aboutsummaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/affs/file.c2
-rw-r--r--fs/btrfs/disk-io.c9
-rw-r--r--fs/btrfs/file.c13
-rw-r--r--fs/btrfs/fs.h6
-rw-r--r--fs/btrfs/qgroup.c39
-rw-r--r--fs/btrfs/space-info.c3
-rw-r--r--fs/btrfs/tree-log.c47
-rw-r--r--fs/btrfs/volumes.c61
-rw-r--r--fs/btrfs/zoned.c2
-rw-r--r--fs/erofs/super.c13
-rw-r--r--fs/erofs/zdata.c12
-rw-r--r--fs/erofs/zmap.c10
-rw-r--r--fs/nfsd/netns.h2
-rw-r--r--fs/nfsd/nfs4proc.c1
-rw-r--r--fs/nfsd/nfs4state.c30
-rw-r--r--fs/nfsd/nfsctl.c7
-rw-r--r--fs/nfsd/nfsd.h6
-rw-r--r--fs/nilfs2/btree.c15
-rw-r--r--fs/userfaultfd.c28
-rw-r--r--fs/zonefs/super.c22
20 files changed, 219 insertions, 109 deletions
diff --git a/fs/affs/file.c b/fs/affs/file.c
index cefa222f7881..8daeed31e1af 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -880,7 +880,7 @@ affs_truncate(struct inode *inode)
if (inode->i_size > AFFS_I(inode)->mmu_private) {
struct address_space *mapping = inode->i_mapping;
struct page *page;
- void *fsdata;
+ void *fsdata = NULL;
loff_t isize = inode->i_size;
int res;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8aeaada1fcae..3aa04224315e 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -367,7 +367,14 @@ error:
btrfs_print_tree(eb, 0);
btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
eb->start);
- WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ /*
+ * Be noisy if this is an extent buffer from a log tree. We don't abort
+ * a transaction in case there's a bad log tree extent buffer, we just
+ * fallback to a transaction commit. Still we want to know when there is
+ * a bad log tree extent buffer, as that may signal a bug somewhere.
+ */
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) ||
+ btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID);
return ret;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 834bbcb91102..af046d22300e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -3541,6 +3541,7 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
struct extent_buffer *leaf = path->nodes[0];
struct btrfs_file_extent_item *extent;
u64 extent_end;
+ u8 type;
if (path->slots[0] >= btrfs_header_nritems(leaf)) {
ret = btrfs_next_leaf(root, path);
@@ -3596,10 +3597,16 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_file_extent_item);
+ type = btrfs_file_extent_type(leaf, extent);
- if (btrfs_file_extent_disk_bytenr(leaf, extent) == 0 ||
- btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_PREALLOC) {
+ /*
+ * Can't access the extent's disk_bytenr field if this is an
+ * inline extent, since at that offset, it's where the extent
+ * data starts.
+ */
+ if (type == BTRFS_FILE_EXTENT_PREALLOC ||
+ (type == BTRFS_FILE_EXTENT_REG &&
+ btrfs_file_extent_disk_bytenr(leaf, extent) == 0)) {
/*
* Explicit hole or prealloc extent, search for delalloc.
* A prealloc extent is treated like a hole.
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index a749367e5ae2..37b86acfcbcf 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -119,6 +119,12 @@ enum {
/* Indicate that we want to commit the transaction. */
BTRFS_FS_NEED_TRANS_COMMIT,
+ /*
+ * Indicate metadata over-commit is disabled. This is set when active
+ * zone tracking is needed.
+ */
+ BTRFS_FS_NO_OVERCOMMIT,
+
#if BITS_PER_LONG == 32
/* Indicate if we have error/warn message printed on 32bit systems */
BTRFS_FS_32BIT_ERROR,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d275bf24b250..af97413abcf4 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2765,9 +2765,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
/*
* Old roots should be searched when inserting qgroup
- * extent record
+ * extent record.
+ *
+ * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case,
+ * we may have some record inserted during
+ * NO_ACCOUNTING (thus no old_roots populated), but
+ * later we start rescan, which clears NO_ACCOUNTING,
+ * leaving some inserted records without old_roots
+ * populated.
+ *
+ * Those cases are rare and should not cause too much
+ * time spent during commit_transaction().
*/
- if (WARN_ON(!record->old_roots)) {
+ if (!record->old_roots) {
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(&ctx, false);
if (ret < 0)
@@ -3357,6 +3367,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
int err = -ENOMEM;
int ret = 0;
bool stopped = false;
+ bool did_leaf_rescans = false;
path = btrfs_alloc_path();
if (!path)
@@ -3377,6 +3388,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
}
err = qgroup_rescan_leaf(trans, path);
+ did_leaf_rescans = true;
if (err > 0)
btrfs_commit_transaction(trans);
@@ -3397,16 +3409,23 @@ out:
mutex_unlock(&fs_info->qgroup_rescan_lock);
/*
- * only update status, since the previous part has already updated the
- * qgroup info.
+ * Only update status, since the previous part has already updated the
+ * qgroup info, and only if we did any actual work. This also prevents
+ * race with a concurrent quota disable, which has already set
+ * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at
+ * btrfs_quota_disable().
*/
- trans = btrfs_start_transaction(fs_info->quota_root, 1);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
+ if (did_leaf_rescans) {
+ trans = btrfs_start_transaction(fs_info->quota_root, 1);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ trans = NULL;
+ btrfs_err(fs_info,
+ "fail to start transaction for status update: %d",
+ err);
+ }
+ } else {
trans = NULL;
- btrfs_err(fs_info,
- "fail to start transaction for status update: %d",
- err);
}
mutex_lock(&fs_info->qgroup_rescan_lock);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index d28ee4e36f3d..69c09508afb5 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -407,7 +407,8 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
return 0;
used = btrfs_space_info_used(space_info, true);
- if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
+ if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) &&
+ (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
avail = 0;
else
avail = calc_available_free_space(fs_info, space_info, flush);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fb52aa060093..d43261545264 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2980,7 +2980,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
ret = 0;
if (ret) {
blk_finish_plug(&plug);
- btrfs_abort_transaction(trans, ret);
btrfs_set_log_full_commit(trans);
mutex_unlock(&root->log_mutex);
goto out;
@@ -3045,15 +3044,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
blk_finish_plug(&plug);
btrfs_set_log_full_commit(trans);
-
- if (ret != -ENOSPC) {
- btrfs_abort_transaction(trans, ret);
- mutex_unlock(&log_root_tree->log_mutex);
- goto out;
- }
+ if (ret != -ENOSPC)
+ btrfs_err(fs_info,
+ "failed to update log for root %llu ret %d",
+ root->root_key.objectid, ret);
btrfs_wait_tree_log_extents(log, mark);
mutex_unlock(&log_root_tree->log_mutex);
- ret = BTRFS_LOG_FORCE_COMMIT;
goto out;
}
@@ -3112,7 +3108,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
goto out_wake_log_root;
} else if (ret) {
btrfs_set_log_full_commit(trans);
- btrfs_abort_transaction(trans, ret);
mutex_unlock(&log_root_tree->log_mutex);
goto out_wake_log_root;
}
@@ -3826,7 +3821,10 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
path->slots[0]);
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
}
+
goto done;
}
@@ -3846,19 +3844,34 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
*/
if (tmp.type == BTRFS_DIR_INDEX_KEY)
last_old_dentry_offset = tmp.offset;
+ } else if (ret < 0) {
+ err = ret;
+ goto done;
}
+
btrfs_release_path(path);
/*
- * Find the first key from this transaction again. See the note for
- * log_new_dir_dentries, if we're logging a directory recursively we
- * won't be holding its i_mutex, which means we can modify the directory
- * while we're logging it. If we remove an entry between our first
- * search and this search we'll not find the key again and can just
- * bail.
+ * Find the first key from this transaction again or the one we were at
+ * in the loop below in case we had to reschedule. We may be logging the
+ * directory without holding its VFS lock, which happen when logging new
+ * dentries (through log_new_dir_dentries()) or in some cases when we
+ * need to log the parent directory of an inode. This means a dir index
+ * key might be deleted from the inode's root, and therefore we may not
+ * find it anymore. If we can't find it, just move to the next key. We
+ * can not bail out and ignore, because if we do that we will simply
+ * not log dir index keys that come after the one that was just deleted
+ * and we can end up logging a dir index range that ends at (u64)-1
+ * (@last_offset is initialized to that), resulting in removing dir
+ * entries we should not remove at log replay time.
*/
search:
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
+ if (ret > 0)
+ ret = btrfs_next_item(root, path);
+ if (ret < 0)
+ err = ret;
+ /* If ret is 1, there are no more keys in the inode's root. */
if (ret != 0)
goto done;
@@ -5580,8 +5593,10 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans,
* LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction
* commits.
*/
- if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES)
+ if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) {
+ btrfs_set_log_full_commit(trans);
return BTRFS_LOG_FORCE_COMMIT;
+ }
inode = btrfs_iget(root->fs_info->sb, ino, root);
/*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index aa25fa335d3e..bcfef75b97da 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -768,8 +768,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
error = lookup_bdev(path, &path_devt);
- if (error)
+ if (error) {
+ btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+ path, error);
return ERR_PTR(error);
+ }
if (fsid_change_in_progress) {
if (!has_metadata_uuid)
@@ -836,6 +839,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
unsigned int nofs_flag;
if (fs_devices->opened) {
+ btrfs_err(NULL,
+ "device %s belongs to fsid %pU, and the fs is already mounted",
+ path, fs_devices->fsid);
mutex_unlock(&fs_devices->device_list_mutex);
return ERR_PTR(-EBUSY);
}
@@ -905,6 +911,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
* generation are equal.
*/
mutex_unlock(&fs_devices->device_list_mutex);
+ btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+ path, found_transid, device->generation);
return ERR_PTR(-EEXIST);
}
@@ -2005,42 +2014,42 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info)
return num_devices;
}
+static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
+ struct block_device *bdev, int copy_num)
+{
+ struct btrfs_super_block *disk_super;
+ const size_t len = sizeof(disk_super->magic);
+ const u64 bytenr = btrfs_sb_offset(copy_num);
+ int ret;
+
+ disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr);
+ if (IS_ERR(disk_super))
+ return;
+
+ memset(&disk_super->magic, 0, len);
+ folio_mark_dirty(virt_to_folio(disk_super));
+ btrfs_release_disk_super(disk_super);
+
+ ret = sync_blockdev_range(bdev, bytenr, bytenr + len - 1);
+ if (ret)
+ btrfs_warn(fs_info, "error clearing superblock number %d (%d)",
+ copy_num, ret);
+}
+
void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
struct block_device *bdev,
const char *device_path)
{
- struct btrfs_super_block *disk_super;
int copy_num;
if (!bdev)
return;
for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) {
- struct page *page;
- int ret;
-
- disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
- if (IS_ERR(disk_super))
- continue;
-
- if (bdev_is_zoned(bdev)) {
+ if (bdev_is_zoned(bdev))
btrfs_reset_sb_log_zones(bdev, copy_num);
- continue;
- }
-
- memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-
- page = virt_to_page(disk_super);
- set_page_dirty(page);
- lock_page(page);
- /* write_on_page() unlocks the page */
- ret = write_one_page(page);
- if (ret)
- btrfs_warn(fs_info,
- "error clearing superblock number %d (%d)",
- copy_num, ret);
- btrfs_release_disk_super(disk_super);
-
+ else
+ btrfs_scratch_superblock(fs_info, bdev, copy_num);
}
/* Notify udev that device has changed */
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index a759668477bb..1f503e8e42d4 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -539,6 +539,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache)
}
atomic_set(&zone_info->active_zones_left,
max_active_zones - nactive);
+ /* Overcommit does not work well with active zone tacking. */
+ set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags);
}
/* Validate superblock log */
diff --git a/fs/erofs/super.c b/fs/erofs/super.c
index 481788c24a68..626a615dafc2 100644
--- a/fs/erofs/super.c
+++ b/fs/erofs/super.c
@@ -577,26 +577,25 @@ static int erofs_fc_parse_param(struct fs_context *fc,
}
++ctx->devs->extra_devices;
break;
- case Opt_fsid:
#ifdef CONFIG_EROFS_FS_ONDEMAND
+ case Opt_fsid:
kfree(ctx->fsid);
ctx->fsid = kstrdup(param->string, GFP_KERNEL);
if (!ctx->fsid)
return -ENOMEM;
-#else
- errorfc(fc, "fsid option not supported");
-#endif
break;
case Opt_domain_id:
-#ifdef CONFIG_EROFS_FS_ONDEMAND
kfree(ctx->domain_id);
ctx->domain_id = kstrdup(param->string, GFP_KERNEL);
if (!ctx->domain_id)
return -ENOMEM;
+ break;
#else
- errorfc(fc, "domain_id option not supported");
-#endif
+ case Opt_fsid:
+ case Opt_domain_id:
+ errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name);
break;
+#endif
default:
return -ENOPARAM;
}
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index ccf7c55d477f..5200bb86e264 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -1032,12 +1032,12 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be,
if (!be->decompressed_pages)
be->decompressed_pages =
- kvcalloc(be->nr_pages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(be->nr_pages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
if (!be->compressed_pages)
be->compressed_pages =
- kvcalloc(pclusterpages, sizeof(struct page *),
- GFP_KERNEL | __GFP_NOFAIL);
+ kcalloc(pclusterpages, sizeof(struct page *),
+ GFP_KERNEL | __GFP_NOFAIL);
z_erofs_parse_out_bvecs(be);
err2 = z_erofs_parse_in_bvecs(be, &overlapped);
@@ -1085,7 +1085,7 @@ out:
}
if (be->compressed_pages < be->onstack_pages ||
be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES)
- kvfree(be->compressed_pages);
+ kfree(be->compressed_pages);
z_erofs_fill_other_copies(be, err);
for (i = 0; i < be->nr_pages; ++i) {
@@ -1104,7 +1104,7 @@ out:
}
if (be->decompressed_pages != be->onstack_pages)
- kvfree(be->decompressed_pages);
+ kfree(be->decompressed_pages);
pcl->length = 0;
pcl->partial = true;
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 0150570c33aa..98fb90b9af71 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -793,12 +793,16 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset,
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
/*
- * No strict rule how to describe extents for post EOF, yet
- * we need do like below. Otherwise, iomap itself will get
+ * No strict rule on how to describe extents for post EOF, yet
+ * we need to do like below. Otherwise, iomap itself will get
* into an endless loop on post EOF.
+ *
+ * Calculate the effective offset by subtracting extent start
+ * (map.m_la) from the requested offset, and add it to length.
+ * (NB: offset >= map.m_la always)
*/
if (iomap->offset >= inode->i_size)
- iomap->length = length + map.m_la - offset;
+ iomap->length = length + offset - map.m_la;
}
iomap->flags = 0;
return 0;
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 8c854ba3285b..51a4b7885cae 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -195,7 +195,7 @@ struct nfsd_net {
atomic_t nfsd_courtesy_clients;
struct shrinker nfsd_client_shrinker;
- struct delayed_work nfsd_shrinker_work;
+ struct work_struct nfsd_shrinker_work;
};
/* Simple check to find out if a given net was properly initialized */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 9b81d012666e..f189ba7995f5 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -1318,6 +1318,7 @@ try_again:
/* allow 20secs for mount/unmount for now - revisit */
if (signal_pending(current) ||
(schedule_timeout(20*HZ) == 0)) {
+ finish_wait(&nn->nfsd_ssc_waitq, &wait);
kfree(work);
return nfserr_eagain;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4809ae0f0138..4ef529379065 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4411,7 +4411,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc)
if (!count)
count = atomic_long_read(&num_delegations);
if (count)
- mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0);
+ queue_work(laundry_wq, &nn->nfsd_shrinker_work);
return (unsigned long)count;
}
@@ -4421,7 +4421,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc)
return SHRINK_STOP;
}
-int
+void
nfsd4_init_leases_net(struct nfsd_net *nn)
{
struct sysinfo si;
@@ -4443,16 +4443,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn)
nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB);
atomic_set(&nn->nfsd_courtesy_clients, 0);
- nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
- nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
- nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
- return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client");
-}
-
-void
-nfsd4_leases_net_shutdown(struct nfsd_net *nn)
-{
- unregister_shrinker(&nn->nfsd_client_shrinker);
}
static void init_nfs4_replay(struct nfs4_replay *rp)
@@ -6235,8 +6225,7 @@ deleg_reaper(struct nfsd_net *nn)
static void
nfsd4_state_shrinker_worker(struct work_struct *work)
{
- struct delayed_work *dwork = to_delayed_work(work);
- struct nfsd_net *nn = container_of(dwork, struct nfsd_net,
+ struct nfsd_net *nn = container_of(work, struct nfsd_net,
nfsd_shrinker_work);
courtesy_client_reaper(nn);
@@ -8066,11 +8055,20 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->blocked_locks_lru);
INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main);
- INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
+ INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker);
get_net(net);
+ nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan;
+ nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count;
+ nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS;
+
+ if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"))
+ goto err_shrinker;
return 0;
+err_shrinker:
+ put_net(net);
+ kfree(nn->sessionid_hashtbl);
err_sessionid:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
@@ -8163,6 +8161,8 @@ nfs4_state_shutdown_net(struct net *net)
struct list_head *pos, *next, reaplist;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ unregister_shrinker(&nn->nfsd_client_shrinker);
+ cancel_work(&nn->nfsd_shrinker_work);
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index d1e581a60480..c2577ee7ffb2 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1457,9 +1457,7 @@ static __net_init int nfsd_init_net(struct net *net)
goto out_idmap_error;
nn->nfsd_versions = NULL;
nn->nfsd4_minorversions = NULL;
- retval = nfsd4_init_leases_net(nn);
- if (retval)
- goto out_drc_error;
+ nfsd4_init_leases_net(nn);
retval = nfsd_reply_cache_init(nn);
if (retval)
goto out_cache_error;
@@ -1469,8 +1467,6 @@ static __net_init int nfsd_init_net(struct net *net)
return 0;
out_cache_error:
- nfsd4_leases_net_shutdown(nn);
-out_drc_error:
nfsd_idmap_shutdown(net);
out_idmap_error:
nfsd_export_shutdown(net);
@@ -1486,7 +1482,6 @@ static __net_exit void nfsd_exit_net(struct net *net)
nfsd_idmap_shutdown(net);
nfsd_export_shutdown(net);
nfsd_netns_free_versions(net_generic(net, nfsd_net_id));
- nfsd4_leases_net_shutdown(nn);
}
static struct pernet_operations nfsd_net_ops = {
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index 93b42ef9ed91..fa0144a74267 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void);
extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn);
#endif
-extern int nfsd4_init_leases_net(struct nfsd_net *nn);
-extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn);
+extern void nfsd4_init_leases_net(struct nfsd_net *nn);
#else /* CONFIG_NFSD_V4 */
static inline int nfsd4_is_junction(struct dentry *dentry)
@@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry)
return 0;
}
-static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; };
-static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {};
+static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { };
#define register_cld_notifier() 0
#define unregister_cld_notifier() do { } while(0)
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b9d15c3df3cc..40ce92a332fe 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr,
ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh,
&submit_ptr);
if (ret) {
- if (ret != -EEXIST)
- return ret;
- goto out_check;
+ if (likely(ret == -EEXIST))
+ goto out_check;
+ if (ret == -ENOENT) {
+ /*
+ * Block address translation failed due to invalid
+ * value of 'ptr'. In this case, return internal code
+ * -EINVAL (broken bmap) to notify bmap layer of fatal
+ * metadata corruption.
+ */
+ ret = -EINVAL;
+ }
+ return ret;
}
if (ra) {
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 98ac37e34e3d..cc694846617a 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
return ctx->features & UFFD_FEATURE_INITIALIZED;
}
+static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+
+ vma->vm_flags = flags;
+ /*
+ * For shared mappings, we want to enable writenotify while
+ * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
+ * recalculate vma->vm_page_prot whenever userfaultfd-wp changes.
+ */
+ if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed)
+ vma_set_page_prot(vma);
+}
+
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
int wake_flags, void *key)
{
@@ -618,7 +633,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
for_each_vma(vmi, vma) {
if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma,
+ vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
mmap_write_unlock(mm);
@@ -652,7 +668,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
octx = vma->vm_userfaultfd_ctx.ctx;
if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
return 0;
}
@@ -733,7 +749,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma,
} else {
/* Drop uffd context if remap feature not enabled */
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
+ userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS);
}
}
@@ -895,7 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
prev = vma;
}
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
}
mmap_write_unlock(mm);
@@ -1463,7 +1479,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx.ctx = ctx;
if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
@@ -1651,7 +1667,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
* the next vma was merged into the current one and
* the current one has not been updated yet.
*/
- vma->vm_flags = new_flags;
+ userfaultfd_set_vm_flags(vma, new_flags);
vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
skip:
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index 2c53fbb8d918..a9c5c3f720ad 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -442,6 +442,10 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx,
data_size = zonefs_check_zone_condition(inode, zone,
false, false);
}
+ } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO &&
+ data_size > isize) {
+ /* Do not expose garbage data */
+ data_size = isize;
}
/*
@@ -805,6 +809,24 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
ret = submit_bio_wait(bio);
+ /*
+ * If the file zone was written underneath the file system, the zone
+ * write pointer may not be where we expect it to be, but the zone
+ * append write can still succeed. So check manually that we wrote where
+ * we intended to, that is, at zi->i_wpoffset.
+ */
+ if (!ret) {
+ sector_t wpsector =
+ zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT);
+
+ if (bio->bi_iter.bi_sector != wpsector) {
+ zonefs_warn(inode->i_sb,
+ "Corrupted write pointer %llu for zone at %llu\n",
+ wpsector, zi->i_zsector);
+ ret = -EIO;
+ }
+ }
+
zonefs_file_write_dio_end_io(iocb, size, ret, 0);
trace_zonefs_file_dio_append(inode, size, ret);
Powered by cgit, Gruvboxed by Blaster4385.