summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/send.c5
-rw-r--r--fs/cifs/dir.c5
-rw-r--r--fs/ecryptfs/ecryptfs_kernel.h25
-rw-r--r--fs/ecryptfs/keystore.c9
-rw-r--r--fs/ext4/inode.c2
-rw-r--r--fs/ext4/mballoc.c6
-rw-r--r--fs/ext4/super.c4
-rw-r--r--fs/ext4/xattr.c19
-rw-r--r--fs/fscache/object-list.c7
-rw-r--r--fs/fuse/dir.c3
-rw-r--r--fs/ocfs2/alloc.c24
-rw-r--r--fs/ocfs2/dlmglue.c105
-rw-r--r--fs/ocfs2/dlmglue.h18
-rw-r--r--fs/ocfs2/ocfs2.h1
14 files changed, 199 insertions, 34 deletions
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 3cc2d1dfd7bf..fc2472ef5011 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1640,6 +1640,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
{
int ret;
+ if (ino == BTRFS_FIRST_FREE_OBJECTID)
+ return 1;
+
ret = get_cur_inode_state(sctx, ino, gen);
if (ret < 0)
goto out;
@@ -1825,7 +1828,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
* not delted and then re-created, if it was then we have no overwrite
* and we can just unlink this entry.
*/
- if (sctx->parent_root) {
+ if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
NULL, NULL, NULL);
if (ret < 0 && ret != -ENOENT)
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 6fe4526b5209..6dc46b6e6cb5 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -193,7 +193,8 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon)
struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
int i;
- if (unlikely(direntry->d_name.len >
+ if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength &&
+ direntry->d_name.len >
le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength)))
return -ENAMETOOLONG;
@@ -509,7 +510,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
rc = check_name(direntry, tcon);
if (rc)
- goto out_free_xid;
+ goto out;
server = tcon->ses->server;
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 90d1882b306f..4682bef34bb6 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -84,11 +84,16 @@ struct ecryptfs_page_crypt_context {
static inline struct ecryptfs_auth_tok *
ecryptfs_get_encrypted_key_payload_data(struct key *key)
{
- if (key->type == &key_type_encrypted)
- return (struct ecryptfs_auth_tok *)
- (&((struct encrypted_key_payload *)key->payload.data)->payload_data);
- else
+ struct encrypted_key_payload *payload;
+
+ if (key->type != &key_type_encrypted)
return NULL;
+
+ payload = key->payload.data;
+ if (!payload)
+ return ERR_PTR(-EKEYREVOKED);
+
+ return (struct ecryptfs_auth_tok *)payload->payload_data;
}
static inline struct key *ecryptfs_get_encrypted_key(char *sig)
@@ -114,13 +119,17 @@ static inline struct ecryptfs_auth_tok *
ecryptfs_get_key_payload_data(struct key *key)
{
struct ecryptfs_auth_tok *auth_tok;
+ struct user_key_payload *ukp;
auth_tok = ecryptfs_get_encrypted_key_payload_data(key);
- if (!auth_tok)
- return (struct ecryptfs_auth_tok *)
- (((struct user_key_payload *)key->payload.data)->data);
- else
+ if (auth_tok)
return auth_tok;
+
+ ukp = key->payload.data;
+ if (!ukp)
+ return ERR_PTR(-EKEYREVOKED);
+
+ return (struct ecryptfs_auth_tok *)ukp->data;
}
#define ECRYPTFS_MAX_KEYSET_SIZE 1024
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index 635e8e16a5b7..5924e279733f 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -458,7 +458,8 @@ out:
* @auth_tok_key: key containing the authentication token
* @auth_tok: authentication token
*
- * Returns zero on valid auth tok; -EINVAL otherwise
+ * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or
+ * -EKEYREVOKED if the key was revoked before we acquired its semaphore.
*/
static int
ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key,
@@ -467,6 +468,12 @@ ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key,
int rc = 0;
(*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key);
+ if (IS_ERR(*auth_tok)) {
+ rc = PTR_ERR(*auth_tok);
+ *auth_tok = NULL;
+ goto out;
+ }
+
if (ecryptfs_verify_version((*auth_tok)->version)) {
printk(KERN_ERR "Data structure version mismatch. Userspace "
"tools must match eCryptfs kernel module with major "
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ea8493d7bbe8..6b3482c74679 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5085,8 +5085,6 @@ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
sbi->s_want_extra_isize,
iloc, handle);
if (ret) {
- ext4_set_inode_state(inode,
- EXT4_STATE_NO_EXPAND);
if (mnt_count !=
le16_to_cpu(sbi->s_es->s_mnt_count)) {
ext4_warning(inode->i_sb,
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 2309de2a5917..2fcb8ba4b06c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2113,8 +2113,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
* We search using buddy data only if the order of the request
* is greater than equal to the sbi_s_mb_order2_reqs
* You can tune it via /sys/fs/ext4/<partition>/mb_order2_req
+ * We also support searching for power-of-two requests only for
+ * requests upto maximum buddy size we have constructed.
*/
- if (i >= sbi->s_mb_order2_reqs) {
+ if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) {
/*
* This should tell if fe_len is exactly power of 2
*/
@@ -2176,7 +2178,7 @@ repeat:
}
ac->ac_groups_scanned++;
- if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2)
+ if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 && sbi->s_stripe &&
!(ac->ac_g_ex.fe_len % sbi->s_stripe))
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3ea5c300d84c..8c1d2b6c7c84 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2460,9 +2460,9 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
ret = sbi->s_stripe;
- else if (stripe_width <= sbi->s_blocks_per_group)
+ else if (stripe_width && stripe_width <= sbi->s_blocks_per_group)
ret = stripe_width;
- else if (stride <= sbi->s_blocks_per_group)
+ else if (stride && stride <= sbi->s_blocks_per_group)
ret = stride;
else
ret = 0;
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index c71329f05b26..c57c83806fb9 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -1291,11 +1291,13 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
down_write(&EXT4_I(inode)->xattr_sem);
+ /*
+ * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
+ */
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
- if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
- up_write(&EXT4_I(inode)->xattr_sem);
- return 0;
- }
+ if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+ goto out;
header = IHDR(inode, raw_inode);
entry = IFIRST(header);
@@ -1324,8 +1326,7 @@ retry:
(void *)header, total_ino,
inode->i_sb->s_blocksize);
EXT4_I(inode)->i_extra_isize = new_extra_isize;
- error = 0;
- goto cleanup;
+ goto out;
}
/*
@@ -1485,6 +1486,8 @@ retry:
kfree(bs);
}
brelse(bh);
+out:
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
up_write(&EXT4_I(inode)->xattr_sem);
return 0;
@@ -1496,6 +1499,10 @@ cleanup:
kfree(is);
kfree(bs);
brelse(bh);
+ /*
+ * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
+ * size expansion failed.
+ */
up_write(&EXT4_I(inode)->xattr_sem);
return error;
}
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 51dde817e1f2..11cf71ac1cb5 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -330,6 +330,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
rcu_read_lock();
confkey = key->payload.data;
+ if (!confkey) {
+ /* key was revoked */
+ rcu_read_unlock();
+ key_put(key);
+ goto no_config;
+ }
+
buf = confkey->data;
for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b555c4f6cbc0..6a9b03adddd7 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1416,7 +1416,8 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file,
*/
over = !dir_emit(ctx, dirent->name, dirent->namelen,
dirent->ino, dirent->type);
- ctx->pos = dirent->off;
+ if (!over)
+ ctx->pos = dirent->off;
}
buf += reclen;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index a93bf9892256..d9db90446c9d 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7235,13 +7235,24 @@ out:
static int ocfs2_trim_extent(struct super_block *sb,
struct ocfs2_group_desc *gd,
- u32 start, u32 count)
+ u64 group, u32 start, u32 count)
{
u64 discard, bcount;
+ struct ocfs2_super *osb = OCFS2_SB(sb);
bcount = ocfs2_clusters_to_blocks(sb, count);
- discard = le64_to_cpu(gd->bg_blkno) +
- ocfs2_clusters_to_blocks(sb, start);
+ discard = ocfs2_clusters_to_blocks(sb, start);
+
+ /*
+ * For the first cluster group, the gd->bg_blkno is not at the start
+ * of the group, but at an offset from the start. If we add it while
+ * calculating discard for first group, we will wrongly start fstrim a
+ * few blocks after the desried start block and the range can cross
+ * over into the next cluster group. So, add it only if this is not
+ * the first cluster group.
+ */
+ if (group != osb->first_cluster_group_blkno)
+ discard += le64_to_cpu(gd->bg_blkno);
trace_ocfs2_trim_extent(sb, (unsigned long long)discard, bcount);
@@ -7249,7 +7260,7 @@ static int ocfs2_trim_extent(struct super_block *sb,
}
static int ocfs2_trim_group(struct super_block *sb,
- struct ocfs2_group_desc *gd,
+ struct ocfs2_group_desc *gd, u64 group,
u32 start, u32 max, u32 minbits)
{
int ret = 0, count = 0, next;
@@ -7268,7 +7279,7 @@ static int ocfs2_trim_group(struct super_block *sb,
next = ocfs2_find_next_bit(bitmap, max, start);
if ((next - start) >= minbits) {
- ret = ocfs2_trim_extent(sb, gd,
+ ret = ocfs2_trim_extent(sb, gd, group,
start, next - start);
if (ret < 0) {
mlog_errno(ret);
@@ -7366,7 +7377,8 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
}
gd = (struct ocfs2_group_desc *)gd_bh->b_data;
- cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen);
+ cnt = ocfs2_trim_group(sb, gd, group,
+ first_bit, last_bit, minlen);
brelse(gd_bh);
gd_bh = NULL;
if (cnt < 0) {
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 12fe56b2e870..2402353f290c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -531,6 +531,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
init_waitqueue_head(&res->l_event);
INIT_LIST_HEAD(&res->l_blocked_list);
INIT_LIST_HEAD(&res->l_mask_waiters);
+ INIT_LIST_HEAD(&res->l_holders);
}
void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
@@ -748,6 +749,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
res->l_flags = 0UL;
}
+/*
+ * Keep a list of processes who have interest in a lockres.
+ * Note: this is now only uesed for check recursive cluster locking.
+ */
+static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
+ struct ocfs2_lock_holder *oh)
+{
+ INIT_LIST_HEAD(&oh->oh_list);
+ oh->oh_owner_pid = get_pid(task_pid(current));
+
+ spin_lock(&lockres->l_lock);
+ list_add_tail(&oh->oh_list, &lockres->l_holders);
+ spin_unlock(&lockres->l_lock);
+}
+
+static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
+ struct ocfs2_lock_holder *oh)
+{
+ spin_lock(&lockres->l_lock);
+ list_del(&oh->oh_list);
+ spin_unlock(&lockres->l_lock);
+
+ put_pid(oh->oh_owner_pid);
+}
+
+static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres)
+{
+ struct ocfs2_lock_holder *oh;
+ struct pid *pid;
+
+ /* look in the list of holders for one with the current task as owner */
+ spin_lock(&lockres->l_lock);
+ pid = task_pid(current);
+ list_for_each_entry(oh, &lockres->l_holders, oh_list) {
+ if (oh->oh_owner_pid == pid) {
+ spin_unlock(&lockres->l_lock);
+ return 1;
+ }
+ }
+ spin_unlock(&lockres->l_lock);
+
+ return 0;
+}
+
static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres,
int level)
{
@@ -2313,8 +2358,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
goto getbh;
}
- if (ocfs2_mount_local(osb))
- goto local;
+ if ((arg_flags & OCFS2_META_LOCK_GETBH) ||
+ ocfs2_mount_local(osb))
+ goto update;
if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
ocfs2_wait_for_recovery(osb);
@@ -2343,7 +2389,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
ocfs2_wait_for_recovery(osb);
-local:
+update:
/*
* We only see this flag if we're being called from
* ocfs2_read_locked_inode(). It means we're locking an inode
@@ -2485,6 +2531,59 @@ void ocfs2_inode_unlock(struct inode *inode,
ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
}
+/*
+ * This _tracker variantes are introduced to deal with the recursive cluster
+ * locking issue. The idea is to keep track of a lock holder on the stack of
+ * the current process. If there's a lock holder on the stack, we know the
+ * task context is already protected by cluster locking. Currently, they're
+ * used in some VFS entry routines.
+ *
+ * return < 0 on error, return == 0 if there's no lock holder on the stack
+ * before this call, return == 1 if this call would be a recursive locking.
+ */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+ struct buffer_head **ret_bh,
+ int ex,
+ struct ocfs2_lock_holder *oh)
+{
+ int status;
+ int arg_flags = 0, has_locked;
+ struct ocfs2_lock_res *lockres;
+
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ has_locked = ocfs2_is_locked_by_me(lockres);
+ /* Just get buffer head if the cluster lock has been taken */
+ if (has_locked)
+ arg_flags = OCFS2_META_LOCK_GETBH;
+
+ if (likely(!has_locked || ret_bh)) {
+ status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags);
+ if (status < 0) {
+ if (status != -ENOENT)
+ mlog_errno(status);
+ return status;
+ }
+ }
+ if (!has_locked)
+ ocfs2_add_holder(lockres, oh);
+
+ return has_locked;
+}
+
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+ int ex,
+ struct ocfs2_lock_holder *oh,
+ int had_lock)
+{
+ struct ocfs2_lock_res *lockres;
+
+ lockres = &OCFS2_I(inode)->ip_inode_lockres;
+ if (!had_lock) {
+ ocfs2_remove_holder(lockres, oh);
+ ocfs2_inode_unlock(inode, ex);
+ }
+}
+
int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
{
struct ocfs2_lock_res *lockres;
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index d293a22c32c5..a7fc18ba0dc1 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb {
__be32 lvb_os_seqno;
};
+struct ocfs2_lock_holder {
+ struct list_head oh_list;
+ struct pid *oh_owner_pid;
+};
+
/* ocfs2_inode_lock_full() 'arg_flags' flags */
/* don't wait on recovery. */
#define OCFS2_META_LOCK_RECOVERY (0x01)
@@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb {
#define OCFS2_META_LOCK_NOQUEUE (0x02)
/* don't block waiting for the downconvert thread, instead return -EAGAIN */
#define OCFS2_LOCK_NONBLOCK (0x04)
+/* just get back disk inode bh if we've got cluster lock. */
+#define OCFS2_META_LOCK_GETBH (0x08)
/* Locking subclasses of inode cluster lock */
enum {
@@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
/* To set the locking protocol on module initialization */
void ocfs2_set_locking_protocol(void);
+
+/* The _tracker pair is used to avoid cluster recursive locking */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+ struct buffer_head **ret_bh,
+ int ex,
+ struct ocfs2_lock_holder *oh);
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+ int ex,
+ struct ocfs2_lock_holder *oh,
+ int had_lock);
+
#endif /* DLMGLUE_H */
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index bbec539230fd..6a90e364f648 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -166,6 +166,7 @@ struct ocfs2_lock_res {
struct list_head l_blocked_list;
struct list_head l_mask_waiters;
+ struct list_head l_holders;
unsigned long l_flags;
char l_name[OCFS2_LOCK_ID_MAX_LEN];
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-19 03:28:30 +0000