summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/bfs/inode.c2
-rw-r--r--fs/bio.c22
-rw-r--r--fs/block_dev.c2
-rw-r--r--fs/btrfs/backref.c48
-rw-r--r--fs/btrfs/ctree.c1
-rw-r--r--fs/btrfs/dev-replace.c2
-rw-r--r--fs/btrfs/extent_io.c9
-rw-r--r--fs/btrfs/file.c64
-rw-r--r--fs/btrfs/inode.c54
-rw-r--r--fs/btrfs/transaction.c8
-rw-r--r--fs/btrfs/transaction.h2
-rw-r--r--fs/btrfs/tree-log.c5
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/cifs/cifsencrypt.c14
-rw-r--r--fs/cifs/cifsfs.c11
-rw-r--r--fs/cifs/cifsglob.h4
-rw-r--r--fs/cifs/cifsproto.h4
-rw-r--r--fs/cifs/connect.c7
-rw-r--r--fs/cifs/file.c3
-rw-r--r--fs/cifs/link.c84
-rw-r--r--fs/cifs/readdir.c8
-rw-r--r--fs/cifs/sess.c6
-rw-r--r--fs/cifs/smb1ops.c1
-rw-r--r--fs/cifs/smb2transport.c9
-rw-r--r--fs/dcache.c98
-rw-r--r--fs/debugfs/inode.c69
-rw-r--r--fs/direct-io.c126
-rw-r--r--fs/dlm/ast.c5
-rw-r--r--fs/dlm/user.c25
-rw-r--r--fs/efs/inode.c2
-rw-r--r--fs/eventpoll.c31
-rw-r--r--fs/exec.c4
-rw-r--r--fs/ext3/dir.c2
-rw-r--r--fs/ext4/balloc.c24
-rw-r--r--fs/ext4/dir.c2
-rw-r--r--fs/ext4/ext4.h70
-rw-r--r--fs/ext4/ext4_extents.h6
-rw-r--r--fs/ext4/ext4_jbd2.c8
-rw-r--r--fs/ext4/ext4_jbd2.h2
-rw-r--r--fs/ext4/extents.c298
-rw-r--r--fs/ext4/extents_status.c125
-rw-r--r--fs/ext4/extents_status.h51
-rw-r--r--fs/ext4/file.c23
-rw-r--r--fs/ext4/ialloc.c100
-rw-r--r--fs/ext4/indirect.c1
-rw-r--r--fs/ext4/inode.c403
-rw-r--r--fs/ext4/ioctl.c10
-rw-r--r--fs/ext4/mballoc.c49
-rw-r--r--fs/ext4/migrate.c4
-rw-r--r--fs/ext4/move_extent.c2
-rw-r--r--fs/ext4/namei.c35
-rw-r--r--fs/ext4/page-io.c30
-rw-r--r--fs/ext4/super.c83
-rw-r--r--fs/f2fs/checkpoint.c24
-rw-r--r--fs/f2fs/data.c28
-rw-r--r--fs/f2fs/debug.c34
-rw-r--r--fs/f2fs/dir.c19
-rw-r--r--fs/f2fs/f2fs.h106
-rw-r--r--fs/f2fs/file.c25
-rw-r--r--fs/f2fs/gc.c58
-rw-r--r--fs/f2fs/gc.h38
-rw-r--r--fs/f2fs/inode.c15
-rw-r--r--fs/f2fs/namei.c33
-rw-r--r--fs/f2fs/node.c100
-rw-r--r--fs/f2fs/node.h44
-rw-r--r--fs/f2fs/recovery.c29
-rw-r--r--fs/f2fs/segment.c41
-rw-r--r--fs/f2fs/segment.h6
-rw-r--r--fs/f2fs/super.c209
-rw-r--r--fs/f2fs/xattr.c289
-rw-r--r--fs/f2fs/xattr.h15
-rw-r--r--fs/fcntl.c4
-rw-r--r--fs/file_table.c6
-rw-r--r--fs/fuse/cuse.c13
-rw-r--r--fs/gfs2/glock.c8
-rw-r--r--fs/gfs2/glops.c18
-rw-r--r--fs/gfs2/inode.c6
-rw-r--r--fs/gfs2/main.c2
-rw-r--r--fs/hugetlbfs/inode.c18
-rw-r--r--fs/inode.c2
-rw-r--r--fs/jbd2/commit.c6
-rw-r--r--fs/jbd2/journal.c5
-rw-r--r--fs/jbd2/recovery.c24
-rw-r--r--fs/jfs/jfs_dtree.c31
-rw-r--r--fs/lockd/clntlock.c13
-rw-r--r--fs/lockd/clntproc.c5
-rw-r--r--fs/namei.c274
-rw-r--r--fs/namespace.c4
-rw-r--r--fs/nfs/inode.c11
-rw-r--r--fs/nfs/nfs4proc.c8
-rw-r--r--fs/nfs/super.c4
-rw-r--r--fs/nfsd/nfs4proc.c2
-rw-r--r--fs/nfsd/nfs4state.c2
-rw-r--r--fs/nfsd/nfs4xdr.c19
-rw-r--r--fs/nilfs2/segbuf.c5
-rw-r--r--fs/nilfs2/super.c26
-rw-r--r--fs/ocfs2/aops.c10
-rw-r--r--fs/ocfs2/dir.c4
-rw-r--r--fs/ocfs2/file.c6
-rw-r--r--fs/ocfs2/journal.h2
-rw-r--r--fs/ocfs2/move_extents.c2
-rw-r--r--fs/ocfs2/refcounttree.c53
-rw-r--r--fs/ocfs2/refcounttree.h6
-rw-r--r--fs/ocfs2/super.c2
-rw-r--r--fs/open.c13
-rw-r--r--fs/proc/fd.c2
-rw-r--r--fs/proc/generic.c2
-rw-r--r--fs/proc/inode.c16
-rw-r--r--fs/proc/root.c4
-rw-r--r--fs/proc/task_mmu.c31
-rw-r--r--fs/pstore/Kconfig2
-rw-r--r--fs/pstore/inode.c10
-rw-r--r--fs/pstore/internal.h5
-rw-r--r--fs/pstore/platform.c212
-rw-r--r--fs/pstore/ram.c47
-rw-r--r--fs/quota/dquot.c46
-rw-r--r--fs/reiserfs/procfs.c99
-rw-r--r--fs/reiserfs/super.c3
-rw-r--r--fs/stat.c11
-rw-r--r--fs/super.c18
-rw-r--r--fs/sysfs/bin.c13
-rw-r--r--fs/sysfs/dir.c41
-rw-r--r--fs/sysfs/file.c82
-rw-r--r--fs/sysfs/group.c92
-rw-r--r--fs/sysfs/inode.c21
-rw-r--r--fs/sysfs/mount.c2
-rw-r--r--fs/sysfs/symlink.c18
-rw-r--r--fs/sysfs/sysfs.h18
-rw-r--r--fs/xfs/xfs_aops.c28
-rw-r--r--fs/xfs/xfs_aops.h3
130 files changed, 3043 insertions, 1570 deletions
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 5e376bb93419..8defc6b3f9a2 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -40,7 +40,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
int block, off;
inode = iget_locked(sb, ino);
- if (IS_ERR(inode))
+ if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
diff --git a/fs/bio.c b/fs/bio.c
index 94bbc04dba77..b3b20ed9510e 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1045,12 +1045,22 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
int bio_uncopy_user(struct bio *bio)
{
struct bio_map_data *bmd = bio->bi_private;
- int ret = 0;
+ struct bio_vec *bvec;
+ int ret = 0, i;
- if (!bio_flagged(bio, BIO_NULL_MAPPED))
- ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
- bmd->nr_sgvecs, bio_data_dir(bio) == READ,
- 0, bmd->is_our_pages);
+ if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+ /*
+ * if we're in a workqueue, the request is orphaned, so
+ * 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,
+ 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);
bio_put(bio);
return ret;
@@ -1946,7 +1956,7 @@ int bio_associate_current(struct bio *bio)
/* associate blkcg if exists */
rcu_read_lock();
- css = task_subsys_state(current, blkio_subsys_id);
+ css = task_css(current, blkio_subsys_id);
if (css && css_tryget(css))
bio->bi_css = css;
rcu_read_unlock();
diff --git a/fs/block_dev.c b/fs/block_dev.c
index c7bda5cd3da7..1173a4ee0830 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1519,7 +1519,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov,
blk_start_plug(&plug);
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
- if (ret > 0 || ret == -EIOCBQUEUED) {
+ if (ret > 0) {
ssize_t err;
err = generic_write_sync(file, pos, ret);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index eaf133384a8f..8bc5e8ccb091 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -36,16 +36,23 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
u64 extent_item_pos,
struct extent_inode_elem **eie)
{
- u64 data_offset;
- u64 data_len;
+ u64 offset = 0;
struct extent_inode_elem *e;
- data_offset = btrfs_file_extent_offset(eb, fi);
- data_len = btrfs_file_extent_num_bytes(eb, fi);
+ if (!btrfs_file_extent_compression(eb, fi) &&
+ !btrfs_file_extent_encryption(eb, fi) &&
+ !btrfs_file_extent_other_encoding(eb, fi)) {
+ u64 data_offset;
+ u64 data_len;
- if (extent_item_pos < data_offset ||
- extent_item_pos >= data_offset + data_len)
- return 1;
+ data_offset = btrfs_file_extent_offset(eb, fi);
+ data_len = btrfs_file_extent_num_bytes(eb, fi);
+
+ if (extent_item_pos < data_offset ||
+ extent_item_pos >= data_offset + data_len)
+ return 1;
+ offset = extent_item_pos - data_offset;
+ }
e = kmalloc(sizeof(*e), GFP_NOFS);
if (!e)
@@ -53,7 +60,7 @@ static int check_extent_in_eb(struct btrfs_key *key, struct extent_buffer *eb,
e->next = *eie;
e->inum = key->objectid;
- e->offset = key->offset + (extent_item_pos - data_offset);
+ e->offset = key->offset + offset;
*eie = e;
return 0;
@@ -189,7 +196,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
struct extent_buffer *eb;
struct btrfs_key key;
struct btrfs_file_extent_item *fi;
- struct extent_inode_elem *eie = NULL;
+ struct extent_inode_elem *eie = NULL, *old = NULL;
u64 disk_byte;
if (level != 0) {
@@ -223,6 +230,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (disk_byte == wanted_disk_byte) {
eie = NULL;
+ old = NULL;
if (extent_item_pos) {
ret = check_extent_in_eb(&key, eb, fi,
*extent_item_pos,
@@ -230,18 +238,20 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
if (ret < 0)
break;
}
- if (!ret) {
- ret = ulist_add(parents, eb->start,
- (uintptr_t)eie, GFP_NOFS);
- if (ret < 0)
- break;
- if (!extent_item_pos) {
- ret = btrfs_next_old_leaf(root, path,
- time_seq);
- continue;
- }
+ if (ret > 0)
+ goto next;
+ ret = ulist_add_merge(parents, eb->start,
+ (uintptr_t)eie,
+ (u64 *)&old, GFP_NOFS);
+ if (ret < 0)
+ break;
+ if (!ret && extent_item_pos) {
+ while (old->next)
+ old = old->next;
+ old->next = eie;
}
}
+next:
ret = btrfs_next_old_item(root, path, time_seq);
}
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 5bf4c39e2ad6..ed504607d8ec 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1271,7 +1271,6 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
BUG_ON(!eb_rewin);
}
- extent_buffer_get(eb_rewin);
btrfs_tree_read_unlock(eb);
free_extent_buffer(eb);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 4253ad580e39..5f8f3341c099 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -747,7 +747,7 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
WARN_ON(atomic_xchg(
&fs_info->mutually_exclusive_operation_running, 1));
task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
- return PTR_RET(task);
+ return PTR_ERR_OR_ZERO(task);
}
static int btrfs_dev_replace_kthread(void *data)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 583d98bd065e..fe443fece851 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4048,7 +4048,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
}
while (!end) {
- u64 offset_in_extent;
+ u64 offset_in_extent = 0;
/* break if the extent we found is outside the range */
if (em->start >= max || extent_map_end(em) < off)
@@ -4064,9 +4064,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
/*
* record the offset from the start of the extent
- * for adjusting the disk offset below
+ * for adjusting the disk offset below. Only do this if the
+ * extent isn't compressed since our in ram offset may be past
+ * what we have actually allocated on disk.
*/
- offset_in_extent = em_start - em->start;
+ if (!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
+ offset_in_extent = em_start - em->start;
em_end = extent_map_end(em);
em_len = em_end - em_start;
emflags = em->flags;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a005fe2c072a..4d2eb6417145 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -596,20 +596,29 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
if (no_splits)
goto next;
- if (em->block_start < EXTENT_MAP_LAST_BYTE &&
- em->start < start) {
+ if (em->start < start) {
split->start = em->start;
split->len = start - em->start;
- split->orig_start = em->orig_start;
- split->block_start = em->block_start;
- if (compressed)
- split->block_len = em->block_len;
- else
- split->block_len = split->len;
- split->ram_bytes = em->ram_bytes;
- split->orig_block_len = max(split->block_len,
- em->orig_block_len);
+ if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+ split->orig_start = em->orig_start;
+ split->block_start = em->block_start;
+
+ if (compressed)
+ split->block_len = em->block_len;
+ else
+ split->block_len = split->len;
+ split->orig_block_len = max(split->block_len,
+ em->orig_block_len);
+ split->ram_bytes = em->ram_bytes;
+ } else {
+ split->orig_start = split->start;
+ split->block_len = 0;
+ split->block_start = em->block_start;
+ split->orig_block_len = 0;
+ split->ram_bytes = split->len;
+ }
+
split->generation = gen;
split->bdev = em->bdev;
split->flags = flags;
@@ -620,8 +629,7 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split = split2;
split2 = NULL;
}
- if (em->block_start < EXTENT_MAP_LAST_BYTE &&
- testend && em->start + em->len > start + len) {
+ if (testend && em->start + em->len > start + len) {
u64 diff = start + len - em->start;
split->start = start + len;
@@ -630,18 +638,28 @@ void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split->flags = flags;
split->compress_type = em->compress_type;
split->generation = gen;
- split->orig_block_len = max(em->block_len,
+
+ if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+ split->orig_block_len = max(em->block_len,
em->orig_block_len);
- split->ram_bytes = em->ram_bytes;
- if (compressed) {
- split->block_len = em->block_len;
- split->block_start = em->block_start;
- split->orig_start = em->orig_start;
+ split->ram_bytes = em->ram_bytes;
+ if (compressed) {
+ split->block_len = em->block_len;
+ split->block_start = em->block_start;
+ split->orig_start = em->orig_start;
+ } else {
+ split->block_len = split->len;
+ split->block_start = em->block_start
+ + diff;
+ split->orig_start = em->orig_start;
+ }
} else {
- split->block_len = split->len;
- split->block_start = em->block_start + diff;
- split->orig_start = em->orig_start;
+ split->ram_bytes = split->len;
+ split->orig_start = split->start;
+ split->block_len = 0;
+ split->block_start = em->block_start;
+ split->orig_block_len = 0;
}
ret = add_extent_mapping(em_tree, split, modified);
@@ -1709,7 +1727,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
*/
BTRFS_I(inode)->last_trans = root->fs_info->generation + 1;
BTRFS_I(inode)->last_sub_trans = root->log_transid;
- if (num_written > 0 || num_written == -EIOCBQUEUED) {
+ if (num_written > 0) {
err = generic_write_sync(file, pos, num_written);
if (err < 0 && num_written > 0)
num_written = err;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6d1b93c8aafb..7bdc83d04d54 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2166,16 +2166,23 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
if (btrfs_file_extent_disk_bytenr(leaf, extent) != old->bytenr)
continue;
- extent_offset = btrfs_file_extent_offset(leaf, extent);
- if (key.offset - extent_offset != offset)
+ /*
+ * 'offset' refers to the exact key.offset,
+ * NOT the 'offset' field in btrfs_extent_data_ref, ie.
+ * (key.offset - extent_offset).
+ */
+ if (key.offset != offset)
continue;
+ extent_offset = btrfs_file_extent_offset(leaf, extent);
num_bytes = btrfs_file_extent_num_bytes(leaf, extent);
+
if (extent_offset >= old->extent_offset + old->offset +
old->len || extent_offset + num_bytes <=
old->extent_offset + old->offset)
continue;
+ ret = 0;
break;
}
@@ -2187,7 +2194,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
backref->root_id = root_id;
backref->inum = inum;
- backref->file_pos = offset + extent_offset;
+ backref->file_pos = offset;
backref->num_bytes = num_bytes;
backref->extent_offset = extent_offset;
backref->generation = btrfs_file_extent_generation(leaf, extent);
@@ -2210,7 +2217,8 @@ static noinline bool record_extent_backrefs(struct btrfs_path *path,
new->path = path;
list_for_each_entry_safe(old, tmp, &new->head, list) {
- ret = iterate_inodes_from_logical(old->bytenr, fs_info,
+ ret = iterate_inodes_from_logical(old->bytenr +
+ old->extent_offset, fs_info,
path, record_one_backref,
old);
BUG_ON(ret < 0 && ret != -ENOENT);
@@ -3166,7 +3174,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
found_key.type = BTRFS_INODE_ITEM_KEY;
found_key.offset = 0;
inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL);
- ret = PTR_RET(inode);
+ ret = PTR_ERR_OR_ZERO(inode);
if (ret && ret != -ESTALE)
goto out;
@@ -4391,9 +4399,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
int mask = attr->ia_valid;
int ret;
- if (newsize == oldsize)
- return 0;
-
/*
* The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
* special case where we need to update the times despite not having
@@ -5165,14 +5170,31 @@ next:
}
/* Reached end of directory/root. Bump pos past the last item. */
- if (key_type == BTRFS_DIR_INDEX_KEY)
- /*
- * 32-bit glibc will use getdents64, but then strtol -
- * so the last number we can serve is this.
- */
- ctx->pos = 0x7fffffff;
- else
- ctx->pos++;
+ ctx->pos++;
+
+ /*
+ * Stop new entries from being returned after we return the last
+ * entry.
+ *
+ * New directory entries are assigned a strictly increasing
+ * offset. This means that new entries created during readdir
+ * are *guaranteed* to be seen in the future by that readdir.
+ * This has broken buggy programs which operate on names as
+ * they're returned by readdir. Until we re-use freed offsets
+ * we have this hack to stop new entries from being returned
+ * under the assumption that they'll never reach this huge
+ * offset.
+ *
+ * This is being careful not to overflow 32bit loff_t unless the
+ * last entry requires it because doing so has broken 32bit apps
+ * in the past.
+ */
+ if (key_type == BTRFS_DIR_INDEX_KEY) {
+ if (ctx->pos >= INT_MAX)
+ ctx->pos = LLONG_MAX;
+ else
+ ctx->pos = INT_MAX;
+ }
nopos:
ret = 0;
err:
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index d58cce77fc6c..af1931a5960d 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -983,12 +983,12 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
* a dirty root struct and adds it into the list of dead roots that need to
* be deleted
*/
-int btrfs_add_dead_root(struct btrfs_root *root)
+void btrfs_add_dead_root(struct btrfs_root *root)
{
spin_lock(&root->fs_info->trans_lock);
- list_add_tail(&root->root_list, &root->fs_info->dead_roots);
+ if (list_empty(&root->root_list))
+ list_add_tail(&root->root_list, &root->fs_info->dead_roots);
spin_unlock(&root->fs_info->trans_lock);
- return 0;
}
/*
@@ -1925,7 +1925,7 @@ int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
}
root = list_first_entry(&fs_info->dead_roots,
struct btrfs_root, root_list);
- list_del(&root->root_list);
+ list_del_init(&root->root_list);
spin_unlock(&fs_info->trans_lock);
pr_debug("btrfs: cleaner removing %llu\n",
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 005b0375d18c..defbc4269897 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -143,7 +143,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
-int btrfs_add_dead_root(struct btrfs_root *root);
+void btrfs_add_dead_root(struct btrfs_root *root);
int btrfs_defrag_root(struct btrfs_root *root);
int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 2c6791493637..ff60d8978ae2 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3746,8 +3746,9 @@ next_slot:
}
log_extents:
+ btrfs_release_path(path);
+ btrfs_release_path(dst_path);
if (fast_search) {
- btrfs_release_path(dst_path);
ret = btrfs_log_changed_extents(trans, root, inode, dst_path);
if (ret) {
err = ret;
@@ -3764,8 +3765,6 @@ log_extents:
}
if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
- btrfs_release_path(path);
- btrfs_release_path(dst_path);
ret = log_directory_changes(trans, root, inode, path, dst_path);
if (ret) {
err = ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 78b871753cb6..67a085381845 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3302,7 +3302,7 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
}
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
- return PTR_RET(tsk);
+ return PTR_ERR_OR_ZERO(tsk);
}
int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 45e57cc38200..fc6f4f3a1a9d 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -43,17 +43,18 @@ cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
server->secmech.md5 = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(server->secmech.md5)) {
cifs_dbg(VFS, "could not allocate crypto md5\n");
- return PTR_ERR(server->secmech.md5);
+ rc = PTR_ERR(server->secmech.md5);
+ server->secmech.md5 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
crypto_shash_descsize(server->secmech.md5);
server->secmech.sdescmd5 = kmalloc(size, GFP_KERNEL);
if (!server->secmech.sdescmd5) {
- rc = -ENOMEM;
crypto_free_shash(server->secmech.md5);
server->secmech.md5 = NULL;
- return rc;
+ return -ENOMEM;
}
server->secmech.sdescmd5->shash.tfm = server->secmech.md5;
server->secmech.sdescmd5->shash.flags = 0x0;
@@ -421,7 +422,7 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
if (blobptr + attrsize > blobend)
break;
if (type == NTLMSSP_AV_NB_DOMAIN_NAME) {
- if (!attrsize)
+ if (!attrsize || attrsize >= CIFS_MAX_DOMAINNAME_LEN)
break;
if (!ses->domainName) {
ses->domainName =
@@ -591,6 +592,7 @@ CalcNTLMv2_response(const struct cifs_ses *ses, char *ntlmv2_hash)
static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server)
{
+ int rc;
unsigned int size;
/* check if already allocated */
@@ -600,7 +602,9 @@ static int crypto_hmacmd5_alloc(struct TCP_Server_Info *server)
server->secmech.hmacmd5 = crypto_alloc_shash("hmac(md5)", 0, 0);
if (IS_ERR(server->secmech.hmacmd5)) {
cifs_dbg(VFS, "could not allocate crypto hmacmd5\n");
- return PTR_ERR(server->secmech.hmacmd5);
+ rc = PTR_ERR(server->secmech.hmacmd5);
+ server->secmech.hmacmd5 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 4bdd547dbf6f..85ea98d139fc 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -147,18 +147,17 @@ cifs_read_super(struct super_block *sb)
goto out_no_root;
}
+ if (cifs_sb_master_tcon(cifs_sb)->nocase)
+ sb->s_d_op = &cifs_ci_dentry_ops;
+ else
+ sb->s_d_op = &cifs_dentry_ops;
+
sb->s_root = d_make_root(inode);
if (!sb->s_root) {
rc = -ENOMEM;
goto out_no_root;
}
- /* do that *after* d_make_root() - we want NULL ->d_op for root here */
- if (cifs_sb_master_tcon(cifs_sb)->nocase)
- sb->s_d_op = &cifs_ci_dentry_ops;
- else
- sb->s_d_op = &cifs_dentry_ops;
-
#ifdef CONFIG_CIFS_NFSD_EXPORT
if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) {
cifs_dbg(FYI, "export ops supported\n");
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 1fdc37041057..52ca861ed35e 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -44,6 +44,7 @@
#define MAX_TREE_SIZE (2 + MAX_SERVER_SIZE + 1 + MAX_SHARE_SIZE + 1)
#define MAX_SERVER_SIZE 15
#define MAX_SHARE_SIZE 80
+#define CIFS_MAX_DOMAINNAME_LEN 256 /* max domain name length */
#define MAX_USERNAME_SIZE 256 /* reasonable maximum for current servers */
#define MAX_PASSWORD_SIZE 512 /* max for windows seems to be 256 wide chars */
@@ -369,6 +370,9 @@ struct smb_version_operations {
void (*generate_signingkey)(struct TCP_Server_Info *server);
int (*calc_signature)(struct smb_rqst *rqst,
struct TCP_Server_Info *server);
+ int (*query_mf_symlink)(const unsigned char *path, char *pbuf,
+ unsigned int *pbytes_read, struct cifs_sb_info *cifs_sb,
+ unsigned int xid);
};
struct smb_version_values {
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index f7e584d047e2..b29a012bed33 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -497,5 +497,7 @@ 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);
#endif /* _CIFSPROTO_H */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index fa68813396b5..d67c550c4980 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1675,7 +1675,8 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
if (string == NULL)
goto out_nomem;
- if (strnlen(string, 256) == 256) {
+ if (strnlen(string, CIFS_MAX_DOMAINNAME_LEN)
+ == CIFS_MAX_DOMAINNAME_LEN) {
printk(KERN_WARNING "CIFS: domain name too"
" long\n");
goto cifs_parse_mount_err;
@@ -2276,8 +2277,8 @@ cifs_put_smb_ses(struct cifs_ses *ses)
#ifdef CONFIG_KEYS
-/* strlen("cifs:a:") + INET6_ADDRSTRLEN + 1 */
-#define CIFSCREDS_DESC_SIZE (7 + INET6_ADDRSTRLEN + 1)
+/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */
+#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1)
/* Populate username and pw fields from keyring if possible */
static int
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 1e57f36ea1b2..9d0dd952ad79 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -647,6 +647,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
oflags, &oplock, &cfile->fid.netfid, xid);
if (rc == 0) {
cifs_dbg(FYI, "posix reopen succeeded\n");
+ oparms.reconnect = true;
goto reopen_success;
}
/*
@@ -2552,7 +2553,7 @@ cifs_writev(struct kiocb *iocb, const struct iovec *iov,
mutex_unlock(&inode->i_mutex);
}
- if (rc > 0 || rc == -EIOCBQUEUED) {
+ if (rc > 0) {
ssize_t err;
err = generic_write_sync(file, pos, rc);
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index b83c3f5646bd..562044f700e5 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -305,67 +305,89 @@ CIFSCouldBeMFSymlink(const struct cifs_fattr *fattr)
}
int
-CIFSCheckMFSymlink(struct cifs_fattr *fattr,
- const unsigned char *path,
- struct cifs_sb_info *cifs_sb, unsigned int xid)
+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_tcon *ptcon;
struct cifs_io_parms io_parms;
- u8 *buf;
- char *pbuf;
- unsigned int bytes_read = 0;
int buf_type = CIFS_NO_BUFFER;
- unsigned int link_len = 0;
FILE_ALL_INFO file_info;
- if (!CIFSCouldBeMFSymlink(fattr))
- /* it's not a symlink */
- return 0;
-
tlink = cifs_sb_tlink(cifs_sb);
if (IS_ERR(tlink))
return PTR_ERR(tlink);
- pTcon = tlink_tcon(tlink);
+ ptcon = tlink_tcon(tlink);
- rc = CIFSSMBOpen(xid, pTcon, path, FILE_OPEN, GENERIC_READ,
+ 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)
- goto out;
+ if (rc != 0) {
+ cifs_put_tlink(tlink);
+ return rc;
+ }
if (file_info.EndOfFile != cpu_to_le64(CIFS_MF_SYMLINK_FILE_SIZE)) {
- CIFSSMBClose(xid, pTcon, netfid);
+ CIFSSMBClose(xid, ptcon, netfid);
+ cifs_put_tlink(tlink);
/* it's not a symlink */
- goto out;
+ return rc;
}
- buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
- if (!buf) {
- rc = -ENOMEM;
- goto out;
- }
- pbuf = buf;
io_parms.netfid = netfid;
io_parms.pid = current->tgid;
- io_parms.tcon = pTcon;
+ io_parms.tcon = ptcon;
io_parms.offset = 0;
io_parms.length = CIFS_MF_SYMLINK_FILE_SIZE;
- rc = CIFSSMBRead(xid, &io_parms, &bytes_read, &pbuf, &buf_type);
- CIFSSMBClose(xid, pTcon, netfid);
- if (rc != 0) {
- kfree(buf);
+ rc = CIFSSMBRead(xid, &io_parms, pbytes_read, &pbuf, &buf_type);
+ CIFSSMBClose(xid, ptcon, netfid);
+ cifs_put_tlink(tlink);
+ return rc;
+}
+
+
+int
+CIFSCheckMFSymlink(struct cifs_fattr *fattr,
+ const unsigned char *path,
+ struct cifs_sb_info *cifs_sb, unsigned int xid)
+{
+ int rc = 0;
+ u8 *buf = NULL;
+ unsigned int link_len = 0;
+ unsigned int bytes_read = 0;
+ struct cifs_tcon *ptcon;
+
+ if (!CIFSCouldBeMFSymlink(fattr))
+ /* it's not a symlink */
+ return 0;
+
+ buf = kmalloc(CIFS_MF_SYMLINK_FILE_SIZE, GFP_KERNEL);
+ if (!buf) {
+ rc = -ENOMEM;
goto out;
}
+ ptcon = tlink_tcon(cifs_sb_tlink(cifs_sb));
+ if ((ptcon->ses) && (ptcon->ses->server->ops->query_mf_symlink))
+ rc = ptcon->ses->server->ops->query_mf_symlink(path, buf,
+ &bytes_read, cifs_sb, xid);
+ else
+ goto out;
+
+ if (rc != 0)
+ goto out;
+
+ if (bytes_read == 0) /* not a symlink */
+ goto out;
+
rc = CIFSParseMFSymlink(buf, bytes_read, &link_len, NULL);
- kfree(buf);
if (rc == -EINVAL) {
/* it's not a symlink */
rc = 0;
@@ -381,7 +403,7 @@ CIFSCheckMFSymlink(struct cifs_fattr *fattr,
fattr->cf_mode |= S_IFLNK | S_IRWXU | S_IRWXG | S_IRWXO;
fattr->cf_dtype = DT_LNK;
out:
- cifs_put_tlink(tlink);
+ kfree(buf);
return rc;
}
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index ab8778469394..69d2c826a23b 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -111,6 +111,14 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
return;
}
+ /*
+ * If we know that the inode will need to be revalidated immediately,
+ * then don't create a new dentry for it. We'll end up doing an on
+ * the wire call either way and this spares us an invalidation.
+ */
+ if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)
+ return;
+
dentry = d_alloc(parent, name);
if (!dentry)
return;
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 79358e341fd2..08dd37bb23aa 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -197,7 +197,7 @@ static void unicode_domain_string(char **pbcc_area, struct cifs_ses *ses,
bytes_ret = 0;
} else
bytes_ret = cifs_strtoUTF16((__le16 *) bcc_ptr, ses->domainName,
- 256, nls_cp);
+ CIFS_MAX_DOMAINNAME_LEN, nls_cp);
bcc_ptr += 2 * bytes_ret;
bcc_ptr += 2; /* account for null terminator */
@@ -255,8 +255,8 @@ static void ascii_ssetup_strings(char **pbcc_area, struct cifs_ses *ses,
/* copy domain */
if (ses->domainName != NULL) {
- strncpy(bcc_ptr, ses->domainName, 256);
- bcc_ptr += strnlen(ses->domainName, 256);
+ strncpy(bcc_ptr, ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
+ bcc_ptr += strnlen(ses->domainName, CIFS_MAX_DOMAINNAME_LEN);
} /* else we will send a null domain name
so the server will default to its own domain */
*bcc_ptr = 0;
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 6457690731a2..60943978aec3 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -944,6 +944,7 @@ 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,
};
struct smb_version_values smb1_values = {
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 301b191270b9..4f2300d020c7 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -42,6 +42,7 @@
static int
smb2_crypto_shash_allocate(struct TCP_Server_Info *server)
{
+ int rc;
unsigned int size;
if (server->secmech.sdeschmacsha256 != NULL)
@@ -50,7 +51,9 @@ smb2_crypto_shash_allocate(struct TCP_Server_Info *server)
server->secmech.hmacsha256 = crypto_alloc_shash("hmac(sha256)", 0, 0);
if (IS_ERR(server->secmech.hmacsha256)) {
cifs_dbg(VFS, "could not allocate crypto hmacsha256\n");
- return PTR_ERR(server->secmech.hmacsha256);
+ rc = PTR_ERR(server->secmech.hmacsha256);
+ server->secmech.hmacsha256 = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
@@ -87,7 +90,9 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
server->secmech.sdeschmacsha256 = NULL;
crypto_free_shash(server->secmech.hmacsha256);
server->secmech.hmacsha256 = NULL;
- return PTR_ERR(server->secmech.cmacaes);
+ rc = PTR_ERR(server->secmech.cmacaes);
+ server->secmech.cmacaes = NULL;
+ return rc;
}
size = sizeof(struct shash_desc) +
diff --git a/fs/dcache.c b/fs/dcache.c
index 87bdb5329c3c..5aa53bc056ba 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -229,7 +229,7 @@ static void __d_free(struct rcu_head *head)
*/
static void d_free(struct dentry *dentry)
{
- BUG_ON(dentry->d_count);
+ BUG_ON(dentry->d_lockref.count);
this_cpu_dec(nr_dentry);
if (dentry->d_op && dentry->d_op->d_release)
dentry->d_op->d_release(dentry);
@@ -467,12 +467,12 @@ relock:
}
if (ref)
- dentry->d_count--;
+ dentry->d_lockref.count--;
/*
* inform the fs via d_prune that this dentry is about to be
* unhashed and destroyed.
*/
- if (dentry->d_flags & DCACHE_OP_PRUNE)
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
dentry_lru_del(dentry);
@@ -513,15 +513,10 @@ void dput(struct dentry *dentry)
return;
repeat:
- if (dentry->d_count == 1)
+ if (dentry->d_lockref.count == 1)
might_sleep();
- spin_lock(&dentry->d_lock);
- BUG_ON(!dentry->d_count);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
+ if (lockref_put_or_lock(&dentry->d_lockref))
return;
- }
if (dentry->d_flags & DCACHE_OP_DELETE) {
if (dentry->d_op->d_delete(dentry))
@@ -535,7 +530,7 @@ repeat:
dentry->d_flags |= DCACHE_REFERENCED;
dentry_lru_add(dentry);
- dentry->d_count--;
+ dentry->d_lockref.count--;
spin_unlock(&dentry->d_lock);
return;
@@ -590,7 +585,7 @@ int d_invalidate(struct dentry * dentry)
* We also need to leave mountpoints alone,
* directory or not.
*/
- if (dentry->d_count > 1 && dentry->d_inode) {
+ if (dentry->d_lockref.count > 1 && dentry->d_inode) {
if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
spin_unlock(&dentry->d_lock);
return -EBUSY;
@@ -606,20 +601,33 @@ EXPORT_SYMBOL(d_invalidate);
/* This must be called with d_lock held */
static inline void __dget_dlock(struct dentry *dentry)
{
- dentry->d_count++;
+ dentry->d_lockref.count++;
}
static inline void __dget(struct dentry *dentry)
{
- spin_lock(&dentry->d_lock);
- __dget_dlock(dentry);
- spin_unlock(&dentry->d_lock);
+ lockref_get(&dentry->d_lockref);
}
struct dentry *dget_parent(struct dentry *dentry)
{
+ int gotref;
struct dentry *ret;
+ /*
+ * Do optimistic parent lookup without any
+ * locking.
+ */
+ rcu_read_lock();
+ ret = ACCESS_ONCE(dentry->d_parent);
+ gotref = lockref_get_not_zero(&ret->d_lockref);
+ rcu_read_unlock();
+ if (likely(gotref)) {
+ if (likely(ret == ACCESS_ONCE(dentry->d_parent)))
+ return ret;
+ dput(ret);
+ }
+
repeat:
/*
* Don't need rcu_dereference because we re-check it was correct under
@@ -634,8 +642,8 @@ repeat:
goto repeat;
}
rcu_read_unlock();
- BUG_ON(!ret->d_count);
- ret->d_count++;
+ BUG_ON(!ret->d_lockref.count);
+ ret->d_lockref.count++;
spin_unlock(&ret->d_lock);
return ret;
}
@@ -718,7 +726,15 @@ restart:
spin_lock(&inode->i_lock);
hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
spin_lock(&dentry->d_lock);
- if (!dentry->d_count) {
+ if (!dentry->d_lockref.count) {
+ /*
+ * inform the fs via d_prune that this dentry
+ * is about to be unhashed and destroyed.
+ */
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
+ !d_unhashed(dentry))
+ dentry->d_op->d_prune(dentry);
+
__dget_dlock(dentry);
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
@@ -763,12 +779,8 @@ static void try_prune_one_dentry(struct dentry *dentry)
/* Prune ancestors. */
dentry = parent;
while (dentry) {
- spin_lock(&dentry->d_lock);
- if (dentry->d_count > 1) {
- dentry->d_count--;
- spin_unlock(&dentry->d_lock);
+ if (lockref_put_or_lock(&dentry->d_lockref))
return;
- }
dentry = dentry_kill(dentry, 1);
}
}
@@ -793,7 +805,7 @@ static void shrink_dentry_list(struct list_head *list)
* the LRU because of laziness during lookup. Do not free
* it - just keep it off the LRU list.
*/
- if (dentry->d_count) {
+ if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
spin_unlock(&dentry->d_lock);
continue;
@@ -907,13 +919,14 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
* inform the fs that this dentry is about to be
* unhashed and destroyed.
*/
- if (dentry->d_flags & DCACHE_OP_PRUNE)
+ if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
+ !d_unhashed(dentry))
dentry->d_op->d_prune(dentry);
dentry_lru_del(dentry);
__d_shrink(dentry);
- if (dentry->d_count != 0) {
+ if (dentry->d_lockref.count != 0) {
printk(KERN_ERR
"BUG: Dentry %p{i=%lx,n=%s}"
" still in use (%d)"
@@ -922,7 +935,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
dentry->d_inode ?
dentry->d_inode->i_ino : 0UL,
dentry->d_name.name,
- dentry->d_count,
+ dentry->d_lockref.count,
dentry->d_sb->s_type->name,
dentry->d_sb->s_id);
BUG();
@@ -933,7 +946,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
list_del(&dentry->d_u.d_child);
} else {
parent = dentry->d_parent;
- parent->d_count--;
+ parent->d_lockref.count--;
list_del(&dentry->d_u.d_child);
}
@@ -981,7 +994,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
dentry = sb->s_root;
sb->s_root = NULL;
- dentry->d_count--;
+ dentry->d_lockref.count--;
shrink_dcache_for_umount_subtree(dentry);
while (!hlist_bl_empty(&sb->s_anon)) {
@@ -1147,7 +1160,7 @@ resume:
* loop in shrink_dcache_parent() might not make any progress
* and loop forever.
*/
- if (dentry->d_count) {
+ if (dentry->d_lockref.count) {
dentry_lru_del(dentry);
} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
dentry_lru_move_list(dentry, dispose);
@@ -1269,7 +1282,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
smp_wmb();
dentry->d_name.name = dname;
- dentry->d_count = 1;
+ dentry->d_lockref.count = 1;
dentry->d_flags = 0;
spin_lock_init(&dentry->d_lock);
seqcount_init(&dentry->d_seq);
@@ -1782,7 +1795,7 @@ static noinline enum slow_d_compare slow_dentry_cmp(
* without taking d_lock and checking d_seq sequence count against @seq
* returned here.
*
- * A refcount may be taken on the found dentry with the __d_rcu_to_refcount
+ * A refcount may be taken on the found dentry with the d_rcu_to_refcount
* function.
*
* Alternatively, __d_lookup_rcu may be called again to look up the child of
@@ -1970,7 +1983,7 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
goto next;
}
- dentry->d_count++;
+ dentry->d_lockref.count++;
found = dentry;
spin_unlock(&dentry->d_lock);
break;
@@ -2069,7 +2082,7 @@ again:
spin_lock(&dentry->d_lock);
inode = dentry->d_inode;
isdir = S_ISDIR(inode->i_mode);
- if (dentry->d_count == 1) {
+ if (dentry->d_lockref.count == 1) {
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
cpu_relax();
@@ -2724,6 +2737,17 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
return memcpy(buffer, temp, sz);
}
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+ char *end = buffer + buflen;
+ /* these dentries are never renamed, so d_lock is not needed */
+ if (prepend(&end, &buflen, " (deleted)", 11) ||
+ prepend_name(&end, &buflen, &dentry->d_name) ||
+ prepend(&end, &buflen, "/", 1))
+ end = ERR_PTR(-ENAMETOOLONG);
+ return end;
+}
+
/*
* Write full pathname from the root of the filesystem into the buffer.
*/
@@ -2937,7 +2961,7 @@ resume:
}
if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
dentry->d_flags |= DCACHE_GENOCIDE;
- dentry->d_count--;
+ dentry->d_lockref.count--;
}
spin_unlock(&dentry->d_lock);
}
@@ -2945,7 +2969,7 @@ resume:
struct dentry *child = this_parent;
if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
this_parent->d_flags |= DCACHE_GENOCIDE;
- this_parent->d_count--;
+ this_parent->d_lockref.count--;
}
this_parent = try_to_ascend(this_parent, locked, seq);
if (!this_parent)
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 4888cb3fdef7..c7c83ff0f752 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -533,8 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
*/
void debugfs_remove_recursive(struct dentry *dentry)
{
- struct dentry *child;
- struct dentry *parent;
+ struct dentry *child, *next, *parent;
if (IS_ERR_OR_NULL(dentry))
return;
@@ -544,61 +543,37 @@ void debugfs_remove_recursive(struct dentry *dentry)
return;
parent = dentry;
+ down:
mutex_lock(&parent->d_inode->i_mutex);
+ list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+ if (!debugfs_positive(child))
+ continue;
- while (1) {
- /*
- * When all dentries under "parent" has been removed,
- * walk up the tree until we reach our starting point.
- */
- if (list_empty(&parent->d_subdirs)) {
- mutex_unlock(&parent->d_inode->i_mutex);
- if (parent == dentry)
- break;
- parent = parent->d_parent;
- mutex_lock(&parent->d_inode->i_mutex);
- }
- child = list_entry(parent->d_subdirs.next, struct dentry,
- d_u.d_child);
- next_sibling:
-
- /*
- * If "child" isn't empty, walk down the tree and
- * remove all its descendants first.
- */
+ /* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
mutex_unlock(&parent->d_inode->i_mutex);
parent = child;
- mutex_lock(&parent->d_inode->i_mutex);
- continue;
+ goto down;
}
- __debugfs_remove(child, parent);
- if (parent->d_subdirs.next == &child->d_u.d_child) {
- /*
- * Try the next sibling.
- */
- if (child->d_u.d_child.next != &parent->d_subdirs) {
- child = list_entry(child->d_u.d_child.next,
- struct dentry,
- d_u.d_child);
- goto next_sibling;
- }
-
- /*
- * Avoid infinite loop if we fail to remove
- * one dentry.
- */
- mutex_unlock(&parent->d_inode->i_mutex);
- break;
- }
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ up:
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
- parent = dentry->d_parent;
+ mutex_unlock(&parent->d_inode->i_mutex);
+ child = parent;
+ parent = parent->d_parent;
mutex_lock(&parent->d_inode->i_mutex);
- __debugfs_remove(dentry, parent);
+
+ if (child != dentry) {
+ next = list_entry(child->d_u.d_child.next, struct dentry,
+ d_u.d_child);
+ goto up;
+ }
+
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
mutex_unlock(&parent->d_inode->i_mutex);
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 7ab90f5081ee..1782023bd68a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -127,6 +127,7 @@ struct dio {
spinlock_t bio_lock; /* protects BIO fields below */
int page_errors; /* errno from get_user_pages() */
int is_async; /* is IO async ? */
+ bool defer_completion; /* defer AIO completion to workqueue? */
int io_error; /* IO error in completion path */
unsigned long refcount; /* direct_io_worker() and bios */
struct bio *bio_list; /* singly linked via bi_private */
@@ -141,7 +142,10 @@ struct dio {
* allocation time. Don't add new fields after pages[] unless you
* wish that they not be zeroed.
*/
- struct page *pages[DIO_PAGES]; /* page buffer */
+ union {
+ struct page *pages[DIO_PAGES]; /* page buffer */
+ struct work_struct complete_work;/* deferred AIO completion */
+ };
} ____cacheline_aligned_in_smp;
static struct kmem_cache *dio_cache __read_mostly;
@@ -221,16 +225,16 @@ static inline struct page *dio_get_page(struct dio *dio,
* dio_complete() - called when all DIO BIO I/O has been completed
* @offset: the byte offset in the file of the completed operation
*
- * This releases locks as dictated by the locking type, lets interested parties
- * know that a DIO operation has completed, and calculates the resulting return
- * code for the operation.
+ * This drops i_dio_count, lets interested parties know that a DIO operation
+ * has completed, and calculates the resulting return code for the operation.
*
* It lets the filesystem know if it registered an interest earlier via
* get_block. Pass the private field of the map buffer_head so that
* filesystems can use it to hold additional state between get_block calls and
* dio_complete.
*/
-static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is_async)
+static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret,
+ bool is_async)
{
ssize_t transferred = 0;
@@ -258,19 +262,36 @@ static ssize_t dio_complete(struct dio *dio, loff_t offset, ssize_t ret, bool is
if (ret == 0)
ret = transferred;
- if (dio->end_io && dio->result) {
- dio->end_io(dio->iocb, offset, transferred,
- dio->private, ret, is_async);
- } else {
- inode_dio_done(dio->inode);
- if (is_async)
- aio_complete(dio->iocb, ret, 0);
+ if (dio->end_io && dio->result)
+ dio->end_io(dio->iocb, offset, transferred, dio->private);
+
+ inode_dio_done(dio->inode);
+ if (is_async) {
+ if (dio->rw & WRITE) {
+ int err;
+
+ err = generic_write_sync(dio->iocb->ki_filp, offset,
+ transferred);
+ if (err < 0 && ret > 0)
+ ret = err;
+ }
+
+ aio_complete(dio->iocb, ret, 0);
}
+ kmem_cache_free(dio_cache, dio);
return ret;
}
+static void dio_aio_complete_work(struct work_struct *work)
+{
+ struct dio *dio = container_of(work, struct dio, complete_work);
+
+ dio_complete(dio, dio->iocb->ki_pos, 0, true);
+}
+
static int dio_bio_complete(struct dio *dio, struct bio *bio);
+
/*
* Asynchronous IO callback.
*/
@@ -290,8 +311,13 @@ static void dio_bio_end_aio(struct bio *bio, int error)
spin_unlock_irqrestore(&dio->bio_lock, flags);
if (remaining == 0) {
- dio_complete(dio, dio->iocb->ki_pos, 0, true);
- kmem_cache_free(dio_cache, dio);
+ if (dio->result && dio->defer_completion) {
+ INIT_WORK(&dio->complete_work, dio_aio_complete_work);
+ queue_work(dio->inode->i_sb->s_dio_done_wq,
+ &dio->complete_work);
+ } else {
+ dio_complete(dio, dio->iocb->ki_pos, 0, true);
+ }
}
}
@@ -511,6 +537,41 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio)
}
/*
+ * Create workqueue for deferred direct IO completions. We allocate the
+ * workqueue when it's first needed. This avoids creating workqueue for
+ * filesystems that don't need it and also allows us to create the workqueue
+ * late enough so the we can include s_id in the name of the workqueue.
+ */
+static int sb_init_dio_done_wq(struct super_block *sb)
+{
+ struct workqueue_struct *wq = alloc_workqueue("dio/%s",
+ WQ_MEM_RECLAIM, 0,
+ sb->s_id);
+ if (!wq)
+ return -ENOMEM;
+ /*
+ * This has to be atomic as more DIOs can race to create the workqueue
+ */
+ cmpxchg(&sb->s_dio_done_wq, NULL, wq);
+ /* Someone created workqueue before us? Free ours... */
+ if (wq != sb->s_dio_done_wq)
+ destroy_workqueue(wq);
+ return 0;
+}
+
+static int dio_set_defer_completion(struct dio *dio)
+{
+ struct super_block *sb = dio->inode->i_sb;
+
+ if (dio->defer_completion)
+ return 0;
+ dio->defer_completion = true;
+ if (!sb->s_dio_done_wq)
+ return sb_init_dio_done_wq(sb);
+ return 0;
+}
+
+/*
* Call into the fs to map some more disk blocks. We record the current number
* of available blocks at sdio->blocks_available. These are in units of the
* fs blocksize, (1 << inode->i_blkbits).
@@ -581,6 +642,9 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
/* Store for completion */
dio->private = map_bh->b_private;
+
+ if (ret == 0 && buffer_defer_completion(map_bh))
+ ret = dio_set_defer_completion(dio);
}
return ret;
}
@@ -1129,11 +1193,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
}
/*
- * Will be decremented at I/O completion time.
- */
- atomic_inc(&inode->i_dio_count);
-
- /*
* For file extending writes updating i_size before data
* writeouts complete can expose uninitialized blocks. So
* even for AIO, we need to wait for i/o to complete before
@@ -1141,11 +1200,33 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
*/
dio->is_async = !is_sync_kiocb(iocb) && !((rw & WRITE) &&
(end > i_size_read(inode)));
-
- retval = 0;
-
dio->inode = inode;
dio->rw = rw;
+
+ /*
+ * For AIO O_(D)SYNC writes we need to defer completions to a workqueue
+ * so that we can call ->fsync.
+ */
+ if (dio->is_async && (rw & WRITE) &&
+ ((iocb->ki_filp->f_flags & O_DSYNC) ||
+ IS_SYNC(iocb->ki_filp->f_mapping->host))) {
+ retval = dio_set_defer_completion(dio);
+ if (retval) {
+ /*
+ * We grab i_mutex only for reads so we don't have
+ * to release it here
+ */
+ kmem_cache_free(dio_cache, dio);
+ goto out;
+ }
+ }
+
+ /*
+ * Will be decremented at I/O completion time.
+ */
+ atomic_inc(&inode->i_dio_count);
+
+ retval = 0;
sdio.blkbits = blkbits;
sdio.blkfactor = i_blkbits - blkbits;
sdio.block_in_file = offset >> blkbits;
@@ -1269,7 +1350,6 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
if (drop_refcount(dio) == 0) {
retval = dio_complete(dio, offset, retval, false);
- kmem_cache_free(dio_cache, dio);
} else
BUG_ON(retval != -EIOCBQUEUED);
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 27a6ba9aaeec..0e90f0c91b93 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -267,10 +267,7 @@ void dlm_callback_work(struct work_struct *work)
int dlm_callback_start(struct dlm_ls *ls)
{
ls->ls_callback_wq = alloc_workqueue("dlm_callback",
- WQ_UNBOUND |
- WQ_MEM_RECLAIM |
- WQ_NON_REENTRANT,
- 0);
+ WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
if (!ls->ls_callback_wq) {
log_print("can't start dlm_callback workqueue");
return -ENOMEM;
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 911649a47dd5..142e21655eed 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -493,7 +493,6 @@ static ssize_t device_write(struct file *file, const char __user *buf,
{
struct dlm_user_proc *proc = file->private_data;
struct dlm_write_request *kbuf;
- sigset_t tmpsig, allsigs;
int error;
#ifdef CONFIG_COMPAT
@@ -557,9 +556,6 @@ static ssize_t device_write(struct file *file, const char __user *buf,
goto out_free;
}
- sigfillset(&allsigs);
- sigprocmask(SIG_BLOCK, &allsigs, &tmpsig);
-
error = -EINVAL;
switch (kbuf->cmd)
@@ -567,7 +563,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_LOCK:
if (!proc) {
log_print("no locking on control device");
- goto out_sig;
+ goto out_free;
}
error = device_user_lock(proc, &kbuf->i.lock);
break;
@@ -575,7 +571,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_UNLOCK:
if (!proc) {
log_print("no locking on control device");
- goto out_sig;
+ goto out_free;
}
error = device_user_unlock(proc, &kbuf->i.lock);
break;
@@ -583,7 +579,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_DEADLOCK:
if (!proc) {
log_print("no locking on control device");
- goto out_sig;
+ goto out_free;
}
error = device_user_deadlock(proc, &kbuf->i.lock);
break;
@@ -591,7 +587,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_CREATE_LOCKSPACE:
if (proc) {
log_print("create/remove only on control device");
- goto out_sig;
+ goto out_free;
}
error = device_create_lockspace(&kbuf->i.lspace);
break;
@@ -599,7 +595,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_REMOVE_LOCKSPACE:
if (proc) {
log_print("create/remove only on control device");
- goto out_sig;
+ goto out_free;
}
error = device_remove_lockspace(&kbuf->i.lspace);
break;
@@ -607,7 +603,7 @@ static ssize_t device_write(struct file *file, const char __user *buf,
case DLM_USER_PURGE:
if (!proc) {
log_print("no locking on control device");
- goto out_sig;
+ goto out_free;
}
error = device_user_purge(proc, &kbuf->i.purge);
break;
@@ -617,8 +613,6 @@ static ssize_t device_write(struct file *file, const char __user *buf,
kbuf->cmd);
}
- out_sig:
- sigprocmask(SIG_SETMASK, &tmpsig, NULL);
out_free:
kfree(kbuf);
return error;
@@ -659,15 +653,11 @@ static int device_close(struct inode *inode, struct file *file)
{
struct dlm_user_proc *proc = file->private_data;
struct dlm_ls *ls;
- sigset_t tmpsig, allsigs;
ls = dlm_find_lockspace_local(proc->lockspace);
if (!ls)
return -ENOENT;
- sigfillset(&allsigs);
- sigprocmask(SIG_BLOCK, &allsigs, &tmpsig);
-
set_bit(DLM_PROC_FLAGS_CLOSING, &proc->flags);
dlm_clear_proc_locks(ls, proc);
@@ -685,9 +675,6 @@ static int device_close(struct inode *inode, struct file *file)
/* FIXME: AUTOFREE: if this ls is no longer used do
device_remove_lockspace() */
- sigprocmask(SIG_SETMASK, &tmpsig, NULL);
- recalc_sigpending();
-
return 0;
}
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index f3913eb2c474..d15ccf20f1b3 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -57,7 +57,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
struct inode *inode;
inode = iget_locked(super, ino);
- if (IS_ERR(inode))
+ if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 9ad17b15b454..293f86741ddb 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1792,7 +1792,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
{
int error;
int did_lock_epmutex = 0;
- struct file *file, *tfile;
+ struct fd f, tf;
struct eventpoll *ep;
struct epitem *epi;
struct epoll_event epds;
@@ -1802,20 +1802,19 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
copy_from_user(&epds, event, sizeof(struct epoll_event)))
goto error_return;
- /* Get the "struct file *" for the eventpoll file */
error = -EBADF;
- file = fget(epfd);
- if (!file)
+ f = fdget(epfd);
+ if (!f.file)
goto error_return;
/* Get the "struct file *" for the target file */
- tfile = fget(fd);
- if (!tfile)
+ tf = fdget(fd);
+ if (!tf.file)
goto error_fput;
/* The target file descriptor must support poll */
error = -EPERM;
- if (!tfile->f_op || !tfile->f_op->poll)
+ if (!tf.file->f_op || !tf.file->f_op->poll)
goto error_tgt_fput;
/* Check if EPOLLWAKEUP is allowed */
@@ -1828,14 +1827,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
* adding an epoll file descriptor inside itself.
*/
error = -EINVAL;
- if (file == tfile || !is_file_epoll(file))
+ if (f.file == tf.file || !is_file_epoll(f.file))
goto error_tgt_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
- ep = file->private_data;
+ ep = f.file->private_data;
/*
* When we insert an epoll file descriptor, inside another epoll file
@@ -1854,14 +1853,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
did_lock_epmutex = 1;
}
if (op == EPOLL_CTL_ADD) {
- if (is_file_epoll(tfile)) {
+ if (is_file_epoll(tf.file)) {
error = -ELOOP;
- if (ep_loop_check(ep, tfile) != 0) {
+ if (ep_loop_check(ep, tf.file) != 0) {
clear_tfile_check_list();
goto error_tgt_fput;
}
} else
- list_add(&tfile->f_tfile_llink, &tfile_check_list);
+ list_add(&tf.file->f_tfile_llink, &tfile_check_list);
}
mutex_lock_nested(&ep->mtx, 0);
@@ -1871,14 +1870,14 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
* above, we can be sure to be able to use the item looked up by
* ep_find() till we release the mutex.
*/
- epi = ep_find(ep, tfile, fd);
+ epi = ep_find(ep, tf.file, fd);
error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD:
if (!epi) {
epds.events |= POLLERR | POLLHUP;
- error = ep_insert(ep, &epds, tfile, fd);
+ error = ep_insert(ep, &epds, tf.file, fd);
} else
error = -EEXIST;
clear_tfile_check_list();
@@ -1903,9 +1902,9 @@ error_tgt_fput:
if (did_lock_epmutex)
mutex_unlock(&epmutex);
- fput(tfile);
+ fdput(tf);
error_fput:
- fput(file);
+ fdput(f);
error_return:
return error;
diff --git a/fs/exec.c b/fs/exec.c
index 9c73def87642..fd774c7cb483 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -608,7 +608,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
return -ENOMEM;
lru_add_drain();
- tlb_gather_mmu(&tlb, mm, 0);
+ tlb_gather_mmu(&tlb, mm, old_start, old_end);
if (new_end > old_start) {
/*
* when the old and new regions overlap clear from new_end.
@@ -625,7 +625,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
free_pgd_range(&tlb, old_start, old_end, new_end,
vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
}
- tlb_finish_mmu(&tlb, new_end, old_end);
+ tlb_finish_mmu(&tlb, old_start, old_end);
/*
* Shrink the vma to just the new range. Always succeeds.
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index f522425aaa24..bafdd48eefde 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -41,7 +41,7 @@ static unsigned char get_dtype(struct super_block *sb, int filetype)
/**
* Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
* indexing).
*
* Return 1 if it is a dx dir, 0 if not
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index ddd715e42a5c..dc5d572ebd6a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -184,6 +184,7 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
int flex_bg = 0;
+ struct ext4_group_info *grp;
J_ASSERT_BH(bh, buffer_locked(bh));
@@ -191,11 +192,9 @@ void ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
* essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_group_clusters_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- ext4_block_bitmap_csum_set(sb, block_group, gdp, bh);
+ grp = ext4_get_group_info(sb, block_group);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
memset(bh->b_data, 0, sb->s_blocksize);
@@ -305,7 +304,7 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
*/
static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
- unsigned int block_group,
+ ext4_group_t block_group,
struct buffer_head *bh)
{
ext4_grpblk_t offset;
@@ -352,10 +351,11 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
void ext4_validate_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
- unsigned int block_group,
+ ext4_group_t block_group,
struct buffer_head *bh)
{
ext4_fsblk_t blk;
+ struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
if (buffer_verified(bh))
return;
@@ -366,12 +366,14 @@ void ext4_validate_block_bitmap(struct super_block *sb,
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: block %llu: invalid block bitmap",
block_group, blk);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
desc, bh))) {
ext4_unlock_group(sb, block_group);
ext4_error(sb, "bg %u: bad block bitmap checksum", block_group);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
return;
}
set_buffer_verified(bh);
@@ -445,7 +447,10 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
return bh;
verify:
ext4_validate_block_bitmap(sb, desc, block_group, bh);
- return bh;
+ if (buffer_verified(bh))
+ return bh;
+ put_bh(bh);
+ return NULL;
}
/* Returns 0 on success, 1 on error */
@@ -469,7 +474,8 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
clear_buffer_new(bh);
/* Panic or remount fs read-only if block bitmap is invalid */
ext4_validate_block_bitmap(sb, desc, block_group, bh);
- return 0;
+ /* ...but check for error just in case errors=continue. */
+ return !buffer_verified(bh);
}
struct buffer_head *
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 3c7d288ae94c..680bb3388919 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -33,7 +33,7 @@ static int ext4_dx_readdir(struct file *, struct dir_context *);
/**
* Check if the given dir-inode refers to an htree-indexed directory
- * (or a directory which chould potentially get coverted to use htree
+ * (or a directory which could potentially get converted to use htree
* indexing).
*
* Return 1 if it is a dx dir, 0 if not
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b577e45425b0..af815ea9d7cc 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -180,7 +180,6 @@ struct ext4_map_blocks {
* Flags for ext4_io_end->flags
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
-#define EXT4_IO_END_DIRECT 0x0002
/*
* For converting uninitialized extents on a work queue. 'handle' is used for
@@ -196,8 +195,6 @@ typedef struct ext4_io_end {
unsigned int flag; /* unwritten or not */
loff_t offset; /* offset in the file */
ssize_t size; /* size of the extent */
- struct kiocb *iocb; /* iocb struct for AIO */
- int result; /* error value for AIO */
atomic_t count; /* reference counter */
} ext4_io_end_t;
@@ -561,6 +558,18 @@ enum {
#define EXT4_GET_BLOCKS_NO_PUT_HOLE 0x0200
/*
+ * The bit position of these flags must not overlap with any of the
+ * EXT4_GET_BLOCKS_*. They are used by ext4_ext_find_extent(),
+ * read_extent_tree_block(), ext4_split_extent_at(),
+ * ext4_ext_insert_extent(), and ext4_ext_create_new_leaf().
+ * EXT4_EX_NOCACHE is used to indicate that the we shouldn't be
+ * caching the extents when reading from the extent tree while a
+ * truncate or punch hole operation is in progress.
+ */
+#define EXT4_EX_NOCACHE 0x0400
+#define EXT4_EX_FORCE_CACHE 0x0800
+
+/*
* Flags used by ext4_free_blocks
*/
#define EXT4_FREE_BLOCKS_METADATA 0x0001
@@ -569,6 +578,7 @@ enum {
#define EXT4_FREE_BLOCKS_NO_QUOT_UPDATE 0x0008
#define EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER 0x0010
#define EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER 0x0020
+#define EXT4_FREE_BLOCKS_RESERVE 0x0040
/*
* ioctl commands
@@ -590,6 +600,7 @@ enum {
#define EXT4_IOC_MOVE_EXT _IOWR('f', 15, struct move_extent)
#define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64)
#define EXT4_IOC_SWAP_BOOT _IO('f', 17)
+#define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18)
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
@@ -900,11 +911,9 @@ struct ext4_inode_info {
* Completed IOs that need unwritten extents handling and don't have
* transaction reserved
*/
- struct list_head i_unrsv_conversion_list;
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
atomic_t i_unwritten; /* Nr. of inflight conversions pending */
struct work_struct i_rsv_conversion_work;
- struct work_struct i_unrsv_conversion_work;
spinlock_t i_block_reservation_lock;
@@ -1276,8 +1285,6 @@ struct ext4_sb_info {
struct flex_groups *s_flex_groups;
ext4_group_t s_flex_groups_allocated;
- /* workqueue for unreserved extent convertions (dio) */
- struct workqueue_struct *unrsv_conversion_wq;
/* workqueue for reserved extent conversions (buffered io) */
struct workqueue_struct *rsv_conversion_wq;
@@ -1340,9 +1347,6 @@ static inline void ext4_set_io_unwritten_flag(struct inode *inode,
struct ext4_io_end *io_end)
{
if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
- /* Writeback has to have coversion transaction reserved */
- WARN_ON(EXT4_SB(inode->i_sb)->s_journal && !io_end->handle &&
- !(io_end->flag & EXT4_IO_END_DIRECT));
io_end->flag |= EXT4_IO_END_UNWRITTEN;
atomic_inc(&EXT4_I(inode)->i_unwritten);
}
@@ -1375,6 +1379,7 @@ enum {
nolocking */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
EXT4_STATE_ORDERED_MODE, /* data=ordered mode */
+ EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
};
#define EXT4_INODE_BIT_FNS(name, field, offset) \
@@ -1915,7 +1920,7 @@ extern ext4_group_t ext4_get_group_number(struct super_block *sb,
extern void ext4_validate_block_bitmap(struct super_block *sb,
struct ext4_group_desc *desc,
- unsigned int block_group,
+ ext4_group_t block_group,
struct buffer_head *bh);
extern unsigned int ext4_block_group(struct super_block *sb,
ext4_fsblk_t blocknr);
@@ -2086,6 +2091,7 @@ extern int ext4_sync_inode(handle_t *, struct inode *);
extern void ext4_dirty_inode(struct inode *, int);
extern int ext4_change_inode_journal_flag(struct inode *, int);
extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_inode_attach_jinode(struct inode *inode);
extern int ext4_can_truncate(struct inode *inode);
extern void ext4_truncate(struct inode *);
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
@@ -2416,16 +2422,32 @@ do { \
#define EXT4_FREECLUSTERS_WATERMARK 0
#endif
+/* Update i_disksize. Requires i_mutex to avoid races with truncate */
static inline void ext4_update_i_disksize(struct inode *inode, loff_t newsize)
{
- /*
- * XXX: replace with spinlock if seen contended -bzzz
- */
+ WARN_ON_ONCE(S_ISREG(inode->i_mode) &&
+ !mutex_is_locked(&inode->i_mutex));
down_write(&EXT4_I(inode)->i_data_sem);
if (newsize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = newsize;
up_write(&EXT4_I(inode)->i_data_sem);
- return ;
+}
+
+/*
+ * Update i_disksize after writeback has been started. Races with truncate
+ * are avoided by checking i_size under i_data_sem.
+ */
+static inline void ext4_wb_update_i_disksize(struct inode *inode, loff_t newsize)
+{
+ loff_t i_size;
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ i_size = i_size_read(inode);
+ if (newsize > i_size)
+ newsize = i_size;
+ if (newsize > EXT4_I(inode)->i_disksize)
+ EXT4_I(inode)->i_disksize = newsize;
+ up_write(&EXT4_I(inode)->i_data_sem);
}
struct ext4_group_info {
@@ -2448,9 +2470,15 @@ struct ext4_group_info {
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
+#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
+#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
#define EXT4_MB_GRP_NEED_INIT(grp) \
(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_BBITMAP_CORRUPT(grp) \
+ (test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \
+ (test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
(test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
@@ -2654,6 +2682,12 @@ extern int ext4_check_blockref(const char *, unsigned int,
struct ext4_ext_path;
struct ext4_extent;
+/*
+ * Maximum number of logical blocks in a file; ext4_extent's ee_block is
+ * __le32.
+ */
+#define EXT_MAX_BLOCKS 0xffffffff
+
extern int ext4_ext_tree_init(handle_t *handle, struct inode *);
extern int ext4_ext_writepage_trans_blocks(struct inode *, int);
extern int ext4_ext_index_trans_blocks(struct inode *inode, int extents);
@@ -2683,7 +2717,8 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *,
struct ext4_ext_path *,
struct ext4_extent *, int);
extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
- struct ext4_ext_path *);
+ struct ext4_ext_path *,
+ int flags);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
extern int ext4_find_delalloc_range(struct inode *inode,
@@ -2692,7 +2727,7 @@ extern int ext4_find_delalloc_range(struct inode *inode,
extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
-
+extern int ext4_ext_precache(struct inode *inode);
/* move_extent.c */
extern void ext4_double_down_write_data_sem(struct inode *first,
@@ -2715,7 +2750,6 @@ extern void ext4_put_io_end_defer(ext4_io_end_t *io_end);
extern void ext4_io_submit_init(struct ext4_io_submit *io,
struct writeback_control *wbc);
extern void ext4_end_io_rsv_work(struct work_struct *work);
-extern void ext4_end_io_unrsv_work(struct work_struct *work);
extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 51bc821ade90..5074fe23f19e 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -134,12 +134,6 @@ struct ext4_ext_path {
*/
/*
- * Maximum number of logical blocks in a file; ext4_extent's ee_block is
- * __le32.
- */
-#define EXT_MAX_BLOCKS 0xffffffff
-
-/*
* EXT_INIT_MAX_LEN is the maximum number of blocks we can have in an
* initialized extent. This is 2^15 and not (2^16 - 1), since we use the
* MSB of ee_len field in the extent datastructure to signify if this
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 72a3600aedbd..17ac112ab101 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -255,10 +255,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
set_buffer_prio(bh);
if (ext4_handle_valid(handle)) {
err = jbd2_journal_dirty_metadata(handle, bh);
- if (err) {
- /* Errors can only happen if there is a bug */
- handle->h_err = err;
- __ext4_journal_stop(where, line, handle);
+ /* Errors can only happen if there is a bug */
+ if (WARN_ON_ONCE(err)) {
+ ext4_journal_abort_handle(where, line, __func__, bh,
+ handle, err);
}
} else {
if (inode)
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 2877258d9497..81cfefa9dc0c 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -197,7 +197,7 @@ static inline void ext4_journal_callback_add(handle_t *handle,
* ext4_journal_callback_del: delete a registered callback
* @handle: active journal transaction handle on which callback was registered
* @jce: registered journal callback entry to unregister
- * Return true if object was sucessfully removed
+ * Return true if object was successfully removed
*/
static inline bool ext4_journal_callback_try_del(handle_t *handle,
struct ext4_journal_cb_entry *jce)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a61873808f76..54d52afcdb19 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -407,7 +407,7 @@ static int ext4_valid_extent_entries(struct inode *inode,
static int __ext4_ext_check(const char *function, unsigned int line,
struct inode *inode, struct ext4_extent_header *eh,
- int depth)
+ int depth, ext4_fsblk_t pblk)
{
const char *error_msg;
int max = 0;
@@ -447,42 +447,149 @@ static int __ext4_ext_check(const char *function, unsigned int line,
corrupted:
ext4_error_inode(inode, function, line, 0,
- "bad header/extent: %s - magic %x, "
- "entries %u, max %u(%u), depth %u(%u)",
- error_msg, le16_to_cpu(eh->eh_magic),
- le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
- max, le16_to_cpu(eh->eh_depth), depth);
-
+ "pblk %llu bad header/extent: %s - magic %x, "
+ "entries %u, max %u(%u), depth %u(%u)",
+ (unsigned long long) pblk, error_msg,
+ le16_to_cpu(eh->eh_magic),
+ le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max),
+ max, le16_to_cpu(eh->eh_depth), depth);
return -EIO;
}
-#define ext4_ext_check(inode, eh, depth) \
- __ext4_ext_check(__func__, __LINE__, inode, eh, depth)
+#define ext4_ext_check(inode, eh, depth, pblk) \
+ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk))
int ext4_ext_check_inode(struct inode *inode)
{
- return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode));
+ return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0);
}
-static int __ext4_ext_check_block(const char *function, unsigned int line,
- struct inode *inode,
- struct ext4_extent_header *eh,
- int depth,
- struct buffer_head *bh)
+static struct buffer_head *
+__read_extent_tree_block(const char *function, unsigned int line,
+ struct inode *inode, ext4_fsblk_t pblk, int depth,
+ int flags)
{
- int ret;
+ struct buffer_head *bh;
+ int err;
- if (buffer_verified(bh))
- return 0;
- ret = ext4_ext_check(inode, eh, depth);
- if (ret)
- return ret;
+ bh = sb_getblk(inode->i_sb, pblk);
+ if (unlikely(!bh))
+ return ERR_PTR(-ENOMEM);
+
+ if (!bh_uptodate_or_lock(bh)) {
+ trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
+ err = bh_submit_read(bh);
+ if (err < 0)
+ goto errout;
+ }
+ if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
+ return bh;
+ err = __ext4_ext_check(function, line, inode,
+ ext_block_hdr(bh), depth, pblk);
+ if (err)
+ goto errout;
set_buffer_verified(bh);
- return ret;
+ /*
+ * If this is a leaf block, cache all of its entries
+ */
+ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) {
+ struct ext4_extent_header *eh = ext_block_hdr(bh);
+ struct ext4_extent *ex = EXT_FIRST_EXTENT(eh);
+ ext4_lblk_t prev = 0;
+ int i;
+
+ for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) {
+ unsigned int status = EXTENT_STATUS_WRITTEN;
+ ext4_lblk_t lblk = le32_to_cpu(ex->ee_block);
+ int len = ext4_ext_get_actual_len(ex);
+
+ if (prev && (prev != lblk))
+ ext4_es_cache_extent(inode, prev,
+ lblk - prev, ~0,
+ EXTENT_STATUS_HOLE);
+
+ if (ext4_ext_is_uninitialized(ex))
+ status = EXTENT_STATUS_UNWRITTEN;
+ ext4_es_cache_extent(inode, lblk, len,
+ ext4_ext_pblock(ex), status);
+ prev = lblk + len;
+ }
+ }
+ return bh;
+errout:
+ put_bh(bh);
+ return ERR_PTR(err);
+
}
-#define ext4_ext_check_block(inode, eh, depth, bh) \
- __ext4_ext_check_block(__func__, __LINE__, inode, eh, depth, bh)
+#define read_extent_tree_block(inode, pblk, depth, flags) \
+ __read_extent_tree_block(__func__, __LINE__, (inode), (pblk), \
+ (depth), (flags))
+
+/*
+ * This function is called to cache a file's extent information in the
+ * extent status tree
+ */
+int ext4_ext_precache(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct ext4_ext_path *path = NULL;
+ struct buffer_head *bh;
+ int i = 0, depth, ret = 0;
+
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ return 0; /* not an extent-mapped inode */
+
+ down_read(&ei->i_data_sem);
+ depth = ext_depth(inode);
+
+ path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+ GFP_NOFS);
+ if (path == NULL) {
+ up_read(&ei->i_data_sem);
+ return -ENOMEM;
+ }
+
+ /* Don't cache anything if there are no external extent blocks */
+ if (depth == 0)
+ goto out;
+ path[0].p_hdr = ext_inode_hdr(inode);
+ ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
+ if (ret)
+ goto out;
+ path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr);
+ while (i >= 0) {
+ /*
+ * If this is a leaf block or we've reached the end of
+ * the index block, go up
+ */
+ if ((i == depth) ||
+ path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) {
+ brelse(path[i].p_bh);
+ path[i].p_bh = NULL;
+ i--;
+ continue;
+ }
+ bh = read_extent_tree_block(inode,
+ ext4_idx_pblock(path[i].p_idx++),
+ depth - i - 1,
+ EXT4_EX_FORCE_CACHE);
+ if (IS_ERR(bh)) {
+ ret = PTR_ERR(bh);
+ break;
+ }
+ i++;
+ path[i].p_bh = bh;
+ path[i].p_hdr = ext_block_hdr(bh);
+ path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr);
+ }
+ ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
+out:
+ up_read(&ei->i_data_sem);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ return ret;
+}
#ifdef EXT_DEBUG
static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
@@ -716,7 +823,7 @@ int ext4_ext_tree_init(handle_t *handle, struct inode *inode)
struct ext4_ext_path *
ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
- struct ext4_ext_path *path)
+ struct ext4_ext_path *path, int flags)
{
struct ext4_extent_header *eh;
struct buffer_head *bh;
@@ -748,20 +855,13 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
path[ppos].p_depth = i;
path[ppos].p_ext = NULL;
- bh = sb_getblk(inode->i_sb, path[ppos].p_block);
- if (unlikely(!bh)) {
- ret = -ENOMEM;
+ bh = read_extent_tree_block(inode, path[ppos].p_block, --i,
+ flags);
+ if (IS_ERR(bh)) {
+ ret = PTR_ERR(bh);
goto err;
}
- if (!bh_uptodate_or_lock(bh)) {
- trace_ext4_ext_load_extent(inode, block,
- path[ppos].p_block);
- ret = bh_submit_read(bh);
- if (ret < 0) {
- put_bh(bh);
- goto err;
- }
- }
+
eh = ext_block_hdr(bh);
ppos++;
if (unlikely(ppos > depth)) {
@@ -773,11 +873,6 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
}
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
- i--;
-
- ret = ext4_ext_check_block(inode, eh, i, bh);
- if (ret < 0)
- goto err;
}
path[ppos].p_depth = i;
@@ -1198,7 +1293,8 @@ out:
* if no free index is found, then it requests in-depth growing.
*/
static int ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode,
- unsigned int flags,
+ unsigned int mb_flags,
+ unsigned int gb_flags,
struct ext4_ext_path *path,
struct ext4_extent *newext)
{
@@ -1220,7 +1316,7 @@ repeat:
if (EXT_HAS_FREE_INDEX(curp)) {
/* if we found index with free entry, then use that
* entry: create all needed subtree and add new leaf */
- err = ext4_ext_split(handle, inode, flags, path, newext, i);
+ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i);
if (err)
goto out;
@@ -1228,12 +1324,12 @@ repeat:
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path);
+ path, gb_flags);
if (IS_ERR(path))
err = PTR_ERR(path);
} else {
/* tree is full, time to grow in depth */
- err = ext4_ext_grow_indepth(handle, inode, flags, newext);
+ err = ext4_ext_grow_indepth(handle, inode, mb_flags, newext);
if (err)
goto out;
@@ -1241,7 +1337,7 @@ repeat:
ext4_ext_drop_refs(path);
path = ext4_ext_find_extent(inode,
(ext4_lblk_t)le32_to_cpu(newext->ee_block),
- path);
+ path, gb_flags);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -1412,29 +1508,21 @@ got_index:
ix++;
block = ext4_idx_pblock(ix);
while (++depth < path->p_depth) {
- bh = sb_bread(inode->i_sb, block);
- if (bh == NULL)
- return -EIO;
- eh = ext_block_hdr(bh);
/* subtract from p_depth to get proper eh_depth */
- if (ext4_ext_check_block(inode, eh,
- path->p_depth - depth, bh)) {
- put_bh(bh);
- return -EIO;
- }
+ bh = read_extent_tree_block(inode, block,
+ path->p_depth - depth, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
+ eh = ext_block_hdr(bh);
ix = EXT_FIRST_INDEX(eh);
block = ext4_idx_pblock(ix);
put_bh(bh);
}
- bh = sb_bread(inode->i_sb, block);
- if (bh == NULL)
- return -EIO;
+ bh = read_extent_tree_block(inode, block, path->p_depth - depth, 0);
+ if (IS_ERR(bh))
+ return PTR_ERR(bh);
eh = ext_block_hdr(bh);
- if (ext4_ext_check_block(inode, eh, path->p_depth - depth, bh)) {
- put_bh(bh);
- return -EIO;
- }
ex = EXT_FIRST_EXTENT(eh);
found_extent:
*logical = le32_to_cpu(ex->ee_block);
@@ -1705,7 +1793,8 @@ static void ext4_ext_try_to_merge_up(handle_t *handle,
brelse(path[1].p_bh);
ext4_free_blocks(handle, inode, NULL, blk, 1,
- EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
+ EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET |
+ EXT4_FREE_BLOCKS_RESERVE);
}
/*
@@ -1793,7 +1882,7 @@ out:
*/
int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
struct ext4_ext_path *path,
- struct ext4_extent *newext, int flag)
+ struct ext4_extent *newext, int gb_flags)
{
struct ext4_extent_header *eh;
struct ext4_extent *ex, *fex;
@@ -1802,7 +1891,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
int depth, len, err;
ext4_lblk_t next;
unsigned uninitialized = 0;
- int flags = 0;
+ int mb_flags = 0;
if (unlikely(ext4_ext_get_actual_len(newext) == 0)) {
EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0");
@@ -1817,7 +1906,7 @@ int ext4_ext_insert_extent(handle_t *handle, struct inode *inode,
}
/* try to insert block into found extent and return */
- if (ex && !(flag & EXT4_GET_BLOCKS_PRE_IO)) {
+ if (ex && !(gb_flags & EXT4_GET_BLOCKS_PRE_IO)) {
/*
* Try to see whether we should rather test the extent on
@@ -1920,7 +2009,7 @@ prepend:
if (next != EXT_MAX_BLOCKS) {
ext_debug("next leaf block - %u\n", next);
BUG_ON(npath != NULL);
- npath = ext4_ext_find_extent(inode, next, NULL);
+ npath = ext4_ext_find_extent(inode, next, NULL, 0);
if (IS_ERR(npath))
return PTR_ERR(npath);
BUG_ON(npath->p_depth != path->p_depth);
@@ -1939,9 +2028,10 @@ prepend:
* There is no free space in the found leaf.
* We're gonna add a new leaf in the tree.
*/
- if (flag & EXT4_GET_BLOCKS_METADATA_NOFAIL)
- flags = EXT4_MB_USE_RESERVED;
- err = ext4_ext_create_new_leaf(handle, inode, flags, path, newext);
+ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL)
+ mb_flags = EXT4_MB_USE_RESERVED;
+ err = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags,
+ path, newext);
if (err)
goto cleanup;
depth = ext_depth(inode);
@@ -2007,7 +2097,7 @@ has_space:
merge:
/* try to merge extents */
- if (!(flag & EXT4_GET_BLOCKS_PRE_IO))
+ if (!(gb_flags & EXT4_GET_BLOCKS_PRE_IO))
ext4_ext_try_to_merge(handle, inode, path, nearex);
@@ -2050,7 +2140,7 @@ static int ext4_fill_fiemap_extents(struct inode *inode,
path = NULL;
}
- path = ext4_ext_find_extent(inode, block, path);
+ path = ext4_ext_find_extent(inode, block, path, 0);
if (IS_ERR(path)) {
up_read(&EXT4_I(inode)->i_data_sem);
err = PTR_ERR(path);
@@ -2195,8 +2285,8 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
ext4_lblk_t block)
{
int depth = ext_depth(inode);
- unsigned long len;
- ext4_lblk_t lblock;
+ unsigned long len = 0;
+ ext4_lblk_t lblock = 0;
struct ext4_extent *ex;
ex = path[depth].p_ext;
@@ -2233,7 +2323,6 @@ ext4_ext_put_gap_in_cache(struct inode *inode, struct ext4_ext_path *path,
ext4_es_insert_extent(inode, lblock, len, ~0,
EXTENT_STATUS_HOLE);
} else {
- lblock = len = 0;
BUG();
}
@@ -2712,7 +2801,7 @@ again:
ext4_lblk_t ee_block;
/* find extent for this block */
- path = ext4_ext_find_extent(inode, end, NULL);
+ path = ext4_ext_find_extent(inode, end, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path)) {
ext4_journal_stop(handle);
return PTR_ERR(path);
@@ -2754,6 +2843,7 @@ again:
*/
err = ext4_split_extent_at(handle, inode, path,
end + 1, split_flag,
+ EXT4_EX_NOCACHE |
EXT4_GET_BLOCKS_PRE_IO |
EXT4_GET_BLOCKS_METADATA_NOFAIL);
@@ -2782,7 +2872,7 @@ again:
path[0].p_hdr = ext_inode_hdr(inode);
i = 0;
- if (ext4_ext_check(inode, path[0].p_hdr, depth)) {
+ if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) {
err = -EIO;
goto out;
}
@@ -2829,10 +2919,12 @@ again:
ext_debug("move to level %d (block %llu)\n",
i + 1, ext4_idx_pblock(path[i].p_idx));
memset(path + i + 1, 0, sizeof(*path));
- bh = sb_bread(sb, ext4_idx_pblock(path[i].p_idx));
- if (!bh) {
+ bh = read_extent_tree_block(inode,
+ ext4_idx_pblock(path[i].p_idx), depth - i - 1,
+ EXT4_EX_NOCACHE);
+ if (IS_ERR(bh)) {
/* should we reset i_size? */
- err = -EIO;
+ err = PTR_ERR(bh);
break;
}
/* Yield here to deal with large extent trees.
@@ -2842,11 +2934,6 @@ again:
err = -EIO;
break;
}
- if (ext4_ext_check_block(inode, ext_block_hdr(bh),
- depth - i - 1, bh)) {
- err = -EIO;
- break;
- }
path[i + 1].p_bh = bh;
/* save actual number of indexes since this
@@ -2961,6 +3048,23 @@ void ext4_ext_release(struct super_block *sb)
#endif
}
+static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
+{
+ ext4_lblk_t ee_block;
+ ext4_fsblk_t ee_pblock;
+ unsigned int ee_len;
+
+ ee_block = le32_to_cpu(ex->ee_block);
+ ee_len = ext4_ext_get_actual_len(ex);
+ ee_pblock = ext4_ext_pblock(ex);
+
+ if (ee_len == 0)
+ return 0;
+
+ return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+ EXTENT_STATUS_WRITTEN);
+}
+
/* FIXME!! we need to try to merge to left or right after zero-out */
static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex)
{
@@ -3113,7 +3217,7 @@ static int ext4_split_extent_at(handle_t *handle,
goto fix_extent_len;
/* update extent status tree */
- err = ext4_es_zeroout(inode, &zero_ex);
+ err = ext4_zeroout_es(inode, &zero_ex);
goto out;
} else if (err)
@@ -3133,7 +3237,7 @@ fix_extent_len:
* ext4_split_extents() splits an extent and mark extent which is covered
* by @map as split_flags indicates
*
- * It may result in splitting the extent into multiple extents (upto three)
+ * It may result in splitting the extent into multiple extents (up to three)
* There are three possibilities:
* a> There is no split required
* b> Splits in two extents: Split is happening at either end of the extent
@@ -3181,7 +3285,7 @@ static int ext4_split_extent(handle_t *handle,
* result in split of original leaf or extent zeroout.
*/
ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
if (IS_ERR(path))
return PTR_ERR(path);
depth = ext_depth(inode);
@@ -3464,7 +3568,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
out:
/* If we have gotten a failure, don't zero out status tree */
if (!err)
- err = ext4_es_zeroout(inode, &zero_ex);
+ err = ext4_zeroout_es(inode, &zero_ex);
return err ? err : allocated;
}
@@ -3565,7 +3669,7 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
if (err < 0)
goto out;
ext4_ext_drop_refs(path);
- path = ext4_ext_find_extent(inode, map->m_lblk, path);
+ path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
goto out;
@@ -4052,7 +4156,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
/* find extent for this block */
- path = ext4_ext_find_extent(inode, map->m_lblk, NULL);
+ path = ext4_ext_find_extent(inode, map->m_lblk, NULL, 0);
if (IS_ERR(path)) {
err = PTR_ERR(path);
path = NULL;
@@ -4412,7 +4516,7 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
retry:
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
- if (err == ENOMEM) {
+ if (err == -ENOMEM) {
cond_resched();
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
@@ -4744,6 +4848,12 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
return error;
}
+ if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+ error = ext4_ext_precache(inode);
+ if (error)
+ return error;
+ }
+
/* fallback to generic here if not in extents fmt */
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return generic_block_fiemap(inode, fieinfo, start, len,
@@ -4771,6 +4881,6 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
error = ext4_fill_fiemap_extents(inode, start_blk,
len_blks, fieinfo);
}
-
+ ext4_es_lru_add(inode);
return error;
}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 91cb110da1b4..2d1bdbe78c04 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -13,7 +13,6 @@
#include <linux/list_sort.h>
#include "ext4.h"
#include "extents_status.h"
-#include "ext4_extents.h"
#include <trace/events/ext4.h>
@@ -263,7 +262,7 @@ void ext4_es_find_delayed_extent_range(struct inode *inode,
if (tree->cache_es) {
es1 = tree->cache_es;
if (in_range(lblk, es1->es_lblk, es1->es_len)) {
- es_debug("%u cached by [%u/%u) %llu %llx\n",
+ es_debug("%u cached by [%u/%u) %llu %x\n",
lblk, es1->es_lblk, es1->es_len,
ext4_es_pblock(es1), ext4_es_status(es1));
goto out;
@@ -409,6 +408,8 @@ ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
}
#ifdef ES_AGGRESSIVE_TEST
+#include "ext4_extents.h" /* Needed when ES_AGGRESSIVE_TEST is defined */
+
static void ext4_es_insert_extent_ext_check(struct inode *inode,
struct extent_status *es)
{
@@ -419,7 +420,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
unsigned short ee_len;
int depth, ee_status, es_status;
- path = ext4_ext_find_extent(inode, es->es_lblk, NULL);
+ path = ext4_ext_find_extent(inode, es->es_lblk, NULL, EXT4_EX_NOCACHE);
if (IS_ERR(path))
return;
@@ -641,13 +642,13 @@ out:
*/
int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned long long status)
+ unsigned int status)
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
int err = 0;
- es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n",
+ es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
lblk, len, pblk, status, inode->i_ino);
if (!len)
@@ -684,6 +685,38 @@ error:
}
/*
+ * ext4_es_cache_extent() inserts information into the extent status
+ * tree if and only if there isn't information about the range in
+ * question already.
+ */
+void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status)
+{
+ struct extent_status *es;
+ struct extent_status newes;
+ ext4_lblk_t end = lblk + len - 1;
+
+ newes.es_lblk = lblk;
+ newes.es_len = len;
+ ext4_es_store_pblock(&newes, pblk);
+ ext4_es_store_status(&newes, status);
+ trace_ext4_es_cache_extent(inode, &newes);
+
+ if (!len)
+ return;
+
+ BUG_ON(end < lblk);
+
+ write_lock(&EXT4_I(inode)->i_es_lock);
+
+ es = __es_tree_search(&EXT4_I(inode)->i_es_tree.root, lblk);
+ if (!es || es->es_lblk > end)
+ __es_insert_extent(inode, &newes);
+ write_unlock(&EXT4_I(inode)->i_es_lock);
+}
+
+/*
* ext4_es_lookup_extent() looks up an extent in extent status tree.
*
* ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
@@ -871,23 +904,6 @@ int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
return err;
}
-int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
-{
- ext4_lblk_t ee_block;
- ext4_fsblk_t ee_pblock;
- unsigned int ee_len;
-
- ee_block = le32_to_cpu(ex->ee_block);
- ee_len = ext4_ext_get_actual_len(ex);
- ee_pblock = ext4_ext_pblock(ex);
-
- if (ee_len == 0)
- return 0;
-
- return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
- EXTENT_STATUS_WRITTEN);
-}
-
static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
struct list_head *b)
{
@@ -895,6 +911,12 @@ static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
eia = list_entry(a, struct ext4_inode_info, i_es_lru);
eib = list_entry(b, struct ext4_inode_info, i_es_lru);
+ if (ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
+ !ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
+ return 1;
+ if (!ext4_test_inode_state(&eia->vfs_inode, EXT4_STATE_EXT_PRECACHED) &&
+ ext4_test_inode_state(&eib->vfs_inode, EXT4_STATE_EXT_PRECACHED))
+ return -1;
if (eia->i_touch_when == eib->i_touch_when)
return 0;
if (time_after(eia->i_touch_when, eib->i_touch_when))
@@ -908,21 +930,13 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
{
struct ext4_inode_info *ei;
struct list_head *cur, *tmp;
- LIST_HEAD(skiped);
+ LIST_HEAD(skipped);
int ret, nr_shrunk = 0;
+ int retried = 0, skip_precached = 1, nr_skipped = 0;
spin_lock(&sbi->s_es_lru_lock);
- /*
- * If the inode that is at the head of LRU list is newer than
- * last_sorted time, that means that we need to sort this list.
- */
- ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info, i_es_lru);
- if (sbi->s_es_last_sorted < ei->i_touch_when) {
- list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
- sbi->s_es_last_sorted = jiffies;
- }
-
+retry:
list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
/*
* If we have already reclaimed all extents from extent
@@ -933,9 +947,16 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
ei = list_entry(cur, struct ext4_inode_info, i_es_lru);
- /* Skip the inode that is newer than the last_sorted time */
- if (sbi->s_es_last_sorted < ei->i_touch_when) {
- list_move_tail(cur, &skiped);
+ /*
+ * Skip the inode that is newer than the last_sorted
+ * time. Normally we try hard to avoid shrinking
+ * precached inodes, but we will as a last resort.
+ */
+ if ((sbi->s_es_last_sorted < ei->i_touch_when) ||
+ (skip_precached && ext4_test_inode_state(&ei->vfs_inode,
+ EXT4_STATE_EXT_PRECACHED))) {
+ nr_skipped++;
+ list_move_tail(cur, &skipped);
continue;
}
@@ -955,11 +976,33 @@ static int __ext4_es_shrink(struct ext4_sb_info *sbi, int nr_to_scan,
}
/* Move the newer inodes into the tail of the LRU list. */
- list_splice_tail(&skiped, &sbi->s_es_lru);
+ list_splice_tail(&skipped, &sbi->s_es_lru);
+ INIT_LIST_HEAD(&skipped);
+
+ /*
+ * If we skipped any inodes, and we weren't able to make any
+ * forward progress, sort the list and try again.
+ */
+ if ((nr_shrunk == 0) && nr_skipped && !retried) {
+ retried++;
+ list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
+ sbi->s_es_last_sorted = jiffies;
+ ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info,
+ i_es_lru);
+ /*
+ * If there are no non-precached inodes left on the
+ * list, start releasing precached extents.
+ */
+ if (ext4_test_inode_state(&ei->vfs_inode,
+ EXT4_STATE_EXT_PRECACHED))
+ skip_precached = 0;
+ goto retry;
+ }
+
spin_unlock(&sbi->s_es_lru_lock);
if (locked_ei && nr_shrunk == 0)
- nr_shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan);
+ nr_shrunk = __es_try_to_reclaim_extents(locked_ei, nr_to_scan);
return nr_shrunk;
}
@@ -1034,10 +1077,16 @@ static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
struct rb_node *node;
struct extent_status *es;
int nr_shrunk = 0;
+ static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
+ DEFAULT_RATELIMIT_BURST);
if (ei->i_es_lru_nr == 0)
return 0;
+ if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED) &&
+ __ratelimit(&_rs))
+ ext4_warning(inode->i_sb, "forced shrink of precached extents");
+
node = rb_first(&tree->root);
while (node != NULL) {
es = rb_entry(node, struct extent_status, rb_node);
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index e936730cc5b0..167f4ab8ecc3 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -29,16 +29,26 @@
/*
* These flags live in the high bits of extent_status.es_pblk
*/
-#define EXTENT_STATUS_WRITTEN (1ULL << 63)
-#define EXTENT_STATUS_UNWRITTEN (1ULL << 62)
-#define EXTENT_STATUS_DELAYED (1ULL << 61)
-#define EXTENT_STATUS_HOLE (1ULL << 60)
+#define ES_SHIFT 60
+
+#define EXTENT_STATUS_WRITTEN (1 << 3)
+#define EXTENT_STATUS_UNWRITTEN (1 << 2)
+#define EXTENT_STATUS_DELAYED (1 << 1)
+#define EXTENT_STATUS_HOLE (1 << 0)
#define EXTENT_STATUS_FLAGS (EXTENT_STATUS_WRITTEN | \
EXTENT_STATUS_UNWRITTEN | \
EXTENT_STATUS_DELAYED | \
EXTENT_STATUS_HOLE)
+#define ES_WRITTEN (1ULL << 63)
+#define ES_UNWRITTEN (1ULL << 62)
+#define ES_DELAYED (1ULL << 61)
+#define ES_HOLE (1ULL << 60)
+
+#define ES_MASK (ES_WRITTEN | ES_UNWRITTEN | \
+ ES_DELAYED | ES_HOLE)
+
struct ext4_sb_info;
struct ext4_extent;
@@ -60,7 +70,10 @@ extern void ext4_es_init_tree(struct ext4_es_tree *tree);
extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned long long status);
+ unsigned int status);
+extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status);
extern int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len);
extern void ext4_es_find_delayed_extent_range(struct inode *inode,
@@ -68,36 +81,35 @@ extern void ext4_es_find_delayed_extent_range(struct inode *inode,
struct extent_status *es);
extern int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
struct extent_status *es);
-extern int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex);
static inline int ext4_es_is_written(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_WRITTEN) != 0;
+ return (es->es_pblk & ES_WRITTEN) != 0;
}
static inline int ext4_es_is_unwritten(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_UNWRITTEN) != 0;
+ return (es->es_pblk & ES_UNWRITTEN) != 0;
}
static inline int ext4_es_is_delayed(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_DELAYED) != 0;
+ return (es->es_pblk & ES_DELAYED) != 0;
}
static inline int ext4_es_is_hole(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_HOLE) != 0;
+ return (es->es_pblk & ES_HOLE) != 0;
}
-static inline ext4_fsblk_t ext4_es_status(struct extent_status *es)
+static inline unsigned int ext4_es_status(struct extent_status *es)
{
- return (es->es_pblk & EXTENT_STATUS_FLAGS);
+ return es->es_pblk >> ES_SHIFT;
}
static inline ext4_fsblk_t ext4_es_pblock(struct extent_status *es)
{
- return (es->es_pblk & ~EXTENT_STATUS_FLAGS);
+ return es->es_pblk & ~ES_MASK;
}
static inline void ext4_es_store_pblock(struct extent_status *es,
@@ -105,19 +117,16 @@ static inline void ext4_es_store_pblock(struct extent_status *es,
{
ext4_fsblk_t block;
- block = (pb & ~EXTENT_STATUS_FLAGS) |
- (es->es_pblk & EXTENT_STATUS_FLAGS);
+ block = (pb & ~ES_MASK) | (es->es_pblk & ES_MASK);
es->es_pblk = block;
}
static inline void ext4_es_store_status(struct extent_status *es,
- unsigned long long status)
+ unsigned int status)
{
- ext4_fsblk_t block;
-
- block = (status & EXTENT_STATUS_FLAGS) |
- (es->es_pblk & ~EXTENT_STATUS_FLAGS);
- es->es_pblk = block;
+ es->es_pblk = (((ext4_fsblk_t)
+ (status & EXTENT_STATUS_FLAGS) << ES_SHIFT) |
+ (es->es_pblk & ~ES_MASK));
}
extern void ext4_es_register_shrinker(struct ext4_sb_info *sbi);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6f4cc567c382..3da21945ff1f 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -149,7 +149,7 @@ ext4_file_dio_write(struct kiocb *iocb, const struct iovec *iov,
ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos);
mutex_unlock(&inode->i_mutex);
- if (ret > 0 || ret == -EIOCBQUEUED) {
+ if (ret > 0) {
ssize_t err;
err = generic_write_sync(file, pos, ret);
@@ -219,7 +219,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
@@ -259,22 +258,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
- if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
- struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
-
- spin_lock(&inode->i_lock);
- if (!ei->jinode) {
- if (!jinode) {
- spin_unlock(&inode->i_lock);
- return -ENOMEM;
- }
- ei->jinode = jinode;
- jbd2_journal_init_jbd_inode(ei->jinode, inode);
- jinode = NULL;
- }
- spin_unlock(&inode->i_lock);
- if (unlikely(jinode != NULL))
- jbd2_free_inode(jinode);
+ if (filp->f_mode & FMODE_WRITE) {
+ int ret = ext4_inode_attach_jinode(inode);
+ if (ret < 0)
+ return ret;
}
return dquot_file_open(inode, filp);
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f03598c6ffd3..137193ff389b 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -70,18 +70,16 @@ static unsigned ext4_init_inode_bitmap(struct super_block *sb,
ext4_group_t block_group,
struct ext4_group_desc *gdp)
{
+ struct ext4_group_info *grp;
J_ASSERT_BH(bh, buffer_locked(bh));
/* If checksum is bad mark all blocks and inodes use to prevent
* allocation, essentially implementing a per-group read-only flag. */
if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) {
ext4_error(sb, "Checksum bad for group %u", block_group);
- ext4_free_group_clusters_set(sb, gdp, 0);
- ext4_free_inodes_set(sb, gdp, 0);
- ext4_itable_unused_set(sb, gdp, 0);
- memset(bh->b_data, 0xff, sb->s_blocksize);
- ext4_inode_bitmap_csum_set(sb, block_group, gdp, bh,
- EXT4_INODES_PER_GROUP(sb) / 8);
+ grp = ext4_get_group_info(sb, block_group);
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
return 0;
}
@@ -117,6 +115,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
struct ext4_group_desc *desc;
struct buffer_head *bh = NULL;
ext4_fsblk_t bitmap_blk;
+ struct ext4_group_info *grp;
desc = ext4_get_group_desc(sb, block_group, NULL);
if (!desc)
@@ -185,6 +184,8 @@ verify:
put_bh(bh);
ext4_error(sb, "Corrupt inode bitmap - block_group = %u, "
"inode_bitmap = %llu", block_group, bitmap_blk);
+ grp = ext4_get_group_info(sb, block_group);
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
return NULL;
}
ext4_unlock_group(sb, block_group);
@@ -221,6 +222,7 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
struct ext4_super_block *es;
struct ext4_sb_info *sbi;
int fatal = 0, err, count, cleared;
+ struct ext4_group_info *grp;
if (!sb) {
printk(KERN_ERR "EXT4-fs: %s:%d: inode on "
@@ -266,7 +268,9 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
- if (!bitmap_bh)
+ /* Don't bother if the inode bitmap is corrupt. */
+ grp = ext4_get_group_info(sb, block_group);
+ if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) || !bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
@@ -315,8 +319,10 @@ out:
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!fatal)
fatal = err;
- } else
+ } else {
ext4_error(sb, "bit already cleared for inode %lu", ino);
+ set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &grp->bb_state);
+ }
error_return:
brelse(bitmap_bh);
@@ -625,6 +631,51 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
}
/*
+ * In no journal mode, if an inode has recently been deleted, we want
+ * to avoid reusing it until we're reasonably sure the inode table
+ * block has been written back to disk. (Yes, these values are
+ * somewhat arbitrary...)
+ */
+#define RECENTCY_MIN 5
+#define RECENTCY_DIRTY 30
+
+static int recently_deleted(struct super_block *sb, ext4_group_t group, int ino)
+{
+ struct ext4_group_desc *gdp;
+ struct ext4_inode *raw_inode;
+ struct buffer_head *bh;
+ unsigned long dtime, now;
+ int inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
+ int offset, ret = 0, recentcy = RECENTCY_MIN;
+
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (unlikely(!gdp))
+ return 0;
+
+ bh = sb_getblk(sb, ext4_inode_table(sb, gdp) +
+ (ino / inodes_per_block));
+ if (unlikely(!bh) || !buffer_uptodate(bh))
+ /*
+ * If the block is not in the buffer cache, then it
+ * must have been written out.
+ */
+ goto out;
+
+ offset = (ino % inodes_per_block) * EXT4_INODE_SIZE(sb);
+ raw_inode = (struct ext4_inode *) (bh->b_data + offset);
+ dtime = le32_to_cpu(raw_inode->i_dtime);
+ now = get_seconds();
+ if (buffer_dirty(bh))
+ recentcy += RECENTCY_DIRTY;
+
+ if (dtime && (dtime < now) && (now < dtime + recentcy))
+ ret = 1;
+out:
+ brelse(bh);
+ return ret;
+}
+
+/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
@@ -652,6 +703,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
struct inode *ret;
ext4_group_t i;
ext4_group_t flex_group;
+ struct ext4_group_info *grp;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
@@ -725,25 +777,39 @@ got_group:
continue;
}
+ grp = ext4_get_group_info(sb, group);
+ /* Skip groups with already-known suspicious inode tables */
+ if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
+ if (++group == ngroups)
+ group = 0;
+ continue;
+ }
+
brelse(inode_bitmap_bh);
inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
- if (!inode_bitmap_bh)
- goto out;
+ /* Skip groups with suspicious inode tables */
+ if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) || !inode_bitmap_bh) {
+ if (++group == ngroups)
+ group = 0;
+ continue;
+ }
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
EXT4_INODES_PER_GROUP(sb), ino);
- if (ino >= EXT4_INODES_PER_GROUP(sb)) {
- if (++group == ngroups)
- group = 0;
- continue;
- }
+ if (ino >= EXT4_INODES_PER_GROUP(sb))
+ goto next_group;
if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
ext4_error(sb, "reserved inode found cleared - "
"inode=%lu", ino + 1);
continue;
}
+ if ((EXT4_SB(sb)->s_journal == NULL) &&
+ recently_deleted(sb, group, ino)) {
+ ino++;
+ goto next_inode;
+ }
if (!handle) {
BUG_ON(nblocks <= 0);
handle = __ext4_journal_start_sb(dir->i_sb, line_no,
@@ -767,8 +833,12 @@ repeat_in_this_group:
ino++; /* the inode bitmap is zero-based */
if (!ret2)
goto got; /* we grabbed the inode! */
+next_inode:
if (ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
+next_group:
+ if (++group == ngroups)
+ group = 0;
}
err = -ENOSPC;
goto out;
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 87b30cd357e7..594009f5f523 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -23,7 +23,6 @@
#include <linux/aio.h>
#include "ext4_jbd2.h"
#include "truncate.h"
-#include "ext4_extents.h" /* Needed for EXT_MAX_BLOCKS */
#include <trace/events/ext4.h>
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ba33c67d6e48..c79fd7dabe79 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -553,16 +553,15 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
}
if (retval > 0) {
int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -654,16 +653,15 @@ found:
if (retval > 0) {
int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (allocation)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
/*
* If the extent has been zeroed out, we don't need to update
@@ -729,8 +727,12 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock,
ret = ext4_map_blocks(handle, inode, &map, flags);
if (ret > 0) {
+ ext4_io_end_t *io_end = ext4_inode_aio(inode);
+
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags;
+ if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN)
+ set_buffer_defer_completion(bh);
bh->b_size = inode->i_sb->s_blocksize * map.m_len;
ret = 0;
}
@@ -971,7 +973,8 @@ retry_journal:
ext4_journal_stop(handle);
goto retry_grab;
}
- wait_on_page_writeback(page);
+ /* In case writeback began while the page was unlocked */
+ wait_for_stable_page(page);
if (ext4_should_dioread_nolock(inode))
ret = __block_write_begin(page, pos, len, ext4_get_block_write);
@@ -1635,16 +1638,15 @@ add_delayed:
set_buffer_delay(bh);
} else if (retval > 0) {
int ret;
- unsigned long long status;
+ unsigned int status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -1893,12 +1895,32 @@ static int ext4_writepage(struct page *page,
return ret;
}
+static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
+{
+ int len;
+ loff_t size = i_size_read(mpd->inode);
+ int err;
+
+ BUG_ON(page->index != mpd->first_page);
+ if (page->index == size >> PAGE_CACHE_SHIFT)
+ len = size & ~PAGE_CACHE_MASK;
+ else
+ len = PAGE_CACHE_SIZE;
+ clear_page_dirty_for_io(page);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
+ if (!err)
+ mpd->wbc->nr_to_write--;
+ mpd->first_page++;
+
+ return err;
+}
+
#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
/*
* mballoc gives us at most this number of blocks...
* XXX: That seems to be only a limitation of ext4_mb_normalize_request().
- * The rest of mballoc seems to handle chunks upto full group size.
+ * The rest of mballoc seems to handle chunks up to full group size.
*/
#define MAX_WRITEPAGES_EXTENT_LEN 2048
@@ -1907,82 +1929,94 @@ static int ext4_writepage(struct page *page,
*
* @mpd - extent of blocks
* @lblk - logical number of the block in the file
- * @b_state - b_state of the buffer head added
+ * @bh - buffer head we want to add to the extent
*
- * the function is used to collect contig. blocks in same state
+ * The function is used to collect contig. blocks in the same state. If the
+ * buffer doesn't require mapping for writeback and we haven't started the
+ * extent of buffers to map yet, the function returns 'true' immediately - the
+ * caller can write the buffer right away. Otherwise the function returns true
+ * if the block has been added to the extent, false if the block couldn't be
+ * added.
*/
-static int mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
- unsigned long b_state)
+static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
+ struct buffer_head *bh)
{
struct ext4_map_blocks *map = &mpd->map;
- /* Don't go larger than mballoc is willing to allocate */
- if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
- return 0;
+ /* Buffer that doesn't need mapping for writeback? */
+ if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
+ (!buffer_delay(bh) && !buffer_unwritten(bh))) {
+ /* So far no extent to map => we write the buffer right away */
+ if (map->m_len == 0)
+ return true;
+ return false;
+ }
/* First block in the extent? */
if (map->m_len == 0) {
map->m_lblk = lblk;
map->m_len = 1;
- map->m_flags = b_state & BH_FLAGS;
- return 1;
+ map->m_flags = bh->b_state & BH_FLAGS;
+ return true;
}
+ /* Don't go larger than mballoc is willing to allocate */
+ if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN)
+ return false;
+
/* Can we merge the block to our big extent? */
if (lblk == map->m_lblk + map->m_len &&
- (b_state & BH_FLAGS) == map->m_flags) {
+ (bh->b_state & BH_FLAGS) == map->m_flags) {
map->m_len++;
- return 1;
+ return true;
}
- return 0;
+ return false;
}
-static bool add_page_bufs_to_extent(struct mpage_da_data *mpd,
- struct buffer_head *head,
- struct buffer_head *bh,
- ext4_lblk_t lblk)
+/*
+ * mpage_process_page_bufs - submit page buffers for IO or add them to extent
+ *
+ * @mpd - extent of blocks for mapping
+ * @head - the first buffer in the page
+ * @bh - buffer we should start processing from
+ * @lblk - logical number of the block in the file corresponding to @bh
+ *
+ * Walk through page buffers from @bh upto @head (exclusive) and either submit
+ * the page for IO if all buffers in this page were mapped and there's no
+ * accumulated extent of buffers to map or add buffers in the page to the
+ * extent of buffers to map. The function returns 1 if the caller can continue
+ * by processing the next page, 0 if it should stop adding buffers to the
+ * extent to map because we cannot extend it anymore. It can also return value
+ * < 0 in case of error during IO submission.
+ */
+static int mpage_process_page_bufs(struct mpage_da_data *mpd,
+ struct buffer_head *head,
+ struct buffer_head *bh,
+ ext4_lblk_t lblk)
{
struct inode *inode = mpd->inode;
+ int err;
ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
>> inode->i_blkbits;
do {
BUG_ON(buffer_locked(bh));
- if (!buffer_dirty(bh) || !buffer_mapped(bh) ||
- (!buffer_delay(bh) && !buffer_unwritten(bh)) ||
- lblk >= blocks) {
+ if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) {
/* Found extent to map? */
if (mpd->map.m_len)
- return false;
- if (lblk >= blocks)
- return true;
- continue;
+ return 0;
+ /* Everything mapped so far and we hit EOF */
+ break;
}
- if (!mpage_add_bh_to_extent(mpd, lblk, bh->b_state))
- return false;
} while (lblk++, (bh = bh->b_this_page) != head);
- return true;
-}
-
-static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
-{
- int len;
- loff_t size = i_size_read(mpd->inode);
- int err;
-
- BUG_ON(page->index != mpd->first_page);
- if (page->index == size >> PAGE_CACHE_SHIFT)
- len = size & ~PAGE_CACHE_MASK;
- else
- len = PAGE_CACHE_SIZE;
- clear_page_dirty_for_io(page);
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc);
- if (!err)
- mpd->wbc->nr_to_write--;
- mpd->first_page++;
-
- return err;
+ /* So far everything mapped? Submit the page for IO. */
+ if (mpd->map.m_len == 0) {
+ err = mpage_submit_page(mpd, head->b_page);
+ if (err < 0)
+ return err;
+ }
+ return lblk < blocks;
}
/*
@@ -2006,8 +2040,6 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
struct inode *inode = mpd->inode;
struct buffer_head *head, *bh;
int bpp_bits = PAGE_CACHE_SHIFT - inode->i_blkbits;
- ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
- >> inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
sector_t pblock;
@@ -2029,7 +2061,7 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
if (page->index > end)
break;
- /* Upto 'end' pages must be contiguous */
+ /* Up to 'end' pages must be contiguous */
BUG_ON(page->index != start);
bh = head = page_buffers(page);
do {
@@ -2042,18 +2074,26 @@ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd)
*/
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
- add_page_bufs_to_extent(mpd, head, bh,
- lblk);
+ /*
+ * FIXME: If dioread_nolock supports
+ * blocksize < pagesize, we need to make
+ * sure we add size mapped so far to
+ * io_end->size as the following call
+ * can submit the page for IO.
+ */
+ err = mpage_process_page_bufs(mpd, head,
+ bh, lblk);
pagevec_release(&pvec);
- return 0;
+ if (err > 0)
+ err = 0;
+ return err;
}
if (buffer_delay(bh)) {
clear_buffer_delay(bh);
bh->b_blocknr = pblock++;
}
clear_buffer_unwritten(bh);
- } while (++lblk < blocks &&
- (bh = bh->b_this_page) != head);
+ } while (lblk++, (bh = bh->b_this_page) != head);
/*
* FIXME: This is going to break if dioread_nolock
@@ -2202,12 +2242,10 @@ static int mpage_map_and_submit_extent(handle_t *handle,
/* Update on-disk size after IO is submitted */
disksize = ((loff_t)mpd->first_page) << PAGE_CACHE_SHIFT;
- if (disksize > i_size_read(inode))
- disksize = i_size_read(inode);
if (disksize > EXT4_I(inode)->i_disksize) {
int err2;
- ext4_update_i_disksize(inode, disksize);
+ ext4_wb_update_i_disksize(inode, disksize);
err2 = ext4_mark_inode_dirty(handle, inode);
if (err2)
ext4_error(inode->i_sb,
@@ -2222,7 +2260,7 @@ static int mpage_map_and_submit_extent(handle_t *handle,
/*
* Calculate the total number of credits to reserve for one writepages
* iteration. This is called from ext4_writepages(). We map an extent of
- * upto MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
+ * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping
* the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN +
* bpp - 1 blocks in bpp different extents.
*/
@@ -2322,14 +2360,10 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd)
lblk = ((ext4_lblk_t)page->index) <<
(PAGE_CACHE_SHIFT - blkbits);
head = page_buffers(page);
- if (!add_page_bufs_to_extent(mpd, head, head, lblk))
+ err = mpage_process_page_bufs(mpd, head, head, lblk);
+ if (err <= 0)
goto out;
- /* So far everything mapped? Submit the page for IO. */
- if (mpd->map.m_len == 0) {
- err = mpage_submit_page(mpd, page);
- if (err < 0)
- goto out;
- }
+ err = 0;
/*
* Accumulated enough dirty pages? This doesn't apply
@@ -2413,7 +2447,7 @@ static int ext4_writepages(struct address_space *mapping,
if (ext4_should_dioread_nolock(inode)) {
/*
- * We may need to convert upto one extent per block in
+ * We may need to convert up to one extent per block in
* the page and we may dirty the inode.
*/
rsv_blocks = 1 + (PAGE_CACHE_SIZE >> inode->i_blkbits);
@@ -2649,7 +2683,7 @@ retry_journal:
goto retry_grab;
}
/* In case writeback began while the page was unlocked */
- wait_on_page_writeback(page);
+ wait_for_stable_page(page);
ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep);
if (ret < 0) {
@@ -2994,19 +3028,13 @@ static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock,
}
static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
- ssize_t size, void *private, int ret,
- bool is_async)
+ ssize_t size, void *private)
{
- struct inode *inode = file_inode(iocb->ki_filp);
ext4_io_end_t *io_end = iocb->private;
/* if not async direct IO just return */
- if (!io_end) {
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
+ if (!io_end)
return;
- }
ext_debug("ext4_end_io_dio(): io_end 0x%p "
"for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
@@ -3016,11 +3044,7 @@ static void ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
iocb->private = NULL;
io_end->offset = offset;
io_end->size = size;
- if (is_async) {
- io_end->iocb = iocb;
- io_end->result = ret;
- }
- ext4_put_io_end_defer(io_end);
+ ext4_put_io_end(io_end);
}
/*
@@ -3105,7 +3129,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
ret = -ENOMEM;
goto retake_lock;
}
- io_end->flag |= EXT4_IO_END_DIRECT;
/*
* Grab reference for DIO. Will be dropped in ext4_end_io_dio()
*/
@@ -3150,13 +3173,6 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
if (ret <= 0 && ret != -EIOCBQUEUED && iocb->private) {
WARN_ON(iocb->private != io_end);
WARN_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
- WARN_ON(io_end->iocb);
- /*
- * Generic code already did inode_dio_done() so we
- * have to clear EXT4_IO_END_DIRECT to not do it for
- * the second time.
- */
- io_end->flag = 0;
ext4_put_io_end(io_end);
iocb->private = NULL;
}
@@ -3536,6 +3552,18 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
offset;
}
+ if (offset & (sb->s_blocksize - 1) ||
+ (offset + length) & (sb->s_blocksize - 1)) {
+ /*
+ * Attach jinode to inode for jbd2 if we do any zeroing of
+ * partial block
+ */
+ ret = ext4_inode_attach_jinode(inode);
+ if (ret < 0)
+ goto out_mutex;
+
+ }
+
first_block_offset = round_up(offset, sb->s_blocksize);
last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
@@ -3604,6 +3632,31 @@ out_mutex:
return ret;
}
+int ext4_inode_attach_jinode(struct inode *inode)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ struct jbd2_inode *jinode;
+
+ if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
+ return 0;
+
+ jinode = jbd2_alloc_inode(GFP_KERNEL);
+ spin_lock(&inode->i_lock);
+ if (!ei->jinode) {
+ if (!jinode) {
+ spin_unlock(&inode->i_lock);
+ return -ENOMEM;
+ }
+ ei->jinode = jinode;
+ jbd2_journal_init_jbd_inode(ei->jinode, inode);
+ jinode = NULL;
+ }
+ spin_unlock(&inode->i_lock);
+ if (unlikely(jinode != NULL))
+ jbd2_free_inode(jinode);
+ return 0;
+}
+
/*
* ext4_truncate()
*
@@ -3664,6 +3717,12 @@ void ext4_truncate(struct inode *inode)
return;
}
+ /* If we zero-out tail of the page, we have to create jinode for jbd2 */
+ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
+ if (ext4_inode_attach_jinode(inode) < 0)
+ return;
+ }
+
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
credits = ext4_writepage_trans_blocks(inode);
else
@@ -4526,7 +4585,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
ext4_journal_stop(handle);
}
- if (attr->ia_valid & ATTR_SIZE) {
+ if (attr->ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) {
+ handle_t *handle;
+ loff_t oldsize = inode->i_size;
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -4534,73 +4595,69 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
if (attr->ia_size > sbi->s_bitmap_maxbytes)
return -EFBIG;
}
- }
-
- if (S_ISREG(inode->i_mode) &&
- attr->ia_valid & ATTR_SIZE &&
- (attr->ia_size < inode->i_size)) {
- handle_t *handle;
-
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
- if (IS_ERR(handle)) {
- error = PTR_ERR(handle);
- goto err_out;
- }
- if (ext4_handle_valid(handle)) {
- error = ext4_orphan_add(handle, inode);
- orphan = 1;
- }
- EXT4_I(inode)->i_disksize = attr->ia_size;
- rc = ext4_mark_inode_dirty(handle, inode);
- if (!error)
- error = rc;
- ext4_journal_stop(handle);
-
- if (ext4_should_order_data(inode)) {
- error = ext4_begin_ordered_truncate(inode,
+ if (S_ISREG(inode->i_mode) &&
+ (attr->ia_size < inode->i_size)) {
+ if (ext4_should_order_data(inode)) {
+ error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
- if (error) {
- /* Do as much error cleanup as possible */
- handle = ext4_journal_start(inode,
- EXT4_HT_INODE, 3);
- if (IS_ERR(handle)) {
- ext4_orphan_del(NULL, inode);
+ if (error)
goto err_out;
- }
- ext4_orphan_del(handle, inode);
- orphan = 0;
- ext4_journal_stop(handle);
+ }
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
+ if (IS_ERR(handle)) {
+ error = PTR_ERR(handle);
goto err_out;
}
- }
- }
-
- if (attr->ia_valid & ATTR_SIZE) {
- if (attr->ia_size != inode->i_size) {
- loff_t oldsize = inode->i_size;
-
- i_size_write(inode, attr->ia_size);
- /*
- * Blocks are going to be removed from the inode. Wait
- * for dio in flight. Temporarily disable
- * dioread_nolock to prevent livelock.
- */
- if (orphan) {
- if (!ext4_should_journal_data(inode)) {
- ext4_inode_block_unlocked_dio(inode);
- inode_dio_wait(inode);
- ext4_inode_resume_unlocked_dio(inode);
- } else
- ext4_wait_for_tail_page_commit(inode);
+ if (ext4_handle_valid(handle)) {
+ error = ext4_orphan_add(handle, inode);
+ orphan = 1;
}
+ down_write(&EXT4_I(inode)->i_data_sem);
+ EXT4_I(inode)->i_disksize = attr->ia_size;
+ rc = ext4_mark_inode_dirty(handle, inode);
+ if (!error)
+ error = rc;
/*
- * Truncate pagecache after we've waited for commit
- * in data=journal mode to make pages freeable.
+ * We have to update i_size under i_data_sem together
+ * with i_disksize to avoid races with writeback code
+ * running ext4_wb_update_i_disksize().
*/
- truncate_pagecache(inode, oldsize, inode->i_size);
+ if (!error)
+ i_size_write(inode, attr->ia_size);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ ext4_journal_stop(handle);
+ if (error) {
+ ext4_orphan_del(NULL, inode);
+ goto err_out;
+ }
+ } else
+ i_size_write(inode, attr->ia_size);
+
+ /*
+ * Blocks are going to be removed from the inode. Wait
+ * for dio in flight. Temporarily disable
+ * dioread_nolock to prevent livelock.
+ */
+ if (orphan) {
+ if (!ext4_should_journal_data(inode)) {
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+ ext4_inode_resume_unlocked_dio(inode);
+ } else
+ ext4_wait_for_tail_page_commit(inode);
}
- ext4_truncate(inode);
+ /*
+ * Truncate pagecache after we've waited for commit
+ * in data=journal mode to make pages freeable.
+ */
+ truncate_pagecache(inode, oldsize, inode->i_size);
}
+ /*
+ * We want to call ext4_truncate() even if attr->ia_size ==
+ * inode->i_size for cases like truncation of fallocated space
+ */
+ if (attr->ia_valid & ATTR_SIZE)
+ ext4_truncate(inode);
if (!rc) {
setattr_copy(inode, attr);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 9491ac0590f7..a569d335f804 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -17,7 +17,6 @@
#include <asm/uaccess.h>
#include "ext4_jbd2.h"
#include "ext4.h"
-#include "ext4_extents.h"
#define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
@@ -77,8 +76,10 @@ static void swap_inode_data(struct inode *inode1, struct inode *inode2)
memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
memswap(&ei1->i_flags, &ei2->i_flags, sizeof(ei1->i_flags));
memswap(&ei1->i_disksize, &ei2->i_disksize, sizeof(ei1->i_disksize));
- memswap(&ei1->i_es_tree, &ei2->i_es_tree, sizeof(ei1->i_es_tree));
- memswap(&ei1->i_es_lru_nr, &ei2->i_es_lru_nr, sizeof(ei1->i_es_lru_nr));
+ ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
+ ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
+ ext4_es_lru_del(inode1);
+ ext4_es_lru_del(inode2);
isize = i_size_read(inode1);
i_size_write(inode1, i_size_read(inode2));
@@ -622,6 +623,8 @@ resizefs_out:
return 0;
}
+ case EXT4_IOC_PRECACHE_EXTENTS:
+ return ext4_ext_precache(inode);
default:
return -ENOTTY;
@@ -686,6 +689,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_MOVE_EXT:
case FITRIM:
case EXT4_IOC_RESIZE_FS:
+ case EXT4_IOC_PRECACHE_EXTENTS:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 4bbbf13bd743..a41e3ba8cfaa 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -751,13 +751,15 @@ void ext4_mb_generate_buddy(struct super_block *sb,
if (free != grp->bb_free) {
ext4_grp_locked_error(sb, group, 0, 0,
- "%u clusters in bitmap, %u in gd",
+ "%u clusters in bitmap, %u in gd; "
+ "block bitmap corrupt.",
free, grp->bb_free);
/*
- * If we intent to continue, we consider group descritor
+ * If we intend to continue, we consider group descriptor
* corrupt and update bb_free using bitmap value
*/
grp->bb_free = free;
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &grp->bb_state);
}
mb_set_largest_free_order(sb, grp);
@@ -1398,6 +1400,10 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
BUG_ON(last >= (sb->s_blocksize << 3));
assert_spin_locked(ext4_group_lock_ptr(sb, e4b->bd_group));
+ /* Don't bother if the block group is corrupt. */
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ return;
+
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
@@ -1423,7 +1429,11 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
inode ? inode->i_ino : 0,
blocknr,
"freeing already freed block "
- "(bit %u)", block);
+ "(bit %u); block bitmap corrupt.",
+ block);
+ /* Mark the block group as corrupt. */
+ set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+ &e4b->bd_info->bb_state);
mb_regenerate_buddy(e4b);
goto done;
}
@@ -1790,6 +1800,11 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
if (err)
return err;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
+ ext4_mb_unload_buddy(e4b);
+ return 0;
+ }
+
ext4_lock_group(ac->ac_sb, group);
max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
@@ -1987,6 +2002,9 @@ static int ext4_mb_good_group(struct ext4_allocation_context *ac,
if (cr <= 2 && free < ac->ac_g_ex.fe_len)
return 0;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp)))
+ return 0;
+
/* We only do this if the grp has never been initialized */
if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
int ret = ext4_mb_init_group(ac->ac_sb, group);
@@ -4585,6 +4603,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
struct buffer_head *gd_bh;
ext4_group_t block_group;
struct ext4_sb_info *sbi;
+ struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_buddy e4b;
unsigned int count_clusters;
int err = 0;
@@ -4673,6 +4692,10 @@ do_more:
overflow = 0;
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(
+ ext4_get_group_info(sb, block_group))))
+ return;
+
/*
* Check to see if we are freeing blocks across a group
* boundary.
@@ -4784,7 +4807,6 @@ do_more:
ext4_block_bitmap_csum_set(sb, block_group, gdp, bitmap_bh);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
- percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
@@ -4792,10 +4814,23 @@ do_more:
&sbi->s_flex_groups[flex_group].free_clusters);
}
- ext4_mb_unload_buddy(&e4b);
-
- if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ if (flags & EXT4_FREE_BLOCKS_RESERVE && ei->i_reserved_data_blocks) {
+ percpu_counter_add(&sbi->s_dirtyclusters_counter,
+ count_clusters);
+ spin_lock(&ei->i_block_reservation_lock);
+ if (flags & EXT4_FREE_BLOCKS_METADATA)
+ ei->i_reserved_meta_blocks += count_clusters;
+ else
+ ei->i_reserved_data_blocks += count_clusters;
+ spin_unlock(&ei->i_block_reservation_lock);
+ if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
+ dquot_reclaim_block(inode,
+ EXT4_C2B(sbi, count_clusters));
+ } else if (!(flags & EXT4_FREE_BLOCKS_NO_QUOT_UPDATE))
dquot_free_block(inode, EXT4_C2B(sbi, count_clusters));
+ percpu_counter_add(&sbi->s_freeclusters_counter, count_clusters);
+
+ ext4_mb_unload_buddy(&e4b);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 49e8bdff9163..2ae73a80c19b 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -39,7 +39,7 @@ static int finish_range(handle_t *handle, struct inode *inode,
newext.ee_block = cpu_to_le32(lb->first_block);
newext.ee_len = cpu_to_le16(lb->last_block - lb->first_block + 1);
ext4_ext_store_pblock(&newext, lb->first_pblock);
- path = ext4_ext_find_extent(inode, lb->first_block, NULL);
+ path = ext4_ext_find_extent(inode, lb->first_block, NULL, 0);
if (IS_ERR(path)) {
retval = PTR_ERR(path);
@@ -494,7 +494,7 @@ int ext4_ext_migrate(struct inode *inode)
* superblock modification.
*
* For the tmp_inode we already have committed the
- * trascation that created the inode. Later as and
+ * transaction that created the inode. Later as and
* when we add extents we extent the journal
*/
/*
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index e86dddbd8296..7fa4d855dbd5 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -37,7 +37,7 @@ get_ext_path(struct inode *inode, ext4_lblk_t lblock,
int ret = 0;
struct ext4_ext_path *path;
- path = ext4_ext_find_extent(inode, lblock, *orig_path);
+ path = ext4_ext_find_extent(inode, lblock, *orig_path, EXT4_EX_NOCACHE);
if (IS_ERR(path))
ret = PTR_ERR(path);
else if (path[ext_depth(inode)].p_ext == NULL)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 35f55a0dbc4b..1bec5a5c1e45 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -3005,15 +3005,19 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
/*
* Anybody can rename anything with this: the permission checks are left to the
* higher-level routines.
+ *
+ * n.b. old_{dentry,inode) refers to the source dentry/inode
+ * while new_{dentry,inode) refers to the destination dentry/inode
+ * This comes from rename(const char *oldpath, const char *newpath)
*/
static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry)
{
- handle_t *handle;
+ handle_t *handle = NULL;
struct inode *old_inode, *new_inode;
struct buffer_head *old_bh, *new_bh, *dir_bh;
struct ext4_dir_entry_2 *old_de, *new_de;
- int retval, force_da_alloc = 0;
+ int retval;
int inlined = 0, new_inlined = 0;
struct ext4_dir_entry_2 *parent_de;
@@ -3026,14 +3030,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
* in separate transaction */
if (new_dentry->d_inode)
dquot_initialize(new_dentry->d_inode);
- handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
- (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
- EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
- ext4_handle_sync(handle);
old_bh = ext4_find_entry(old_dir, &old_dentry->d_name, &old_de, NULL);
/*
@@ -3056,6 +3052,18 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
new_bh = NULL;
}
}
+ if (new_inode && !test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
+ ext4_alloc_da_blocks(old_inode);
+
+ handle = ext4_journal_start(old_dir, EXT4_HT_DIR,
+ (2 * EXT4_DATA_TRANS_BLOCKS(old_dir->i_sb) +
+ EXT4_INDEX_EXTRA_TRANS_BLOCKS + 2));
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
+ ext4_handle_sync(handle);
+
if (S_ISDIR(old_inode->i_mode)) {
if (new_inode) {
retval = -ENOTEMPTY;
@@ -3186,8 +3194,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
ext4_mark_inode_dirty(handle, new_inode);
if (!new_inode->i_nlink)
ext4_orphan_add(handle, new_inode);
- if (!test_opt(new_dir->i_sb, NO_AUTO_DA_ALLOC))
- force_da_alloc = 1;
}
retval = 0;
@@ -3195,9 +3201,8 @@ end_rename:
brelse(dir_bh);
brelse(old_bh);
brelse(new_bh);
- ext4_journal_stop(handle);
- if (retval == 0 && force_da_alloc)
- ext4_alloc_da_blocks(old_inode);
+ if (handle)
+ ext4_journal_stop(handle);
return retval;
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 6625d210fb45..d7d0c7b46ed4 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -123,10 +123,6 @@ static void ext4_release_io_end(ext4_io_end_t *io_end)
ext4_finish_bio(bio);
bio_put(bio);
}
- if (io_end->flag & EXT4_IO_END_DIRECT)
- inode_dio_done(io_end->inode);
- if (io_end->iocb)
- aio_complete(io_end->iocb, io_end->result, 0);
kmem_cache_free(io_end_cachep, io_end);
}
@@ -204,19 +200,14 @@ static void ext4_add_complete_io(ext4_io_end_t *io_end)
struct workqueue_struct *wq;
unsigned long flags;
- BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+ /* Only reserved conversions from writeback should enter here */
+ WARN_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+ WARN_ON(!io_end->handle);
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
- if (io_end->handle) {
- wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
- if (list_empty(&ei->i_rsv_conversion_list))
- queue_work(wq, &ei->i_rsv_conversion_work);
- list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
- } else {
- wq = EXT4_SB(io_end->inode->i_sb)->unrsv_conversion_wq;
- if (list_empty(&ei->i_unrsv_conversion_list))
- queue_work(wq, &ei->i_unrsv_conversion_work);
- list_add_tail(&io_end->list, &ei->i_unrsv_conversion_list);
- }
+ wq = EXT4_SB(io_end->inode->i_sb)->rsv_conversion_wq;
+ if (list_empty(&ei->i_rsv_conversion_list))
+ queue_work(wq, &ei->i_rsv_conversion_work);
+ list_add_tail(&io_end->list, &ei->i_rsv_conversion_list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
}
@@ -256,13 +247,6 @@ void ext4_end_io_rsv_work(struct work_struct *work)
ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_rsv_conversion_list);
}
-void ext4_end_io_unrsv_work(struct work_struct *work)
-{
- struct ext4_inode_info *ei = container_of(work, struct ext4_inode_info,
- i_unrsv_conversion_work);
- ext4_do_flush_completed_IO(&ei->vfs_inode, &ei->i_unrsv_conversion_list);
-}
-
ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
{
ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bca26f34edf4..049c8a8bdc0e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -762,9 +762,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_li_request(sb);
dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
- flush_workqueue(sbi->unrsv_conversion_wq);
flush_workqueue(sbi->rsv_conversion_wq);
- destroy_workqueue(sbi->unrsv_conversion_wq);
destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
@@ -875,14 +873,12 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
#endif
ei->jinode = NULL;
INIT_LIST_HEAD(&ei->i_rsv_conversion_list);
- INIT_LIST_HEAD(&ei->i_unrsv_conversion_list);
spin_lock_init(&ei->i_completed_io_lock);
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
atomic_set(&ei->i_unwritten, 0);
INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
- INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work);
return &ei->vfs_inode;
}
@@ -1134,8 +1130,8 @@ enum {
Opt_nouid32, Opt_debug, Opt_removed,
Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
- Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
- Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
+ Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
+ Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
Opt_data_err_abort, Opt_data_err_ignore,
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
@@ -1179,6 +1175,7 @@ static const match_table_t tokens = {
{Opt_min_batch_time, "min_batch_time=%u"},
{Opt_max_batch_time, "max_batch_time=%u"},
{Opt_journal_dev, "journal_dev=%u"},
+ {Opt_journal_path, "journal_path=%s"},
{Opt_journal_checksum, "journal_checksum"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_abort, "abort"},
@@ -1338,6 +1335,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
#define MOPT_NO_EXT2 0x0100
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
+#define MOPT_STRING 0x0400
static const struct mount_opts {
int token;
@@ -1359,7 +1357,7 @@ static const struct mount_opts {
{Opt_delalloc, EXT4_MOUNT_DELALLOC,
MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
- MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT},
+ MOPT_EXT4_ONLY | MOPT_CLEAR},
{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
MOPT_EXT4_ONLY | MOPT_SET},
{Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT |
@@ -1387,6 +1385,7 @@ static const struct mount_opts {
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
{Opt_journal_dev, 0, MOPT_GTE0},
+ {Opt_journal_path, 0, MOPT_STRING},
{Opt_journal_ioprio, 0, MOPT_GTE0},
{Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
{Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
@@ -1480,7 +1479,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
- if (args->from && match_int(args, &arg))
+ if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
return -1;
if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
return -1;
@@ -1544,6 +1543,44 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
return -1;
}
*journal_devnum = arg;
+ } else if (token == Opt_journal_path) {
+ char *journal_path;
+ struct inode *journal_inode;
+ struct path path;
+ int error;
+
+ if (is_remount) {
+ ext4_msg(sb, KERN_ERR,
+ "Cannot specify journal on remount");
+ return -1;
+ }
+ journal_path = match_strdup(&args[0]);
+ if (!journal_path) {
+ ext4_msg(sb, KERN_ERR, "error: could not dup "
+ "journal device string");
+ return -1;
+ }
+
+ error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+ if (error) {
+ ext4_msg(sb, KERN_ERR, "error: could not find "
+ "journal device path: error %d", error);
+ kfree(journal_path);
+ return -1;
+ }
+
+ journal_inode = path.dentry->d_inode;
+ if (!S_ISBLK(journal_inode->i_mode)) {
+ ext4_msg(sb, KERN_ERR, "error: journal path %s "
+ "is not a block device", journal_path);
+ path_put(&path);
+ kfree(journal_path);
+ return -1;
+ }
+
+ *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+ path_put(&path);
+ kfree(journal_path);
} else if (token == Opt_journal_ioprio) {
if (arg > 7) {
ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"
@@ -3483,7 +3520,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
if (test_opt(sb, DIOREAD_NOLOCK)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and delalloc");
+ "both data=journal and dioread_nolock");
goto failed_mount;
}
if (test_opt(sb, DELALLOC))
@@ -3954,14 +3991,6 @@ no_journal:
goto failed_mount4;
}
- EXT4_SB(sb)->unrsv_conversion_wq =
- alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
- if (!EXT4_SB(sb)->unrsv_conversion_wq) {
- printk(KERN_ERR "EXT4-fs: failed to create workqueue\n");
- ret = -ENOMEM;
- goto failed_mount4;
- }
-
/*
* The jbd2_journal_load will have done any necessary log recovery,
* so we can safely mount the rest of the filesystem now.
@@ -4115,8 +4144,6 @@ failed_mount4:
ext4_msg(sb, KERN_ERR, "mount failed");
if (EXT4_SB(sb)->rsv_conversion_wq)
destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
- if (EXT4_SB(sb)->unrsv_conversion_wq)
- destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
failed_mount_wq:
if (sbi->s_journal) {
jbd2_journal_destroy(sbi->s_journal);
@@ -4564,7 +4591,6 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->rsv_conversion_wq);
- flush_workqueue(sbi->unrsv_conversion_wq);
/*
* Writeback quota in non-journalled quota case - journalled quota has
* no dirty dquots
@@ -4600,7 +4626,6 @@ static int ext4_sync_fs_nojournal(struct super_block *sb, int wait)
trace_ext4_sync_fs(sb, wait);
flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
- flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq);
dquot_writeback_dquots(sb, -1);
if (wait && test_opt(sb, BARRIER))
ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
@@ -4727,6 +4752,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
goto restore_opts;
}
+ if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
+ if (test_opt2(sb, EXPLICIT_DELALLOC)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and delalloc");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ if (test_opt(sb, DIOREAD_NOLOCK)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dioread_nolock");
+ err = -EINVAL;
+ goto restore_opts;
+ }
+ }
+
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, "Abort forced by user");
@@ -5481,6 +5521,7 @@ static void __exit ext4_exit_fs(void)
kset_unregister(ext4_kset);
ext4_exit_system_zone();
ext4_exit_pageio();
+ ext4_exit_es();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 66a6b85a51d8..bb312201ca95 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -182,7 +182,7 @@ const struct address_space_operations f2fs_meta_aops = {
.set_page_dirty = f2fs_set_meta_page_dirty,
};
-int check_orphan_space(struct f2fs_sb_info *sbi)
+int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
unsigned int max_orphans;
int err = 0;
@@ -197,10 +197,19 @@ int check_orphan_space(struct f2fs_sb_info *sbi)
mutex_lock(&sbi->orphan_inode_mutex);
if (sbi->n_orphans >= max_orphans)
err = -ENOSPC;
+ else
+ sbi->n_orphans++;
mutex_unlock(&sbi->orphan_inode_mutex);
return err;
}
+void release_orphan_inode(struct f2fs_sb_info *sbi)
+{
+ mutex_lock(&sbi->orphan_inode_mutex);
+ sbi->n_orphans--;
+ mutex_unlock(&sbi->orphan_inode_mutex);
+}
+
void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
struct list_head *head, *this;
@@ -229,21 +238,18 @@ retry:
list_add(&new->list, this->prev);
else
list_add_tail(&new->list, head);
-
- sbi->n_orphans++;
out:
mutex_unlock(&sbi->orphan_inode_mutex);
}
void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
- struct list_head *this, *next, *head;
+ struct list_head *head;
struct orphan_inode_entry *orphan;
mutex_lock(&sbi->orphan_inode_mutex);
head = &sbi->orphan_inode_list;
- list_for_each_safe(this, next, head) {
- orphan = list_entry(this, struct orphan_inode_entry, list);
+ list_for_each_entry(orphan, head, list) {
if (orphan->ino == ino) {
list_del(&orphan->list);
kmem_cache_free(orphan_entry_slab, orphan);
@@ -373,7 +379,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp1;
- pre_version = le64_to_cpu(cp_block->checkpoint_ver);
+ pre_version = cur_cp_version(cp_block);
/* Read the 2nd cp block in this CP pack */
cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
@@ -388,7 +394,7 @@ static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
if (!f2fs_crc_valid(crc, cp_block, crc_offset))
goto invalid_cp2;
- cur_version = le64_to_cpu(cp_block->checkpoint_ver);
+ cur_version = cur_cp_version(cp_block);
if (cur_version == pre_version) {
*version = cur_version;
@@ -793,7 +799,7 @@ void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
* Increase the version number so that
* SIT entries and seg summaries are written at correct place
*/
- ckpt_ver = le64_to_cpu(ckpt->checkpoint_ver);
+ ckpt_ver = cur_cp_version(ckpt);
ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
/* write cached NAT/SIT entries to NAT/SIT area */
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 035f9a345cdf..941f9b9ca3a5 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -37,9 +37,9 @@ static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
struct page *node_page = dn->node_page;
unsigned int ofs_in_node = dn->ofs_in_node;
- wait_on_page_writeback(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, false);
- rn = (struct f2fs_node *)page_address(node_page);
+ rn = F2FS_NODE(node_page);
/* Get physical address of data block */
addr_array = blkaddr_in_node(rn);
@@ -117,7 +117,8 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
block_t start_blkaddr, end_blkaddr;
BUG_ON(blk_addr == NEW_ADDR);
- fofs = start_bidx_of_node(ofs_of_node(dn->node_page)) + dn->ofs_in_node;
+ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
+ dn->ofs_in_node;
/* Update the page address in the parent node */
__set_data_blkaddr(dn, blk_addr);
@@ -176,7 +177,6 @@ void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
end_update:
write_unlock(&fi->ext.ext_lock);
sync_inode_page(dn);
- return;
}
struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
@@ -260,8 +260,17 @@ repeat:
if (PageUptodate(page))
return page;
- BUG_ON(dn.data_blkaddr == NEW_ADDR);
- BUG_ON(dn.data_blkaddr == NULL_ADDR);
+ /*
+ * A new dentry page is allocated but not able to be written, since its
+ * new inode page couldn't be allocated due to -ENOSPC.
+ * In such the case, its blkaddr can be remained as NEW_ADDR.
+ * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
+ */
+ if (dn.data_blkaddr == NEW_ADDR) {
+ zero_user_segment(page, 0, PAGE_CACHE_SIZE);
+ SetPageUptodate(page);
+ return page;
+ }
err = f2fs_readpage(sbi, page, dn.data_blkaddr, READ_SYNC);
if (err)
@@ -365,7 +374,6 @@ static void read_end_io(struct bio *bio, int err)
}
unlock_page(page);
} while (bvec >= bio->bi_io_vec);
- kfree(bio->bi_private);
bio_put(bio);
}
@@ -391,7 +399,6 @@ int f2fs_readpage(struct f2fs_sb_info *sbi, struct page *page,
bio->bi_end_io = read_end_io;
if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
- kfree(bio->bi_private);
bio_put(bio);
up_read(&sbi->bio_sem);
f2fs_put_page(page, 1);
@@ -442,7 +449,7 @@ static int get_data_block_ro(struct inode *inode, sector_t iblock,
unsigned int end_offset;
end_offset = IS_INODE(dn.node_page) ?
- ADDRS_PER_INODE :
+ ADDRS_PER_INODE(F2FS_I(inode)) :
ADDRS_PER_BLOCK;
clear_buffer_new(bh_result);
@@ -636,9 +643,6 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
int err = 0;
int ilock;
- /* for nobh_write_end */
- *fsdata = NULL;
-
f2fs_balance_fs(sbi);
repeat:
page = grab_cache_page_write_begin(mapping, index, flags);
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index 0d6c6aafb235..a84b0a8e6854 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -29,7 +29,7 @@ static DEFINE_MUTEX(f2fs_stat_mutex);
static void update_general_status(struct f2fs_sb_info *sbi)
{
- struct f2fs_stat_info *si = sbi->stat_info;
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
int i;
/* valid check of the segment numbers */
@@ -83,7 +83,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
*/
static void update_sit_info(struct f2fs_sb_info *sbi)
{
- struct f2fs_stat_info *si = sbi->stat_info;
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned int blks_per_sec, hblks_per_sec, total_vblocks, bimodal, dist;
struct sit_info *sit_i = SIT_I(sbi);
unsigned int segno, vblocks;
@@ -118,7 +118,7 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
*/
static void update_mem_info(struct f2fs_sb_info *sbi)
{
- struct f2fs_stat_info *si = sbi->stat_info;
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
unsigned npages;
if (si->base_mem)
@@ -253,21 +253,21 @@ static int stat_show(struct seq_file *s, void *v)
si->nats, NM_WOUT_THRESHOLD);
seq_printf(s, " - SITs: %5d\n - free_nids: %5d\n",
si->sits, si->fnids);
- seq_printf(s, "\nDistribution of User Blocks:");
- seq_printf(s, " [ valid | invalid | free ]\n");
- seq_printf(s, " [");
+ seq_puts(s, "\nDistribution of User Blocks:");
+ seq_puts(s, " [ valid | invalid | free ]\n");
+ seq_puts(s, " [");
for (j = 0; j < si->util_valid; j++)
- seq_printf(s, "-");
- seq_printf(s, "|");
+ seq_putc(s, '-');
+ seq_putc(s, '|');
for (j = 0; j < si->util_invalid; j++)
- seq_printf(s, "-");
- seq_printf(s, "|");
+ seq_putc(s, '-');
+ seq_putc(s, '|');
for (j = 0; j < si->util_free; j++)
- seq_printf(s, "-");
- seq_printf(s, "]\n\n");
+ seq_putc(s, '-');
+ seq_puts(s, "]\n\n");
seq_printf(s, "SSR: %u blocks in %u segments\n",
si->block_count[SSR], si->segment_count[SSR]);
seq_printf(s, "LFS: %u blocks in %u segments\n",
@@ -305,11 +305,10 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
struct f2fs_stat_info *si;
- sbi->stat_info = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
- if (!sbi->stat_info)
+ si = kzalloc(sizeof(struct f2fs_stat_info), GFP_KERNEL);
+ if (!si)
return -ENOMEM;
- si = sbi->stat_info;
si->all_area_segs = le32_to_cpu(raw_super->segment_count);
si->sit_area_segs = le32_to_cpu(raw_super->segment_count_sit);
si->nat_area_segs = le32_to_cpu(raw_super->segment_count_nat);
@@ -319,6 +318,7 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
si->main_area_zones = si->main_area_sections /
le32_to_cpu(raw_super->secs_per_zone);
si->sbi = sbi;
+ sbi->stat_info = si;
mutex_lock(&f2fs_stat_mutex);
list_add_tail(&si->stat_list, &f2fs_stat_list);
@@ -329,13 +329,13 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
void f2fs_destroy_stats(struct f2fs_sb_info *sbi)
{
- struct f2fs_stat_info *si = sbi->stat_info;
+ struct f2fs_stat_info *si = F2FS_STAT(sbi);
mutex_lock(&f2fs_stat_mutex);
list_del(&si->stat_list);
mutex_unlock(&f2fs_stat_mutex);
- kfree(sbi->stat_info);
+ kfree(si);
}
void __init f2fs_create_root_stats(void)
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 62f0d5977c64..384c6daf9a89 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -270,12 +270,27 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
struct f2fs_node *rn;
/* copy name info. to this inode page */
- rn = (struct f2fs_node *)page_address(ipage);
+ rn = F2FS_NODE(ipage);
rn->i.i_namelen = cpu_to_le32(name->len);
memcpy(rn->i.i_name, name->name, name->len);
set_page_dirty(ipage);
}
+int update_dent_inode(struct inode *inode, const struct qstr *name)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct page *page;
+
+ page = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(page))
+ return PTR_ERR(page);
+
+ init_dent_inode(name, page);
+ f2fs_put_page(page, 1);
+
+ return 0;
+}
+
static int make_empty_dir(struct inode *inode,
struct inode *parent, struct page *page)
{
@@ -557,6 +572,8 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
if (inode->i_nlink == 0)
add_orphan_inode(sbi, inode->i_ino);
+ else
+ release_orphan_inode(sbi);
}
if (bit_pos == NR_DENTRY_IN_BLOCK) {
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 467d42d65c48..608f0df5b919 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -17,6 +17,7 @@
#include <linux/slab.h>
#include <linux/crc32.h>
#include <linux/magic.h>
+#include <linux/kobject.h>
/*
* For mount options
@@ -28,6 +29,7 @@
#define F2FS_MOUNT_XATTR_USER 0x00000010
#define F2FS_MOUNT_POSIX_ACL 0x00000020
#define F2FS_MOUNT_DISABLE_EXT_IDENTIFY 0x00000040
+#define F2FS_MOUNT_INLINE_XATTR 0x00000080
#define clear_opt(sbi, option) (sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
#define set_opt(sbi, option) (sbi->mount_opt.opt |= F2FS_MOUNT_##option)
@@ -134,11 +136,13 @@ static inline int update_sits_in_cursum(struct f2fs_summary_block *rs, int i)
/*
* For INODE and NODE manager
*/
-#define XATTR_NODE_OFFSET (-1) /*
- * store xattrs to one node block per
- * file keeping -1 as its node offset to
- * distinguish from index node blocks.
- */
+/*
+ * XATTR_NODE_OFFSET stores xattrs to one node block per file keeping -1
+ * as its node offset to distinguish from index node blocks.
+ * But some bits are used to mark the node block.
+ */
+#define XATTR_NODE_OFFSET ((((unsigned int)-1) << OFFSET_BIT_SHIFT) \
+ >> OFFSET_BIT_SHIFT)
enum {
ALLOC_NODE, /* allocate a new node page if needed */
LOOKUP_NODE, /* look up a node without readahead */
@@ -178,6 +182,7 @@ struct f2fs_inode_info {
f2fs_hash_t chash; /* hash value of given file name */
unsigned int clevel; /* maximum level of given file name */
nid_t i_xattr_nid; /* node id that contains xattrs */
+ unsigned long long xattr_ver; /* cp version of xattr modification */
struct extent_info ext; /* in-memory extent cache entry */
};
@@ -296,15 +301,6 @@ struct f2fs_sm_info {
};
/*
- * For directory operation
- */
-#define NODE_DIR1_BLOCK (ADDRS_PER_INODE + 1)
-#define NODE_DIR2_BLOCK (ADDRS_PER_INODE + 2)
-#define NODE_IND1_BLOCK (ADDRS_PER_INODE + 3)
-#define NODE_IND2_BLOCK (ADDRS_PER_INODE + 4)
-#define NODE_DIND_BLOCK (ADDRS_PER_INODE + 5)
-
-/*
* For superblock
*/
/*
@@ -350,6 +346,7 @@ enum page_type {
struct f2fs_sb_info {
struct super_block *sb; /* pointer to VFS super block */
+ struct proc_dir_entry *s_proc; /* proc entry */
struct buffer_head *raw_super_buf; /* buffer head of raw sb */
struct f2fs_super_block *raw_super; /* raw super block pointer */
int s_dirty; /* dirty flag for checkpoint */
@@ -429,6 +426,10 @@ struct f2fs_sb_info {
#endif
unsigned int last_victim[2]; /* last victim segment # */
spinlock_t stat_lock; /* lock for stat operations */
+
+ /* For sysfs suppport */
+ struct kobject s_kobj;
+ struct completion s_kobj_unregister;
};
/*
@@ -454,6 +455,11 @@ static inline struct f2fs_checkpoint *F2FS_CKPT(struct f2fs_sb_info *sbi)
return (struct f2fs_checkpoint *)(sbi->ckpt);
}
+static inline struct f2fs_node *F2FS_NODE(struct page *page)
+{
+ return (struct f2fs_node *)page_address(page);
+}
+
static inline struct f2fs_nm_info *NM_I(struct f2fs_sb_info *sbi)
{
return (struct f2fs_nm_info *)(sbi->nm_info);
@@ -489,6 +495,11 @@ static inline void F2FS_RESET_SB_DIRT(struct f2fs_sb_info *sbi)
sbi->s_dirty = 0;
}
+static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
+{
+ return le64_to_cpu(cp->checkpoint_ver);
+}
+
static inline bool is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
{
unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
@@ -677,7 +688,7 @@ static inline block_t __start_cp_addr(struct f2fs_sb_info *sbi)
{
block_t start_addr;
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- unsigned long long ckpt_version = le64_to_cpu(ckpt->checkpoint_ver);
+ unsigned long long ckpt_version = cur_cp_version(ckpt);
start_addr = le32_to_cpu(F2FS_RAW_SUPER(sbi)->cp_blkaddr);
@@ -812,7 +823,7 @@ static inline struct kmem_cache *f2fs_kmem_cache_create(const char *name,
static inline bool IS_INODE(struct page *page)
{
- struct f2fs_node *p = (struct f2fs_node *)page_address(page);
+ struct f2fs_node *p = F2FS_NODE(page);
return RAW_IS_INODE(p);
}
@@ -826,7 +837,7 @@ static inline block_t datablock_addr(struct page *node_page,
{
struct f2fs_node *raw_node;
__le32 *addr_array;
- raw_node = (struct f2fs_node *)page_address(node_page);
+ raw_node = F2FS_NODE(node_page);
addr_array = blkaddr_in_node(raw_node);
return le32_to_cpu(addr_array[offset]);
}
@@ -873,6 +884,7 @@ enum {
FI_NO_ALLOC, /* should not allocate any blocks */
FI_UPDATE_DIR, /* should update inode block for consistency */
FI_DELAY_IPUT, /* used for the recovery */
+ FI_INLINE_XATTR, /* used for inline xattr */
};
static inline void set_inode_flag(struct f2fs_inode_info *fi, int flag)
@@ -905,6 +917,45 @@ static inline int cond_clear_inode_flag(struct f2fs_inode_info *fi, int flag)
return 0;
}
+static inline void get_inline_info(struct f2fs_inode_info *fi,
+ struct f2fs_inode *ri)
+{
+ if (ri->i_inline & F2FS_INLINE_XATTR)
+ set_inode_flag(fi, FI_INLINE_XATTR);
+}
+
+static inline void set_raw_inline(struct f2fs_inode_info *fi,
+ struct f2fs_inode *ri)
+{
+ ri->i_inline = 0;
+
+ if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+ ri->i_inline |= F2FS_INLINE_XATTR;
+}
+
+static inline unsigned int addrs_per_inode(struct f2fs_inode_info *fi)
+{
+ if (is_inode_flag_set(fi, FI_INLINE_XATTR))
+ return DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS;
+ return DEF_ADDRS_PER_INODE;
+}
+
+static inline void *inline_xattr_addr(struct page *page)
+{
+ struct f2fs_inode *ri;
+ ri = (struct f2fs_inode *)page_address(page);
+ return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
+ F2FS_INLINE_XATTR_ADDRS]);
+}
+
+static inline int inline_xattr_size(struct inode *inode)
+{
+ if (is_inode_flag_set(F2FS_I(inode), FI_INLINE_XATTR))
+ return F2FS_INLINE_XATTR_ADDRS << 2;
+ else
+ return 0;
+}
+
static inline int f2fs_readonly(struct super_block *sb)
{
return sb->s_flags & MS_RDONLY;
@@ -947,6 +998,7 @@ struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
ino_t f2fs_inode_by_name(struct inode *, struct qstr *);
void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
struct page *, struct inode *);
+int update_dent_inode(struct inode *, const struct qstr *);
int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *);
void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *);
int f2fs_make_empty(struct inode *, struct inode *);
@@ -980,6 +1032,7 @@ int is_checkpointed_node(struct f2fs_sb_info *, nid_t);
void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
int truncate_inode_blocks(struct inode *, pgoff_t);
+int truncate_xattr_node(struct inode *, struct page *);
int remove_inode_page(struct inode *);
struct page *new_inode_page(struct inode *, const struct qstr *);
struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
@@ -1012,7 +1065,8 @@ int npages_for_summary_flush(struct f2fs_sb_info *);
void allocate_new_segments(struct f2fs_sb_info *);
struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
struct bio *f2fs_bio_alloc(struct block_device *, int);
-void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool sync);
+void f2fs_submit_bio(struct f2fs_sb_info *, enum page_type, bool);
+void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
void write_meta_page(struct f2fs_sb_info *, struct page *);
void write_node_page(struct f2fs_sb_info *, struct page *, unsigned int,
block_t, block_t *);
@@ -1037,7 +1091,8 @@ void destroy_segment_manager(struct f2fs_sb_info *);
struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-int check_orphan_space(struct f2fs_sb_info *);
+int acquire_orphan_inode(struct f2fs_sb_info *);
+void release_orphan_inode(struct f2fs_sb_info *);
void add_orphan_inode(struct f2fs_sb_info *, nid_t);
void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
int recover_orphan_inodes(struct f2fs_sb_info *);
@@ -1068,7 +1123,7 @@ int do_write_data_page(struct page *);
*/
int start_gc_thread(struct f2fs_sb_info *);
void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int);
+block_t start_bidx_of_node(unsigned int, struct f2fs_inode_info *);
int f2fs_gc(struct f2fs_sb_info *);
void build_gc_manager(struct f2fs_sb_info *);
int __init create_gc_caches(void);
@@ -1112,11 +1167,16 @@ struct f2fs_stat_info {
unsigned base_mem, cache_mem;
};
+static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
+{
+ return (struct f2fs_stat_info*)sbi->stat_info;
+}
+
#define stat_inc_call_count(si) ((si)->call_count++)
#define stat_inc_seg_count(sbi, type) \
do { \
- struct f2fs_stat_info *si = sbi->stat_info; \
+ struct f2fs_stat_info *si = F2FS_STAT(sbi); \
(si)->tot_segs++; \
if (type == SUM_TYPE_DATA) \
si->data_segs++; \
@@ -1129,14 +1189,14 @@ struct f2fs_stat_info {
#define stat_inc_data_blk_count(sbi, blks) \
do { \
- struct f2fs_stat_info *si = sbi->stat_info; \
+ struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->data_blks += (blks); \
} while (0)
#define stat_inc_node_blk_count(sbi, blks) \
do { \
- struct f2fs_stat_info *si = sbi->stat_info; \
+ struct f2fs_stat_info *si = F2FS_STAT(sbi); \
stat_inc_tot_blk_count(si, blks); \
si->node_blks += (blks); \
} while (0)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index d2d2b7dbdcc1..02c906971cc6 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -112,11 +112,13 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
if (!dentry)
return 0;
- inode = igrab(dentry->d_parent->d_inode);
- dput(dentry);
+ if (update_dent_inode(inode, &dentry->d_name)) {
+ dput(dentry);
+ return 0;
+ }
- *pino = inode->i_ino;
- iput(inode);
+ *pino = parent_ino(dentry);
+ dput(dentry);
return 1;
}
@@ -147,9 +149,10 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
mutex_lock(&inode->i_mutex);
- if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
- goto out;
-
+ /*
+ * Both of fdatasync() and fsync() are able to be recovered from
+ * sudden-power-off.
+ */
if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
need_cp = true;
else if (file_wrong_pino(inode))
@@ -158,10 +161,14 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
need_cp = true;
else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
need_cp = true;
+ else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
+ need_cp = true;
if (need_cp) {
nid_t pino;
+ F2FS_I(inode)->xattr_ver = 0;
+
/* all the dirty node pages should be flushed for POR */
ret = f2fs_sync_fs(inode->i_sb, 1);
if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
@@ -205,7 +212,7 @@ int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
struct f2fs_node *raw_node;
__le32 *addr;
- raw_node = page_address(dn->node_page);
+ raw_node = F2FS_NODE(dn->node_page);
addr = blkaddr_in_node(raw_node) + ofs;
for ( ; count > 0; count--, addr++, dn->ofs_in_node++) {
@@ -283,7 +290,7 @@ static int truncate_blocks(struct inode *inode, u64 from)
}
if (IS_INODE(dn.node_page))
- count = ADDRS_PER_INODE;
+ count = ADDRS_PER_INODE(F2FS_I(inode));
else
count = ADDRS_PER_BLOCK;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 35f9b1a196aa..2f157e883687 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -29,10 +29,11 @@ static struct kmem_cache *winode_slab;
static int gc_thread_func(void *data)
{
struct f2fs_sb_info *sbi = data;
+ struct f2fs_gc_kthread *gc_th = sbi->gc_thread;
wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head;
long wait_ms;
- wait_ms = GC_THREAD_MIN_SLEEP_TIME;
+ wait_ms = gc_th->min_sleep_time;
do {
if (try_to_freeze())
@@ -45,7 +46,7 @@ static int gc_thread_func(void *data)
break;
if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) {
- wait_ms = GC_THREAD_MAX_SLEEP_TIME;
+ wait_ms = increase_sleep_time(gc_th, wait_ms);
continue;
}
@@ -66,15 +67,15 @@ static int gc_thread_func(void *data)
continue;
if (!is_idle(sbi)) {
- wait_ms = increase_sleep_time(wait_ms);
+ wait_ms = increase_sleep_time(gc_th, wait_ms);
mutex_unlock(&sbi->gc_mutex);
continue;
}
if (has_enough_invalid_blocks(sbi))
- wait_ms = decrease_sleep_time(wait_ms);
+ wait_ms = decrease_sleep_time(gc_th, wait_ms);
else
- wait_ms = increase_sleep_time(wait_ms);
+ wait_ms = increase_sleep_time(gc_th, wait_ms);
#ifdef CONFIG_F2FS_STAT_FS
sbi->bg_gc++;
@@ -82,7 +83,7 @@ static int gc_thread_func(void *data)
/* if return value is not zero, no victim was selected */
if (f2fs_gc(sbi))
- wait_ms = GC_THREAD_NOGC_SLEEP_TIME;
+ wait_ms = gc_th->no_gc_sleep_time;
} while (!kthread_should_stop());
return 0;
}
@@ -101,6 +102,12 @@ int start_gc_thread(struct f2fs_sb_info *sbi)
goto out;
}
+ gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME;
+ gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME;
+ gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME;
+
+ gc_th->gc_idle = 0;
+
sbi->gc_thread = gc_th;
init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head);
sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi,
@@ -125,9 +132,17 @@ void stop_gc_thread(struct f2fs_sb_info *sbi)
sbi->gc_thread = NULL;
}
-static int select_gc_type(int gc_type)
+static int select_gc_type(struct f2fs_gc_kthread *gc_th, int gc_type)
{
- return (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+ int gc_mode = (gc_type == BG_GC) ? GC_CB : GC_GREEDY;
+
+ if (gc_th && gc_th->gc_idle) {
+ if (gc_th->gc_idle == 1)
+ gc_mode = GC_CB;
+ else if (gc_th->gc_idle == 2)
+ gc_mode = GC_GREEDY;
+ }
+ return gc_mode;
}
static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
@@ -138,12 +153,18 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
if (p->alloc_mode == SSR) {
p->gc_mode = GC_GREEDY;
p->dirty_segmap = dirty_i->dirty_segmap[type];
+ p->max_search = dirty_i->nr_dirty[type];
p->ofs_unit = 1;
} else {
- p->gc_mode = select_gc_type(gc_type);
+ p->gc_mode = select_gc_type(sbi->gc_thread, gc_type);
p->dirty_segmap = dirty_i->dirty_segmap[DIRTY];
+ p->max_search = dirty_i->nr_dirty[DIRTY];
p->ofs_unit = sbi->segs_per_sec;
}
+
+ if (p->max_search > MAX_VICTIM_SEARCH)
+ p->max_search = MAX_VICTIM_SEARCH;
+
p->offset = sbi->last_victim[p->gc_mode];
}
@@ -290,7 +311,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
if (cost == max_cost)
continue;
- if (nsearched++ >= MAX_VICTIM_SEARCH) {
+ if (nsearched++ >= p.max_search) {
sbi->last_victim[p.gc_mode] = segno;
break;
}
@@ -407,8 +428,7 @@ next_step:
/* set page dirty and write it */
if (gc_type == FG_GC) {
- f2fs_submit_bio(sbi, NODE, true);
- wait_on_page_writeback(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, true);
set_page_dirty(node_page);
} else {
if (!PageWriteback(node_page))
@@ -447,7 +467,7 @@ next_step:
* as indirect or double indirect node blocks, are given, it must be a caller's
* bug.
*/
-block_t start_bidx_of_node(unsigned int node_ofs)
+block_t start_bidx_of_node(unsigned int node_ofs, struct f2fs_inode_info *fi)
{
unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4;
unsigned int bidx;
@@ -464,7 +484,7 @@ block_t start_bidx_of_node(unsigned int node_ofs)
int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1);
bidx = node_ofs - 5 - dec;
}
- return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE;
+ return bidx * ADDRS_PER_BLOCK + ADDRS_PER_INODE(fi);
}
static int check_dnode(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -508,10 +528,7 @@ static void move_data_page(struct inode *inode, struct page *page, int gc_type)
} else {
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- if (PageWriteback(page)) {
- f2fs_submit_bio(sbi, DATA, true);
- wait_on_page_writeback(page);
- }
+ f2fs_wait_on_page_writeback(page, DATA, true);
if (clear_page_dirty_for_io(page) &&
S_ISDIR(inode->i_mode)) {
@@ -575,7 +592,6 @@ next_step:
continue;
}
- start_bidx = start_bidx_of_node(nofs);
ofs_in_node = le16_to_cpu(entry->ofs_in_node);
if (phase == 2) {
@@ -583,6 +599,8 @@ next_step:
if (IS_ERR(inode))
continue;
+ start_bidx = start_bidx_of_node(nofs, F2FS_I(inode));
+
data_page = find_data_page(inode,
start_bidx + ofs_in_node, false);
if (IS_ERR(data_page))
@@ -593,6 +611,8 @@ next_step:
} else {
inode = find_gc_inode(dni.ino, ilist);
if (inode) {
+ start_bidx = start_bidx_of_node(nofs,
+ F2FS_I(inode));
data_page = get_lock_data_page(inode,
start_bidx + ofs_in_node);
if (IS_ERR(data_page))
diff --git a/fs/f2fs/gc.h b/fs/f2fs/gc.h
index 2c6a6bd08322..507056d22205 100644
--- a/fs/f2fs/gc.h
+++ b/fs/f2fs/gc.h
@@ -13,18 +13,26 @@
* whether IO subsystem is idle
* or not
*/
-#define GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */
-#define GC_THREAD_MAX_SLEEP_TIME 60000
-#define GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */
+#define DEF_GC_THREAD_MIN_SLEEP_TIME 30000 /* milliseconds */
+#define DEF_GC_THREAD_MAX_SLEEP_TIME 60000
+#define DEF_GC_THREAD_NOGC_SLEEP_TIME 300000 /* wait 5 min */
#define LIMIT_INVALID_BLOCK 40 /* percentage over total user space */
#define LIMIT_FREE_BLOCK 40 /* percentage over invalid + free space */
/* Search max. number of dirty segments to select a victim segment */
-#define MAX_VICTIM_SEARCH 20
+#define MAX_VICTIM_SEARCH 4096 /* covers 8GB */
struct f2fs_gc_kthread {
struct task_struct *f2fs_gc_task;
wait_queue_head_t gc_wait_queue_head;
+
+ /* for gc sleep time */
+ unsigned int min_sleep_time;
+ unsigned int max_sleep_time;
+ unsigned int no_gc_sleep_time;
+
+ /* for changing gc mode */
+ unsigned int gc_idle;
};
struct inode_entry {
@@ -56,25 +64,25 @@ static inline block_t limit_free_user_blocks(struct f2fs_sb_info *sbi)
return (long)(reclaimable_user_blocks * LIMIT_FREE_BLOCK) / 100;
}
-static inline long increase_sleep_time(long wait)
+static inline long increase_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
{
- if (wait == GC_THREAD_NOGC_SLEEP_TIME)
+ if (wait == gc_th->no_gc_sleep_time)
return wait;
- wait += GC_THREAD_MIN_SLEEP_TIME;
- if (wait > GC_THREAD_MAX_SLEEP_TIME)
- wait = GC_THREAD_MAX_SLEEP_TIME;
+ wait += gc_th->min_sleep_time;
+ if (wait > gc_th->max_sleep_time)
+ wait = gc_th->max_sleep_time;
return wait;
}
-static inline long decrease_sleep_time(long wait)
+static inline long decrease_sleep_time(struct f2fs_gc_kthread *gc_th, long wait)
{
- if (wait == GC_THREAD_NOGC_SLEEP_TIME)
- wait = GC_THREAD_MAX_SLEEP_TIME;
+ if (wait == gc_th->no_gc_sleep_time)
+ wait = gc_th->max_sleep_time;
- wait -= GC_THREAD_MIN_SLEEP_TIME;
- if (wait <= GC_THREAD_MIN_SLEEP_TIME)
- wait = GC_THREAD_MIN_SLEEP_TIME;
+ wait -= gc_th->min_sleep_time;
+ if (wait <= gc_th->min_sleep_time)
+ wait = gc_th->min_sleep_time;
return wait;
}
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index 2b2d45d19e3e..9339cd292047 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -56,7 +56,7 @@ static int do_read_inode(struct inode *inode)
if (IS_ERR(node_page))
return PTR_ERR(node_page);
- rn = page_address(node_page);
+ rn = F2FS_NODE(node_page);
ri = &(rn->i);
inode->i_mode = le16_to_cpu(ri->i_mode);
@@ -85,6 +85,7 @@ static int do_read_inode(struct inode *inode)
fi->i_advise = ri->i_advise;
fi->i_pino = le32_to_cpu(ri->i_pino);
get_extent_info(&fi->ext, ri->i_ext);
+ get_inline_info(fi, ri);
f2fs_put_page(node_page, 1);
return 0;
}
@@ -151,9 +152,9 @@ void update_inode(struct inode *inode, struct page *node_page)
struct f2fs_node *rn;
struct f2fs_inode *ri;
- wait_on_page_writeback(node_page);
+ f2fs_wait_on_page_writeback(node_page, NODE, false);
- rn = page_address(node_page);
+ rn = F2FS_NODE(node_page);
ri = &(rn->i);
ri->i_mode = cpu_to_le16(inode->i_mode);
@@ -164,6 +165,7 @@ void update_inode(struct inode *inode, struct page *node_page)
ri->i_size = cpu_to_le64(i_size_read(inode));
ri->i_blocks = cpu_to_le64(inode->i_blocks);
set_raw_extent(&F2FS_I(inode)->ext, &ri->i_ext);
+ set_raw_inline(F2FS_I(inode), ri);
ri->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
ri->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
@@ -221,9 +223,6 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
if (!is_inode_flag_set(F2FS_I(inode), FI_DIRTY_INODE))
return 0;
- if (wbc)
- f2fs_balance_fs(sbi);
-
/*
* We need to lock here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
@@ -231,6 +230,10 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
ilock = mutex_lock_op(sbi);
ret = update_inode_page(inode);
mutex_unlock_op(sbi, ilock);
+
+ if (wbc)
+ f2fs_balance_fs(sbi);
+
return ret;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 64c07169df05..2a5359c990fc 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -83,21 +83,11 @@ static int is_multimedia_file(const unsigned char *s, const char *sub)
{
size_t slen = strlen(s);
size_t sublen = strlen(sub);
- int ret;
if (sublen > slen)
return 0;
- ret = memcmp(s + slen - sublen, sub, sublen);
- if (ret) { /* compare upper case */
- int i;
- char upper_sub[8];
- for (i = 0; i < sublen && i < sizeof(upper_sub); i++)
- upper_sub[i] = toupper(sub[i]);
- return !memcmp(s + slen - sublen, upper_sub, sublen);
- }
-
- return !ret;
+ return !strncasecmp(s + slen - sublen, sub, sublen);
}
/*
@@ -239,7 +229,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
if (!de)
goto fail;
- err = check_orphan_space(sbi);
+ err = acquire_orphan_inode(sbi);
if (err) {
kunmap(page);
f2fs_put_page(page, 0);
@@ -393,7 +383,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *old_inode = old_dentry->d_inode;
struct inode *new_inode = new_dentry->d_inode;
struct page *old_dir_page;
- struct page *old_page;
+ struct page *old_page, *new_page;
struct f2fs_dir_entry *old_dir_entry = NULL;
struct f2fs_dir_entry *old_entry;
struct f2fs_dir_entry *new_entry;
@@ -415,7 +405,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
ilock = mutex_lock_op(sbi);
if (new_inode) {
- struct page *new_page;
err = -ENOTEMPTY;
if (old_dir_entry && !f2fs_empty_dir(new_inode))
@@ -427,14 +416,28 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (!new_entry)
goto out_dir;
+ err = acquire_orphan_inode(sbi);
+ if (err)
+ goto put_out_dir;
+
+ if (update_dent_inode(old_inode, &new_dentry->d_name)) {
+ release_orphan_inode(sbi);
+ goto put_out_dir;
+ }
+
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
new_inode->i_ctime = CURRENT_TIME;
if (old_dir_entry)
drop_nlink(new_inode);
drop_nlink(new_inode);
+
if (!new_inode->i_nlink)
add_orphan_inode(sbi, new_inode->i_ino);
+ else
+ release_orphan_inode(sbi);
+
+ update_inode_page(old_inode);
update_inode_page(new_inode);
} else {
err = f2fs_add_link(new_dentry, old_inode);
@@ -467,6 +470,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
mutex_unlock_op(sbi, ilock);
return 0;
+put_out_dir:
+ f2fs_put_page(new_page, 1);
out_dir:
if (old_dir_entry) {
kunmap(old_dir_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b418aee09573..51ef27894433 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -315,9 +315,10 @@ cache:
* The maximum depth is four.
* Offset[0] will have raw inode offset.
*/
-static int get_node_path(long block, int offset[4], unsigned int noffset[4])
+static int get_node_path(struct f2fs_inode_info *fi, long block,
+ int offset[4], unsigned int noffset[4])
{
- const long direct_index = ADDRS_PER_INODE;
+ const long direct_index = ADDRS_PER_INODE(fi);
const long direct_blks = ADDRS_PER_BLOCK;
const long dptrs_per_blk = NIDS_PER_BLOCK;
const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
@@ -405,7 +406,7 @@ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
int level, i;
int err = 0;
- level = get_node_path(index, offset, noffset);
+ level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);
nids[0] = dn->inode->i_ino;
npage[0] = dn->inode_page;
@@ -565,7 +566,7 @@ static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
return PTR_ERR(page);
}
- rn = (struct f2fs_node *)page_address(page);
+ rn = F2FS_NODE(page);
if (depth < 3) {
for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
child_nid = le32_to_cpu(rn->in.nid[i]);
@@ -687,7 +688,7 @@ int truncate_inode_blocks(struct inode *inode, pgoff_t from)
trace_f2fs_truncate_inode_blocks_enter(inode, from);
- level = get_node_path(from, offset, noffset);
+ level = get_node_path(F2FS_I(inode), from, offset, noffset);
restart:
page = get_node_page(sbi, inode->i_ino);
if (IS_ERR(page)) {
@@ -698,7 +699,7 @@ restart:
set_new_dnode(&dn, inode, page, NULL, 0);
unlock_page(page);
- rn = page_address(page);
+ rn = F2FS_NODE(page);
switch (level) {
case 0:
case 1:
@@ -771,6 +772,33 @@ fail:
return err > 0 ? 0 : err;
}
+int truncate_xattr_node(struct inode *inode, struct page *page)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ nid_t nid = F2FS_I(inode)->i_xattr_nid;
+ struct dnode_of_data dn;
+ struct page *npage;
+
+ if (!nid)
+ return 0;
+
+ npage = get_node_page(sbi, nid);
+ if (IS_ERR(npage))
+ return PTR_ERR(npage);
+
+ F2FS_I(inode)->i_xattr_nid = 0;
+
+ /* need to do checkpoint during fsync */
+ F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
+
+ set_new_dnode(&dn, inode, page, npage, nid);
+
+ if (page)
+ dn.inode_page_locked = 1;
+ truncate_node(&dn);
+ return 0;
+}
+
/*
* Caller should grab and release a mutex by calling mutex_lock_op() and
* mutex_unlock_op().
@@ -781,22 +809,16 @@ int remove_inode_page(struct inode *inode)
struct page *page;
nid_t ino = inode->i_ino;
struct dnode_of_data dn;
+ int err;
page = get_node_page(sbi, ino);
if (IS_ERR(page))
return PTR_ERR(page);
- if (F2FS_I(inode)->i_xattr_nid) {
- nid_t nid = F2FS_I(inode)->i_xattr_nid;
- struct page *npage = get_node_page(sbi, nid);
-
- if (IS_ERR(npage))
- return PTR_ERR(npage);
-
- F2FS_I(inode)->i_xattr_nid = 0;
- set_new_dnode(&dn, inode, page, npage, nid);
- dn.inode_page_locked = 1;
- truncate_node(&dn);
+ err = truncate_xattr_node(inode, page);
+ if (err) {
+ f2fs_put_page(page, 1);
+ return err;
}
/* 0 is possible, after f2fs_new_inode() is failed */
@@ -833,29 +855,32 @@ struct page *new_node_page(struct dnode_of_data *dn,
if (!page)
return ERR_PTR(-ENOMEM);
- get_node_info(sbi, dn->nid, &old_ni);
+ if (!inc_valid_node_count(sbi, dn->inode, 1)) {
+ err = -ENOSPC;
+ goto fail;
+ }
- SetPageUptodate(page);
- fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
+ get_node_info(sbi, dn->nid, &old_ni);
/* Reinitialize old_ni with new node page */
BUG_ON(old_ni.blk_addr != NULL_ADDR);
new_ni = old_ni;
new_ni.ino = dn->inode->i_ino;
-
- if (!inc_valid_node_count(sbi, dn->inode, 1)) {
- err = -ENOSPC;
- goto fail;
- }
set_node_addr(sbi, &new_ni, NEW_ADDR);
+
+ fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
set_cold_node(dn->inode, page);
+ SetPageUptodate(page);
+ set_page_dirty(page);
+
+ if (ofs == XATTR_NODE_OFFSET)
+ F2FS_I(dn->inode)->i_xattr_nid = dn->nid;
dn->node_page = page;
if (ipage)
update_inode(dn->inode, ipage);
else
sync_inode_page(dn);
- set_page_dirty(page);
if (ofs == 0)
inc_valid_inode_count(sbi);
@@ -916,7 +941,6 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
f2fs_put_page(apage, 0);
else if (err == LOCKED_PAGE)
f2fs_put_page(apage, 1);
- return;
}
struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
@@ -1167,9 +1191,9 @@ static int f2fs_write_node_page(struct page *page,
/*
* It is very important to gather dirty pages and write at once, so that we can
* submit a big bio without interfering other data writes.
- * Be default, 512 pages (2MB), a segment size, is quite reasonable.
+ * Be default, 512 pages (2MB) * 3 node types, is more reasonable.
*/
-#define COLLECT_DIRTY_NODES 512
+#define COLLECT_DIRTY_NODES 1536
static int f2fs_write_node_pages(struct address_space *mapping,
struct writeback_control *wbc)
{
@@ -1187,9 +1211,10 @@ static int f2fs_write_node_pages(struct address_space *mapping,
return 0;
/* if mounting is failed, skip writing node pages */
- wbc->nr_to_write = max_hw_blocks(sbi);
+ wbc->nr_to_write = 3 * max_hw_blocks(sbi);
sync_node_pages(sbi, 0, wbc);
- wbc->nr_to_write = nr_to_write - (max_hw_blocks(sbi) - wbc->nr_to_write);
+ wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) -
+ wbc->nr_to_write);
return 0;
}
@@ -1444,6 +1469,9 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
struct f2fs_nm_info *nm_i = NM_I(sbi);
struct free_nid *i;
+ if (!nid)
+ return;
+
spin_lock(&nm_i->free_nid_list_lock);
i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
BUG_ON(!i || i->state != NID_ALLOC);
@@ -1484,8 +1512,8 @@ int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
SetPageUptodate(ipage);
fill_node_footer(ipage, ino, ino, 0, true);
- src = (struct f2fs_node *)page_address(page);
- dst = (struct f2fs_node *)page_address(ipage);
+ src = F2FS_NODE(page);
+ dst = F2FS_NODE(ipage);
memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i);
dst->i.i_size = 0;
@@ -1515,8 +1543,8 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
/* alloc temporal page for read node */
page = alloc_page(GFP_NOFS | __GFP_ZERO);
- if (IS_ERR(page))
- return PTR_ERR(page);
+ if (!page)
+ return -ENOMEM;
lock_page(page);
/* scan the node segment */
@@ -1535,7 +1563,7 @@ int restore_node_summary(struct f2fs_sb_info *sbi,
goto out;
lock_page(page);
- rn = (struct f2fs_node *)page_address(page);
+ rn = F2FS_NODE(page);
sum_entry->nid = rn->footer.nid;
sum_entry->version = 0;
sum_entry->ofs_in_node = 0;
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index c65fb4f4230f..3496bb3e15dc 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -155,8 +155,7 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
static inline void fill_node_footer(struct page *page, nid_t nid,
nid_t ino, unsigned int ofs, bool reset)
{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(page);
if (reset)
memset(rn, 0, sizeof(*rn));
rn->footer.nid = cpu_to_le32(nid);
@@ -166,10 +165,8 @@ static inline void fill_node_footer(struct page *page, nid_t nid,
static inline void copy_node_footer(struct page *dst, struct page *src)
{
- void *src_addr = page_address(src);
- void *dst_addr = page_address(dst);
- struct f2fs_node *src_rn = (struct f2fs_node *)src_addr;
- struct f2fs_node *dst_rn = (struct f2fs_node *)dst_addr;
+ struct f2fs_node *src_rn = F2FS_NODE(src);
+ struct f2fs_node *dst_rn = F2FS_NODE(dst);
memcpy(&dst_rn->footer, &src_rn->footer, sizeof(struct node_footer));
}
@@ -177,45 +174,40 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
{
struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(page);
+
rn->footer.cp_ver = ckpt->checkpoint_ver;
rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
}
static inline nid_t ino_of_node(struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.ino);
}
static inline nid_t nid_of_node(struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.nid);
}
static inline unsigned int ofs_of_node(struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(node_page);
unsigned flag = le32_to_cpu(rn->footer.flag);
return flag >> OFFSET_BIT_SHIFT;
}
static inline unsigned long long cpver_of_node(struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(node_page);
return le64_to_cpu(rn->footer.cp_ver);
}
static inline block_t next_blkaddr_of_node(struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(node_page);
return le32_to_cpu(rn->footer.next_blkaddr);
}
@@ -237,6 +229,10 @@ static inline block_t next_blkaddr_of_node(struct page *node_page)
static inline bool IS_DNODE(struct page *node_page)
{
unsigned int ofs = ofs_of_node(node_page);
+
+ if (ofs == XATTR_NODE_OFFSET)
+ return false;
+
if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
ofs == 5 + 2 * NIDS_PER_BLOCK)
return false;
@@ -250,7 +246,7 @@ static inline bool IS_DNODE(struct page *node_page)
static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
{
- struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+ struct f2fs_node *rn = F2FS_NODE(p);
wait_on_page_writeback(p);
@@ -263,7 +259,8 @@ static inline void set_nid(struct page *p, int off, nid_t nid, bool i)
static inline nid_t get_nid(struct page *p, int off, bool i)
{
- struct f2fs_node *rn = (struct f2fs_node *)page_address(p);
+ struct f2fs_node *rn = F2FS_NODE(p);
+
if (i)
return le32_to_cpu(rn->i.i_nid[off - NODE_DIR1_BLOCK]);
return le32_to_cpu(rn->in.nid[off]);
@@ -314,8 +311,7 @@ static inline void clear_cold_data(struct page *page)
static inline int is_node(struct page *page, int type)
{
- void *kaddr = page_address(page);
- struct f2fs_node *rn = (struct f2fs_node *)kaddr;
+ struct f2fs_node *rn = F2FS_NODE(page);
return le32_to_cpu(rn->footer.flag) & (1 << type);
}
@@ -325,7 +321,7 @@ static inline int is_node(struct page *page, int type)
static inline void set_cold_node(struct inode *inode, struct page *page)
{
- struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+ struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (S_ISDIR(inode->i_mode))
@@ -337,7 +333,7 @@ static inline void set_cold_node(struct inode *inode, struct page *page)
static inline void set_mark(struct page *page, int mark, int type)
{
- struct f2fs_node *rn = (struct f2fs_node *)page_address(page);
+ struct f2fs_node *rn = F2FS_NODE(page);
unsigned int flag = le32_to_cpu(rn->footer.flag);
if (mark)
flag |= (0x1 << type);
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index d56d951c2253..51ef5eec33d7 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -40,8 +40,7 @@ static struct fsync_inode_entry *get_fsync_inode(struct list_head *head,
static int recover_dentry(struct page *ipage, struct inode *inode)
{
- void *kaddr = page_address(ipage);
- struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
+ struct f2fs_node *raw_node = F2FS_NODE(ipage);
struct f2fs_inode *raw_inode = &(raw_node->i);
nid_t pino = le32_to_cpu(raw_inode->i_pino);
struct f2fs_dir_entry *de;
@@ -93,8 +92,7 @@ out:
static int recover_inode(struct inode *inode, struct page *node_page)
{
- void *kaddr = page_address(node_page);
- struct f2fs_node *raw_node = (struct f2fs_node *)kaddr;
+ struct f2fs_node *raw_node = F2FS_NODE(node_page);
struct f2fs_inode *raw_inode = &(raw_node->i);
if (!IS_INODE(node_page))
@@ -119,7 +117,7 @@ static int recover_inode(struct inode *inode, struct page *node_page)
static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
{
- unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+ unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page;
block_t blkaddr;
@@ -131,8 +129,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
/* read node page */
page = alloc_page(GFP_F2FS_ZERO);
- if (IS_ERR(page))
- return PTR_ERR(page);
+ if (!page)
+ return -ENOMEM;
lock_page(page);
while (1) {
@@ -215,6 +213,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
void *kaddr;
struct inode *inode;
struct page *node_page;
+ unsigned int offset;
block_t bidx;
int i;
@@ -259,8 +258,8 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
node_page = get_node_page(sbi, nid);
if (IS_ERR(node_page))
return PTR_ERR(node_page);
- bidx = start_bidx_of_node(ofs_of_node(node_page)) +
- le16_to_cpu(sum.ofs_in_node);
+
+ offset = ofs_of_node(node_page);
ino = ino_of_node(node_page);
f2fs_put_page(node_page, 1);
@@ -269,6 +268,9 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
if (IS_ERR(inode))
return PTR_ERR(inode);
+ bidx = start_bidx_of_node(offset, F2FS_I(inode)) +
+ le16_to_cpu(sum.ofs_in_node);
+
truncate_hole(inode, bidx, bidx + 1);
iput(inode);
return 0;
@@ -277,6 +279,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi,
static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
struct page *page, block_t blkaddr)
{
+ struct f2fs_inode_info *fi = F2FS_I(inode);
unsigned int start, end;
struct dnode_of_data dn;
struct f2fs_summary sum;
@@ -284,9 +287,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
int err = 0, recovered = 0;
int ilock;
- start = start_bidx_of_node(ofs_of_node(page));
+ start = start_bidx_of_node(ofs_of_node(page), fi);
if (IS_INODE(page))
- end = start + ADDRS_PER_INODE;
+ end = start + ADDRS_PER_INODE(fi);
else
end = start + ADDRS_PER_BLOCK;
@@ -357,7 +360,7 @@ err:
static int recover_data(struct f2fs_sb_info *sbi,
struct list_head *head, int type)
{
- unsigned long long cp_ver = le64_to_cpu(sbi->ckpt->checkpoint_ver);
+ unsigned long long cp_ver = cur_cp_version(F2FS_CKPT(sbi));
struct curseg_info *curseg;
struct page *page;
int err = 0;
@@ -369,7 +372,7 @@ static int recover_data(struct f2fs_sb_info *sbi,
/* read node page */
page = alloc_page(GFP_NOFS | __GFP_ZERO);
- if (IS_ERR(page))
+ if (!page)
return -ENOMEM;
lock_page(page);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index a86d125a9885..09af9c7b0f52 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -117,7 +117,6 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
}
mutex_unlock(&dirty_i->seglist_lock);
- return;
}
/*
@@ -261,7 +260,6 @@ static void __add_sum_entry(struct f2fs_sb_info *sbi, int type,
void *addr = curseg->sum_blk;
addr += curseg->next_blkoff * sizeof(struct f2fs_summary);
memcpy(addr, sum, sizeof(struct f2fs_summary));
- return;
}
/*
@@ -542,12 +540,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
- if (force) {
+ if (force)
new_curseg(sbi, type, true);
- goto out;
- }
-
- if (type == CURSEG_WARM_NODE)
+ else if (type == CURSEG_WARM_NODE)
new_curseg(sbi, type, false);
else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
new_curseg(sbi, type, false);
@@ -555,11 +550,9 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
change_curseg(sbi, type, true);
else
new_curseg(sbi, type, false);
-out:
#ifdef CONFIG_F2FS_STAT_FS
sbi->segment_count[curseg->alloc_type]++;
#endif
- return;
}
void allocate_new_segments(struct f2fs_sb_info *sbi)
@@ -611,18 +604,12 @@ static void f2fs_end_io_write(struct bio *bio, int err)
struct bio *f2fs_bio_alloc(struct block_device *bdev, int npages)
{
struct bio *bio;
- struct bio_private *priv;
-retry:
- priv = kmalloc(sizeof(struct bio_private), GFP_NOFS);
- if (!priv) {
- cond_resched();
- goto retry;
- }
/* No failure on bio allocation */
bio = bio_alloc(GFP_NOIO, npages);
bio->bi_bdev = bdev;
- bio->bi_private = priv;
+ bio->bi_private = NULL;
+
return bio;
}
@@ -681,8 +668,17 @@ static void submit_write_page(struct f2fs_sb_info *sbi, struct page *page,
do_submit_bio(sbi, type, false);
alloc_new:
if (sbi->bio[type] == NULL) {
+ struct bio_private *priv;
+retry:
+ priv = kmalloc(sizeof(struct bio_private), GFP_NOFS);
+ if (!priv) {
+ cond_resched();
+ goto retry;
+ }
+
sbi->bio[type] = f2fs_bio_alloc(bdev, max_hw_blocks(sbi));
sbi->bio[type]->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
+ sbi->bio[type]->bi_private = priv;
/*
* The end_io will be assigned at the sumbission phase.
* Until then, let bio_add_page() merge consecutive IOs as much
@@ -702,6 +698,16 @@ alloc_new:
trace_f2fs_submit_write_page(page, blk_addr, type);
}
+void f2fs_wait_on_page_writeback(struct page *page,
+ enum page_type type, bool sync)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
+ if (PageWriteback(page)) {
+ f2fs_submit_bio(sbi, type, sync);
+ wait_on_page_writeback(page);
+ }
+}
+
static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
{
struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1179,7 +1185,6 @@ void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk)
{
if (is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG))
write_normal_summaries(sbi, start_blk, CURSEG_HOT_NODE);
- return;
}
int lookup_journal_in_cursum(struct f2fs_summary_block *sum, int type,
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 062424a0e4c3..bdd10eab8c40 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -142,6 +142,7 @@ struct victim_sel_policy {
int alloc_mode; /* LFS or SSR */
int gc_mode; /* GC_CB or GC_GREEDY */
unsigned long *dirty_segmap; /* dirty segment bitmap */
+ unsigned int max_search; /* maximum # of segments to search */
unsigned int offset; /* last scanned bitmap offset */
unsigned int ofs_unit; /* bitmap search unit */
unsigned int min_cost; /* minimum cost */
@@ -453,7 +454,8 @@ static inline int reserved_sections(struct f2fs_sb_info *sbi)
static inline bool need_SSR(struct f2fs_sb_info *sbi)
{
- return (free_sections(sbi) < overprovision_sections(sbi));
+ return ((prefree_segments(sbi) / sbi->segs_per_sec)
+ + free_sections(sbi) < overprovision_sections(sbi));
}
static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
@@ -470,7 +472,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, int freed)
static inline int utilization(struct f2fs_sb_info *sbi)
{
- return div_u64(valid_user_blocks(sbi) * 100, sbi->user_block_count);
+ return div_u64((u64)valid_user_blocks(sbi) * 100, sbi->user_block_count);
}
/*
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 75c7dc363e92..13d0a0fe49dd 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -18,20 +18,25 @@
#include <linux/parser.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
#include <linux/random.h>
#include <linux/exportfs.h>
#include <linux/blkdev.h>
#include <linux/f2fs_fs.h>
+#include <linux/sysfs.h>
#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
+#include "gc.h"
#define CREATE_TRACE_POINTS
#include <trace/events/f2fs.h>
+static struct proc_dir_entry *f2fs_proc_root;
static struct kmem_cache *f2fs_inode_cachep;
+static struct kset *f2fs_kset;
enum {
Opt_gc_background,
@@ -42,6 +47,7 @@ enum {
Opt_noacl,
Opt_active_logs,
Opt_disable_ext_identify,
+ Opt_inline_xattr,
Opt_err,
};
@@ -54,9 +60,117 @@ static match_table_t f2fs_tokens = {
{Opt_noacl, "noacl"},
{Opt_active_logs, "active_logs=%u"},
{Opt_disable_ext_identify, "disable_ext_identify"},
+ {Opt_inline_xattr, "inline_xattr"},
{Opt_err, NULL},
};
+/* Sysfs support for f2fs */
+struct f2fs_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
+ ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
+ const char *, size_t);
+ int offset;
+};
+
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi, char *buf)
+{
+ struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
+ unsigned int *ui;
+
+ if (!gc_kth)
+ return -EINVAL;
+
+ ui = (unsigned int *)(((char *)gc_kth) + a->offset);
+
+ return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
+ struct f2fs_sb_info *sbi,
+ const char *buf, size_t count)
+{
+ struct f2fs_gc_kthread *gc_kth = sbi->gc_thread;
+ unsigned long t;
+ unsigned int *ui;
+ ssize_t ret;
+
+ if (!gc_kth)
+ return -EINVAL;
+
+ ui = (unsigned int *)(((char *)gc_kth) + a->offset);
+
+ ret = kstrtoul(skip_spaces(buf), 0, &t);
+ if (ret < 0)
+ return ret;
+ *ui = t;
+ return count;
+}
+
+static ssize_t f2fs_attr_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+ return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+ return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void f2fs_sb_release(struct kobject *kobj)
+{
+ struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+ s_kobj);
+ complete(&sbi->s_kobj_unregister);
+}
+
+#define F2FS_ATTR_OFFSET(_name, _mode, _show, _store, _elname) \
+static struct f2fs_attr f2fs_attr_##_name = { \
+ .attr = {.name = __stringify(_name), .mode = _mode }, \
+ .show = _show, \
+ .store = _store, \
+ .offset = offsetof(struct f2fs_gc_kthread, _elname), \
+}
+
+#define F2FS_RW_ATTR(name, elname) \
+ F2FS_ATTR_OFFSET(name, 0644, f2fs_sbi_show, f2fs_sbi_store, elname)
+
+F2FS_RW_ATTR(gc_min_sleep_time, min_sleep_time);
+F2FS_RW_ATTR(gc_max_sleep_time, max_sleep_time);
+F2FS_RW_ATTR(gc_no_gc_sleep_time, no_gc_sleep_time);
+F2FS_RW_ATTR(gc_idle, gc_idle);
+
+#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
+static struct attribute *f2fs_attrs[] = {
+ ATTR_LIST(gc_min_sleep_time),
+ ATTR_LIST(gc_max_sleep_time),
+ ATTR_LIST(gc_no_gc_sleep_time),
+ ATTR_LIST(gc_idle),
+ NULL,
+};
+
+static const struct sysfs_ops f2fs_attr_ops = {
+ .show = f2fs_attr_show,
+ .store = f2fs_attr_store,
+};
+
+static struct kobj_type f2fs_ktype = {
+ .default_attrs = f2fs_attrs,
+ .sysfs_ops = &f2fs_attr_ops,
+ .release = f2fs_sb_release,
+};
+
void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
{
struct va_format vaf;
@@ -126,11 +240,18 @@ static int parse_options(struct super_block *sb, char *options)
case Opt_nouser_xattr:
clear_opt(sbi, XATTR_USER);
break;
+ case Opt_inline_xattr:
+ set_opt(sbi, INLINE_XATTR);
+ break;
#else
case Opt_nouser_xattr:
f2fs_msg(sb, KERN_INFO,
"nouser_xattr options not supported");
break;
+ case Opt_inline_xattr:
+ f2fs_msg(sb, KERN_INFO,
+ "inline_xattr options not supported");
+ break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
case Opt_noacl:
@@ -180,6 +301,9 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
set_inode_flag(fi, FI_NEW_INODE);
+ if (test_opt(F2FS_SB(sb), INLINE_XATTR))
+ set_inode_flag(fi, FI_INLINE_XATTR);
+
return &fi->vfs_inode;
}
@@ -205,7 +329,6 @@ static int f2fs_drop_inode(struct inode *inode)
static void f2fs_dirty_inode(struct inode *inode, int flags)
{
set_inode_flag(F2FS_I(inode), FI_DIRTY_INODE);
- return;
}
static void f2fs_i_callback(struct rcu_head *head)
@@ -223,6 +346,12 @@ static void f2fs_put_super(struct super_block *sb)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ if (sbi->s_proc) {
+ remove_proc_entry("segment_info", sbi->s_proc);
+ remove_proc_entry(sb->s_id, f2fs_proc_root);
+ }
+ kobject_del(&sbi->s_kobj);
+
f2fs_destroy_stats(sbi);
stop_gc_thread(sbi);
@@ -236,6 +365,8 @@ static void f2fs_put_super(struct super_block *sb)
destroy_segment_manager(sbi);
kfree(sbi->ckpt);
+ kobject_put(&sbi->s_kobj);
+ wait_for_completion(&sbi->s_kobj_unregister);
sb->s_fs_info = NULL;
brelse(sbi->raw_super_buf);
@@ -325,6 +456,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
seq_puts(seq, ",user_xattr");
else
seq_puts(seq, ",nouser_xattr");
+ if (test_opt(sbi, INLINE_XATTR))
+ seq_puts(seq, ",inline_xattr");
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
if (test_opt(sbi, POSIX_ACL))
@@ -340,6 +473,36 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
return 0;
}
+static int segment_info_seq_show(struct seq_file *seq, void *offset)
+{
+ struct super_block *sb = seq->private;
+ struct f2fs_sb_info *sbi = F2FS_SB(sb);
+ unsigned int total_segs = le32_to_cpu(sbi->raw_super->segment_count_main);
+ int i;
+
+ for (i = 0; i < total_segs; i++) {
+ seq_printf(seq, "%u", get_valid_blocks(sbi, i, 1));
+ if (i != 0 && (i % 10) == 0)
+ seq_puts(seq, "\n");
+ else
+ seq_puts(seq, " ");
+ }
+ return 0;
+}
+
+static int segment_info_open_fs(struct inode *inode, struct file *file)
+{
+ return single_open(file, segment_info_seq_show, PDE_DATA(inode));
+}
+
+static const struct file_operations f2fs_seq_segment_info_fops = {
+ .owner = THIS_MODULE,
+ .open = segment_info_open_fs,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static int f2fs_remount(struct super_block *sb, int *flags, char *data)
{
struct f2fs_sb_info *sbi = F2FS_SB(sb);
@@ -455,7 +618,7 @@ static const struct export_operations f2fs_export_ops = {
static loff_t max_file_size(unsigned bits)
{
- loff_t result = ADDRS_PER_INODE;
+ loff_t result = (DEF_ADDRS_PER_INODE - F2FS_INLINE_XATTR_ADDRS);
loff_t leaf_count = ADDRS_PER_BLOCK;
/* two direct node blocks */
@@ -766,6 +929,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto fail;
+ if (f2fs_proc_root)
+ sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
+
+ if (sbi->s_proc)
+ proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
+ &f2fs_seq_segment_info_fops, sb);
+
if (test_opt(sbi, DISCARD)) {
struct request_queue *q = bdev_get_queue(sb->s_bdev);
if (!blk_queue_discard(q))
@@ -774,6 +944,13 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
"the device does not support discard");
}
+ sbi->s_kobj.kset = f2fs_kset;
+ init_completion(&sbi->s_kobj_unregister);
+ err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
+ "%s", sb->s_id);
+ if (err)
+ goto fail;
+
return 0;
fail:
stop_gc_thread(sbi);
@@ -841,29 +1018,49 @@ static int __init init_f2fs_fs(void)
goto fail;
err = create_node_manager_caches();
if (err)
- goto fail;
+ goto free_inodecache;
err = create_gc_caches();
if (err)
- goto fail;
+ goto free_node_manager_caches;
err = create_checkpoint_caches();
if (err)
- goto fail;
+ goto free_gc_caches;
+ f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
+ if (!f2fs_kset) {
+ err = -ENOMEM;
+ goto free_checkpoint_caches;
+ }
err = register_filesystem(&f2fs_fs_type);
if (err)
- goto fail;
+ goto free_kset;
f2fs_create_root_stats();
+ f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+ return 0;
+
+free_kset:
+ kset_unregister(f2fs_kset);
+free_checkpoint_caches:
+ destroy_checkpoint_caches();
+free_gc_caches:
+ destroy_gc_caches();
+free_node_manager_caches:
+ destroy_node_manager_caches();
+free_inodecache:
+ destroy_inodecache();
fail:
return err;
}
static void __exit exit_f2fs_fs(void)
{
+ remove_proc_entry("fs/f2fs", NULL);
f2fs_destroy_root_stats();
unregister_filesystem(&f2fs_fs_type);
destroy_checkpoint_caches();
destroy_gc_caches();
destroy_node_manager_caches();
destroy_inodecache();
+ kset_unregister(f2fs_kset);
}
module_init(init_f2fs_fs)
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 3ab07ecd86ca..1ac8a5f6e380 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -246,40 +246,170 @@ static inline const struct xattr_handler *f2fs_xattr_handler(int name_index)
return handler;
}
+static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int name_index,
+ size_t name_len, const char *name)
+{
+ struct f2fs_xattr_entry *entry;
+
+ list_for_each_xattr(entry, base_addr) {
+ if (entry->e_name_index != name_index)
+ continue;
+ if (entry->e_name_len != name_len)
+ continue;
+ if (!memcmp(entry->e_name, name, name_len))
+ break;
+ }
+ return entry;
+}
+
+static void *read_all_xattrs(struct inode *inode, struct page *ipage)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ struct f2fs_xattr_header *header;
+ size_t size = PAGE_SIZE, inline_size = 0;
+ void *txattr_addr;
+
+ inline_size = inline_xattr_size(inode);
+
+ txattr_addr = kzalloc(inline_size + size, GFP_KERNEL);
+ if (!txattr_addr)
+ return NULL;
+
+ /* read from inline xattr */
+ if (inline_size) {
+ struct page *page = NULL;
+ void *inline_addr;
+
+ if (ipage) {
+ inline_addr = inline_xattr_addr(ipage);
+ } else {
+ page = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(page))
+ goto fail;
+ inline_addr = inline_xattr_addr(page);
+ }
+ memcpy(txattr_addr, inline_addr, inline_size);
+ f2fs_put_page(page, 1);
+ }
+
+ /* read from xattr node block */
+ if (F2FS_I(inode)->i_xattr_nid) {
+ struct page *xpage;
+ void *xattr_addr;
+
+ /* The inode already has an extended attribute block. */
+ xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+ if (IS_ERR(xpage))
+ goto fail;
+
+ xattr_addr = page_address(xpage);
+ memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
+ f2fs_put_page(xpage, 1);
+ }
+
+ header = XATTR_HDR(txattr_addr);
+
+ /* never been allocated xattrs */
+ if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
+ header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
+ header->h_refcount = cpu_to_le32(1);
+ }
+ return txattr_addr;
+fail:
+ kzfree(txattr_addr);
+ return NULL;
+}
+
+static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
+ void *txattr_addr, struct page *ipage)
+{
+ struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
+ size_t inline_size = 0;
+ void *xattr_addr;
+ struct page *xpage;
+ nid_t new_nid = 0;
+ int err;
+
+ inline_size = inline_xattr_size(inode);
+
+ if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
+ if (!alloc_nid(sbi, &new_nid))
+ return -ENOSPC;
+
+ /* write to inline xattr */
+ if (inline_size) {
+ struct page *page = NULL;
+ void *inline_addr;
+
+ if (ipage) {
+ inline_addr = inline_xattr_addr(ipage);
+ } else {
+ page = get_node_page(sbi, inode->i_ino);
+ if (IS_ERR(page)) {
+ alloc_nid_failed(sbi, new_nid);
+ return PTR_ERR(page);
+ }
+ inline_addr = inline_xattr_addr(page);
+ }
+ memcpy(inline_addr, txattr_addr, inline_size);
+ f2fs_put_page(page, 1);
+
+ /* no need to use xattr node block */
+ if (hsize <= inline_size) {
+ err = truncate_xattr_node(inode, ipage);
+ alloc_nid_failed(sbi, new_nid);
+ return err;
+ }
+ }
+
+ /* write to xattr node block */
+ if (F2FS_I(inode)->i_xattr_nid) {
+ xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+ if (IS_ERR(xpage)) {
+ alloc_nid_failed(sbi, new_nid);
+ return PTR_ERR(xpage);
+ }
+ BUG_ON(new_nid);
+ } else {
+ struct dnode_of_data dn;
+ set_new_dnode(&dn, inode, NULL, NULL, new_nid);
+ xpage = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
+ if (IS_ERR(xpage)) {
+ alloc_nid_failed(sbi, new_nid);
+ return PTR_ERR(xpage);
+ }
+ alloc_nid_done(sbi, new_nid);
+ }
+
+ xattr_addr = page_address(xpage);
+ memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
+ sizeof(struct node_footer));
+ set_page_dirty(xpage);
+ f2fs_put_page(xpage, 1);
+
+ /* need to checkpoint during fsync */
+ F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
+ return 0;
+}
+
int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
void *buffer, size_t buffer_size)
{
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_xattr_entry *entry;
- struct page *page;
void *base_addr;
- int error = 0, found = 0;
+ int error = 0;
size_t value_len, name_len;
if (name == NULL)
return -EINVAL;
name_len = strlen(name);
- if (!fi->i_xattr_nid)
- return -ENODATA;
+ base_addr = read_all_xattrs(inode, NULL);
+ if (!base_addr)
+ return -ENOMEM;
- page = get_node_page(sbi, fi->i_xattr_nid);
- if (IS_ERR(page))
- return PTR_ERR(page);
- base_addr = page_address(page);
-
- list_for_each_xattr(entry, base_addr) {
- if (entry->e_name_index != name_index)
- continue;
- if (entry->e_name_len != name_len)
- continue;
- if (!memcmp(entry->e_name, name, name_len)) {
- found = 1;
- break;
- }
- }
- if (!found) {
+ entry = __find_xattr(base_addr, name_index, name_len, name);
+ if (IS_XATTR_LAST_ENTRY(entry)) {
error = -ENODATA;
goto cleanup;
}
@@ -298,28 +428,21 @@ int f2fs_getxattr(struct inode *inode, int name_index, const char *name,
error = value_len;
cleanup:
- f2fs_put_page(page, 1);
+ kzfree(base_addr);
return error;
}
ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
{
struct inode *inode = dentry->d_inode;
- struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
- struct f2fs_inode_info *fi = F2FS_I(inode);
struct f2fs_xattr_entry *entry;
- struct page *page;
void *base_addr;
int error = 0;
size_t rest = buffer_size;
- if (!fi->i_xattr_nid)
- return 0;
-
- page = get_node_page(sbi, fi->i_xattr_nid);
- if (IS_ERR(page))
- return PTR_ERR(page);
- base_addr = page_address(page);
+ base_addr = read_all_xattrs(inode, NULL);
+ if (!base_addr)
+ return -ENOMEM;
list_for_each_xattr(entry, base_addr) {
const struct xattr_handler *handler =
@@ -342,7 +465,7 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
}
error = buffer_size - rest;
cleanup:
- f2fs_put_page(page, 1);
+ kzfree(base_addr);
return error;
}
@@ -351,14 +474,13 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
{
struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
struct f2fs_inode_info *fi = F2FS_I(inode);
- struct f2fs_xattr_header *header = NULL;
struct f2fs_xattr_entry *here, *last;
- struct page *page;
void *base_addr;
- int error, found, free, newsize;
+ int found, newsize;
size_t name_len;
- char *pval;
int ilock;
+ __u32 new_hsize;
+ int error = -ENOMEM;
if (name == NULL)
return -EINVAL;
@@ -368,67 +490,21 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
name_len = strlen(name);
- if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN)
+ if (name_len > F2FS_NAME_LEN || value_len > MAX_VALUE_LEN(inode))
return -ERANGE;
f2fs_balance_fs(sbi);
ilock = mutex_lock_op(sbi);
- if (!fi->i_xattr_nid) {
- /* Allocate new attribute block */
- struct dnode_of_data dn;
-
- if (!alloc_nid(sbi, &fi->i_xattr_nid)) {
- error = -ENOSPC;
- goto exit;
- }
- set_new_dnode(&dn, inode, NULL, NULL, fi->i_xattr_nid);
- mark_inode_dirty(inode);
-
- page = new_node_page(&dn, XATTR_NODE_OFFSET, ipage);
- if (IS_ERR(page)) {
- alloc_nid_failed(sbi, fi->i_xattr_nid);
- fi->i_xattr_nid = 0;
- error = PTR_ERR(page);
- goto exit;
- }
-
- alloc_nid_done(sbi, fi->i_xattr_nid);
- base_addr = page_address(page);
- header = XATTR_HDR(base_addr);
- header->h_magic = cpu_to_le32(F2FS_XATTR_MAGIC);
- header->h_refcount = cpu_to_le32(1);
- } else {
- /* The inode already has an extended attribute block. */
- page = get_node_page(sbi, fi->i_xattr_nid);
- if (IS_ERR(page)) {
- error = PTR_ERR(page);
- goto exit;
- }
-
- base_addr = page_address(page);
- header = XATTR_HDR(base_addr);
- }
-
- if (le32_to_cpu(header->h_magic) != F2FS_XATTR_MAGIC) {
- error = -EIO;
- goto cleanup;
- }
+ base_addr = read_all_xattrs(inode, ipage);
+ if (!base_addr)
+ goto exit;
/* find entry with wanted name. */
- found = 0;
- list_for_each_xattr(here, base_addr) {
- if (here->e_name_index != name_index)
- continue;
- if (here->e_name_len != name_len)
- continue;
- if (!memcmp(here->e_name, name, name_len)) {
- found = 1;
- break;
- }
- }
+ here = __find_xattr(base_addr, name_index, name_len, name);
+ found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
last = here;
while (!IS_XATTR_LAST_ENTRY(last))
@@ -439,22 +515,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
/* 1. Check space */
if (value) {
- /* If value is NULL, it is remove operation.
+ int free;
+ /*
+ * If value is NULL, it is remove operation.
* In case of update operation, we caculate free.
*/
- free = MIN_OFFSET - ((char *)last - (char *)header);
+ free = MIN_OFFSET(inode) - ((char *)last - (char *)base_addr);
if (found)
free = free - ENTRY_SIZE(here);
if (free < newsize) {
error = -ENOSPC;
- goto cleanup;
+ goto exit;
}
}
/* 2. Remove old entry */
if (found) {
- /* If entry is found, remove old entry.
+ /*
+ * If entry is found, remove old entry.
* If not found, remove operation is not needed.
*/
struct f2fs_xattr_entry *next = XATTR_NEXT_ENTRY(here);
@@ -465,10 +544,15 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
memset(last, 0, oldsize);
}
+ new_hsize = (char *)last - (char *)base_addr;
+
/* 3. Write new entry */
if (value) {
- /* Before we come here, old entry is removed.
- * We just write new entry. */
+ char *pval;
+ /*
+ * Before we come here, old entry is removed.
+ * We just write new entry.
+ */
memset(last, 0, newsize);
last->e_name_index = name_index;
last->e_name_len = name_len;
@@ -476,26 +560,25 @@ int f2fs_setxattr(struct inode *inode, int name_index, const char *name,
pval = last->e_name + name_len;
memcpy(pval, value, value_len);
last->e_value_size = cpu_to_le16(value_len);
+ new_hsize += newsize;
}
- set_page_dirty(page);
- f2fs_put_page(page, 1);
+ error = write_all_xattrs(inode, new_hsize, base_addr, ipage);
+ if (error)
+ goto exit;
if (is_inode_flag_set(fi, FI_ACL_MODE)) {
inode->i_mode = fi->i_acl_mode;
inode->i_ctime = CURRENT_TIME;
clear_inode_flag(fi, FI_ACL_MODE);
}
+
if (ipage)
update_inode(inode, ipage);
else
update_inode_page(inode);
- mutex_unlock_op(sbi, ilock);
-
- return 0;
-cleanup:
- f2fs_put_page(page, 1);
exit:
mutex_unlock_op(sbi, ilock);
+ kzfree(base_addr);
return error;
}
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index 3c0817bef25d..02a08fb88a15 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -51,7 +51,7 @@ struct f2fs_xattr_entry {
#define XATTR_HDR(ptr) ((struct f2fs_xattr_header *)(ptr))
#define XATTR_ENTRY(ptr) ((struct f2fs_xattr_entry *)(ptr))
-#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr)+1))
+#define XATTR_FIRST_ENTRY(ptr) (XATTR_ENTRY(XATTR_HDR(ptr) + 1))
#define XATTR_ROUND (3)
#define XATTR_ALIGN(size) ((size + XATTR_ROUND) & ~XATTR_ROUND)
@@ -69,17 +69,16 @@ struct f2fs_xattr_entry {
!IS_XATTR_LAST_ENTRY(entry);\
entry = XATTR_NEXT_ENTRY(entry))
+#define MIN_OFFSET(i) XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE - \
+ sizeof(struct node_footer) - sizeof(__u32))
-#define MIN_OFFSET XATTR_ALIGN(PAGE_SIZE - \
- sizeof(struct node_footer) - \
- sizeof(__u32))
-
-#define MAX_VALUE_LEN (MIN_OFFSET - sizeof(struct f2fs_xattr_header) - \
- sizeof(struct f2fs_xattr_entry))
+#define MAX_VALUE_LEN(i) (MIN_OFFSET(i) - \
+ sizeof(struct f2fs_xattr_header) - \
+ sizeof(struct f2fs_xattr_entry))
/*
* On-disk structure of f2fs_xattr
- * We use only 1 block for xattr.
+ * We use inline xattrs space + 1 block for xattr.
*
* +--------------------+
* | f2fs_xattr_header |
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 6599222536eb..65343c3741ff 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -730,14 +730,14 @@ static int __init fcntl_init(void)
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
O_RDONLY | O_WRONLY | O_RDWR |
O_CREAT | O_EXCL | O_NOCTTY |
O_TRUNC | O_APPEND | /* O_NONBLOCK | */
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC | O_PATH
+ __FMODE_EXEC | O_PATH | __O_TMPFILE
));
fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/file_table.c b/fs/file_table.c
index b44e4c559786..322cd37626cb 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -385,6 +385,10 @@ static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
*/
void file_sb_list_add(struct file *file, struct super_block *sb)
{
+ if (likely(!(file->f_mode & FMODE_WRITE)))
+ return;
+ if (!S_ISREG(file_inode(file)->i_mode))
+ return;
lg_local_lock(&files_lglock);
__file_sb_list_add(file, sb);
lg_local_unlock(&files_lglock);
@@ -450,8 +454,6 @@ void mark_files_ro(struct super_block *sb)
lg_global_lock(&files_lglock);
do_file_list_for_each_entry(sb, f) {
- if (!S_ISREG(file_inode(f)->i_mode))
- continue;
if (!file_count(f))
continue;
if (!(f->f_mode & FMODE_WRITE))
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index aef34b1e635e..adbfd66b380f 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -568,6 +568,7 @@ static ssize_t cuse_class_waiting_show(struct device *dev,
return sprintf(buf, "%d\n", atomic_read(&cc->fc.num_waiting));
}
+static DEVICE_ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL);
static ssize_t cuse_class_abort_store(struct device *dev,
struct device_attribute *attr,
@@ -578,12 +579,14 @@ static ssize_t cuse_class_abort_store(struct device *dev,
fuse_abort_conn(&cc->fc);
return count;
}
+static DEVICE_ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store);
-static struct device_attribute cuse_class_dev_attrs[] = {
- __ATTR(waiting, S_IFREG | 0400, cuse_class_waiting_show, NULL),
- __ATTR(abort, S_IFREG | 0200, NULL, cuse_class_abort_store),
- { }
+static struct attribute *cuse_class_dev_attrs[] = {
+ &dev_attr_waiting.attr,
+ &dev_attr_abort.attr,
+ NULL,
};
+ATTRIBUTE_GROUPS(cuse_class_dev);
static struct miscdevice cuse_miscdev = {
.minor = MISC_DYNAMIC_MINOR,
@@ -609,7 +612,7 @@ static int __init cuse_init(void)
if (IS_ERR(cuse_class))
return PTR_ERR(cuse_class);
- cuse_class->dev_attrs = cuse_class_dev_attrs;
+ cuse_class->dev_groups = cuse_class_dev_groups;
rc = misc_register(&cuse_miscdev);
if (rc) {
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9435384562a2..544a809819c3 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1838,14 +1838,14 @@ int __init gfs2_glock_init(void)
glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
WQ_HIGHPRI | WQ_FREEZABLE, 0);
- if (IS_ERR(glock_workqueue))
- return PTR_ERR(glock_workqueue);
+ if (!glock_workqueue)
+ return -ENOMEM;
gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
WQ_MEM_RECLAIM | WQ_FREEZABLE,
0);
- if (IS_ERR(gfs2_delete_workqueue)) {
+ if (!gfs2_delete_workqueue) {
destroy_workqueue(glock_workqueue);
- return PTR_ERR(gfs2_delete_workqueue);
+ return -ENOMEM;
}
register_shrinker(&glock_shrinker);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 5f2e5224c51c..e2e0a90396e7 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -47,7 +47,8 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
* None of the buffers should be dirty, locked, or pinned.
*/
-static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
+ unsigned int nr_revokes)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct list_head *head = &gl->gl_ail_list;
@@ -57,7 +58,9 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
gfs2_log_lock(sdp);
spin_lock(&sdp->sd_ail_lock);
- list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) {
+ list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) {
+ if (nr_revokes == 0)
+ break;
bh = bd->bd_bh;
if (bh->b_state & b_state) {
if (fsync)
@@ -65,6 +68,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
gfs2_ail_error(gl, bh);
}
gfs2_trans_add_revoke(sdp, bd);
+ nr_revokes--;
}
GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count));
spin_unlock(&sdp->sd_ail_lock);
@@ -91,7 +95,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
WARN_ON_ONCE(current->journal_info);
current->journal_info = &tr;
- __gfs2_ail_flush(gl, 0);
+ __gfs2_ail_flush(gl, 0, tr.tr_revokes);
gfs2_trans_end(sdp);
gfs2_log_flush(sdp, NULL);
@@ -101,15 +105,19 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
unsigned int revokes = atomic_read(&gl->gl_ail_count);
+ unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
int ret;
if (!revokes)
return;
- ret = gfs2_trans_begin(sdp, 0, revokes);
+ while (revokes > max_revokes)
+ max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+
+ ret = gfs2_trans_begin(sdp, 0, max_revokes);
if (ret)
return;
- __gfs2_ail_flush(gl, fsync);
+ __gfs2_ail_flush(gl, fsync, max_revokes);
gfs2_trans_end(sdp);
gfs2_log_flush(sdp, NULL);
}
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index bbb2715171cd..64915eeae5a7 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -594,7 +594,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
}
gfs2_glock_dq_uninit(ghs);
if (IS_ERR(d))
- return PTR_RET(d);
+ return PTR_ERR(d);
return error;
} else if (error != -ENOENT) {
goto fail_gunlock;
@@ -1750,6 +1750,10 @@ static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
struct gfs2_holder gh;
int ret;
+ /* For selinux during lookup */
+ if (gfs2_glock_is_locked_by_me(ip->i_gl))
+ return generic_getxattr(dentry, name, data, size);
+
gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
ret = gfs2_glock_nq(&gh);
if (ret == 0) {
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index e04d0e09ee7b..7b0f5043cf24 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -155,7 +155,7 @@ static int __init init_gfs2_fs(void)
goto fail_wq;
gfs2_control_wq = alloc_workqueue("gfs2_control",
- WQ_NON_REENTRANT | WQ_UNBOUND | WQ_FREEZABLE, 0);
+ WQ_UNBOUND | WQ_FREEZABLE, 0);
if (!gfs2_control_wq)
goto fail_recovery;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index a3f868ae3fd4..d19b30ababf1 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -463,6 +463,14 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
return inode;
}
+/*
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * be taken from reclaim -- unlike regular filesystems. This needs an
+ * annotation because huge_pmd_share() does an allocation under
+ * i_mmap_mutex.
+ */
+struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+
static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct inode *dir,
umode_t mode, dev_t dev)
@@ -474,6 +482,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
struct hugetlbfs_inode_info *info;
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
+ lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
+ &hugetlbfs_i_mmap_mutex_key);
inode->i_mapping->a_ops = &hugetlbfs_aops;
inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
@@ -916,14 +926,8 @@ static int get_hstate_idx(int page_size_log)
return h - hstates;
}
-static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
-{
- return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
- dentry->d_name.name);
-}
-
static struct dentry_operations anon_ops = {
- .d_dname = hugetlb_dname
+ .d_dname = simple_dname
};
/*
diff --git a/fs/inode.c b/fs/inode.c
index d6dfb09c8280..93a0625b46e4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1525,7 +1525,7 @@ static int update_time(struct inode *inode, struct timespec *time, int flags)
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
-void touch_atime(struct path *path)
+void touch_atime(const struct path *path)
{
struct vfsmount *mnt = path->mnt;
struct inode *inode = path->dentry->d_inode;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 559bec1a37b4..cf2fc0594063 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -343,14 +343,14 @@ static void jbd2_block_tag_csum_set(journal_t *j, journal_block_tag_t *tag,
struct page *page = bh->b_page;
__u8 *addr;
__u32 csum32;
+ __be32 seq;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return;
- sequence = cpu_to_be32(sequence);
+ seq = cpu_to_be32(sequence);
addr = kmap_atomic(page);
- csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
- sizeof(sequence));
+ csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
csum32 = jbd2_chksum(j, csum32, addr + offset_in_page(bh->b_data),
bh->b_size);
kunmap_atomic(addr);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 02c7ad9d7a41..52032647dd4a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -130,9 +130,10 @@ int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb)
return sb->s_checksum_type == JBD2_CRC32C_CHKSUM;
}
-static __u32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
+static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb)
{
- __u32 csum, old_csum;
+ __u32 csum;
+ __be32 old_csum;
old_csum = sb->s_checksum;
sb->s_checksum = 0;
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index d4851464b57e..3929c50428b1 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -178,7 +178,8 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
void *buf)
{
struct jbd2_journal_block_tail *tail;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return 1;
@@ -190,8 +191,7 @@ static int jbd2_descr_block_csum_verify(journal_t *j,
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
tail->t_checksum = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
/*
@@ -381,7 +381,8 @@ static int calc_chksums(journal_t *journal, struct buffer_head *bh,
static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
{
struct commit_header *h;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return 1;
@@ -392,21 +393,20 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
h->h_chksum[0] = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
void *buf, __u32 sequence)
{
__u32 csum32;
+ __be32 seq;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return 1;
- sequence = cpu_to_be32(sequence);
- csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&sequence,
- sizeof(sequence));
+ seq = cpu_to_be32(sequence);
+ csum32 = jbd2_chksum(j, j->j_csum_seed, (__u8 *)&seq, sizeof(seq));
csum32 = jbd2_chksum(j, csum32, buf, j->j_blocksize);
return tag->t_checksum == cpu_to_be16(csum32);
@@ -808,7 +808,8 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
void *buf)
{
struct jbd2_journal_revoke_tail *tail;
- __u32 provided, calculated;
+ __be32 provided;
+ __u32 calculated;
if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2))
return 1;
@@ -820,8 +821,7 @@ static int jbd2_revoke_block_csum_verify(journal_t *j,
calculated = jbd2_chksum(j, j->j_csum_seed, buf, j->j_blocksize);
tail->r_checksum = provided;
- provided = be32_to_cpu(provided);
- return provided == calculated;
+ return provided == cpu_to_be32(calculated);
}
/* Scan a revoke record, marking all blocks mentioned as revoked. */
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 8743ba9c6742..984c2bbf4f61 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3047,6 +3047,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
dir_index = (u32) ctx->pos;
+ /*
+ * NFSv4 reserves cookies 1 and 2 for . and .. so the value
+ * we return to the vfs is one greater than the one we use
+ * internally.
+ */
+ if (dir_index)
+ dir_index--;
+
if (dir_index > 1) {
struct dir_table_slot dirtab_slot;
@@ -3086,7 +3094,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
if (p->header.flag & BT_INTERNAL) {
jfs_err("jfs_readdir: bad index table");
DT_PUTPAGE(mp);
- ctx->pos = -1;
+ ctx->pos = DIREND;
return 0;
}
} else {
@@ -3094,14 +3102,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
/*
* self "."
*/
- ctx->pos = 0;
+ ctx->pos = 1;
if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR))
return 0;
}
/*
* parent ".."
*/
- ctx->pos = 1;
+ ctx->pos = 2;
if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR))
return 0;
@@ -3122,22 +3130,23 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
/*
* Legacy filesystem - OS/2 & Linux JFS < 0.3.6
*
- * pn = index = 0: First entry "."
- * pn = 0; index = 1: Second entry ".."
+ * pn = 0; index = 1: First entry "."
+ * pn = 0; index = 2: Second entry ".."
* pn > 0: Real entries, pn=1 -> leftmost page
* pn = index = -1: No more entries
*/
dtpos = ctx->pos;
- if (dtpos == 0) {
+ if (dtpos < 2) {
/* build "." entry */
+ ctx->pos = 1;
if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR))
return 0;
- dtoffset->index = 1;
+ dtoffset->index = 2;
ctx->pos = dtpos;
}
if (dtoffset->pn == 0) {
- if (dtoffset->index == 1) {
+ if (dtoffset->index == 2) {
/* build ".." entry */
if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR))
return 0;
@@ -3228,6 +3237,12 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
}
jfs_dirent->position = unique_pos++;
}
+ /*
+ * We add 1 to the index because we may
+ * use a value of 2 internally, and NFSv4
+ * doesn't like that.
+ */
+ jfs_dirent->position++;
} else {
jfs_dirent->position = dtpos;
len = min(d_namleft, DTLHDRDATALEN_LEGACY);
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 01bfe7662751..41e491b8e5d7 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -64,12 +64,17 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
nlm_init->protocol, nlm_version,
nlm_init->hostname, nlm_init->noresvport,
nlm_init->net);
- if (host == NULL) {
- lockd_down(nlm_init->net);
- return ERR_PTR(-ENOLCK);
- }
+ if (host == NULL)
+ goto out_nohost;
+ if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
+ goto out_nobind;
return host;
+out_nobind:
+ nlmclnt_release_host(host);
+out_nohost:
+ lockd_down(nlm_init->net);
+ return ERR_PTR(-ENOLCK);
}
EXPORT_SYMBOL_GPL(nlmclnt_init);
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 9760ecb9b60f..acd394716349 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -125,14 +125,15 @@ static void nlmclnt_setlockargs(struct nlm_rqst *req, struct file_lock *fl)
{
struct nlm_args *argp = &req->a_args;
struct nlm_lock *lock = &argp->lock;
+ char *nodename = req->a_host->h_rpcclnt->cl_nodename;
nlmclnt_next_cookie(&argp->cookie);
memcpy(&lock->fh, NFS_FH(file_inode(fl->fl_file)), sizeof(struct nfs_fh));
- lock->caller = utsname()->nodename;
+ lock->caller = nodename;
lock->oh.data = req->a_owner;
lock->oh.len = snprintf(req->a_owner, sizeof(req->a_owner), "%u@%s",
(unsigned int)fl->fl_u.nfs_fl.owner->pid,
- utsname()->nodename);
+ nodename);
lock->svid = fl->fl_u.nfs_fl.owner->pid;
lock->fl.fl_start = fl->fl_start;
lock->fl.fl_end = fl->fl_end;
diff --git a/fs/namei.c b/fs/namei.c
index 8b61d103a8a7..f415c6683a83 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -494,6 +494,50 @@ static inline void unlock_rcu_walk(void)
br_read_unlock(&vfsmount_lock);
}
+/*
+ * When we move over from the RCU domain to properly refcounted
+ * long-lived dentries, we need to check the sequence numbers
+ * we got before lookup very carefully.
+ *
+ * We cannot blindly increment a dentry refcount - even if it
+ * is not locked - if it is zero, because it may have gone
+ * through the final d_kill() logic already.
+ *
+ * So for a zero refcount, we need to get the spinlock (which is
+ * safe even for a dead dentry because the de-allocation is
+ * RCU-delayed), and check the sequence count under the lock.
+ *
+ * Once we have checked the sequence count, we know it is live,
+ * and since we hold the spinlock it cannot die from under us.
+ *
+ * In contrast, if the reference count wasn't zero, we can just
+ * increment the lockref without having to take the spinlock.
+ * Even if the sequence number ends up being stale, we haven't
+ * gone through the final dput() and killed the dentry yet.
+ */
+static inline int d_rcu_to_refcount(struct dentry *dentry, seqcount_t *validate, unsigned seq)
+{
+ int gotref;
+
+ gotref = lockref_get_or_lock(&dentry->d_lockref);
+
+ /* Does the sequence number still match? */
+ if (read_seqcount_retry(validate, seq)) {
+ if (gotref)
+ dput(dentry);
+ else
+ spin_unlock(&dentry->d_lock);
+ return -ECHILD;
+ }
+
+ /* Get the ref now, if we couldn't get it originally */
+ if (!gotref) {
+ dentry->d_lockref.count++;
+ spin_unlock(&dentry->d_lock);
+ }
+ return 0;
+}
+
/**
* unlazy_walk - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
@@ -518,29 +562,28 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
nd->root.dentry != fs->root.dentry)
goto err_root;
}
- spin_lock(&parent->d_lock);
+
+ /*
+ * For a negative lookup, the lookup sequence point is the parents
+ * sequence point, and it only needs to revalidate the parent dentry.
+ *
+ * For a positive lookup, we need to move both the parent and the
+ * dentry from the RCU domain to be properly refcounted. And the
+ * sequence number in the dentry validates *both* dentry counters,
+ * since we checked the sequence number of the parent after we got
+ * the child sequence number. So we know the parent must still
+ * be valid if the child sequence number is still valid.
+ */
if (!dentry) {
- if (!__d_rcu_to_refcount(parent, nd->seq))
- goto err_parent;
+ if (d_rcu_to_refcount(parent, &parent->d_seq, nd->seq) < 0)
+ goto err_root;
BUG_ON(nd->inode != parent->d_inode);
} else {
- if (dentry->d_parent != parent)
+ if (d_rcu_to_refcount(dentry, &dentry->d_seq, nd->seq) < 0)
+ goto err_root;
+ if (d_rcu_to_refcount(parent, &dentry->d_seq, nd->seq) < 0)
goto err_parent;
- spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
- if (!__d_rcu_to_refcount(dentry, nd->seq))
- goto err_child;
- /*
- * If the sequence check on the child dentry passed, then
- * the child has not been removed from its parent. This
- * means the parent dentry must be valid and able to take
- * a reference at this point.
- */
- BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
- BUG_ON(!parent->d_count);
- parent->d_count++;
- spin_unlock(&dentry->d_lock);
}
- spin_unlock(&parent->d_lock);
if (want_root) {
path_get(&nd->root);
spin_unlock(&fs->lock);
@@ -551,10 +594,8 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
nd->flags &= ~LOOKUP_RCU;
return 0;
-err_child:
- spin_unlock(&dentry->d_lock);
err_parent:
- spin_unlock(&parent->d_lock);
+ dput(dentry);
err_root:
if (want_root)
spin_unlock(&fs->lock);
@@ -585,14 +626,11 @@ static int complete_walk(struct nameidata *nd)
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
- spin_lock(&dentry->d_lock);
- if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
- spin_unlock(&dentry->d_lock);
+
+ if (d_rcu_to_refcount(dentry, &dentry->d_seq, nd->seq) < 0) {
unlock_rcu_walk();
return -ECHILD;
}
- BUG_ON(nd->inode != dentry->d_inode);
- spin_unlock(&dentry->d_lock);
mntget(nd->path.mnt);
unlock_rcu_walk();
}
@@ -2184,6 +2222,188 @@ user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
return s;
}
+/**
+ * umount_lookup_last - look up last component for umount
+ * @nd: pathwalk nameidata - currently pointing at parent directory of "last"
+ * @path: pointer to container for result
+ *
+ * This is a special lookup_last function just for umount. In this case, we
+ * need to resolve the path without doing any revalidation.
+ *
+ * The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
+ * mountpoints are always pinned in the dcache, their ancestors are too. Thus,
+ * in almost all cases, this lookup will be served out of the dcache. The only
+ * cases where it won't are if nd->last refers to a symlink or the path is
+ * bogus and it doesn't exist.
+ *
+ * Returns:
+ * -error: if there was an error during lookup. This includes -ENOENT if the
+ * lookup found a negative dentry. The nd->path reference will also be
+ * put in this case.
+ *
+ * 0: if we successfully resolved nd->path and found it to not to be a
+ * symlink that needs to be followed. "path" will also be populated.
+ * The nd->path reference will also be put.
+ *
+ * 1: if we successfully resolved nd->last and found it to be a symlink
+ * that needs to be followed. "path" will be populated with the path
+ * to the link, and nd->path will *not* be put.
+ */
+static int
+umount_lookup_last(struct nameidata *nd, struct path *path)
+{
+ int error = 0;
+ struct dentry *dentry;
+ struct dentry *dir = nd->path.dentry;
+
+ if (unlikely(nd->flags & LOOKUP_RCU)) {
+ WARN_ON_ONCE(1);
+ error = -ECHILD;
+ goto error_check;
+ }
+
+ nd->flags &= ~LOOKUP_PARENT;
+
+ if (unlikely(nd->last_type != LAST_NORM)) {
+ error = handle_dots(nd, nd->last_type);
+ if (!error)
+ dentry = dget(nd->path.dentry);
+ goto error_check;
+ }
+
+ mutex_lock(&dir->d_inode->i_mutex);
+ dentry = d_lookup(dir, &nd->last);
+ if (!dentry) {
+ /*
+ * No cached dentry. Mounted dentries are pinned in the cache,
+ * so that means that this dentry is probably a symlink or the
+ * path doesn't actually point to a mounted dentry.
+ */
+ dentry = d_alloc(dir, &nd->last);
+ if (!dentry) {
+ error = -ENOMEM;
+ } else {
+ dentry = lookup_real(dir->d_inode, dentry, nd->flags);
+ if (IS_ERR(dentry))
+ error = PTR_ERR(dentry);
+ }
+ }
+ mutex_unlock(&dir->d_inode->i_mutex);
+
+error_check:
+ if (!error) {
+ if (!dentry->d_inode) {
+ error = -ENOENT;
+ dput(dentry);
+ } else {
+ path->dentry = dentry;
+ path->mnt = mntget(nd->path.mnt);
+ if (should_follow_link(dentry->d_inode,
+ nd->flags & LOOKUP_FOLLOW))
+ return 1;
+ follow_mount(path);
+ }
+ }
+ terminate_walk(nd);
+ return error;
+}
+
+/**
+ * path_umountat - look up a path to be umounted
+ * @dfd: directory file descriptor to start walk from
+ * @name: full pathname to walk
+ * @flags: lookup flags
+ * @nd: pathwalk nameidata
+ *
+ * Look up the given name, but don't attempt to revalidate the last component.
+ * Returns 0 and "path" will be valid on success; Retuns error otherwise.
+ */
+static int
+path_umountat(int dfd, const char *name, struct path *path, unsigned int flags)
+{
+ struct file *base = NULL;
+ struct nameidata nd;
+ int err;
+
+ err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
+ if (unlikely(err))
+ return err;
+
+ current->total_link_count = 0;
+ err = link_path_walk(name, &nd);
+ if (err)
+ goto out;
+
+ /* If we're in rcuwalk, drop out of it to handle last component */
+ if (nd.flags & LOOKUP_RCU) {
+ err = unlazy_walk(&nd, NULL);
+ if (err) {
+ terminate_walk(&nd);
+ goto out;
+ }
+ }
+
+ err = umount_lookup_last(&nd, path);
+ while (err > 0) {
+ void *cookie;
+ struct path link = *path;
+ err = may_follow_link(&link, &nd);
+ if (unlikely(err))
+ break;
+ nd.flags |= LOOKUP_PARENT;
+ err = follow_link(&link, &nd, &cookie);
+ if (err)
+ break;
+ err = umount_lookup_last(&nd, path);
+ put_link(&nd, &link, cookie);
+ }
+out:
+ if (base)
+ fput(base);
+
+ if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
+ path_put(&nd.root);
+
+ return err;
+}
+
+/**
+ * user_path_umountat - lookup a path from userland in order to umount it
+ * @dfd: directory file descriptor
+ * @name: pathname from userland
+ * @flags: lookup flags
+ * @path: pointer to container to hold result
+ *
+ * A umount is a special case for path walking. We're not actually interested
+ * in the inode in this situation, and ESTALE errors can be a problem. We
+ * simply want track down the dentry and vfsmount attached at the mountpoint
+ * and avoid revalidating the last component.
+ *
+ * Returns 0 and populates "path" on success.
+ */
+int
+user_path_umountat(int dfd, const char __user *name, unsigned int flags,
+ struct path *path)
+{
+ struct filename *s = getname(name);
+ int error;
+
+ if (IS_ERR(s))
+ return PTR_ERR(s);
+
+ error = path_umountat(dfd, s->name, path, flags | LOOKUP_RCU);
+ if (unlikely(error == -ECHILD))
+ error = path_umountat(dfd, s->name, path, flags);
+ if (unlikely(error == -ESTALE))
+ error = path_umountat(dfd, s->name, path, flags | LOOKUP_REVAL);
+
+ if (likely(!error))
+ audit_inode(s, path->dentry, 0);
+
+ putname(s);
+ return error;
+}
+
/*
* It's inline, so penalty for filesystems that don't use sticky bit is
* minimal.
@@ -3327,7 +3547,7 @@ void dentry_unhash(struct dentry *dentry)
{
shrink_dcache_parent(dentry);
spin_lock(&dentry->d_lock);
- if (dentry->d_count == 1)
+ if (dentry->d_lockref.count == 1)
__d_drop(dentry);
spin_unlock(&dentry->d_lock);
}
diff --git a/fs/namespace.c b/fs/namespace.c
index 7b1ca9ba0b0a..ad8ea9bc2518 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1318,7 +1318,7 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
- retval = user_path_at(AT_FDCWD, name, lookup_flags, &path);
+ retval = user_path_umountat(AT_FDCWD, name, lookup_flags, &path);
if (retval)
goto out;
mnt = real_mount(path.mnt);
@@ -1429,7 +1429,7 @@ struct vfsmount *collect_mounts(struct path *path)
CL_COPY_ALL | CL_PRIVATE);
namespace_unlock();
if (IS_ERR(tree))
- return NULL;
+ return ERR_CAST(tree);
return &tree->mnt;
}
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index af6e806044d7..941246f2b43d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -463,7 +463,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
unlock_new_inode(inode);
} else
nfs_refresh_inode(inode, fattr);
- nfs_setsecurity(inode, fattr, label);
dprintk("NFS: nfs_fhget(%s/%Ld fh_crc=0x%08x ct=%d)\n",
inode->i_sb->s_id,
(long long)NFS_FILEID(inode),
@@ -963,9 +962,15 @@ EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
{
struct nfs_inode *nfsi = NFS_I(inode);
-
+ int ret;
+
if (mapping->nrpages != 0) {
- int ret = invalidate_inode_pages2(mapping);
+ if (S_ISREG(inode->i_mode)) {
+ ret = nfs_sync_mapping(mapping);
+ if (ret < 0)
+ return ret;
+ }
+ ret = invalidate_inode_pages2(mapping);
if (ret < 0)
return ret;
}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index cf11799297c4..108a774095f7 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3071,15 +3071,13 @@ struct rpc_clnt *
nfs4_proc_lookup_mountpoint(struct inode *dir, struct qstr *name,
struct nfs_fh *fhandle, struct nfs_fattr *fattr)
{
+ struct rpc_clnt *client = NFS_CLIENT(dir);
int status;
- struct rpc_clnt *client = rpc_clone_client(NFS_CLIENT(dir));
status = nfs4_proc_lookup_common(&client, dir, name, fhandle, fattr, NULL);
- if (status < 0) {
- rpc_shutdown_client(client);
+ if (status < 0)
return ERR_PTR(status);
- }
- return client;
+ return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
}
static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 71fdc0dfa0d2..f6db66d8f647 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2478,6 +2478,10 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
if (server->flags & NFS_MOUNT_NOAC)
sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+ if (mount_info->cloned != NULL && mount_info->cloned->sb != NULL)
+ if (mount_info->cloned->sb->s_flags & MS_SYNCHRONOUS)
+ sb_mntdata.mntflags |= MS_SYNCHRONOUS;
+
/* Get a superblock - note that we may end up sharing one that already exists */
s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata);
if (IS_ERR(s)) {
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 0d4c410e4589..419572f33b72 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1524,7 +1524,7 @@ 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 + 0 + /* eir_flags, spr_how, SP4_NONE (for now) */\
+ 1 + 1 + 2 + /* eir_flags, spr_how, spo_must_enforce & _allow */\
2 + /*eir_server_owner.so_minor_id */\
/* eir_server_owner.so_major_id<> */\
XDR_QUADLEN(NFS4_OPAQUE_LIMIT) + 1 +\
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 280acef6f0dc..43f42290e5df 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1264,6 +1264,8 @@ static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp)
struct svc_cred *cr = &rqstp->rq_cred;
u32 service;
+ if (!cr->cr_gss_mech)
+ return false;
service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor);
return service == RPC_GSS_SVC_INTEGRITY ||
service == RPC_GSS_SVC_PRIVACY;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0c0f3ea90de5..d9454fe5653f 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1816,10 +1816,7 @@ static __be32 nfsd4_encode_fs_location4(struct nfsd4_fs_location *location,
static __be32 nfsd4_encode_path(const struct path *root,
const struct path *path, __be32 **pp, int *buflen)
{
- struct path cur = {
- .mnt = path->mnt,
- .dentry = path->dentry,
- };
+ struct path cur = *path;
__be32 *p = *pp;
struct dentry **components = NULL;
unsigned int ncomponents = 0;
@@ -1859,14 +1856,19 @@ static __be32 nfsd4_encode_path(const struct path *root,
while (ncomponents) {
struct dentry *dentry = components[ncomponents - 1];
- unsigned int len = dentry->d_name.len;
+ unsigned int len;
+ spin_lock(&dentry->d_lock);
+ len = dentry->d_name.len;
*buflen -= 4 + (XDR_QUADLEN(len) << 2);
- if (*buflen < 0)
+ if (*buflen < 0) {
+ spin_unlock(&dentry->d_lock);
goto out_free;
+ }
WRITE32(len);
WRITEMEM(dentry->d_name.name, len);
dprintk("/%s", dentry->d_name.name);
+ spin_unlock(&dentry->d_lock);
dput(dentry);
ncomponents--;
}
@@ -3360,7 +3362,8 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
8 /* eir_clientid */ +
4 /* eir_sequenceid */ +
4 /* eir_flags */ +
- 4 /* spr_how (SP4_NONE) */ +
+ 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) +
@@ -3372,8 +3375,6 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr,
WRITE32(exid->seqid);
WRITE32(exid->flags);
- /* state_protect4_r. Currently only support SP4_NONE */
- BUG_ON(exid->spa_how != SP4_NONE);
WRITE32(exid->spa_how);
switch (exid->spa_how) {
case SP4_NONE:
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index dc9a913784ab..2d8be51f90dc 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
if (err == -EOPNOTSUPP) {
set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
- bio_put(bio);
- /* to be detected by submit_seg_bio() */
+ /* to be detected by nilfs_segbuf_submit_bio() */
}
if (!uptodate)
@@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
bio->bi_private = segbuf;
bio_get(bio);
submit_bio(mode, bio);
+ segbuf->sb_nbio++;
if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
bio_put(bio);
err = -EOPNOTSUPP;
goto failed;
}
- segbuf->sb_nbio++;
bio_put(bio);
wi->bio = NULL;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index af3ba0478cdf..7ac2a122ca1d 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -994,23 +994,16 @@ static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
return ret;
}
-static int nilfs_tree_was_touched(struct dentry *root_dentry)
-{
- return d_count(root_dentry) > 1;
-}
-
/**
- * nilfs_try_to_shrink_tree() - try to shrink dentries of a checkpoint
+ * nilfs_tree_is_busy() - try to shrink dentries of a checkpoint
* @root_dentry: root dentry of the tree to be shrunk
*
* This function returns true if the tree was in-use.
*/
-static int nilfs_try_to_shrink_tree(struct dentry *root_dentry)
+static bool nilfs_tree_is_busy(struct dentry *root_dentry)
{
- if (have_submounts(root_dentry))
- return true;
shrink_dcache_parent(root_dentry);
- return nilfs_tree_was_touched(root_dentry);
+ return d_count(root_dentry) > 1;
}
int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
@@ -1034,8 +1027,7 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
if (inode) {
dentry = d_find_alias(inode);
if (dentry) {
- if (nilfs_tree_was_touched(dentry))
- ret = nilfs_try_to_shrink_tree(dentry);
+ ret = nilfs_tree_is_busy(dentry);
dput(dentry);
}
iput(inode);
@@ -1331,11 +1323,8 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
s->s_flags |= MS_ACTIVE;
} else if (!sd.cno) {
- int busy = false;
-
- if (nilfs_tree_was_touched(s->s_root)) {
- busy = nilfs_try_to_shrink_tree(s->s_root);
- if (busy && (flags ^ s->s_flags) & MS_RDONLY) {
+ if (nilfs_tree_is_busy(s->s_root)) {
+ if ((flags ^ s->s_flags) & MS_RDONLY) {
printk(KERN_ERR "NILFS: the device already "
"has a %s mount.\n",
(s->s_flags & MS_RDONLY) ?
@@ -1343,8 +1332,7 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
err = -EBUSY;
goto failed_super;
}
- }
- if (!busy) {
+ } else {
/*
* Try remount to setup mount states if the current
* tree is not mounted and only snapshots use this sb.
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 79736a28d84f..94417a85ce6e 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -565,9 +565,7 @@ bail:
static void ocfs2_dio_end_io(struct kiocb *iocb,
loff_t offset,
ssize_t bytes,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct inode *inode = file_inode(iocb->ki_filp);
int level;
@@ -592,10 +590,6 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
level = ocfs2_iocb_rw_locked_level(iocb);
ocfs2_rw_unlock(inode, level);
-
- inode_dio_done(inode);
- if (is_async)
- aio_complete(iocb, ret, 0);
}
/*
@@ -1757,7 +1751,7 @@ try_again:
goto out;
} else if (ret == 1) {
clusters_need = wc->w_clen;
- ret = ocfs2_refcount_cow(inode, filp, di_bh,
+ ret = ocfs2_refcount_cow(inode, di_bh,
wc->w_cpos, wc->w_clen, UINT_MAX);
if (ret) {
mlog_errno(ret);
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index eb760d8acd50..30544ce8e9f7 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -2153,11 +2153,9 @@ int ocfs2_empty_dir(struct inode *inode)
{
int ret;
struct ocfs2_empty_dir_priv priv = {
- .ctx.actor = ocfs2_empty_dir_filldir
+ .ctx.actor = ocfs2_empty_dir_filldir,
};
- memset(&priv, 0, sizeof(priv));
-
if (ocfs2_dir_indexed(inode)) {
ret = ocfs2_empty_dir_dx(inode, &priv);
if (ret)
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 41000f223ca4..3261d71319ee 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -370,7 +370,7 @@ static int ocfs2_cow_file_pos(struct inode *inode,
if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
goto out;
- return ocfs2_refcount_cow(inode, NULL, fe_bh, cpos, 1, cpos+1);
+ return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
out:
return status;
@@ -899,7 +899,7 @@ static int ocfs2_zero_extend_get_range(struct inode *inode,
zero_clusters = last_cpos - zero_cpos;
if (needs_cow) {
- rc = ocfs2_refcount_cow(inode, NULL, di_bh, zero_cpos,
+ rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos,
zero_clusters, UINT_MAX);
if (rc) {
mlog_errno(rc);
@@ -2078,7 +2078,7 @@ static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
*meta_level = 1;
- ret = ocfs2_refcount_cow(inode, file, di_bh, cpos, clusters, UINT_MAX);
+ ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
if (ret)
mlog_errno(ret);
out:
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 96f9ac237e86..0a992737dcaf 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -537,7 +537,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb,
extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);
return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks +
- ocfs2_quota_trans_credits(sb) + bits_wanted;
+ ocfs2_quota_trans_credits(sb);
}
static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index f1fc172175b6..452068b45749 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -69,7 +69,7 @@ static int __ocfs2_move_extent(handle_t *handle,
u64 ino = ocfs2_metadata_cache_owner(context->et.et_ci);
u64 old_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cpos);
- ret = ocfs2_duplicate_clusters_by_page(handle, context->file, cpos,
+ ret = ocfs2_duplicate_clusters_by_page(handle, inode, cpos,
p_cpos, new_p_cpos, len);
if (ret) {
mlog_errno(ret);
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 9f6b96a09615..a70d604593b6 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -49,7 +49,6 @@
struct ocfs2_cow_context {
struct inode *inode;
- struct file *file;
u32 cow_start;
u32 cow_len;
struct ocfs2_extent_tree data_et;
@@ -66,7 +65,7 @@ struct ocfs2_cow_context {
u32 *num_clusters,
unsigned int *extent_flags);
int (*cow_duplicate_clusters)(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
};
@@ -2922,14 +2921,12 @@ static int ocfs2_clear_cow_buffer(handle_t *handle, struct buffer_head *bh)
}
int ocfs2_duplicate_clusters_by_page(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len)
{
int ret = 0, partial;
- struct inode *inode = file_inode(file);
- struct ocfs2_caching_info *ci = INODE_CACHE(inode);
- struct super_block *sb = ocfs2_metadata_cache_get_super(ci);
+ struct super_block *sb = inode->i_sb;
u64 new_block = ocfs2_clusters_to_blocks(sb, new_cluster);
struct page *page;
pgoff_t page_index;
@@ -2978,13 +2975,6 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
if (PAGE_CACHE_SIZE <= OCFS2_SB(sb)->s_clustersize)
BUG_ON(PageDirty(page));
- if (PageReadahead(page)) {
- page_cache_async_readahead(mapping,
- &file->f_ra, file,
- page, page_index,
- readahead_pages);
- }
-
if (!PageUptodate(page)) {
ret = block_read_full_page(page, ocfs2_get_block);
if (ret) {
@@ -3004,7 +2994,8 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
}
}
- ocfs2_map_and_dirty_page(inode, handle, from, to,
+ ocfs2_map_and_dirty_page(inode,
+ handle, from, to,
page, 0, &new_block);
mark_page_accessed(page);
unlock:
@@ -3020,12 +3011,11 @@ unlock:
}
int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len)
{
int ret = 0;
- struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
struct ocfs2_caching_info *ci = INODE_CACHE(inode);
int i, blocks = ocfs2_clusters_to_blocks(sb, new_len);
@@ -3150,7 +3140,7 @@ static int ocfs2_replace_clusters(handle_t *handle,
/*If the old clusters is unwritten, no need to duplicate. */
if (!(ext_flags & OCFS2_EXT_UNWRITTEN)) {
- ret = context->cow_duplicate_clusters(handle, context->file,
+ ret = context->cow_duplicate_clusters(handle, context->inode,
cpos, old, new, len);
if (ret) {
mlog_errno(ret);
@@ -3428,35 +3418,12 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
return ret;
}
-static void ocfs2_readahead_for_cow(struct inode *inode,
- struct file *file,
- u32 start, u32 len)
-{
- struct address_space *mapping;
- pgoff_t index;
- unsigned long num_pages;
- int cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-
- if (!file)
- return;
-
- mapping = file->f_mapping;
- num_pages = (len << cs_bits) >> PAGE_CACHE_SHIFT;
- if (!num_pages)
- num_pages = 1;
-
- index = ((loff_t)start << cs_bits) >> PAGE_CACHE_SHIFT;
- page_cache_sync_readahead(mapping, &file->f_ra, file,
- index, num_pages);
-}
-
/*
* Starting at cpos, try to CoW write_len clusters. Don't CoW
* past max_cpos. This will stop when it runs into a hole or an
* unrefcounted extent.
*/
static int ocfs2_refcount_cow_hunk(struct inode *inode,
- struct file *file,
struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos)
{
@@ -3485,8 +3452,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
BUG_ON(cow_len == 0);
- ocfs2_readahead_for_cow(inode, file, cow_start, cow_len);
-
context = kzalloc(sizeof(struct ocfs2_cow_context), GFP_NOFS);
if (!context) {
ret = -ENOMEM;
@@ -3508,7 +3473,6 @@ static int ocfs2_refcount_cow_hunk(struct inode *inode,
context->ref_root_bh = ref_root_bh;
context->cow_duplicate_clusters = ocfs2_duplicate_clusters_by_page;
context->get_clusters = ocfs2_di_get_clusters;
- context->file = file;
ocfs2_init_dinode_extent_tree(&context->data_et,
INODE_CACHE(inode), di_bh);
@@ -3537,7 +3501,6 @@ out:
* clusters between cpos and cpos+write_len are safe to modify.
*/
int ocfs2_refcount_cow(struct inode *inode,
- struct file *file,
struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos)
{
@@ -3557,7 +3520,7 @@ int ocfs2_refcount_cow(struct inode *inode,
num_clusters = write_len;
if (ext_flags & OCFS2_EXT_REFCOUNTED) {
- ret = ocfs2_refcount_cow_hunk(inode, file, di_bh, cpos,
+ ret = ocfs2_refcount_cow_hunk(inode, di_bh, cpos,
num_clusters, max_cpos);
if (ret) {
mlog_errno(ret);
diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h
index 7754608c83a4..6422bbcdb525 100644
--- a/fs/ocfs2/refcounttree.h
+++ b/fs/ocfs2/refcounttree.h
@@ -53,7 +53,7 @@ int ocfs2_prepare_refcount_change_for_del(struct inode *inode,
int *credits,
int *ref_blocks);
int ocfs2_refcount_cow(struct inode *inode,
- struct file *filep, struct buffer_head *di_bh,
+ struct buffer_head *di_bh,
u32 cpos, u32 write_len, u32 max_cpos);
typedef int (ocfs2_post_refcount_func)(struct inode *inode,
@@ -85,11 +85,11 @@ int ocfs2_refcount_cow_xattr(struct inode *inode,
u32 cpos, u32 write_len,
struct ocfs2_post_refcount *post);
int ocfs2_duplicate_clusters_by_page(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
int ocfs2_duplicate_clusters_by_jbd(handle_t *handle,
- struct file *file,
+ struct inode *inode,
u32 cpos, u32 old_cluster,
u32 new_cluster, u32 new_len);
int ocfs2_cow_sync_writeback(struct super_block *sb,
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 854d80955bf8..121da2dc3be8 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1022,7 +1022,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
struct inode *inode = NULL;
struct ocfs2_super *osb = NULL;
struct buffer_head *bh = NULL;
- char nodestr[8];
+ char nodestr[12];
struct ocfs2_blockcheck_stats stats;
trace_ocfs2_fill_super(sb, data, silent);
diff --git a/fs/open.c b/fs/open.c
index d53e29895082..8070825b285b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -485,14 +485,13 @@ out_unlock:
SYSCALL_DEFINE2(fchmod, unsigned int, fd, umode_t, mode)
{
- struct file * file;
+ struct fd f = fdget(fd);
int err = -EBADF;
- file = fget(fd);
- if (file) {
- audit_inode(NULL, file->f_path.dentry, 0);
- err = chmod_common(&file->f_path, mode);
- fput(file);
+ if (f.file) {
+ audit_inode(NULL, f.file->f_path.dentry, 0);
+ err = chmod_common(&f.file->f_path, mode);
+ fdput(f);
}
return err;
}
@@ -823,7 +822,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
int lookup_flags = 0;
int acc_mode;
- if (flags & O_CREAT)
+ if (flags & (O_CREAT | __O_TMPFILE))
op->mode = (mode & S_IALLUGO) | S_IFREG;
else
op->mode = 0;
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 75f2890abbd8..0ff80f9b930f 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -230,8 +230,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
if (!dir_emit_dots(file, ctx))
goto out;
- if (!dir_emit_dots(file, ctx))
- goto out;
files = get_files_struct(p);
if (!files)
goto out;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 94441a407337..737e15615b04 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -271,7 +271,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
de = next;
} while (de);
spin_unlock(&proc_subdir_lock);
- return 0;
+ return 1;
}
int proc_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 073aea60cf8f..9f8ef9b7674d 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -285,6 +285,20 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
return rv;
}
+static unsigned long proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct proc_dir_entry *pde = PDE(file_inode(file));
+ int rv = -EIO;
+ unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+ if (use_pde(pde)) {
+ get_unmapped_area = pde->proc_fops->get_unmapped_area;
+ if (get_unmapped_area)
+ rv = get_unmapped_area(file, orig_addr, len, pgoff, flags);
+ unuse_pde(pde);
+ }
+ return rv;
+}
+
static int proc_reg_open(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
@@ -356,6 +370,7 @@ static const struct file_operations proc_reg_file_ops = {
.compat_ioctl = proc_reg_compat_ioctl,
#endif
.mmap = proc_reg_mmap,
+ .get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
@@ -368,6 +383,7 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
+ .get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 229e366598da..e0a790da726d 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -205,7 +205,9 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr
static int proc_root_readdir(struct file *file, struct dir_context *ctx)
{
if (ctx->pos < FIRST_PROCESS_ENTRY) {
- proc_readdir(file, ctx);
+ int error = proc_readdir(file, ctx);
+ if (unlikely(error <= 0))
+ return error;
ctx->pos = FIRST_PROCESS_ENTRY;
}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index dbf61f6174f0..107d026f5d6e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -730,8 +730,16 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
* of how soft-dirty works.
*/
pte_t ptent = *pte;
- ptent = pte_wrprotect(ptent);
- ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+
+ if (pte_present(ptent)) {
+ ptent = pte_wrprotect(ptent);
+ ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+ } else if (is_swap_pte(ptent)) {
+ ptent = pte_swp_clear_soft_dirty(ptent);
+ } else if (pte_file(ptent)) {
+ ptent = pte_file_clear_soft_dirty(ptent);
+ }
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -752,14 +760,15 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE) {
ptent = *pte;
- if (!pte_present(ptent))
- continue;
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty(vma, addr, pte);
continue;
}
+ if (!pte_present(ptent))
+ continue;
+
page = vm_normal_page(vma, addr, ptent);
if (!page)
continue;
@@ -859,7 +868,7 @@ typedef struct {
} pagemap_entry_t;
struct pagemapread {
- int pos, len;
+ int pos, len; /* units: PM_ENTRY_BYTES, not bytes */
pagemap_entry_t *buffer;
bool v2;
};
@@ -867,7 +876,7 @@ struct pagemapread {
#define PAGEMAP_WALK_SIZE (PMD_SIZE)
#define PAGEMAP_WALK_MASK (PMD_MASK)
-#define PM_ENTRY_BYTES sizeof(u64)
+#define PM_ENTRY_BYTES sizeof(pagemap_entry_t)
#define PM_STATUS_BITS 3
#define PM_STATUS_OFFSET (64 - PM_STATUS_BITS)
#define PM_STATUS_MASK (((1LL << PM_STATUS_BITS) - 1) << PM_STATUS_OFFSET)
@@ -930,8 +939,10 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
flags = PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
} else if (is_swap_pte(pte)) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
+ swp_entry_t entry;
+ if (pte_swp_soft_dirty(pte))
+ flags2 |= __PM_SOFT_DIRTY;
+ entry = pte_to_swp_entry(pte);
frame = swp_type(entry) |
(swp_offset(entry) << MAX_SWAPFILES_SHIFT);
flags = PM_SWAP;
@@ -1116,8 +1127,8 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
goto out_task;
pm.v2 = soft_dirty_cleared;
- pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
- pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
+ pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
+ pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY);
ret = -ENOMEM;
if (!pm.buffer)
goto out_task;
diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index ca71db69da07..983d9510becc 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -1,6 +1,8 @@
config PSTORE
bool "Persistent store support"
default n
+ select ZLIB_DEFLATE
+ select ZLIB_INFLATE
help
This option enables generic access to platform level
persistent storage via "pstore" filesystem that can
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 71bf5f4ae84c..12823845d324 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -275,8 +275,8 @@ int pstore_is_mounted(void)
* Set the mtime & ctime to the date that this record was originally stored.
*/
int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
- char *data, size_t size, struct timespec time,
- struct pstore_info *psi)
+ char *data, bool compressed, size_t size,
+ struct timespec time, struct pstore_info *psi)
{
struct dentry *root = pstore_sb->s_root;
struct dentry *dentry;
@@ -315,7 +315,8 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
switch (type) {
case PSTORE_TYPE_DMESG:
- sprintf(name, "dmesg-%s-%lld", psname, id);
+ sprintf(name, "dmesg-%s-%lld%s", psname, id,
+ compressed ? ".enc.z" : "");
break;
case PSTORE_TYPE_CONSOLE:
sprintf(name, "console-%s", psname);
@@ -345,9 +346,8 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
mutex_lock(&root->d_inode->i_mutex);
- rc = -ENOSPC;
dentry = d_alloc_name(root, name);
- if (IS_ERR(dentry))
+ if (!dentry)
goto fail_lockedalloc;
memcpy(private->data, data, size);
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index 937d820f273c..3b3d305277c4 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -50,8 +50,9 @@ extern struct pstore_info *psinfo;
extern void pstore_set_kmsg_bytes(int);
extern void pstore_get_records(int);
extern int pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
- int count, char *data, size_t size,
- struct timespec time, struct pstore_info *psi);
+ int count, char *data, bool compressed,
+ size_t size, struct timespec time,
+ struct pstore_info *psi);
extern int pstore_is_mounted(void);
#endif
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 422962ae9fc2..4ffb7ab5e397 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -26,6 +26,7 @@
#include <linux/console.h>
#include <linux/module.h>
#include <linux/pstore.h>
+#include <linux/zlib.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/slab.h>
@@ -65,6 +66,15 @@ struct pstore_info *psinfo;
static char *backend;
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
+
+static char *big_oops_buf;
+static size_t big_oops_buf_sz;
+
/* How much of the console log to snapshot */
static unsigned long kmsg_bytes = 10240;
@@ -117,6 +127,121 @@ bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
}
EXPORT_SYMBOL_GPL(pstore_cannot_block_path);
+/* Derived from logfs_compress() */
+static int pstore_compress(const void *in, void *out, size_t inlen,
+ size_t outlen)
+{
+ int err, ret;
+
+ ret = -EIO;
+ err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+ MEM_LEVEL, Z_DEFAULT_STRATEGY);
+ if (err != Z_OK)
+ goto error;
+
+ stream.next_in = in;
+ stream.avail_in = inlen;
+ stream.total_in = 0;
+ stream.next_out = out;
+ stream.avail_out = outlen;
+ stream.total_out = 0;
+
+ err = zlib_deflate(&stream, Z_FINISH);
+ if (err != Z_STREAM_END)
+ goto error;
+
+ err = zlib_deflateEnd(&stream);
+ if (err != Z_OK)
+ goto error;
+
+ if (stream.total_out >= stream.total_in)
+ goto error;
+
+ ret = stream.total_out;
+error:
+ return ret;
+}
+
+/* Derived from logfs_uncompress */
+static int pstore_decompress(void *in, void *out, size_t inlen, size_t outlen)
+{
+ int err, ret;
+
+ ret = -EIO;
+ err = zlib_inflateInit(&stream);
+ if (err != Z_OK)
+ goto error;
+
+ stream.next_in = in;
+ stream.avail_in = inlen;
+ stream.total_in = 0;
+ stream.next_out = out;
+ stream.avail_out = outlen;
+ stream.total_out = 0;
+
+ err = zlib_inflate(&stream, Z_FINISH);
+ if (err != Z_STREAM_END)
+ goto error;
+
+ err = zlib_inflateEnd(&stream);
+ if (err != Z_OK)
+ goto error;
+
+ ret = stream.total_out;
+error:
+ return ret;
+}
+
+static void allocate_buf_for_compression(void)
+{
+ size_t size;
+
+ big_oops_buf_sz = (psinfo->bufsize * 100) / 45;
+ big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+ if (big_oops_buf) {
+ size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL),
+ zlib_inflate_workspacesize());
+ stream.workspace = kmalloc(size, GFP_KERNEL);
+ if (!stream.workspace) {
+ pr_err("pstore: No memory for compression workspace; "
+ "skipping compression\n");
+ kfree(big_oops_buf);
+ big_oops_buf = NULL;
+ }
+ } else {
+ pr_err("No memory for uncompressed data; "
+ "skipping compression\n");
+ stream.workspace = NULL;
+ }
+
+}
+
+/*
+ * Called when compression fails, since the printk buffer
+ * would be fetched for compression calling it again when
+ * compression fails would have moved the iterator of
+ * printk buffer which results in fetching old contents.
+ * Copy the recent messages from big_oops_buf to psinfo->buf
+ */
+static size_t copy_kmsg_to_buffer(int hsize, size_t len)
+{
+ size_t total_len;
+ size_t diff;
+
+ total_len = hsize + len;
+
+ if (total_len > psinfo->bufsize) {
+ diff = total_len - psinfo->bufsize + hsize;
+ memcpy(psinfo->buf, big_oops_buf, hsize);
+ memcpy(psinfo->buf + hsize, big_oops_buf + diff,
+ psinfo->bufsize - hsize);
+ total_len = psinfo->bufsize;
+ } else
+ memcpy(psinfo->buf, big_oops_buf, total_len);
+
+ return total_len;
+}
+
/*
* callback from kmsg_dump. (s2,l2) has the most recently
* written bytes, older bytes are in (s1,l1). Save as much
@@ -148,22 +273,56 @@ static void pstore_dump(struct kmsg_dumper *dumper,
char *dst;
unsigned long size;
int hsize;
+ int zipped_len = -1;
size_t len;
+ bool compressed;
+ size_t total_len;
- dst = psinfo->buf;
- hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount, part);
- size = psinfo->bufsize - hsize;
- dst += hsize;
+ if (big_oops_buf) {
+ dst = big_oops_buf;
+ hsize = sprintf(dst, "%s#%d Part%d\n", why,
+ oopscount, part);
+ size = big_oops_buf_sz - hsize;
- if (!kmsg_dump_get_buffer(dumper, true, dst, size, &len))
- break;
+ if (!kmsg_dump_get_buffer(dumper, true, dst + hsize,
+ size, &len))
+ break;
+
+ zipped_len = pstore_compress(dst, psinfo->buf,
+ hsize + len, psinfo->bufsize);
+
+ if (zipped_len > 0) {
+ compressed = true;
+ total_len = zipped_len;
+ } else {
+ pr_err("pstore: compression failed for Part %d"
+ " returned %d\n", part, zipped_len);
+ pr_err("pstore: Capture uncompressed"
+ " oops/panic report of Part %d\n", part);
+ compressed = false;
+ total_len = copy_kmsg_to_buffer(hsize, len);
+ }
+ } else {
+ dst = psinfo->buf;
+ hsize = sprintf(dst, "%s#%d Part%d\n", why, oopscount,
+ part);
+ size = psinfo->bufsize - hsize;
+ dst += hsize;
+
+ if (!kmsg_dump_get_buffer(dumper, true, dst,
+ size, &len))
+ break;
+
+ compressed = false;
+ total_len = hsize + len;
+ }
ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part,
- oopscount, hsize, hsize + len, psinfo);
+ oopscount, compressed, total_len, psinfo);
if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
pstore_new_entry = 1;
- total += hsize + len;
+ total += total_len;
part++;
}
if (pstore_cannot_block_path(reason)) {
@@ -221,10 +380,10 @@ static void pstore_register_console(void) {}
static int pstore_write_compat(enum pstore_type_id type,
enum kmsg_dump_reason reason,
u64 *id, unsigned int part, int count,
- size_t hsize, size_t size,
+ bool compressed, size_t size,
struct pstore_info *psi)
{
- return psi->write_buf(type, reason, id, part, psinfo->buf, hsize,
+ return psi->write_buf(type, reason, id, part, psinfo->buf, compressed,
size, psi);
}
@@ -261,6 +420,8 @@ int pstore_register(struct pstore_info *psi)
return -EINVAL;
}
+ allocate_buf_for_compression();
+
if (pstore_is_mounted())
pstore_get_records(0);
@@ -297,6 +458,8 @@ void pstore_get_records(int quiet)
enum pstore_type_id type;
struct timespec time;
int failed = 0, rc;
+ bool compressed;
+ int unzipped_len = -1;
if (!psi)
return;
@@ -305,11 +468,32 @@ void pstore_get_records(int quiet)
if (psi->open && psi->open(psi))
goto out;
- while ((size = psi->read(&id, &type, &count, &time, &buf, psi)) > 0) {
+ while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed,
+ psi)) > 0) {
+ if (compressed && (type == PSTORE_TYPE_DMESG)) {
+ if (big_oops_buf)
+ unzipped_len = pstore_decompress(buf,
+ big_oops_buf, size,
+ big_oops_buf_sz);
+
+ if (unzipped_len > 0) {
+ buf = big_oops_buf;
+ size = unzipped_len;
+ compressed = false;
+ } else {
+ pr_err("pstore: decompression failed;"
+ "returned %d\n", unzipped_len);
+ compressed = true;
+ }
+ }
rc = pstore_mkfile(type, psi->name, id, count, buf,
- (size_t)size, time, psi);
- kfree(buf);
- buf = NULL;
+ compressed, (size_t)size, time, psi);
+ if (unzipped_len < 0) {
+ /* Free buffer other than big oops */
+ kfree(buf);
+ buf = NULL;
+ } else
+ unzipped_len = -1;
if (rc && (rc != -EEXIST || !quiet))
failed++;
}
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index a6119f9469e2..fa8cef2cca3a 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -131,9 +131,31 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max,
return prz;
}
+static void ramoops_read_kmsg_hdr(char *buffer, struct timespec *time,
+ bool *compressed)
+{
+ char data_type;
+
+ if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n",
+ &time->tv_sec, &time->tv_nsec, &data_type) == 3) {
+ if (data_type == 'C')
+ *compressed = true;
+ else
+ *compressed = false;
+ } else if (sscanf(buffer, RAMOOPS_KERNMSG_HDR "%lu.%lu\n",
+ &time->tv_sec, &time->tv_nsec) == 2) {
+ *compressed = false;
+ } else {
+ time->tv_sec = 0;
+ time->tv_nsec = 0;
+ *compressed = false;
+ }
+}
+
static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
int *count, struct timespec *time,
- char **buf, struct pstore_info *psi)
+ char **buf, bool *compressed,
+ struct pstore_info *psi)
{
ssize_t size;
ssize_t ecc_notice_size;
@@ -152,10 +174,6 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
if (!prz)
return 0;
- /* TODO(kees): Bogus time for the moment. */
- time->tv_sec = 0;
- time->tv_nsec = 0;
-
size = persistent_ram_old_size(prz);
/* ECC correction notice */
@@ -166,12 +184,14 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
return -ENOMEM;
memcpy(*buf, persistent_ram_old(prz), size);
+ ramoops_read_kmsg_hdr(*buf, time, compressed);
persistent_ram_ecc_string(prz, *buf + size, ecc_notice_size + 1);
return size + ecc_notice_size;
}
-static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz)
+static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz,
+ bool compressed)
{
char *hdr;
struct timespec timestamp;
@@ -182,8 +202,9 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz)
timestamp.tv_sec = 0;
timestamp.tv_nsec = 0;
}
- hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu\n",
- (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000));
+ hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n",
+ (long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000),
+ compressed ? 'C' : 'D');
WARN_ON_ONCE(!hdr);
len = hdr ? strlen(hdr) : 0;
persistent_ram_write(prz, hdr, len);
@@ -196,7 +217,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
enum kmsg_dump_reason reason,
u64 *id, unsigned int part,
const char *buf,
- size_t hsize, size_t size,
+ bool compressed, size_t size,
struct pstore_info *psi)
{
struct ramoops_context *cxt = psi->data;
@@ -242,7 +263,7 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
prz = cxt->przs[cxt->dump_write_cnt];
- hlen = ramoops_write_kmsg_hdr(prz);
+ hlen = ramoops_write_kmsg_hdr(prz, compressed);
if (size + hlen > prz->buffer_size)
size = prz->buffer_size - hlen;
persistent_ram_write(prz, buf, size);
@@ -400,11 +421,11 @@ static int ramoops_probe(struct platform_device *pdev)
goto fail_out;
}
- if (!is_power_of_2(pdata->record_size))
+ if (pdata->record_size && !is_power_of_2(pdata->record_size))
pdata->record_size = rounddown_pow_of_two(pdata->record_size);
- if (!is_power_of_2(pdata->console_size))
+ if (pdata->console_size && !is_power_of_2(pdata->console_size))
pdata->console_size = rounddown_pow_of_two(pdata->console_size);
- if (!is_power_of_2(pdata->ftrace_size))
+ if (pdata->ftrace_size && !is_power_of_2(pdata->ftrace_size))
pdata->ftrace_size = rounddown_pow_of_two(pdata->ftrace_size);
cxt->dump_read_cnt = 0;
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index fbad622841f9..9a702e193538 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1094,6 +1094,14 @@ static void dquot_claim_reserved_space(struct dquot *dquot, qsize_t number)
dquot->dq_dqb.dqb_rsvspace -= number;
}
+static void dquot_reclaim_reserved_space(struct dquot *dquot, qsize_t number)
+{
+ if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number))
+ number = dquot->dq_dqb.dqb_curspace;
+ dquot->dq_dqb.dqb_rsvspace += number;
+ dquot->dq_dqb.dqb_curspace -= number;
+}
+
static inline
void dquot_free_reserved_space(struct dquot *dquot, qsize_t number)
{
@@ -1528,6 +1536,15 @@ void inode_claim_rsv_space(struct inode *inode, qsize_t number)
}
EXPORT_SYMBOL(inode_claim_rsv_space);
+void inode_reclaim_rsv_space(struct inode *inode, qsize_t number)
+{
+ spin_lock(&inode->i_lock);
+ *inode_reserved_space(inode) += number;
+ __inode_sub_bytes(inode, number);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(inode_reclaim_rsv_space);
+
void inode_sub_rsv_space(struct inode *inode, qsize_t number)
{
spin_lock(&inode->i_lock);
@@ -1702,6 +1719,35 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number)
EXPORT_SYMBOL(dquot_claim_space_nodirty);
/*
+ * Convert allocated space back to in-memory reserved quotas
+ */
+void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number)
+{
+ int cnt;
+
+ if (!dquot_active(inode)) {
+ inode_reclaim_rsv_space(inode, number);
+ return;
+ }
+
+ down_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ spin_lock(&dq_data_lock);
+ /* Claim reserved quotas to allocated quotas */
+ for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+ if (inode->i_dquot[cnt])
+ dquot_reclaim_reserved_space(inode->i_dquot[cnt],
+ number);
+ }
+ /* Update inode bytes */
+ inode_reclaim_rsv_space(inode, number);
+ spin_unlock(&dq_data_lock);
+ mark_all_dquot_dirty(inode->i_dquot);
+ up_read(&sb_dqopt(inode->i_sb)->dqptr_sem);
+ return;
+}
+EXPORT_SYMBOL(dquot_reclaim_space_nodirty);
+
+/*
* This operation can block, but only after everything is updated
*/
void __dquot_free_space(struct inode *inode, qsize_t number, int flags)
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 33532f79b4f7..a958444a75fc 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -19,12 +19,13 @@
/*
* LOCKING:
*
- * We rely on new Alexander Viro's super-block locking.
+ * These guys are evicted from procfs as the very first step in ->kill_sb().
*
*/
-static int show_version(struct seq_file *m, struct super_block *sb)
+static int show_version(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
char *format;
if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
@@ -66,8 +67,9 @@ static int show_version(struct seq_file *m, struct super_block *sb)
#define DJP( x ) le32_to_cpu( jp -> x )
#define JF( x ) ( r -> s_journal -> x )
-static int show_super(struct seq_file *m, struct super_block *sb)
+static int show_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "state: \t%s\n"
@@ -128,8 +130,9 @@ static int show_super(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_per_level(struct seq_file *m, struct super_block *sb)
+static int show_per_level(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
int level;
@@ -186,8 +189,9 @@ static int show_per_level(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_bitmap(struct seq_file *m, struct super_block *sb)
+static int show_bitmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "free_block: %lu\n"
@@ -218,8 +222,9 @@ static int show_bitmap(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+static int show_on_disk_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
int hash_code = DFL(s_hash_function_code);
@@ -261,8 +266,9 @@ static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_oidmap(struct seq_file *m, struct super_block *sb)
+static int show_oidmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
@@ -291,8 +297,9 @@ static int show_oidmap(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_journal(struct seq_file *m, struct super_block *sb)
+static int show_journal(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
struct reiserfs_super_block *rs = r->s_rs;
struct journal_params *jp = &rs->s_v1.s_journal;
@@ -383,92 +390,24 @@ static int show_journal(struct seq_file *m, struct super_block *sb)
return 0;
}
-/* iterator */
-static int test_sb(struct super_block *sb, void *data)
-{
- return data == sb;
-}
-
-static int set_sb(struct super_block *sb, void *data)
-{
- return -ENOENT;
-}
-
-struct reiserfs_seq_private {
- struct super_block *sb;
- int (*show) (struct seq_file *, struct super_block *);
-};
-
-static void *r_start(struct seq_file *m, loff_t * pos)
-{
- struct reiserfs_seq_private *priv = m->private;
- loff_t l = *pos;
-
- if (l)
- return NULL;
-
- if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb)))
- return NULL;
-
- up_write(&priv->sb->s_umount);
- return priv->sb;
-}
-
-static void *r_next(struct seq_file *m, void *v, loff_t * pos)
-{
- ++*pos;
- if (v)
- deactivate_super(v);
- return NULL;
-}
-
-static void r_stop(struct seq_file *m, void *v)
-{
- if (v)
- deactivate_super(v);
-}
-
-static int r_show(struct seq_file *m, void *v)
-{
- struct reiserfs_seq_private *priv = m->private;
- return priv->show(m, v);
-}
-
-static const struct seq_operations r_ops = {
- .start = r_start,
- .next = r_next,
- .stop = r_stop,
- .show = r_show,
-};
-
static int r_open(struct inode *inode, struct file *file)
{
- struct reiserfs_seq_private *priv;
- int ret = seq_open_private(file, &r_ops,
- sizeof(struct reiserfs_seq_private));
-
- if (!ret) {
- struct seq_file *m = file->private_data;
- priv = m->private;
- priv->sb = proc_get_parent_data(inode);
- priv->show = PDE_DATA(inode);
- }
- return ret;
+ return single_open(file, PDE_DATA(inode),
+ proc_get_parent_data(inode));
}
static const struct file_operations r_file_operations = {
.open = r_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
- .owner = THIS_MODULE,
+ .release = single_release,
};
static struct proc_dir_entry *proc_info_root = NULL;
static const char proc_info_root_name[] = "fs/reiserfs";
static void add_file(struct super_block *sb, char *name,
- int (*func) (struct seq_file *, struct super_block *))
+ int (*func) (struct seq_file *, void *))
{
proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
&r_file_operations, func);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index bb20d791bbdc..3ead145dadc4 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -502,6 +502,7 @@ int remove_save_link(struct inode *inode, int truncate)
static void reiserfs_kill_sb(struct super_block *s)
{
if (REISERFS_SB(s)) {
+ reiserfs_proc_info_done(s);
/*
* Force any pending inode evictions to occur now. Any
* inodes to be removed that have extended attributes
@@ -557,8 +558,6 @@ static void reiserfs_put_super(struct super_block *s)
REISERFS_SB(s)->reserved_blocks);
}
- reiserfs_proc_info_done(s);
-
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
kfree(s->s_fs_info);
diff --git a/fs/stat.c b/fs/stat.c
index 04ce1ac20d20..d0ea7ef75e26 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -447,9 +447,8 @@ void inode_add_bytes(struct inode *inode, loff_t bytes)
EXPORT_SYMBOL(inode_add_bytes);
-void inode_sub_bytes(struct inode *inode, loff_t bytes)
+void __inode_sub_bytes(struct inode *inode, loff_t bytes)
{
- spin_lock(&inode->i_lock);
inode->i_blocks -= bytes >> 9;
bytes &= 511;
if (inode->i_bytes < bytes) {
@@ -457,6 +456,14 @@ void inode_sub_bytes(struct inode *inode, loff_t bytes)
inode->i_bytes += 512;
}
inode->i_bytes -= bytes;
+}
+
+EXPORT_SYMBOL(__inode_sub_bytes);
+
+void inode_sub_bytes(struct inode *inode, loff_t bytes)
+{
+ spin_lock(&inode->i_lock);
+ __inode_sub_bytes(inode, bytes);
spin_unlock(&inode->i_lock);
}
diff --git a/fs/super.c b/fs/super.c
index 68307c029228..5536a95186e2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -152,15 +152,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
static const struct super_operations default_op;
if (s) {
- if (security_sb_alloc(s)) {
- /*
- * We cannot call security_sb_free() without
- * security_sb_alloc() succeeding. So bail out manually
- */
- kfree(s);
- s = NULL;
- goto out;
- }
+ if (security_sb_alloc(s))
+ goto out_free_sb;
+
#ifdef CONFIG_SMP
s->s_files = alloc_percpu(struct list_head);
if (!s->s_files)
@@ -228,6 +222,7 @@ err_out:
free_percpu(s->s_files);
#endif
destroy_sb_writers(s);
+out_free_sb:
kfree(s);
s = NULL;
goto out;
@@ -414,6 +409,11 @@ void generic_shutdown_super(struct super_block *sb)
evict_inodes(sb);
+ if (sb->s_dio_done_wq) {
+ destroy_workqueue(sb->s_dio_done_wq);
+ sb->s_dio_done_wq = NULL;
+ }
+
if (sop->put_super)
sop->put_super(sb);
diff --git a/fs/sysfs/bin.c b/fs/sysfs/bin.c
index 15c68f9489ae..c590cabd57bb 100644
--- a/fs/sysfs/bin.c
+++ b/fs/sysfs/bin.c
@@ -22,8 +22,7 @@
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/mm.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include "sysfs.h"
@@ -391,7 +390,7 @@ out_unlock:
return rc;
}
-static int open(struct inode * inode, struct file * file)
+static int open(struct inode *inode, struct file *file)
{
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
@@ -435,7 +434,7 @@ static int open(struct inode * inode, struct file * file)
return error;
}
-static int release(struct inode * inode, struct file * file)
+static int release(struct inode *inode, struct file *file)
{
struct bin_buffer *bb = file->private_data;
@@ -481,7 +480,6 @@ void unmap_bin_file(struct sysfs_dirent *attr_sd)
* @kobj: object.
* @attr: attribute descriptor.
*/
-
int sysfs_create_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
@@ -489,19 +487,16 @@ int sysfs_create_bin_file(struct kobject *kobj,
return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
}
-
+EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
/**
* sysfs_remove_bin_file - remove binary file for object.
* @kobj: object.
* @attr: attribute descriptor.
*/
-
void sysfs_remove_bin_file(struct kobject *kobj,
const struct bin_attribute *attr)
{
sysfs_hash_and_remove(kobj->sd, NULL, attr->attr.name);
}
-
-EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index e068e744dbdd..99ec5b40e977 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -46,7 +46,7 @@ static unsigned int sysfs_name_hash(const void *ns, const char *name)
unsigned int len = strlen(name);
while (len--)
hash = partial_name_hash(*name++, hash);
- hash = ( end_name_hash(hash) ^ hash_ptr( (void *)ns, 31 ) );
+ hash = (end_name_hash(hash) ^ hash_ptr((void *)ns, 31));
hash &= 0x7fffffffU;
/* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */
if (hash < 1)
@@ -258,7 +258,7 @@ static void sysfs_free_ino(unsigned int ino)
spin_unlock(&sysfs_ino_lock);
}
-void release_sysfs_dirent(struct sysfs_dirent * sd)
+void release_sysfs_dirent(struct sysfs_dirent *sd)
{
struct sysfs_dirent *parent_sd;
@@ -451,7 +451,7 @@ int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
if (!!sysfs_ns_type(acxt->parent_sd) != !!sd->s_ns) {
WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
- sysfs_ns_type(acxt->parent_sd)? "required": "invalid",
+ sysfs_ns_type(acxt->parent_sd) ? "required" : "invalid",
acxt->parent_sd->s_name, sd->s_name);
return -EINVAL;
}
@@ -619,7 +619,7 @@ struct sysfs_dirent *sysfs_find_dirent(struct sysfs_dirent *parent_sd,
if (!!sysfs_ns_type(parent_sd) != !!ns) {
WARN(1, KERN_WARNING "sysfs: ns %s in '%s' for '%s'\n",
- sysfs_ns_type(parent_sd)? "required": "invalid",
+ sysfs_ns_type(parent_sd) ? "required" : "invalid",
parent_sd->s_name, name);
return NULL;
}
@@ -674,7 +674,7 @@ static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd,
enum kobj_ns_type type, const void *ns, const char *name,
struct sysfs_dirent **p_sd)
{
- umode_t mode = S_IFDIR| S_IRWXU | S_IRUGO | S_IXUGO;
+ umode_t mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent *sd;
int rc;
@@ -735,9 +735,9 @@ static enum kobj_ns_type sysfs_read_ns_type(struct kobject *kobj)
/**
* sysfs_create_dir - create a directory for an object.
- * @kobj: object we're creating directory for.
+ * @kobj: object we're creating directory for.
*/
-int sysfs_create_dir(struct kobject * kobj)
+int sysfs_create_dir(struct kobject *kobj)
{
enum kobj_ns_type type;
struct sysfs_dirent *parent_sd, *sd;
@@ -764,8 +764,8 @@ int sysfs_create_dir(struct kobject * kobj)
return error;
}
-static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
- unsigned int flags)
+static struct dentry *sysfs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
{
struct dentry *ret = NULL;
struct dentry *parent = dentry->d_parent;
@@ -857,7 +857,7 @@ static void __sysfs_remove_dir(struct sysfs_dirent *dir_sd)
* what used to be sysfs_rmdir() below, instead of calling separately.
*/
-void sysfs_remove_dir(struct kobject * kobj)
+void sysfs_remove_dir(struct kobject *kobj)
{
struct sysfs_dirent *sd = kobj->sd;
@@ -896,7 +896,9 @@ int sysfs_rename(struct sysfs_dirent *sd,
sd->s_name = new_name;
}
- /* Move to the appropriate place in the appropriate directories rbtree. */
+ /*
+ * Move to the appropriate place in the appropriate directories rbtree.
+ */
sysfs_unlink_sibling(sd);
sysfs_get(new_parent_sd);
sysfs_put(sd->s_parent);
@@ -988,20 +990,21 @@ static struct sysfs_dirent *sysfs_dir_next_pos(const void *ns,
struct sysfs_dirent *parent_sd, ino_t ino, struct sysfs_dirent *pos)
{
pos = sysfs_dir_pos(ns, parent_sd, ino, pos);
- if (pos) do {
- struct rb_node *node = rb_next(&pos->s_rb);
- if (!node)
- pos = NULL;
- else
- pos = to_sysfs_dirent(node);
- } while (pos && pos->s_ns != ns);
+ if (pos)
+ do {
+ struct rb_node *node = rb_next(&pos->s_rb);
+ if (!node)
+ pos = NULL;
+ else
+ pos = to_sysfs_dirent(node);
+ } while (pos && pos->s_ns != ns);
return pos;
}
static int sysfs_readdir(struct file *file, struct dir_context *ctx)
{
struct dentry *dentry = file->f_path.dentry;
- struct sysfs_dirent * parent_sd = dentry->d_fsdata;
+ struct sysfs_dirent *parent_sd = dentry->d_fsdata;
struct sysfs_dirent *pos = file->private_data;
enum kobj_ns_type type;
const void *ns;
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index d2bb7ed8fa74..15ef5eb13663 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -20,7 +20,7 @@
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/limits.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include "sysfs.h"
@@ -45,8 +45,8 @@ struct sysfs_open_dirent {
struct sysfs_buffer {
size_t count;
loff_t pos;
- char * page;
- const struct sysfs_ops * ops;
+ char *page;
+ const struct sysfs_ops *ops;
struct mutex mutex;
int needs_read_fill;
int event;
@@ -59,16 +59,16 @@ struct sysfs_buffer {
* @buffer: data buffer for file.
*
* Allocate @buffer->page, if it hasn't been already, then call the
- * kobject's show() method to fill the buffer with this attribute's
- * data.
+ * kobject's show() method to fill the buffer with this attribute's
+ * data.
* This is called only once, on the file's first read unless an error
* is returned.
*/
-static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer)
+static int fill_read_buffer(struct dentry *dentry, struct sysfs_buffer *buffer)
{
struct sysfs_dirent *attr_sd = dentry->d_fsdata;
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- const struct sysfs_ops * ops = buffer->ops;
+ const struct sysfs_ops *ops = buffer->ops;
int ret = 0;
ssize_t count;
@@ -106,7 +106,7 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer
}
/**
- * sysfs_read_file - read an attribute.
+ * sysfs_read_file - read an attribute.
* @file: file pointer.
* @buf: buffer to fill.
* @count: number of bytes to read.
@@ -127,12 +127,12 @@ static int fill_read_buffer(struct dentry * dentry, struct sysfs_buffer * buffer
static ssize_t
sysfs_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
- struct sysfs_buffer * buffer = file->private_data;
+ struct sysfs_buffer *buffer = file->private_data;
ssize_t retval = 0;
mutex_lock(&buffer->mutex);
if (buffer->needs_read_fill || *ppos == 0) {
- retval = fill_read_buffer(file->f_path.dentry,buffer);
+ retval = fill_read_buffer(file->f_path.dentry, buffer);
if (retval)
goto out;
}
@@ -154,9 +154,8 @@ out:
* Allocate @buffer->page if it hasn't been already, then
* copy the user-supplied buffer into it.
*/
-
-static int
-fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t count)
+static int fill_write_buffer(struct sysfs_buffer *buffer,
+ const char __user *buf, size_t count)
{
int error;
@@ -167,7 +166,7 @@ fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t
if (count >= PAGE_SIZE)
count = PAGE_SIZE - 1;
- error = copy_from_user(buffer->page,buf,count);
+ error = copy_from_user(buffer->page, buf, count);
buffer->needs_read_fill = 1;
/* if buf is assumed to contain a string, terminate it by \0,
so e.g. sscanf() can scan the string easily */
@@ -183,16 +182,15 @@ fill_write_buffer(struct sysfs_buffer * buffer, const char __user * buf, size_t
* @count: number of bytes
*
* Get the correct pointers for the kobject and the attribute we're
- * dealing with, then call the store() method for the attribute,
+ * dealing with, then call the store() method for the attribute,
* passing the buffer that we acquired in fill_write_buffer().
*/
-
-static int
-flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t count)
+static int flush_write_buffer(struct dentry *dentry,
+ struct sysfs_buffer *buffer, size_t count)
{
struct sysfs_dirent *attr_sd = dentry->d_fsdata;
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
- const struct sysfs_ops * ops = buffer->ops;
+ const struct sysfs_ops *ops = buffer->ops;
int rc;
/* need attr_sd for attr and ops, its parent for kobj */
@@ -219,15 +217,14 @@ flush_write_buffer(struct dentry * dentry, struct sysfs_buffer * buffer, size_t
* then push it to the kobject in flush_write_buffer().
* There is no easy way for us to know if userspace is only doing a partial
* write, so we don't support them. We expect the entire buffer to come
- * on the first write.
+ * on the first write.
* Hint: if you're writing a value, first read the file, modify only the
- * the value you're changing, then write entire buffer back.
+ * the value you're changing, then write entire buffer back.
*/
-
-static ssize_t
-sysfs_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+static ssize_t sysfs_write_file(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
{
- struct sysfs_buffer * buffer = file->private_data;
+ struct sysfs_buffer *buffer = file->private_data;
ssize_t len;
mutex_lock(&buffer->mutex);
@@ -339,13 +336,14 @@ static int sysfs_open_file(struct inode *inode, struct file *file)
if (kobj->ktype && kobj->ktype->sysfs_ops)
ops = kobj->ktype->sysfs_ops;
else {
- WARN(1, KERN_ERR "missing sysfs attribute operations for "
- "kobject: %s\n", kobject_name(kobj));
+ WARN(1, KERN_ERR
+ "missing sysfs attribute operations for kobject: %s\n",
+ kobject_name(kobj));
goto err_out;
}
/* File needs write support.
- * The inode's perms must say it's ok,
+ * The inode's perms must say it's ok,
* and we must have a store method.
*/
if (file->f_mode & FMODE_WRITE) {
@@ -420,7 +418,7 @@ static int sysfs_release(struct inode *inode, struct file *filp)
*/
static unsigned int sysfs_poll(struct file *filp, poll_table *wait)
{
- struct sysfs_buffer * buffer = filp->private_data;
+ struct sysfs_buffer *buffer = filp->private_data;
struct sysfs_dirent *attr_sd = filp->f_path.dentry->d_fsdata;
struct sysfs_open_dirent *od = attr_sd->s_attr.open;
@@ -518,8 +516,9 @@ static int sysfs_attr_ns(struct kobject *kobj, const struct attribute *attr,
ns = ops->namespace(kobj, attr);
out:
if (err) {
- WARN(1, KERN_ERR "missing sysfs namespace attribute operation for "
- "kobject: %s\n", kobject_name(kobj));
+ WARN(1, KERN_ERR
+ "missing sysfs namespace attribute operation for kobject: %s\n",
+ kobject_name(kobj));
}
*pns = ns;
return err;
@@ -566,17 +565,17 @@ int sysfs_add_file(struct sysfs_dirent *dir_sd, const struct attribute *attr,
/**
* sysfs_create_file - create an attribute file for an object.
- * @kobj: object we're creating for.
+ * @kobj: object we're creating for.
* @attr: attribute descriptor.
*/
-
-int sysfs_create_file(struct kobject * kobj, const struct attribute * attr)
+int sysfs_create_file(struct kobject *kobj, const struct attribute *attr)
{
BUG_ON(!kobj || !kobj->sd || !attr);
return sysfs_add_file(kobj->sd, attr, SYSFS_KOBJ_ATTR);
}
+EXPORT_SYMBOL_GPL(sysfs_create_file);
int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
{
@@ -590,6 +589,7 @@ int sysfs_create_files(struct kobject *kobj, const struct attribute **ptr)
sysfs_remove_file(kobj, ptr[i]);
return err;
}
+EXPORT_SYMBOL_GPL(sysfs_create_files);
/**
* sysfs_add_file_to_group - add an attribute file to a pre-existing group.
@@ -654,7 +654,6 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
}
EXPORT_SYMBOL_GPL(sysfs_chmod_file);
-
/**
* sysfs_remove_file - remove an object attribute.
* @kobj: object we're acting for.
@@ -662,8 +661,7 @@ EXPORT_SYMBOL_GPL(sysfs_chmod_file);
*
* Hash the attribute name and kill the victim.
*/
-
-void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr)
+void sysfs_remove_file(struct kobject *kobj, const struct attribute *attr)
{
const void *ns;
@@ -672,13 +670,15 @@ void sysfs_remove_file(struct kobject * kobj, const struct attribute * attr)
sysfs_hash_and_remove(kobj->sd, ns, attr->name);
}
+EXPORT_SYMBOL_GPL(sysfs_remove_file);
-void sysfs_remove_files(struct kobject * kobj, const struct attribute **ptr)
+void sysfs_remove_files(struct kobject *kobj, const struct attribute **ptr)
{
int i;
for (i = 0; ptr[i]; i++)
sysfs_remove_file(kobj, ptr[i]);
}
+EXPORT_SYMBOL_GPL(sysfs_remove_files);
/**
* sysfs_remove_file_from_group - remove an attribute file from a group.
@@ -793,9 +793,3 @@ int sysfs_schedule_callback(struct kobject *kobj, void (*func)(void *),
return 0;
}
EXPORT_SYMBOL_GPL(sysfs_schedule_callback);
-
-
-EXPORT_SYMBOL_GPL(sysfs_create_file);
-EXPORT_SYMBOL_GPL(sysfs_remove_file);
-EXPORT_SYMBOL_GPL(sysfs_remove_files);
-EXPORT_SYMBOL_GPL(sysfs_create_files);
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 09a1a25cd145..5f92cd2f61c1 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -3,8 +3,10 @@
*
* Copyright (c) 2003 Patrick Mochel
* Copyright (c) 2003 Open Source Development Lab
+ * Copyright (c) 2013 Greg Kroah-Hartman
+ * Copyright (c) 2013 The Linux Foundation
*
- * This file is released undert the GPL v2.
+ * This file is released undert the GPL v2.
*
*/
@@ -19,8 +21,8 @@
static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
const struct attribute_group *grp)
{
- struct attribute *const* attr;
- struct bin_attribute *const* bin_attr;
+ struct attribute *const *attr;
+ struct bin_attribute *const *bin_attr;
if (grp->attrs)
for (attr = grp->attrs; *attr; attr++)
@@ -33,8 +35,8 @@ static void remove_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
static int create_files(struct sysfs_dirent *dir_sd, struct kobject *kobj,
const struct attribute_group *grp, int update)
{
- struct attribute *const* attr;
- struct bin_attribute *const* bin_attr;
+ struct attribute *const *attr;
+ struct bin_attribute *const *bin_attr;
int error = 0, i;
if (grp->attrs) {
@@ -129,6 +131,41 @@ int sysfs_create_group(struct kobject *kobj,
{
return internal_create_group(kobj, 0, grp);
}
+EXPORT_SYMBOL_GPL(sysfs_create_group);
+
+/**
+ * sysfs_create_groups - given a directory kobject, create a bunch of attribute groups
+ * @kobj: The kobject to create the group on
+ * @groups: The attribute groups to create, NULL terminated
+ *
+ * This function creates a bunch of attribute groups. If an error occurs when
+ * creating a group, all previously created groups will be removed, unwinding
+ * everything back to the original state when this function was called.
+ * It will explicitly warn and error if any of the attribute files being
+ * created already exist.
+ *
+ * Returns 0 on success or error code from sysfs_create_group on error.
+ */
+int sysfs_create_groups(struct kobject *kobj,
+ const struct attribute_group **groups)
+{
+ int error = 0;
+ int i;
+
+ if (!groups)
+ return 0;
+
+ for (i = 0; groups[i]; i++) {
+ error = sysfs_create_group(kobj, groups[i]);
+ if (error) {
+ while (--i >= 0)
+ sysfs_remove_group(kobj, groups[i]);
+ break;
+ }
+ }
+ return error;
+}
+EXPORT_SYMBOL_GPL(sysfs_create_groups);
/**
* sysfs_update_group - given a directory kobject, update an attribute group
@@ -152,11 +189,18 @@ int sysfs_update_group(struct kobject *kobj,
{
return internal_create_group(kobj, 1, grp);
}
+EXPORT_SYMBOL_GPL(sysfs_update_group);
-
-
-void sysfs_remove_group(struct kobject * kobj,
- const struct attribute_group * grp)
+/**
+ * sysfs_remove_group: remove a group from a kobject
+ * @kobj: kobject to remove the group from
+ * @grp: group to remove
+ *
+ * This function removes a group of attributes from a kobject. The attributes
+ * previously have to have been created for this group, otherwise it will fail.
+ */
+void sysfs_remove_group(struct kobject *kobj,
+ const struct attribute_group *grp)
{
struct sysfs_dirent *dir_sd = kobj->sd;
struct sysfs_dirent *sd;
@@ -164,8 +208,9 @@ void sysfs_remove_group(struct kobject * kobj,
if (grp->name) {
sd = sysfs_get_dirent(dir_sd, NULL, grp->name);
if (!sd) {
- WARN(!sd, KERN_WARNING "sysfs group %p not found for "
- "kobject '%s'\n", grp, kobject_name(kobj));
+ WARN(!sd, KERN_WARNING
+ "sysfs group %p not found for kobject '%s'\n",
+ grp, kobject_name(kobj));
return;
}
} else
@@ -177,6 +222,27 @@ void sysfs_remove_group(struct kobject * kobj,
sysfs_put(sd);
}
+EXPORT_SYMBOL_GPL(sysfs_remove_group);
+
+/**
+ * sysfs_remove_groups - remove a list of groups
+ *
+ * @kobj: The kobject for the groups to be removed from
+ * @groups: NULL terminated list of groups to be removed
+ *
+ * If groups is not NULL, remove the specified groups from the kobject.
+ */
+void sysfs_remove_groups(struct kobject *kobj,
+ const struct attribute_group **groups)
+{
+ int i;
+
+ if (!groups)
+ return;
+ for (i = 0; groups[i]; i++)
+ sysfs_remove_group(kobj, groups[i]);
+}
+EXPORT_SYMBOL_GPL(sysfs_remove_groups);
/**
* sysfs_merge_group - merge files into a pre-existing attribute group.
@@ -273,7 +339,3 @@ void sysfs_remove_link_from_group(struct kobject *kobj, const char *group_name,
}
}
EXPORT_SYMBOL_GPL(sysfs_remove_link_from_group);
-
-EXPORT_SYMBOL_GPL(sysfs_create_group);
-EXPORT_SYMBOL_GPL(sysfs_update_group);
-EXPORT_SYMBOL_GPL(sysfs_remove_group);
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 3e2837a633ed..963f910c8034 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -10,7 +10,7 @@
* Please see Documentation/filesystems/sysfs.txt for more information.
*/
-#undef DEBUG
+#undef DEBUG
#include <linux/pagemap.h>
#include <linux/namei.h>
@@ -36,7 +36,7 @@ static struct backing_dev_info sysfs_backing_dev_info = {
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
-static const struct inode_operations sysfs_inode_operations ={
+static const struct inode_operations sysfs_inode_operations = {
.permission = sysfs_permission,
.setattr = sysfs_setattr,
.getattr = sysfs_getattr,
@@ -67,7 +67,7 @@ static struct sysfs_inode_attrs *sysfs_init_inode_attrs(struct sysfs_dirent *sd)
return attrs;
}
-int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr * iattr)
+int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr)
{
struct sysfs_inode_attrs *sd_attrs;
struct iattr *iattrs;
@@ -128,7 +128,8 @@ out:
return error;
}
-static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata, u32 *secdata_len)
+static int sysfs_sd_setsecdata(struct sysfs_dirent *sd, void **secdata,
+ u32 *secdata_len)
{
struct sysfs_inode_attrs *iattrs;
void *old_secdata;
@@ -186,13 +187,13 @@ out:
return error;
}
-static inline void set_default_inode_attr(struct inode * inode, umode_t mode)
+static inline void set_default_inode_attr(struct inode *inode, umode_t mode)
{
inode->i_mode = mode;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
}
-static inline void set_inode_attr(struct inode * inode, struct iattr * iattr)
+static inline void set_inode_attr(struct inode *inode, struct iattr *iattr)
{
inode->i_uid = iattr->ia_uid;
inode->i_gid = iattr->ia_gid;
@@ -220,7 +221,8 @@ static void sysfs_refresh_inode(struct sysfs_dirent *sd, struct inode *inode)
set_nlink(inode, sd->s_dir.subdirs + 2);
}
-int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
struct inode *inode = dentry->d_inode;
@@ -285,7 +287,7 @@ static void sysfs_init_inode(struct sysfs_dirent *sd, struct inode *inode)
* RETURNS:
* Pointer to allocated inode on success, NULL on failure.
*/
-struct inode * sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd)
+struct inode *sysfs_get_inode(struct super_block *sb, struct sysfs_dirent *sd)
{
struct inode *inode;
@@ -312,7 +314,8 @@ void sysfs_evict_inode(struct inode *inode)
sysfs_put(sd);
}
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name)
+int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
+ const char *name)
{
struct sysfs_addrm_cxt acxt;
struct sysfs_dirent *sd;
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index afd83273e6ce..fd7ce7a39f91 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -64,7 +64,7 @@ static int sysfs_fill_super(struct super_block *sb, void *data, int silent)
/* instantiate and link root dentry */
root = d_make_root(inode);
if (!root) {
- pr_debug("%s: could not get root dentry!\n",__func__);
+ pr_debug("%s: could not get root dentry!\n", __func__);
return -ENOMEM;
}
root->d_fsdata = &sysfs_root;
diff --git a/fs/sysfs/symlink.c b/fs/sysfs/symlink.c
index 8c940df97a52..2dd4507d9edd 100644
--- a/fs/sysfs/symlink.c
+++ b/fs/sysfs/symlink.c
@@ -125,6 +125,7 @@ int sysfs_create_link(struct kobject *kobj, struct kobject *target,
{
return sysfs_do_create_link(kobj, target, name, 1);
}
+EXPORT_SYMBOL_GPL(sysfs_create_link);
/**
* sysfs_create_link_nowarn - create symlink between two objects.
@@ -166,8 +167,7 @@ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ,
* @kobj: object we're acting for.
* @name: name of the symlink to remove.
*/
-
-void sysfs_remove_link(struct kobject * kobj, const char * name)
+void sysfs_remove_link(struct kobject *kobj, const char *name)
{
struct sysfs_dirent *parent_sd = NULL;
@@ -178,6 +178,7 @@ void sysfs_remove_link(struct kobject * kobj, const char * name)
sysfs_hash_and_remove(parent_sd, NULL, name);
}
+EXPORT_SYMBOL_GPL(sysfs_remove_link);
/**
* sysfs_rename_link - rename symlink in object's directory.
@@ -223,6 +224,7 @@ out:
sysfs_put(sd);
return result;
}
+EXPORT_SYMBOL_GPL(sysfs_rename_link);
static int sysfs_get_target_path(struct sysfs_dirent *parent_sd,
struct sysfs_dirent *target_sd, char *path)
@@ -276,7 +278,7 @@ static int sysfs_get_target_path(struct sysfs_dirent *parent_sd,
return 0;
}
-static int sysfs_getlink(struct dentry *dentry, char * path)
+static int sysfs_getlink(struct dentry *dentry, char *path)
{
struct sysfs_dirent *sd = dentry->d_fsdata;
struct sysfs_dirent *parent_sd = sd->s_parent;
@@ -295,7 +297,7 @@ static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd)
int error = -ENOMEM;
unsigned long page = get_zeroed_page(GFP_KERNEL);
if (page) {
- error = sysfs_getlink(dentry, (char *) page);
+ error = sysfs_getlink(dentry, (char *) page);
if (error < 0)
free_page((unsigned long)page);
}
@@ -303,7 +305,8 @@ static void *sysfs_follow_link(struct dentry *dentry, struct nameidata *nd)
return NULL;
}
-static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static void sysfs_put_link(struct dentry *dentry, struct nameidata *nd,
+ void *cookie)
{
char *page = nd_get_link(nd);
if (!IS_ERR(page))
@@ -319,8 +322,3 @@ const struct inode_operations sysfs_symlink_inode_operations = {
.getattr = sysfs_getattr,
.permission = sysfs_permission,
};
-
-
-EXPORT_SYMBOL_GPL(sysfs_create_link);
-EXPORT_SYMBOL_GPL(sysfs_remove_link);
-EXPORT_SYMBOL_GPL(sysfs_rename_link);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d1e4043eb0c3..b6deca3e301d 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -78,7 +78,7 @@ struct sysfs_dirent {
};
unsigned short s_flags;
- umode_t s_mode;
+ umode_t s_mode;
unsigned int s_ino;
struct sysfs_inode_attrs *s_iattr;
};
@@ -123,9 +123,9 @@ do { \
key = &attr->skey; \
\
lockdep_init_map(&sd->dep_map, "s_active", key, 0); \
-} while(0)
+} while (0)
#else
-#define sysfs_dirent_init_lockdep(sd) do {} while(0)
+#define sysfs_dirent_init_lockdep(sd) do {} while (0)
#endif
/*
@@ -186,8 +186,8 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name,
struct sysfs_dirent **p_sd);
void sysfs_remove_subdir(struct sysfs_dirent *sd);
-int sysfs_rename(struct sysfs_dirent *sd,
- struct sysfs_dirent *new_parent_sd, const void *ns, const char *new_name);
+int sysfs_rename(struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd,
+ const void *ns, const char *new_name);
static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd)
{
@@ -214,10 +214,12 @@ void sysfs_evict_inode(struct inode *inode);
int sysfs_sd_setattr(struct sysfs_dirent *sd, struct iattr *iattr);
int sysfs_permission(struct inode *inode, int mask);
int sysfs_setattr(struct dentry *dentry, struct iattr *iattr);
-int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat);
+int sysfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat);
int sysfs_setxattr(struct dentry *dentry, const char *name, const void *value,
- size_t size, int flags);
-int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns, const char *name);
+ size_t size, int flags);
+int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const void *ns,
+ const char *name);
int sysfs_inode_init(void);
/*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 596ec71da00e..e11d654af786 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -86,14 +86,6 @@ xfs_destroy_ioend(
bh->b_end_io(bh, !ioend->io_error);
}
- if (ioend->io_iocb) {
- inode_dio_done(ioend->io_inode);
- if (ioend->io_isasync) {
- aio_complete(ioend->io_iocb, ioend->io_error ?
- ioend->io_error : ioend->io_result, 0);
- }
- }
-
mempool_free(ioend, xfs_ioend_pool);
}
@@ -281,7 +273,6 @@ xfs_alloc_ioend(
* all the I/O from calling the completion routine too early.
*/
atomic_set(&ioend->io_remaining, 1);
- ioend->io_isasync = 0;
ioend->io_isdirect = 0;
ioend->io_error = 0;
ioend->io_list = NULL;
@@ -291,8 +282,6 @@ xfs_alloc_ioend(
ioend->io_buffer_tail = NULL;
ioend->io_offset = 0;
ioend->io_size = 0;
- ioend->io_iocb = NULL;
- ioend->io_result = 0;
ioend->io_append_trans = NULL;
INIT_WORK(&ioend->io_work, xfs_end_io);
@@ -1292,8 +1281,10 @@ __xfs_get_blocks(
if (create || !ISUNWRITTEN(&imap))
xfs_map_buffer(inode, bh_result, &imap, offset);
if (create && ISUNWRITTEN(&imap)) {
- if (direct)
+ if (direct) {
bh_result->b_private = inode;
+ set_buffer_defer_completion(bh_result);
+ }
set_buffer_unwritten(bh_result);
}
}
@@ -1390,9 +1381,7 @@ xfs_end_io_direct_write(
struct kiocb *iocb,
loff_t offset,
ssize_t size,
- void *private,
- int ret,
- bool is_async)
+ void *private)
{
struct xfs_ioend *ioend = iocb->private;
@@ -1414,17 +1403,10 @@ xfs_end_io_direct_write(
ioend->io_offset = offset;
ioend->io_size = size;
- ioend->io_iocb = iocb;
- ioend->io_result = ret;
if (private && size > 0)
ioend->io_type = XFS_IO_UNWRITTEN;
- if (is_async) {
- ioend->io_isasync = 1;
- xfs_finish_ioend(ioend);
- } else {
- xfs_finish_ioend_sync(ioend);
- }
+ xfs_finish_ioend_sync(ioend);
}
STATIC ssize_t
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index c325abb8d61a..f94dd459dff9 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -45,7 +45,6 @@ typedef struct xfs_ioend {
unsigned int io_type; /* delalloc / unwritten */
int io_error; /* I/O error code */
atomic_t io_remaining; /* hold count */
- unsigned int io_isasync : 1; /* needs aio_complete */
unsigned int io_isdirect : 1;/* direct I/O */
struct inode *io_inode; /* file being written to */
struct buffer_head *io_buffer_head;/* buffer linked list head */
@@ -54,8 +53,6 @@ typedef struct xfs_ioend {
xfs_off_t io_offset; /* offset in the file */
struct work_struct io_work; /* xfsdatad work queue */
struct xfs_trans *io_append_trans;/* xact. for size update */
- struct kiocb *io_iocb;
- int io_result;
} xfs_ioend_t;
extern const struct address_space_operations xfs_address_space_operations;