aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/acl.c6
-rw-r--r--fs/btrfs/compression.c27
-rw-r--r--fs/btrfs/disk-io.c7
-rw-r--r--fs/btrfs/export.c2
-rw-r--r--fs/btrfs/extent-tree.c98
-rw-r--r--fs/btrfs/extent_io.c6
-rw-r--r--fs/btrfs/file-item.c5
-rw-r--r--fs/btrfs/file.c20
-rw-r--r--fs/btrfs/free-space-cache.c162
-rw-r--r--fs/btrfs/inode.c35
-rw-r--r--fs/btrfs/ioctl.c19
-rw-r--r--fs/btrfs/ordered-data.c2
-rw-r--r--fs/btrfs/print-tree.c1
-rw-r--r--fs/btrfs/relocation.c29
-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.c19
-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/readdir.c3
-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/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/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.c20
-rw-r--r--fs/open.c2
-rw-r--r--fs/super.c5
54 files changed, 886 insertions, 386 deletions
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 15b5ca2..9c94934 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 f745287..4d2110e 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 b531c36..fdce879 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1550,6 +1550,7 @@ 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 +2454,14 @@ 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 +2559,8 @@ 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 9786963..ff27d7a 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 b552693..4e7e012 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;
@@ -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 2e993cf..5e76a47 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;
@@ -2126,7 +2128,7 @@ 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;
}
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index a562a25..4f19a3e 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 c800d58..c1d3a81 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -793,8 +793,12 @@ 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 +950,10 @@ 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 +992,8 @@ 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 +1023,8 @@ 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 60d6842..a039065 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 160b55b..bcc461a 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,
@@ -771,7 +772,7 @@ 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;
@@ -1049,7 +1050,7 @@ 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;
@@ -1557,6 +1558,7 @@ out:
out_page:
unlock_page(page);
page_cache_release(page);
+ kfree(fixup);
}
/*
@@ -1703,7 +1705,7 @@ 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 +1722,7 @@ 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 +2357,7 @@ 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 +2385,7 @@ 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 +2646,7 @@ 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 +2719,10 @@ 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 +2733,7 @@ static int check_path_shared(struct btrfs_root *root,
if (refs > 1)
return 1;
}
- return ret; /* XXX callers? */
+ return 0;
}
/*
@@ -4134,7 +4140,7 @@ 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 +4353,8 @@ 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 +4380,7 @@ 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 +5185,8 @@ 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 +5291,8 @@ 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 +5516,7 @@ 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 +5651,7 @@ 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 a506a22..02d224e 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);
@@ -2334,6 +2341,8 @@ 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 2b61e1d..083a554 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 0d126be..fb2605d 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 045c9c2..1f5556a 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2028,6 +2028,7 @@ 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 +2148,12 @@ 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 +3229,7 @@ truncate:
trans = btrfs_join_transaction(root, 0);
if (IS_ERR(trans)) {
btrfs_free_path(path);
+ ret = PTR_ERR(trans);
goto out;
}
@@ -3628,6 +3636,7 @@ 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 +3666,7 @@ 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 +3814,10 @@ 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 +4035,7 @@ 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 +4139,11 @@ 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 +4173,13 @@ 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 b2130c4..a004008 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 bae5c7b..3d73c8d 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 054744a..a4bbb85 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 d158530..2636a05 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;
@@ -1606,6 +1610,12 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
}
trans = btrfs_start_transaction(root, 0);
+ if (IS_ERR(trans)) {
+ kfree(device);
+ ret = PTR_ERR(trans);
+ goto error;
+ }
+
lock_chunks(root);
device->writeable = 1;
@@ -1873,7 +1883,7 @@ 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 +2057,7 @@ 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 +2223,11 @@ 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/cifs/Kconfig b/fs/cifs/Kconfig
index ee45648..7cb0f7f 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 f1c6862..0a265ad 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 1e7636b..beeebf1 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 0db5f1d..a51585f 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 14789a9..4a33302 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 "1.70"
#endif /* _CIFSFS_H */
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index edd5b29..17afb0f 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 3106f5e..904aa47 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 47d8ff6..8d6c17a 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 0de17c1..e964b1c 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 02cd60a..e8804d3 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 a09e077..2a930a7 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/readdir.c b/fs/cifs/readdir.c
index 7f25cc3..f8e4cd2 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/smbencrypt.c b/fs/cifs/smbencrypt.c
index b5450e9..b5041c8 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 c1ccca1..46d8756 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 9c64ae9..2d8c87b 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/eventpoll.c b/fs/eventpoll.c
index cc8a9b7..267d0ad 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 c62efcb..52a447d 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 4268542..a755523 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 0c8d97b..3aa0b72 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 63a7581..ccce8a7 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 2e8322c..7b80d54 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 851f49b..d1fe09a 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 7270dcf..955cc30 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 48ce561..f6a318f 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 ecc8b39..cb10261 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 c3e89ad..eb36b6b 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/hfsplus/extents.c b/fs/hfsplus/extents.c
index 52a0bca..b1991a2 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 d66ad11..40ad88c 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 9a3b479..b49b555 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 1962317..3031d81 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 a59635e..1eebeb7 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 9e46869..97e7346 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 faad2bd..1d11910 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 7d77f24..ec4b2d0 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -561,10 +561,14 @@ 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);
+ struct file *file = nd->intent.open.file;
+
+ if (file && !IS_ERR(file)) {
+ if (file->f_path.dentry == NULL)
+ put_filp(file);
+ else
+ fput(file);
+ }
}
/*
@@ -2265,8 +2269,6 @@ 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 +2391,6 @@ 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 +2477,7 @@ 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 +2554,7 @@ 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 +2562,6 @@ 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/open.c b/fs/open.c
index e52389e..5a2c6eb 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/super.c b/fs/super.c
index 74e149e..7e9dd4c 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 {