summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/fuse/dev.c16
-rw-r--r--fs/fuse/file.c4
-rw-r--r--fs/gfs2/bmap.c54
-rw-r--r--fs/gfs2/rgrp.c3
-rw-r--r--fs/inode.c7
-rw-r--r--fs/namespace.c6
-rw-r--r--fs/nfs/callback_proc.c4
-rw-r--r--fs/nfs/delegation.c11
-rw-r--r--fs/nfs/nfs4state.c10
-rw-r--r--fs/nfsd/nfs4proc.c3
-rw-r--r--fs/notify/fanotify/fanotify.c10
-rw-r--r--fs/notify/fsnotify.c7
-rw-r--r--fs/ocfs2/aops.c12
-rw-r--r--fs/ocfs2/cluster/masklog.h9
14 files changed, 101 insertions, 55 deletions
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index ae813e609932..a5e516a40e7a 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -165,9 +165,13 @@ static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background)
static void fuse_drop_waiting(struct fuse_conn *fc)
{
- if (fc->connected) {
- atomic_dec(&fc->num_waiting);
- } else if (atomic_dec_and_test(&fc->num_waiting)) {
+ /*
+ * lockess check of fc->connected is okay, because atomic_dec_and_test()
+ * provides a memory barrier mached with the one in fuse_wait_aborted()
+ * to ensure no wake-up is missed.
+ */
+ if (atomic_dec_and_test(&fc->num_waiting) &&
+ !READ_ONCE(fc->connected)) {
/* wake up aborters */
wake_up_all(&fc->blocked_waitq);
}
@@ -1768,8 +1772,10 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode,
req->in.args[1].size = total_len;
err = fuse_request_send_notify_reply(fc, req, outarg->notify_unique);
- if (err)
+ if (err) {
fuse_retrieve_end(fc, req);
+ fuse_put_request(fc, req);
+ }
return err;
}
@@ -2219,6 +2225,8 @@ EXPORT_SYMBOL_GPL(fuse_abort_conn);
void fuse_wait_aborted(struct fuse_conn *fc)
{
+ /* matches implicit memory barrier in fuse_drop_waiting() */
+ smp_mb();
wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0);
}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index cc2121b37bf5..b52f9baaa3e7 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2924,10 +2924,12 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
}
if (io->async) {
+ bool blocking = io->blocking;
+
fuse_aio_complete(io, ret < 0 ? ret : 0, -1);
/* we have a non-extending, async request, so return */
- if (!io->blocking)
+ if (!blocking)
return -EIOCBQUEUED;
wait_for_completion(&wait);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index a683d9b27d76..9a4a15d646eb 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -826,7 +826,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
ret = gfs2_meta_inode_buffer(ip, &dibh);
if (ret)
goto unlock;
- iomap->private = dibh;
+ mp->mp_bh[0] = dibh;
if (gfs2_is_stuffed(ip)) {
if (flags & IOMAP_WRITE) {
@@ -863,9 +863,6 @@ unstuff:
len = lblock_stop - lblock + 1;
iomap->length = len << inode->i_blkbits;
- get_bh(dibh);
- mp->mp_bh[0] = dibh;
-
height = ip->i_height;
while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
height++;
@@ -898,8 +895,6 @@ out:
iomap->bdev = inode->i_sb->s_bdev;
unlock:
up_read(&ip->i_rw_mutex);
- if (ret && dibh)
- brelse(dibh);
return ret;
do_alloc:
@@ -980,9 +975,9 @@ static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
loff_t length, unsigned flags,
- struct iomap *iomap)
+ struct iomap *iomap,
+ struct metapath *mp)
{
- struct metapath mp = { .mp_aheight = 1, };
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
@@ -996,9 +991,9 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
unstuff = gfs2_is_stuffed(ip) &&
pos + length > gfs2_max_stuffed_size(ip);
- ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+ ret = gfs2_iomap_get(inode, pos, length, flags, iomap, mp);
if (ret)
- goto out_release;
+ goto out_unlock;
alloc_required = unstuff || iomap->type == IOMAP_HOLE;
@@ -1013,7 +1008,7 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
ret = gfs2_quota_lock_check(ip, &ap);
if (ret)
- goto out_release;
+ goto out_unlock;
ret = gfs2_inplace_reserve(ip, &ap);
if (ret)
@@ -1038,17 +1033,15 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
ret = gfs2_unstuff_dinode(ip, NULL);
if (ret)
goto out_trans_end;
- release_metapath(&mp);
- brelse(iomap->private);
- iomap->private = NULL;
+ release_metapath(mp);
ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
- flags, iomap, &mp);
+ flags, iomap, mp);
if (ret)
goto out_trans_end;
}
if (iomap->type == IOMAP_HOLE) {
- ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+ ret = gfs2_iomap_alloc(inode, iomap, flags, mp);
if (ret) {
gfs2_trans_end(sdp);
gfs2_inplace_release(ip);
@@ -1056,7 +1049,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
goto out_qunlock;
}
}
- release_metapath(&mp);
if (!gfs2_is_stuffed(ip) && gfs2_is_jdata(ip))
iomap->page_done = gfs2_iomap_journaled_page_done;
return 0;
@@ -1069,10 +1061,7 @@ out_trans_fail:
out_qunlock:
if (alloc_required)
gfs2_quota_unlock(ip);
-out_release:
- if (iomap->private)
- brelse(iomap->private);
- release_metapath(&mp);
+out_unlock:
gfs2_write_unlock(inode);
return ret;
}
@@ -1088,10 +1077,10 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
trace_gfs2_iomap_start(ip, pos, length, flags);
if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) {
- ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap);
+ ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap, &mp);
} else {
ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
- release_metapath(&mp);
+
/*
* Silently fall back to buffered I/O for stuffed files or if
* we've hot a hole (see gfs2_file_direct_write).
@@ -1100,6 +1089,11 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
iomap->type != IOMAP_MAPPED)
ret = -ENOTBLK;
}
+ if (!ret) {
+ get_bh(mp.mp_bh[0]);
+ iomap->private = mp.mp_bh[0];
+ }
+ release_metapath(&mp);
trace_gfs2_iomap_end(ip, iomap, ret);
return ret;
}
@@ -1908,10 +1902,16 @@ static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length)
if (ret < 0)
goto out;
- /* issue read-ahead on metadata */
- if (mp.mp_aheight > 1) {
- for (; ret > 1; ret--) {
- metapointer_range(&mp, mp.mp_aheight - ret,
+ /* On the first pass, issue read-ahead on metadata. */
+ if (mp.mp_aheight > 1 && strip_h == ip->i_height - 1) {
+ unsigned int height = mp.mp_aheight - 1;
+
+ /* No read-ahead for data blocks. */
+ if (mp.mp_aheight - 1 == strip_h)
+ height--;
+
+ for (; height >= mp.mp_aheight - ret; height--) {
+ metapointer_range(&mp, height,
start_list, start_aligned,
end_list, end_aligned,
&start, &end);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ffe3032b1043..b08a530433ad 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -733,6 +733,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
if (gl) {
glock_clear_object(gl, rgd);
+ gfs2_rgrp_brelse(rgd);
gfs2_glock_put(gl);
}
@@ -1174,7 +1175,7 @@ static u32 count_unlinked(struct gfs2_rgrpd *rgd)
* @rgd: the struct gfs2_rgrpd describing the RG to read in
*
* Read in all of a Resource Group's header and bitmap blocks.
- * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps.
+ * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps.
*
* Returns: errno
*/
diff --git a/fs/inode.c b/fs/inode.c
index 9e198f00b64c..35d2108d567c 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -730,8 +730,11 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
return LRU_REMOVED;
}
- /* recently referenced inodes get one more pass */
- if (inode->i_state & I_REFERENCED) {
+ /*
+ * Recently referenced inodes and inodes with many attached pages
+ * get one more pass.
+ */
+ if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) {
inode->i_state &= ~I_REFERENCED;
spin_unlock(&inode->i_lock);
return LRU_ROTATE;
diff --git a/fs/namespace.c b/fs/namespace.c
index 74f64294a410..a7f91265ea67 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -695,9 +695,6 @@ static struct mountpoint *lookup_mountpoint(struct dentry *dentry)
hlist_for_each_entry(mp, chain, m_hash) {
if (mp->m_dentry == dentry) {
- /* might be worth a WARN_ON() */
- if (d_unlinked(dentry))
- return ERR_PTR(-ENOENT);
mp->m_count++;
return mp;
}
@@ -711,6 +708,9 @@ static struct mountpoint *get_mountpoint(struct dentry *dentry)
int ret;
if (d_mountpoint(dentry)) {
+ /* might be worth a WARN_ON() */
+ if (d_unlinked(dentry))
+ return ERR_PTR(-ENOENT);
mountpoint:
read_seqlock_excl(&mount_lock);
mp = lookup_mountpoint(dentry);
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index fa515d5ea5ba..7b861bbc0b43 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -66,7 +66,7 @@ __be32 nfs4_callback_getattr(void *argp, void *resp,
out_iput:
rcu_read_unlock();
trace_nfs4_cb_getattr(cps->clp, &args->fh, inode, -ntohl(res->status));
- iput(inode);
+ nfs_iput_and_deactive(inode);
out:
dprintk("%s: exit with status = %d\n", __func__, ntohl(res->status));
return res->status;
@@ -108,7 +108,7 @@ __be32 nfs4_callback_recall(void *argp, void *resp,
}
trace_nfs4_cb_recall(cps->clp, &args->fh, inode,
&args->stateid, -ntohl(res));
- iput(inode);
+ nfs_iput_and_deactive(inode);
out:
dprintk("%s: exit with status = %d\n", __func__, ntohl(res));
return res;
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 07b839560576..6ec2f78c1e19 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -850,16 +850,23 @@ nfs_delegation_find_inode_server(struct nfs_server *server,
const struct nfs_fh *fhandle)
{
struct nfs_delegation *delegation;
- struct inode *res = NULL;
+ struct inode *freeme, *res = NULL;
list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
spin_lock(&delegation->lock);
if (delegation->inode != NULL &&
nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) {
- res = igrab(delegation->inode);
+ freeme = igrab(delegation->inode);
+ if (freeme && nfs_sb_active(freeme->i_sb))
+ res = freeme;
spin_unlock(&delegation->lock);
if (res != NULL)
return res;
+ if (freeme) {
+ rcu_read_unlock();
+ iput(freeme);
+ rcu_read_lock();
+ }
return ERR_PTR(-EAGAIN);
}
spin_unlock(&delegation->lock);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 62ae0fd345ad..ffea57885394 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2601,11 +2601,12 @@ static void nfs4_state_manager(struct nfs_client *clp)
nfs4_clear_state_manager_bit(clp);
/* Did we race with an attempt to give us more work? */
if (clp->cl_state == 0)
- break;
+ return;
if (test_and_set_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state) != 0)
- break;
- } while (refcount_read(&clp->cl_count) > 1);
- return;
+ return;
+ } while (refcount_read(&clp->cl_count) > 1 && !signalled());
+ goto out_drain;
+
out_error:
if (strlen(section))
section_sep = ": ";
@@ -2613,6 +2614,7 @@ out_error:
" with error %d\n", section_sep, section,
clp->cl_hostname, -status);
ssleep(1);
+out_drain:
nfs4_end_drain_session(clp);
nfs4_clear_state_manager_bit(clp);
}
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index edff074d38c7..d505990dac7c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1038,6 +1038,9 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
__be32 status;
+ if (!cstate->save_fh.fh_dentry)
+ return nfserr_nofilehandle;
+
status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh,
src_stateid, RD_STATE, src, NULL);
if (status) {
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 5769cf3ff035..e08a6647267b 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -115,12 +115,12 @@ static bool fanotify_should_send_event(struct fsnotify_iter_info *iter_info,
continue;
mark = iter_info->marks[type];
/*
- * if the event is for a child and this inode doesn't care about
- * events on the child, don't send it!
+ * If the event is for a child and this mark doesn't care about
+ * events on a child, don't send it!
*/
- if (type == FSNOTIFY_OBJ_TYPE_INODE &&
- (event_mask & FS_EVENT_ON_CHILD) &&
- !(mark->mask & FS_EVENT_ON_CHILD))
+ if (event_mask & FS_EVENT_ON_CHILD &&
+ (type != FSNOTIFY_OBJ_TYPE_INODE ||
+ !(mark->mask & FS_EVENT_ON_CHILD)))
continue;
marks_mask |= mark->mask;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 2172ba516c61..d2c34900ae05 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -167,9 +167,9 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask
parent = dget_parent(dentry);
p_inode = parent->d_inode;
- if (unlikely(!fsnotify_inode_watches_children(p_inode)))
+ if (unlikely(!fsnotify_inode_watches_children(p_inode))) {
__fsnotify_update_child_dentry_flags(p_inode);
- else if (p_inode->i_fsnotify_mask & mask) {
+ } else if (p_inode->i_fsnotify_mask & mask & ALL_FSNOTIFY_EVENTS) {
struct name_snapshot name;
/* we are notifying a parent so come up with the new mask which
@@ -339,6 +339,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
sb = mnt->mnt.mnt_sb;
mnt_or_sb_mask = mnt->mnt_fsnotify_mask | sb->s_fsnotify_mask;
}
+ /* An event "on child" is not intended for a mount/sb mark */
+ if (mask & FS_EVENT_ON_CHILD)
+ mnt_or_sb_mask = 0;
/*
* Optimization: srcu_read_lock() has a memory barrier which can
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index da578ad4c08f..eb1ce30412dc 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2411,8 +2411,16 @@ static int ocfs2_dio_end_io(struct kiocb *iocb,
/* this io's submitter should not have unlocked this before we could */
BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
- if (bytes > 0 && private)
- ret = ocfs2_dio_end_io_write(inode, private, offset, bytes);
+ if (bytes <= 0)
+ mlog_ratelimited(ML_ERROR, "Direct IO failed, bytes = %lld",
+ (long long)bytes);
+ if (private) {
+ if (bytes > 0)
+ ret = ocfs2_dio_end_io_write(inode, private, offset,
+ bytes);
+ else
+ ocfs2_dio_free_write_ctx(inode, private);
+ }
ocfs2_iocb_clear_rw_locked(iocb);
diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
index 308ea0eb35fd..a396096a5099 100644
--- a/fs/ocfs2/cluster/masklog.h
+++ b/fs/ocfs2/cluster/masklog.h
@@ -178,6 +178,15 @@ do { \
##__VA_ARGS__); \
} while (0)
+#define mlog_ratelimited(mask, fmt, ...) \
+do { \
+ static DEFINE_RATELIMIT_STATE(_rs, \
+ DEFAULT_RATELIMIT_INTERVAL, \
+ DEFAULT_RATELIMIT_BURST); \
+ if (__ratelimit(&_rs)) \
+ mlog(mask, fmt, ##__VA_ARGS__); \
+} while (0)
+
#define mlog_errno(st) ({ \
int _st = (st); \
if (_st != -ERESTARTSYS && _st != -EINTR && \
generated by cgit v1.2.3 (git 2.39.0) at 2024-11-19 20:31:55 +0300