aboutsummaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorBen Hutchings <ben.hutchings@codethink.co.uk>2018-06-19 19:04:01 +0100
committerBen Hutchings <ben.hutchings@codethink.co.uk>2018-06-19 19:04:01 +0100
commitbe9ee971feb8758055b10d7b9057bd1fe4d5a796 (patch)
tree8f0d3b95724398ca046638adef4361bcf933f3ae /fs
parent45133bfcbb0c1cf87ce4097b64c100882bf19e85 (diff)
parent0bd2bedb3501db249b347e5acbfd3415bd7667a5 (diff)
downloadlinux-cip-be9ee971feb8758055b10d7b9057bd1fe4d5a796.tar.gz
Merge tag 'v4.4.138' into linux-4.4.y-cip
This is the 4.4.138 stable release
Diffstat (limited to 'fs')
-rw-r--r--fs/affs/namei.c10
-rw-r--r--fs/aio.c7
-rw-r--r--fs/btrfs/ctree.c18
-rw-r--r--fs/btrfs/disk-io.c4
-rw-r--r--fs/btrfs/extent-tree.c1
-rw-r--r--fs/btrfs/file.c9
-rw-r--r--fs/btrfs/inode.c16
-rw-r--r--fs/btrfs/raid56.c18
-rw-r--r--fs/btrfs/send.c3
-rw-r--r--fs/btrfs/tests/qgroup-tests.c2
-rw-r--r--fs/btrfs/tree-log.c19
-rw-r--r--fs/btrfs/volumes.c18
-rw-r--r--fs/cifs/cifssmb.c4
-rw-r--r--fs/dcache.c22
-rw-r--r--fs/ecryptfs/inode.c3
-rw-r--r--fs/ext2/inode.c10
-rw-r--r--fs/ext2/namei.c6
-rw-r--r--fs/ext4/balloc.c17
-rw-r--r--fs/ext4/extents.c16
-rw-r--r--fs/ext4/ialloc.c7
-rw-r--r--fs/ext4/namei.c6
-rw-r--r--fs/f2fs/data.c2
-rw-r--r--fs/f2fs/namei.c12
-rw-r--r--fs/fs-writeback.c2
-rw-r--r--fs/fscache/page.c13
-rw-r--r--fs/gfs2/file.c5
-rw-r--r--fs/gfs2/quota.h2
-rw-r--r--fs/hfsplus/super.c1
-rw-r--r--fs/jbd2/transaction.c1
-rw-r--r--fs/jffs2/dir.c12
-rw-r--r--fs/jffs2/fs.c1
-rw-r--r--fs/jfs/namei.c12
-rw-r--r--fs/nfs/nfs4proc.c12
-rw-r--r--fs/nfs/nfs4state.c5
-rw-r--r--fs/nfs/nfs4sysctl.c2
-rw-r--r--fs/nilfs2/namei.c6
-rw-r--r--fs/ocfs2/acl.c6
-rw-r--r--fs/ocfs2/dlm/dlmdomain.c14
-rw-r--r--fs/ocfs2/dlm/dlmdomain.h25
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c9
-rw-r--r--fs/ocfs2/journal.c23
-rw-r--r--fs/ocfs2/super.c5
-rw-r--r--fs/ocfs2/xattr.c2
-rw-r--r--fs/pipe.c3
-rw-r--r--fs/proc/base.c84
-rw-r--r--fs/proc/meminfo.c5
-rw-r--r--fs/proc/proc_sysctl.c3
-rw-r--r--fs/reiserfs/namei.c12
-rw-r--r--fs/udf/namei.c6
-rw-r--r--fs/udf/super.c5
-rw-r--r--fs/ufs/namei.c6
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c94
-rw-r--r--fs/xfs/libxfs/xfs_attr.c6
-rw-r--r--fs/xfs/xfs_discard.c14
-rw-r--r--fs/xfs/xfs_file.c14
-rw-r--r--fs/xfs/xfs_log.c7
-rw-r--r--fs/xfs/xfs_mount.h1
-rw-r--r--fs/xfs/xfs_trace.h9
58 files changed, 466 insertions, 191 deletions
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 181e05b46e7261..92448d0ad900c5 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -224,9 +224,10 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
affs_lock_dir(dir);
bh = affs_find_entry(dir, dentry);
- affs_unlock_dir(dir);
- if (IS_ERR(bh))
+ if (IS_ERR(bh)) {
+ affs_unlock_dir(dir);
return ERR_CAST(bh);
+ }
if (bh) {
u32 ino = bh->b_blocknr;
@@ -240,10 +241,13 @@ affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
}
affs_brelse(bh);
inode = affs_iget(sb, ino);
- if (IS_ERR(inode))
+ if (IS_ERR(inode)) {
+ affs_unlock_dir(dir);
return ERR_CAST(inode);
+ }
}
d_add(dentry, inode);
+ affs_unlock_dir(dir);
return NULL;
}
diff --git a/fs/aio.c b/fs/aio.c
index 88ede4a84ce050..c283eb03cb38e2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -628,9 +628,8 @@ static void free_ioctx_users(struct percpu_ref *ref)
while (!list_empty(&ctx->active_reqs)) {
req = list_first_entry(&ctx->active_reqs,
struct aio_kiocb, ki_list);
-
- list_del_init(&req->ki_list);
kiocb_cancel(req);
+ list_del_init(&req->ki_list);
}
spin_unlock_irq(&ctx->ctx_lock);
@@ -1066,8 +1065,8 @@ static struct kioctx *lookup_ioctx(unsigned long ctx_id)
ctx = rcu_dereference(table->table[id]);
if (ctx && ctx->user_id == ctx_id) {
- percpu_ref_get(&ctx->users);
- ret = ctx;
+ if (percpu_ref_tryget_live(&ctx->users))
+ ret = ctx;
}
out:
rcu_read_unlock();
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0f2b7c622ce3e5..38ee086754687a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2497,10 +2497,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
if (p->reada)
reada_for_search(root, p, level, slot, key->objectid);
- btrfs_release_path(p);
-
ret = -EAGAIN;
- tmp = read_tree_block(root, blocknr, 0);
+ tmp = read_tree_block(root, blocknr, gen);
if (!IS_ERR(tmp)) {
/*
* If the read above didn't mark this buffer up to date,
@@ -2512,6 +2510,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
ret = -EIO;
free_extent_buffer(tmp);
}
+
+ btrfs_release_path(p);
return ret;
}
@@ -2769,6 +2769,8 @@ again:
* contention with the cow code
*/
if (cow) {
+ bool last_level = (level == (BTRFS_MAX_LEVEL - 1));
+
/*
* if we don't really need to cow this block
* then we don't want to set the path blocking,
@@ -2793,9 +2795,13 @@ again:
}
btrfs_set_path_blocking(p);
- err = btrfs_cow_block(trans, root, b,
- p->nodes[level + 1],
- p->slots[level + 1], &b);
+ if (last_level)
+ err = btrfs_cow_block(trans, root, b, NULL, 0,
+ &b);
+ else
+ err = btrfs_cow_block(trans, root, b,
+ p->nodes[level + 1],
+ p->slots[level + 1], &b);
if (err) {
ret = err;
goto done;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 85b207d19aa533..7efd70bfeaf78c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -923,7 +923,7 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
if (bio_flags & EXTENT_BIO_TREE_LOG)
return 0;
#ifdef CONFIG_X86
- if (cpu_has_xmm4_2)
+ if (static_cpu_has_safe(X86_FEATURE_XMM4_2))
return 0;
#endif
return 1;
@@ -1196,7 +1196,7 @@ static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
if (!writers)
return ERR_PTR(-ENOMEM);
- ret = percpu_counter_init(&writers->counter, 0, GFP_KERNEL);
+ ret = percpu_counter_init(&writers->counter, 0, GFP_NOFS);
if (ret < 0) {
kfree(writers);
return ERR_PTR(ret);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ceb98331d648a8..42ba01e240d35e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4392,6 +4392,7 @@ again:
if (wait_for_alloc) {
mutex_unlock(&fs_info->chunk_mutex);
wait_for_alloc = 0;
+ cond_resched();
goto again;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d4a6eef3185457..05297362059579 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1861,10 +1861,19 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
{
int ret;
+ struct blk_plug plug;
+ /*
+ * This is only called in fsync, which would do synchronous writes, so
+ * a plug can merge adjacent IOs as much as possible. Esp. in case of
+ * multiple disks using raid profile, a large IO can be split to
+ * several segments of stripe length (currently 64K).
+ */
+ blk_start_plug(&plug);
atomic_inc(&BTRFS_I(inode)->sync_writers);
ret = btrfs_fdatawrite_range(inode, start, end);
atomic_dec(&BTRFS_I(inode)->sync_writers);
+ blk_finish_plug(&plug);
return ret;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 81b5a461d94e2c..1f01a8172308a2 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6413,8 +6413,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
} else {
btrfs_update_inode(trans, root, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
}
out_unlock:
@@ -6489,8 +6488,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans, root);
@@ -6633,12 +6631,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
if (err)
goto out_fail_inode;
- d_instantiate(dentry, inode);
- /*
- * mkdir is special. We're unlocking after we call d_instantiate
- * to avoid a race with nfsd calling d_instantiate.
- */
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
drop_on_err = 0;
out_fail:
@@ -9789,8 +9782,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
goto out_unlock_inode;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out_unlock:
btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1a33d3eb36de18..b9fa99577bf7a3 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2160,11 +2160,21 @@ int raid56_parity_recover(struct btrfs_root *root, struct bio *bio,
}
/*
- * reconstruct from the q stripe if they are
- * asking for mirror 3
+ * Loop retry:
+ * for 'mirror == 2', reconstruct from all other stripes.
+ * for 'mirror_num > 2', select a stripe to fail on every retry.
*/
- if (mirror_num == 3)
- rbio->failb = rbio->real_stripes - 2;
+ if (mirror_num > 2) {
+ /*
+ * 'mirror == 3' is to fail the p stripe and
+ * reconstruct from the q stripe. 'mirror > 3' is to
+ * fail a data stripe and reconstruct from p+q stripe.
+ */
+ rbio->failb = rbio->real_stripes - (mirror_num - 1);
+ ASSERT(rbio->failb > 0);
+ if (rbio->failb <= rbio->faila)
+ rbio->failb--;
+ }
ret = lock_stripe_add(rbio);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 19b56873b797b3..83c73738165e22 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -4674,6 +4674,9 @@ static int send_hole(struct send_ctx *sctx, u64 end)
u64 len;
int ret = 0;
+ if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
+ return send_update_extent(sctx, offset, end - offset);
+
p = fs_path_alloc();
if (!p)
return -ENOMEM;
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index 846d277b190137..2b2978c04e80f6 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -70,7 +70,7 @@ static int insert_normal_tree_ref(struct btrfs_root *root, u64 bytenr,
btrfs_set_extent_generation(leaf, item, 1);
btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_TREE_BLOCK);
block_info = (struct btrfs_tree_block_info *)(item + 1);
- btrfs_set_tree_block_level(leaf, block_info, 1);
+ btrfs_set_tree_block_level(leaf, block_info, 0);
iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
if (parent > 0) {
btrfs_set_extent_inline_ref_type(leaf, iref,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d6359af9789d75..738f5d6beb95eb 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2223,8 +2223,10 @@ again:
nritems = btrfs_header_nritems(path->nodes[0]);
if (path->slots[0] >= nritems) {
ret = btrfs_next_leaf(root, path);
- if (ret)
+ if (ret == 1)
break;
+ else if (ret < 0)
+ goto out;
}
btrfs_item_key_to_cpu(path->nodes[0], &found_key,
path->slots[0]);
@@ -3378,8 +3380,11 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
* from this directory and from this transaction
*/
ret = btrfs_next_leaf(root, path);
- if (ret == 1) {
- last_offset = (u64)-1;
+ if (ret) {
+ if (ret == 1)
+ last_offset = (u64)-1;
+ else
+ err = ret;
goto done;
}
btrfs_item_key_to_cpu(path->nodes[0], &tmp, path->slots[0]);
@@ -3830,6 +3835,7 @@ fill_holes:
ASSERT(ret == 0);
src = src_path->nodes[0];
i = 0;
+ need_find_last_extent = true;
}
btrfs_item_key_to_cpu(src, &key, i);
@@ -4568,6 +4574,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
u64 logged_isize = 0;
bool need_log_inode_item = true;
+ bool xattrs_logged = false;
path = btrfs_alloc_path();
if (!path)
@@ -4808,6 +4815,7 @@ next_slot:
err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
if (err)
goto out_unlock;
+ xattrs_logged = true;
if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
btrfs_release_path(path);
btrfs_release_path(dst_path);
@@ -4820,6 +4828,11 @@ log_extents:
btrfs_release_path(dst_path);
if (need_log_inode_item) {
err = log_inode_item(trans, log, dst_path, inode);
+ if (!err && !xattrs_logged) {
+ err = btrfs_log_all_xattrs(trans, root, inode, path,
+ dst_path);
+ btrfs_release_path(path);
+ }
if (err)
goto out_unlock;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6d874b1cd53c6d..b4d63a9842fac6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3850,6 +3850,15 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
return 0;
}
+ /*
+ * A ro->rw remount sequence should continue with the paused balance
+ * regardless of who pauses it, system or the user as of now, so set
+ * the resume flag.
+ */
+ spin_lock(&fs_info->balance_lock);
+ fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+ spin_unlock(&fs_info->balance_lock);
+
tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
return PTR_ERR_OR_ZERO(tsk);
}
@@ -5047,7 +5056,14 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
else if (map->type & BTRFS_BLOCK_GROUP_RAID5)
ret = 2;
else if (map->type & BTRFS_BLOCK_GROUP_RAID6)
- ret = 3;
+ /*
+ * There could be two corrupted data stripes, we need
+ * to loop retry in order to rebuild the correct data.
+ *
+ * Fail a stripe at a time on every retry except the
+ * stripe under reconstruction.
+ */
+ ret = map->num_stripes;
else
ret = 1;
free_extent_map(em);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 0c92af11f4f45e..8632380d2b9411 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -6421,9 +6421,7 @@ SetEARetry:
pSMB->InformationLevel =
cpu_to_le16(SMB_SET_FILE_EA);
- parm_data =
- (struct fealist *) (((char *) &pSMB->hdr.Protocol) +
- offset);
+ parm_data = (void *)pSMB + offsetof(struct smb_hdr, Protocol) + offset;
pSMB->ParameterOffset = cpu_to_le16(param_offset);
pSMB->DataOffset = cpu_to_le16(offset);
pSMB->SetupCount = 1;
diff --git a/fs/dcache.c b/fs/dcache.c
index 751a0d88f049b1..250c1222e30c6f 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1897,6 +1897,28 @@ struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode)
EXPORT_SYMBOL(d_instantiate_unique);
+/*
+ * This should be equivalent to d_instantiate() + unlock_new_inode(),
+ * with lockdep-related part of unlock_new_inode() done before
+ * anything else. Use that instead of open-coding d_instantiate()/
+ * unlock_new_inode() combinations.
+ */
+void d_instantiate_new(struct dentry *entry, struct inode *inode)
+{
+ BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
+ BUG_ON(!inode);
+ lockdep_annotate_inode_mutex_key(inode);
+ security_d_instantiate(entry, inode);
+ spin_lock(&inode->i_lock);
+ __d_instantiate(entry, inode);
+ WARN_ON(!(inode->i_state & I_NEW));
+ inode->i_state &= ~I_NEW;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_NEW);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(d_instantiate_new);
+
/**
* d_instantiate_no_diralias - instantiate a non-aliased dentry
* @entry: dentry to complete
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e2e47ba5d313a5..844d0c4da84fad 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -287,8 +287,7 @@ ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
iput(ecryptfs_inode);
goto out;
}
- unlock_new_inode(ecryptfs_inode);
- d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+ d_instantiate_new(ecryptfs_dentry, ecryptfs_inode);
out:
return rc;
}
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 0aa9bf6e6e53e2..f600c43f004721 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -1175,21 +1175,11 @@ do_indirects:
static void ext2_truncate_blocks(struct inode *inode, loff_t offset)
{
- /*
- * XXX: it seems like a bug here that we don't allow
- * IS_APPEND inode to have blocks-past-i_size trimmed off.
- * review and fix this.
- *
- * Also would be nice to be able to handle IO errors and such,
- * but that's probably too much to ask.
- */
if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)))
return;
if (ext2_inode_is_fast_symlink(inode))
return;
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
- return;
dax_sem_down_write(EXT2_I(inode));
__ext2_truncate_blocks(inode, offset);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 3267a80dbbe26f..da3d40ef166855 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -40,8 +40,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ext2_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -267,8 +266,7 @@ static int ext2_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
out:
return err;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 78c51ce913db01..c57a94f1c198c0 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -320,6 +320,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_grpblk_t offset;
ext4_grpblk_t next_zero_bit;
+ ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb);
ext4_fsblk_t blk;
ext4_fsblk_t group_first_block;
@@ -337,20 +338,25 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb,
/* check whether block bitmap block number is set */
blk = ext4_block_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+ !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode bitmap block number is set */
blk = ext4_inode_bitmap(sb, desc);
offset = blk - group_first_block;
- if (!ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+ !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data))
/* bad block bitmap */
return blk;
/* check whether the inode table block number is set */
blk = ext4_inode_table(sb, desc);
offset = blk - group_first_block;
+ if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit ||
+ EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit)
+ return blk;
next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
EXT4_B2C(sbi, offset + EXT4_SB(sb)->s_itb_per_group),
EXT4_B2C(sbi, offset));
@@ -416,6 +422,7 @@ struct buffer_head *
ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct buffer_head *bh;
ext4_fsblk_t bitmap_blk;
int err;
@@ -424,6 +431,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
if (!desc)
return ERR_PTR(-EFSCORRUPTED);
bitmap_blk = ext4_block_bitmap(sb, desc);
+ if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+ (bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
+ ext4_error(sb, "Invalid block bitmap block %llu in "
+ "block_group %u", bitmap_blk, block_group);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, "Cannot get buffer for block bitmap - "
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 403c4bae3e18f8..4705c21f9d0311 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5380,8 +5380,9 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
stop = le32_to_cpu(extent->ee_block);
/*
- * In case of left shift, Don't start shifting extents until we make
- * sure the hole is big enough to accommodate the shift.
+ * For left shifts, make sure the hole on the left is big enough to
+ * accommodate the shift. For right shifts, make sure the last extent
+ * won't be shifted beyond EXT_MAX_BLOCKS.
*/
if (SHIFT == SHIFT_LEFT) {
path = ext4_find_extent(inode, start - 1, &path,
@@ -5401,9 +5402,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
if ((start == ex_start && shift > ex_start) ||
(shift > start - ex_end)) {
- ext4_ext_drop_refs(path);
- kfree(path);
- return -EINVAL;
+ ret = -EINVAL;
+ goto out;
+ }
+ } else {
+ if (shift > EXT_MAX_BLOCKS -
+ (stop + ext4_ext_get_actual_len(extent))) {
+ ret = -EINVAL;
+ goto out;
}
}
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index e10c12f59c58e0..9fe55b7d4c2c73 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -119,6 +119,7 @@ static struct buffer_head *
ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
{
struct ext4_group_desc *desc;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
struct buffer_head *bh = NULL;
ext4_fsblk_t bitmap_blk;
int err;
@@ -128,6 +129,12 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
return ERR_PTR(-EFSCORRUPTED);
bitmap_blk = ext4_inode_bitmap(sb, desc);
+ if ((bitmap_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) ||
+ (bitmap_blk >= ext4_blocks_count(sbi->s_es))) {
+ ext4_error(sb, "Invalid inode bitmap blk %llu in "
+ "block_group %u", bitmap_blk, block_group);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
bh = sb_getblk(sb, bitmap_blk);
if (unlikely(!bh)) {
ext4_error(sb, "Cannot read inode bitmap - "
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 32960b3ecd4fb0..97472088d65a70 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2429,8 +2429,7 @@ static int ext4_add_nondir(handle_t *handle,
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
drop_nlink(inode);
@@ -2669,8 +2668,7 @@ out_clear_inode:
err = ext4_mark_inode_dirty(handle, dir);
if (err)
goto out_clear_inode;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
ext4_handle_sync(handle);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 98b2fc2678ff60..f6ccb21f286bf4 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -721,7 +721,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
if (!ret) {
map_bh(bh, inode->i_sb, map.m_pblk);
bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
- bh->b_size = map.m_len << inode->i_blkbits;
+ bh->b_size = (u64)map.m_len << inode->i_blkbits;
}
return ret;
}
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 484df6850747c8..e5553cd8fe4edd 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -150,8 +150,7 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
alloc_nid_done(sbi, ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -399,8 +398,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
err = page_symlink(inode, p_str, p_len);
err_out:
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
/*
* Let's flush symlink data in order to avoid broken symlink as much as
@@ -454,8 +452,7 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
@@ -499,8 +496,7 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
alloc_nid_done(sbi, inode->i_ino);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
if (IS_DIRSYNC(dir))
f2fs_sync_fs(sbi->sb, 1);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 0fe66787585213..cfb75dbb96f5ab 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1906,7 +1906,7 @@ void wb_workfn(struct work_struct *work)
}
if (!list_empty(&wb->work_list))
- mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ wb_wakeup(wb);
else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
wb_wakeup_delayed(wb);
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 6b35fc4860a038..1de16a5a5c4ee7 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -776,6 +776,7 @@ static void fscache_write_op(struct fscache_operation *_op)
_enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
+again:
spin_lock(&object->lock);
cookie = object->cookie;
@@ -816,10 +817,6 @@ static void fscache_write_op(struct fscache_operation *_op)
goto superseded;
page = results[0];
_debug("gang %d [%lx]", n, page->index);
- if (page->index >= op->store_limit) {
- fscache_stat(&fscache_n_store_pages_over_limit);
- goto superseded;
- }
radix_tree_tag_set(&cookie->stores, page->index,
FSCACHE_COOKIE_STORING_TAG);
@@ -829,6 +826,9 @@ static void fscache_write_op(struct fscache_operation *_op)
spin_unlock(&cookie->stores_lock);
spin_unlock(&object->lock);
+ if (page->index >= op->store_limit)
+ goto discard_page;
+
fscache_stat(&fscache_n_store_pages);
fscache_stat(&fscache_n_cop_write_page);
ret = object->cache->ops->write_page(op, page);
@@ -844,6 +844,11 @@ static void fscache_write_op(struct fscache_operation *_op)
_leave("");
return;
+discard_page:
+ fscache_stat(&fscache_n_store_pages_over_limit);
+ fscache_end_page_write(object, page);
+ goto again;
+
superseded:
/* this writer is going away and there aren't any more things to
* write */
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 1543aa1b2a9383..8744bd77382357 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -806,7 +806,7 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_alloc_parms ap = { .aflags = 0, };
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
- loff_t bytes, max_bytes, max_blks = UINT_MAX;
+ loff_t bytes, max_bytes, max_blks;
int error;
const loff_t pos = offset;
const loff_t count = len;
@@ -858,7 +858,8 @@ static long __gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t
return error;
/* ap.allowed tells us how many blocks quota will allow
* us to write. Check if this reduces max_blks */
- if (ap.allowed && ap.allowed < max_blks)
+ max_blks = UINT_MAX;
+ if (ap.allowed)
max_blks = ap.allowed;
error = gfs2_inplace_reserve(ip, &ap);
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index ad04b3acae2b9d..a81ed38d8442d1 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -43,6 +43,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip,
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
int ret;
+
+ ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
return 0;
ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 7302d96ae8bfd7..fa40e756c50137 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -585,6 +585,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
return 0;
out_put_hidden_dir:
+ cancel_delayed_work_sync(&sbi->sync_work);
iput(sbi->hidden_dir);
out_put_root:
dput(sb->s_root);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index a2e724053919b5..f3a31f55f37215 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -527,6 +527,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type,
*/
ret = start_this_handle(journal, handle, GFP_NOFS);
if (ret < 0) {
+ handle->h_journal = journal;
jbd2_journal_free_reserved(handle);
return ret;
}
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 30c4c9ebb693fa..e2731716969724 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -207,8 +207,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
__func__, inode->i_ino, inode->i_mode, inode->i_nlink,
f->inocache->pino_nlink, inode->i_mapping->nrpages);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -428,8 +427,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -573,8 +571,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
@@ -745,8 +742,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
mutex_unlock(&dir_f->sem);
jffs2_complete_reservation(c);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
fail:
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 2caf1682036dc1..85e2594fe95cfe 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -361,7 +361,6 @@ error_io:
ret = -EIO;
error:
mutex_unlock(&f->sem);
- jffs2_do_clear_inode(c, f);
iget_failed(inode);
return ERR_PTR(ret);
}
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 9d7551f5c32a9f..f217ae750adbe5 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -178,8 +178,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -313,8 +312,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1058,8 +1056,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out2:
@@ -1443,8 +1440,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
unlock_new_inode(ip);
iput(ip);
} else {
- unlock_new_inode(ip);
- d_instantiate(dentry, ip);
+ d_instantiate_new(dentry, ip);
}
out1:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0f397e62de5a9d..41c8ddbc80dc43 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1780,7 +1780,7 @@ static int nfs4_open_reclaim(struct nfs4_state_owner *sp, struct nfs4_state *sta
return ret;
}
-static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, int err)
+static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs4_state *state, const nfs4_stateid *stateid, struct file_lock *fl, int err)
{
switch (err) {
default:
@@ -1827,7 +1827,11 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
return -EAGAIN;
case -ENOMEM:
case -NFS4ERR_DENIED:
- /* kill_proc(fl->fl_pid, SIGLOST, 1); */
+ if (fl) {
+ struct nfs4_lock_state *lsp = fl->fl_u.nfs4_fl.owner;
+ if (lsp)
+ set_bit(NFS_LOCK_LOST, &lsp->ls_flags);
+ }
return 0;
}
return err;
@@ -1863,7 +1867,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
err = nfs4_open_recover_helper(opendata, FMODE_READ);
}
nfs4_opendata_put(opendata);
- return nfs4_handle_delegation_recall_error(server, state, stateid, err);
+ return nfs4_handle_delegation_recall_error(server, state, stateid, NULL, err);
}
static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
@@ -6157,7 +6161,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
if (err != 0)
return err;
err = _nfs4_do_setlk(state, F_SETLK, fl, NFS_LOCK_NEW);
- return nfs4_handle_delegation_recall_error(server, state, stateid, err);
+ return nfs4_handle_delegation_recall_error(server, state, stateid, fl, err);
}
struct nfs_release_lockowner_data {
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 83fba40396ae2b..44f5cea4969942 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1386,6 +1386,7 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_
struct inode *inode = state->inode;
struct nfs_inode *nfsi = NFS_I(inode);
struct file_lock *fl;
+ struct nfs4_lock_state *lsp;
int status = 0;
struct file_lock_context *flctx = inode->i_flctx;
struct list_head *list;
@@ -1426,7 +1427,9 @@ restart:
case -NFS4ERR_DENIED:
case -NFS4ERR_RECLAIM_BAD:
case -NFS4ERR_RECLAIM_CONFLICT:
- /* kill_proc(fl->fl_pid, SIGLOST, 1); */
+ lsp = fl->fl_u.nfs4_fl.owner;
+ if (lsp)
+ set_bit(NFS_LOCK_LOST, &lsp->ls_flags);
status = 0;
}
spin_lock(&flctx->flc_lock);
diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c
index 0fbd3ab1be222e..44a7bbbf92f803 100644
--- a/fs/nfs/nfs4sysctl.c
+++ b/fs/nfs/nfs4sysctl.c
@@ -31,7 +31,7 @@ static struct ctl_table nfs4_cb_sysctls[] = {
.data = &nfs_idmap_cache_timeout,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec,
},
{ }
};
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index c9a1a491aa9124..cd7f5b0abe842a 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -50,8 +50,7 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = nilfs_add_link(dentry, inode);
if (!err) {
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -246,8 +245,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
goto out_fail;
nilfs_mark_inode_dirty(inode);
- d_instantiate(dentry, inode);
- unlock_new_inode(inode);
+ d_instantiate_new(dentry, inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 164307b994052c..1e0d8da0d3cd65 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -314,7 +314,9 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
return ERR_PTR(ret);
}
+ down_read(&OCFS2_I(inode)->ip_xattr_sem);
acl = ocfs2_get_acl_nolock(inode, type, di_bh);
+ up_read(&OCFS2_I(inode)->ip_xattr_sem);
ocfs2_inode_unlock(inode, 0);
brelse(di_bh);
@@ -333,7 +335,9 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh)
if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
return 0;
+ down_read(&OCFS2_I(inode)->ip_xattr_sem);
acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh);
+ up_read(&OCFS2_I(inode)->ip_xattr_sem);
if (IS_ERR(acl) || !acl)
return PTR_ERR(acl);
ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode);
@@ -364,8 +368,10 @@ int ocfs2_init_acl(handle_t *handle,
if (!S_ISLNK(inode->i_mode)) {
if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ down_read(&OCFS2_I(dir)->ip_xattr_sem);
acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
dir_bh);
+ up_read(&OCFS2_I(dir)->ip_xattr_sem);
if (IS_ERR(acl))
return PTR_ERR(acl);
}
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ee7fe747cea44..c55a9c47ac1745 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -674,20 +674,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
spin_unlock(&dlm->spinlock);
}
-int dlm_shutting_down(struct dlm_ctxt *dlm)
-{
- int ret = 0;
-
- spin_lock(&dlm_domain_lock);
-
- if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
- ret = 1;
-
- spin_unlock(&dlm_domain_lock);
-
- return ret;
-}
-
void dlm_unregister_domain(struct dlm_ctxt *dlm)
{
int leave = 0;
diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h
index fd6122a38dbdf0..8a9281411c18ff 100644
--- a/fs/ocfs2/dlm/dlmdomain.h
+++ b/fs/ocfs2/dlm/dlmdomain.h
@@ -28,7 +28,30 @@
extern spinlock_t dlm_domain_lock;
extern struct list_head dlm_domains;
-int dlm_shutting_down(struct dlm_ctxt *dlm);
+static inline int dlm_joined(struct dlm_ctxt *dlm)
+{
+ int ret = 0;
+
+ spin_lock(&dlm_domain_lock);
+ if (dlm->dlm_state == DLM_CTXT_JOINED)
+ ret = 1;
+ spin_unlock(&dlm_domain_lock);
+
+ return ret;
+}
+
+static inline int dlm_shutting_down(struct dlm_ctxt *dlm)
+{
+ int ret = 0;
+
+ spin_lock(&dlm_domain_lock);
+ if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
+ ret = 1;
+ spin_unlock(&dlm_domain_lock);
+
+ return ret;
+}
+
void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
int node_num);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 4a338803e7e928..88149b4387c29b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1377,6 +1377,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
if (!dlm_grab(dlm))
return -EINVAL;
+ if (!dlm_joined(dlm)) {
+ mlog(ML_ERROR, "Domain %s not joined! "
+ "lockres %.*s, master %u\n",
+ dlm->name, mres->lockname_len,
+ mres->lockname, mres->master);
+ dlm_put(dlm);
+ return -EINVAL;
+ }
+
BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION)));
real_master = mres->master;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 13534f4fe5b51d..722eb5bc9b8f01 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -666,23 +666,24 @@ static int __ocfs2_journal_access(handle_t *handle,
/* we can safely remove this assertion after testing. */
if (!buffer_uptodate(bh)) {
mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n");
- mlog(ML_ERROR, "b_blocknr=%llu\n",
- (unsigned long long)bh->b_blocknr);
+ mlog(ML_ERROR, "b_blocknr=%llu, b_state=0x%lx\n",
+ (unsigned long long)bh->b_blocknr, bh->b_state);
lock_buffer(bh);
/*
- * A previous attempt to write this buffer head failed.
- * Nothing we can do but to retry the write and hope for
- * the best.
+ * A previous transaction with a couple of buffer heads fail
+ * to checkpoint, so all the bhs are marked as BH_Write_EIO.
+ * For current transaction, the bh is just among those error
+ * bhs which previous transaction handle. We can't just clear
+ * its BH_Write_EIO and reuse directly, since other bhs are
+ * not written to disk yet and that will cause metadata
+ * inconsistency. So we should set fs read-only to avoid
+ * further damage.
*/
if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) {
- clear_buffer_write_io_error(bh);
- set_buffer_uptodate(bh);
- }
-
- if (!buffer_uptodate(bh)) {
unlock_buffer(bh);
- return -EIO;
+ return ocfs2_error(osb->sb, "A previous attempt to "
+ "write this buffer head failed\n");
}
unlock_buffer(bh);
}
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 2de4c8a9340c26..4f5141350af865 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -477,9 +477,8 @@ static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb)
new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
if (!new) {
ocfs2_release_system_inodes(osb);
- status = -EINVAL;
+ status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL;
mlog_errno(status);
- /* FIXME: Should ERROR_RO_FS */
mlog(ML_ERROR, "Unable to load system inode %d, "
"possibly corrupt fs?", i);
goto bail;
@@ -508,7 +507,7 @@ static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb)
new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
if (!new) {
ocfs2_release_system_inodes(osb);
- status = -EINVAL;
+ status = ocfs2_is_soft_readonly(osb) ? -EROFS : -EINVAL;
mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n",
status, i, osb->slot_num);
goto bail;
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 877830b05e127c..4f0788232f2f9c 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -639,9 +639,11 @@ int ocfs2_calc_xattr_init(struct inode *dir,
si->value_len);
if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+ down_read(&OCFS2_I(dir)->ip_xattr_sem);
acl_len = ocfs2_xattr_get_nolock(dir, dir_bh,
OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT,
"", NULL, 0);
+ up_read(&OCFS2_I(dir)->ip_xattr_sem);
if (acl_len > 0) {
a_size = ocfs2_xattr_entry_real_size(0, acl_len);
if (S_ISDIR(mode))
diff --git a/fs/pipe.c b/fs/pipe.c
index 39eff9a672535f..1e7263bb837a6f 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -616,6 +616,9 @@ struct pipe_inode_info *alloc_pipe_info(void)
unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
struct user_struct *user = get_current_user();
+ if (pipe_bufs * PAGE_SIZE > pipe_max_size && !capable(CAP_SYS_RESOURCE))
+ pipe_bufs = pipe_max_size >> PAGE_SHIFT;
+
if (!too_many_pipe_buffers_hard(user)) {
if (too_many_pipe_buffers_soft(user))
pipe_bufs = 1;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index dd732400578e36..5f9cec2db6c3a0 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -94,6 +94,8 @@
#include "internal.h"
#include "fd.h"
+#include "../../lib/kstrtox.h"
+
/* NOTE:
* Implementing inode permission operations in /proc is almost
* certainly an error. Permission checks need to happen during
@@ -953,6 +955,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
unsigned long src = *ppos;
int ret = 0;
struct mm_struct *mm = file->private_data;
+ unsigned long env_start, env_end;
/* Ensure the process spawned far enough to have an environment. */
if (!mm || !mm->env_end)
@@ -965,19 +968,25 @@ static ssize_t environ_read(struct file *file, char __user *buf,
ret = 0;
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+
+ down_read(&mm->mmap_sem);
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
while (count > 0) {
size_t this_len, max_len;
int retval;
- if (src >= (mm->env_end - mm->env_start))
+ if (src >= (env_end - env_start))
break;
- this_len = mm->env_end - (mm->env_start + src);
+ this_len = env_end - (env_start + src);
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (mm->env_start + src),
+ retval = access_remote_vm(mm, (env_start + src),
page, this_len, 0);
if (retval <= 0) {
@@ -1829,8 +1838,33 @@ end_instantiate:
static int dname_to_vma_addr(struct dentry *dentry,
unsigned long *start, unsigned long *end)
{
- if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2)
+ const char *str = dentry->d_name.name;
+ unsigned long long sval, eval;
+ unsigned int len;
+
+ len = _parse_integer(str, 16, &sval);
+ if (len & KSTRTOX_OVERFLOW)
return -EINVAL;
+ if (sval != (unsigned long)sval)
+ return -EINVAL;
+ str += len;
+
+ if (*str != '-')
+ return -EINVAL;
+ str++;
+
+ len = _parse_integer(str, 16, &eval);
+ if (len & KSTRTOX_OVERFLOW)
+ return -EINVAL;
+ if (eval != (unsigned long)eval)
+ return -EINVAL;
+ str += len;
+
+ if (*str != '\0')
+ return -EINVAL;
+
+ *start = sval;
+ *end = eval;
return 0;
}
@@ -3076,6 +3110,44 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
}
/*
+ * proc_tid_comm_permission is a special permission function exclusively
+ * used for the node /proc/<pid>/task/<tid>/comm.
+ * It bypasses generic permission checks in the case where a task of the same
+ * task group attempts to access the node.
+ * The rationale behind this is that glibc and bionic access this node for
+ * cross thread naming (pthread_set/getname_np(!self)). However, if
+ * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0,
+ * which locks out the cross thread naming implementation.
+ * This function makes sure that the node is always accessible for members of
+ * same thread group.
+ */
+static int proc_tid_comm_permission(struct inode *inode, int mask)
+{
+ bool is_same_tgroup;
+ struct task_struct *task;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
+ is_same_tgroup = same_thread_group(current, task);
+ put_task_struct(task);
+
+ if (likely(is_same_tgroup && !(mask & MAY_EXEC))) {
+ /* This file (/proc/<pid>/task/<tid>/comm) can always be
+ * read or written by the members of the corresponding
+ * thread group.
+ */
+ return 0;
+ }
+
+ return generic_permission(inode, mask);
+}
+
+static const struct inode_operations proc_tid_comm_inode_operations = {
+ .permission = proc_tid_comm_permission,
+};
+
+/*
* Tasks
*/
static const struct pid_entry tid_base_stuff[] = {
@@ -3093,7 +3165,9 @@ static const struct pid_entry tid_base_stuff[] = {
#ifdef CONFIG_SCHED_DEBUG
REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations),
#endif
- REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations),
+ NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
+ &proc_tid_comm_inode_operations,
+ &proc_pid_set_comm_operations, {}),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 9155a5a0d3b9de..df4661abadc40f 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -57,11 +57,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
- *
- * Free memory cannot be taken below the low watermark, before the
- * system starts swapping.
*/
- available = i.freeram - wmark_low;
+ available = i.freeram - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 4dbe1e2daeca6e..5e1054f028afd4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -654,7 +654,10 @@ static bool proc_sys_link_fill_cache(struct file *file,
struct ctl_table *table)
{
bool ret = true;
+
head = sysctl_head_grab(head);
+ if (IS_ERR(head))
+ return false;
if (S_ISLNK(table->mode)) {
/* It is not an error if we can not follow the link ignore it */
diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c
index 3ebc70167e416f..eb611bdd472546 100644
--- a/fs/reiserfs/namei.c
+++ b/fs/reiserfs/namei.c
@@ -687,8 +687,7 @@ static int reiserfs_create(struct inode *dir, struct dentry *dentry, umode_t mod
reiserfs_update_inode_transaction(inode);
reiserfs_update_inode_transaction(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -771,8 +770,7 @@ static int reiserfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
@@ -871,8 +869,7 @@ static int reiserfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
/* the above add_entry did not update dir's stat data */
reiserfs_update_sd(&th, dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(dir->i_sb);
@@ -1186,8 +1183,7 @@ static int reiserfs_symlink(struct inode *parent_dir,
goto out_failed;
}
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
retval = journal_end(&th);
out_failed:
reiserfs_write_unlock(parent_dir->i_sb);
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c97b5a8d1e24cf..f34c545f4e5496 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -611,8 +611,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
@@ -722,8 +721,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
inc_nlink(dir);
dir->i_ctime = dir->i_mtime = current_fs_time(dir->i_sb);
mark_inode_dirty(dir);
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
if (fibh.sbh != fibh.ebh)
brelse(fibh.ebh);
brelse(fibh.sbh);
diff --git a/fs/udf/super.c b/fs/udf/super.c
index ee09c97f3ab29d..159977ec8e548b 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -2073,8 +2073,9 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
bool lvid_open = false;
uopt.flags = (1 << UDF_FLAG_USE_AD_IN_ICB) | (1 << UDF_FLAG_STRICT);
- uopt.uid = INVALID_UID;
- uopt.gid = INVALID_GID;
+ /* By default we'll use overflow[ug]id when UDF inode [ug]id == -1 */
+ uopt.uid = make_kuid(current_user_ns(), overflowuid);
+ uopt.gid = make_kgid(current_user_ns(), overflowgid);
uopt.umask = 0;
uopt.fmode = UDF_INVALID_MODE;
uopt.dmode = UDF_INVALID_MODE;
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index 47966554317c92..2ec7689c25cf6f 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -38,8 +38,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
{
int err = ufs_add_link(dentry, inode);
if (!err) {
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
}
inode_dec_link_count(inode);
@@ -191,8 +190,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
if (err)
goto out_fail;
- unlock_new_inode(inode);
- d_instantiate(dentry, inode);
+ d_instantiate_new(dentry, inode);
return 0;
out_fail:
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index e1e7fe3b5424c8..b663b756f55291 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1924,6 +1924,93 @@ xfs_alloc_space_available(
}
/*
+ * Check the agfl fields of the agf for inconsistency or corruption. The purpose
+ * is to detect an agfl header padding mismatch between current and early v5
+ * kernels. This problem manifests as a 1-slot size difference between the
+ * on-disk flcount and the active [first, last] range of a wrapped agfl. This
+ * may also catch variants of agfl count corruption unrelated to padding. Either
+ * way, we'll reset the agfl and warn the user.
+ *
+ * Return true if a reset is required before the agfl can be used, false
+ * otherwise.
+ */
+static bool
+xfs_agfl_needs_reset(
+ struct xfs_mount *mp,
+ struct xfs_agf *agf)
+{
+ uint32_t f = be32_to_cpu(agf->agf_flfirst);
+ uint32_t l = be32_to_cpu(agf->agf_fllast);
+ uint32_t c = be32_to_cpu(agf->agf_flcount);
+ int agfl_size = XFS_AGFL_SIZE(mp);
+ int active;
+
+ /* no agfl header on v4 supers */
+ if (!xfs_sb_version_hascrc(&mp->m_sb))
+ return false;
+
+ /*
+ * The agf read verifier catches severe corruption of these fields.
+ * Repeat some sanity checks to cover a packed -> unpacked mismatch if
+ * the verifier allows it.
+ */
+ if (f >= agfl_size || l >= agfl_size)
+ return true;
+ if (c > agfl_size)
+ return true;
+
+ /*
+ * Check consistency between the on-disk count and the active range. An
+ * agfl padding mismatch manifests as an inconsistent flcount.
+ */
+ if (c && l >= f)
+ active = l - f + 1;
+ else if (c)
+ active = agfl_size - f + l + 1;
+ else
+ active = 0;
+
+ return active != c;
+}
+
+/*
+ * Reset the agfl to an empty state. Ignore/drop any existing blocks since the
+ * agfl content cannot be trusted. Warn the user that a repair is required to
+ * recover leaked blocks.
+ *
+ * The purpose of this mechanism is to handle filesystems affected by the agfl
+ * header padding mismatch problem. A reset keeps the filesystem online with a
+ * relatively minor free space accounting inconsistency rather than suffer the
+ * inevitable crash from use of an invalid agfl block.
+ */
+static void
+xfs_agfl_reset(
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ struct xfs_perag *pag)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp);
+
+ ASSERT(pag->pagf_agflreset);
+ trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_);
+
+ xfs_warn(mp,
+ "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
+ "Please unmount and run xfs_repair.",
+ pag->pag_agno, pag->pagf_flcount);
+
+ agf->agf_flfirst = 0;
+ agf->agf_fllast = cpu_to_be32(XFS_AGFL_SIZE(mp) - 1);
+ agf->agf_flcount = 0;
+ xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLLAST |
+ XFS_AGF_FLCOUNT);
+
+ pag->pagf_flcount = 0;
+ pag->pagf_agflreset = false;
+}
+
+/*
* Decide whether to use this allocation group for this allocation.
* If so, fix up the btree freelist's size.
*/
@@ -1983,6 +2070,10 @@ xfs_alloc_fix_freelist(
}
}
+ /* reset a padding mismatched agfl before final free space check */
+ if (pag->pagf_agflreset)
+ xfs_agfl_reset(tp, agbp, pag);
+
/* If there isn't enough total space or single-extent, reject it. */
need = xfs_alloc_min_freelist(mp, pag);
if (!xfs_alloc_space_available(args, need, flags))
@@ -2121,6 +2212,7 @@ xfs_alloc_get_freelist(
agf->agf_flfirst = 0;
pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+ ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, -1);
xfs_trans_agflist_delta(tp, -1);
pag->pagf_flcount--;
@@ -2226,6 +2318,7 @@ xfs_alloc_put_freelist(
agf->agf_fllast = 0;
pag = xfs_perag_get(mp, be32_to_cpu(agf->agf_seqno));
+ ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, 1);
xfs_trans_agflist_delta(tp, 1);
pag->pagf_flcount++;
@@ -2417,6 +2510,7 @@ xfs_alloc_read_agf(
pag->pagb_count = 0;
pag->pagb_tree = RB_ROOT;
pag->pagf_init = 1;
+ pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
}
#ifdef DEBUG
else if (!XFS_FORCED_SHUTDOWN(mp)) {
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index f949818fa1c76d..fb9636cc927cfe 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -130,9 +130,6 @@ xfs_attr_get(
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
return -EIO;
- if (!xfs_inode_hasattr(ip))
- return -ENOATTR;
-
error = xfs_attr_args_init(&args, ip, name, flags);
if (error)
return error;
@@ -417,9 +414,6 @@ xfs_attr_remove(
if (XFS_FORCED_SHUTDOWN(dp->i_mount))
return -EIO;
- if (!xfs_inode_hasattr(dp))
- return -ENOATTR;
-
error = xfs_attr_args_init(&args, dp, name, flags);
if (error)
return error;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index e85a9519a5aee7..64ad05cb831af2 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -50,19 +50,19 @@ xfs_trim_extents(
pag = xfs_perag_get(mp, agno);
- error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
- if (error || !agbp)
- goto out_put_perag;
-
- cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
-
/*
* Force out the log. This means any transactions that might have freed
- * space before we took the AGF buffer lock are now on disk, and the
+ * space before we take the AGF buffer lock are now on disk, and the
* volatile disk cache is flushed.
*/
xfs_log_force(mp, XFS_LOG_SYNC);
+ error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+ if (error || !agbp)
+ goto out_put_perag;
+
+ cur = xfs_allocbt_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_CNT);
+
/*
* Look up the longest btree in the AGF and start with it.
*/
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 3dd47307363fa8..e917aec4babe49 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -969,22 +969,26 @@ xfs_file_fallocate(
if (error)
goto out_unlock;
} else if (mode & FALLOC_FL_INSERT_RANGE) {
- unsigned int blksize_mask = i_blocksize(inode) - 1;
+ unsigned int blksize_mask = i_blocksize(inode) - 1;
+ loff_t isize = i_size_read(inode);
- new_size = i_size_read(inode) + len;
if (offset & blksize_mask || len & blksize_mask) {
error = -EINVAL;
goto out_unlock;
}
- /* check the new inode size does not wrap through zero */
- if (new_size > inode->i_sb->s_maxbytes) {
+ /*
+ * New inode size must not exceed ->s_maxbytes, accounting for
+ * possible signed overflow.
+ */
+ if (inode->i_sb->s_maxbytes - isize < len) {
error = -EFBIG;
goto out_unlock;
}
+ new_size = isize + len;
/* Offset should be less than i_size */
- if (offset >= i_size_read(inode)) {
+ if (offset >= isize) {
error = -EINVAL;
goto out_unlock;
}
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f52c72a1a06f28..73b725f965ebc7 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3323,8 +3323,6 @@ maybe_sleep:
*/
if (iclog->ic_state & XLOG_STATE_IOERROR)
return -EIO;
- if (log_flushed)
- *log_flushed = 1;
} else {
no_sleep:
@@ -3432,8 +3430,6 @@ try_again:
xlog_wait(&iclog->ic_prev->ic_write_wait,
&log->l_icloglock);
- if (log_flushed)
- *log_flushed = 1;
already_slept = 1;
goto try_again;
}
@@ -3467,9 +3463,6 @@ try_again:
*/
if (iclog->ic_state & XLOG_STATE_IOERROR)
return -EIO;
-
- if (log_flushed)
- *log_flushed = 1;
} else { /* just return */
spin_unlock(&log->l_icloglock);
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b57098481c10a2..ae3e52749f20eb 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -278,6 +278,7 @@ typedef struct xfs_perag {
char pagi_inodeok; /* The agi is ok for inodes */
__uint8_t pagf_levels[XFS_BTNUM_AGF];
/* # of levels in bno & cnt btree */
+ bool pagf_agflreset; /* agfl requires reset before use */
__uint32_t pagf_flcount; /* count of blocks in freelist */
xfs_extlen_t pagf_freeblks; /* total free blocks */
xfs_extlen_t pagf_longest; /* longest free space */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 877079eb0f8f0e..cc6fa64821d2d5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1485,7 +1485,7 @@ TRACE_EVENT(xfs_trans_commit_lsn,
__entry->lsn)
);
-TRACE_EVENT(xfs_agf,
+DECLARE_EVENT_CLASS(xfs_agf_class,
TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
unsigned long caller_ip),
TP_ARGS(mp, agf, flags, caller_ip),
@@ -1541,6 +1541,13 @@ TRACE_EVENT(xfs_agf,
__entry->longest,
(void *)__entry->caller_ip)
);
+#define DEFINE_AGF_EVENT(name) \
+DEFINE_EVENT(xfs_agf_class, name, \
+ TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, \
+ unsigned long caller_ip), \
+ TP_ARGS(mp, agf, flags, caller_ip))
+DEFINE_AGF_EVENT(xfs_agf);
+DEFINE_AGF_EVENT(xfs_agfl_reset);
TRACE_EVENT(xfs_free_extent,
TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,