ptr->n_descsz);
+ break;
+ }
real_sz += sz;
nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
}
kfree(notes_section);
phdr_ptr->p_memsz = real_sz;
+ if (real_sz == 0) {
+ pr_warn("Warning: Zero PT_NOTE entries found\n");
+ return -EINVAL;
+ }
}
return 0;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 831d49a4111f..cfc8dcc16043 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -581,9 +581,17 @@ int dquot_scan_active(struct super_block *sb,
dqstats_inc(DQST_LOOKUPS);
dqput(old_dquot);
old_dquot = dquot;
- ret = fn(dquot, priv);
- if (ret < 0)
- goto out;
+ /*
+ * ->release_dquot() can be racing with us. Our reference
+ * protects us from new calls to it so just wait for any
+ * outstanding call and recheck the DQ_ACTIVE_B after that.
+ */
+ wait_on_dquot(dquot);
+ if (test_bit(DQ_ACTIVE_B, &dquot->dq_flags)) {
+ ret = fn(dquot, priv);
+ if (ret < 0)
+ goto out;
+ }
spin_lock(&dq_list_lock);
/* We are safe to continue now because our dquot could not
* be moved out of the inuse list while we hold the reference */
diff --git a/fs/read_write.c b/fs/read_write.c
index 1193ffd03565..edc5746a902a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -964,9 +964,9 @@ out:
return ret;
}
-COMPAT_SYSCALL_DEFINE3(readv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen)
+ compat_ulong_t, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
@@ -1001,9 +1001,9 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd,
return ret;
}
-COMPAT_SYSCALL_DEFINE5(preadv, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen, u32, pos_low, u32, pos_high)
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return compat_sys_preadv64(fd, vec, vlen, pos);
@@ -1031,9 +1031,9 @@ out:
return ret;
}
-COMPAT_SYSCALL_DEFINE3(writev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd,
const struct compat_iovec __user *, vec,
- unsigned long, vlen)
+ compat_ulong_t, vlen)
{
struct fd f = fdget(fd);
ssize_t ret;
@@ -1068,9 +1068,9 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd,
return ret;
}
-COMPAT_SYSCALL_DEFINE5(pwritev, unsigned long, fd,
+COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd,
const struct compat_iovec __user *,vec,
- unsigned long, vlen, u32, pos_low, u32, pos_high)
+ compat_ulong_t, vlen, u32, pos_low, u32, pos_high)
{
loff_t pos = ((loff_t)pos_high << 32) | pos_low;
return compat_sys_pwritev64(fd, vec, vlen, pos);
diff --git a/fs/reiserfs/do_balan.c b/fs/reiserfs/do_balan.c
index 2b7882b508db..9a3c68cf6026 100644
--- a/fs/reiserfs/do_balan.c
+++ b/fs/reiserfs/do_balan.c
@@ -324,23 +324,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
switch (flag) {
case M_INSERT: /* insert item into L[0] */
- if (item_pos == tb->lnum[0] - 1
- && tb->lbytes != -1) {
+ if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
/* part of new item falls into L[0] */
int new_item_len;
int version;
- ret_val =
- leaf_shift_left(tb, tb->lnum[0] - 1,
- -1);
+ ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, -1);
/* Calculate item length to insert to S[0] */
- new_item_len =
- ih_item_len(ih) - tb->lbytes;
+ new_item_len = ih_item_len(ih) - tb->lbytes;
/* Calculate and check item length to insert to L[0] */
- put_ih_item_len(ih,
- ih_item_len(ih) -
- new_item_len);
+ put_ih_item_len(ih, ih_item_len(ih) - new_item_len);
RFALSE(ih_item_len(ih) <= 0,
"PAP-12080: there is nothing to insert into L[0]: ih_item_len=%d",
@@ -349,30 +343,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
/* Insert new item into L[0] */
buffer_info_init_left(tb, &bi);
leaf_insert_into_buf(&bi,
- n + item_pos -
- ret_val, ih, body,
- zeros_num >
- ih_item_len(ih) ?
- ih_item_len(ih) :
- zeros_num);
+ n + item_pos - ret_val, ih, body,
+ zeros_num > ih_item_len(ih) ? ih_item_len(ih) : zeros_num);
version = ih_version(ih);
/* Calculate key component, item length and body to insert into S[0] */
- set_le_ih_k_offset(ih,
- le_ih_k_offset(ih) +
- (tb->
- lbytes <<
- (is_indirect_le_ih
- (ih) ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT :
- 0)));
+ set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+ (tb-> lbytes << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
put_ih_item_len(ih, new_item_len);
if (tb->lbytes > zeros_num) {
- body +=
- (tb->lbytes - zeros_num);
+ body += (tb->lbytes - zeros_num);
zeros_num = 0;
} else
zeros_num -= tb->lbytes;
@@ -383,15 +365,10 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
} else {
/* new item in whole falls into L[0] */
/* Shift lnum[0]-1 items to L[0] */
- ret_val =
- leaf_shift_left(tb, tb->lnum[0] - 1,
- tb->lbytes);
+ ret_val = leaf_shift_left(tb, tb->lnum[0] - 1, tb->lbytes);
/* Insert new item into L[0] */
buffer_info_init_left(tb, &bi);
- leaf_insert_into_buf(&bi,
- n + item_pos -
- ret_val, ih, body,
- zeros_num);
+ leaf_insert_into_buf(&bi, n + item_pos - ret_val, ih, body, zeros_num);
tb->insert_size[0] = 0;
zeros_num = 0;
}
@@ -399,264 +376,117 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
case M_PASTE: /* append item in L[0] */
- if (item_pos == tb->lnum[0] - 1
- && tb->lbytes != -1) {
+ if (item_pos == tb->lnum[0] - 1 && tb->lbytes != -1) {
/* we must shift the part of the appended item */
- if (is_direntry_le_ih
- (B_N_PITEM_HEAD(tbS0, item_pos))) {
+ if (is_direntry_le_ih(B_N_PITEM_HEAD(tbS0, item_pos))) {
RFALSE(zeros_num,
"PAP-12090: invalid parameter in case of a directory");
/* directory item */
if (tb->lbytes > pos_in_item) {
/* new directory entry falls into L[0] */
- struct item_head
- *pasted;
- int l_pos_in_item =
- pos_in_item;
+ struct item_head *pasted;
+ int l_pos_in_item = pos_in_item;
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 entries from given directory item */
- ret_val =
- leaf_shift_left(tb,
- tb->
- lnum
- [0],
- tb->
- lbytes
- -
- 1);
- if (ret_val
- && !item_pos) {
- pasted =
- B_N_PITEM_HEAD
- (tb->L[0],
- B_NR_ITEMS
- (tb->
- L[0]) -
- 1);
- l_pos_in_item +=
- I_ENTRY_COUNT
- (pasted) -
- (tb->
- lbytes -
- 1);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes-1);
+ if (ret_val && !item_pos) {
+ pasted = B_N_PITEM_HEAD(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1);
+ l_pos_in_item += I_ENTRY_COUNT(pasted) - (tb->lbytes -1);
}
/* Append given directory entry to directory item */
buffer_info_init_left(tb, &bi);
- leaf_paste_in_buffer
- (&bi,
- n + item_pos -
- ret_val,
- l_pos_in_item,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, n + item_pos - ret_val, l_pos_in_item, tb->insert_size[0], body, zeros_num);
/* previous string prepared space for pasting new entry, following string pastes this entry */
/* when we have merge directory item, pos_in_item has been changed too */
/* paste new directory entry. 1 is entry number */
- leaf_paste_entries(&bi,
- n +
- item_pos
- -
- ret_val,
- l_pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, n + item_pos - ret_val, l_pos_in_item,
+ 1, (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
tb->insert_size[0] = 0;
} else {
/* new directory item doesn't fall into L[0] */
/* Shift lnum[0]-1 items in whole. Shift lbytes directory entries from directory item number lnum[0] */
- leaf_shift_left(tb,
- tb->
- lnum[0],
- tb->
- lbytes);
+ leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
}
/* Calculate new position to append in item body */
pos_in_item -= tb->lbytes;
} else {
/* regular object */
- RFALSE(tb->lbytes <= 0,
- "PAP-12095: there is nothing to shift to L[0]. lbytes=%d",
- tb->lbytes);
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
+ RFALSE(tb->lbytes <= 0, "PAP-12095: there is nothing to shift to L[0]. lbytes=%d", tb->lbytes);
+ RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),
"PAP-12100: incorrect position to paste: item_len=%d, pos_in_item=%d",
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
- pos_in_item);
+ ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)),pos_in_item);
if (tb->lbytes >= pos_in_item) {
/* appended item will be in L[0] in whole */
int l_n;
/* this bytes number must be appended to the last item of L[h] */
- l_n =
- tb->lbytes -
- pos_in_item;
+ l_n = tb->lbytes - pos_in_item;
/* Calculate new insert_size[0] */
- tb->insert_size[0] -=
- l_n;
+ tb->insert_size[0] -= l_n;
- RFALSE(tb->
- insert_size[0] <=
- 0,
+ RFALSE(tb->insert_size[0] <= 0,
"PAP-12105: there is nothing to paste into L[0]. insert_size=%d",
- tb->
- insert_size[0]);
- ret_val =
- leaf_shift_left(tb,
- tb->
- lnum
- [0],
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0,
- item_pos)));
+ tb->insert_size[0]);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)));
/* Append to body of item in L[0] */
buffer_info_init_left(tb, &bi);
leaf_paste_in_buffer
- (&bi,
- n + item_pos -
- ret_val,
- ih_item_len
- (B_N_PITEM_HEAD
- (tb->L[0],
- n + item_pos -
- ret_val)), l_n,
- body,
- zeros_num >
- l_n ? l_n :
- zeros_num);
+ (&bi, n + item_pos - ret_val, ih_item_len
+ (B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val)),
+ l_n, body,
+ zeros_num > l_n ? l_n : zeros_num);
/* 0-th item in S0 can be only of DIRECT type when l_n != 0 */
{
int version;
- int temp_l =
- l_n;
-
- RFALSE
- (ih_item_len
- (B_N_PITEM_HEAD
- (tbS0,
- 0)),
+ int temp_l = l_n;
+
+ RFALSE(ih_item_len(B_N_PITEM_HEAD(tbS0, 0)),
"PAP-12106: item length must be 0");
- RFALSE
- (comp_short_le_keys
- (B_N_PKEY
- (tbS0, 0),
- B_N_PKEY
- (tb->L[0],
- n +
- item_pos
- -
- ret_val)),
+ RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY
+ (tb->L[0], n + item_pos - ret_val)),
"PAP-12107: items must be of the same file");
if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val))) {
- temp_l =
- l_n
- <<
- (tb->
- tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT);
+ temp_l = l_n << (tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT);
}
/* update key of first item in S0 */
- version =
- ih_version
- (B_N_PITEM_HEAD
- (tbS0, 0));
- set_le_key_k_offset
- (version,
- B_N_PKEY
- (tbS0, 0),
- le_key_k_offset
- (version,
- B_N_PKEY
- (tbS0,
- 0)) +
- temp_l);
+ version = ih_version(B_N_PITEM_HEAD(tbS0, 0));
+ set_le_key_k_offset(version, B_N_PKEY(tbS0, 0),
+ le_key_k_offset(version,B_N_PKEY(tbS0, 0)) + temp_l);
/* update left delimiting key */
- set_le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->
- CFL[0],
- tb->
- lkey[0]),
- le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->
- CFL[0],
- tb->
- lkey[0]))
- + temp_l);
+ set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]),
+ le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0])) + temp_l);
}
/* Calculate new body, position in item and insert_size[0] */
if (l_n > zeros_num) {
- body +=
- (l_n -
- zeros_num);
+ body += (l_n - zeros_num);
zeros_num = 0;
} else
- zeros_num -=
- l_n;
+ zeros_num -= l_n;
pos_in_item = 0;
- RFALSE
- (comp_short_le_keys
- (B_N_PKEY(tbS0, 0),
- B_N_PKEY(tb->L[0],
- B_NR_ITEMS
- (tb->
- L[0]) -
- 1))
- ||
- !op_is_left_mergeable
- (B_N_PKEY(tbS0, 0),
- tbS0->b_size)
- ||
- !op_is_left_mergeable
- (B_N_PDELIM_KEY
- (tb->CFL[0],
- tb->lkey[0]),
- tbS0->b_size),
+ RFALSE(comp_short_le_keys(B_N_PKEY(tbS0, 0), B_N_PKEY(tb->L[0], B_NR_ITEMS(tb->L[0]) - 1))
+ || !op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)
+ || !op_is_left_mergeable(B_N_PDELIM_KEY(tb->CFL[0], tb->lkey[0]), tbS0->b_size),
"PAP-12120: item must be merge-able with left neighboring item");
} else { /* only part of the appended item will be in L[0] */
/* Calculate position in item for append in S[0] */
- pos_in_item -=
- tb->lbytes;
+ pos_in_item -= tb->lbytes;
- RFALSE(pos_in_item <= 0,
- "PAP-12125: no place for paste. pos_in_item=%d",
- pos_in_item);
+ RFALSE(pos_in_item <= 0, "PAP-12125: no place for paste. pos_in_item=%d", pos_in_item);
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
- leaf_shift_left(tb,
- tb->
- lnum[0],
- tb->
- lbytes);
+ leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
}
}
} else { /* appended item will be in L[0] in whole */
@@ -665,52 +495,30 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
if (!item_pos && op_is_left_mergeable(B_N_PKEY(tbS0, 0), tbS0->b_size)) { /* if we paste into first item of S[0] and it is left mergable */
/* then increment pos_in_item by the size of the last item in L[0] */
- pasted =
- B_N_PITEM_HEAD(tb->L[0],
- n - 1);
+ pasted = B_N_PITEM_HEAD(tb->L[0], n - 1);
if (is_direntry_le_ih(pasted))
- pos_in_item +=
- ih_entry_count
- (pasted);
+ pos_in_item += ih_entry_count(pasted);
else
- pos_in_item +=
- ih_item_len(pasted);
+ pos_in_item += ih_item_len(pasted);
}
/* Shift lnum[0] - 1 items in whole. Shift lbytes - 1 byte from item number lnum[0] */
- ret_val =
- leaf_shift_left(tb, tb->lnum[0],
- tb->lbytes);
+ ret_val = leaf_shift_left(tb, tb->lnum[0], tb->lbytes);
/* Append to body of item in L[0] */
buffer_info_init_left(tb, &bi);
- leaf_paste_in_buffer(&bi,
- n + item_pos -
- ret_val,
+ leaf_paste_in_buffer(&bi, n + item_pos - ret_val,
pos_in_item,
tb->insert_size[0],
body, zeros_num);
/* if appended item is directory, paste entry */
- pasted =
- B_N_PITEM_HEAD(tb->L[0],
- n + item_pos -
- ret_val);
+ pasted = B_N_PITEM_HEAD(tb->L[0], n + item_pos - ret_val);
if (is_direntry_le_ih(pasted))
- leaf_paste_entries(&bi,
- n +
- item_pos -
- ret_val,
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, n + item_pos - ret_val,
+ pos_in_item, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE,
+ tb->insert_size[0]);
/* if appended item is indirect item, put unformatted node into un list */
if (is_indirect_le_ih(pasted))
set_ih_free_space(pasted, 0);
@@ -722,13 +530,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
reiserfs_panic(tb->tb_sb, "PAP-12130",
"lnum > 0: unexpected mode: "
" %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT)
- ? "CUT"
- :
- "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
} else {
/* new item doesn't fall into L[0] */
@@ -748,14 +550,12 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
case M_INSERT: /* insert item */
if (n - tb->rnum[0] < item_pos) { /* new item or its part falls to R[0] */
if (item_pos == n - tb->rnum[0] + 1 && tb->rbytes != -1) { /* part of new item falls into R[0] */
- loff_t old_key_comp, old_len,
- r_zeros_number;
+ loff_t old_key_comp, old_len, r_zeros_number;
const char *r_body;
int version;
loff_t offset;
- leaf_shift_right(tb, tb->rnum[0] - 1,
- -1);
+ leaf_shift_right(tb, tb->rnum[0] - 1, -1);
version = ih_version(ih);
/* Remember key component and item length */
@@ -763,29 +563,17 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
old_len = ih_item_len(ih);
/* Calculate key component and item length to insert into R[0] */
- offset =
- le_ih_k_offset(ih) +
- ((old_len -
- tb->
- rbytes) << (is_indirect_le_ih(ih)
- ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT : 0));
+ offset = le_ih_k_offset(ih) + ((old_len - tb->rbytes) << (is_indirect_le_ih(ih) ? tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT : 0));
set_le_ih_k_offset(ih, offset);
put_ih_item_len(ih, tb->rbytes);
/* Insert part of the item into R[0] */
buffer_info_init_right(tb, &bi);
if ((old_len - tb->rbytes) > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + (old_len -
- tb->rbytes) -
- zeros_num;
+ r_body = body + (old_len - tb->rbytes) - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - (old_len -
- tb->rbytes);
+ r_zeros_number = zeros_num - (old_len - tb->rbytes);
zeros_num -= r_zeros_number;
}
@@ -798,25 +586,18 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
/* Calculate key component and item length to insert into S[0] */
set_le_ih_k_offset(ih, old_key_comp);
- put_ih_item_len(ih,
- old_len - tb->rbytes);
+ put_ih_item_len(ih, old_len - tb->rbytes);
tb->insert_size[0] -= tb->rbytes;
} else { /* whole new item falls into R[0] */
/* Shift rnum[0]-1 items to R[0] */
- ret_val =
- leaf_shift_right(tb,
- tb->rnum[0] - 1,
- tb->rbytes);
+ ret_val = leaf_shift_right(tb, tb->rnum[0] - 1, tb->rbytes);
/* Insert new item into R[0] */
buffer_info_init_right(tb, &bi);
- leaf_insert_into_buf(&bi,
- item_pos - n +
- tb->rnum[0] - 1,
- ih, body,
- zeros_num);
+ leaf_insert_into_buf(&bi, item_pos - n + tb->rnum[0] - 1,
+ ih, body, zeros_num);
if (item_pos - n + tb->rnum[0] - 1 == 0) {
replace_key(tb, tb->CFR[0],
@@ -841,200 +622,97 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
RFALSE(zeros_num,
"PAP-12145: invalid parameter in case of a directory");
- entry_count =
- I_ENTRY_COUNT(B_N_PITEM_HEAD
- (tbS0,
- item_pos));
+ entry_count = I_ENTRY_COUNT(B_N_PITEM_HEAD
+ (tbS0, item_pos));
if (entry_count - tb->rbytes <
pos_in_item)
/* new directory entry falls into R[0] */
{
int paste_entry_position;
- RFALSE(tb->rbytes - 1 >=
- entry_count
- || !tb->
- insert_size[0],
+ RFALSE(tb->rbytes - 1 >= entry_count || !tb-> insert_size[0],
"PAP-12150: no enough of entries to shift to R[0]: rbytes=%d, entry_count=%d",
- tb->rbytes,
- entry_count);
+ tb->rbytes, entry_count);
/* Shift rnum[0]-1 items in whole. Shift rbytes-1 directory entries from directory item number rnum[0] */
- leaf_shift_right(tb,
- tb->
- rnum
- [0],
- tb->
- rbytes
- - 1);
+ leaf_shift_right(tb, tb->rnum[0], tb->rbytes - 1);
/* Paste given directory entry to directory item */
- paste_entry_position =
- pos_in_item -
- entry_count +
- tb->rbytes - 1;
+ paste_entry_position = pos_in_item - entry_count + tb->rbytes - 1;
buffer_info_init_right(tb, &bi);
- leaf_paste_in_buffer
- (&bi, 0,
- paste_entry_position,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, 0, paste_entry_position, tb->insert_size[0], body, zeros_num);
/* paste entry */
- leaf_paste_entries(&bi,
- 0,
- paste_entry_position,
- 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
-
- if (paste_entry_position
- == 0) {
+ leaf_paste_entries(&bi, 0, paste_entry_position, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
+
+ if (paste_entry_position == 0) {
/* change delimiting keys */
- replace_key(tb,
- tb->
- CFR
- [0],
- tb->
- rkey
- [0],
- tb->
- R
- [0],
- 0);
+ replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0],0);
}
tb->insert_size[0] = 0;
pos_in_item++;
} else { /* new directory entry doesn't fall into R[0] */
- leaf_shift_right(tb,
- tb->
- rnum
- [0],
- tb->
- rbytes);
+ leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
}
} else { /* regular object */
- int n_shift, n_rem,
- r_zeros_number;
+ int n_shift, n_rem, r_zeros_number;
const char *r_body;
/* Calculate number of bytes which must be shifted from appended item */
- if ((n_shift =
- tb->rbytes -
- tb->insert_size[0]) < 0)
+ if ((n_shift = tb->rbytes - tb->insert_size[0]) < 0)
n_shift = 0;
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)),
+ RFALSE(pos_in_item != ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)),
"PAP-12155: invalid position to paste. ih_item_len=%d, pos_in_item=%d",
- pos_in_item,
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos)));
-
- leaf_shift_right(tb,
- tb->rnum[0],
- n_shift);
+ pos_in_item, ih_item_len
+ (B_N_PITEM_HEAD(tbS0, item_pos)));
+
+ leaf_shift_right(tb, tb->rnum[0], n_shift);
/* Calculate number of bytes which must remain in body after appending to R[0] */
- if ((n_rem =
- tb->insert_size[0] -
- tb->rbytes) < 0)
+ if ((n_rem = tb->insert_size[0] - tb->rbytes) < 0)
n_rem = 0;
{
int version;
- unsigned long temp_rem =
- n_rem;
-
- version =
- ih_version
- (B_N_PITEM_HEAD
- (tb->R[0], 0));
- if (is_indirect_le_key
- (version,
- B_N_PKEY(tb->R[0],
- 0))) {
- temp_rem =
- n_rem <<
- (tb->tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT);
+ unsigned long temp_rem = n_rem;
+
+ version = ih_version(B_N_PITEM_HEAD(tb->R[0], 0));
+ if (is_indirect_le_key(version, B_N_PKEY(tb->R[0], 0))) {
+ temp_rem = n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT);
}
- set_le_key_k_offset
- (version,
- B_N_PKEY(tb->R[0],
- 0),
- le_key_k_offset
- (version,
- B_N_PKEY(tb->R[0],
- 0)) +
- temp_rem);
- set_le_key_k_offset
- (version,
- B_N_PDELIM_KEY(tb->
- CFR
- [0],
- tb->
- rkey
- [0]),
- le_key_k_offset
- (version,
- B_N_PDELIM_KEY
- (tb->CFR[0],
- tb->rkey[0])) +
- temp_rem);
+ set_le_key_k_offset(version, B_N_PKEY(tb->R[0], 0),
+ le_key_k_offset(version, B_N_PKEY(tb->R[0], 0)) + temp_rem);
+ set_le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0]),
+ le_key_k_offset(version, B_N_PDELIM_KEY(tb->CFR[0], tb->rkey[0])) + temp_rem);
}
/* k_offset (B_N_PKEY(tb->R[0],0)) += n_rem;
k_offset (B_N_PDELIM_KEY(tb->CFR[0],tb->rkey[0])) += n_rem;*/
- do_balance_mark_internal_dirty
- (tb, tb->CFR[0], 0);
+ do_balance_mark_internal_dirty(tb, tb->CFR[0], 0);
/* Append part of body into R[0] */
buffer_info_init_right(tb, &bi);
if (n_rem > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + n_rem -
- zeros_num;
+ r_body = body + n_rem - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - n_rem;
- zeros_num -=
- r_zeros_number;
+ r_zeros_number = zeros_num - n_rem;
+ zeros_num -= r_zeros_number;
}
- leaf_paste_in_buffer(&bi, 0,
- n_shift,
- tb->
- insert_size
- [0] -
- n_rem,
- r_body,
- r_zeros_number);
-
- if (is_indirect_le_ih
- (B_N_PITEM_HEAD
- (tb->R[0], 0))) {
+ leaf_paste_in_buffer(&bi, 0, n_shift,
+ tb->insert_size[0] - n_rem,
+ r_body, r_zeros_number);
+
+ if (is_indirect_le_ih(B_N_PITEM_HEAD(tb->R[0], 0))) {
#if 0
RFALSE(n_rem,
"PAP-12160: paste more than one unformatted node pointer");
#endif
- set_ih_free_space
- (B_N_PITEM_HEAD
- (tb->R[0], 0), 0);
+ set_ih_free_space(B_N_PITEM_HEAD(tb->R[0], 0), 0);
}
tb->insert_size[0] = n_rem;
if (!n_rem)
@@ -1044,58 +722,28 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
struct item_head *pasted;
- ret_val =
- leaf_shift_right(tb, tb->rnum[0],
- tb->rbytes);
+ ret_val = leaf_shift_right(tb, tb->rnum[0], tb->rbytes);
/* append item in R[0] */
if (pos_in_item >= 0) {
buffer_info_init_right(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos -
- n +
- tb->
- rnum[0],
- pos_in_item,
- tb->
- insert_size
- [0], body,
- zeros_num);
+ leaf_paste_in_buffer(&bi, item_pos - n + tb->rnum[0], pos_in_item,
+ tb->insert_size[0], body, zeros_num);
}
/* paste new entry, if item is directory item */
- pasted =
- B_N_PITEM_HEAD(tb->R[0],
- item_pos - n +
- tb->rnum[0]);
- if (is_direntry_le_ih(pasted)
- && pos_in_item >= 0) {
- leaf_paste_entries(&bi,
- item_pos -
- n +
- tb->rnum[0],
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ pasted = B_N_PITEM_HEAD(tb->R[0], item_pos - n + tb->rnum[0]);
+ if (is_direntry_le_ih(pasted) && pos_in_item >= 0) {
+ leaf_paste_entries(&bi, item_pos - n + tb->rnum[0],
+ pos_in_item, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
if (!pos_in_item) {
- RFALSE(item_pos - n +
- tb->rnum[0],
+ RFALSE(item_pos - n + tb->rnum[0],
"PAP-12165: directory item must be first item of node when pasting is in 0th position");
/* update delimiting keys */
- replace_key(tb,
- tb->CFR[0],
- tb->rkey[0],
- tb->R[0],
- 0);
+ replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0);
}
}
@@ -1111,22 +759,16 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
default: /* cases d and t */
reiserfs_panic(tb->tb_sb, "PAP-12175",
"rnum > 0: unexpected mode: %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT) ? "CUT"
- : "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
}
/* tb->rnum[0] > 0 */
RFALSE(tb->blknum[0] > 3,
- "PAP-12180: blknum can not be %d. It must be <= 3",
- tb->blknum[0]);
+ "PAP-12180: blknum can not be %d. It must be <= 3", tb->blknum[0]);
RFALSE(tb->blknum[0] < 0,
- "PAP-12185: blknum can not be %d. It must be >= 0",
- tb->blknum[0]);
+ "PAP-12185: blknum can not be %d. It must be >= 0", tb->blknum[0]);
/* if while adding to a node we discover that it is possible to split
it in two, and merge the left part into the left neighbor and the
@@ -1177,8 +819,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
if (n - snum[i] < item_pos) { /* new item or it's part falls to first new node S_new[i] */
if (item_pos == n - snum[i] + 1 && sbytes[i] != -1) { /* part of new item falls into S_new[i] */
- int old_key_comp, old_len,
- r_zeros_number;
+ int old_key_comp, old_len, r_zeros_number;
const char *r_body;
int version;
@@ -1192,15 +833,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
old_len = ih_item_len(ih);
/* Calculate key component and item length to insert into S_new[i] */
- set_le_ih_k_offset(ih,
- le_ih_k_offset(ih) +
- ((old_len -
- sbytes[i]) <<
- (is_indirect_le_ih
- (ih) ? tb->tb_sb->
- s_blocksize_bits -
- UNFM_P_SHIFT :
- 0)));
+ set_le_ih_k_offset(ih, le_ih_k_offset(ih) +
+ ((old_len - sbytes[i]) << (is_indirect_le_ih(ih) ? tb->tb_sb-> s_blocksize_bits - UNFM_P_SHIFT : 0)));
put_ih_item_len(ih, sbytes[i]);
@@ -1209,39 +843,29 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
if ((old_len - sbytes[i]) > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + (old_len -
- sbytes[i]) -
- zeros_num;
+ r_body = body + (old_len - sbytes[i]) - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - (old_len -
- sbytes[i]);
+ r_zeros_number = zeros_num - (old_len - sbytes[i]);
zeros_num -= r_zeros_number;
}
- leaf_insert_into_buf(&bi, 0, ih, r_body,
- r_zeros_number);
+ leaf_insert_into_buf(&bi, 0, ih, r_body, r_zeros_number);
/* Calculate key component and item length to insert into S[i] */
set_le_ih_k_offset(ih, old_key_comp);
- put_ih_item_len(ih,
- old_len - sbytes[i]);
+ put_ih_item_len(ih, old_len - sbytes[i]);
tb->insert_size[0] -= sbytes[i];
} else { /* whole new item falls into S_new[i] */
/* Shift snum[0] - 1 items to S_new[i] (sbytes[i] of split item) */
leaf_move_items(LEAF_FROM_S_TO_SNEW, tb,
- snum[i] - 1, sbytes[i],
- S_new[i]);
+ snum[i] - 1, sbytes[i], S_new[i]);
/* Insert new item into S_new[i] */
buffer_info_init_bh(tb, &bi, S_new[i]);
- leaf_insert_into_buf(&bi,
- item_pos - n +
- snum[i] - 1, ih,
- body, zeros_num);
+ leaf_insert_into_buf(&bi, item_pos - n + snum[i] - 1,
+ ih, body, zeros_num);
zeros_num = tb->insert_size[0] = 0;
}
@@ -1268,150 +892,73 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
int entry_count;
- entry_count =
- ih_entry_count(aux_ih);
+ entry_count = ih_entry_count(aux_ih);
- if (entry_count - sbytes[i] <
- pos_in_item
- && pos_in_item <=
- entry_count) {
+ if (entry_count - sbytes[i] < pos_in_item && pos_in_item <= entry_count) {
/* new directory entry falls into S_new[i] */
- RFALSE(!tb->
- insert_size[0],
- "PAP-12215: insert_size is already 0");
- RFALSE(sbytes[i] - 1 >=
- entry_count,
+ RFALSE(!tb->insert_size[0], "PAP-12215: insert_size is already 0");
+ RFALSE(sbytes[i] - 1 >= entry_count,
"PAP-12220: there are no so much entries (%d), only %d",
- sbytes[i] - 1,
- entry_count);
+ sbytes[i] - 1, entry_count);
/* Shift snum[i]-1 items in whole. Shift sbytes[i] directory entries from directory item number snum[i] */
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW,
- tb, snum[i],
- sbytes[i] - 1,
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], sbytes[i] - 1, S_new[i]);
/* Paste given directory entry to directory item */
buffer_info_init_bh(tb, &bi, S_new[i]);
- leaf_paste_in_buffer
- (&bi, 0,
- pos_in_item -
- entry_count +
- sbytes[i] - 1,
- tb->insert_size[0],
- body, zeros_num);
+ leaf_paste_in_buffer(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1,
+ tb->insert_size[0], body, zeros_num);
/* paste new directory entry */
- leaf_paste_entries(&bi,
- 0,
- pos_in_item
- -
- entry_count
- +
- sbytes
- [i] -
- 1, 1,
- (struct
- reiserfs_de_head
- *)
- body,
- body
- +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, 0, pos_in_item - entry_count + sbytes[i] - 1, 1,
+ (struct reiserfs_de_head *) body,
+ body + DEH_SIZE, tb->insert_size[0]);
tb->insert_size[0] = 0;
pos_in_item++;
} else { /* new directory entry doesn't fall into S_new[i] */
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW,
- tb, snum[i],
- sbytes[i],
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW,tb, snum[i], sbytes[i], S_new[i]);
}
} else { /* regular object */
- int n_shift, n_rem,
- r_zeros_number;
+ int n_shift, n_rem, r_zeros_number;
const char *r_body;
- RFALSE(pos_in_item !=
- ih_item_len
- (B_N_PITEM_HEAD
- (tbS0, item_pos))
- || tb->insert_size[0] <=
- 0,
+ RFALSE(pos_in_item != ih_item_len(B_N_PITEM_HEAD(tbS0, item_pos)) || tb->insert_size[0] <= 0,
"PAP-12225: item too short or insert_size <= 0");
/* Calculate number of bytes which must be shifted from appended item */
- n_shift =
- sbytes[i] -
- tb->insert_size[0];
+ n_shift = sbytes[i] - tb->insert_size[0];
if (n_shift < 0)
n_shift = 0;
- leaf_move_items
- (LEAF_FROM_S_TO_SNEW, tb,
- snum[i], n_shift,
- S_new[i]);
+ leaf_move_items(LEAF_FROM_S_TO_SNEW, tb, snum[i], n_shift, S_new[i]);
/* Calculate number of bytes which must remain in body after append to S_new[i] */
- n_rem =
- tb->insert_size[0] -
- sbytes[i];
+ n_rem = tb->insert_size[0] - sbytes[i];
if (n_rem < 0)
n_rem = 0;
/* Append part of body into S_new[0] */
buffer_info_init_bh(tb, &bi, S_new[i]);
if (n_rem > zeros_num) {
r_zeros_number = 0;
- r_body =
- body + n_rem -
- zeros_num;
+ r_body = body + n_rem - zeros_num;
} else {
r_body = body;
- r_zeros_number =
- zeros_num - n_rem;
- zeros_num -=
- r_zeros_number;
+ r_zeros_number = zeros_num - n_rem;
+ zeros_num -= r_zeros_number;
}
- leaf_paste_in_buffer(&bi, 0,
- n_shift,
- tb->
- insert_size
- [0] -
- n_rem,
- r_body,
- r_zeros_number);
+ leaf_paste_in_buffer(&bi, 0, n_shift,
+ tb->insert_size[0] - n_rem,
+ r_body, r_zeros_number);
{
struct item_head *tmp;
- tmp =
- B_N_PITEM_HEAD(S_new
- [i],
- 0);
+ tmp = B_N_PITEM_HEAD(S_new[i], 0);
if (is_indirect_le_ih
(tmp)) {
- set_ih_free_space
- (tmp, 0);
- set_le_ih_k_offset
- (tmp,
- le_ih_k_offset
- (tmp) +
- (n_rem <<
- (tb->
- tb_sb->
- s_blocksize_bits
- -
- UNFM_P_SHIFT)));
+ set_ih_free_space(tmp, 0);
+ set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + (n_rem << (tb->tb_sb->s_blocksize_bits - UNFM_P_SHIFT)));
} else {
- set_le_ih_k_offset
- (tmp,
- le_ih_k_offset
- (tmp) +
- n_rem);
+ set_le_ih_k_offset(tmp, le_ih_k_offset(tmp) + n_rem);
}
}
@@ -1426,8 +973,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
struct item_head *pasted;
#ifdef CONFIG_REISERFS_CHECK
- struct item_head *ih_check =
- B_N_PITEM_HEAD(tbS0, item_pos);
+ struct item_head *ih_check = B_N_PITEM_HEAD(tbS0, item_pos);
if (!is_direntry_le_ih(ih_check)
&& (pos_in_item != ih_item_len(ih_check)
@@ -1439,8 +985,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
"to ih_item_len");
#endif /* CONFIG_REISERFS_CHECK */
- leaf_mi =
- leaf_move_items(LEAF_FROM_S_TO_SNEW,
+ leaf_mi = leaf_move_items(LEAF_FROM_S_TO_SNEW,
tb, snum[i],
sbytes[i],
S_new[i]);
@@ -1452,30 +997,19 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
/* paste into item */
buffer_info_init_bh(tb, &bi, S_new[i]);
leaf_paste_in_buffer(&bi,
- item_pos - n +
- snum[i],
+ item_pos - n + snum[i],
pos_in_item,
tb->insert_size[0],
body, zeros_num);
- pasted =
- B_N_PITEM_HEAD(S_new[i],
- item_pos - n +
- snum[i]);
+ pasted = B_N_PITEM_HEAD(S_new[i], item_pos - n + snum[i]);
if (is_direntry_le_ih(pasted)) {
leaf_paste_entries(&bi,
- item_pos -
- n + snum[i],
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
+ item_pos - n + snum[i],
+ pos_in_item, 1,
+ (struct reiserfs_de_head *)body,
+ body + DEH_SIZE,
+ tb->insert_size[0]
);
}
@@ -1495,11 +1029,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
default: /* cases d and t */
reiserfs_panic(tb->tb_sb, "PAP-12245",
"blknum > 2: unexpected mode: %s(%d)",
- (flag ==
- M_DELETE) ? "DELETE" : ((flag ==
- M_CUT) ? "CUT"
- : "UNKNOWN"),
- flag);
+ (flag == M_DELETE) ? "DELETE" : ((flag == M_CUT) ? "CUT" : "UNKNOWN"), flag);
}
memcpy(insert_key + i, B_N_PKEY(S_new[i], 0), KEY_SIZE);
@@ -1524,9 +1054,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
/* If we insert the first key change the delimiting key */
if (item_pos == 0) {
if (tb->CFL[0]) /* can be 0 in reiserfsck */
- replace_key(tb, tb->CFL[0], tb->lkey[0],
- tbS0, 0);
-
+ replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
}
break;
@@ -1536,53 +1064,27 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
pasted = B_N_PITEM_HEAD(tbS0, item_pos);
/* when directory, may be new entry already pasted */
if (is_direntry_le_ih(pasted)) {
- if (pos_in_item >= 0 &&
- pos_in_item <=
- ih_entry_count(pasted)) {
+ if (pos_in_item >= 0 && pos_in_item <= ih_entry_count(pasted)) {
RFALSE(!tb->insert_size[0],
"PAP-12260: insert_size is 0 already");
/* prepare space */
buffer_info_init_tbS0(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos,
- pos_in_item,
- tb->
- insert_size
- [0], body,
+ leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+ tb->insert_size[0], body,
zeros_num);
/* paste entry */
- leaf_paste_entries(&bi,
- item_pos,
- pos_in_item,
- 1,
- (struct
- reiserfs_de_head
- *)body,
- body +
- DEH_SIZE,
- tb->
- insert_size
- [0]
- );
+ leaf_paste_entries(&bi, item_pos, pos_in_item, 1,
+ (struct reiserfs_de_head *)body,
+ body + DEH_SIZE,
+ tb->insert_size[0]);
if (!item_pos && !pos_in_item) {
- RFALSE(!tb->CFL[0]
- || !tb->L[0],
+ RFALSE(!tb->CFL[0] || !tb->L[0],
"PAP-12270: CFL[0]/L[0] must be specified");
- if (tb->CFL[0]) {
- replace_key(tb,
- tb->
- CFL
- [0],
- tb->
- lkey
- [0],
- tbS0,
- 0);
-
- }
+ if (tb->CFL[0])
+ replace_key(tb, tb->CFL[0], tb->lkey[0], tbS0, 0);
}
tb->insert_size[0] = 0;
}
@@ -1593,13 +1095,8 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
"PAP-12275: insert size must not be %d",
tb->insert_size[0]);
buffer_info_init_tbS0(tb, &bi);
- leaf_paste_in_buffer(&bi,
- item_pos,
- pos_in_item,
- tb->
- insert_size
- [0], body,
- zeros_num);
+ leaf_paste_in_buffer(&bi, item_pos, pos_in_item,
+ tb->insert_size[0], body, zeros_num);
if (is_indirect_le_ih(pasted)) {
#if 0
@@ -1611,8 +1108,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
tb->
insert_size[0]);
#endif
- set_ih_free_space
- (pasted, 0);
+ set_ih_free_space(pasted, 0);
}
tb->insert_size[0] = 0;
}
@@ -1620,8 +1116,7 @@ static int balance_leaf(struct tree_balance *tb, struct item_head *ih, /* item h
else {
if (tb->insert_size[0]) {
print_cur_tb("12285");
- reiserfs_panic(tb->
- tb_sb,
+ reiserfs_panic(tb->tb_sb,
"PAP-12285",
"insert_size "
"must be 0 "
diff --git a/fs/super.c b/fs/super.c
index cecd780e0f44..80d5cf2ca765 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -703,7 +703,6 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
if (flags & MS_RDONLY)
acct_auto_close(sb);
shrink_dcache_sb(sb);
- sync_filesystem(sb);
remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
@@ -720,6 +719,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
}
}
+ sync_filesystem(sb);
+
if (sb->s_op->remount_fs) {
retval = sb->s_op->remount_fs(sb, &flags, data);
if (retval) {
diff --git a/fs/sync.c b/fs/sync.c
index f15537452231..b28d1dd10e8b 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -27,11 +27,10 @@
* wait == 1 case since in that case write_inode() functions do
* sync_dirty_buffer() and thus effectively write one block at a time.
*/
-static int __sync_filesystem(struct super_block *sb, int wait,
- unsigned long start)
+static int __sync_filesystem(struct super_block *sb, int wait)
{
if (wait)
- sync_inodes_sb(sb, start);
+ sync_inodes_sb(sb);
else
writeback_inodes_sb(sb, WB_REASON_SYNC);
@@ -48,7 +47,6 @@ static int __sync_filesystem(struct super_block *sb, int wait,
int sync_filesystem(struct super_block *sb)
{
int ret;
- unsigned long start = jiffies;
/*
* We need to be protected against the filesystem going from
@@ -62,17 +60,17 @@ int sync_filesystem(struct super_block *sb)
if (sb->s_flags & MS_RDONLY)
return 0;
- ret = __sync_filesystem(sb, 0, start);
+ ret = __sync_filesystem(sb, 0);
if (ret < 0)
return ret;
- return __sync_filesystem(sb, 1, start);
+ return __sync_filesystem(sb, 1);
}
EXPORT_SYMBOL_GPL(sync_filesystem);
static void sync_inodes_one_sb(struct super_block *sb, void *arg)
{
if (!(sb->s_flags & MS_RDONLY))
- sync_inodes_sb(sb, *((unsigned long *)arg));
+ sync_inodes_sb(sb);
}
static void sync_fs_one_sb(struct super_block *sb, void *arg)
@@ -104,10 +102,9 @@ static void fdatawait_one_bdev(struct block_device *bdev, void *arg)
SYSCALL_DEFINE0(sync)
{
int nowait = 0, wait = 1;
- unsigned long start = jiffies;
wakeup_flusher_threads(0, WB_REASON_SYNC);
- iterate_supers(sync_inodes_one_sb, &start);
+ iterate_supers(sync_inodes_one_sb, NULL);
iterate_supers(sync_fs_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &wait);
iterate_bdevs(fdatawrite_one_bdev, NULL);
@@ -222,23 +219,6 @@ SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
return do_fsync(fd, 1);
}
-/**
- * generic_write_sync - perform syncing after a write if file / inode is sync
- * @file: file to which the write happened
- * @pos: offset where the write started
- * @count: length of the write
- *
- * This is just a simple wrapper about our general syncing function.
- */
-int generic_write_sync(struct file *file, loff_t pos, loff_t count)
-{
- if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host))
- return 0;
- return vfs_fsync_range(file, pos, pos + count - 1,
- (file->f_flags & __O_SYNC) ? 0 : 1);
-}
-EXPORT_SYMBOL(generic_write_sync);
-
/*
* sys_sync_file_range() permits finely controlled syncing over a segment of
* a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 6211230814fd..3eaf5c6622eb 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -27,6 +27,7 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
{
struct dentry *root;
void *ns;
+ bool new_sb;
if (!(flags & MS_KERNMOUNT)) {
if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
@@ -37,8 +38,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
}
ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
- root = kernfs_mount_ns(fs_type, flags, sysfs_root, ns);
- if (IS_ERR(root))
+ root = kernfs_mount_ns(fs_type, flags, sysfs_root, &new_sb, ns);
+ if (IS_ERR(root) || !new_sb)
kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
return root;
}
diff --git a/fs/udf/file.c b/fs/udf/file.c
index c02a27a19c6d..1037637957c7 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -144,6 +144,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
size_t count = iocb->ki_nbytes;
struct udf_inode_info *iinfo = UDF_I(inode);
+ mutex_lock(&inode->i_mutex);
down_write(&iinfo->i_data_sem);
if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
if (file->f_flags & O_APPEND)
@@ -156,6 +157,7 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
pos + count)) {
err = udf_expand_file_adinicb(inode);
if (err) {
+ mutex_unlock(&inode->i_mutex);
udf_debug("udf_expand_adinicb: err=%d\n", err);
return err;
}
@@ -169,9 +171,17 @@ static ssize_t udf_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
} else
up_write(&iinfo->i_data_sem);
- retval = generic_file_aio_write(iocb, iov, nr_segs, ppos);
- if (retval > 0)
+ retval = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
+ mutex_unlock(&inode->i_mutex);
+
+ if (retval > 0) {
+ ssize_t err;
+
mark_inode_dirty(inode);
+ err = generic_write_sync(file, iocb->ki_pos - retval, retval);
+ if (err < 0)
+ retval = err;
+ }
return retval;
}
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 062b7925bca0..982ce05c87ed 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -265,6 +265,7 @@ int udf_expand_file_adinicb(struct inode *inode)
.nr_to_write = 1,
};
+ WARN_ON_ONCE(!mutex_is_locked(&inode->i_mutex));
if (!iinfo->i_lenAlloc) {
if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD))
iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index a26739451b53..db2cfb067d0b 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -407,7 +407,7 @@ xfs_alloc_ioend_bio(
struct bio *bio = bio_alloc(GFP_NOIO, nvecs);
ASSERT(bio->bi_private == NULL);
- bio->bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+ bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
return bio;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 51757113a822..9c061ef2b0d9 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1240,7 +1240,7 @@ next_chunk:
bio = bio_alloc(GFP_NOIO, nr_pages);
bio->bi_bdev = bp->b_target->bt_bdev;
- bio->bi_sector = sector;
+ bio->bi_iter.bi_sector = sector;
bio->bi_end_io = xfs_buf_bio_end_io;
bio->bi_private = bp;
@@ -1262,7 +1262,7 @@ next_chunk:
total_nr_pages--;
}
- if (likely(bio->bi_size)) {
+ if (likely(bio->bi_iter.bi_size)) {
if (xfs_buf_is_vmapped(bp)) {
flush_kernel_vmap_range(bp->b_addr,
xfs_buf_vmap_len(bp));
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 2e7989e3a2d6..64b48eade91d 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -799,7 +799,7 @@ xfs_file_aio_write(
XFS_STATS_ADD(xs_write_bytes, ret);
/* Handle various SYNC-type writes */
- err = generic_write_sync(file, pos, ret);
+ err = generic_write_sync(file, iocb->ki_pos - ret, ret);
if (err < 0)
ret = err;
}
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index f35d5c953ff9..9ddfb8190ca1 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -705,7 +705,6 @@ xfs_setattr_size(
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
- int mask = iattr->ia_valid;
xfs_off_t oldsize, newsize;
struct xfs_trans *tp;
int error;
@@ -726,8 +725,8 @@ xfs_setattr_size(
ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
ASSERT(S_ISREG(ip->i_d.di_mode));
- ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
- ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+ ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+ ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
oldsize = inode->i_size;
newsize = iattr->ia_size;
@@ -736,7 +735,7 @@ xfs_setattr_size(
* Short circuit the truncate case for zero length files.
*/
if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
- if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
+ if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
return 0;
/*
@@ -824,10 +823,11 @@ xfs_setattr_size(
* these flags set. For all other operations the VFS set these flags
* explicitly if it wants a timestamp update.
*/
- if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+ if (newsize != oldsize &&
+ !(iattr->ia_valid & (ATTR_CTIME | ATTR_MTIME))) {
iattr->ia_ctime = iattr->ia_mtime =
current_fs_time(inode->i_sb);
- mask |= ATTR_CTIME | ATTR_MTIME;
+ iattr->ia_valid |= ATTR_CTIME | ATTR_MTIME;
}
/*
@@ -863,9 +863,9 @@ xfs_setattr_size(
xfs_inode_clear_eofblocks_tag(ip);
}
- if (mask & ATTR_MODE)
+ if (iattr->ia_valid & ATTR_MODE)
xfs_setattr_mode(ip, iattr);
- if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
+ if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
xfs_setattr_time(ip, iattr);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index cdebd832c3db..4ef6fdbced78 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -205,16 +205,25 @@ xlog_cil_insert_format_items(
/*
* We 64-bit align the length of each iovec so that the start
* of the next one is naturally aligned. We'll need to
- * account for that slack space here.
+ * account for that slack space here. Then round nbytes up
+ * to 64-bit alignment so that the initial buffer alignment is
+ * easy to calculate and verify.
*/
nbytes += niovecs * sizeof(uint64_t);
+ nbytes = round_up(nbytes, sizeof(uint64_t));
/* grab the old item if it exists for reservation accounting */
old_lv = lip->li_lv;
- /* calc buffer size */
- buf_size = sizeof(struct xfs_log_vec) + nbytes +
- niovecs * sizeof(struct xfs_log_iovec);
+ /*
+ * The data buffer needs to start 64-bit aligned, so round up
+ * that space to ensure we can align it appropriately and not
+ * overrun the buffer.
+ */
+ buf_size = nbytes +
+ round_up((sizeof(struct xfs_log_vec) +
+ niovecs * sizeof(struct xfs_log_iovec)),
+ sizeof(uint64_t));
/* compare to existing item size */
if (lip->li_lv && buf_size <= lip->li_lv->lv_size) {
@@ -251,6 +260,8 @@ xlog_cil_insert_format_items(
/* The allocated data region lies beyond the iovec region */
lv->lv_buf_len = 0;
lv->lv_buf = (char *)lv + buf_size - nbytes;
+ ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
+
lip->li_ops->iop_format(lip, lv);
insert:
ASSERT(lv->lv_buf_len <= nbytes);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 02df7b408a26..f96c05669a9e 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -282,22 +282,29 @@ xfs_readsb(
struct xfs_sb *sbp = &mp->m_sb;
int error;
int loud = !(flags & XFS_MFSI_QUIET);
+ const struct xfs_buf_ops *buf_ops;
ASSERT(mp->m_sb_bp == NULL);
ASSERT(mp->m_ddev_targp != NULL);
/*
+ * For the initial read, we must guess at the sector
+ * size based on the block device. It's enough to
+ * get the sb_sectsize out of the superblock and
+ * then reread with the proper length.
+ * We don't verify it yet, because it may not be complete.
+ */
+ sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+ buf_ops = NULL;
+
+ /*
* Allocate a (locked) buffer to hold the superblock.
* This will be kept around at all times to optimize
* access to the superblock.
*/
- sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
-
reread:
bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), 0,
- loud ? &xfs_sb_buf_ops
- : &xfs_sb_quiet_buf_ops);
+ BTOBB(sector_size), 0, buf_ops);
if (!bp) {
if (loud)
xfs_warn(mp, "SB buffer read failed");
@@ -328,12 +335,13 @@ reread:
}
/*
- * If device sector size is smaller than the superblock size,
- * re-read the superblock so the buffer is correctly sized.
+ * Re-read the superblock so the buffer is correctly sized,
+ * and properly verified.
*/
- if (sector_size < sbp->sb_sectsize) {
+ if (buf_ops == NULL) {
xfs_buf_relse(bp);
sector_size = sbp->sb_sectsize;
+ buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
goto reread;
}
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index b7c9aea77f8f..1e116794bb66 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -295,8 +295,7 @@ xfs_mount_validate_sb(
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp))) {
- XFS_CORRUPTION_ERROR("SB sanity check failed",
- XFS_ERRLEVEL_LOW, mp, sbp);
+ xfs_notice(mp, "SB sanity check failed");
return XFS_ERROR(EFSCORRUPTED);
}
@@ -611,10 +610,10 @@ xfs_sb_read_verify(
XFS_SB_VERSION_5) ||
dsb->sb_crc != 0)) {
- if (!xfs_verify_cksum(bp->b_addr, be16_to_cpu(dsb->sb_sectsize),
+ if (!xfs_verify_cksum(bp->b_addr, BBTOB(bp->b_length),
offsetof(struct xfs_sb, sb_crc))) {
/* Only fail bad secondaries on a known V5 filesystem */
- if (bp->b_bn != XFS_SB_DADDR &&
+ if (bp->b_bn == XFS_SB_DADDR ||
xfs_sb_version_hascrc(&mp->m_sb)) {
error = EFSCORRUPTED;
goto out_error;
@@ -625,7 +624,7 @@ xfs_sb_read_verify(
out_error:
if (error) {
- if (error != EWRONGFS)
+ if (error == EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW,
mp, bp->b_addr);
xfs_buf_ioerror(bp, error);
@@ -644,7 +643,6 @@ xfs_sb_quiet_read_verify(
{
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
-
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
/* XFS filesystem, verify noisily! */
xfs_sb_read_verify(bp);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f317488263dd..d971f4932b5d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -913,7 +913,7 @@ xfs_flush_inodes(
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
- sync_inodes_sb(sb, jiffies);
+ sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}