summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/block_dev.c11
-rw-r--r--fs/btrfs/acl.c6
-rw-r--r--fs/btrfs/compression.c27
-rw-r--r--fs/btrfs/disk-io.c15
-rw-r--r--fs/btrfs/export.c2
-rw-r--r--fs/btrfs/extent-tree.c100
-rw-r--r--fs/btrfs/extent_io.c54
-rw-r--r--fs/btrfs/extent_map.c4
-rw-r--r--fs/btrfs/file-item.c5
-rw-r--r--fs/btrfs/file.c21
-rw-r--r--fs/btrfs/free-space-cache.c162
-rw-r--r--fs/btrfs/inode.c38
-rw-r--r--fs/btrfs/ioctl.c29
-rw-r--r--fs/btrfs/ordered-data.c2
-rw-r--r--fs/btrfs/print-tree.c1
-rw-r--r--fs/btrfs/relocation.c30
-rw-r--r--fs/btrfs/super.c9
-rw-r--r--fs/btrfs/transaction.c5
-rw-r--r--fs/btrfs/tree-log.c35
-rw-r--r--fs/btrfs/volumes.c21
-rw-r--r--fs/ceph/dir.c5
-rw-r--r--fs/ceph/snap.c14
-rw-r--r--fs/ceph/super.h1
-rw-r--r--fs/cifs/Kconfig1
-rw-r--r--fs/cifs/cifs_dfs_ref.c9
-rw-r--r--fs/cifs/cifsacl.c4
-rw-r--r--fs/cifs/cifsencrypt.c5
-rw-r--r--fs/cifs/cifsfs.h2
-rw-r--r--fs/cifs/cifsglob.h4
-rw-r--r--fs/cifs/cifssmb.c8
-rw-r--r--fs/cifs/connect.c47
-rw-r--r--fs/cifs/file.c15
-rw-r--r--fs/cifs/link.c3
-rw-r--r--fs/cifs/misc.c116
-rw-r--r--fs/cifs/netmisc.c8
-rw-r--r--fs/cifs/readdir.c3
-rw-r--r--fs/cifs/sess.c8
-rw-r--r--fs/cifs/smbencrypt.c3
-rw-r--r--fs/cifs/transport.c69
-rw-r--r--fs/dlm/lowcomms.c6
-rw-r--r--fs/ecryptfs/dentry.c22
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h3
-rw-r--r--fs/ecryptfs/file.c1
-rw-r--r--fs/ecryptfs/inode.c138
-rw-r--r--fs/eventfd.c12
-rw-r--r--fs/eventpoll.c16
-rw-r--r--fs/exec.c4
-rw-r--r--fs/exofs/inode.c2
-rw-r--r--fs/ext4/ext4.h10
-rw-r--r--fs/ext4/extents.c10
-rw-r--r--fs/ext4/file.c60
-rw-r--r--fs/ext4/mballoc.c100
-rw-r--r--fs/ext4/page-io.c36
-rw-r--r--fs/ext4/super.c66
-rw-r--r--fs/fcntl.c2
-rw-r--r--fs/file_table.c2
-rw-r--r--fs/gfs2/glock.c4
-rw-r--r--fs/gfs2/main.c2
-rw-r--r--fs/hfsplus/extents.c4
-rw-r--r--fs/hfsplus/part_tbl.c4
-rw-r--r--fs/hfsplus/super.c106
-rw-r--r--fs/hfsplus/wrapper.c4
-rw-r--r--fs/ioctl.c7
-rw-r--r--fs/jbd2/journal.c9
-rw-r--r--fs/jbd2/transaction.c21
-rw-r--r--fs/namei.c151
-rw-r--r--fs/nfsd/nfs4callback.c6
-rw-r--r--fs/nfsd/nfs4state.c186
-rw-r--r--fs/nfsd/nfs4xdr.c8
-rw-r--r--fs/nfsd/state.h5
-rw-r--r--fs/nfsd/vfs.c21
-rw-r--r--fs/open.c2
-rw-r--r--fs/partitions/mac.c17
-rw-r--r--fs/proc/array.c3
-rw-r--r--fs/super.c5
75 files changed, 1234 insertions, 723 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 333a7bb4cb9..4fb8a343153 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1215,12 +1215,6 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
res = __blkdev_get(bdev, mode, 0);
- /* __blkdev_get() may alter read only status, check it afterwards */
- if (!res && (mode & FMODE_WRITE) && bdev_read_only(bdev)) {
- __blkdev_put(bdev, mode, 0);
- res = -EACCES;
- }
-
if (whole) {
/* finish claiming */
mutex_lock(&bdev->bd_mutex);
@@ -1298,6 +1292,11 @@ struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
if (err)
return ERR_PTR(err);
+ if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
+ blkdev_put(bdev, mode);
+ return ERR_PTR(-EACCES);
+ }
+
return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 15b5ca2a260..9c949348510 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -37,6 +37,9 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
char *value = NULL;
struct posix_acl *acl;
+ if (!IS_POSIXACL(inode))
+ return NULL;
+
acl = get_cached_acl(inode, type);
if (acl != ACL_NOT_CACHED)
return acl;
@@ -84,6 +87,9 @@ static int btrfs_xattr_acl_get(struct dentry *dentry, const char *name,
struct posix_acl *acl;
int ret = 0;
+ if (!IS_POSIXACL(dentry->d_inode))
+ return -EOPNOTSUPP;
+
acl = btrfs_get_acl(dentry->d_inode, type);
if (IS_ERR(acl))
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f745287fbf2..4d2110eafe2 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -562,7 +562,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
u64 em_len;
u64 em_start;
struct extent_map *em;
- int ret;
+ int ret = -ENOMEM;
u32 *sums;
tree = &BTRFS_I(inode)->io_tree;
@@ -577,6 +577,9 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
compressed_len = em->block_len;
cb = kmalloc(compressed_bio_size(root, compressed_len), GFP_NOFS);
+ if (!cb)
+ goto out;
+
atomic_set(&cb->pending_bios, 0);
cb->errors = 0;
cb->inode = inode;
@@ -597,13 +600,18 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
nr_pages = (compressed_len + PAGE_CACHE_SIZE - 1) /
PAGE_CACHE_SIZE;
- cb->compressed_pages = kmalloc(sizeof(struct page *) * nr_pages,
+ cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages,
GFP_NOFS);
+ if (!cb->compressed_pages)
+ goto fail1;
+
bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
for (page_index = 0; page_index < nr_pages; page_index++) {
cb->compressed_pages[page_index] = alloc_page(GFP_NOFS |
__GFP_HIGHMEM);
+ if (!cb->compressed_pages[page_index])
+ goto fail2;
}
cb->nr_pages = nr_pages;
@@ -614,6 +622,8 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
cb->len = uncompressed_len;
comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
+ if (!comp_bio)
+ goto fail2;
comp_bio->bi_private = cb;
comp_bio->bi_end_io = end_compressed_bio_read;
atomic_inc(&cb->pending_bios);
@@ -681,6 +691,17 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
bio_put(comp_bio);
return 0;
+
+fail2:
+ for (page_index = 0; page_index < nr_pages; page_index++)
+ free_page((unsigned long)cb->compressed_pages[page_index]);
+
+ kfree(cb->compressed_pages);
+fail1:
+ kfree(cb);
+out:
+ free_extent_map(em);
+ return ret;
}
static struct list_head comp_idle_workspace[BTRFS_COMPRESS_TYPES];
@@ -900,7 +921,7 @@ int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
return ret;
}
-void __exit btrfs_exit_compress(void)
+void btrfs_exit_compress(void)
{
free_workspaces();
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b531c36455d..e1aa8d607bc 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -359,10 +359,14 @@ static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
tree = &BTRFS_I(page->mapping->host)->io_tree;
- if (page->private == EXTENT_PAGE_PRIVATE)
+ if (page->private == EXTENT_PAGE_PRIVATE) {
+ WARN_ON(1);
goto out;
- if (!page->private)
+ }
+ if (!page->private) {
+ WARN_ON(1);
goto out;
+ }
len = page->private >> 2;
WARN_ON(len == 0);
@@ -1550,6 +1554,7 @@ static int transaction_kthread(void *arg)
spin_unlock(&root->fs_info->new_trans_lock);
trans = btrfs_join_transaction(root, 1);
+ BUG_ON(IS_ERR(trans));
if (transid == trans->transid) {
ret = btrfs_commit_transaction(trans, root);
BUG_ON(ret);
@@ -2453,10 +2458,14 @@ int btrfs_commit_super(struct btrfs_root *root)
up_write(&root->fs_info->cleanup_work_sem);
trans = btrfs_join_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_commit_transaction(trans, root);
BUG_ON(ret);
/* run commit again to drop the original snapshot */
trans = btrfs_join_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
btrfs_commit_transaction(trans, root);
ret = btrfs_write_and_wait_transaction(NULL, root);
BUG_ON(ret);
@@ -2554,6 +2563,8 @@ int close_ctree(struct btrfs_root *root)
kfree(fs_info->chunk_root);
kfree(fs_info->dev_root);
kfree(fs_info->csum_root);
+ kfree(fs_info);
+
return 0;
}
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 9786963b07e..ff27d7a477b 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -171,6 +171,8 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
int ret;
path = btrfs_alloc_path();
+ if (!path)
+ return ERR_PTR(-ENOMEM);
if (dir->i_ino == BTRFS_FIRST_FREE_OBJECTID) {
key.objectid = root->root_key.objectid;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b55269340ce..f3c96fc0143 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -320,11 +320,6 @@ static int caching_kthread(void *data)
if (!path)
return -ENOMEM;
- exclude_super_stripes(extent_root, block_group);
- spin_lock(&block_group->space_info->lock);
- block_group->space_info->bytes_readonly += block_group->bytes_super;
- spin_unlock(&block_group->space_info->lock);
-
last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
/*
@@ -467,8 +462,10 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
cache->cached = BTRFS_CACHE_NO;
}
spin_unlock(&cache->lock);
- if (ret == 1)
+ if (ret == 1) {
+ free_excluded_extents(fs_info->extent_root, cache);
return 0;
+ }
}
if (load_cache_only)
@@ -3344,8 +3341,10 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
u64 reserved;
u64 max_reclaim;
u64 reclaimed = 0;
+ long time_left;
int pause = 1;
int nr_pages = (2 * 1024 * 1024) >> PAGE_CACHE_SHIFT;
+ int loops = 0;
block_rsv = &root->fs_info->delalloc_block_rsv;
space_info = block_rsv->space_info;
@@ -3358,7 +3357,7 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
max_reclaim = min(reserved, to_reclaim);
- while (1) {
+ while (loops < 1024) {
/* have the flusher threads jump in and do some IO */
smp_mb();
nr_pages = min_t(unsigned long, nr_pages,
@@ -3366,8 +3365,12 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
writeback_inodes_sb_nr_if_idle(root->fs_info->sb, nr_pages);
spin_lock(&space_info->lock);
- if (reserved > space_info->bytes_reserved)
+ if (reserved > space_info->bytes_reserved) {
+ loops = 0;
reclaimed += reserved - space_info->bytes_reserved;
+ } else {
+ loops++;
+ }
reserved = space_info->bytes_reserved;
spin_unlock(&space_info->lock);
@@ -3378,7 +3381,12 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
return -EAGAIN;
__set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(pause);
+ time_left = schedule_timeout(pause);
+
+ /* We were interrupted, exit */
+ if (time_left)
+ break;
+
pause <<= 1;
if (pause > HZ / 10)
pause = HZ / 10;
@@ -3588,8 +3596,20 @@ void block_rsv_release_bytes(struct btrfs_block_rsv *block_rsv,
if (num_bytes > 0) {
if (dest) {
- block_rsv_add_bytes(dest, num_bytes, 0);
- } else {
+ spin_lock(&dest->lock);
+ if (!dest->full) {
+ u64 bytes_to_add;
+
+ bytes_to_add = dest->size - dest->reserved;
+ bytes_to_add = min(num_bytes, bytes_to_add);
+ dest->reserved += bytes_to_add;
+ if (dest->reserved >= dest->size)
+ dest->full = 1;
+ num_bytes -= bytes_to_add;
+ }
+ spin_unlock(&dest->lock);
+ }
+ if (num_bytes) {
spin_lock(&space_info->lock);
space_info->bytes_reserved -= num_bytes;
spin_unlock(&space_info->lock);
@@ -4012,6 +4032,7 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
num_bytes = ALIGN(num_bytes, root->sectorsize);
atomic_dec(&BTRFS_I(inode)->outstanding_extents);
+ WARN_ON(atomic_read(&BTRFS_I(inode)->outstanding_extents) < 0);
spin_lock(&BTRFS_I(inode)->accounting_lock);
nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents);
@@ -5633,6 +5654,7 @@ use_block_rsv(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u32 blocksize)
{
struct btrfs_block_rsv *block_rsv;
+ struct btrfs_block_rsv *global_rsv = &root->fs_info->global_block_rsv;
int ret;
block_rsv = get_block_rsv(trans, root);
@@ -5640,14 +5662,39 @@ use_block_rsv(struct btrfs_trans_handle *trans,
if (block_rsv->size == 0) {
ret = reserve_metadata_bytes(trans, root, block_rsv,
blocksize, 0);
- if (ret)
+ /*
+ * If we couldn't reserve metadata bytes try and use some from
+ * the global reserve.
+ */
+ if (ret && block_rsv != global_rsv) {
+ ret = block_rsv_use_bytes(global_rsv, blocksize);
+ if (!ret)
+ return global_rsv;
+ return ERR_PTR(ret);
+ } else if (ret) {
return ERR_PTR(ret);
+ }
return block_rsv;
}
ret = block_rsv_use_bytes(block_rsv, blocksize);
if (!ret)
return block_rsv;
+ if (ret) {
+ WARN_ON(1);
+ ret = reserve_metadata_bytes(trans, root, block_rsv, blocksize,
+ 0);
+ if (!ret) {
+ spin_lock(&block_rsv->lock);
+ block_rsv->size += blocksize;
+ spin_unlock(&block_rsv->lock);
+ return block_rsv;
+ } else if (ret && block_rsv != global_rsv) {
+ ret = block_rsv_use_bytes(global_rsv, blocksize);
+ if (!ret)
+ return global_rsv;
+ }
+ }
return ERR_PTR(-ENOSPC);
}
@@ -6221,6 +6268,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
BUG_ON(!wc);
trans = btrfs_start_transaction(tree_root, 0);
+ BUG_ON(IS_ERR(trans));
+
if (block_rsv)
trans->block_rsv = block_rsv;
@@ -6318,6 +6367,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
btrfs_end_transaction_throttle(trans, tree_root);
trans = btrfs_start_transaction(tree_root, 0);
+ BUG_ON(IS_ERR(trans));
if (block_rsv)
trans->block_rsv = block_rsv;
}
@@ -6446,6 +6496,8 @@ static noinline int relocate_inode_pages(struct inode *inode, u64 start,
int ret = 0;
ra = kzalloc(sizeof(*ra), GFP_NOFS);
+ if (!ra)
+ return -ENOMEM;
mutex_lock(&inode->i_mutex);
first_index = start >> PAGE_CACHE_SHIFT;
@@ -6531,7 +6583,7 @@ static noinline int relocate_data_extent(struct inode *reloc_inode,
u64 end = start + extent_key->offset - 1;
em = alloc_extent_map(GFP_NOFS);
- BUG_ON(!em || IS_ERR(em));
+ BUG_ON(!em);
em->start = start;
em->len = extent_key->offset;
@@ -7477,7 +7529,7 @@ int btrfs_drop_dead_reloc_roots(struct btrfs_root *root)
BUG_ON(reloc_root->commit_root != NULL);
while (1) {
trans = btrfs_join_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
mutex_lock(&root->fs_info->drop_mutex);
ret = btrfs_drop_snapshot(trans, reloc_root);
@@ -7535,7 +7587,7 @@ int btrfs_cleanup_reloc_trees(struct btrfs_root *root)
if (found) {
trans = btrfs_start_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
ret = btrfs_commit_transaction(trans, root);
BUG_ON(ret);
}
@@ -7779,7 +7831,7 @@ static noinline int relocate_one_extent(struct btrfs_root *extent_root,
trans = btrfs_start_transaction(extent_root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
if (extent_key->objectid == 0) {
ret = del_extent_zero(trans, extent_root, path, extent_key);
@@ -8270,6 +8322,13 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
if (block_group->cached == BTRFS_CACHE_STARTED)
wait_block_group_cache_done(block_group);
+ /*
+ * We haven't cached this block group, which means we could
+ * possibly have excluded extents on this block group.
+ */
+ if (block_group->cached == BTRFS_CACHE_NO)
+ free_excluded_extents(info->extent_root, block_group);
+
btrfs_remove_free_space_cache(block_group);
btrfs_put_block_group(block_group);
@@ -8385,6 +8444,13 @@ int btrfs_read_block_groups(struct btrfs_root *root)
cache->sectorsize = root->sectorsize;
/*
+ * We need to exclude the super stripes now so that the space
+ * info has super bytes accounted for, otherwise we'll think
+ * we have more space than we actually do.
+ */
+ exclude_super_stripes(root, cache);
+
+ /*
* check for two cases, either we are full, and therefore
* don't need to bother with the caching work since we won't
* find any space, or we are empty, and we can just add all
@@ -8392,12 +8458,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
* time, particularly in the full case.
*/
if (found_key.offset == btrfs_block_group_used(&cache->item)) {
- exclude_super_stripes(root, cache);
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
free_excluded_extents(root, cache);
} else if (btrfs_block_group_used(&cache->item) == 0) {
- exclude_super_stripes(root, cache);
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
add_new_free_space(cache, root->fs_info,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 2e993cf1766..92ac5192c51 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1865,7 +1865,7 @@ static int submit_one_bio(int rw, struct bio *bio, int mirror_num,
bio_get(bio);
if (tree->ops && tree->ops->submit_bio_hook)
- tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
+ ret = tree->ops->submit_bio_hook(page->mapping->host, rw, bio,
mirror_num, bio_flags, start);
else
submit_bio(rw, bio);
@@ -1920,6 +1920,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
nr = bio_get_nr_vecs(bdev);
bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+ if (!bio)
+ return -ENOMEM;
bio_add_page(bio, page, page_size, offset);
bio->bi_end_io = end_io_func;
@@ -1944,6 +1946,7 @@ void set_page_extent_mapped(struct page *page)
static void set_page_extent_head(struct page *page, unsigned long len)
{
+ WARN_ON(!PagePrivate(page));
set_page_private(page, EXTENT_PAGE_PRIVATE_FIRST_PAGE | len << 2);
}
@@ -2126,7 +2129,7 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
ret = __extent_read_full_page(tree, page, get_extent, &bio, 0,
&bio_flags);
if (bio)
- submit_one_bio(READ, bio, 0, bio_flags);
+ ret = submit_one_bio(READ, bio, 0, bio_flags);
return ret;
}
@@ -2819,9 +2822,17 @@ int try_release_extent_state(struct extent_map_tree *map,
* at this point we can safely clear everything except the
* locked bit and the nodatasum bit
*/
- clear_extent_bit(tree, start, end,
+ ret = clear_extent_bit(tree, start, end,
~(EXTENT_LOCKED | EXTENT_NODATASUM),
0, 0, NULL, mask);
+
+ /* if clear_extent_bit failed for enomem reasons,
+ * we can't allow the release to continue.
+ */
+ if (ret < 0)
+ ret = 0;
+ else
+ ret = 1;
}
return ret;
}
@@ -3192,7 +3203,13 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
}
if (!PageUptodate(p))
uptodate = 0;
- unlock_page(p);
+
+ /*
+ * see below about how we avoid a nasty race with release page
+ * and why we unlock later
+ */
+ if (i != 0)
+ unlock_page(p);
}
if (uptodate)
set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
@@ -3216,9 +3233,26 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
atomic_inc(&eb->refs);
spin_unlock(&tree->buffer_lock);
radix_tree_preload_end();
+
+ /*
+ * there is a race where release page may have
+ * tried to find this extent buffer in the radix
+ * but failed. It will tell the VM it is safe to
+ * reclaim the, and it will clear the page private bit.
+ * We must make sure to set the page private bit properly
+ * after the extent buffer is in the radix tree so
+ * it doesn't get lost
+ */
+ set_page_extent_mapped(eb->first_page);
+ set_page_extent_head(eb->first_page, eb->len);
+ if (!page0)
+ unlock_page(eb->first_page);
return eb;
free_eb:
+ if (eb->first_page && !page0)
+ unlock_page(eb->first_page);
+
if (!atomic_dec_and_test(&eb->refs))
return exists;
btrfs_release_extent_buffer(eb);
@@ -3269,10 +3303,11 @@ int clear_extent_buffer_dirty(struct extent_io_tree *tree,
continue;
lock_page(page);
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
if (i == 0)
set_page_extent_head(page, eb->len);
- else
- set_page_private(page, EXTENT_PAGE_PRIVATE);
clear_page_dirty_for_io(page);
spin_lock_irq(&page->mapping->tree_lock);
@@ -3462,6 +3497,13 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
for (i = start_i; i < num_pages; i++) {
page = extent_buffer_page(eb, i);
+
+ WARN_ON(!PagePrivate(page));
+
+ set_page_extent_mapped(page);
+ if (i == 0)
+ set_page_extent_head(page, eb->len);
+
if (inc_all_pages)
page_cache_get(page);
if (!PageUptodate(page)) {
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index b0e1fce1253..2b6c12e983b 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -51,8 +51,8 @@ struct extent_map *alloc_extent_map(gfp_t mask)
{
struct extent_map *em;
em = kmem_cache_alloc(extent_map_cache, mask);
- if (!em || IS_ERR(em))
- return em;
+ if (!em)
+ return NULL;
em->in_tree = 0;
em->flags = 0;
em->compress_type = BTRFS_COMPRESS_NONE;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a562a250ae7..4f19a3e1bf3 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -536,6 +536,8 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
root = root->fs_info->csum_root;
path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
while (1) {
key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
@@ -548,7 +550,10 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
if (path->slots[0] == 0)
goto out;
path->slots[0]--;
+ } else if (ret < 0) {
+ goto out;
}
+
leaf = path->nodes[0];
btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c800d58f301..7084140d594 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -186,6 +186,7 @@ int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
split = alloc_extent_map(GFP_NOFS);
if (!split2)
split2 = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!split || !split2);
write_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len);
@@ -793,8 +794,12 @@ again:
for (i = 0; i < num_pages; i++) {
pages[i] = grab_cache_page(inode->i_mapping, index + i);
if (!pages[i]) {
- err = -ENOMEM;
- BUG_ON(1);
+ int c;
+ for (c = i - 1; c >= 0; c--) {
+ unlock_page(pages[c]);
+ page_cache_release(pages[c]);
+ }
+ return -ENOMEM;
}
wait_on_page_writeback(pages[i]);
}
@@ -946,6 +951,10 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
(sizeof(struct page *)));
pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
+ if (!pages) {
+ ret = -ENOMEM;
+ goto out;
+ }
/* generic_write_checks can change our pos */
start_pos = pos;
@@ -984,8 +993,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
size_t write_bytes = min(iov_iter_count(&i),
nrptrs * (size_t)PAGE_CACHE_SIZE -
offset);
- size_t num_pages = (write_bytes + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
+ size_t num_pages = (write_bytes + offset +
+ PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
WARN_ON(num_pages > nrptrs);
memset(pages, 0, sizeof(struct page *) * nrptrs);
@@ -1015,8 +1024,8 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
copied = btrfs_copy_from_user(pos, num_pages,
write_bytes, pages, &i);
- dirty_pages = (copied + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
+ dirty_pages = (copied + offset + PAGE_CACHE_SIZE - 1) >>
+ PAGE_CACHE_SHIFT;
if (num_pages > dirty_pages) {
if (copied > 0)
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 60d68426695..a0390657451 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -987,11 +987,18 @@ tree_search_offset(struct btrfs_block_group_cache *block_group,
return entry;
}
-static void unlink_free_space(struct btrfs_block_group_cache *block_group,
- struct btrfs_free_space *info)
+static inline void
+__unlink_free_space(struct btrfs_block_group_cache *block_group,
+ struct btrfs_free_space *info)
{
rb_erase(&info->offset_index, &block_group->free_space_offset);
block_group->free_extents--;
+}
+
+static void unlink_free_space(struct btrfs_block_group_cache *block_group,
+ struct btrfs_free_space *info)
+{
+ __unlink_free_space(block_group, info);
block_group->free_space -= info->bytes;
}
@@ -1016,14 +1023,18 @@ static void recalculate_thresholds(struct btrfs_block_group_cache *block_group)
u64 max_bytes;
u64 bitmap_bytes;
u64 extent_bytes;
+ u64 size = block_group->key.offset;
/*
* The goal is to keep the total amount of memory used per 1gb of space
* at or below 32k, so we need to adjust how much memory we allow to be
* used by extent based free space tracking
*/
- max_bytes = MAX_CACHE_BYTES_PER_GIG *
- (div64_u64(block_group->key.offset, 1024 * 1024 * 1024));
+ if (size < 1024 * 1024 * 1024)
+ max_bytes = MAX_CACHE_BYTES_PER_GIG;
+ else
+ max_bytes = MAX_CACHE_BYTES_PER_GIG *
+ div64_u64(size, 1024 * 1024 * 1024);
/*
* we want to account for 1 more bitmap than what we have so we can make
@@ -1171,6 +1182,16 @@ static void add_new_bitmap(struct btrfs_block_group_cache *block_group,
recalculate_thresholds(block_group);
}
+static void free_bitmap(struct btrfs_block_group_cache *block_group,
+ struct btrfs_free_space *bitmap_info)
+{
+ unlink_free_space(block_group, bitmap_info);
+ kfree(bitmap_info->bitmap);
+ kfree(bitmap_info);
+ block_group->total_bitmaps--;
+ recalculate_thresholds(block_group);
+}
+
static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_group,
struct btrfs_free_space *bitmap_info,
u64 *offset, u64 *bytes)
@@ -1195,6 +1216,7 @@ again:
*/
search_start = *offset;
search_bytes = *bytes;
+ search_bytes = min(search_bytes, end - search_start + 1);
ret = search_bitmap(block_group, bitmap_info, &search_start,
&search_bytes);
BUG_ON(ret < 0 || search_start != *offset);
@@ -1211,13 +1233,8 @@ again:
if (*bytes) {
struct rb_node *next = rb_next(&bitmap_info->offset_index);
- if (!bitmap_info->bytes) {
- unlink_free_space(block_group, bitmap_info);
- kfree(bitmap_info->bitmap);
- kfree(bitmap_info);
- block_group->total_bitmaps--;
- recalculate_thresholds(block_group);
- }
+ if (!bitmap_info->bytes)
+ free_bitmap(block_group, bitmap_info);
/*
* no entry after this bitmap, but we still have bytes to
@@ -1250,13 +1267,8 @@ again:
return -EAGAIN;
goto again;
- } else if (!bitmap_info->bytes) {
- unlink_free_space(block_group, bitmap_info);
- kfree(bitmap_info->bitmap);
- kfree(bitmap_info);
- block_group->total_bitmaps--;
- recalculate_thresholds(block_group);
- }
+ } else if (!bitmap_info->bytes)
+ free_bitmap(block_group, bitmap_info);
return 0;
}
@@ -1359,22 +1371,14 @@ out:
return ret;
}
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
- u64 offset, u64 bytes)
+bool try_merge_free_space(struct btrfs_block_group_cache *block_group,
+ struct btrfs_free_space *info, bool update_stat)
{
- struct btrfs_free_space *right_info = NULL;
- struct btrfs_free_space *left_info = NULL;
- struct btrfs_free_space *info = NULL;
- int ret = 0;
-
- info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
- if (!info)
- return -ENOMEM;
-
- info->offset = offset;
- info->bytes = bytes;
-
- spin_lock(&block_group->tree_lock);
+ struct btrfs_free_space *left_info;
+ struct btrfs_free_space *right_info;
+ bool merged = false;
+ u64 offset = info->offset;
+ u64 bytes = info->bytes;
/*
* first we want to see if there is free space adjacent to the range we
@@ -1388,37 +1392,62 @@ int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
else
left_info = tree_search_offset(block_group, offset - 1, 0, 0);
- /*
- * If there was no extent directly to the left or right of this new
- * extent then we know we're going to have to allocate a new extent, so
- * before we do that see if we need to drop this into a bitmap
- */
- if ((!left_info || left_info->bitmap) &&
- (!right_info || right_info->bitmap)) {
- ret = insert_into_bitmap(block_group, info);
-
- if (ret < 0) {
- goto out;
- } else if (ret) {
- ret = 0;
- goto out;
- }
- }
-
if (right_info && !right_info->bitmap) {
- unlink_free_space(block_group, right_info);
+ if (update_stat)
+ unlink_free_space(block_group, right_info);
+ else
+ __unlink_free_space(block_group, right_info);
info->bytes += right_info->bytes;
kfree(right_info);
+ merged = true;
}
if (left_info && !left_info->bitmap &&
left_info->offset + left_info->bytes == offset) {
- unlink_free_space(block_group, left_info);
+ if (update_stat)
+ unlink_free_space(block_group, left_info);
+ else
+ __unlink_free_space(block_group, left_info);
info->offset = left_info->offset;
info->bytes += left_info->bytes;
kfree(left_info);
+ merged = true;
}
+ return merged;
+}
+
+int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+ u64 offset, u64 bytes)
+{
+ struct btrfs_free_space *info;
+ int ret = 0;
+
+ info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
+ if (!info)
+ return -ENOMEM;
+
+ info->offset = offset;
+ info->bytes = bytes;
+
+ spin_lock(&block_group->tree_lock);
+
+ if (try_merge_free_space(block_group, info, true))
+ goto link;
+
+ /*
+ * There was no extent directly to the left or right of this new
+ * extent then we know we're going to have to allocate a new extent, so
+ * before we do that see if we need to drop this into a bitmap
+ */
+ ret = insert_into_bitmap(block_group, info);
+ if (ret < 0) {
+ goto out;
+ } else if (ret) {
+ ret = 0;
+ goto out;
+ }
+link:
ret = link_free_space(block_group, info);
if (ret)
kfree(info);
@@ -1621,6 +1650,7 @@ __btrfs_return_cluster_to_free_space(
node = rb_next(&entry->offset_index);
rb_erase(&entry->offset_index, &cluster->root);
BUG_ON(entry->bitmap);
+ try_merge_free_space(block_group, entry, false);
tree_insert_offset(&block_group->free_space_offset,
entry->offset, &entry->offset_index, 0);
}
@@ -1685,13 +1715,8 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
ret = offset;
if (entry->bitmap) {
bitmap_clear_bits(block_group, entry, offset, bytes);
- if (!entry->bytes) {
- unlink_free_space(block_group, entry);
- kfree(entry->bitmap);
- kfree(entry);
- block_group->total_bitmaps--;
- recalculate_thresholds(block_group);
- }
+ if (!entry->bytes)
+ free_bitmap(block_group, entry);
} else {
unlink_free_space(block_group, entry);
entry->offset += bytes;
@@ -1789,6 +1814,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
ret = search_start;
bitmap_clear_bits(block_group, entry, ret, bytes);
+ if (entry->bytes == 0)
+ free_bitmap(block_group, entry);
out:
spin_unlock(&cluster->lock);
spin_unlock(&block_group->tree_lock);
@@ -1842,15 +1869,26 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
entry->offset += bytes;
entry->bytes -= bytes;
- if (entry->bytes == 0) {
+ if (entry->bytes == 0)
rb_erase(&entry->offset_index, &cluster->root);
- kfree(entry);
- }
break;
}
out:
spin_unlock(&cluster->lock);
+ if (!ret)
+ return 0;
+
+ spin_lock(&block_group->tree_lock);
+
+ block_group->free_space -= bytes;
+ if (entry->bytes == 0) {
+ block_group->free_extents--;
+ kfree(entry);
+ }
+
+ spin_unlock(&block_group->tree_lock);
+
return ret;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 160b55b3e13..fb9bd7832b6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -416,7 +416,7 @@ again:
}
if (start == 0) {
trans = btrfs_join_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -612,6 +612,7 @@ retry:
GFP_NOFS);
trans = btrfs_join_transaction(root, 1);
+ BUG_ON(IS_ERR(trans));
ret = btrfs_reserve_extent(trans, root,
async_extent->compressed_size,
async_extent->compressed_size,
@@ -643,6 +644,7 @@ retry:
async_extent->ram_size - 1, 0);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = async_extent->start;
em->len = async_extent->ram_size;
em->orig_start = em->start;
@@ -771,7 +773,7 @@ static noinline int cow_file_range(struct inode *inode,
BUG_ON(root == root->fs_info->tree_root);
trans = btrfs_join_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -819,6 +821,7 @@ static noinline int cow_file_range(struct inode *inode,
BUG_ON(ret);
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = start;
em->orig_start = em->start;
ram_size = ins.offset;
@@ -1049,7 +1052,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
} else {
trans = btrfs_join_transaction(root, 1);
}
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
cow_start = (u64)-1;
cur_offset = start;
@@ -1168,6 +1171,7 @@ out_check:
struct extent_map_tree *em_tree;
em_tree = &BTRFS_I(inode)->extent_tree;
em = alloc_extent_map(GFP_NOFS);
+ BUG_ON(!em);
em->start = cur_offset;
em->orig_start = em->start;
em->len = num_bytes;
@@ -1557,6 +1561,7 @@ out:
out_page:
unlock_page(page);
page_cache_release(page);
+ kfree(fixup);
}
/*
@@ -1703,7 +1708,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
trans = btrfs_join_transaction_nolock(root, 1);
else
trans = btrfs_join_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
ret = btrfs_update_inode(trans, root, inode);
@@ -1720,6 +1725,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
trans = btrfs_join_transaction_nolock(root, 1);
else
trans = btrfs_join_transaction(root, 1);
+ BUG_ON(IS_ERR(trans));
btrfs_set_trans_block_group(trans, inode);
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -2354,6 +2360,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
*/
if (is_bad_inode(inode)) {
trans = btrfs_start_transaction(root, 0);
+ BUG_ON(IS_ERR(trans));
btrfs_orphan_del(trans, inode);
btrfs_end_transaction(trans, root);
iput(inode);
@@ -2381,6 +2388,7 @@ void btrfs_orphan_cleanup(struct btrfs_root *root)
if (root->orphan_block_rsv || root->orphan_item_inserted) {
trans = btrfs_join_transaction(root, 1);
+ BUG_ON(IS_ERR(trans));
btrfs_end_transaction(trans, root);
}
@@ -2641,7 +2649,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
- goto err;
+ goto out;
}
path->leave_spinning = 1;
@@ -2714,9 +2722,10 @@ static int check_path_shared(struct btrfs_root *root,
struct extent_buffer *eb;
int level;
u64 refs = 1;
- int uninitialized_var(ret);
for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
+ int ret;
+
if (!path->nodes[level])
break;
eb = path->nodes[level];
@@ -2727,7 +2736,7 @@ static int check_path_shared(struct btrfs_root *root,
if (refs > 1)
return 1;
}
- return ret; /* XXX callers? */
+ return 0;
}
/*
@@ -4134,7 +4143,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
}
srcu_read_unlock(&root->fs_info->subvol_srcu, index);
- if (root != sub_root) {
+ if (!IS_ERR(inode) && root != sub_root) {
down_read(&root->fs_info->cleanup_work_sem);
if (!(inode->i_sb->s_flags & MS_RDONLY))
btrfs_orphan_cleanup(sub_root);
@@ -4347,6 +4356,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
trans = btrfs_join_transaction_nolock(root, 1);
else
trans = btrfs_join_transaction(root, 1);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
btrfs_set_trans_block_group(trans, inode);
if (nolock)
ret = btrfs_end_transaction_nolock(trans, root);
@@ -4372,6 +4383,7 @@ void btrfs_dirty_inode(struct inode *inode)
return;
trans = btrfs_join_transaction(root, 1);
+ BUG_ON(IS_ERR(trans));
btrfs_set_trans_block_group(trans, inode);
ret = btrfs_update_inode(trans, root, inode);
@@ -5176,6 +5188,8 @@ again:
em = NULL;
btrfs_release_path(root, path);
trans = btrfs_join_transaction(root, 1);
+ if (IS_ERR(trans))
+ return ERR_CAST(trans);
goto again;
}
map = kmap(page);
@@ -5280,8 +5294,8 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
trans = btrfs_join_transaction(root, 0);
- if (!trans)
- return ERR_PTR(-ENOMEM);
+ if (IS_ERR(trans))
+ return ERR_CAST(trans);
trans->block_rsv = &root->fs_info->delalloc_block_rsv;
@@ -5505,7 +5519,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
* while we look for nocow cross refs
*/
trans = btrfs_join_transaction(root, 0);
- if (!trans)
+ if (IS_ERR(trans))
goto must_cow;
if (can_nocow_odirect(trans, inode, start, len) == 1) {
@@ -5640,7 +5654,7 @@ again:
BUG_ON(!ordered);
trans = btrfs_join_transaction(root, 1);
- if (!trans) {
+ if (IS_ERR(trans)) {
err = -ENOMEM;
goto out;
}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index a506a22b522..be2d4f6aaa5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -203,7 +203,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
trans = btrfs_join_transaction(root, 1);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
ret = btrfs_update_inode(trans, root, inode);
BUG_ON(ret);
@@ -907,6 +907,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
if (new_size > old_size) {
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_unlock;
+ }
ret = btrfs_grow_device(trans, device, new_size);
btrfs_commit_transaction(trans, root);
} else {
@@ -1898,7 +1902,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
memcpy(&new_key, &key, sizeof(new_key));
new_key.objectid = inode->i_ino;
- new_key.offset = key.offset + destoff - off;
+ if (off <= key.offset)
+ new_key.offset = key.offset + destoff - off;
+ else
+ new_key.offset = destoff;
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
@@ -2082,7 +2089,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
ret = -ENOMEM;
trans = btrfs_start_ioctl_transaction(root, 0);
- if (!trans)
+ if (IS_ERR(trans))
goto out_drop;
file->private_data = trans;
@@ -2138,9 +2145,9 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
path->leave_spinning = 1;
trans = btrfs_start_transaction(root, 1);
- if (!trans) {
+ if (IS_ERR(trans)) {
btrfs_free_path(path);
- return -ENOMEM;
+ return PTR_ERR(trans);
}
dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
@@ -2201,7 +2208,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
int num_types = 4;
int alloc_size;
int ret = 0;
- int slot_count = 0;
+ u64 slot_count = 0;
int i, c;
if (copy_from_user(&space_args,
@@ -2240,7 +2247,7 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
goto out;
}
- slot_count = min_t(int, space_args.space_slots, slot_count);
+ slot_count = min_t(u64, space_args.space_slots, slot_count);
alloc_size = sizeof(*dest) * slot_count;
@@ -2260,6 +2267,9 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
for (i = 0; i < num_types; i++) {
struct btrfs_space_info *tmp;
+ if (!slot_count)
+ break;
+
info = NULL;
rcu_read_lock();
list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
@@ -2281,7 +2291,10 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
memcpy(dest, &space, sizeof(space));
dest++;
space_args.total_spaces++;
+ slot_count--;
}
+ if (!slot_count)
+ break;
}
up_read(&info->groups_sem);
}
@@ -2334,6 +2347,8 @@ static noinline long btrfs_ioctl_start_sync(struct file *file, void __user *argp
u64 transid;
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
transid = trans->transid;
btrfs_commit_transaction_async(trans, root, 0);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2b61e1ddcd9..083a5547737 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -141,7 +141,7 @@ static inline struct rb_node *tree_search(struct btrfs_ordered_inode_tree *tree,
u64 file_offset)
{
struct rb_root *root = &tree->tree;
- struct rb_node *prev;
+ struct rb_node *prev = NULL;
struct rb_node *ret;
struct btrfs_ordered_extent *entry;
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 0d126be22b6..fb2605d998e 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -260,6 +260,7 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
#else
BUG();
#endif
+ break;
case BTRFS_BLOCK_GROUP_ITEM_KEY:
bi = btrfs_item_ptr(l, i,
struct btrfs_block_group_item);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 045c9c2b2d7..0825e4ed944 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1157,6 +1157,7 @@ static int clone_backref_node(struct btrfs_trans_handle *trans,
new_node->bytenr = dest->node->start;
new_node->level = node->level;
new_node->lowest = node->lowest;
+ new_node->checked = 1;
new_node->root = dest;
if (!node->lowest) {
@@ -2028,6 +2029,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
while (1) {
trans = btrfs_start_transaction(root, 0);
+ BUG_ON(IS_ERR(trans));
trans->block_rsv = rc->block_rsv;
ret = btrfs_block_rsv_check(trans, root, rc->block_rsv,
@@ -2147,6 +2149,12 @@ again:
}
trans = btrfs_join_transaction(rc->extent_root, 1);
+ if (IS_ERR(trans)) {
+ if (!err)
+ btrfs_block_rsv_release(rc->extent_root,
+ rc->block_rsv, num_bytes);
+ return PTR_ERR(trans);
+ }
if (!err) {
if (num_bytes != rc->merging_rsv_size) {
@@ -3222,6 +3230,7 @@ truncate:
trans = btrfs_join_transaction(root, 0);
if (IS_ERR(trans)) {
btrfs_free_path(path);
+ ret = PTR_ERR(trans);
goto out;
}
@@ -3628,6 +3637,7 @@ int prepare_to_relocate(struct reloc_control *rc)
set_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root, 1);
+ BUG_ON(IS_ERR(trans));
btrfs_commit_transaction(trans, rc->extent_root);
return 0;
}
@@ -3657,6 +3667,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
while (1) {
trans = btrfs_start_transaction(rc->extent_root, 0);
+ BUG_ON(IS_ERR(trans));
if (update_backref_cache(trans, &rc->backref_cache)) {
btrfs_end_transaction(trans, rc->extent_root);
@@ -3804,7 +3815,10 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
/* get rid of pinned extents */
trans = btrfs_join_transaction(rc->extent_root, 1);
- btrfs_commit_transaction(trans, rc->extent_root);
+ if (IS_ERR(trans))
+ err = PTR_ERR(trans);
+ else
+ btrfs_commit_transaction(trans, rc->extent_root);
out_free:
btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
btrfs_free_path(path);
@@ -4022,6 +4036,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
int ret;
trans = btrfs_start_transaction(root->fs_info->tree_root, 0);
+ BUG_ON(IS_ERR(trans));
memset(&root->root_item.drop_progress, 0,
sizeof(root->root_item.drop_progress));
@@ -4125,6 +4140,11 @@ int btrfs_recover_relocation(struct btrfs_root *root)
set_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root, 1);
+ if (IS_ERR(trans)) {
+ unset_reloc_control(rc);
+ err = PTR_ERR(trans);
+ goto out_free;
+ }
rc->merge_reloc_tree = 1;
@@ -4154,9 +4174,13 @@ int btrfs_recover_relocation(struct btrfs_root *root)
unset_reloc_control(rc);
trans = btrfs_join_transaction(rc->extent_root, 1);
- btrfs_commit_transaction(trans, rc->extent_root);
-out:
+ if (IS_ERR(trans))
+ err = PTR_ERR(trans);
+ else
+ btrfs_commit_transaction(trans, rc->extent_root);
+out_free:
kfree(rc);
+out:
while (!list_empty(&reloc_roots)) {
reloc_root = list_entry(reloc_roots.next,
struct btrfs_root, root_list);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index b2130c46fdb..a004008f7d2 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -383,7 +383,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
struct btrfs_fs_devices **fs_devices)
{
substring_t args[MAX_OPT_ARGS];
- char *opts, *p;
+ char *opts, *orig, *p;
int error = 0;
int intarg;
@@ -397,6 +397,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
opts = kstrdup(options, GFP_KERNEL);
if (!opts)
return -ENOMEM;
+ orig = opts;
while ((p = strsep(&opts, ",")) != NULL) {
int token;
@@ -432,7 +433,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
}
out_free_opts:
- kfree(opts);
+ kfree(orig);
out:
/*
* If no subvolume name is specified we use the default one. Allocate
@@ -623,6 +624,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
btrfs_wait_ordered_extents(root, 0, 0);
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
ret = btrfs_commit_transaction(trans, root);
return ret;
}
@@ -761,6 +764,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
}
btrfs_close_devices(fs_devices);
+ kfree(fs_info);
+ kfree(tree_root);
} else {
char b[BDEVNAME_SIZE];
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index bae5c7b8bbe..3d73c8d93bb 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1161,6 +1161,11 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
INIT_DELAYED_WORK(&ac->work, do_async_commit);
ac->root = root;
ac->newtrans = btrfs_join_transaction(root, 0);
+ if (IS_ERR(ac->newtrans)) {
+ int err = PTR_ERR(ac->newtrans);
+ kfree(ac);
+ return err;
+ }
/* take transaction reference */
mutex_lock(&root->fs_info->trans_mutex);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 054744ac571..a4bbb854dfd 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -338,6 +338,12 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans,
}
dst_copy = kmalloc(item_size, GFP_NOFS);
src_copy = kmalloc(item_size, GFP_NOFS);
+ if (!dst_copy || !src_copy) {
+ btrfs_release_path(root, path);
+ kfree(dst_copy);
+ kfree(src_copy);
+ return -ENOMEM;
+ }
read_extent_buffer(eb, src_copy, src_ptr, item_size);
@@ -665,6 +671,9 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
btrfs_dir_item_key_to_cpu(leaf, di, &location);
name_len = btrfs_dir_name_len(leaf, di);
name = kmalloc(name_len, GFP_NOFS);
+ if (!name)
+ return -ENOMEM;
+
read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
btrfs_release_path(root, path);
@@ -744,6 +753,9 @@ static noinline int backref_in_log(struct btrfs_root *log,
int match = 0;
path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
if (ret != 0)
goto out;
@@ -967,6 +979,8 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
key.offset = (u64)-1;
path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
while (1) {
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -1178,6 +1192,9 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
name_len = btrfs_dir_name_len(eb, di);
name = kmalloc(name_len, GFP_NOFS);
+ if (!name)
+ return -ENOMEM;
+
log_type = btrfs_dir_type(eb, di);
read_extent_buffer(eb, name, (unsigned long)(di + 1),
name_len);
@@ -1692,6 +1709,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
root_owner = btrfs_header_owner(parent);
next = btrfs_find_create_tree_block(root, bytenr, blocksize);
+ if (!next)
+ return -ENOMEM;
if (*level == 1) {
wc->process_func(root, next, wc, ptr_gen);
@@ -2032,6 +2051,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
wait_log_commit(trans, log_root_tree,
log_root_tree->log_transid);
mutex_unlock(&log_root_tree->log_mutex);
+ ret = 0;
goto out;
}
atomic_set(&log_root_tree->log_commit[index2], 1);
@@ -2096,7 +2116,7 @@ out:
smp_mb();
if (waitqueue_active(&root->log_commit_wait[index1]))
wake_up(&root->log_commit_wait[index1]);
- return 0;
+ return ret;
}
static void free_log_tree(struct btrfs_trans_handle *trans,
@@ -2194,6 +2214,9 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
log = root->log_root;
path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+
di = btrfs_lookup_dir_item(trans, log, path, dir->i_ino,
name, name_len, -1);
if (IS_ERR(di)) {
@@ -2594,6 +2617,9 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
ins_data = kmalloc(nr * sizeof(struct btrfs_key) +
nr * sizeof(u32), GFP_NOFS);
+ if (!ins_data)
+ return -ENOMEM;
+
ins_sizes = (u32 *)ins_data;
ins_keys = (struct btrfs_key *)(ins_data + nr * sizeof(u32));
@@ -2725,7 +2751,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
log = root->log_root;
path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
dst_path = btrfs_alloc_path();
+ if (!dst_path) {
+ btrfs_free_path(path);
+ return -ENOMEM;
+ }
min_key.objectid = inode->i_ino;
min_key.type = BTRFS_INODE_ITEM_KEY;
@@ -3080,6 +3112,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
BUG_ON(!path);
trans = btrfs_start_transaction(fs_info->tree_root, 0);
+ BUG_ON(IS_ERR(trans));
wc.trans = trans;
wc.pin = 1;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d158530233b..af7dbca1527 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1213,6 +1213,10 @@ static int btrfs_rm_dev_item(struct btrfs_root *root,
return -ENOMEM;
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ btrfs_free_path(path);
+ return PTR_ERR(trans);
+ }
key.objectid = BTRFS_DEV_ITEMS_OBJECTID;
key.type = BTRFS_DEV_ITEM_KEY;
key.offset = device->devid;
@@ -1601,11 +1605,19 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
ret = find_next_devid(root, &device->devid);
if (ret) {
+ kfree(device->name);
kfree(device);
goto error;
}
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ kfree(device->name);
+ kfree(device);
+ ret = PTR_ERR(trans);
+ goto error;
+ }
+
lock_chunks(root);
device->writeable = 1;
@@ -1873,7 +1885,7 @@ static int btrfs_relocate_chunk(struct btrfs_root *root,
return ret;
trans = btrfs_start_transaction(root, 0);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
lock_chunks(root);
@@ -2047,7 +2059,7 @@ int btrfs_balance(struct btrfs_root *dev_root)
BUG_ON(ret);
trans = btrfs_start_transaction(dev_root, 0);
- BUG_ON(!trans);
+ BUG_ON(IS_ERR(trans));
ret = btrfs_grow_device(trans, device, old_size);
BUG_ON(ret);
@@ -2213,6 +2225,11 @@ again:
/* Shrinking succeeded, else we would be at "done". */
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto done;
+ }
+
lock_chunks(root);
device->disk_total_bytes = new_size;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0bc68de8edd..f0aef787a10 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -60,6 +60,7 @@ int ceph_init_dentry(struct dentry *dentry)
}
di->dentry = dentry;
di->lease_session = NULL;
+ di->parent_inode = igrab(dentry->d_parent->d_inode);
dentry->d_fsdata = di;
dentry->d_time = jiffies;
ceph_dentry_lru_add(dentry);
@@ -1033,7 +1034,7 @@ static void ceph_dentry_release(struct dentry *dentry)
u64 snapid = CEPH_NOSNAP;
if (!IS_ROOT(dentry)) {
- parent_inode = dentry->d_parent->d_inode;
+ parent_inode = di->parent_inode;
if (parent_inode)
snapid = ceph_snap(parent_inode);
}
@@ -1058,6 +1059,8 @@ static void ceph_dentry_release(struct dentry *dentry)
kmem_cache_free(ceph_dentry_cachep, di);
dentry->d_fsdata = NULL;
}
+ if (parent_inode)
+ iput(parent_inode);
}
static int ceph_snapdir_d_revalidate(struct dentry *dentry,
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 39c243acd06..f40b9139e43 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -584,10 +584,14 @@ static void queue_realm_cap_snaps(struct ceph_snap_realm *realm)
if (lastinode)
iput(lastinode);
- dout("queue_realm_cap_snaps %p %llx children\n", realm, realm->ino);
- list_for_each_entry(child, &realm->children, child_item)
- queue_realm_cap_snaps(child);
+ list_for_each_entry(child, &realm->children, child_item) {
+ dout("queue_realm_cap_snaps %p %llx queue child %p %llx\n",
+ realm, realm->ino, child, child->ino);
+ list_del_init(&child->dirty_item);
+ list_add(&child->dirty_item, &realm->dirty_item);
+ }
+ list_del_init(&realm->dirty_item);
dout("queue_realm_cap_snaps %p %llx done\n", realm, realm->ino);
}
@@ -683,7 +687,9 @@ more:
* queue cap snaps _after_ we've built the new snap contexts,
* so that i_head_snapc can be set appropriately.
*/
- list_for_each_entry(realm, &dirty_realms, dirty_item) {
+ while (!list_empty(&dirty_realms)) {
+ realm = list_first_entry(&dirty_realms, struct ceph_snap_realm,
+ dirty_item);
queue_realm_cap_snaps(realm);
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 20b907d76ae..88fcaa21b80 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -207,6 +207,7 @@ struct ceph_dentry_info {
struct dentry *dentry;
u64 time;
u64 offset;
+ struct inode *parent_inode;
};
struct ceph_inode_xattrs_info {
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index ee45648b0d1..7cb0f7f847e 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -3,6 +3,7 @@ config CIFS
depends on INET
select NLS
select CRYPTO
+ select CRYPTO_MD4
select CRYPTO_MD5
select CRYPTO_HMAC
select CRYPTO_ARC4
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index f1c68629f27..0a265ad9e42 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -282,8 +282,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
cFYI(1, "in %s", __func__);
BUG_ON(IS_ROOT(mntpt));
- xid = GetXid();
-
/*
* The MSDFS spec states that paths in DFS referral requests and
* responses must be prefixed by a single '\' character instead of
@@ -293,7 +291,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
mnt = ERR_PTR(-ENOMEM);
full_path = build_path_from_dentry(mntpt);
if (full_path == NULL)
- goto free_xid;
+ goto cdda_exit;
cifs_sb = CIFS_SB(mntpt->d_inode->i_sb);
tlink = cifs_sb_tlink(cifs_sb);
@@ -303,9 +301,11 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
}
ses = tlink_tcon(tlink)->ses;
+ xid = GetXid();
rc = get_dfs_path(xid, ses, full_path + 1, cifs_sb->local_nls,
&num_referrals, &referrals,
cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR);
+ FreeXid(xid);
cifs_put_tlink(tlink);
@@ -338,8 +338,7 @@ success:
free_dfs_info_array(referrals, num_referrals);
free_full_path:
kfree(full_path);
-free_xid:
- FreeXid(xid);
+cdda_exit:
cFYI(1, "leaving %s" , __func__);
return mnt;
}
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 1e7636b145a..beeebf19423 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -372,6 +372,10 @@ static void parse_dacl(struct cifs_acl *pdacl, char *end_of_acl,
ppace = kmalloc(num_aces * sizeof(struct cifs_ace *),
GFP_KERNEL);
+ if (!ppace) {
+ cERROR(1, "DACL memory allocation error");
+ return;
+ }
for (i = 0; i < num_aces; ++i) {
ppace[i] = (struct cifs_ace *) (acl_base + acl_size);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 0db5f1de022..a51585f9852 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -657,9 +657,10 @@ calc_seckey(struct cifsSesInfo *ses)
get_random_bytes(sec_key, CIFS_SESS_KEY_SIZE);
tfm_arc4 = crypto_alloc_blkcipher("ecb(arc4)", 0, CRYPTO_ALG_ASYNC);
- if (!tfm_arc4 || IS_ERR(tfm_arc4)) {
+ if (IS_ERR(tfm_arc4)) {
+ rc = PTR_ERR(tfm_arc4);
cERROR(1, "could not allocate crypto API arc4\n");
- return PTR_ERR(tfm_arc4);
+ return rc;
}
desc.tfm = tfm_arc4;
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 14789a97304..a9371b6578c 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -127,5 +127,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
extern const struct export_operations cifs_export_ops;
#endif /* EXPERIMENTAL */
-#define CIFS_VERSION "1.69"
+#define CIFS_VERSION "1.71"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index edd5b29b53c..17afb0fbcae 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -188,6 +188,8 @@ struct TCP_Server_Info {
/* multiplexed reads or writes */
unsigned int maxBuf; /* maxBuf specifies the maximum */
/* message size the server can send or receive for non-raw SMBs */
+ /* maxBuf is returned by SMB NegotiateProtocol so maxBuf is only 0 */
+ /* when socket is setup (and during reconnect) before NegProt sent */
unsigned int max_rw; /* maxRw specifies the maximum */
/* message size the server can send or receive for */
/* SMB_COM_WRITE_RAW or SMB_COM_READ_RAW. */
@@ -652,7 +654,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
#define MID_REQUEST_SUBMITTED 2
#define MID_RESPONSE_RECEIVED 4
#define MID_RETRY_NEEDED 8 /* session closed while this request out */
-#define MID_NO_RESP_NEEDED 0x10
+#define MID_RESPONSE_MALFORMED 0x10
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 3106f5e5c63..904aa47e351 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -136,9 +136,6 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command)
}
}
- if (ses->status == CifsExiting)
- return -EIO;
-
/*
* Give demultiplex thread up to 10 seconds to reconnect, should be
* greater than cifs socket timeout which is 7 seconds
@@ -156,7 +153,7 @@ cifs_reconnect_tcon(struct cifsTconInfo *tcon, int smb_command)
* retrying until process is killed or server comes
* back on-line
*/
- if (!tcon->retry || ses->status == CifsExiting) {
+ if (!tcon->retry) {
cFYI(1, "gave up waiting on reconnect in smb_init");
return -EHOSTDOWN;
}
@@ -4914,7 +4911,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
__u16 fid, __u32 pid_of_opener, bool SetAllocation)
{
struct smb_com_transaction2_sfi_req *pSMB = NULL;
- char *data_offset;
struct file_end_of_file_info *parm_data;
int rc = 0;
__u16 params, param_offset, offset, byte_count, count;
@@ -4938,8 +4934,6 @@ CIFSSMBSetFileSize(const int xid, struct cifsTconInfo *tcon, __u64 size,
param_offset = offsetof(struct smb_com_transaction2_sfi_req, Fid) - 4;
offset = param_offset + params;
- data_offset = (char *) (&pSMB->hdr.Protocol) + offset;
-
count = sizeof(struct file_end_of_file_info);
pSMB->MaxParameterCount = cpu_to_le16(2);
/* BB find exact max SMB PDU from sess structure BB */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 47d8ff62368..8d6c17ab593 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -337,8 +337,13 @@ cifs_echo_request(struct work_struct *work)
struct TCP_Server_Info *server = container_of(work,
struct TCP_Server_Info, echo.work);
- /* no need to ping if we got a response recently */
- if (time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
+ /*
+ * We cannot send an echo until the NEGOTIATE_PROTOCOL request is
+ * done, which is indicated by maxBuf != 0. Also, no need to ping if
+ * we got a response recently
+ */
+ if (server->maxBuf == 0 ||
+ time_before(jiffies, server->lstrp + SMB_ECHO_INTERVAL - HZ))
goto requeue_echo;
rc = CIFSSMBEcho(server);
@@ -578,14 +583,23 @@ incomplete_rcv:
else if (reconnect == 1)
continue;
- length += 4; /* account for rfc1002 hdr */
+ total_read += 4; /* account for rfc1002 hdr */
+ dump_smb(smb_buffer, total_read);
- dump_smb(smb_buffer, length);
- if (checkSMB(smb_buffer, smb_buffer->Mid, total_read+4)) {
- cifs_dump_mem("Bad SMB: ", smb_buffer, 48);
- continue;
- }
+ /*
+ * We know that we received enough to get to the MID as we
+ * checked the pdu_length earlier. Now check to see
+ * if the rest of the header is OK. We borrow the length
+ * var for the rest of the loop to avoid a new stack var.
+ *
+ * 48 bytes is enough to display the header and a little bit
+ * into the payload for debugging purposes.
+ */
+ length = checkSMB(smb_buffer, smb_buffer->Mid, total_read);
+ if (length != 0)
+ cifs_dump_mem("Bad SMB: ", smb_buffer,
+ min_t(unsigned int, total_read, 48));
mid_entry = NULL;
server->lstrp = jiffies;
@@ -597,7 +611,8 @@ incomplete_rcv:
if ((mid_entry->mid == smb_buffer->Mid) &&
(mid_entry->midState == MID_REQUEST_SUBMITTED) &&
(mid_entry->command == smb_buffer->Command)) {
- if (check2ndT2(smb_buffer,server->maxBuf) > 0) {
+ if (length == 0 &&
+ check2ndT2(smb_buffer, server->maxBuf) > 0) {
/* We have a multipart transact2 resp */
isMultiRsp = true;
if (mid_entry->resp_buf) {
@@ -632,12 +647,17 @@ incomplete_rcv:
mid_entry->resp_buf = smb_buffer;
mid_entry->largeBuf = isLargeBuf;
multi_t2_fnd:
- mid_entry->midState = MID_RESPONSE_RECEIVED;
- list_del_init(&mid_entry->qhead);
- mid_entry->callback(mid_entry);
+ if (length == 0)
+ mid_entry->midState =
+ MID_RESPONSE_RECEIVED;
+ else
+ mid_entry->midState =
+ MID_RESPONSE_MALFORMED;
#ifdef CONFIG_CIFS_STATS2
mid_entry->when_received = jiffies;
#endif
+ list_del_init(&mid_entry->qhead);
+ mid_entry->callback(mid_entry);
break;
}
mid_entry = NULL;
@@ -653,6 +673,9 @@ multi_t2_fnd:
else
smallbuf = NULL;
}
+ } else if (length != 0) {
+ /* response sanity checks failed */
+ continue;
} else if (!is_valid_oplock_break(smb_buffer, server) &&
!isMultiRsp) {
cERROR(1, "No task to wake, unknown frame received! "
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0de17c1db60..e964b1cd5dd 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -346,7 +346,6 @@ int cifs_open(struct inode *inode, struct file *file)
struct cifsTconInfo *tcon;
struct tcon_link *tlink;
struct cifsFileInfo *pCifsFile = NULL;
- struct cifsInodeInfo *pCifsInode;
char *full_path = NULL;
bool posix_open_ok = false;
__u16 netfid;
@@ -361,8 +360,6 @@ int cifs_open(struct inode *inode, struct file *file)
}
tcon = tlink_tcon(tlink);
- pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
-
full_path = build_path_from_dentry(file->f_path.dentry);
if (full_path == NULL) {
rc = -ENOMEM;
@@ -1146,7 +1143,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
char *write_data;
int rc = -EFAULT;
int bytes_written = 0;
- struct cifs_sb_info *cifs_sb;
struct inode *inode;
struct cifsFileInfo *open_file;
@@ -1154,7 +1150,6 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
return -EFAULT;
inode = page->mapping->host;
- cifs_sb = CIFS_SB(inode->i_sb);
offset += (loff_t)from;
write_data = kmap(page);
@@ -1667,9 +1662,10 @@ static ssize_t
cifs_iovec_write(struct file *file, const struct iovec *iov,
unsigned long nr_segs, loff_t *poffset)
{
- size_t total_written = 0, written = 0;
- unsigned long num_pages, npages;
- size_t copied, len, cur_len, i;
+ unsigned int written;
+ unsigned long num_pages, npages, i;
+ size_t copied, len, cur_len;
+ ssize_t total_written = 0;
struct kvec *to_send;
struct page **pages;
struct iov_iter it;
@@ -1825,7 +1821,8 @@ cifs_iovec_read(struct file *file, const struct iovec *iov,
{
int rc;
int xid;
- unsigned int total_read, bytes_read = 0;
+ ssize_t total_read;
+ unsigned int bytes_read = 0;
size_t len, cur_len;
int iov_offset = 0;
struct cifs_sb_info *cifs_sb;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index 02cd60aefbf..e8804d37340 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -55,8 +55,9 @@ symlink_hash(unsigned int link_len, const char *link_str, u8 *md5_hash)
md5 = crypto_alloc_shash("md5", 0, 0);
if (IS_ERR(md5)) {
+ rc = PTR_ERR(md5);
cERROR(1, "%s: Crypto md5 allocation error %d\n", __func__, rc);
- return PTR_ERR(md5);
+ return rc;
}
size = sizeof(struct shash_desc) + crypto_shash_descsize(md5);
sdescmd5 = kmalloc(size, GFP_KERNEL);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index a09e077ba92..2a930a752a7 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -236,10 +236,7 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
{
__u16 mid = 0;
__u16 last_mid;
- int collision;
-
- if (server == NULL)
- return mid;
+ bool collision;
spin_lock(&GlobalMid_Lock);
last_mid = server->CurrentMid; /* we do not want to loop forever */
@@ -252,24 +249,38 @@ __u16 GetNextMid(struct TCP_Server_Info *server)
(and it would also have to have been a request that
did not time out) */
while (server->CurrentMid != last_mid) {
- struct list_head *tmp;
struct mid_q_entry *mid_entry;
+ unsigned int num_mids;
- collision = 0;
+ collision = false;
if (server->CurrentMid == 0)
server->CurrentMid++;
- list_for_each(tmp, &server->pending_mid_q) {
- mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
-
- if ((mid_entry->mid == server->CurrentMid) &&
- (mid_entry->midState == MID_REQUEST_SUBMITTED)) {
+ num_mids = 0;
+ list_for_each_entry(mid_entry, &server->pending_mid_q, qhead) {
+ ++num_mids;
+ if (mid_entry->mid == server->CurrentMid &&
+ mid_entry->midState == MID_REQUEST_SUBMITTED) {
/* This mid is in use, try a different one */
- collision = 1;
+ collision = true;
break;
}
}
- if (collision == 0) {
+
+ /*
+ * if we have more than 32k mids in the list, then something
+ * is very wrong. Possibly a local user is trying to DoS the
+ * box by issuing long-running calls and SIGKILL'ing them. If
+ * we get to 2^16 mids then we're in big trouble as this
+ * function could loop forever.
+ *
+ * Go ahead and assign out the mid in this situation, but force
+ * an eventual reconnect to clean out the pending_mid_q.
+ */
+ if (num_mids > 32768)
+ server->tcpStatus = CifsNeedReconnect;
+
+ if (!collision) {
mid = server->CurrentMid;
break;
}
@@ -381,29 +392,31 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
}
static int
-checkSMBhdr(struct smb_hdr *smb, __u16 mid)
+check_smb_hdr(struct smb_hdr *smb, __u16 mid)
{
- /* Make sure that this really is an SMB, that it is a response,
- and that the message ids match */
- if ((*(__le32 *) smb->Protocol == cpu_to_le32(0x424d53ff)) &&
- (mid == smb->Mid)) {
- if (smb->Flags & SMBFLG_RESPONSE)
- return 0;
- else {
- /* only one valid case where server sends us request */
- if (smb->Command == SMB_COM_LOCKING_ANDX)
- return 0;
- else
- cERROR(1, "Received Request not response");
- }
- } else { /* bad signature or mid */
- if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff))
- cERROR(1, "Bad protocol string signature header %x",
- *(unsigned int *) smb->Protocol);
- if (mid != smb->Mid)
- cERROR(1, "Mids do not match");
+ /* does it have the right SMB "signature" ? */
+ if (*(__le32 *) smb->Protocol != cpu_to_le32(0x424d53ff)) {
+ cERROR(1, "Bad protocol string signature header 0x%x",
+ *(unsigned int *)smb->Protocol);
+ return 1;
+ }
+
+ /* Make sure that message ids match */
+ if (mid != smb->Mid) {
+ cERROR(1, "Mids do not match. received=%u expected=%u",
+ smb->Mid, mid);
+ return 1;
}
- cERROR(1, "bad smb detected. The Mid=%d", smb->Mid);
+
+ /* if it's a response then accept */
+ if (smb->Flags & SMBFLG_RESPONSE)
+ return 0;
+
+ /* only one valid case where server sends us request */
+ if (smb->Command == SMB_COM_LOCKING_ANDX)
+ return 0;
+
+ cERROR(1, "Server sent request, not response. mid=%u", smb->Mid);
return 1;
}
@@ -448,7 +461,7 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length)
return 1;
}
- if (checkSMBhdr(smb, mid))
+ if (check_smb_hdr(smb, mid))
return 1;
clc_len = smbCalcSize_LE(smb);
@@ -465,25 +478,26 @@ checkSMB(struct smb_hdr *smb, __u16 mid, unsigned int length)
if (((4 + len) & 0xFFFF) == (clc_len & 0xFFFF))
return 0; /* bcc wrapped */
}
- cFYI(1, "Calculated size %d vs length %d mismatch for mid %d",
+ cFYI(1, "Calculated size %u vs length %u mismatch for mid=%u",
clc_len, 4 + len, smb->Mid);
- /* Windows XP can return a few bytes too much, presumably
- an illegal pad, at the end of byte range lock responses
- so we allow for that three byte pad, as long as actual
- received length is as long or longer than calculated length */
- /* We have now had to extend this more, since there is a
- case in which it needs to be bigger still to handle a
- malformed response to transact2 findfirst from WinXP when
- access denied is returned and thus bcc and wct are zero
- but server says length is 0x21 bytes too long as if the server
- forget to reset the smb rfc1001 length when it reset the
- wct and bcc to minimum size and drop the t2 parms and data */
- if ((4+len > clc_len) && (len <= clc_len + 512))
- return 0;
- else {
- cERROR(1, "RFC1001 size %d bigger than SMB for Mid=%d",
+
+ if (4 + len < clc_len) {
+ cERROR(1, "RFC1001 size %u smaller than SMB for mid=%u",
len, smb->Mid);
return 1;
+ } else if (len > clc_len + 512) {
+ /*
+ * Some servers (Windows XP in particular) send more
+ * data than the lengths in the SMB packet would
+ * indicate on certain calls (byte range locks and
+ * trans2 find first calls in particular). While the
+ * client can handle such a frame by ignoring the
+ * trailing data, we choose limit the amount of extra
+ * data to 512 bytes.
+ */
+ cERROR(1, "RFC1001 size %u more than 512 bytes larger "
+ "than SMB for mid=%u", len, smb->Mid);
+ return 1;
}
}
return 0;
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index 8d9189f6447..79f641eeda3 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -170,7 +170,7 @@ cifs_convert_address(struct sockaddr *dst, const char *src, int len)
{
int rc, alen, slen;
const char *pct;
- char *endp, scope_id[13];
+ char scope_id[13];
struct sockaddr_in *s4 = (struct sockaddr_in *) dst;
struct sockaddr_in6 *s6 = (struct sockaddr_in6 *) dst;
@@ -197,9 +197,9 @@ cifs_convert_address(struct sockaddr *dst, const char *src, int len)
memcpy(scope_id, pct + 1, slen);
scope_id[slen] = '\0';
- s6->sin6_scope_id = (u32) simple_strtoul(pct, &endp, 0);
- if (endp != scope_id + slen)
- return 0;
+ rc = strict_strtoul(scope_id, 0,
+ (unsigned long *)&s6->sin6_scope_id);
+ rc = (rc == 0) ? 1 : 0;
}
return rc;
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 7f25cc3d225..f8e4cd2a791 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -764,7 +764,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
{
int rc = 0;
int xid, i;
- struct cifs_sb_info *cifs_sb;
struct cifsTconInfo *pTcon;
struct cifsFileInfo *cifsFile = NULL;
char *current_entry;
@@ -775,8 +774,6 @@ int cifs_readdir(struct file *file, void *direntry, filldir_t filldir)
xid = GetXid();
- cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
-
/*
* Ensure FindFirst doesn't fail before doing filldir() for '.' and
* '..'. Otherwise we won't be able to notify VFS in case of failure.
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 1adc9625a34..16765703131 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -656,13 +656,13 @@ ssetup_ntlmssp_authenticate:
if (type == LANMAN) {
#ifdef CONFIG_CIFS_WEAK_PW_HASH
- char lnm_session_key[CIFS_SESS_KEY_SIZE];
+ char lnm_session_key[CIFS_AUTH_RESP_SIZE];
pSMB->req.hdr.Flags2 &= ~SMBFLG2_UNICODE;
/* no capabilities flags in old lanman negotiation */
- pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_SESS_KEY_SIZE);
+ pSMB->old_req.PasswordLength = cpu_to_le16(CIFS_AUTH_RESP_SIZE);
/* Calculate hash with password and copy into bcc_ptr.
* Encryption Key (stored as in cryptkey) gets used if the
@@ -675,8 +675,8 @@ ssetup_ntlmssp_authenticate:
true : false, lnm_session_key);
ses->flags |= CIFS_SES_LANMAN;
- memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_SESS_KEY_SIZE);
- bcc_ptr += CIFS_SESS_KEY_SIZE;
+ memcpy(bcc_ptr, (char *)lnm_session_key, CIFS_AUTH_RESP_SIZE);
+ bcc_ptr += CIFS_AUTH_RESP_SIZE;
/* can not sign if LANMAN negotiated so no need
to calculate signing key? but what if server
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index b5450e9f40c..b5041c84998 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -58,8 +58,9 @@ mdfour(unsigned char *md4_hash, unsigned char *link_str, int link_len)
md4 = crypto_alloc_shash("md4", 0, 0);
if (IS_ERR(md4)) {
+ rc = PTR_ERR(md4);
cERROR(1, "%s: Crypto md4 allocation error %d\n", __func__, rc);
- return PTR_ERR(md4);
+ return rc;
}
size = sizeof(struct shash_desc) + crypto_shash_descsize(md4);
sdescmd4 = kmalloc(size, GFP_KERNEL);
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c1ccca1a933..46d8756f2b2 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -236,9 +236,9 @@ smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
server->tcpStatus = CifsNeedReconnect;
}
- if (rc < 0) {
+ if (rc < 0 && rc != -EINTR)
cERROR(1, "Error %d sending data on socket to server", rc);
- } else
+ else
rc = 0;
/* Don't want to modify the buffer as a
@@ -359,6 +359,10 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_hdr *in_buf,
if (rc)
return rc;
+ /* enable signing if server requires it */
+ if (server->secMode & (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
+ in_buf->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
+
mutex_lock(&server->srv_mutex);
mid = AllocMidQEntry(in_buf, server);
if (mid == NULL) {
@@ -453,6 +457,9 @@ sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
case MID_RETRY_NEEDED:
rc = -EAGAIN;
break;
+ case MID_RESPONSE_MALFORMED:
+ rc = -EIO;
+ break;
default:
cERROR(1, "%s: invalid mid state mid=%d state=%d", __func__,
mid->mid, mid->midState);
@@ -570,17 +577,33 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
#endif
mutex_unlock(&ses->server->srv_mutex);
- cifs_small_buf_release(in_buf);
- if (rc < 0)
+ if (rc < 0) {
+ cifs_small_buf_release(in_buf);
goto out;
+ }
- if (long_op == CIFS_ASYNC_OP)
+ if (long_op == CIFS_ASYNC_OP) {
+ cifs_small_buf_release(in_buf);
goto out;
+ }
rc = wait_for_response(ses->server, midQ);
- if (rc != 0)
- goto out;
+ if (rc != 0) {
+ send_nt_cancel(ses->server, in_buf, midQ);
+ spin_lock(&GlobalMid_Lock);
+ if (midQ->midState == MID_REQUEST_SUBMITTED) {
+ midQ->callback = DeleteMidQEntry;
+ spin_unlock(&GlobalMid_Lock);
+ cifs_small_buf_release(in_buf);
+ atomic_dec(&ses->server->inFlight);
+ wake_up(&ses->server->request_q);
+ return rc;
+ }
+ spin_unlock(&GlobalMid_Lock);
+ }
+
+ cifs_small_buf_release(in_buf);
rc = sync_mid_result(midQ, ses->server);
if (rc != 0) {
@@ -724,8 +747,19 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
goto out;
rc = wait_for_response(ses->server, midQ);
- if (rc != 0)
- goto out;
+ if (rc != 0) {
+ send_nt_cancel(ses->server, in_buf, midQ);
+ spin_lock(&GlobalMid_Lock);
+ if (midQ->midState == MID_REQUEST_SUBMITTED) {
+ /* no longer considered to be "in-flight" */
+ midQ->callback = DeleteMidQEntry;
+ spin_unlock(&GlobalMid_Lock);
+ atomic_dec(&ses->server->inFlight);
+ wake_up(&ses->server->request_q);
+ return rc;
+ }
+ spin_unlock(&GlobalMid_Lock);
+ }
rc = sync_mid_result(midQ, ses->server);
if (rc != 0) {
@@ -922,10 +956,21 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
}
}
- if (wait_for_response(ses->server, midQ) == 0) {
- /* We got the response - restart system call. */
- rstart = 1;
+ rc = wait_for_response(ses->server, midQ);
+ if (rc) {
+ send_nt_cancel(ses->server, in_buf, midQ);
+ spin_lock(&GlobalMid_Lock);
+ if (midQ->midState == MID_REQUEST_SUBMITTED) {
+ /* no longer considered to be "in-flight" */
+ midQ->callback = DeleteMidQEntry;
+ spin_unlock(&GlobalMid_Lock);
+ return rc;
+ }
+ spin_unlock(&GlobalMid_Lock);
}
+
+ /* We got the response - restart system call. */
+ rstart = 1;
}
rc = sync_mid_result(midQ, ses->server);
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 9c64ae9e4c1..2d8c87b951c 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -1468,15 +1468,13 @@ static void work_stop(void)
static int work_start(void)
{
- recv_workqueue = alloc_workqueue("dlm_recv", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ recv_workqueue = create_singlethread_workqueue("dlm_recv");
if (!recv_workqueue) {
log_print("can't start dlm_recv");
return -ENOMEM;
}
- send_workqueue = alloc_workqueue("dlm_send", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ send_workqueue = create_singlethread_workqueue("dlm_send");
if (!send_workqueue) {
log_print("can't start dlm_send");
destroy_workqueue(recv_workqueue);
diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c
index 6fc4f319b55..534c1d46e69 100644
--- a/fs/ecryptfs/dentry.c
+++ b/fs/ecryptfs/dentry.c
@@ -46,24 +46,28 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
{
struct dentry *lower_dentry;
struct vfsmount *lower_mnt;
- struct dentry *dentry_save;
- struct vfsmount *vfsmount_save;
+ struct dentry *dentry_save = NULL;
+ struct vfsmount *vfsmount_save = NULL;
int rc = 1;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
lower_dentry = ecryptfs_dentry_to_lower(dentry);
lower_mnt = ecryptfs_dentry_to_lower_mnt(dentry);
if (!lower_dentry->d_op || !lower_dentry->d_op->d_revalidate)
goto out;
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
+ if (nd) {
+ dentry_save = nd->path.dentry;
+ vfsmount_save = nd->path.mnt;
+ nd->path.dentry = lower_dentry;
+ nd->path.mnt = lower_mnt;
+ }
rc = lower_dentry->d_op->d_revalidate(lower_dentry, nd);
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
+ if (nd) {
+ nd->path.dentry = dentry_save;
+ nd->path.mnt = vfsmount_save;
+ }
if (dentry->d_inode) {
struct inode *lower_inode =
ecryptfs_inode_to_lower(dentry->d_inode);
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index dbc84ed9633..e00753496e3 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -632,8 +632,7 @@ int ecryptfs_interpose(struct dentry *hidden_dentry,
u32 flags);
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct inode *ecryptfs_dir_inode,
- struct nameidata *ecryptfs_nd);
+ struct inode *ecryptfs_dir_inode);
int ecryptfs_decode_and_decrypt_filename(char **decrypted_name,
size_t *decrypted_name_size,
struct dentry *ecryptfs_dentry,
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 81e10e6a944..7d1050e254f 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -317,6 +317,7 @@ ecryptfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
const struct file_operations ecryptfs_dir_fops = {
.readdir = ecryptfs_readdir,
+ .read = generic_read_dir,
.unlocked_ioctl = ecryptfs_unlocked_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = ecryptfs_compat_ioctl,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index bd33f87a190..b592938a84b 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -74,16 +74,20 @@ ecryptfs_create_underlying_file(struct inode *lower_dir_inode,
unsigned int flags_save;
int rc;
- dentry_save = nd->path.dentry;
- vfsmount_save = nd->path.mnt;
- flags_save = nd->flags;
- nd->path.dentry = lower_dentry;
- nd->path.mnt = lower_mnt;
- nd->flags &= ~LOOKUP_OPEN;
+ if (nd) {
+ dentry_save = nd->path.dentry;
+ vfsmount_save = nd->path.mnt;
+ flags_save = nd->flags;
+ nd->path.dentry = lower_dentry;
+ nd->path.mnt = lower_mnt;
+ nd->flags &= ~LOOKUP_OPEN;
+ }
rc = vfs_create(lower_dir_inode, lower_dentry, mode, nd);
- nd->path.dentry = dentry_save;
- nd->path.mnt = vfsmount_save;
- nd->flags = flags_save;
+ if (nd) {
+ nd->path.dentry = dentry_save;
+ nd->path.mnt = vfsmount_save;
+ nd->flags = flags_save;
+ }
return rc;
}
@@ -241,8 +245,7 @@ out:
*/
int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
struct dentry *lower_dentry,
- struct inode *ecryptfs_dir_inode,
- struct nameidata *ecryptfs_nd)
+ struct inode *ecryptfs_dir_inode)
{
struct dentry *lower_dir_dentry;
struct vfsmount *lower_mnt;
@@ -290,8 +293,6 @@ int ecryptfs_lookup_and_interpose_lower(struct dentry *ecryptfs_dentry,
goto out;
if (special_file(lower_inode->i_mode))
goto out;
- if (!ecryptfs_nd)
- goto out;
/* Released in this function */
page_virt = kmem_cache_zalloc(ecryptfs_header_cache_2, GFP_USER);
if (!page_virt) {
@@ -349,75 +350,6 @@ out:
}
/**
- * ecryptfs_new_lower_dentry
- * @name: The name of the new dentry.
- * @lower_dir_dentry: Parent directory of the new dentry.
- * @nd: nameidata from last lookup.
- *
- * Create a new dentry or get it from lower parent dir.
- */
-static struct dentry *
-ecryptfs_new_lower_dentry(struct qstr *name, struct dentry *lower_dir_dentry,
- struct nameidata *nd)
-{
- struct dentry *new_dentry;
- struct dentry *tmp;
- struct inode *lower_dir_inode;
-
- lower_dir_inode = lower_dir_dentry->d_inode;
-
- tmp = d_alloc(lower_dir_dentry, name);
- if (!tmp)
- return ERR_PTR(-ENOMEM);
-
- mutex_lock(&lower_dir_inode->i_mutex);
- new_dentry = lower_dir_inode->i_op->lookup(lower_dir_inode, tmp, nd);
- mutex_unlock(&lower_dir_inode->i_mutex);
-
- if (!new_dentry)
- new_dentry = tmp;
- else
- dput(tmp);
-
- return new_dentry;
-}
-
-
-/**
- * ecryptfs_lookup_one_lower
- * @ecryptfs_dentry: The eCryptfs dentry that we are looking up
- * @lower_dir_dentry: lower parent directory
- * @name: lower file name
- *
- * Get the lower dentry from vfs. If lower dentry does not exist yet,
- * create it.
- */
-static struct dentry *
-ecryptfs_lookup_one_lower(struct dentry *ecryptfs_dentry,
- struct dentry *lower_dir_dentry, struct qstr *name)
-{
- struct nameidata nd;
- struct vfsmount *lower_mnt;
- int err;
-
- lower_mnt = mntget(ecryptfs_dentry_to_lower_mnt(
- ecryptfs_dentry->d_parent));
- err = vfs_path_lookup(lower_dir_dentry, lower_mnt, name->name , 0, &nd);
- mntput(lower_mnt);
-
- if (!err) {
- /* we dont need the mount */
- mntput(nd.path.mnt);
- return nd.path.dentry;
- }
- if (err != -ENOENT)
- return ERR_PTR(err);
-
- /* create a new lower dentry */
- return ecryptfs_new_lower_dentry(name, lower_dir_dentry, &nd);
-}
-
-/**
* ecryptfs_lookup
* @ecryptfs_dir_inode: The eCryptfs directory inode
* @ecryptfs_dentry: The eCryptfs dentry that we are looking up
@@ -434,7 +366,6 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
size_t encrypted_and_encoded_name_size;
struct ecryptfs_mount_crypt_stat *mount_crypt_stat = NULL;
struct dentry *lower_dir_dentry, *lower_dentry;
- struct qstr lower_name;
int rc = 0;
if ((ecryptfs_dentry->d_name.len == 1
@@ -444,20 +375,14 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
goto out_d_drop;
}
lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent);
- lower_name.name = ecryptfs_dentry->d_name.name;
- lower_name.len = ecryptfs_dentry->d_name.len;
- lower_name.hash = ecryptfs_dentry->d_name.hash;
- if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
- rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
- lower_dir_dentry->d_inode, &lower_name);
- if (rc < 0)
- goto out_d_drop;
- }
- lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry,
- lower_dir_dentry, &lower_name);
+ mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name,
+ lower_dir_dentry,
+ ecryptfs_dentry->d_name.len);
+ mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned "
+ ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
"[%d] on lower_dentry = [%s]\n", __func__, rc,
encrypted_and_encoded_name);
goto out_d_drop;
@@ -479,28 +404,21 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode,
"filename; rc = [%d]\n", __func__, rc);
goto out_d_drop;
}
- lower_name.name = encrypted_and_encoded_name;
- lower_name.len = encrypted_and_encoded_name_size;
- lower_name.hash = full_name_hash(lower_name.name, lower_name.len);
- if (lower_dir_dentry->d_op && lower_dir_dentry->d_op->d_hash) {
- rc = lower_dir_dentry->d_op->d_hash(lower_dir_dentry,
- lower_dir_dentry->d_inode, &lower_name);
- if (rc < 0)
- goto out_d_drop;
- }
- lower_dentry = ecryptfs_lookup_one_lower(ecryptfs_dentry,
- lower_dir_dentry, &lower_name);
+ mutex_lock(&lower_dir_dentry->d_inode->i_mutex);
+ lower_dentry = lookup_one_len(encrypted_and_encoded_name,
+ lower_dir_dentry,
+ encrypted_and_encoded_name_size);
+ mutex_unlock(&lower_dir_dentry->d_inode->i_mutex);
if (IS_ERR(lower_dentry)) {
rc = PTR_ERR(lower_dentry);
- ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_lower() returned "
+ ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned "
"[%d] on lower_dentry = [%s]\n", __func__, rc,
encrypted_and_encoded_name);
goto out_d_drop;
}
lookup_and_interpose:
rc = ecryptfs_lookup_and_interpose_lower(ecryptfs_dentry, lower_dentry,
- ecryptfs_dir_inode,
- ecryptfs_nd);
+ ecryptfs_dir_inode);
goto out;
out_d_drop:
d_drop(ecryptfs_dentry);
@@ -1092,6 +1010,8 @@ int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
rc = vfs_getattr(ecryptfs_dentry_to_lower_mnt(dentry),
ecryptfs_dentry_to_lower(dentry), &lower_stat);
if (!rc) {
+ fsstack_copy_attr_all(dentry->d_inode,
+ ecryptfs_inode_to_lower(dentry->d_inode));
generic_fillattr(dentry->d_inode, stat);
stat->blocks = lower_stat.blocks;
}
diff --git a/fs/eventfd.c b/fs/eventfd.c
index e0194b3e14d..d9a59177391 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -99,7 +99,7 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_get);
* @ctx: [in] Pointer to eventfd context.
*
* The eventfd context reference must have been previously acquired either
- * with eventfd_ctx_get() or eventfd_ctx_fdget()).
+ * with eventfd_ctx_get() or eventfd_ctx_fdget().
*/
void eventfd_ctx_put(struct eventfd_ctx *ctx)
{
@@ -146,9 +146,9 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
* eventfd_ctx_remove_wait_queue - Read the current counter and removes wait queue.
* @ctx: [in] Pointer to eventfd context.
* @wait: [in] Wait queue to be removed.
- * @cnt: [out] Pointer to the 64bit conter value.
+ * @cnt: [out] Pointer to the 64-bit counter value.
*
- * Returns zero if successful, or the following error codes:
+ * Returns %0 if successful, or the following error codes:
*
* -EAGAIN : The operation would have blocked.
*
@@ -175,11 +175,11 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
* eventfd_ctx_read - Reads the eventfd counter or wait if it is zero.
* @ctx: [in] Pointer to eventfd context.
* @no_wait: [in] Different from zero if the operation should not block.
- * @cnt: [out] Pointer to the 64bit conter value.
+ * @cnt: [out] Pointer to the 64-bit counter value.
*
- * Returns zero if successful, or the following error codes:
+ * Returns %0 if successful, or the following error codes:
*
- * -EAGAIN : The operation would have blocked but @no_wait was nonzero.
+ * -EAGAIN : The operation would have blocked but @no_wait was non-zero.
* -ERESTARTSYS : A signal interrupted the wait operation.
*
* If @no_wait is zero, the function might sleep until the eventfd internal
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index cc8a9b7d606..267d0ada454 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1114,6 +1114,17 @@ static int ep_send_events(struct eventpoll *ep,
return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
}
+static inline struct timespec ep_set_mstimeout(long ms)
+{
+ struct timespec now, ts = {
+ .tv_sec = ms / MSEC_PER_SEC,
+ .tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC),
+ };
+
+ ktime_get_ts(&now);
+ return timespec_add_safe(now, ts);
+}
+
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
int maxevents, long timeout)
{
@@ -1121,12 +1132,11 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
unsigned long flags;
long slack;
wait_queue_t wait;
- struct timespec end_time;
ktime_t expires, *to = NULL;
if (timeout > 0) {
- ktime_get_ts(&end_time);
- timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
+ struct timespec end_time = ep_set_mstimeout(timeout);
+
slack = select_estimate_accuracy(&end_time);
to = &expires;
*to = timespec_to_ktime(end_time);
diff --git a/fs/exec.c b/fs/exec.c
index c62efcb959c..52a447d9b6a 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -120,7 +120,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library)
goto out;
file = do_filp_open(AT_FDCWD, tmp,
- O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+ O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
MAY_READ | MAY_EXEC | MAY_OPEN);
putname(tmp);
error = PTR_ERR(file);
@@ -723,7 +723,7 @@ struct file *open_exec(const char *name)
int err;
file = do_filp_open(AT_FDCWD, name,
- O_LARGEFILE | O_RDONLY | FMODE_EXEC, 0,
+ O_LARGEFILE | O_RDONLY | __FMODE_EXEC, 0,
MAY_EXEC | MAY_OPEN);
if (IS_ERR(file))
goto out;
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 42685424817..a7555238c41 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -1030,7 +1030,6 @@ struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
}
- inode->i_mapping->backing_dev_info = sb->s_bdi;
if (S_ISREG(inode->i_mode)) {
inode->i_op = &exofs_file_inode_operations;
inode->i_fop = &exofs_file_operations;
@@ -1131,7 +1130,6 @@ struct inode *exofs_new_inode(struct inode *dir, int mode)
sbi = sb->s_fs_info;
- inode->i_mapping->backing_dev_info = sb->s_bdi;
sb->s_dirt = 1;
inode_init_owner(inode, dir, mode);
inode->i_ino = sbi->s_nextid++;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0c8d97b56f3..3aa0b72b3b9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -848,6 +848,7 @@ struct ext4_inode_info {
atomic_t i_ioend_count; /* Number of outstanding io_end structs */
/* current io_end structure for async DIO write*/
ext4_io_end_t *cur_aio_dio;
+ atomic_t i_aiodio_unwritten; /* Nr. of inflight conversions pending */
spinlock_t i_block_reservation_lock;
@@ -2119,6 +2120,15 @@ static inline void set_bitmap_uptodate(struct buffer_head *bh)
#define in_range(b, first, len) ((b) >= (first) && (b) <= (first) + (len) - 1)
+/* For ioend & aio unwritten conversion wait queues */
+#define EXT4_WQ_HASH_SZ 37
+#define ext4_ioend_wq(v) (&ext4__ioend_wq[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+#define ext4_aio_mutex(v) (&ext4__aio_mutex[((unsigned long)(v)) %\
+ EXT4_WQ_HASH_SZ])
+extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+extern struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 63a75810b7c..ccce8a7e94e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3174,9 +3174,10 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
* that this IO needs to convertion to written when IO is
* completed
*/
- if (io)
+ if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
io->flag = EXT4_IO_END_UNWRITTEN;
- else
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ } else
ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
if (ext4_should_dioread_nolock(inode))
map->m_flags |= EXT4_MAP_UNINIT;
@@ -3463,9 +3464,10 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* that we need to perform convertion when IO is done.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO)) {
- if (io)
+ if (io && !(io->flag & EXT4_IO_END_UNWRITTEN)) {
io->flag = EXT4_IO_END_UNWRITTEN;
- else
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ } else
ext4_set_inode_state(inode,
EXT4_STATE_DIO_UNWRITTEN);
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 2e8322c8aa8..7b80d543b89 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -55,11 +55,47 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
return 0;
}
+static void ext4_aiodio_wait(struct inode *inode)
+{
+ wait_queue_head_t *wq = ext4_ioend_wq(inode);
+
+ wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
+}
+
+/*
+ * This tests whether the IO in question is block-aligned or not.
+ * Ext4 utilizes unwritten extents when hole-filling during direct IO, and they
+ * are converted to written only after the IO is complete. Until they are
+ * mapped, these blocks appear as holes, so dio_zero_block() will assume that
+ * it needs to zero out portions of the start and/or end block. If 2 AIO
+ * threads are at work on the same unwritten block, they must be synchronized
+ * or one thread will zero the other's data, causing corruption.
+ */
+static int
+ext4_unaligned_aio(struct inode *inode, const struct iovec *iov,
+ unsigned long nr_segs, loff_t pos)
+{
+ struct super_block *sb = inode->i_sb;
+ int blockmask = sb->s_blocksize - 1;
+ size_t count = iov_length(iov, nr_segs);
+ loff_t final_size = pos + count;
+
+ if (pos >= inode->i_size)
+ return 0;
+
+ if ((pos & blockmask) || (final_size & blockmask))
+ return 1;
+
+ return 0;
+}
+
static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
+ int unaligned_aio = 0;
+ int ret;
/*
* If we have encountered a bitmap-format file, the size limit
@@ -78,9 +114,31 @@ ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
nr_segs = iov_shorten((struct iovec *)iov, nr_segs,
sbi->s_bitmap_maxbytes - pos);
}
+ } else if (unlikely((iocb->ki_filp->f_flags & O_DIRECT) &&
+ !is_sync_kiocb(iocb))) {
+ unaligned_aio = ext4_unaligned_aio(inode, iov, nr_segs, pos);
}
- return generic_file_aio_write(iocb, iov, nr_segs, pos);
+ /* Unaligned direct AIO must be serialized; see comment above */
+ if (unaligned_aio) {
+ static unsigned long unaligned_warn_time;
+
+ /* Warn about this once per day */
+ if (printk_timed_ratelimit(&unaligned_warn_time, 60*60*24*HZ))
+ ext4_msg(inode->i_sb, KERN_WARNING,
+ "Unaligned AIO/DIO on inode %ld by %s; "
+ "performance will be poor.",
+ inode->i_ino, current->comm);
+ mutex_lock(ext4_aio_mutex(inode));
+ ext4_aiodio_wait(inode);
+ }
+
+ ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
+
+ if (unaligned_aio)
+ mutex_unlock(ext4_aio_mutex(inode));
+
+ return ret;
}
static const struct vm_operations_struct ext4_file_vm_ops = {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 851f49b2f9d..d1fe09aea73 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -342,10 +342,15 @@ static struct kmem_cache *ext4_free_ext_cachep;
/* We create slab caches for groupinfo data structures based on the
* superblock block size. There will be one per mounted filesystem for
* each unique s_blocksize_bits */
-#define NR_GRPINFO_CACHES \
- (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE + 1)
+#define NR_GRPINFO_CACHES 8
static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
+static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+ "ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
+ "ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
+ "ext4_groupinfo_64k", "ext4_groupinfo_128k"
+};
+
static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
@@ -2414,6 +2419,55 @@ err_freesgi:
return -ENOMEM;
}
+static void ext4_groupinfo_destroy_slabs(void)
+{
+ int i;
+
+ for (i = 0; i < NR_GRPINFO_CACHES; i++) {
+ if (ext4_groupinfo_caches[i])
+ kmem_cache_destroy(ext4_groupinfo_caches[i]);
+ ext4_groupinfo_caches[i] = NULL;
+ }
+}
+
+static int ext4_groupinfo_create_slab(size_t size)
+{
+ static DEFINE_MUTEX(ext4_grpinfo_slab_create_mutex);
+ int slab_size;
+ int blocksize_bits = order_base_2(size);
+ int cache_index = blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
+ struct kmem_cache *cachep;
+
+ if (cache_index >= NR_GRPINFO_CACHES)
+ return -EINVAL;
+
+ if (unlikely(cache_index < 0))
+ cache_index = 0;
+
+ mutex_lock(&ext4_grpinfo_slab_create_mutex);
+ if (ext4_groupinfo_caches[cache_index]) {
+ mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+ return 0; /* Already created */
+ }
+
+ slab_size = offsetof(struct ext4_group_info,
+ bb_counters[blocksize_bits + 2]);
+
+ cachep = kmem_cache_create(ext4_groupinfo_slab_names[cache_index],
+ slab_size, 0, SLAB_RECLAIM_ACCOUNT,
+ NULL);
+
+ mutex_unlock(&ext4_grpinfo_slab_create_mutex);
+ if (!cachep) {
+ printk(KERN_EMERG "EXT4: no memory for groupinfo slab cache\n");
+ return -ENOMEM;
+ }
+
+ ext4_groupinfo_caches[cache_index] = cachep;
+
+ return 0;
+}
+
int ext4_mb_init(struct super_block *sb, int needs_recovery)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -2421,9 +2475,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
unsigned offset;
unsigned max;
int ret;
- int cache_index;
- struct kmem_cache *cachep;
- char *namep = NULL;
i = (sb->s_blocksize_bits + 2) * sizeof(*sbi->s_mb_offsets);
@@ -2440,30 +2491,9 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
goto out;
}
- cache_index = sb->s_blocksize_bits - EXT4_MIN_BLOCK_LOG_SIZE;
- cachep = ext4_groupinfo_caches[cache_index];
- if (!cachep) {
- char name[32];
- int len = offsetof(struct ext4_group_info,
- bb_counters[sb->s_blocksize_bits + 2]);
-
- sprintf(name, "ext4_groupinfo_%d", sb->s_blocksize_bits);
- namep = kstrdup(name, GFP_KERNEL);
- if (!namep) {
- ret = -ENOMEM;
- goto out;
- }
-
- /* Need to free the kmem_cache_name() when we
- * destroy the slab */
- cachep = kmem_cache_create(namep, len, 0,
- SLAB_RECLAIM_ACCOUNT, NULL);
- if (!cachep) {
- ret = -ENOMEM;
- goto out;
- }
- ext4_groupinfo_caches[cache_index] = cachep;
- }
+ ret = ext4_groupinfo_create_slab(sb->s_blocksize);
+ if (ret < 0)
+ goto out;
/* order 0 is regular bitmap */
sbi->s_mb_maxs[0] = sb->s_blocksize << 3;
@@ -2520,7 +2550,6 @@ out:
if (ret) {
kfree(sbi->s_mb_offsets);
kfree(sbi->s_mb_maxs);
- kfree(namep);
}
return ret;
}
@@ -2734,7 +2763,6 @@ int __init ext4_init_mballoc(void)
void ext4_exit_mballoc(void)
{
- int i;
/*
* Wait for completion of call_rcu()'s on ext4_pspace_cachep
* before destroying the slab cache.
@@ -2743,15 +2771,7 @@ void ext4_exit_mballoc(void)
kmem_cache_destroy(ext4_pspace_cachep);
kmem_cache_destroy(ext4_ac_cachep);
kmem_cache_destroy(ext4_free_ext_cachep);
-
- for (i = 0; i < NR_GRPINFO_CACHES; i++) {
- struct kmem_cache *cachep = ext4_groupinfo_caches[i];
- if (cachep) {
- char *name = (char *)kmem_cache_name(cachep);
- kmem_cache_destroy(cachep);
- kfree(name);
- }
- }
+ ext4_groupinfo_destroy_slabs();
ext4_remove_debugfs_entry();
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7270dcfca92..955cc309142 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -32,14 +32,8 @@
static struct kmem_cache *io_page_cachep, *io_end_cachep;
-#define WQ_HASH_SZ 37
-#define to_ioend_wq(v) (&ioend_wq[((unsigned long)v) % WQ_HASH_SZ])
-static wait_queue_head_t ioend_wq[WQ_HASH_SZ];
-
int __init ext4_init_pageio(void)
{
- int i;
-
io_page_cachep = KMEM_CACHE(ext4_io_page, SLAB_RECLAIM_ACCOUNT);
if (io_page_cachep == NULL)
return -ENOMEM;
@@ -48,9 +42,6 @@ int __init ext4_init_pageio(void)
kmem_cache_destroy(io_page_cachep);
return -ENOMEM;
}
- for (i = 0; i < WQ_HASH_SZ; i++)
- init_waitqueue_head(&ioend_wq[i]);
-
return 0;
}
@@ -62,7 +53,7 @@ void ext4_exit_pageio(void)
void ext4_ioend_wait(struct inode *inode)
{
- wait_queue_head_t *wq = to_ioend_wq(inode);
+ wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_ioend_count) == 0));
}
@@ -87,7 +78,7 @@ void ext4_free_io_end(ext4_io_end_t *io)
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
- wq = to_ioend_wq(io->inode);
+ wq = ext4_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
waitqueue_active(wq))
wake_up_all(wq);
@@ -102,6 +93,7 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
+ wait_queue_head_t *wq;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
@@ -126,7 +118,16 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
/* clear the DIO AIO unwritten flag */
- io->flag &= ~EXT4_IO_END_UNWRITTEN;
+ if (io->flag & EXT4_IO_END_UNWRITTEN) {
+ io->flag &= ~EXT4_IO_END_UNWRITTEN;
+ /* Wake up anyone waiting on unwritten extent conversion */
+ wq = ext4_ioend_wq(io->inode);
+ if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
+ waitqueue_active(wq)) {
+ wake_up_all(wq);
+ }
+ }
+
return ret;
}
@@ -190,6 +191,7 @@ static void ext4_end_bio(struct bio *bio, int error)
struct inode *inode;
unsigned long flags;
int i;
+ sector_t bi_sector = bio->bi_sector;
BUG_ON(!io_end);
bio->bi_private = NULL;
@@ -207,9 +209,7 @@ static void ext4_end_bio(struct bio *bio, int error)
if (error)
SetPageError(page);
BUG_ON(!head);
- if (head->b_size == PAGE_CACHE_SIZE)
- clear_buffer_dirty(head);
- else {
+ if (head->b_size != PAGE_CACHE_SIZE) {
loff_t offset;
loff_t io_end_offset = io_end->offset + io_end->size;
@@ -221,7 +221,6 @@ static void ext4_end_bio(struct bio *bio, int error)
if (error)
buffer_io_error(bh);
- clear_buffer_dirty(bh);
}
if (buffer_delay(bh))
partial_write = 1;
@@ -257,7 +256,7 @@ static void ext4_end_bio(struct bio *bio, int error)
(unsigned long long) io_end->offset,
(long) io_end->size,
(unsigned long long)
- bio->bi_sector >> (inode->i_blkbits - 9));
+ bi_sector >> (inode->i_blkbits - 9));
}
/* Add the io_end to per-inode completed io list*/
@@ -380,6 +379,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
blocksize = 1 << inode->i_blkbits;
+ BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
set_page_writeback(page);
ClearPageError(page);
@@ -397,12 +397,14 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
for (bh = head = page_buffers(page), block_start = 0;
bh != head || !block_start;
block_start = block_end, bh = bh->b_this_page) {
+
block_end = block_start + blocksize;
if (block_start >= len) {
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
continue;
}
+ clear_buffer_dirty(bh);
ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
if (ret) {
/*
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 48ce561fafa..f6a318f836b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -77,6 +77,7 @@ static struct dentry *ext4_mount(struct file_system_type *fs_type, int flags,
const char *dev_name, void *data);
static void ext4_destroy_lazyinit_thread(void);
static void ext4_unregister_li_request(struct super_block *sb);
+static void ext4_clear_request_list(void);
#if !defined(CONFIG_EXT3_FS) && !defined(CONFIG_EXT3_FS_MODULE) && defined(CONFIG_EXT4_USE_FOR_EXT23)
static struct file_system_type ext3_fs_type = {
@@ -832,6 +833,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
ei->i_sync_tid = 0;
ei->i_datasync_tid = 0;
atomic_set(&ei->i_ioend_count, 0);
+ atomic_set(&ei->i_aiodio_unwritten, 0);
return &ei->vfs_inode;
}
@@ -2716,6 +2718,8 @@ static void ext4_unregister_li_request(struct super_block *sb)
mutex_unlock(&ext4_li_info->li_list_mtx);
}
+static struct task_struct *ext4_lazyinit_task;
+
/*
* This is the function where ext4lazyinit thread lives. It walks
* through the request list searching for next scheduled filesystem.
@@ -2784,6 +2788,10 @@ cont_thread:
if (time_before(jiffies, next_wakeup))
schedule();
finish_wait(&eli->li_wait_daemon, &wait);
+ if (kthread_should_stop()) {
+ ext4_clear_request_list();
+ goto exit_thread;
+ }
}
exit_thread:
@@ -2808,6 +2816,7 @@ exit_thread:
wake_up(&eli->li_wait_task);
kfree(ext4_li_info);
+ ext4_lazyinit_task = NULL;
ext4_li_info = NULL;
mutex_unlock(&ext4_li_mtx);
@@ -2830,11 +2839,10 @@ static void ext4_clear_request_list(void)
static int ext4_run_lazyinit_thread(void)
{
- struct task_struct *t;
-
- t = kthread_run(ext4_lazyinit_thread, ext4_li_info, "ext4lazyinit");
- if (IS_ERR(t)) {
- int err = PTR_ERR(t);
+ ext4_lazyinit_task = kthread_run(ext4_lazyinit_thread,
+ ext4_li_info, "ext4lazyinit");
+ if (IS_ERR(ext4_lazyinit_task)) {
+ int err = PTR_ERR(ext4_lazyinit_task);
ext4_clear_request_list();
del_timer_sync(&ext4_li_info->li_timer);
kfree(ext4_li_info);
@@ -2985,16 +2993,10 @@ static void ext4_destroy_lazyinit_thread(void)
* If thread exited earlier
* there's nothing to be done.
*/
- if (!ext4_li_info)
+ if (!ext4_li_info || !ext4_lazyinit_task)
return;
- ext4_clear_request_list();
-
- while (ext4_li_info->li_task) {
- wake_up(&ext4_li_info->li_wait_daemon);
- wait_event(ext4_li_info->li_wait_task,
- ext4_li_info->li_task == NULL);
- }
+ kthread_stop(ext4_lazyinit_task);
}
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
@@ -4768,7 +4770,7 @@ static struct file_system_type ext4_fs_type = {
.fs_flags = FS_REQUIRES_DEV,
};
-int __init ext4_init_feat_adverts(void)
+static int __init ext4_init_feat_adverts(void)
{
struct ext4_features *ef;
int ret = -ENOMEM;
@@ -4792,23 +4794,44 @@ out:
return ret;
}
+static void ext4_exit_feat_adverts(void)
+{
+ kobject_put(&ext4_feat->f_kobj);
+ wait_for_completion(&ext4_feat->f_kobj_unregister);
+ kfree(ext4_feat);
+}
+
+/* Shared across all ext4 file systems */
+wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
+struct mutex ext4__aio_mutex[EXT4_WQ_HASH_SZ];
+
static int __init ext4_init_fs(void)
{
- int err;
+ int i, err;
ext4_check_flag_values();
+
+ for (i = 0; i < EXT4_WQ_HASH_SZ; i++) {
+ mutex_init(&ext4__aio_mutex[i]);
+ init_waitqueue_head(&ext4__ioend_wq[i]);
+ }
+
err = ext4_init_pageio();
if (err)
return err;
err = ext4_init_system_zone();
if (err)
- goto out5;
+ goto out7;
ext4_kset = kset_create_and_add("ext4", NULL, fs_kobj);
if (!ext4_kset)
- goto out4;
+ goto out6;
ext4_proc_root = proc_mkdir("fs/ext4", NULL);
+ if (!ext4_proc_root)
+ goto out5;
err = ext4_init_feat_adverts();
+ if (err)
+ goto out4;
err = ext4_init_mballoc();
if (err)
@@ -4838,12 +4861,14 @@ out1:
out2:
ext4_exit_mballoc();
out3:
- kfree(ext4_feat);
+ ext4_exit_feat_adverts();
+out4:
remove_proc_entry("fs/ext4", NULL);
+out5:
kset_unregister(ext4_kset);
-out4:
+out6:
ext4_exit_system_zone();
-out5:
+out7:
ext4_exit_pageio();
return err;
}
@@ -4857,6 +4882,7 @@ static void __exit ext4_exit_fs(void)
destroy_inodecache();
ext4_exit_xattr();
ext4_exit_mballoc();
+ ext4_exit_feat_adverts();
remove_proc_entry("fs/ext4", NULL);
kset_unregister(ext4_kset);
ext4_exit_system_zone();
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ecc8b3954ed..cb1026181bd 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -815,7 +815,7 @@ static int __init fcntl_init(void)
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- FMODE_EXEC
+ __FMODE_EXEC
));
fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/file_table.c b/fs/file_table.c
index c3e89adf53c..eb36b6b17e2 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -125,13 +125,13 @@ struct file *get_empty_filp(void)
goto fail;
percpu_counter_inc(&nr_files);
+ f->f_cred = get_cred(cred);
if (security_file_alloc(f))
goto fail_sec;
INIT_LIST_HEAD(&f->f_u.fu_list);
atomic_long_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
- f->f_cred = get_cred(cred);
spin_lock_init(&f->f_lock);
eventpoll_init_file(f);
/* f->f_version: 0 */
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 08a8beb152e..7cd9a5a68d5 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1779,11 +1779,11 @@ int __init gfs2_glock_init(void)
#endif
glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ WQ_HIGHPRI | WQ_FREEZABLE, 0);
if (IS_ERR(glock_workqueue))
return PTR_ERR(glock_workqueue);
gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+ WQ_MEM_RECLAIM | WQ_FREEZABLE,
0);
if (IS_ERR(gfs2_delete_workqueue)) {
destroy_workqueue(glock_workqueue);
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index ebef7ab6e17..85ba027d1c4 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -144,7 +144,7 @@ static int __init init_gfs2_fs(void)
error = -ENOMEM;
gfs_recovery_wq = alloc_workqueue("gfs_recovery",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0);
+ WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
if (!gfs_recovery_wq)
goto fail_wq;
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 52a0bcaa7b6..b1991a2a08e 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -397,8 +397,8 @@ int hfsplus_file_extend(struct inode *inode)
u32 start, len, goal;
int res;
- if (sbi->total_blocks - sbi->free_blocks + 8 >
- sbi->alloc_file->i_size * 8) {
+ if (sbi->alloc_file->i_size * 8 <
+ sbi->total_blocks - sbi->free_blocks + 8) {
/* extend alloc file */
printk(KERN_ERR "hfs: extend alloc file! "
"(%llu,%u,%u)\n",
diff --git a/fs/hfsplus/part_tbl.c b/fs/hfsplus/part_tbl.c
index d66ad113b1c..40ad88c12c6 100644
--- a/fs/hfsplus/part_tbl.c
+++ b/fs/hfsplus/part_tbl.c
@@ -134,7 +134,7 @@ int hfs_part_find(struct super_block *sb,
res = hfsplus_submit_bio(sb->s_bdev, *part_start + HFS_PMAP_BLK,
data, READ);
if (res)
- return res;
+ goto out;
switch (be16_to_cpu(*((__be16 *)data))) {
case HFS_OLD_PMAP_MAGIC:
@@ -147,7 +147,7 @@ int hfs_part_find(struct super_block *sb,
res = -ENOENT;
break;
}
-
+out:
kfree(data);
return res;
}
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 9a3b4795f43..b49b55584c8 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -338,20 +338,22 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
struct inode *root, *inode;
struct qstr str;
struct nls_table *nls = NULL;
- int err = -EINVAL;
+ int err;
+ err = -EINVAL;
sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
if (!sbi)
- return -ENOMEM;
+ goto out;
sb->s_fs_info = sbi;
mutex_init(&sbi->alloc_mutex);
mutex_init(&sbi->vh_mutex);
hfsplus_fill_defaults(sbi);
+
+ err = -EINVAL;
if (!hfsplus_parse_options(data, sbi)) {
printk(KERN_ERR "hfs: unable to parse mount options\n");
- err = -EINVAL;
- goto cleanup;
+ goto out_unload_nls;
}
/* temporarily use utf8 to correctly find the hidden dir below */
@@ -359,16 +361,14 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
sbi->nls = load_nls("utf8");
if (!sbi->nls) {
printk(KERN_ERR "hfs: unable to load nls for utf8\n");
- err = -EINVAL;
- goto cleanup;
+ goto out_unload_nls;
}
/* Grab the volume header */
if (hfsplus_read_wrapper(sb)) {
if (!silent)
printk(KERN_WARNING "hfs: unable to find HFS+ superblock\n");
- err = -EINVAL;
- goto cleanup;
+ goto out_unload_nls;
}
vhdr = sbi->s_vhdr;
@@ -377,7 +377,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
if (be16_to_cpu(vhdr->version) < HFSPLUS_MIN_VERSION ||
be16_to_cpu(vhdr->version) > HFSPLUS_CURRENT_VERSION) {
printk(KERN_ERR "hfs: wrong filesystem version\n");
- goto cleanup;
+ goto out_free_vhdr;
}
sbi->total_blocks = be32_to_cpu(vhdr->total_blocks);
sbi->free_blocks = be32_to_cpu(vhdr->free_blocks);
@@ -421,19 +421,19 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
sbi->ext_tree = hfs_btree_open(sb, HFSPLUS_EXT_CNID);
if (!sbi->ext_tree) {
printk(KERN_ERR "hfs: failed to load extents file\n");
- goto cleanup;
+ goto out_free_vhdr;
}
sbi->cat_tree = hfs_btree_open(sb, HFSPLUS_CAT_CNID);
if (!sbi->cat_tree) {
printk(KERN_ERR "hfs: failed to load catalog file\n");
- goto cleanup;
+ goto out_close_ext_tree;
}
inode = hfsplus_iget(sb, HFSPLUS_ALLOC_CNID);
if (IS_ERR(inode)) {
printk(KERN_ERR "hfs: failed to load allocation file\n");
err = PTR_ERR(inode);
- goto cleanup;
+ goto out_close_cat_tree;
}
sbi->alloc_file = inode;
@@ -442,14 +442,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
if (IS_ERR(root)) {
printk(KERN_ERR "hfs: failed to load root directory\n");
err = PTR_ERR(root);
- goto cleanup;
- }
- sb->s_d_op = &hfsplus_dentry_operations;
- sb->s_root = d_alloc_root(root);
- if (!sb->s_root) {
- iput(root);
- err = -ENOMEM;
- goto cleanup;
+ goto out_put_alloc_file;
}
str.len = sizeof(HFSP_HIDDENDIR_NAME) - 1;
@@ -459,46 +452,69 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
hfs_find_exit(&fd);
if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
- goto cleanup;
+ goto out_put_root;
inode = hfsplus_iget(sb, be32_to_cpu(entry.folder.id));
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
- goto cleanup;
+ goto out_put_root;
}
sbi->hidden_dir = inode;
} else
hfs_find_exit(&fd);
- if (sb->s_flags & MS_RDONLY)
- goto out;
+ if (!(sb->s_flags & MS_RDONLY)) {
+ /*
+ * H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused
+ * all three are registered with Apple for our use
+ */
+ vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION);
+ vhdr->modify_date = hfsp_now2mt();
+ be32_add_cpu(&vhdr->write_count, 1);
+ vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
+ vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
+ hfsplus_sync_fs(sb, 1);
- /* H+LX == hfsplusutils, H+Lx == this driver, H+lx is unused
- * all three are registered with Apple for our use
- */
- vhdr->last_mount_vers = cpu_to_be32(HFSP_MOUNT_VERSION);
- vhdr->modify_date = hfsp_now2mt();
- be32_add_cpu(&vhdr->write_count, 1);
- vhdr->attributes &= cpu_to_be32(~HFSPLUS_VOL_UNMNT);
- vhdr->attributes |= cpu_to_be32(HFSPLUS_VOL_INCNSTNT);
- hfsplus_sync_fs(sb, 1);
-
- if (!sbi->hidden_dir) {
- mutex_lock(&sbi->vh_mutex);
- sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
- hfsplus_create_cat(sbi->hidden_dir->i_ino, sb->s_root->d_inode,
- &str, sbi->hidden_dir);
- mutex_unlock(&sbi->vh_mutex);
-
- hfsplus_mark_inode_dirty(sbi->hidden_dir, HFSPLUS_I_CAT_DIRTY);
+ if (!sbi->hidden_dir) {
+ mutex_lock(&sbi->vh_mutex);
+ sbi->hidden_dir = hfsplus_new_inode(sb, S_IFDIR);
+ hfsplus_create_cat(sbi->hidden_dir->i_ino, root, &str,
+ sbi->hidden_dir);
+ mutex_unlock(&sbi->vh_mutex);
+
+ hfsplus_mark_inode_dirty(sbi->hidden_dir,
+ HFSPLUS_I_CAT_DIRTY);
+ }
}
-out:
+
+ sb->s_d_op = &hfsplus_dentry_operations;
+ sb->s_root = d_alloc_root(root);
+ if (!sb->s_root) {
+ err = -ENOMEM;
+ goto out_put_hidden_dir;
+ }
+
unload_nls(sbi->nls);
sbi->nls = nls;
return 0;
-cleanup:
- hfsplus_put_super(sb);
+out_put_hidden_dir:
+ iput(sbi->hidden_dir);
+out_put_root:
+ iput(sbi->alloc_file);
+out_put_alloc_file:
+ iput(sbi->alloc_file);
+out_close_cat_tree:
+ hfs_btree_close(sbi->cat_tree);
+out_close_ext_tree:
+ hfs_btree_close(sbi->ext_tree);
+out_free_vhdr:
+ kfree(sbi->s_vhdr);
+ kfree(sbi->s_backup_vhdr);
+out_unload_nls:
+ unload_nls(sbi->nls);
unload_nls(nls);
+ kfree(sbi);
+out:
return err;
}
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index 196231794f6..3031d81f5f0 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -167,7 +167,7 @@ reread:
break;
case cpu_to_be16(HFSP_WRAP_MAGIC):
if (!hfsplus_read_mdb(sbi->s_vhdr, &wd))
- goto out;
+ goto out_free_backup_vhdr;
wd.ablk_size >>= HFSPLUS_SECTOR_SHIFT;
part_start += wd.ablk_start + wd.embed_start * wd.ablk_size;
part_size = wd.embed_count * wd.ablk_size;
@@ -179,7 +179,7 @@ reread:
* (should do this only for cdrom/loop though)
*/
if (hfs_part_find(sb, &part_start, &part_size))
- goto out;
+ goto out_free_backup_vhdr;
goto reread;
}
diff --git a/fs/ioctl.c b/fs/ioctl.c
index a59635e295f..1eebeb72b20 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -273,6 +273,13 @@ int __generic_block_fiemap(struct inode *inode,
len = isize;
}
+ /*
+ * Some filesystems can't deal with being asked to map less than
+ * blocksize, so make sure our len is at least block length.
+ */
+ if (logical_to_blk(inode, len) == 0)
+ len = blk_to_logical(inode, 1);
+
start_blk = logical_to_blk(inode, start);
last_blk = logical_to_blk(inode, start + len - 1);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 9e4686900f1..97e73469b2c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -473,7 +473,8 @@ int __jbd2_log_space_left(journal_t *journal)
}
/*
- * Called under j_state_lock. Returns true if a transaction commit was started.
+ * Called with j_state_lock locked for writing.
+ * Returns true if a transaction commit was started.
*/
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
@@ -520,11 +521,13 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
{
transaction_t *transaction = NULL;
tid_t tid;
+ int need_to_start = 0;
read_lock(&journal->j_state_lock);
if (journal->j_running_transaction && !current->journal_info) {
transaction = journal->j_running_transaction;
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ if (!tid_geq(journal->j_commit_request, transaction->t_tid))
+ need_to_start = 1;
} else if (journal->j_committing_transaction)
transaction = journal->j_committing_transaction;
@@ -535,6 +538,8 @@ int jbd2_journal_force_commit_nested(journal_t *journal)
tid = transaction->t_tid;
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
jbd2_log_wait_commit(journal, tid);
return 1;
}
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index faad2bd787c..1d1191050f9 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -117,10 +117,10 @@ static inline void update_t_max_wait(transaction_t *transaction)
static int start_this_handle(journal_t *journal, handle_t *handle,
int gfp_mask)
{
- transaction_t *transaction;
- int needed;
- int nblocks = handle->h_buffer_credits;
- transaction_t *new_transaction = NULL;
+ transaction_t *transaction, *new_transaction = NULL;
+ tid_t tid;
+ int needed, need_to_start;
+ int nblocks = handle->h_buffer_credits;
if (nblocks > journal->j_max_transaction_buffers) {
printk(KERN_ERR "JBD: %s wants too many credits (%d > %d)\n",
@@ -222,8 +222,11 @@ repeat:
atomic_sub(nblocks, &transaction->t_outstanding_credits);
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ tid = transaction->t_tid;
+ need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
@@ -442,7 +445,8 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
- int ret;
+ tid_t tid;
+ int need_to_start, ret;
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
@@ -465,8 +469,11 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, int gfp_mask)
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
- __jbd2_log_start_commit(journal, transaction->t_tid);
+ tid = transaction->t_tid;
+ need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
+ if (need_to_start)
+ jbd2_log_start_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
diff --git a/fs/namei.c b/fs/namei.c
index 7d77f24d32a..0087cf9c2c6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -455,14 +455,6 @@ static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry
struct fs_struct *fs = current->fs;
struct dentry *parent = nd->path.dentry;
- /*
- * It can be possible to revalidate the dentry that we started
- * the path walk with. force_reval_path may also revalidate the
- * dentry already committed to the nameidata.
- */
- if (unlikely(parent == dentry))
- return nameidata_drop_rcu(nd);
-
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (nd->root.mnt) {
spin_lock(&fs->lock);
@@ -561,39 +553,25 @@ static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
*/
void release_open_intent(struct nameidata *nd)
{
- if (nd->intent.open.file->f_path.dentry == NULL)
- put_filp(nd->intent.open.file);
- else
- fput(nd->intent.open.file);
-}
-
-/*
- * Call d_revalidate and handle filesystems that request rcu-walk
- * to be dropped. This may be called and return in rcu-walk mode,
- * regardless of success or error. If -ECHILD is returned, the caller
- * must return -ECHILD back up the path walk stack so path walk may
- * be restarted in ref-walk mode.
- */
-static int d_revalidate(struct dentry *dentry, struct nameidata *nd)
-{
- int status;
+ struct file *file = nd->intent.open.file;
- status = dentry->d_op->d_revalidate(dentry, nd);
- if (status == -ECHILD) {
- if (nameidata_dentry_drop_rcu(nd, dentry))
- return status;
- status = dentry->d_op->d_revalidate(dentry, nd);
+ if (file && !IS_ERR(file)) {
+ if (file->f_path.dentry == NULL)
+ put_filp(file);
+ else
+ fput(file);
}
+}
- return status;
+static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+ return dentry->d_op->d_revalidate(dentry, nd);
}
-static inline struct dentry *
+static struct dentry *
do_revalidate(struct dentry *dentry, struct nameidata *nd)
{
- int status;
-
- status = d_revalidate(dentry, nd);
+ int status = d_revalidate(dentry, nd);
if (unlikely(status <= 0)) {
/*
* The dentry failed validation.
@@ -602,24 +580,39 @@ do_revalidate(struct dentry *dentry, struct nameidata *nd)
* to return a fail status.
*/
if (status < 0) {
- /* If we're in rcu-walk, we don't have a ref */
- if (!(nd->flags & LOOKUP_RCU))
- dput(dentry);
+ dput(dentry);
dentry = ERR_PTR(status);
-
- } else {
- /* Don't d_invalidate in rcu-walk mode */
- if (nameidata_dentry_drop_rcu_maybe(nd, dentry))
- return ERR_PTR(-ECHILD);
- if (!d_invalidate(dentry)) {
- dput(dentry);
- dentry = NULL;
- }
+ } else if (!d_invalidate(dentry)) {
+ dput(dentry);
+ dentry = NULL;
}
}
return dentry;
}
+static inline struct dentry *
+do_revalidate_rcu(struct dentry *dentry, struct nameidata *nd)
+{
+ int status = d_revalidate(dentry, nd);
+ if (likely(status > 0))
+ return dentry;
+ if (status == -ECHILD) {
+ if (nameidata_dentry_drop_rcu(nd, dentry))
+ return ERR_PTR(-ECHILD);
+ return do_revalidate(dentry, nd);
+ }
+ if (status < 0)
+ return ERR_PTR(status);
+ /* Don't d_invalidate in rcu-walk mode */
+ if (nameidata_dentry_drop_rcu(nd, dentry))
+ return ERR_PTR(-ECHILD);
+ if (!d_invalidate(dentry)) {
+ dput(dentry);
+ dentry = NULL;
+ }
+ return dentry;
+}
+
static inline int need_reval_dot(struct dentry *dentry)
{
if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
@@ -664,9 +657,6 @@ force_reval_path(struct path *path, struct nameidata *nd)
return 0;
if (!status) {
- /* Don't d_invalidate in rcu-walk mode */
- if (nameidata_drop_rcu(nd))
- return -ECHILD;
d_invalidate(dentry);
status = -ESTALE;
}
@@ -773,6 +763,8 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p)
int error;
struct dentry *dentry = link->dentry;
+ BUG_ON(nd->flags & LOOKUP_RCU);
+
touch_atime(link->mnt, dentry);
nd_set_link(nd, NULL);
@@ -803,10 +795,16 @@ __do_follow_link(const struct path *link, struct nameidata *nd, void **p)
* Without that kind of total limit, nasty chains of consecutive
* symlinks can cause almost arbitrarily long lookups.
*/
-static inline int do_follow_link(struct path *path, struct nameidata *nd)
+static inline int do_follow_link(struct inode *inode, struct path *path, struct nameidata *nd)
{
void *cookie;
int err = -ELOOP;
+
+ /* We drop rcu-walk here */
+ if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry))
+ return -ECHILD;
+ BUG_ON(inode != path->dentry->d_inode);
+
if (current->link_count >= MAX_NESTED_LINKS)
goto loop;
if (current->total_link_count >= 40)
@@ -1251,9 +1249,15 @@ static int do_lookup(struct nameidata *nd, struct qstr *name,
return -ECHILD;
nd->seq = seq;
- if (dentry->d_flags & DCACHE_OP_REVALIDATE)
- goto need_revalidate;
-done2:
+ if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+ dentry = do_revalidate_rcu(dentry, nd);
+ if (!dentry)
+ goto need_lookup;
+ if (IS_ERR(dentry))
+ goto fail;
+ if (!(nd->flags & LOOKUP_RCU))
+ goto done;
+ }
path->mnt = mnt;
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode, false)))
@@ -1266,8 +1270,13 @@ done2:
if (!dentry)
goto need_lookup;
found:
- if (dentry->d_flags & DCACHE_OP_REVALIDATE)
- goto need_revalidate;
+ if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
+ dentry = do_revalidate(dentry, nd);
+ if (!dentry)
+ goto need_lookup;
+ if (IS_ERR(dentry))
+ goto fail;
+ }
done:
path->mnt = mnt;
path->dentry = dentry;
@@ -1309,16 +1318,6 @@ need_lookup:
mutex_unlock(&dir->i_mutex);
goto found;
-need_revalidate:
- dentry = do_revalidate(dentry, nd);
- if (!dentry)
- goto need_lookup;
- if (IS_ERR(dentry))
- goto fail;
- if (nd->flags & LOOKUP_RCU)
- goto done2;
- goto done;
-
fail:
return PTR_ERR(dentry);
}
@@ -1415,11 +1414,7 @@ exec_again:
goto out_dput;
if (inode->i_op->follow_link) {
- /* We commonly drop rcu-walk here */
- if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
- return -ECHILD;
- BUG_ON(inode != next.dentry->d_inode);
- err = do_follow_link(&next, nd);
+ err = do_follow_link(inode, &next, nd);
if (err)
goto return_err;
nd->inode = nd->path.dentry->d_inode;
@@ -1463,10 +1458,7 @@ last_component:
break;
if (inode && unlikely(inode->i_op->follow_link) &&
(lookup_flags & LOOKUP_FOLLOW)) {
- if (nameidata_dentry_drop_rcu_maybe(nd, next.dentry))
- return -ECHILD;
- BUG_ON(inode != next.dentry->d_inode);
- err = do_follow_link(&next, nd);
+ err = do_follow_link(inode, &next, nd);
if (err)
goto return_err;
nd->inode = nd->path.dentry->d_inode;
@@ -1500,12 +1492,15 @@ return_reval:
* We may need to check the cached dentry for staleness.
*/
if (need_reval_dot(nd->path.dentry)) {
+ if (nameidata_drop_rcu_last_maybe(nd))
+ return -ECHILD;
/* Note: we do not d_invalidate() */
err = d_revalidate(nd->path.dentry, nd);
if (!err)
err = -ESTALE;
if (err < 0)
break;
+ return 0;
}
return_base:
if (nameidata_drop_rcu_last_maybe(nd))
@@ -2265,8 +2260,6 @@ static struct file *finish_open(struct nameidata *nd,
return filp;
exit:
- if (!IS_ERR(nd->intent.open.file))
- release_open_intent(nd);
path_put(&nd->path);
return ERR_PTR(error);
}
@@ -2389,8 +2382,6 @@ exit_mutex_unlock:
exit_dput:
path_put_conditional(path, nd);
exit:
- if (!IS_ERR(nd->intent.open.file))
- release_open_intent(nd);
path_put(&nd->path);
return ERR_PTR(error);
}
@@ -2477,6 +2468,7 @@ struct file *do_filp_open(int dfd, const char *pathname,
}
audit_inode(pathname, nd.path.dentry);
filp = finish_open(&nd, open_flag, acc_mode);
+ release_open_intent(&nd);
return filp;
creat:
@@ -2553,6 +2545,7 @@ out:
path_put(&nd.root);
if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
goto reval;
+ release_open_intent(&nd);
return filp;
exit_dput:
@@ -2560,8 +2553,6 @@ exit_dput:
out_path:
path_put(&nd.path);
out_filp:
- if (!IS_ERR(nd.intent.open.file))
- release_open_intent(&nd);
filp = ERR_PTR(error);
goto out;
}
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 3be975e1891..cde36cb0f34 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -484,7 +484,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr,
out:
return status;
out_default:
- return nfs_cb_stat_to_errno(status);
+ return nfs_cb_stat_to_errno(nfserr);
}
/*
@@ -564,11 +564,9 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
if (unlikely(status))
goto out;
if (unlikely(nfserr != NFS4_OK))
- goto out_default;
+ status = nfs_cb_stat_to_errno(nfserr);
out:
return status;
-out_default:
- return nfs_cb_stat_to_errno(status);
}
/*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d98d0213285..54b60bfceb8 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -230,9 +230,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
dp->dl_client = clp;
get_nfs4_file(fp);
dp->dl_file = fp;
- dp->dl_vfs_file = find_readable_file(fp);
- get_file(dp->dl_vfs_file);
- dp->dl_flock = NULL;
dp->dl_type = type;
dp->dl_stateid.si_boot = boot_time;
dp->dl_stateid.si_stateownerid = current_delegid++;
@@ -241,8 +238,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_f
fh_copy_shallow(&dp->dl_fh, &current_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
- list_add(&dp->dl_perfile, &fp->fi_delegations);
- list_add(&dp->dl_perclnt, &clp->cl_delegations);
INIT_WORK(&dp->dl_recall.cb_work, nfsd4_do_callback_rpc);
return dp;
}
@@ -253,36 +248,30 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- fput(dp->dl_vfs_file);
kmem_cache_free(deleg_slab, dp);
num_delegations--;
}
}
-/* Remove the associated file_lock first, then remove the delegation.
- * lease_modify() is called to remove the FS_LEASE file_lock from
- * the i_flock list, eventually calling nfsd's lock_manager
- * fl_release_callback.
- */
-static void
-nfs4_close_delegation(struct nfs4_delegation *dp)
+static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
- dprintk("NFSD: close_delegation dp %p\n",dp);
- /* XXX: do we even need this check?: */
- if (dp->dl_flock)
- vfs_setlease(dp->dl_vfs_file, F_UNLCK, &dp->dl_flock);
+ if (atomic_dec_and_test(&fp->fi_delegees)) {
+ vfs_setlease(fp->fi_deleg_file, F_UNLCK, &fp->fi_lease);
+ fp->fi_lease = NULL;
+ fp->fi_deleg_file = NULL;
+ }
}
/* Called under the state lock. */
static void
unhash_delegation(struct nfs4_delegation *dp)
{
- list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_perclnt);
spin_lock(&recall_lock);
+ list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_recall_lru);
spin_unlock(&recall_lock);
- nfs4_close_delegation(dp);
+ nfs4_put_deleg_lease(dp->dl_file);
nfs4_put_delegation(dp);
}
@@ -958,8 +947,6 @@ expire_client(struct nfs4_client *clp)
spin_lock(&recall_lock);
while (!list_empty(&clp->cl_delegations)) {
dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
- dprintk("NFSD: expire client. dp %p, fp %p\n", dp,
- dp->dl_flock);
list_del_init(&dp->dl_perclnt);
list_move(&dp->dl_recall_lru, &reaplist);
}
@@ -2078,6 +2065,7 @@ alloc_init_file(struct inode *ino)
fp->fi_inode = igrab(ino);
fp->fi_id = current_fileid++;
fp->fi_had_conflict = false;
+ fp->fi_lease = NULL;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
spin_lock(&recall_lock);
@@ -2329,23 +2317,8 @@ nfs4_file_downgrade(struct nfs4_file *fp, unsigned int share_access)
nfs4_file_put_access(fp, O_RDONLY);
}
-/*
- * Spawn a thread to perform a recall on the delegation represented
- * by the lease (file_lock)
- *
- * Called from break_lease() with lock_flocks() held.
- * Note: we assume break_lease will only call this *once* for any given
- * lease.
- */
-static
-void nfsd_break_deleg_cb(struct file_lock *fl)
+static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
{
- struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner;
-
- dprintk("NFSD nfsd_break_deleg_cb: dp %p fl %p\n",dp,fl);
- if (!dp)
- return;
-
/* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
* callback (and since the lease code is serialized by the kernel
@@ -2353,22 +2326,35 @@ void nfsd_break_deleg_cb(struct file_lock *fl)
* it's safe to take a reference: */
atomic_inc(&dp->dl_count);
- spin_lock(&recall_lock);
list_add_tail(&dp->dl_recall_lru, &del_recall_lru);
- spin_unlock(&recall_lock);
/* only place dl_time is set. protected by lock_flocks*/
dp->dl_time = get_seconds();
+ nfsd4_cb_recall(dp);
+}
+
+/* Called from break_lease() with lock_flocks() held. */
+static void nfsd_break_deleg_cb(struct file_lock *fl)
+{
+ struct nfs4_file *fp = (struct nfs4_file *)fl->fl_owner;
+ struct nfs4_delegation *dp;
+
+ BUG_ON(!fp);
+ /* We assume break_lease is only called once per lease: */
+ BUG_ON(fp->fi_had_conflict);
/*
* We don't want the locks code to timeout the lease for us;
- * we'll remove it ourself if the delegation isn't returned
- * in time.
+ * we'll remove it ourself if a delegation isn't returned
+ * in time:
*/
fl->fl_break_time = 0;
- dp->dl_file->fi_had_conflict = true;
- nfsd4_cb_recall(dp);
+ spin_lock(&recall_lock);
+ fp->fi_had_conflict = true;
+ list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
+ nfsd_break_one_deleg(dp);
+ spin_unlock(&recall_lock);
}
static
@@ -2459,13 +2445,15 @@ nfs4_check_delegmode(struct nfs4_delegation *dp, int flags)
static struct nfs4_delegation *
find_delegation_file(struct nfs4_file *fp, stateid_t *stid)
{
- struct nfs4_delegation *dp;
+ struct nfs4_delegation *dp = NULL;
+ spin_lock(&recall_lock);
list_for_each_entry(dp, &fp->fi_delegations, dl_perfile) {
if (dp->dl_stateid.si_stateownerid == stid->si_stateownerid)
- return dp;
+ break;
}
- return NULL;
+ spin_unlock(&recall_lock);
+ return dp;
}
int share_access_to_flags(u32 share_access)
@@ -2641,6 +2629,66 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
}
+static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int flag)
+{
+ struct file_lock *fl;
+
+ fl = locks_alloc_lock();
+ if (!fl)
+ return NULL;
+ locks_init_lock(fl);
+ fl->fl_lmops = &nfsd_lease_mng_ops;
+ fl->fl_flags = FL_LEASE;
+ fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
+ fl->fl_end = OFFSET_MAX;
+ fl->fl_owner = (fl_owner_t)(dp->dl_file);
+ fl->fl_pid = current->tgid;
+ return fl;
+}
+
+static int nfs4_setlease(struct nfs4_delegation *dp, int flag)
+{
+ struct nfs4_file *fp = dp->dl_file;
+ struct file_lock *fl;
+ int status;
+
+ fl = nfs4_alloc_init_lease(dp, flag);
+ if (!fl)
+ return -ENOMEM;
+ fl->fl_file = find_readable_file(fp);
+ list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations);
+ status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
+ if (status) {
+ list_del_init(&dp->dl_perclnt);
+ locks_free_lock(fl);
+ return -ENOMEM;
+ }
+ fp->fi_lease = fl;
+ fp->fi_deleg_file = fl->fl_file;
+ get_file(fp->fi_deleg_file);
+ atomic_set(&fp->fi_delegees, 1);
+ list_add(&dp->dl_perfile, &fp->fi_delegations);
+ return 0;
+}
+
+static int nfs4_set_delegation(struct nfs4_delegation *dp, int flag)
+{
+ struct nfs4_file *fp = dp->dl_file;
+
+ if (!fp->fi_lease)
+ return nfs4_setlease(dp, flag);
+ spin_lock(&recall_lock);
+ if (fp->fi_had_conflict) {
+ spin_unlock(&recall_lock);
+ return -EAGAIN;
+ }
+ atomic_inc(&fp->fi_delegees);
+ list_add(&dp->dl_perfile, &fp->fi_delegations);
+ spin_unlock(&recall_lock);
+ list_add(&dp->dl_perclnt, &dp->dl_client->cl_delegations);
+ return 0;
+}
+
/*
* Attempt to hand out a delegation.
*/
@@ -2650,7 +2698,6 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
struct nfs4_delegation *dp;
struct nfs4_stateowner *sop = stp->st_stateowner;
int cb_up;
- struct file_lock *fl;
int status, flag = 0;
cb_up = nfsd4_cb_channel_good(sop->so_client);
@@ -2681,36 +2728,11 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
}
dp = alloc_init_deleg(sop->so_client, stp, fh, flag);
- if (dp == NULL) {
- flag = NFS4_OPEN_DELEGATE_NONE;
- goto out;
- }
- status = -ENOMEM;
- fl = locks_alloc_lock();
- if (!fl)
- goto out;
- locks_init_lock(fl);
- fl->fl_lmops = &nfsd_lease_mng_ops;
- fl->fl_flags = FL_LEASE;
- fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
- fl->fl_end = OFFSET_MAX;
- fl->fl_owner = (fl_owner_t)dp;
- fl->fl_file = find_readable_file(stp->st_file);
- BUG_ON(!fl->fl_file);
- fl->fl_pid = current->tgid;
- dp->dl_flock = fl;
-
- /* vfs_setlease checks to see if delegation should be handed out.
- * the lock_manager callback fl_change is used
- */
- if ((status = vfs_setlease(fl->fl_file, fl->fl_type, &fl))) {
- dprintk("NFSD: setlease failed [%d], no delegation\n", status);
- dp->dl_flock = NULL;
- locks_free_lock(fl);
- unhash_delegation(dp);
- flag = NFS4_OPEN_DELEGATE_NONE;
- goto out;
- }
+ if (dp == NULL)
+ goto out_no_deleg;
+ status = nfs4_set_delegation(dp, flag);
+ if (status)
+ goto out_free;
memcpy(&open->op_delegate_stateid, &dp->dl_stateid, sizeof(dp->dl_stateid));
@@ -2722,6 +2744,12 @@ out:
&& open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE)
dprintk("NFSD: WARNING: refusing delegation reclaim\n");
open->op_delegate_type = flag;
+ return;
+out_free:
+ nfs4_put_delegation(dp);
+out_no_deleg:
+ flag = NFS4_OPEN_DELEGATE_NONE;
+ goto out;
}
/*
@@ -2916,8 +2944,6 @@ nfs4_laundromat(void)
test_val = u;
break;
}
- dprintk("NFSD: purging unused delegation dp %p, fp %p\n",
- dp, dp->dl_flock);
list_move(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&recall_lock);
@@ -3128,7 +3154,7 @@ nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
goto out;
renew_client(dp->dl_client);
if (filpp) {
- *filpp = find_readable_file(dp->dl_file);
+ *filpp = dp->dl_file->fi_deleg_file;
BUG_ON(!*filpp);
}
} else { /* open or lock stateid */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 956629b9cdc..1275b865507 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -317,8 +317,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
- if ((host_err = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid)))
- goto out_nfserr;
+ if ((status = nfsd_map_name_to_uid(argp->rqstp, buf, dummy32, &iattr->ia_uid)))
+ return status;
iattr->ia_valid |= ATTR_UID;
}
if (bmval[1] & FATTR4_WORD1_OWNER_GROUP) {
@@ -328,8 +328,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval,
READ_BUF(dummy32);
len += (XDR_QUADLEN(dummy32) << 2);
READMEM(buf, dummy32);
- if ((host_err = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid)))
- goto out_nfserr;
+ if ((status = nfsd_map_name_to_gid(argp->rqstp, buf, dummy32, &iattr->ia_gid)))
+ return status;
iattr->ia_valid |= ATTR_GID;
}
if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 3074656ba7b..2d31224b07b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -83,8 +83,6 @@ struct nfs4_delegation {
atomic_t dl_count; /* ref count */
struct nfs4_client *dl_client;
struct nfs4_file *dl_file;
- struct file *dl_vfs_file;
- struct file_lock *dl_flock;
u32 dl_type;
time_t dl_time;
/* For recall: */
@@ -379,6 +377,9 @@ struct nfs4_file {
*/
atomic_t fi_readers;
atomic_t fi_writers;
+ struct file *fi_deleg_file;
+ struct file_lock *fi_lease;
+ atomic_t fi_delegees;
struct inode *fi_inode;
u32 fi_id; /* used with stateowner->so_id
* for stateid_hashtbl hash */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 641117f2188..da1d9701f8e 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -808,7 +808,7 @@ nfsd_get_raparms(dev_t dev, ino_t ino)
if (ra->p_count == 0)
frap = rap;
}
- depth = nfsdstats.ra_size*11/10;
+ depth = nfsdstats.ra_size;
if (!frap) {
spin_unlock(&rab->pb_lock);
return NULL;
@@ -1744,6 +1744,13 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
host_err = nfsd_break_lease(odentry->d_inode);
if (host_err)
goto out_drop_write;
+ if (ndentry->d_inode) {
+ host_err = nfsd_break_lease(ndentry->d_inode);
+ if (host_err)
+ goto out_drop_write;
+ }
+ if (host_err)
+ goto out_drop_write;
host_err = vfs_rename(fdir, odentry, tdir, ndentry);
if (!host_err) {
host_err = commit_metadata(tfhp);
@@ -1812,22 +1819,22 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type,
host_err = mnt_want_write(fhp->fh_export->ex_path.mnt);
if (host_err)
- goto out_nfserr;
+ goto out_put;
host_err = nfsd_break_lease(rdentry->d_inode);
if (host_err)
- goto out_put;
+ goto out_drop_write;
if (type != S_IFDIR)
host_err = vfs_unlink(dirp, rdentry);
else
host_err = vfs_rmdir(dirp, rdentry);
-out_put:
- dput(rdentry);
-
if (!host_err)
host_err = commit_metadata(fhp);
-
+out_drop_write:
mnt_drop_write(fhp->fh_export->ex_path.mnt);
+out_put:
+ dput(rdentry);
+
out_nfserr:
err = nfserrno(host_err);
out:
diff --git a/fs/open.c b/fs/open.c
index e52389e1f05..5a2c6ebc22b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -790,6 +790,8 @@ struct file *nameidata_to_filp(struct nameidata *nd)
/* Pick up the filp from the open intent */
filp = nd->intent.open.file;
+ nd->intent.open.file = NULL;
+
/* Has the filesystem initialised the file for us? */
if (filp->f_path.dentry == NULL) {
path_get(&nd->path);
diff --git a/fs/partitions/mac.c b/fs/partitions/mac.c
index 68d6a216ee7..11f688bd76c 100644
--- a/fs/partitions/mac.c
+++ b/fs/partitions/mac.c
@@ -29,10 +29,9 @@ static inline void mac_fix_string(char *stg, int len)
int mac_partition(struct parsed_partitions *state)
{
- int slot = 1;
Sector sect;
unsigned char *data;
- int blk, blocks_in_map;
+ int slot, blocks_in_map;
unsigned secsize;
#ifdef CONFIG_PPC_PMAC
int found_root = 0;
@@ -59,10 +58,14 @@ int mac_partition(struct parsed_partitions *state)
put_dev_sector(sect);
return 0; /* not a MacOS disk */
}
- strlcat(state->pp_buf, " [mac]", PAGE_SIZE);
blocks_in_map = be32_to_cpu(part->map_count);
- for (blk = 1; blk <= blocks_in_map; ++blk) {
- int pos = blk * secsize;
+ if (blocks_in_map < 0 || blocks_in_map >= DISK_MAX_PARTS) {
+ put_dev_sector(sect);
+ return 0;
+ }
+ strlcat(state->pp_buf, " [mac]", PAGE_SIZE);
+ for (slot = 1; slot <= blocks_in_map; ++slot) {
+ int pos = slot * secsize;
put_dev_sector(sect);
data = read_part_sector(state, pos/512, &sect);
if (!data)
@@ -113,13 +116,11 @@ int mac_partition(struct parsed_partitions *state)
}
if (goodness > found_root_goodness) {
- found_root = blk;
+ found_root = slot;
found_root_goodness = goodness;
}
}
#endif /* CONFIG_PPC_PMAC */
-
- ++slot;
}
#ifdef CONFIG_PPC_PMAC
if (found_root_goodness)
diff --git a/fs/proc/array.c b/fs/proc/array.c
index df2b703b9d0..7c99c1cf7e5 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -353,9 +353,6 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
task_cap(m, task);
task_cpus_allowed(m, task);
cpuset_task_status_allowed(m, task);
-#if defined(CONFIG_S390)
- task_show_regs(m, task);
-#endif
task_context_switch_counts(m, task);
return 0;
}
diff --git a/fs/super.c b/fs/super.c
index 74e149efed8..7e9dd4cc2c0 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -177,6 +177,11 @@ void deactivate_locked_super(struct super_block *s)
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
fs->kill_sb(s);
+ /*
+ * We need to call rcu_barrier so all the delayed rcu free
+ * inodes are flushed before we release the fs module.
+ */
+ rcu_barrier();
put_filesystem(fs);
put_super(s);
} else {