From 116e0f61852489520aaad930b8fcbe40834819bf Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 4 May 2024 12:10:26 +0200 Subject: Merging upstream version 6.1.82. Signed-off-by: Daniel Baumann --- fs/9p/v9fs_vfs.h | 1 + fs/9p/vfs_inode.c | 6 +- fs/9p/vfs_inode_dotl.c | 1 + fs/afs/callback.c | 3 +- fs/afs/dir.c | 4 +- fs/afs/server.c | 7 +- fs/afs/volume.c | 4 +- fs/aio.c | 9 +- fs/btrfs/block-group.c | 49 ++- fs/btrfs/block-group.h | 7 + fs/btrfs/delalloc-space.c | 29 +- fs/btrfs/dev-replace.c | 24 +- fs/btrfs/disk-io.c | 29 +- fs/btrfs/disk-io.h | 2 +- fs/btrfs/inode.c | 26 +- fs/btrfs/ioctl.c | 7 +- fs/btrfs/qgroup.c | 14 + fs/btrfs/send.c | 19 +- fs/btrfs/transaction.c | 2 +- fs/cachefiles/cache.c | 2 + fs/cachefiles/daemon.c | 1 + fs/ceph/caps.c | 12 +- fs/ceph/mds_client.c | 2 +- fs/ceph/mdsmap.c | 7 +- fs/ceph/quota.c | 39 ++- fs/dcache.c | 7 +- fs/dlm/lowcomms.c | 38 +-- fs/ecryptfs/inode.c | 8 + fs/efivarfs/vars.c | 17 +- fs/erofs/compress.h | 4 + fs/erofs/data.c | 1 + fs/erofs/decompressor.c | 60 +++- fs/erofs/decompressor_lzma.c | 4 +- fs/erofs/internal.h | 28 +- fs/erofs/namei.c | 28 +- fs/erofs/super.c | 72 +--- fs/erofs/zdata.c | 2 +- fs/erofs/zmap.c | 23 +- fs/exportfs/expfs.c | 8 +- fs/ext4/extents.c | 111 ++++--- fs/ext4/mballoc.c | 81 +++-- fs/ext4/move_extent.c | 6 +- fs/ext4/resize.c | 37 ++- fs/f2fs/compress.c | 31 +- fs/f2fs/f2fs.h | 2 + fs/f2fs/file.c | 2 + fs/f2fs/recovery.c | 25 +- fs/f2fs/super.c | 4 +- fs/hugetlbfs/inode.c | 19 +- fs/jfs/jfs_dmap.c | 57 ++-- fs/jfs/jfs_dtree.c | 7 +- fs/jfs/jfs_imap.c | 3 + fs/jfs/jfs_mount.c | 6 +- fs/kernfs/dir.c | 12 + fs/lockd/svc4proc.c | 1 + fs/lockd/svclock.c | 17 +- fs/lockd/svcproc.c | 1 + fs/lockd/svcsubs.c | 4 +- fs/locks.c | 24 +- fs/namespace.c | 11 +- fs/nfs/nfs4trace.h | 6 +- fs/nfs/nfstrace.h | 6 +- fs/nfs/write.c | 4 +- fs/nfsd/Kconfig | 19 +- fs/nfsd/Makefile | 5 +- fs/nfsd/blocklayout.c | 1 + fs/nfsd/blocklayoutxdr.c | 1 + fs/nfsd/export.h | 1 - fs/nfsd/filecache.c | 39 ++- fs/nfsd/flexfilelayout.c | 1 + fs/nfsd/netns.h | 2 +- fs/nfsd/nfs4callback.c | 72 ++++ fs/nfsd/nfs4idmap.c | 1 + fs/nfsd/nfs4proc.c | 31 +- fs/nfsd/nfs4state.c | 349 +++++++++++++------- fs/nfsd/nfs4xdr.c | 771 +++++++++++++++++++++++-------------------- fs/nfsd/nfsctl.c | 13 +- fs/nfsd/nfsd.h | 9 +- fs/nfsd/nfsfh.h | 10 +- fs/nfsd/nfsproc.c | 66 +--- fs/nfsd/nfssvc.c | 8 +- fs/nfsd/state.h | 11 +- fs/nfsd/trace.h | 106 ++++++ fs/nfsd/vfs.c | 64 +++- fs/nfsd/vfs.h | 1 + fs/nfsd/xdr4.h | 5 + fs/nfsd/xdr4cb.h | 6 + fs/nilfs2/dat.c | 27 +- fs/nilfs2/file.c | 8 +- fs/nilfs2/recovery.c | 7 +- fs/nilfs2/segment.c | 8 +- fs/ntfs3/attrib.c | 20 +- fs/ntfs3/attrlist.c | 8 +- fs/ntfs3/dir.c | 40 ++- fs/ntfs3/file.c | 2 + fs/ntfs3/frecord.c | 5 +- fs/ntfs3/fslog.c | 14 +- fs/ntfs3/fsntfs.c | 41 ++- fs/ntfs3/index.c | 14 +- fs/ntfs3/inode.c | 2 +- fs/ntfs3/ntfs.h | 4 +- fs/ntfs3/ntfs_fs.h | 16 +- fs/ntfs3/record.c | 25 +- fs/ntfs3/xattr.c | 3 + fs/proc/array.c | 65 ++-- fs/pstore/ram.c | 1 + fs/smb/client/cached_dir.c | 10 +- fs/smb/client/cifsencrypt.c | 2 +- fs/smb/client/cifsglob.h | 2 +- fs/smb/client/fs_context.c | 2 +- fs/smb/client/readdir.c | 15 +- fs/smb/client/sess.c | 2 + fs/smb/client/smb2ops.c | 2 +- fs/smb/client/smb2pdu.c | 99 +++--- fs/smb/client/smb2proto.h | 12 +- fs/smb/client/transport.c | 15 +- fs/smb/server/smb2pdu.c | 8 +- fs/zonefs/file.c | 42 ++- fs/zonefs/super.c | 66 ++-- 119 files changed, 2048 insertions(+), 1214 deletions(-) (limited to 'fs') diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index bc417da7e..633fe4f52 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -46,6 +46,7 @@ struct inode *v9fs_alloc_inode(struct super_block *sb); void v9fs_free_inode(struct inode *inode); struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev); +void v9fs_set_netfs_context(struct inode *inode); int v9fs_init_inode(struct v9fs_session_info *v9ses, struct inode *inode, umode_t mode, dev_t rdev); void v9fs_evict_inode(struct inode *inode); diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 4d1a4a8d9..5e2657c1d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -250,7 +250,7 @@ void v9fs_free_inode(struct inode *inode) /* * Set parameters for the netfs library */ -static void v9fs_set_netfs_context(struct inode *inode) +void v9fs_set_netfs_context(struct inode *inode) { struct v9fs_inode *v9inode = V9FS_I(inode); netfs_inode_init(&v9inode->netfs, &v9fs_req_ops); @@ -344,8 +344,6 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses, err = -EINVAL; goto error; } - - v9fs_set_netfs_context(inode); error: return err; @@ -377,6 +375,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, umode_t mode, dev_t rdev) iput(inode); return ERR_PTR(err); } + v9fs_set_netfs_context(inode); return inode; } @@ -479,6 +478,7 @@ static struct inode *v9fs_qid_iget(struct super_block *sb, goto error; v9fs_stat2inode(st, inode, sb, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); unlock_new_inode(inode); return inode; diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 5cfa4b4f0..e15ad4683 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -130,6 +130,7 @@ static struct inode *v9fs_qid_iget_dotl(struct super_block *sb, goto error; v9fs_stat2inode_dotl(st, inode, 0); + v9fs_set_netfs_context(inode); v9fs_cache_inode_get_cookie(inode); retval = v9fs_get_acl(inode, fid); if (retval) diff --git a/fs/afs/callback.c b/fs/afs/callback.c index a484fa642..90f9b2a46 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -110,13 +110,14 @@ static struct afs_volume *afs_lookup_volume_rcu(struct afs_cell *cell, { struct afs_volume *volume = NULL; struct rb_node *p; - int seq = 0; + int seq = 1; do { /* Unfortunately, rbtree walking doesn't give reliable results * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&cell->volume_lock, &seq); p = rcu_dereference_raw(cell->volumes.rb_node); diff --git a/fs/afs/dir.c b/fs/afs/dir.c index cf811b77e..6e2c967fa 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -478,8 +478,10 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, dire->u.name[0] == '.' && ctx->actor != afs_lookup_filldir && ctx->actor != afs_lookup_one_filldir && - memcmp(dire->u.name, ".__afs", 6) == 0) + memcmp(dire->u.name, ".__afs", 6) == 0) { + ctx->pos = blkoff + next * sizeof(union afs_xdr_dirent); continue; + } /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, diff --git a/fs/afs/server.c b/fs/afs/server.c index b5237206e..0bd2f5ba6 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -27,7 +27,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - int seq = 0, diff; + int seq = 1, diff; rcu_read_lock(); @@ -35,6 +35,7 @@ struct afs_server *afs_find_server(struct afs_net *net, if (server) afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq); if (srx->transport.family == AF_INET6) { @@ -90,7 +91,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu { struct afs_server *server = NULL; struct rb_node *p; - int diff, seq = 0; + int diff, seq = 1; _enter("%pU", uuid); @@ -102,7 +103,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu if (server) afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; - + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_lock, &seq); p = net->fs_servers.rb_node; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 1c9144e3e..a146d70ef 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -341,7 +341,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -349,7 +349,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { diff --git a/fs/aio.c b/fs/aio.c index e85ba0b77..849c3e3ed 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -595,6 +595,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1476,7 +1483,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 08017b180..9f77565bd 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1318,6 +1318,7 @@ out: */ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) { + LIST_HEAD(retry_list); struct btrfs_block_group *block_group; struct btrfs_space_info *space_info; struct btrfs_trans_handle *trans; @@ -1339,6 +1340,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) spin_lock(&fs_info->unused_bgs_lock); while (!list_empty(&fs_info->unused_bgs)) { + u64 used; int trimming; block_group = list_first_entry(&fs_info->unused_bgs, @@ -1374,9 +1376,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) goto next; } + spin_lock(&space_info->lock); spin_lock(&block_group->lock); - if (block_group->reserved || block_group->pinned || - block_group->used || block_group->ro || + if (btrfs_is_block_group_used(block_group) || block_group->ro || list_is_singular(&block_group->list)) { /* * We want to bail if we made new allocations or have @@ -1386,10 +1388,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) */ trace_btrfs_skip_unused_block_group(block_group); spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); + up_write(&space_info->groups_sem); + goto next; + } + + /* + * The block group may be unused but there may be space reserved + * accounting with the existence of that block group, that is, + * space_info->bytes_may_use was incremented by a task but no + * space was yet allocated from the block group by the task. + * That space may or may not be allocated, as we are generally + * pessimistic about space reservation for metadata as well as + * for data when using compression (as we reserve space based on + * the worst case, when data can't be compressed, and before + * actually attempting compression, before starting writeback). + * + * So check if the total space of the space_info minus the size + * of this block group is less than the used space of the + * space_info - if that's the case, then it means we have tasks + * that might be relying on the block group in order to allocate + * extents, and add back the block group to the unused list when + * we finish, so that we retry later in case no tasks ended up + * needing to allocate extents from the block group. + */ + used = btrfs_space_info_used(space_info, true); + if (space_info->total_bytes - block_group->length < used) { + /* + * Add a reference for the list, compensate for the ref + * drop under the "next" label for the + * fs_info->unused_bgs list. + */ + btrfs_get_block_group(block_group); + list_add_tail(&block_group->bg_list, &retry_list); + + trace_btrfs_skip_unused_block_group(block_group); + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); up_write(&space_info->groups_sem); goto next; } + spin_unlock(&block_group->lock); + spin_unlock(&space_info->lock); /* We don't want to force the issue, only flip if it's ok. */ ret = inc_block_group_ro(block_group, 0); @@ -1513,12 +1554,16 @@ next: btrfs_put_block_group(block_group); spin_lock(&fs_info->unused_bgs_lock); } + list_splice_tail(&retry_list, &fs_info->unused_bgs); spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); return; flip_async: btrfs_end_transaction(trans); + spin_lock(&fs_info->unused_bgs_lock); + list_splice_tail(&retry_list, &fs_info->unused_bgs); + spin_unlock(&fs_info->unused_bgs_lock); mutex_unlock(&fs_info->reclaim_bgs_lock); btrfs_put_block_group(block_group); btrfs_discard_punt_unused_bgs_list(fs_info); diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 47a2dcbfe..bace40a00 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -241,6 +241,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) return (block_group->start + block_group->length); } +static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg) +{ + lockdep_assert_held(&bg->lock); + + return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0); +} + static inline bool btrfs_is_block_group_data_only( struct btrfs_block_group *block_group) { diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c index f2bc5563c..63b7fa706 100644 --- a/fs/btrfs/delalloc-space.c +++ b/fs/btrfs/delalloc-space.c @@ -243,7 +243,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *block_rsv = &inode->block_rsv; u64 reserve_size = 0; u64 qgroup_rsv_size = 0; - u64 csum_leaves; unsigned outstanding_extents; lockdep_assert_held(&inode->lock); @@ -258,10 +257,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, outstanding_extents); reserve_size += btrfs_calc_metadata_size(fs_info, 1); } - csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, - inode->csum_bytes); - reserve_size += btrfs_calc_insert_metadata_size(fs_info, - csum_leaves); + if (!(inode->flags & BTRFS_INODE_NODATASUM)) { + u64 csum_leaves; + + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes); + reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves); + } /* * For qgroup rsv, the calculation is very simple: * account one nodesize for each outstanding extent @@ -276,14 +277,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info, spin_unlock(&block_rsv->lock); } -static void calc_inode_reservations(struct btrfs_fs_info *fs_info, +static void calc_inode_reservations(struct btrfs_inode *inode, u64 num_bytes, u64 disk_num_bytes, u64 *meta_reserve, u64 *qgroup_reserve) { + struct btrfs_fs_info *fs_info = inode->root->fs_info; u64 nr_extents = count_max_extents(fs_info, num_bytes); - u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + u64 csum_leaves; u64 inode_update = btrfs_calc_metadata_size(fs_info, 1); + if (inode->flags & BTRFS_INODE_NODATASUM) + csum_leaves = 0; + else + csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes); + *meta_reserve = btrfs_calc_insert_metadata_size(fs_info, nr_extents + csum_leaves); @@ -335,7 +342,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, * everything out and try again, which is bad. This way we just * over-reserve slightly, and clean up the mess when we are done. */ - calc_inode_reservations(fs_info, num_bytes, disk_num_bytes, + calc_inode_reservations(inode, num_bytes, disk_num_bytes, &meta_reserve, &qgroup_reserve); ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true, noflush); @@ -356,7 +363,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes, spin_lock(&inode->lock); nr_extents = count_max_extents(fs_info, num_bytes); btrfs_mod_outstanding_extents(inode, nr_extents); - inode->csum_bytes += disk_num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes += disk_num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); @@ -390,7 +398,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes, num_bytes = ALIGN(num_bytes, fs_info->sectorsize); spin_lock(&inode->lock); - inode->csum_bytes -= num_bytes; + if (!(inode->flags & BTRFS_INODE_NODATASUM)) + inode->csum_bytes -= num_bytes; btrfs_calculate_inode_block_rsv_size(fs_info, inode); spin_unlock(&inode->lock); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 61e58066b..9c856a73d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -740,6 +740,23 @@ leave: return ret; } +static int btrfs_check_replace_dev_names(struct btrfs_ioctl_dev_replace_args *args) +{ + if (args->start.srcdevid == 0) { + if (memchr(args->start.srcdev_name, 0, + sizeof(args->start.srcdev_name)) == NULL) + return -ENAMETOOLONG; + } else { + args->start.srcdev_name[0] = 0; + } + + if (memchr(args->start.tgtdev_name, 0, + sizeof(args->start.tgtdev_name)) == NULL) + return -ENAMETOOLONG; + + return 0; +} + int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, struct btrfs_ioctl_dev_replace_args *args) { @@ -752,10 +769,9 @@ int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info, default: return -EINVAL; } - - if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') || - args->start.tgtdev_name[0] == '\0') - return -EINVAL; + ret = btrfs_check_replace_dev_names(args); + if (ret < 0) + return ret; ret = btrfs_dev_replace_start(fs_info, args->start.tgtdev_name, args->start.srcdevid, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 40152458e..5756edb37 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1643,12 +1643,12 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info) * * @objectid: root id * @anon_dev: preallocated anonymous block device number for new roots, - * pass 0 for new allocation. + * pass NULL for a new allocation. * @check_ref: whether to check root item references, If true, return -ENOENT * for orphan roots */ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev, + u64 objectid, dev_t *anon_dev, bool check_ref) { struct btrfs_root *root; @@ -1662,8 +1662,17 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info, again: root = btrfs_lookup_fs_root(fs_info, objectid); if (root) { - /* Shouldn't get preallocated anon_dev for cached roots */ - ASSERT(!anon_dev); + /* + * Some other caller may have read out the newly inserted + * subvolume already (for things like backref walk etc). Not + * that common but still possible. In that case, we just need + * to free the anon_dev. + */ + if (unlikely(anon_dev && *anon_dev)) { + free_anon_bdev(*anon_dev); + *anon_dev = 0; + } + if (check_ref && btrfs_root_refs(&root->root_item) == 0) { btrfs_put_root(root); return ERR_PTR(-ENOENT); @@ -1683,7 +1692,7 @@ again: goto fail; } - ret = btrfs_init_fs_root(root, anon_dev); + ret = btrfs_init_fs_root(root, anon_dev ? *anon_dev : 0); if (ret) goto fail; @@ -1719,7 +1728,7 @@ fail: * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root() * and once again by our caller. */ - if (anon_dev) + if (anon_dev && *anon_dev) root->anon_dev = 0; btrfs_put_root(root); return ERR_PTR(ret); @@ -1735,7 +1744,7 @@ fail: struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref) { - return btrfs_get_root_ref(fs_info, objectid, 0, check_ref); + return btrfs_get_root_ref(fs_info, objectid, NULL, check_ref); } /* @@ -1743,11 +1752,11 @@ struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, * the anonymous block device id * * @objectid: tree objectid - * @anon_dev: if zero, allocate a new anonymous block device or use the - * parameter value + * @anon_dev: if NULL, allocate a new anonymous block device or use the + * parameter value if not NULL */ struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev) + u64 objectid, dev_t *anon_dev) { return btrfs_get_root_ref(fs_info, objectid, anon_dev, true); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 7322af63c..24bddca86 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -65,7 +65,7 @@ void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info, u64 objectid, bool check_ref); struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info, - u64 objectid, dev_t anon_dev); + u64 objectid, dev_t *anon_dev); struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 objectid); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 82f92b565..f7f4bcc09 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3364,8 +3364,23 @@ out: unwritten_start += logical_len; clear_extent_uptodate(io_tree, unwritten_start, end, NULL); - /* Drop extent maps for the part of the extent we didn't write. */ - btrfs_drop_extent_map_range(inode, unwritten_start, end, false); + /* + * Drop extent maps for the part of the extent we didn't write. + * + * We have an exception here for the free_space_inode, this is + * because when we do btrfs_get_extent() on the free space inode + * we will search the commit root. If this is a new block group + * we won't find anything, and we will trip over the assert in + * writepage where we do ASSERT(em->block_start != + * EXTENT_MAP_HOLE). + * + * Theoretically we could also skip this for any NOCOW extent as + * we don't mess with the extent map tree in the NOCOW case, but + * for now simply skip this if we are the free space inode. + */ + if (!btrfs_is_free_space_inode(inode)) + btrfs_drop_extent_map_range(inode, unwritten_start, + end, false); /* * If the ordered extent had an IOERR or something else went @@ -10774,6 +10789,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE) return -EINVAL; + /* + * Compressed extents should always have checksums, so error out if we + * have a NOCOW file or inode was created while mounted with NODATASUM. + */ + if (inode->flags & BTRFS_INODE_NODATASUM) + return -EINVAL; + orig_count = iov_iter_count(from); /* The extent size must be sane. */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 8516c70b5..64b37afb7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -708,7 +708,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns, free_extent_buffer(leaf); leaf = NULL; - new_root = btrfs_get_new_fs_root(fs_info, objectid, anon_dev); + new_root = btrfs_get_new_fs_root(fs_info, objectid, &anon_dev); if (IS_ERR(new_root)) { ret = PTR_ERR(new_root); btrfs_abort_transaction(trans, ret); @@ -4695,6 +4695,11 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg) goto out; } + if (sa->create && is_fstree(sa->qgroupid)) { + ret = -EINVAL; + goto out; + } + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { ret = PTR_ERR(trans); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 96ec9ccc2..b3472bf6b 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1635,6 +1635,15 @@ out: return ret; } +static bool qgroup_has_usage(struct btrfs_qgroup *qgroup) +{ + return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 || + qgroup->excl > 0 || qgroup->excl_cmpr > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 || + qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0); +} + int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1654,6 +1663,11 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) goto out; } + if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) { + ret = -EBUSY; + goto out; + } + /* Check if there are no children of this qgroup */ if (!list_empty(&qgroup->members)) { ret = -EBUSY; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 4a4d65b5e..9f7ffd9ef 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6462,11 +6462,20 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (ret) goto out; } - if (sctx->cur_inode_last_extent < - sctx->cur_inode_size) { - ret = send_hole(sctx, sctx->cur_inode_size); - if (ret) + if (sctx->cur_inode_last_extent < sctx->cur_inode_size) { + ret = range_is_hole_in_parent(sctx, + sctx->cur_inode_last_extent, + sctx->cur_inode_size); + if (ret < 0) { goto out; + } else if (ret == 0) { + ret = send_hole(sctx, sctx->cur_inode_size); + if (ret < 0) + goto out; + } else { + /* Range is already a hole, skip. */ + ret = 0; + } } } if (need_truncate) { @@ -7852,7 +7861,7 @@ long btrfs_ioctl_send(struct inode *inode, struct btrfs_ioctl_send_args *arg) } if (arg->flags & ~BTRFS_SEND_FLAG_MASK) { - ret = -EINVAL; + ret = -EOPNOTSUPP; goto out; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 60db4c3b8..b172091f4 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1809,7 +1809,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, } key.offset = (u64)-1; - pending->snap = btrfs_get_new_fs_root(fs_info, objectid, pending->anon_dev); + pending->snap = btrfs_get_new_fs_root(fs_info, objectid, &pending->anon_dev); if (IS_ERR(pending->snap)) { ret = PTR_ERR(pending->snap); pending->snap = NULL; diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6..f449f7340 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ error_unsupported: dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index aa4efcabb..5f4df9588 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -805,6 +805,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 36052a362..57603782e 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1391,7 +1391,7 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, if (flushing & CEPH_CAP_XATTR_EXCL) { arg->old_xattr_buf = __ceph_build_xattrs_blob(ci); arg->xattr_version = ci->i_xattrs.version; - arg->xattr_buf = ci->i_xattrs.blob; + arg->xattr_buf = ceph_buffer_get(ci->i_xattrs.blob); } else { arg->xattr_buf = NULL; arg->old_xattr_buf = NULL; @@ -1457,6 +1457,7 @@ static void __send_cap(struct cap_msg_args *arg, struct ceph_inode_info *ci) encode_cap_msg(msg, arg); ceph_con_send(&arg->session->s_con, msg); ceph_buffer_put(arg->old_xattr_buf); + ceph_buffer_put(arg->xattr_buf); if (arg->wake) wake_up_all(&ci->i_cap_wq); } @@ -4597,12 +4598,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, struct inode *dir, int mds, int drop, int unless) { - struct dentry *parent = NULL; struct ceph_mds_request_release *rel = *p; struct ceph_dentry_info *di = ceph_dentry(dentry); int force = 0; int ret; + /* This shouldn't happen */ + BUG_ON(!dir); + /* * force an record for the directory caps if we have a dentry lease. * this is racy (can't take i_ceph_lock and d_lock together), but it @@ -4612,14 +4615,9 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry, spin_lock(&dentry->d_lock); if (di->lease_session && di->lease_session->s_mds == mds) force = 1; - if (!dir) { - parent = dget(dentry->d_parent); - dir = d_inode(parent); - } spin_unlock(&dentry->d_lock); ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force); - dput(parent); spin_lock(&dentry->d_lock); if (ret && di->lease_session && di->lease_session->s_mds == mds) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 82874be94..da9fcf48a 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3650,11 +3650,11 @@ static void handle_session(struct ceph_mds_session *session, if (session->s_state == CEPH_MDS_SESSION_RECONNECTING) pr_info("mds%d reconnect success\n", session->s_mds); + session->s_features = features; if (session->s_state == CEPH_MDS_SESSION_OPEN) { pr_notice("mds%d is already opened\n", session->s_mds); } else { session->s_state = CEPH_MDS_SESSION_OPEN; - session->s_features = features; renewed_caps(mdsc, session, 0); if (test_bit(CEPHFS_FEATURE_METRIC_COLLECT, &session->s_features)) diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 3fbabc98e..4a089d70e 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -379,10 +379,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2) ceph_decode_skip_8(p, end, bad_ext); /* required_client_features */ ceph_decode_skip_set(p, end, 64, bad_ext); + /* bal_rank_mask */ + ceph_decode_skip_string(p, end, bad_ext); + } + if (mdsmap_ev >= 18) { ceph_decode_64_safe(p, end, m->m_max_xattr_size, bad_ext); - } else { - /* This forces the usage of the (sync) SETXATTR Op */ - m->m_max_xattr_size = 0; } bad_ext: dout("mdsmap_decode m_enabled: %d, m_damaged: %d, m_num_laggy: %d\n", diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index f7fcf7f08..ca4932e6f 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -194,10 +194,10 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) } /* - * This function walks through the snaprealm for an inode and returns the - * ceph_snap_realm for the first snaprealm that has quotas set (max_files, + * This function walks through the snaprealm for an inode and set the + * realmp with the first snaprealm that has quotas set (max_files, * max_bytes, or any, depending on the 'which_quota' argument). If the root is - * reached, return the root ceph_snap_realm instead. + * reached, set the realmp with the root ceph_snap_realm instead. * * Note that the caller is responsible for calling ceph_put_snap_realm() on the * returned realm. @@ -208,18 +208,19 @@ void ceph_cleanup_quotarealms_inodes(struct ceph_mds_client *mdsc) * this function will return -EAGAIN; otherwise, the snaprealms walk-through * will be restarted. */ -static struct ceph_snap_realm *get_quota_realm(struct ceph_mds_client *mdsc, - struct inode *inode, - enum quota_get_realm which_quota, - bool retry) +static int get_quota_realm(struct ceph_mds_client *mdsc, struct inode *inode, + enum quota_get_realm which_quota, + struct ceph_snap_realm **realmp, bool retry) { struct ceph_inode_info *ci = NULL; struct ceph_snap_realm *realm, *next; struct inode *in; bool has_quota; + if (realmp) + *realmp = NULL; if (ceph_snap(inode) != CEPH_NOSNAP) - return NULL; + return 0; restart: realm = ceph_inode(inode)->i_snap_realm; @@ -245,7 +246,7 @@ restart: break; ceph_put_snap_realm(mdsc, realm); if (!retry) - return ERR_PTR(-EAGAIN); + return -EAGAIN; goto restart; } @@ -254,8 +255,11 @@ restart: iput(in); next = realm->parent; - if (has_quota || !next) - return realm; + if (has_quota || !next) { + if (realmp) + *realmp = realm; + return 0; + } ceph_get_snap_realm(mdsc, next); ceph_put_snap_realm(mdsc, realm); @@ -264,7 +268,7 @@ restart: if (realm) ceph_put_snap_realm(mdsc, realm); - return NULL; + return 0; } bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) @@ -272,6 +276,7 @@ bool ceph_quota_is_same_realm(struct inode *old, struct inode *new) struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(old->i_sb); struct ceph_snap_realm *old_realm, *new_realm; bool is_same; + int ret; restart: /* @@ -281,9 +286,9 @@ restart: * dropped and we can then restart the whole operation. */ down_read(&mdsc->snap_rwsem); - old_realm = get_quota_realm(mdsc, old, QUOTA_GET_ANY, true); - new_realm = get_quota_realm(mdsc, new, QUOTA_GET_ANY, false); - if (PTR_ERR(new_realm) == -EAGAIN) { + get_quota_realm(mdsc, old, QUOTA_GET_ANY, &old_realm, true); + ret = get_quota_realm(mdsc, new, QUOTA_GET_ANY, &new_realm, false); + if (ret == -EAGAIN) { up_read(&mdsc->snap_rwsem); if (old_realm) ceph_put_snap_realm(mdsc, old_realm); @@ -485,8 +490,8 @@ bool ceph_quota_update_statfs(struct ceph_fs_client *fsc, struct kstatfs *buf) bool is_updated = false; down_read(&mdsc->snap_rwsem); - realm = get_quota_realm(mdsc, d_inode(fsc->sb->s_root), - QUOTA_GET_MAX_BYTES, true); + get_quota_realm(mdsc, d_inode(fsc->sb->s_root), QUOTA_GET_MAX_BYTES, + &realm, true); up_read(&mdsc->snap_rwsem); if (!realm) return false; diff --git a/fs/dcache.c b/fs/dcache.c index 52e6d5fda..b09bc88db 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -787,12 +787,12 @@ static inline bool fast_dput(struct dentry *dentry) */ if (unlikely(ret < 0)) { spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count > 1) { - dentry->d_lockref.count--; + if (WARN_ON_ONCE(dentry->d_lockref.count <= 0)) { spin_unlock(&dentry->d_lock); return true; } - return false; + dentry->d_lockref.count--; + goto locked; } /* @@ -850,6 +850,7 @@ static inline bool fast_dput(struct dentry *dentry) * else could have killed it and marked it dead. Either way, we * don't need to do anything else. */ +locked: if (dentry->d_lockref.count) { spin_unlock(&dentry->d_lock); return true; diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 72f34f96d..2c797eb51 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -174,7 +174,7 @@ static LIST_HEAD(dlm_node_addrs); static DEFINE_SPINLOCK(dlm_node_addrs_spin); static struct listen_connection listen_con; -static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; +static struct sockaddr_storage dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; int dlm_allow_conn; @@ -398,7 +398,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out, if (!sa_out) return 0; - if (dlm_local_addr[0]->ss_family == AF_INET) { + if (dlm_local_addr[0].ss_family == AF_INET) { struct sockaddr_in *in4 = (struct sockaddr_in *) &sas; struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out; ret4->sin_addr.s_addr = in4->sin_addr.s_addr; @@ -727,7 +727,7 @@ static void add_sock(struct socket *sock, struct connection *con) static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, int *addr_len) { - saddr->ss_family = dlm_local_addr[0]->ss_family; + saddr->ss_family = dlm_local_addr[0].ss_family; if (saddr->ss_family == AF_INET) { struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr; in4_addr->sin_port = cpu_to_be16(port); @@ -1167,7 +1167,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { - memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr)); + memcpy(&localaddr, &dlm_local_addr[i], sizeof(localaddr)); make_sockaddr(&localaddr, port, &addr_len); if (!i) @@ -1187,7 +1187,7 @@ static int sctp_bind_addrs(struct socket *sock, uint16_t port) /* Get local addresses */ static void init_local(void) { - struct sockaddr_storage sas, *addr; + struct sockaddr_storage sas; int i; dlm_local_count = 0; @@ -1195,21 +1195,10 @@ static void init_local(void) if (dlm_our_addr(&sas, i)) break; - addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS); - if (!addr) - break; - dlm_local_addr[dlm_local_count++] = addr; + memcpy(&dlm_local_addr[dlm_local_count++], &sas, sizeof(sas)); } } -static void deinit_local(void) -{ - int i; - - for (i = 0; i < dlm_local_count; i++) - kfree(dlm_local_addr[i]); -} - static struct writequeue_entry *new_writequeue_entry(struct connection *con) { struct writequeue_entry *entry; @@ -1575,7 +1564,7 @@ static void dlm_connect(struct connection *con) } /* Create a socket to communicate with */ - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) goto socket_err; @@ -1786,7 +1775,6 @@ void dlm_lowcomms_stop(void) foreach_conn(free_conn); srcu_read_unlock(&connections_srcu, idx); work_stop(); - deinit_local(); dlm_proto_ops = NULL; } @@ -1803,7 +1791,7 @@ static int dlm_listen_for_all(void) if (result < 0) return result; - result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, + result = sock_create_kern(&init_net, dlm_local_addr[0].ss_family, SOCK_STREAM, dlm_proto_ops->proto, &sock); if (result < 0) { log_print("Can't create comms socket: %d", result); @@ -1842,7 +1830,7 @@ static int dlm_tcp_bind(struct socket *sock) /* Bind to our cluster-known address connecting to avoid * routing problems. */ - memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); + memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); result = kernel_bind(sock, (struct sockaddr *)&src_addr, @@ -1899,9 +1887,9 @@ static int dlm_tcp_listen_bind(struct socket *sock) int addr_len; /* Bind to our port */ - make_sockaddr(dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); + make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0], - addr_len); + addr_len); } static const struct dlm_proto_ops dlm_tcp_ops = { @@ -1992,7 +1980,7 @@ int dlm_lowcomms_start(void) error = work_start(); if (error) - goto fail_local; + goto fail; dlm_allow_conn = 1; @@ -2022,8 +2010,6 @@ fail_listen: fail_proto_ops: dlm_allow_conn = 0; work_stop(); -fail_local: - deinit_local(); fail: return error; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index c214fe098..55340ac61 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -76,6 +76,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode, if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) return ERR_PTR(-EXDEV); + + /* Reject dealing with casefold directories. */ + if (IS_CASEFOLDED(lower_inode)) { + pr_err_ratelimited("%s: Can't handle casefolded directory.\n", + __func__); + return ERR_PTR(-EREMOTE); + } + if (!igrab(lower_inode)) return ERR_PTR(-ESTALE); inode = iget5_locked(sb, (unsigned long)lower_inode, diff --git a/fs/efivarfs/vars.c b/fs/efivarfs/vars.c index 9e4f47808..13bc60698 100644 --- a/fs/efivarfs/vars.c +++ b/fs/efivarfs/vars.c @@ -372,7 +372,7 @@ static void dup_variable_bug(efi_char16_t *str16, efi_guid_t *vendor_guid, int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), void *data, bool duplicates, struct list_head *head) { - unsigned long variable_name_size = 1024; + unsigned long variable_name_size = 512; efi_char16_t *variable_name; efi_status_t status; efi_guid_t vendor_guid; @@ -389,12 +389,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), goto free; /* - * Per EFI spec, the maximum storage allocated for both - * the variable name and variable data is 1024 bytes. + * A small set of old UEFI implementations reject sizes + * above a certain threshold, the lowest seen in the wild + * is 512. */ do { - variable_name_size = 1024; + variable_name_size = 512; status = efivar_get_next_variable(&variable_name_size, variable_name, @@ -431,9 +432,13 @@ int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *), break; case EFI_NOT_FOUND: break; + case EFI_BUFFER_TOO_SMALL: + pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n", + variable_name_size); + status = EFI_NOT_FOUND; + break; default: - printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n", - status); + pr_warn("efivars: get_next_variable: status=%lx\n", status); status = EFI_NOT_FOUND; break; } diff --git a/fs/erofs/compress.h b/fs/erofs/compress.h index 26fa17009..c4a3187bd 100644 --- a/fs/erofs/compress.h +++ b/fs/erofs/compress.h @@ -21,6 +21,8 @@ struct z_erofs_decompress_req { }; struct z_erofs_decompressor { + int (*config)(struct super_block *sb, struct erofs_super_block *dsb, + void *data, int size); int (*decompress)(struct z_erofs_decompress_req *rq, struct page **pagepool); char *name; @@ -93,6 +95,8 @@ int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); /* prototypes for specific algorithms */ +int z_erofs_load_lzma_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size); int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool); #endif diff --git a/fs/erofs/data.c b/fs/erofs/data.c index b32801d71..9d20e5d23 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -440,4 +440,5 @@ const struct file_operations erofs_file_fops = { .read_iter = erofs_file_read_iter, .mmap = erofs_file_mmap, .splice_read = generic_file_splice_read, + .get_unmapped_area = thp_get_unmapped_area, }; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 0cfad7437..1eefa4411 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -24,11 +24,11 @@ struct z_erofs_lz4_decompress_ctx { unsigned int oend; }; -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int size) +static int z_erofs_load_lz4_config(struct super_block *sb, + struct erofs_super_block *dsb, void *data, int size) { struct erofs_sb_info *sbi = EROFS_SB(sb); + struct z_erofs_lz4_cfgs *lz4 = data; u16 distance; if (lz4) { @@ -374,17 +374,71 @@ static struct z_erofs_decompressor decompressors[] = { .name = "interlaced" }, [Z_EROFS_COMPRESSION_LZ4] = { + .config = z_erofs_load_lz4_config, .decompress = z_erofs_lz4_decompress, .name = "lz4" }, #ifdef CONFIG_EROFS_FS_ZIP_LZMA [Z_EROFS_COMPRESSION_LZMA] = { + .config = z_erofs_load_lzma_config, .decompress = z_erofs_lzma_decompress, .name = "lzma" }, #endif }; +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + unsigned int algs, alg; + erofs_off_t offset; + int size, ret = 0; + + if (!erofs_sb_has_compr_cfgs(sbi)) { + sbi->available_compr_algs = 1 << Z_EROFS_COMPRESSION_LZ4; + return z_erofs_load_lz4_config(sb, dsb, NULL, 0); + } + + sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); + if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { + erofs_err(sb, "unidentified algorithms %x, please upgrade kernel", + sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); + return -EOPNOTSUPP; + } + + offset = EROFS_SUPER_OFFSET + sbi->sb_size; + alg = 0; + for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { + void *data; + + if (!(algs & 1)) + continue; + + data = erofs_read_metadata(sb, &buf, &offset, &size); + if (IS_ERR(data)) { + ret = PTR_ERR(data); + break; + } + + if (alg >= ARRAY_SIZE(decompressors) || + !decompressors[alg].config) { + erofs_err(sb, "algorithm %d isn't enabled on this kernel", + alg); + ret = -EOPNOTSUPP; + } else { + ret = decompressors[alg].config(sb, + dsb, data, size); + } + + kfree(data); + if (ret) + break; + } + erofs_put_metabuf(&buf); + return ret; +} + int z_erofs_decompress(struct z_erofs_decompress_req *rq, struct page **pagepool) { diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index 49addc345..970464c4b 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -72,10 +72,10 @@ int z_erofs_lzma_init(void) } int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) + struct erofs_super_block *dsb, void *data, int size) { static DEFINE_MUTEX(lzma_resize_mutex); + struct z_erofs_lzma_cfgs *lzma = data; unsigned int dict_size, i; struct z_erofs_lzma *strm, *head = NULL; int err; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index d8d09fc3e..79a7a5815 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -471,6 +471,8 @@ struct erofs_map_dev { /* data.c */ extern const struct file_operations erofs_file_fops; +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); void *erofs_bread(struct erofs_buf *buf, struct inode *inode, @@ -565,9 +567,7 @@ void z_erofs_exit_zip_subsystem(void); int erofs_try_to_free_all_cached_pages(struct erofs_sb_info *sbi, struct erofs_workgroup *egrp); int erofs_try_to_free_cached_page(struct page *page); -int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len); +int z_erofs_parse_cfgs(struct super_block *sb, struct erofs_super_block *dsb); #else static inline void erofs_shrinker_register(struct super_block *sb) {} static inline void erofs_shrinker_unregister(struct super_block *sb) {} @@ -575,36 +575,14 @@ static inline int erofs_init_shrinker(void) { return 0; } static inline void erofs_exit_shrinker(void) {} static inline int z_erofs_init_zip_subsystem(void) { return 0; } static inline void z_erofs_exit_zip_subsystem(void) {} -static inline int z_erofs_load_lz4_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lz4_cfgs *lz4, int len) -{ - if (lz4 || dsb->u1.lz4_max_distance) { - erofs_err(sb, "lz4 algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA int z_erofs_lzma_init(void); void z_erofs_lzma_exit(void); -int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size); #else static inline int z_erofs_lzma_init(void) { return 0; } static inline int z_erofs_lzma_exit(void) { return 0; } -static inline int z_erofs_load_lzma_config(struct super_block *sb, - struct erofs_super_block *dsb, - struct z_erofs_lzma_cfgs *lzma, int size) { - if (lzma) { - erofs_err(sb, "lzma algorithm isn't enabled"); - return -EINVAL; - } - return 0; -} #endif /* !CONFIG_EROFS_FS_ZIP */ /* flags for erofs_fscache_register_cookie() */ diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 0dc347210..e8ccaa761 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -137,24 +137,24 @@ static void *find_target_block_classic(struct erofs_buf *target, /* string comparison without already matched prefix */ diff = erofs_dirnamecmp(name, &dname, &matched); - if (!diff) { - *_ndirents = 0; - goto out; - } else if (diff > 0) { - head = mid + 1; - startprfx = matched; - - if (!IS_ERR(candidate)) - erofs_put_metabuf(target); - *target = buf; - candidate = de; - *_ndirents = ndirents; - } else { + if (diff < 0) { erofs_put_metabuf(&buf); - back = mid - 1; endprfx = matched; + continue; + } + + if (!IS_ERR(candidate)) + erofs_put_metabuf(target); + *target = buf; + if (!diff) { + *_ndirents = 0; + return de; } + head = mid + 1; + startprfx = matched; + candidate = de; + *_ndirents = ndirents; continue; } out: /* free if the candidate is valid */ diff --git a/fs/erofs/super.c b/fs/erofs/super.c index bd8bf8fc2..f2647126c 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -126,8 +126,8 @@ static bool check_layout_compatibility(struct super_block *sb, #ifdef CONFIG_EROFS_FS_ZIP /* read variable-sized metadata, offset will be aligned by 4-byte */ -static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, - erofs_off_t *offset, int *lengthp) +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; @@ -159,64 +159,15 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, } return buffer; } - -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) -{ - struct erofs_sb_info *sbi = EROFS_SB(sb); - struct erofs_buf buf = __EROFS_BUF_INITIALIZER; - unsigned int algs, alg; - erofs_off_t offset; - int size, ret = 0; - - sbi->available_compr_algs = le16_to_cpu(dsb->u1.available_compr_algs); - if (sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS) { - erofs_err(sb, "try to load compressed fs with unsupported algorithms %x", - sbi->available_compr_algs & ~Z_EROFS_ALL_COMPR_ALGS); - return -EINVAL; - } - - offset = EROFS_SUPER_OFFSET + sbi->sb_size; - alg = 0; - for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { - void *data; - - if (!(algs & 1)) - continue; - - data = erofs_read_metadata(sb, &buf, &offset, &size); - if (IS_ERR(data)) { - ret = PTR_ERR(data); - break; - } - - switch (alg) { - case Z_EROFS_COMPRESSION_LZ4: - ret = z_erofs_load_lz4_config(sb, dsb, data, size); - break; - case Z_EROFS_COMPRESSION_LZMA: - ret = z_erofs_load_lzma_config(sb, dsb, data, size); - break; - default: - DBG_BUGON(1); - ret = -EFAULT; - } - kfree(data); - if (ret) - break; - } - erofs_put_metabuf(&buf); - return ret; -} #else -static int erofs_load_compr_cfgs(struct super_block *sb, - struct erofs_super_block *dsb) +static int z_erofs_parse_cfgs(struct super_block *sb, + struct erofs_super_block *dsb) { - if (dsb->u1.available_compr_algs) { - erofs_err(sb, "try to load compressed fs when compression is disabled"); - return -EINVAL; - } - return 0; + if (!dsb->u1.available_compr_algs) + return 0; + + erofs_err(sb, "compression disabled, unable to mount compressed EROFS"); + return -EOPNOTSUPP; } #endif @@ -398,10 +349,7 @@ static int erofs_read_superblock(struct super_block *sb) } /* parse on-disk compression configurations */ - if (erofs_sb_has_compr_cfgs(sbi)) - ret = erofs_load_compr_cfgs(sb, dsb); - else - ret = z_erofs_load_lz4_config(sb, dsb, NULL, 0); + ret = z_erofs_parse_cfgs(sb, dsb); if (ret < 0) goto out; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index cf9a2fa7f..47e71964e 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -652,7 +652,6 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (ztailpacking) { pcl->obj.index = 0; /* which indicates ztailpacking */ - pcl->pageofs_in = erofs_blkoff(map->m_pa); pcl->tailpacking_size = map->m_plen; } else { pcl->obj.index = map->m_pa >> PAGE_SHIFT; @@ -852,6 +851,7 @@ repeat: get_page(fe->map.buf.page); WRITE_ONCE(fe->pcl->compressed_bvecs[0].page, fe->map.buf.page); + fe->pcl->pageofs_in = map->m_pa & ~PAGE_MASK; fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE; } else { /* bind cache first when cached decompression is preferred */ diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0337b70b2..abcded1ac 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -610,7 +610,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, .map = map, }; int err = 0; - unsigned int lclusterbits, endoff; + unsigned int lclusterbits, endoff, afmt; unsigned long initial_lcn; unsigned long long ofs, end; @@ -700,17 +700,20 @@ static int z_erofs_do_map_blocks(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) - map->m_algorithmformat = - Z_EROFS_COMPRESSION_INTERLACED; - else - map->m_algorithmformat = - Z_EROFS_COMPRESSION_SHIFTED; - } else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { - map->m_algorithmformat = vi->z_algorithmtype[1]; + afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? + Z_EROFS_COMPRESSION_INTERLACED : + Z_EROFS_COMPRESSION_SHIFTED; } else { - map->m_algorithmformat = vi->z_algorithmtype[0]; + afmt = m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 ? + vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; + if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + afmt, vi->nid); + err = -EFSCORRUPTED; + goto unmap_out; + } } + map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index c648a493f..3204bd33e 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -18,7 +18,7 @@ #include #include -#define dprintk(fmt, args...) do{}while(0) +#define dprintk(fmt, args...) pr_debug(fmt, ##args) static int get_name(const struct path *path, char *name, struct dentry *child); @@ -132,8 +132,8 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, inode_unlock(dentry->d_inode); if (IS_ERR(parent)) { - dprintk("%s: get_parent of %ld failed, err %d\n", - __func__, dentry->d_inode->i_ino, PTR_ERR(parent)); + dprintk("get_parent of %lu failed, err %ld\n", + dentry->d_inode->i_ino, PTR_ERR(parent)); return parent; } @@ -147,7 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, dprintk("%s: found name: %s\n", __func__, nbuf); tmp = lookup_one_unlocked(mnt_user_ns(mnt), nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { - dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + dprintk("lookup failed: %ld\n", PTR_ERR(tmp)); err = PTR_ERR(tmp); goto out_err; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index aa5aadd70..67af684e4 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2229,7 +2229,7 @@ static int ext4_fill_es_cache_info(struct inode *inode, /* - * ext4_ext_determine_hole - determine hole around given block + * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole @@ -2241,9 +2241,9 @@ static int ext4_fill_es_cache_info(struct inode *inode, * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ -static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, - struct ext4_ext_path *path, - ext4_lblk_t *lblk) +static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; @@ -2270,30 +2270,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode, return len; } -/* - * ext4_ext_put_gap_in_cache: - * calculate boundaries of the gap that the requested block fits into - * and cache this gap - */ -static void -ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start, - ext4_lblk_t hole_len) -{ - struct extent_status es; - - ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, - hole_start + hole_len - 1, &es); - if (es.es_len) { - /* There's delayed extent containing lblock? */ - if (es.es_lblk <= hole_start) - return; - hole_len = min(es.es_lblk - hole_start, hole_len); - } - ext_debug(inode, " -> %u:%u\n", hole_start, hole_len); - ext4_es_insert_extent(inode, hole_start, hole_len, ~0, - EXTENT_STATUS_HOLE); -} - /* * ext4_ext_rm_idx: * removes index from the index block. @@ -4064,6 +4040,69 @@ static int get_implied_cluster_alloc(struct super_block *sb, return 0; } +/* + * Determine hole length around the given logical block, first try to + * locate and expand the hole from the given @path, and then adjust it + * if it's partially or completely converted to delayed extents, insert + * it into the extent cache tree if it's indeed a hole, finally return + * the length of the determined extent. + */ +static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, + struct ext4_ext_path *path, + ext4_lblk_t lblk) +{ + ext4_lblk_t hole_start, len; + struct extent_status es; + + hole_start = lblk; + len = ext4_ext_find_hole(inode, path, &hole_start); +again: + ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, + hole_start + len - 1, &es); + if (!es.es_len) + goto insert_hole; + + /* + * There's a delalloc extent in the hole, handle it if the delalloc + * extent is in front of, behind and straddle the queried range. + */ + if (lblk >= es.es_lblk + es.es_len) { + /* + * The delalloc extent is in front of the queried range, + * find again from the queried start block. + */ + len -= lblk - hole_start; + hole_start = lblk; + goto again; + } else if (in_range(lblk, es.es_lblk, es.es_len)) { + /* + * The delalloc extent containing lblk, it must have been + * added after ext4_map_blocks() checked the extent status + * tree, adjust the length to the delalloc extent's after + * lblk. + */ + len = es.es_lblk + es.es_len - lblk; + return len; + } else { + /* + * The delalloc extent is partially or completely behind + * the queried range, update hole length until the + * beginning of the delalloc extent. + */ + len = min(es.es_lblk - hole_start, len); + } + +insert_hole: + /* Put just found gap into cache to speed up subsequent requests */ + ext_debug(inode, " -> %u:%u\n", hole_start, len); + ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); + + /* Update hole_len to reflect hole size after lblk */ + if (hole_start != lblk) + len -= lblk - hole_start; + + return len; +} /* * Block allocation/map/preallocation routine for extents based files @@ -4181,22 +4220,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * we couldn't try to create block if create flag is zero */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { - ext4_lblk_t hole_start, hole_len; + ext4_lblk_t len; - hole_start = map->m_lblk; - hole_len = ext4_ext_determine_hole(inode, path, &hole_start); - /* - * put just found gap into cache to speed up - * subsequent requests - */ - ext4_ext_put_gap_in_cache(inode, hole_start, hole_len); + len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); - /* Update hole_len to reflect hole size after map->m_lblk */ - if (hole_start != map->m_lblk) - hole_len -= map->m_lblk - hole_start; map->m_pblk = 0; - map->m_len = min_t(unsigned int, map->m_len, hole_len); - + map->m_len = min_t(unsigned int, map->m_len, len); goto out; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 33be702d6..6a3e27771 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -831,7 +831,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp) struct ext4_sb_info *sbi = EXT4_SB(sb); int new_order; - if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0) + if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0) return; new_order = mb_avg_fragment_size_order(sb, @@ -1118,6 +1118,24 @@ void ext4_mb_generate_buddy(struct super_block *sb, atomic64_add(period, &sbi->s_mb_generation_time); } +static void mb_regenerate_buddy(struct ext4_buddy *e4b) +{ + int count; + int order = 1; + void *buddy; + + while ((buddy = mb_find_buddy(e4b, order++, &count))) + mb_set_bits(buddy, 0, count); + + e4b->bd_info->bb_fragments = 0; + memset(e4b->bd_info->bb_counters, 0, + sizeof(*e4b->bd_info->bb_counters) * + (e4b->bd_sb->s_blocksize_bits + 2)); + + ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy, + e4b->bd_bitmap, e4b->bd_group, e4b->bd_info); +} + /* The buddy information is attached the buddy cache inode * for convenience. The information regarding each group * is loaded via ext4_mb_load_buddy. The information involve @@ -1767,11 +1785,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, mb_check_buddy(e4b); mb_free_blocks_double(inode, e4b, first, count); - this_cpu_inc(discard_pa_seq); - e4b->bd_info->bb_free += count; - if (first < e4b->bd_info->bb_first_free) - e4b->bd_info->bb_first_free = first; - /* access memory sequentially: check left neighbour, * clear range and then check right neighbour */ @@ -1785,21 +1798,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_fsblk_t blocknr; + /* + * Fastcommit replay can free already freed blocks which + * corrupts allocation info. Regenerate it. + */ + if (sbi->s_mount_state & EXT4_FC_REPLAY) { + mb_regenerate_buddy(e4b); + goto check; + } + blocknr = ext4_group_first_block_no(sb, e4b->bd_group); blocknr += EXT4_C2B(sbi, block); - if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) { - ext4_grp_locked_error(sb, e4b->bd_group, - inode ? inode->i_ino : 0, - blocknr, - "freeing already freed block (bit %u); block bitmap corrupt.", - block); - ext4_mark_group_bitmap_corrupted( - sb, e4b->bd_group, + ext4_grp_locked_error(sb, e4b->bd_group, + inode ? inode->i_ino : 0, blocknr, + "freeing already freed block (bit %u); block bitmap corrupt.", + block); + ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT); - } - goto done; + return; } + this_cpu_inc(discard_pa_seq); + e4b->bd_info->bb_free += count; + if (first < e4b->bd_info->bb_first_free) + e4b->bd_info->bb_first_free = first; + /* let's maintain fragments counter */ if (left_is_free && right_is_free) e4b->bd_info->bb_fragments--; @@ -1824,9 +1847,9 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b, if (first <= last) mb_buddy_mark_free(e4b, first >> 1, last >> 1); -done: mb_set_largest_free_order(sb, e4b->bd_info); mb_update_avg_fragment_size(sb, e4b->bd_info); +check: mb_check_buddy(e4b); } @@ -2153,6 +2176,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, return err; ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex); if (max > 0) { @@ -2160,6 +2186,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac, ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -2188,12 +2215,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, if (err) return err; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) { - ext4_mb_unload_buddy(e4b); - return 0; - } - ext4_lock_group(ac->ac_sb, group); + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) + goto out; + max = mb_find_extent(e4b, ac->ac_g_ex.fe_start, ac->ac_g_ex.fe_len, &ex); ex.fe_logical = 0xDEADFA11; /* debug value */ @@ -2226,6 +2251,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac, ac->ac_b_ex = ex; ext4_mb_use_best_found(ac, e4b); } +out: ext4_unlock_group(ac->ac_sb, group); ext4_mb_unload_buddy(e4b); @@ -6444,13 +6470,15 @@ static int ext4_try_to_trim_range(struct super_block *sb, __acquires(ext4_group_lock_ptr(sb, e4b->bd_group)) __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) { - ext4_grpblk_t next, count, free_count; + ext4_grpblk_t next, count, free_count, last, origin_start; bool set_trimmed = false; void *bitmap; + last = ext4_last_grp_cluster(sb, e4b->bd_group); bitmap = e4b->bd_bitmap; - if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group)) + if (start == 0 && max >= last) set_trimmed = true; + origin_start = start; start = max(e4b->bd_info->bb_first_free, start); count = 0; free_count = 0; @@ -6459,7 +6487,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group)) start = mb_find_next_zero_bit(bitmap, max + 1, start); if (start > max) break; - next = mb_find_next_bit(bitmap, max + 1, start); + + next = mb_find_next_bit(bitmap, last + 1, start); + if (origin_start == 0 && next >= last) + set_trimmed = true; if ((next - start) >= minblocks) { int ret = ext4_trim_extent(sb, start, next - start, e4b); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index dedc9d445..8e3ff150b 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -621,6 +621,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, goto out; o_end = o_start + len; + *moved_len = 0; while (o_start < o_end) { struct ext4_extent *ex; ext4_lblk_t cur_blk, next_blk; @@ -675,7 +676,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, */ ext4_double_up_write_data_sem(orig_inode, donor_inode); /* Swap original branches with new branches */ - move_extent_per_page(o_filp, donor_inode, + *moved_len += move_extent_per_page(o_filp, donor_inode, orig_page_index, donor_page_index, offset_in_page, cur_len, unwritten, &ret); @@ -685,9 +686,6 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, o_start += cur_len; d_start += cur_len; } - *moved_len = o_start - orig_blk; - if (*moved_len > len) - *moved_len = len; out: if (*moved_len) { diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9833ab6db..f2ed15af7 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -231,17 +231,24 @@ struct ext4_new_flex_group_data { in the flex group */ __u16 *bg_flags; /* block group flags of groups in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ ext4_group_t count; /* number of groups in @groups */ }; +/* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + /* * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of * @flexbg_size. * * Returns NULL on failure otherwise address of the allocated structure. */ -static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) { struct ext4_new_flex_group_data *flex_gd; @@ -249,17 +256,18 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) - goto out2; - flex_gd->count = flexbg_size; + if (unlikely(flexbg_size > MAX_RESIZE_BG)) + flex_gd->resize_bg = MAX_RESIZE_BG; + else + flex_gd->resize_bg = flexbg_size; - flex_gd->groups = kmalloc_array(flexbg_size, + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); if (flex_gd->groups == NULL) goto out2; - flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16), + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), GFP_NOFS); if (flex_gd->bg_flags == NULL) goto out1; @@ -296,7 +304,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) */ static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - int flexbg_size) + unsigned int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; ext4_fsblk_t start_blk; @@ -397,12 +405,12 @@ next_group: group = group_data[0].group; printk(KERN_DEBUG "EXT4-fs: adding a flex group with " - "%d groups, flexbg size is %d:\n", flex_gd->count, + "%u groups, flexbg size is %u:\n", flex_gd->count, flexbg_size); for (i = 0; i < flex_gd->count; i++) { ext4_debug( - "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n", + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", ext4_bg_has_super(sb, group + i) ? "normal" : "no-super", group + i, group_data[i].blocks_count, @@ -1623,8 +1631,7 @@ exit: static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - ext4_fsblk_t n_blocks_count, - unsigned long flexbg_size) + ext4_fsblk_t n_blocks_count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1648,7 +1655,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, BUG_ON(last); ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last); - last_group = group | (flexbg_size - 1); + last_group = group | (flex_gd->resize_bg - 1); if (last_group > n_group) last_group = n_group; @@ -2010,8 +2017,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; - int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int err = 0; int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi); /* See if the device is actually as big as what was requested */ bh = ext4_sb_bread(sb, n_blocks_count - 1, 0); @@ -2152,8 +2160,7 @@ retry: /* Add flex groups. Note that a regular group is a * flex group with 1 group. */ - while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, - flexbg_size)) { + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { if (time_is_before_jiffies(last_update_time + HZ * 10)) { if (last_update_time) ext4_msg(sb, KERN_INFO, diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 4cb58e8d6..967262c37 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -55,6 +55,7 @@ struct f2fs_compress_ops { int (*init_decompress_ctx)(struct decompress_io_ctx *dic); void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); + bool (*is_level_valid)(int level); }; static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index) @@ -322,11 +323,21 @@ static int lz4_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool lz4_is_level_valid(int lvl) +{ +#ifdef CONFIG_F2FS_FS_LZ4HC + return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL); +#else + return lvl == 0; +#endif +} + static const struct f2fs_compress_ops f2fs_lz4_ops = { .init_compress_ctx = lz4_init_compress_ctx, .destroy_compress_ctx = lz4_destroy_compress_ctx, .compress_pages = lz4_compress_pages, .decompress_pages = lz4_decompress_pages, + .is_level_valid = lz4_is_level_valid, }; #endif @@ -490,6 +501,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) return 0; } +static bool zstd_is_level_valid(int lvl) +{ + return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel(); +} + static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_compress_ctx = zstd_init_compress_ctx, .destroy_compress_ctx = zstd_destroy_compress_ctx, @@ -497,6 +513,7 @@ static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_decompress_ctx = zstd_init_decompress_ctx, .destroy_decompress_ctx = zstd_destroy_decompress_ctx, .decompress_pages = zstd_decompress_pages, + .is_level_valid = zstd_is_level_valid, }; #endif @@ -555,6 +572,16 @@ bool f2fs_is_compress_backend_ready(struct inode *inode) return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } +bool f2fs_is_compress_level_valid(int alg, int lvl) +{ + const struct f2fs_compress_ops *cops = f2fs_cops[alg]; + + if (cops->is_level_valid) + return cops->is_level_valid(lvl); + + return lvl == 0; +} + static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); @@ -1026,8 +1053,10 @@ static void set_cluster_dirty(struct compress_ctx *cc) int i; for (i = 0; i < cc->cluster_size; i++) - if (cc->rpages[i]) + if (cc->rpages[i]) { set_page_dirty(cc->rpages[i]); + set_page_private_gcing(cc->rpages[i]); + } } static int prepare_compress_overwrite(struct compress_ctx *cc, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5c76ba764..e5a9498b8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -4219,6 +4219,7 @@ bool f2fs_compress_write_end(struct inode *inode, void *fsdata, int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock); void f2fs_compress_write_end_io(struct bio *bio, struct page *page); bool f2fs_is_compress_backend_ready(struct inode *inode); +bool f2fs_is_compress_level_valid(int alg, int lvl); int f2fs_init_compress_mempool(void); void f2fs_destroy_compress_mempool(void); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task); @@ -4283,6 +4284,7 @@ static inline bool f2fs_is_compress_backend_ready(struct inode *inode) /* not support compression */ return false; } +static inline bool f2fs_is_compress_level_valid(int alg, int lvl) { return false; } static inline struct page *f2fs_compress_control_page(struct page *page) { WARN_ON_ONCE(1); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index fd22854db..46e4960a9 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1326,6 +1326,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, } memcpy_page(pdst, 0, psrc, 0, PAGE_SIZE); set_page_dirty(pdst); + set_page_private_gcing(pdst); f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); @@ -4037,6 +4038,7 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len) f2fs_bug_on(F2FS_I_SB(inode), !page); set_page_dirty(page); + set_page_private_gcing(page); f2fs_put_page(page, 1); f2fs_put_page(page, 0); } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index dea95b48b..53a6487f9 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -683,7 +683,16 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - f2fs_reserve_new_block(&dn); + do { + err = f2fs_reserve_new_block(&dn); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + if (err) + goto err; continue; } @@ -691,12 +700,14 @@ retry_dn: if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { if (src == NULL_ADDR) { - err = f2fs_reserve_new_block(&dn); - while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)) + do { err = f2fs_reserve_new_block(&dn); - /* We should not get -ENOSPC */ - f2fs_bug_on(sbi, err); + if (err == -ENOSPC) { + f2fs_bug_on(sbi, 1); + break; + } + } while (err && + IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); if (err) goto err; } @@ -887,6 +898,8 @@ skip: if (!err && fix_curseg_write_pointer && !f2fs_readonly(sbi->sb) && f2fs_sb_has_blkzoned(sbi)) { err = f2fs_fix_curseg_write_pointer(sbi); + if (!err) + err = f2fs_check_write_pointer(sbi); ret = err; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 3805162dc..0c0d0671f 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -628,7 +628,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (level < LZ4HC_MIN_CLEVEL || level > LZ4HC_MAX_CLEVEL) { + if (!f2fs_is_compress_level_valid(COMPRESS_LZ4, level)) { f2fs_info(sbi, "invalid lz4hc compress level: %d", level); return -EINVAL; } @@ -666,7 +666,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (level < zstd_min_clevel() || level > zstd_max_clevel()) { + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 8eea709e3..4fe4b3393 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -123,6 +123,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); + vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has @@ -164,10 +165,20 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) file_accessed(file); ret = -ENOMEM; + + vm_flags = vma->vm_flags; + /* + * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip + * reserving here. Note: only for SHM hugetlbfs file, the inode + * flag S_PRIVATE is set. + */ + if (inode->i_flags & S_PRIVATE) + vm_flags |= VM_NORESERVE; + if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, - vma->vm_flags)) + vm_flags)) goto out; ret = 0; @@ -1350,6 +1361,7 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; + struct hstate *h; char *rest; unsigned long ps; int opt; @@ -1394,11 +1406,12 @@ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *par case Opt_pagesize: ps = memparse(param->string, &rest); - ctx->hstate = size_to_hstate(ps); - if (!ctx->hstate) { + h = size_to_hstate(ps); + if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } + ctx->hstate = h; return 0; case Opt_min_size: diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 4d56f6081..4462274e3 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -63,10 +63,10 @@ */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval); -static int dbBackSplit(dmtree_t * tp, int leafno); -static int dbJoin(dmtree_t * tp, int leafno, int newval); -static void dbAdjTree(dmtree_t * tp, int leafno, int newval); +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); @@ -2103,7 +2103,7 @@ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, * system. */ if (dp->tree.stree[word] == NOFREE) - dbBackSplit((dmtree_t *) & dp->tree, word); + dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } @@ -2189,7 +2189,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { @@ -2229,7 +2229,7 @@ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, * system of the leaves to reflect the current * allocation (size). */ - dbSplit(tp, word, size, NOFREE); + dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); @@ -2336,7 +2336,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, - dbMaxBud((u8 *) & dp->wmap[word])); + dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; @@ -2369,7 +2369,7 @@ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, /* update the leaf. */ - rc = dbJoin(tp, word, size); + rc = dbJoin(tp, word, size, false); if (rc) return rc; @@ -2521,16 +2521,16 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { - rc = dbBackSplit((dmtree_t *) dcp, leafno); + rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) { release_metapage(mp); return rc; } oldval = dcp->stree[ti]; } - dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval); + dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { - rc = dbJoin((dmtree_t *) dcp, leafno, newval); + rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) { release_metapage(mp); return rc; @@ -2561,7 +2561,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, - oldval); + oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system @@ -2571,9 +2571,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) - dcp, leafno); + dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, - dcp->budmin, oldval); + dcp->budmin, oldval, true); } /* release the buffer and return the error. @@ -2621,7 +2621,7 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) +static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; @@ -2643,7 +2643,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ - dbAdjTree(tp, leafno ^ budsz, cursz); + dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ @@ -2655,7 +2655,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) /* adjust the dmap tree to reflect the specified leaf's new * value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); } @@ -2686,7 +2686,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval) * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ -static int dbBackSplit(dmtree_t * tp, int leafno) +static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; @@ -2737,7 +2737,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * system in two. */ cursz = leaf[bud] - 1; - dbSplit(tp, bud, cursz, cursz); + dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } @@ -2765,7 +2765,7 @@ static int dbBackSplit(dmtree_t * tp, int leafno) * * RETURN VALUES: none */ -static int dbJoin(dmtree_t * tp, int leafno, int newval) +static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; @@ -2820,12 +2820,12 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) if (leafno < buddy) { /* leafno is the left buddy. */ - dbAdjTree(tp, buddy, NOFREE); + dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ - dbAdjTree(tp, leafno, NOFREE); + dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } @@ -2838,7 +2838,7 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) /* update the leaf value. */ - dbAdjTree(tp, leafno, newval); + dbAdjTree(tp, leafno, newval, is_ctl); return 0; } @@ -2859,15 +2859,20 @@ static int dbJoin(dmtree_t * tp, int leafno, int newval) * * RETURN VALUES: none */ -static void dbAdjTree(dmtree_t * tp, int leafno, int newval) +static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; - int max; + int max, size; + + size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); + if (WARN_ON_ONCE(lp >= size || lp < 0)) + return; + /* is the current value the same as the old value ? if so, * there is nothing to do. */ diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index 92b7c5334..031d8f570 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) { index = base + (lim >> 1); + if (stbl[index] < 0) { + rc = -EIO; + goto out; + } + if (p->header.flag & BT_LEAF) { /* uppercase leaf name to compare */ cmp = @@ -1970,7 +1975,7 @@ static int dtSplitRoot(tid_t tid, do { f = &rp->slot[fsi]; fsi = f->next; - } while (fsi != -1); + } while (fsi >= 0); f->next = n; } diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 6ed2e1d4c..ac42f8ee5 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2179,6 +2179,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* get the ag and iag numbers for this iag. */ agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + if (agno >= MAXAG || agno < 0) + return -EIO; + iagno = le32_to_cpu(iagp->iagnum); /* check if this is the last free extent within the diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index 48d1f70f7..21d8d4a5c 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb) } jfs_info("jfs_mount: ipimap:0x%p", ipimap); - /* map further access of per fileset inodes by the fileset inode */ - sbi->ipimap = ipimap; - /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); goto err_ipimap; } + /* map further access of per fileset inodes by the fileset inode */ + sbi->ipimap = ipimap; + return rc; /* diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 44842e6cf..a00e11ebf 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -669,6 +669,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, { struct kernfs_node *kn; + if (parent->mode & S_ISGID) { + /* this code block imitates inode_init_owner() for + * kernfs + */ + + if (parent->iattr) + gid = parent->iattr->ia_gid; + + if (flags & KERNFS_DIR) + mode |= S_ISGID; + } + kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 284b019cb..b72023a6b 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -52,6 +52,7 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, *filp = file; /* Set up the missing parts of the file_lock structure */ + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_start = (loff_t)lock->lock_start; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 9c1aa7544..4e30f3c50 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -659,11 +659,13 @@ nlmsvc_unlock(struct net *net, struct nlm_file *file, struct nlm_lock *lock) nlmsvc_cancel_blocked(net, file, lock); lock->fl.fl_type = F_UNLCK; - if (file->f_file[O_RDONLY]) - error = vfs_lock_file(file->f_file[O_RDONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_RDONLY]; + if (lock->fl.fl_file) + error = vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); - if (file->f_file[O_WRONLY]) - error = vfs_lock_file(file->f_file[O_WRONLY], F_SETLK, + lock->fl.fl_file = file->f_file[O_WRONLY]; + if (lock->fl.fl_file) + error |= vfs_lock_file(lock->fl.fl_file, F_SETLK, &lock->fl, NULL); return (error < 0)? nlm_lck_denied_nolocks : nlm_granted; @@ -697,9 +699,10 @@ nlmsvc_cancel_blocked(struct net *net, struct nlm_file *file, struct nlm_lock *l block = nlmsvc_lookup_block(file, lock); mutex_unlock(&file->f_mutex); if (block != NULL) { - mode = lock_to_openmode(&lock->fl); - vfs_cancel_lock(block->b_file->f_file[mode], - &block->b_call->a_args.lock.fl); + struct file_lock *fl = &block->b_call->a_args.lock.fl; + + mode = lock_to_openmode(fl); + vfs_cancel_lock(block->b_file->f_file[mode], fl); status = nlmsvc_unlink_block(block); nlmsvc_release_block(block); } diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index e35c05e27..32784f508 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -77,6 +77,7 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp, /* Set up the missing parts of the file_lock structure */ mode = lock_to_openmode(&lock->fl); + lock->fl.fl_flags = FL_POSIX; lock->fl.fl_file = file->f_file[mode]; lock->fl.fl_pid = current->tgid; lock->fl.fl_lmops = &nlmsvc_lock_operations; diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index 3515f17ea..e3b6229e7 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -210,7 +210,7 @@ nlm_traverse_locks(struct nlm_host *host, struct nlm_file *file, { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); struct nlm_host *lockhost; if (!flctx || list_empty_careful(&flctx->flc_posix)) @@ -265,7 +265,7 @@ nlm_file_inuse(struct nlm_file *file) { struct inode *inode = nlmsvc_file_inode(file); struct file_lock *fl; - struct file_lock_context *flctx = inode->i_flctx; + struct file_lock_context *flctx = locks_inode_context(inode); if (file->f_count || !list_empty(&file->f_blocks) || file->f_shares) return 1; diff --git a/fs/locks.c b/fs/locks.c index 1047ab2b1..7d0918b8f 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -175,7 +175,7 @@ locks_get_lock_context(struct inode *inode, int type) struct file_lock_context *ctx; /* paired with cmpxchg() below */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; @@ -194,7 +194,7 @@ locks_get_lock_context(struct inode *inode, int type) */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); @@ -247,7 +247,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, void locks_free_lock_context(struct inode *inode) { - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); @@ -891,7 +891,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) void *owner; void (*func)(void); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { fl->fl_type = F_UNLCK; return; @@ -1483,7 +1483,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); goto free_lock; @@ -1588,7 +1588,7 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) struct file_lock_context *ctx; struct file_lock *fl; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); fl = list_first_entry_or_null(&ctx->flc_lease, @@ -1634,7 +1634,7 @@ int fcntl_getlease(struct file *filp) int type = F_UNLCK; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); @@ -1823,7 +1823,7 @@ static int generic_delete_lease(struct file *filp, void *owner) struct file_lock_context *ctx; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; @@ -2562,7 +2562,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; @@ -2635,7 +2635,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); + ctx = locks_inode_context(locks_inode(filp)); if (!ctx) return; @@ -2682,7 +2682,7 @@ bool vfs_inode_has_locks(struct inode *inode) struct file_lock_context *ctx; bool ret; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return false; @@ -2863,7 +2863,7 @@ void show_fd_locks(struct seq_file *f, struct file_lock_context *ctx; int id = 0; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return; diff --git a/fs/namespace.c b/fs/namespace.c index 29a8d90dd..1533550f7 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4172,10 +4172,15 @@ static int do_mount_setattr(struct path *path, struct mount_kattr *kattr) /* * If this is an attached mount make sure it's located in the callers * mount namespace. If it's not don't let the caller interact with it. - * If this is a detached mount make sure it has an anonymous mount - * namespace attached to it, i.e. we've created it via OPEN_TREE_CLONE. + * + * If this mount doesn't have a parent it's most often simply a + * detached mount with an anonymous mount namespace. IOW, something + * that's simply not attached yet. But there are apparently also users + * that do change mount properties on the rootfs itself. That obviously + * neither has a parent nor is it a detached mount so we cannot + * unconditionally check for detached mounts. */ - if (!(mnt_has_parent(mnt) ? check_mnt(mnt) : is_anon_ns(mnt->mnt_ns))) + if ((mnt_has_parent(mnt) || !is_anon_ns(mnt->mnt_ns)) && !check_mnt(mnt)) goto out; /* diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 3fa77ad72..c8a57cfde 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -9,10 +9,10 @@ #define _TRACE_NFS4_H #include -#include +#include -#include -#include +#include +#include #define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 8c6cc5867..642f69218 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -11,9 +11,9 @@ #include #include -#include -#include -#include +#include +#include +#include #define nfs_show_cache_validity(v) \ __print_flags(v, "|", \ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f41d24b54..6a0606668 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -667,8 +667,10 @@ static int nfs_writepage_locked(struct page *page, int err; if (wbc->sync_mode == WB_SYNC_NONE && - NFS_SERVER(inode)->write_congested) + NFS_SERVER(inode)->write_congested) { + redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; + } nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_pageio_init_write(&pgio, inode, 0, diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index f6a2fd301..7c441f2bd 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -8,6 +8,7 @@ config NFSD select SUNRPC select EXPORTFS select NFS_ACL_SUPPORT if NFSD_V2_ACL + select NFS_ACL_SUPPORT if NFSD_V3_ACL depends on MULTIUSER help Choose Y here if you want to allow other computers to access @@ -26,19 +27,29 @@ config NFSD Below you can choose which versions of the NFS protocol are available to clients mounting the NFS server on this system. - Support for NFS version 2 (RFC 1094) is always available when + Support for NFS version 3 (RFC 1813) is always available when CONFIG_NFSD is selected. If unsure, say N. -config NFSD_V2_ACL - bool +config NFSD_V2 + bool "NFS server support for NFS version 2 (DEPRECATED)" depends on NFSD + default n + help + NFSv2 (RFC 1094) was the first publicly-released version of NFS. + Unless you are hosting ancient (1990's era) NFS clients, you don't + need this. + + If unsure, say N. + +config NFSD_V2_ACL + bool "NFS server support for the NFSv2 ACL protocol extension" + depends on NFSD_V2 config NFSD_V3_ACL bool "NFS server support for the NFSv3 ACL protocol extension" depends on NFSD - select NFSD_V2_ACL help Solaris NFS servers support an auxiliary NFSv3 ACL protocol that never became an official part of the NFS version 3 protocol. diff --git a/fs/nfsd/Makefile b/fs/nfsd/Makefile index 805c06d5f..6fffc8f03 100644 --- a/fs/nfsd/Makefile +++ b/fs/nfsd/Makefile @@ -10,9 +10,10 @@ obj-$(CONFIG_NFSD) += nfsd.o # this one should be compiled first, as the tracing macros can easily blow up nfsd-y += trace.o -nfsd-y += nfssvc.o nfsctl.o nfsproc.o nfsfh.o vfs.o \ - export.o auth.o lockd.o nfscache.o nfsxdr.o \ +nfsd-y += nfssvc.o nfsctl.o nfsfh.o vfs.o \ + export.o auth.o lockd.o nfscache.o \ stats.o filecache.o nfs3proc.o nfs3xdr.o +nfsd-$(CONFIG_NFSD_V2) += nfsproc.o nfsxdr.o nfsd-$(CONFIG_NFSD_V2_ACL) += nfs2acl.o nfsd-$(CONFIG_NFSD_V3_ACL) += nfs3acl.o nfsd-$(CONFIG_NFSD_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4idmap.o \ diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index e7e6e78d9..01d7fd108 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -12,6 +12,7 @@ #include "blocklayoutxdr.h" #include "pnfs.h" #include "filecache.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/blocklayoutxdr.c b/fs/nfsd/blocklayoutxdr.c index 2455dc8be..1ed2f691e 100644 --- a/fs/nfsd/blocklayoutxdr.c +++ b/fs/nfsd/blocklayoutxdr.c @@ -9,6 +9,7 @@ #include "nfsd.h" #include "blocklayoutxdr.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h index ee0e3aba4..d03f7f6a8 100644 --- a/fs/nfsd/export.h +++ b/fs/nfsd/export.h @@ -115,7 +115,6 @@ struct svc_export * rqst_find_fsidzero_export(struct svc_rqst *); int exp_rootfh(struct net *, struct auth_domain *, char *path, struct knfsd_fh *, int maxsize); __be32 exp_pseudoroot(struct svc_rqst *, struct svc_fh *); -__be32 nfserrno(int errno); static inline void exp_put(struct svc_export *exp) { diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 5cb8cce15..697acf5c3 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -1,7 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * Open file cache. + * The NFSD open file cache. * * (c) 2015 - Jeff Layton + * + * An nfsd_file object is a per-file collection of open state that binds + * together: + * - a struct file * + * - a user credential + * - a network namespace + * - a read-ahead context + * - monitoring for writeback errors + * + * nfsd_file objects are reference-counted. Consumers acquire a new + * object via the nfsd_file_acquire API. They manage their interest in + * the acquired object, and hence the object's reference count, via + * nfsd_file_get and nfsd_file_put. There are two varieties of nfsd_file + * object: + * + * * non-garbage-collected: When a consumer wants to precisely control + * the lifetime of a file's open state, it acquires a non-garbage- + * collected nfsd_file. The final nfsd_file_put releases the open + * state immediately. + * + * * garbage-collected: When a consumer does not control the lifetime + * of open state, it acquires a garbage-collected nfsd_file. The + * final nfsd_file_put allows the open state to linger for a period + * during which it may be re-used. */ #include @@ -186,12 +211,9 @@ static const struct rhashtable_params nfsd_file_rhash_params = { static void nfsd_file_schedule_laundrette(void) { - if ((atomic_read(&nfsd_file_rhash_tbl.nelems) == 0) || - test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 0) - return; - - queue_delayed_work(system_wq, &nfsd_filecache_laundrette, - NFSD_LAUNDRETTE_DELAY); + if (test_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags)) + queue_delayed_work(system_wq, &nfsd_filecache_laundrette, + NFSD_LAUNDRETTE_DELAY); } static void @@ -589,7 +611,8 @@ static void nfsd_file_gc_worker(struct work_struct *work) { nfsd_file_gc(); - nfsd_file_schedule_laundrette(); + if (list_lru_count(&nfsd_file_lru)) + nfsd_file_schedule_laundrette(); } static unsigned long diff --git a/fs/nfsd/flexfilelayout.c b/fs/nfsd/flexfilelayout.c index 070f90ed0..3ca530444 100644 --- a/fs/nfsd/flexfilelayout.c +++ b/fs/nfsd/flexfilelayout.c @@ -15,6 +15,7 @@ #include "flexfilelayoutxdr.h" #include "pnfs.h" +#include "vfs.h" #define NFSDDBG_FACILITY NFSDDBG_PNFS diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba32..51a4b7885 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/nfs4callback.c b/fs/nfsd/nfs4callback.c index 39989c14c..4eae2c5af 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -76,6 +76,17 @@ static __be32 *xdr_encode_empty_array(__be32 *p) * 1 Protocol" */ +static void encode_uint32(struct xdr_stream *xdr, u32 n) +{ + WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0); +} + +static void encode_bitmap4(struct xdr_stream *xdr, const __u32 *bitmap, + size_t len) +{ + WARN_ON_ONCE(xdr_stream_encode_uint32_array(xdr, bitmap, len) < 0); +} + /* * nfs_cb_opnum4 * @@ -328,6 +339,24 @@ static void encode_cb_recall4args(struct xdr_stream *xdr, hdr->nops++; } +/* + * CB_RECALLANY4args + * + * struct CB_RECALLANY4args { + * uint32_t craa_objects_to_keep; + * bitmap4 craa_type_mask; + * }; + */ +static void +encode_cb_recallany4args(struct xdr_stream *xdr, + struct nfs4_cb_compound_hdr *hdr, struct nfsd4_cb_recall_any *ra) +{ + encode_nfs_cb_opnum4(xdr, OP_CB_RECALL_ANY); + encode_uint32(xdr, ra->ra_keep); + encode_bitmap4(xdr, ra->ra_bmval, ARRAY_SIZE(ra->ra_bmval)); + hdr->nops++; +} + /* * CB_SEQUENCE4args * @@ -482,6 +511,26 @@ static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr, encode_cb_nops(&hdr); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static void +nfs4_xdr_enc_cb_recall_any(struct rpc_rqst *req, + struct xdr_stream *xdr, const void *data) +{ + const struct nfsd4_callback *cb = data; + struct nfsd4_cb_recall_any *ra; + struct nfs4_cb_compound_hdr hdr = { + .ident = cb->cb_clp->cl_cb_ident, + .minorversion = cb->cb_clp->cl_minorversion, + }; + + ra = container_of(cb, struct nfsd4_cb_recall_any, ra_cb); + encode_cb_compound4args(xdr, &hdr); + encode_cb_sequence4args(xdr, cb, &hdr); + encode_cb_recallany4args(xdr, &hdr, ra); + encode_cb_nops(&hdr); +} /* * NFSv4.0 and NFSv4.1 XDR decode functions @@ -520,6 +569,28 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp, return decode_cb_op_status(xdr, OP_CB_RECALL, &cb->cb_status); } +/* + * 20.6. Operation 8: CB_RECALL_ANY - Keep Any N Recallable Objects + */ +static int +nfs4_xdr_dec_cb_recall_any(struct rpc_rqst *rqstp, + struct xdr_stream *xdr, + void *data) +{ + struct nfsd4_callback *cb = data; + struct nfs4_cb_compound_hdr hdr; + int status; + + status = decode_cb_compound4res(xdr, &hdr); + if (unlikely(status)) + return status; + status = decode_cb_sequence4res(xdr, cb); + if (unlikely(status || cb->cb_seq_status)) + return status; + status = decode_cb_op_status(xdr, OP_CB_RECALL_ANY, &cb->cb_status); + return status; +} + #ifdef CONFIG_NFSD_PNFS /* * CB_LAYOUTRECALL4args @@ -783,6 +854,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = { #endif PROC(CB_NOTIFY_LOCK, COMPOUND, cb_notify_lock, cb_notify_lock), PROC(CB_OFFLOAD, COMPOUND, cb_offload, cb_offload), + PROC(CB_RECALL_ANY, COMPOUND, cb_recall_any, cb_recall_any), }; static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)]; diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c index e70a1a299..5e9809aff 100644 --- a/fs/nfsd/nfs4idmap.c +++ b/fs/nfsd/nfs4idmap.c @@ -41,6 +41,7 @@ #include "idmap.h" #include "nfsd.h" #include "netns.h" +#include "vfs.h" /* * Turn off idmapping when using AUTH_SYS. diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a9105e95b..ba53cd89e 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -943,12 +943,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &read->rd_stateid, RD_STATE, &read->rd_nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_read: couldn't process stateid!\n"); - goto out; - } - status = nfs_ok; -out: + read->rd_rqstp = rqstp; read->rd_fhp = &cstate->current_fh; return status; @@ -1117,10 +1112,8 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &setattr->sa_stateid, WR_STATE, NULL, NULL); - if (status) { - dprintk("NFSD: nfsd4_setattr: couldn't process stateid!\n"); + if (status) return status; - } } err = fh_want_write(&cstate->current_fh); if (err) @@ -1170,10 +1163,8 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_offset, cnt); status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, stateid, WR_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_write: couldn't process stateid!\n"); + if (status) return status; - } write->wr_how_written = write->wr_stable_how; @@ -1204,17 +1195,13 @@ nfsd4_verify_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->save_fh, src_stateid, RD_STATE, src, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process src stateid!\n", __func__); + if (status) goto out; - } status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, dst_stateid, WR_STATE, dst, NULL); - if (status) { - dprintk("NFSD: %s: couldn't process dst stateid!\n", __func__); + if (status) goto out_put_src; - } /* fix up for NFS-specific error code */ if (!S_ISREG(file_inode((*src)->nf_file)->i_mode) || @@ -1935,10 +1922,8 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &fallocate->falloc_stateid, WR_STATE, &nf, NULL); - if (status != nfs_ok) { - dprintk("NFSD: nfsd4_fallocate: couldn't process stateid!\n"); + if (status != nfs_ok) return status; - } status = nfsd4_vfs_fallocate(rqstp, &cstate->current_fh, nf->nf_file, fallocate->falloc_offset, @@ -1994,10 +1979,8 @@ nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &seek->seek_stateid, RD_STATE, &nf, NULL); - if (status) { - dprintk("NFSD: nfsd4_seek: couldn't process stateid!\n"); + if (status) return status; - } switch (seek->seek_whence) { case NFS4_CONTENT_DATA: diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index faecdbfa0..b9d694ec2 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -44,7 +44,9 @@ #include #include #include +#include #include + #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -84,6 +86,7 @@ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); +static void nfsd4_file_hash_remove(struct nfs4_file *fi); /* Locking: */ @@ -588,11 +591,8 @@ static void nfsd4_free_file_rcu(struct rcu_head *rcu) void put_nfs4_file(struct nfs4_file *fi) { - might_lock(&state_lock); - - if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del_rcu(&fi->fi_hash); - spin_unlock(&state_lock); + if (refcount_dec_and_test(&fi->fi_ref)) { + nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); @@ -717,19 +717,20 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; } -/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) +static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; -static unsigned int file_hashval(struct svc_fh *fh) -{ - struct inode *inode = d_inode(fh->fh_dentry); - - /* XXX: why not (here & in file cache) use inode? */ - return (unsigned int)hash_long(inode->i_ino, FILE_HASH_BITS); -} +static const struct rhashtable_params nfs4_file_rhash_params = { + .key_len = sizeof_field(struct nfs4_file, fi_inode), + .key_offset = offsetof(struct nfs4_file, fi_inode), + .head_offset = offsetof(struct nfs4_file, fi_rlist), -static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +}; /* * Check if courtesy clients have conflicting access and resolve it if possible @@ -1367,6 +1368,8 @@ static void revoke_delegation(struct nfs4_delegation *dp) WARN_ON(!list_empty(&dp->dl_recall_lru)); + trace_nfsd_stid_revoke(&dp->dl_stid); + if (clp->cl_minorversion) { spin_lock(&clp->cl_lock); dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; @@ -1831,13 +1834,12 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; - int mem, i; + int i; - BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) - + sizeof(struct nfsd4_session) > PAGE_SIZE); - mem = numslots * sizeof(struct nfsd4_slot *); + BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) + > PAGE_SIZE); - new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); if (!new) return NULL; /* allocate each struct nfsd4_slot and data cache in one piece */ @@ -2143,6 +2145,7 @@ static void __free_client(struct kref *k) kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); + kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); } @@ -2870,6 +2873,37 @@ static const struct tree_descr client_files[] = { [3] = {""}, }; +static int +nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, + struct rpc_task *task) +{ + trace_nfsd_cb_recall_any_done(cb, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + spin_lock(&nn->client_lock); + clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + put_client_renew_locked(clp); + spin_unlock(&nn->client_lock); +} + +static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { + .done = nfsd4_cb_recall_any_done, + .release = nfsd4_cb_recall_any_release, +}; + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2907,6 +2941,14 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); + if (!clp->cl_ra) { + free_client(clp); + return NULL; + } + clp->cl_ra_time = 0; + nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, + NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } @@ -4276,11 +4318,9 @@ static struct nfs4_file *nfsd4_alloc_file(void) } /* OPEN Share state helper functions */ -static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, - struct nfs4_file *fp) -{ - lockdep_assert_held(&state_lock); +static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) +{ refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); @@ -4298,7 +4338,6 @@ static void nfsd4_init_file(struct svc_fh *fh, unsigned int hashval, INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif - hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } void @@ -4363,25 +4402,27 @@ out: } static unsigned long -nfsd_courtesy_client_count(struct shrinker *shrink, struct shrink_control *sc) +nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { - int cnt; + int count; struct nfsd_net *nn = container_of(shrink, struct nfsd_net, nfsd_client_shrinker); - cnt = atomic_read(&nn->nfsd_courtesy_clients); - if (cnt > 0) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); - return (unsigned long)cnt; + count = atomic_read(&nn->nfsd_courtesy_clients); + if (!count) + count = atomic_long_read(&num_delegations); + if (count) + queue_work(laundry_wq, &nn->nfsd_shrinker_work); + return (unsigned long)count; } static unsigned long -nfsd_courtesy_client_scan(struct shrinker *shrink, struct shrink_control *sc) +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; @@ -4403,16 +4444,6 @@ 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 = nfsd_courtesy_client_scan; - nn->nfsd_client_shrinker.count_objects = nfsd_courtesy_client_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) @@ -4683,71 +4714,80 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) nfs4_put_stid(&last->st_stid); } -/* search file_hashtbl[] for file */ -static struct nfs4_file * -find_file_locked(struct svc_fh *fh, unsigned int hashval) +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_lookup(const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *fi; - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - return fp; + rcu_read_lock(); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) { + rcu_read_unlock(); + return fi; + } } } + rcu_read_unlock(); return NULL; } -static struct nfs4_file *insert_file(struct nfs4_file *new, struct svc_fh *fh, - unsigned int hashval) +/* + * On hash insertion, identify entries with the same inode but + * distinct filehandles. They will all be on the list returned + * by rhltable_lookup(). + * + * inode->i_lock prevents racing insertions from adding an entry + * for the same inode/fhp pair twice. + */ +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; + struct nfs4_file *fi; + int err; - spin_lock(&state_lock); - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash, - lockdep_is_held(&state_lock)) { - if (fh_match(&fp->fi_fhandle, &fh->fh_handle)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - ret = fp; - } else if (d_inode(fh->fh_dentry) == fp->fi_inode) - fp->fi_aliased = alias_found = true; - } - if (likely(ret == NULL)) { - nfsd4_init_file(fh, hashval, new); - new->fi_aliased = alias_found; - ret = new; + rcu_read_lock(); + spin_lock(&inode->i_lock); + + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) + ret = fi; + } else + fi->fi_aliased = alias_found = true; } - spin_unlock(&state_lock); - return ret; -} + if (ret) + goto out_unlock; -static struct nfs4_file * find_file(struct svc_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); + nfsd4_file_init(fhp, new); + err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, + nfs4_file_rhash_params); + if (err) + goto out_unlock; - rcu_read_lock(); - fp = find_file_locked(fh, hashval); + new->fi_aliased = alias_found; + ret = new; + +out_unlock: + spin_unlock(&inode->i_lock); rcu_read_unlock(); - return fp; + return ret; } -static struct nfs4_file * -find_or_add_file(struct nfs4_file *new, struct svc_fh *fh) +static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); - - rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - if (fp) - return fp; - - return insert_file(new, fh, hashval); + rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, + nfs4_file_rhash_params); } /* @@ -4760,9 +4800,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) struct nfs4_file *fp; __be32 ret = nfs_ok; - fp = find_file(current_fh); + fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; + /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) @@ -4774,7 +4815,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) static bool nfsd4_deleg_present(const struct inode *inode) { - struct file_lock_context *ctx = smp_load_acquire(&inode->i_flctx); + struct file_lock_context *ctx = locks_inode_context(inode); return ctx && !list_empty_careful(&ctx->flc_lease); } @@ -4908,10 +4949,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); return false; } @@ -5499,12 +5538,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); @@ -5656,7 +5696,9 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ - fp = find_or_add_file(open->op_file, current_fh); + fp = nfsd4_file_hash_insert(open->op_file, current_fh); + if (unlikely(!fp)) + return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) @@ -5933,7 +5975,7 @@ nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { nf = stp->st_stid.sc_file; - ctx = nf->fi_inode->i_flctx; + ctx = locks_inode_context(nf->fi_inode); if (!ctx) continue; if (locks_owner_has_blockers(ctx, lo)) @@ -6161,17 +6203,63 @@ laundromat_main(struct work_struct *laundry) } static void -courtesy_client_reaper(struct work_struct *reaper) +courtesy_client_reaper(struct nfsd_net *nn) { struct list_head reaplist; - struct delayed_work *dwork = to_delayed_work(reaper); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, - nfsd_shrinker_work); nfs4_get_courtesy_client_reaplist(nn, &reaplist); nfs4_process_client_reaplist(&reaplist); } +static void +deleg_reaper(struct nfsd_net *nn) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + struct list_head cblist; + + INIT_LIST_HEAD(&cblist); + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + if (clp->cl_state != NFSD4_ACTIVE || + list_empty(&clp->cl_delegations) || + atomic_read(&clp->cl_delegs_in_recall) || + test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || + (ktime_get_boottime_seconds() - + clp->cl_ra_time < 5)) { + continue; + } + list_add(&clp->cl_ra_cblist, &cblist); + + /* release in nfsd4_cb_recall_any_release */ + atomic_inc(&clp->cl_rpc_users); + set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); + clp->cl_ra_time = ktime_get_boottime_seconds(); + } + spin_unlock(&nn->client_lock); + + while (!list_empty(&cblist)) { + clp = list_first_entry(&cblist, struct nfs4_client, + cl_ra_cblist); + list_del_init(&clp->cl_ra_cblist); + clp->cl_ra->ra_keep = 0; + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG); + trace_nfsd_cb_recall_any(clp->cl_ra); + nfsd4_run_cb(&clp->cl_ra->ra_cb); + } +} + +static void +nfsd4_state_shrinker_worker(struct work_struct *work) +{ + struct nfsd_net *nn = container_of(work, struct nfsd_net, + nfsd_shrinker_work); + + courtesy_client_reaper(nn); + deleg_reaper(nn); +} + static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) @@ -6936,6 +7024,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + trace_nfsd_deleg_return(stateid); wake_up_var(d_inode(cstate->current_fh.fh_dentry)); destroy_delegation(dp); put_stateid: @@ -7736,18 +7825,20 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct nfsd_file *nf = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } inode = locks_inode(nf->nf_file); - flctx = inode->i_flctx; + flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); @@ -7759,7 +7850,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) } spin_unlock(&flctx->flc_lock); } - nfsd_file_put(nf); +out: + spin_unlock(&fp->fi_lock); return status; } @@ -7769,10 +7861,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * - * The lockowner's so_count is bumped when a lock record is added - * or when copying a conflicting lock. The latter case is brief, - * but can lead to fleeting false positives when looking for - * locks-in-use. + * Check if theree are any locks still held and if not - free the lockowner + * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found @@ -7808,10 +7898,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, spin_unlock(&clp->cl_lock); return nfs_ok; } - if (atomic_read(&lo->lo_owner.so_count) != 2) { - spin_unlock(&clp->cl_lock); - nfs4_put_stateowner(&lo->lo_owner); - return nfserr_locks_held; + + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { @@ -7992,11 +8085,20 @@ 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, courtesy_client_reaper); + 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: @@ -8068,10 +8170,16 @@ nfs4_state_start(void) { int ret; - ret = nfsd4_create_callback_queue(); + ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) return ret; + ret = nfsd4_create_callback_queue(); + if (ret) { + rhltable_destroy(&nfs4_file_rhltable); + return ret; + } + set_max_delegations(); return 0; } @@ -8083,6 +8191,8 @@ 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); @@ -8111,6 +8221,7 @@ void nfs4_state_shutdown(void) { nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 89a579be0..597f14a80 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -770,16 +770,18 @@ nfsd4_decode_cb_sec(struct nfsd4_compoundargs *argp, struct nfsd4_cb_sec *cbs) static __be32 nfsd4_decode_access(struct nfsd4_compoundargs *argp, - struct nfsd4_access *access) + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; if (xdr_stream_decode_u32(argp->xdr, &access->ac_req_access) < 0) return nfserr_bad_xdr; return nfs_ok; } static __be32 -nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) +nfsd4_decode_close(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; if (xdr_stream_decode_u32(argp->xdr, &close->cl_seqid) < 0) return nfserr_bad_xdr; return nfsd4_decode_stateid4(argp, &close->cl_stateid); @@ -787,8 +789,9 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) static __be32 -nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit) +nfsd4_decode_commit(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; if (xdr_stream_decode_u64(argp->xdr, &commit->co_offset) < 0) return nfserr_bad_xdr; if (xdr_stream_decode_u32(argp->xdr, &commit->co_count) < 0) @@ -798,8 +801,9 @@ nfsd4_decode_commit(struct nfsd4_compoundargs *argp, struct nfsd4_commit *commit } static __be32 -nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create) +nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; __be32 *p, status; memset(create, 0, sizeof(*create)); @@ -844,22 +848,25 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create } static inline __be32 -nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) +nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_delegreturn *dr = &u->delegreturn; return nfsd4_decode_stateid4(argp, &dr->dr_stateid); } static inline __be32 -nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, struct nfsd4_getattr *getattr) +nfsd4_decode_getattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; memset(getattr, 0, sizeof(*getattr)); return nfsd4_decode_bitmap4(argp, getattr->ga_bmval, ARRAY_SIZE(getattr->ga_bmval)); } static __be32 -nfsd4_decode_link(struct nfsd4_compoundargs *argp, struct nfsd4_link *link) +nfsd4_decode_link(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; memset(link, 0, sizeof(*link)); return nfsd4_decode_component4(argp, &link->li_name, &link->li_namelen); } @@ -907,8 +914,9 @@ nfsd4_decode_locker4(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) +nfsd4_decode_lock(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; memset(lock, 0, sizeof(*lock)); if (xdr_stream_decode_u32(argp->xdr, &lock->lk_type) < 0) return nfserr_bad_xdr; @@ -924,8 +932,9 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) } static __be32 -nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) +nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; memset(lockt, 0, sizeof(*lockt)); if (xdr_stream_decode_u32(argp->xdr, &lockt->lt_type) < 0) return nfserr_bad_xdr; @@ -940,8 +949,9 @@ nfsd4_decode_lockt(struct nfsd4_compoundargs *argp, struct nfsd4_lockt *lockt) } static __be32 -nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) +nfsd4_decode_locku(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; __be32 status; if (xdr_stream_decode_u32(argp->xdr, &locku->lu_type) < 0) @@ -962,8 +972,9 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) } static __be32 -nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, struct nfsd4_lookup *lookup) +nfsd4_decode_lookup(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_lookup *lookup = &u->lookup; return nfsd4_decode_component4(argp, &lookup->lo_name, &lookup->lo_len); } @@ -1143,8 +1154,9 @@ nfsd4_decode_open_claim4(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) +nfsd4_decode_open(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; __be32 status; u32 dummy; @@ -1171,8 +1183,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) } static __be32 -nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_confirm *open_conf) +nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *open_conf = &u->open_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1190,8 +1204,10 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con } static __be32 -nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_downgrade *open_down) +nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *open_down = &u->open_downgrade; __be32 status; memset(open_down, 0, sizeof(*open_down)); @@ -1209,8 +1225,9 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d } static __be32 -nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) +nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_putfh *putfh = &u->putfh; __be32 *p; if (xdr_stream_decode_u32(argp->xdr, &putfh->pf_fhlen) < 0) @@ -1229,7 +1246,7 @@ nfsd4_decode_putfh(struct nfsd4_compoundargs *argp, struct nfsd4_putfh *putfh) } static __be32 -nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { if (argp->minorversion == 0) return nfs_ok; @@ -1237,8 +1254,9 @@ nfsd4_decode_putpubfh(struct nfsd4_compoundargs *argp, void *p) } static __be32 -nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) +nfsd4_decode_read(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; __be32 status; memset(read, 0, sizeof(*read)); @@ -1254,8 +1272,9 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) } static __be32 -nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *readdir) +nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; __be32 status; memset(readdir, 0, sizeof(*readdir)); @@ -1276,15 +1295,17 @@ nfsd4_decode_readdir(struct nfsd4_compoundargs *argp, struct nfsd4_readdir *read } static __be32 -nfsd4_decode_remove(struct nfsd4_compoundargs *argp, struct nfsd4_remove *remove) +nfsd4_decode_remove(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; memset(&remove->rm_cinfo, 0, sizeof(remove->rm_cinfo)); return nfsd4_decode_component4(argp, &remove->rm_name, &remove->rm_namelen); } static __be32 -nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename) +nfsd4_decode_rename(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; __be32 status; memset(rename, 0, sizeof(*rename)); @@ -1295,22 +1316,25 @@ nfsd4_decode_rename(struct nfsd4_compoundargs *argp, struct nfsd4_rename *rename } static __be32 -nfsd4_decode_renew(struct nfsd4_compoundargs *argp, clientid_t *clientid) +nfsd4_decode_renew(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + clientid_t *clientid = &u->renew; return nfsd4_decode_clientid4(argp, clientid); } static __be32 nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; secinfo->si_exp = NULL; return nfsd4_decode_component4(argp, &secinfo->si_name, &secinfo->si_namelen); } static __be32 -nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) +nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; __be32 status; memset(setattr, 0, sizeof(*setattr)); @@ -1324,8 +1348,9 @@ nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *seta } static __be32 -nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid *setclientid) +nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_setclientid *setclientid = &u->setclientid; __be32 *p, status; memset(setclientid, 0, sizeof(*setclientid)); @@ -1367,8 +1392,10 @@ nfsd4_decode_setclientid(struct nfsd4_compoundargs *argp, struct nfsd4_setclient } static __be32 -nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_setclientid_confirm *scd_c) +nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_setclientid_confirm *scd_c = &u->setclientid_confirm; __be32 status; if (argp->minorversion >= 1) @@ -1382,8 +1409,9 @@ nfsd4_decode_setclientid_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_s /* Also used for NVERIFY */ static __be32 -nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify) +nfsd4_decode_verify(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_verify *verify = &u->verify; __be32 *p, status; memset(verify, 0, sizeof(*verify)); @@ -1409,8 +1437,9 @@ nfsd4_decode_verify(struct nfsd4_compoundargs *argp, struct nfsd4_verify *verify } static __be32 -nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) +nfsd4_decode_write(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; __be32 status; status = nfsd4_decode_stateid4(argp, &write->wr_stateid); @@ -1434,8 +1463,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) } static __be32 -nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_release_lockowner *rlockowner) +nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; __be32 status; if (argp->minorversion >= 1) @@ -1452,16 +1483,20 @@ nfsd4_decode_release_lockowner(struct nfsd4_compoundargs *argp, struct nfsd4_rel return nfs_ok; } -static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, struct nfsd4_backchannel_ctl *bc) +static __be32 nfsd4_decode_backchannel_ctl(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; memset(bc, 0, sizeof(*bc)); if (xdr_stream_decode_u32(argp->xdr, &bc->bc_cb_program) < 0) return nfserr_bad_xdr; return nfsd4_decode_cb_sec(argp, &bc->bc_cb_sec); } -static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_decode_bind_conn_to_session(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; u32 use_conn_in_rdma_mode; __be32 status; @@ -1603,8 +1638,9 @@ nfsd4_decode_nfs_impl_id4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_exchange_id(struct nfsd4_compoundargs *argp, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; __be32 status; memset(exid, 0, sizeof(*exid)); @@ -1656,8 +1692,9 @@ nfsd4_decode_channel_attrs4(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; __be32 status; memset(sess, 0, sizeof(*sess)); @@ -1681,23 +1718,26 @@ nfsd4_decode_create_session(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_destroy_session(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_session *destroy_session) + union nfsd4_op_u *u) { + struct nfsd4_destroy_session *destroy_session = &u->destroy_session; return nfsd4_decode_sessionid4(argp, &destroy_session->sessionid); } static __be32 nfsd4_decode_free_stateid(struct nfsd4_compoundargs *argp, - struct nfsd4_free_stateid *free_stateid) + union nfsd4_op_u *u) { + struct nfsd4_free_stateid *free_stateid = &u->free_stateid; return nfsd4_decode_stateid4(argp, &free_stateid->fr_stateid); } #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; __be32 status; memset(gdev, 0, sizeof(*gdev)); @@ -1717,8 +1757,9 @@ nfsd4_decode_getdeviceinfo(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; __be32 *p, status; memset(lcp, 0, sizeof(*lcp)); @@ -1753,8 +1794,9 @@ nfsd4_decode_layoutcommit(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; __be32 status; memset(lgp, 0, sizeof(*lgp)); @@ -1781,8 +1823,9 @@ nfsd4_decode_layoutget(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; memset(lrp, 0, sizeof(*lrp)); if (xdr_stream_decode_bool(argp->xdr, &lrp->lr_reclaim) < 0) return nfserr_bad_xdr; @@ -1795,8 +1838,9 @@ nfsd4_decode_layoutreturn(struct nfsd4_compoundargs *argp, #endif /* CONFIG_NFSD_PNFS */ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, - struct nfsd4_secinfo_no_name *sin) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; @@ -1806,8 +1850,9 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; __be32 *p, status; status = nfsd4_decode_sessionid4(argp, &seq->sessionid); @@ -1826,8 +1871,10 @@ nfsd4_decode_sequence(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_stateid *test_stateid) +nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; __be32 status; u32 i; @@ -1852,14 +1899,16 @@ nfsd4_decode_test_stateid(struct nfsd4_compoundargs *argp, struct nfsd4_test_sta } static __be32 nfsd4_decode_destroy_clientid(struct nfsd4_compoundargs *argp, - struct nfsd4_destroy_clientid *dc) + union nfsd4_op_u *u) { + struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; return nfsd4_decode_clientid4(argp, &dc->clientid); } static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, - struct nfsd4_reclaim_complete *rc) + union nfsd4_op_u *u) { + struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; if (xdr_stream_decode_bool(argp->xdr, &rc->rca_one_fs) < 0) return nfserr_bad_xdr; return nfs_ok; @@ -1867,8 +1916,9 @@ static __be32 nfsd4_decode_reclaim_complete(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_fallocate(struct nfsd4_compoundargs *argp, - struct nfsd4_fallocate *fallocate) + union nfsd4_op_u *u) { + struct nfsd4_fallocate *fallocate = &u->allocate; __be32 status; status = nfsd4_decode_stateid4(argp, &fallocate->falloc_stateid); @@ -1924,8 +1974,9 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, } static __be32 -nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) +nfsd4_decode_copy(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; u32 consecutive, i, count, sync; struct nl4_server *ns_dummy; __be32 status; @@ -1982,8 +2033,9 @@ nfsd4_decode_copy(struct nfsd4_compoundargs *argp, struct nfsd4_copy *copy) static __be32 nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; __be32 status; memset(cn, 0, sizeof(*cn)); @@ -2002,16 +2054,18 @@ nfsd4_decode_copy_notify(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_offload_status(struct nfsd4_compoundargs *argp, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; os->count = 0; os->status = 0; return nfsd4_decode_stateid4(argp, &os->stateid); } static __be32 -nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) +nfsd4_decode_seek(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 status; status = nfsd4_decode_stateid4(argp, &seek->seek_stateid); @@ -2028,8 +2082,9 @@ nfsd4_decode_seek(struct nfsd4_compoundargs *argp, struct nfsd4_seek *seek) } static __be32 -nfsd4_decode_clone(struct nfsd4_compoundargs *argp, struct nfsd4_clone *clone) +nfsd4_decode_clone(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { + struct nfsd4_clone *clone = &u->clone; __be32 status; status = nfsd4_decode_stateid4(argp, &clone->cl_src_stateid); @@ -2154,8 +2209,9 @@ nfsd4_decode_xattr_name(struct nfsd4_compoundargs *argp, char **namep) */ static __be32 nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; __be32 status; u32 maxcount; @@ -2173,8 +2229,9 @@ nfsd4_decode_getxattr(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; u32 flags, maxcount, size; __be32 status; @@ -2214,8 +2271,9 @@ nfsd4_decode_setxattr(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; u32 maxcount; memset(listxattrs, 0, sizeof(*listxattrs)); @@ -2245,113 +2303,114 @@ nfsd4_decode_listxattrs(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_removexattr(struct nfsd4_compoundargs *argp, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; memset(removexattr, 0, sizeof(*removexattr)); return nfsd4_decode_xattr_name(argp, &removexattr->rmxa_name); } static __be32 -nfsd4_decode_noop(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_noop(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfs_ok; } static __be32 -nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, void *p) +nfsd4_decode_notsupp(struct nfsd4_compoundargs *argp, union nfsd4_op_u *p) { return nfserr_notsupp; } -typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, void *); +typedef __be32(*nfsd4_dec)(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u); static const nfsd4_dec nfsd4_dec_ops[] = { - [OP_ACCESS] = (nfsd4_dec)nfsd4_decode_access, - [OP_CLOSE] = (nfsd4_dec)nfsd4_decode_close, - [OP_COMMIT] = (nfsd4_dec)nfsd4_decode_commit, - [OP_CREATE] = (nfsd4_dec)nfsd4_decode_create, - [OP_DELEGPURGE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DELEGRETURN] = (nfsd4_dec)nfsd4_decode_delegreturn, - [OP_GETATTR] = (nfsd4_dec)nfsd4_decode_getattr, - [OP_GETFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_LINK] = (nfsd4_dec)nfsd4_decode_link, - [OP_LOCK] = (nfsd4_dec)nfsd4_decode_lock, - [OP_LOCKT] = (nfsd4_dec)nfsd4_decode_lockt, - [OP_LOCKU] = (nfsd4_dec)nfsd4_decode_locku, - [OP_LOOKUP] = (nfsd4_dec)nfsd4_decode_lookup, - [OP_LOOKUPP] = (nfsd4_dec)nfsd4_decode_noop, - [OP_NVERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_OPEN] = (nfsd4_dec)nfsd4_decode_open, - [OP_OPENATTR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OPEN_CONFIRM] = (nfsd4_dec)nfsd4_decode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_dec)nfsd4_decode_open_downgrade, - [OP_PUTFH] = (nfsd4_dec)nfsd4_decode_putfh, - [OP_PUTPUBFH] = (nfsd4_dec)nfsd4_decode_putpubfh, - [OP_PUTROOTFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_READ] = (nfsd4_dec)nfsd4_decode_read, - [OP_READDIR] = (nfsd4_dec)nfsd4_decode_readdir, - [OP_READLINK] = (nfsd4_dec)nfsd4_decode_noop, - [OP_REMOVE] = (nfsd4_dec)nfsd4_decode_remove, - [OP_RENAME] = (nfsd4_dec)nfsd4_decode_rename, - [OP_RENEW] = (nfsd4_dec)nfsd4_decode_renew, - [OP_RESTOREFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SAVEFH] = (nfsd4_dec)nfsd4_decode_noop, - [OP_SECINFO] = (nfsd4_dec)nfsd4_decode_secinfo, - [OP_SETATTR] = (nfsd4_dec)nfsd4_decode_setattr, - [OP_SETCLIENTID] = (nfsd4_dec)nfsd4_decode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_dec)nfsd4_decode_setclientid_confirm, - [OP_VERIFY] = (nfsd4_dec)nfsd4_decode_verify, - [OP_WRITE] = (nfsd4_dec)nfsd4_decode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_dec)nfsd4_decode_release_lockowner, + [OP_ACCESS] = nfsd4_decode_access, + [OP_CLOSE] = nfsd4_decode_close, + [OP_COMMIT] = nfsd4_decode_commit, + [OP_CREATE] = nfsd4_decode_create, + [OP_DELEGPURGE] = nfsd4_decode_notsupp, + [OP_DELEGRETURN] = nfsd4_decode_delegreturn, + [OP_GETATTR] = nfsd4_decode_getattr, + [OP_GETFH] = nfsd4_decode_noop, + [OP_LINK] = nfsd4_decode_link, + [OP_LOCK] = nfsd4_decode_lock, + [OP_LOCKT] = nfsd4_decode_lockt, + [OP_LOCKU] = nfsd4_decode_locku, + [OP_LOOKUP] = nfsd4_decode_lookup, + [OP_LOOKUPP] = nfsd4_decode_noop, + [OP_NVERIFY] = nfsd4_decode_verify, + [OP_OPEN] = nfsd4_decode_open, + [OP_OPENATTR] = nfsd4_decode_notsupp, + [OP_OPEN_CONFIRM] = nfsd4_decode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_decode_open_downgrade, + [OP_PUTFH] = nfsd4_decode_putfh, + [OP_PUTPUBFH] = nfsd4_decode_putpubfh, + [OP_PUTROOTFH] = nfsd4_decode_noop, + [OP_READ] = nfsd4_decode_read, + [OP_READDIR] = nfsd4_decode_readdir, + [OP_READLINK] = nfsd4_decode_noop, + [OP_REMOVE] = nfsd4_decode_remove, + [OP_RENAME] = nfsd4_decode_rename, + [OP_RENEW] = nfsd4_decode_renew, + [OP_RESTOREFH] = nfsd4_decode_noop, + [OP_SAVEFH] = nfsd4_decode_noop, + [OP_SECINFO] = nfsd4_decode_secinfo, + [OP_SETATTR] = nfsd4_decode_setattr, + [OP_SETCLIENTID] = nfsd4_decode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_decode_setclientid_confirm, + [OP_VERIFY] = nfsd4_decode_verify, + [OP_WRITE] = nfsd4_decode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_decode_release_lockowner, /* new operations for NFSv4.1 */ - [OP_BACKCHANNEL_CTL] = (nfsd4_dec)nfsd4_decode_backchannel_ctl, - [OP_BIND_CONN_TO_SESSION]= (nfsd4_dec)nfsd4_decode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_dec)nfsd4_decode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_dec)nfsd4_decode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_dec)nfsd4_decode_destroy_session, - [OP_FREE_STATEID] = (nfsd4_dec)nfsd4_decode_free_stateid, - [OP_GET_DIR_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_BACKCHANNEL_CTL] = nfsd4_decode_backchannel_ctl, + [OP_BIND_CONN_TO_SESSION] = nfsd4_decode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_decode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_decode_create_session, + [OP_DESTROY_SESSION] = nfsd4_decode_destroy_session, + [OP_FREE_STATEID] = nfsd4_decode_free_stateid, + [OP_GET_DIR_DELEGATION] = nfsd4_decode_notsupp, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_decode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_decode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_decode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_GETDEVICELIST] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTCOMMIT] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTGET] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTRETURN] = (nfsd4_dec)nfsd4_decode_notsupp, + [OP_GETDEVICEINFO] = nfsd4_decode_notsupp, + [OP_GETDEVICELIST] = nfsd4_decode_notsupp, + [OP_LAYOUTCOMMIT] = nfsd4_decode_notsupp, + [OP_LAYOUTGET] = nfsd4_decode_notsupp, + [OP_LAYOUTRETURN] = nfsd4_decode_notsupp, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_dec)nfsd4_decode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_dec)nfsd4_decode_sequence, - [OP_SET_SSV] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_TEST_STATEID] = (nfsd4_dec)nfsd4_decode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_DESTROY_CLIENTID] = (nfsd4_dec)nfsd4_decode_destroy_clientid, - [OP_RECLAIM_COMPLETE] = (nfsd4_dec)nfsd4_decode_reclaim_complete, + [OP_SECINFO_NO_NAME] = nfsd4_decode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_decode_sequence, + [OP_SET_SSV] = nfsd4_decode_notsupp, + [OP_TEST_STATEID] = nfsd4_decode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_decode_notsupp, + [OP_DESTROY_CLIENTID] = nfsd4_decode_destroy_clientid, + [OP_RECLAIM_COMPLETE] = nfsd4_decode_reclaim_complete, /* new operations for NFSv4.2 */ - [OP_ALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_COPY] = (nfsd4_dec)nfsd4_decode_copy, - [OP_COPY_NOTIFY] = (nfsd4_dec)nfsd4_decode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_dec)nfsd4_decode_fallocate, - [OP_IO_ADVISE] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTERROR] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_LAYOUTSTATS] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_OFFLOAD_CANCEL] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_OFFLOAD_STATUS] = (nfsd4_dec)nfsd4_decode_offload_status, - [OP_READ_PLUS] = (nfsd4_dec)nfsd4_decode_read, - [OP_SEEK] = (nfsd4_dec)nfsd4_decode_seek, - [OP_WRITE_SAME] = (nfsd4_dec)nfsd4_decode_notsupp, - [OP_CLONE] = (nfsd4_dec)nfsd4_decode_clone, + [OP_ALLOCATE] = nfsd4_decode_fallocate, + [OP_COPY] = nfsd4_decode_copy, + [OP_COPY_NOTIFY] = nfsd4_decode_copy_notify, + [OP_DEALLOCATE] = nfsd4_decode_fallocate, + [OP_IO_ADVISE] = nfsd4_decode_notsupp, + [OP_LAYOUTERROR] = nfsd4_decode_notsupp, + [OP_LAYOUTSTATS] = nfsd4_decode_notsupp, + [OP_OFFLOAD_CANCEL] = nfsd4_decode_offload_status, + [OP_OFFLOAD_STATUS] = nfsd4_decode_offload_status, + [OP_READ_PLUS] = nfsd4_decode_read, + [OP_SEEK] = nfsd4_decode_seek, + [OP_WRITE_SAME] = nfsd4_decode_notsupp, + [OP_CLONE] = nfsd4_decode_clone, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_dec)nfsd4_decode_getxattr, - [OP_SETXATTR] = (nfsd4_dec)nfsd4_decode_setxattr, - [OP_LISTXATTRS] = (nfsd4_dec)nfsd4_decode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_dec)nfsd4_decode_removexattr, + [OP_GETXATTR] = nfsd4_decode_getxattr, + [OP_SETXATTR] = nfsd4_decode_setxattr, + [OP_LISTXATTRS] = nfsd4_decode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_decode_removexattr, }; static inline bool @@ -3643,8 +3702,10 @@ nfsd4_encode_stateid(struct xdr_stream *xdr, stateid_t *sid) } static __be32 -nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) +nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_access *access = &u->access; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3656,8 +3717,10 @@ nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ return 0; } -static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_bind_conn_to_session *bcts) +static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3673,8 +3736,10 @@ static __be32 nfsd4_encode_bind_conn_to_session(struct nfsd4_compoundres *resp, } static __be32 -nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_close *close) +nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_close *close = &u->close; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &close->cl_stateid); @@ -3682,8 +3747,10 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c static __be32 -nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_commit *commit) +nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_commit *commit = &u->commit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3696,8 +3763,10 @@ nfsd4_encode_commit(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_create *create) +nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_create *create = &u->create; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3710,8 +3779,10 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_getattr *getattr) +nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_getattr *getattr = &u->getattr; struct svc_fh *fhp = getattr->ga_fhp; struct xdr_stream *xdr = resp->xdr; @@ -3720,8 +3791,10 @@ nfsd4_encode_getattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, struct svc_fh **fhpp) +nfsd4_encode_getfh(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct svc_fh **fhpp = &u->getfh; struct xdr_stream *xdr = resp->xdr; struct svc_fh *fhp = *fhpp; unsigned int len; @@ -3775,8 +3848,10 @@ again: } static __be32 -nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lock *lock) +nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lock *lock = &u->lock; struct xdr_stream *xdr = resp->xdr; if (!nfserr) @@ -3788,8 +3863,10 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo } static __be32 -nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lockt *lockt) +nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_lockt *lockt = &u->lockt; struct xdr_stream *xdr = resp->xdr; if (nfserr == nfserr_denied) @@ -3798,8 +3875,10 @@ nfsd4_encode_lockt(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l } static __be32 -nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_locku *locku) +nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_locku *locku = &u->locku; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &locku->lu_stateid); @@ -3807,8 +3886,10 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l static __be32 -nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_link *link) +nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_link *link = &u->link; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3821,8 +3902,10 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 -nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) +nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open *open = &u->open; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -3915,16 +3998,20 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op } static __be32 -nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) +nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_confirm *oc = &u->open_confirm; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &oc->oc_resp_stateid); } static __be32 -nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) +nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_open_downgrade *od = &u->open_downgrade; struct xdr_stream *xdr = resp->xdr; return nfsd4_encode_stateid(xdr, &od->od_stateid); @@ -4023,8 +4110,9 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, static __be32 nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { + struct nfsd4_read *read = &u->read; bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); unsigned long maxcount; struct xdr_stream *xdr = resp->xdr; @@ -4065,8 +4153,10 @@ nfsd4_encode_read(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 -nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readlink *readlink) +nfsd4_encode_readlink(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readlink *readlink = &u->readlink; __be32 *p, *maxcount_p, zero = xdr_zero; struct xdr_stream *xdr = resp->xdr; int length_offset = xdr->buf->len; @@ -4110,8 +4200,10 @@ out_err: } static __be32 -nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_readdir *readdir) +nfsd4_encode_readdir(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_readdir *readdir = &u->readdir; int maxcount; int bytes_left; loff_t offset; @@ -4201,8 +4293,10 @@ err_no_verf: } static __be32 -nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_remove *remove) +nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_remove *remove = &u->remove; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4214,8 +4308,10 @@ nfsd4_encode_remove(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_ } static __be32 -nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_rename *rename) +nfsd4_encode_rename(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_rename *rename = &u->rename; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4297,8 +4393,9 @@ nfsd4_do_encode_secinfo(struct xdr_stream *xdr, struct svc_export *exp) static __be32 nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo *secinfo = &u->secinfo; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->si_exp); @@ -4306,8 +4403,9 @@ nfsd4_encode_secinfo(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_secinfo_no_name *secinfo) + union nfsd4_op_u *u) { + struct nfsd4_secinfo_no_name *secinfo = &u->secinfo_no_name; struct xdr_stream *xdr = resp->xdr; return nfsd4_do_encode_secinfo(xdr, secinfo->sin_exp); @@ -4318,8 +4416,10 @@ nfsd4_encode_secinfo_no_name(struct nfsd4_compoundres *resp, __be32 nfserr, * regardless of the error status. */ static __be32 -nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setattr *setattr) +nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setattr *setattr = &u->setattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4342,8 +4442,10 @@ nfsd4_encode_setattr(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4 } static __be32 -nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_setclientid *scd) +nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_setclientid *scd = &u->setclientid; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4366,8 +4468,10 @@ nfsd4_encode_setclientid(struct nfsd4_compoundres *resp, __be32 nfserr, struct n } static __be32 -nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_write *write) +nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *u) { + struct nfsd4_write *write = &u->write; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4383,8 +4487,9 @@ nfsd4_encode_write(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_w static __be32 nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_exchange_id *exid) + union nfsd4_op_u *u) { + struct nfsd4_exchange_id *exid = &u->exchange_id; struct xdr_stream *xdr = resp->xdr; __be32 *p; char *major_id; @@ -4461,8 +4566,9 @@ nfsd4_encode_exchange_id(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_create_session *sess) + union nfsd4_op_u *u) { + struct nfsd4_create_session *sess = &u->create_session; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4514,8 +4620,9 @@ nfsd4_encode_create_session(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_sequence *seq) + union nfsd4_op_u *u) { + struct nfsd4_sequence *seq = &u->sequence; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4537,8 +4644,9 @@ nfsd4_encode_sequence(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_test_stateid *test_stateid) + union nfsd4_op_u *u) { + struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct xdr_stream *xdr = resp->xdr; struct nfsd4_test_stateid_id *stateid, *next; __be32 *p; @@ -4558,8 +4666,9 @@ nfsd4_encode_test_stateid(struct nfsd4_compoundres *resp, __be32 nfserr, #ifdef CONFIG_NFSD_PNFS static __be32 nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getdeviceinfo *gdev) + union nfsd4_op_u *u) { + struct nfsd4_getdeviceinfo *gdev = &u->getdeviceinfo; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; u32 starting_len = xdr->buf->len, needed_len; @@ -4611,8 +4720,9 @@ toosmall: static __be32 nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutget *lgp) + union nfsd4_op_u *u) { + struct nfsd4_layoutget *lgp = &u->layoutget; struct xdr_stream *xdr = resp->xdr; const struct nfsd4_layout_ops *ops; __be32 *p; @@ -4638,8 +4748,9 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutcommit *lcp) + union nfsd4_op_u *u) { + struct nfsd4_layoutcommit *lcp = &u->layoutcommit; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4659,8 +4770,9 @@ nfsd4_encode_layoutcommit(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_layoutreturn(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_layoutreturn *lrp) + union nfsd4_op_u *u) { + struct nfsd4_layoutreturn *lrp = &u->layoutreturn; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4745,8 +4857,9 @@ nfsd42_encode_nl4_server(struct nfsd4_compoundres *resp, struct nl4_server *ns) static __be32 nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy *copy) + union nfsd4_op_u *u) { + struct nfsd4_copy *copy = &u->copy; __be32 *p; nfserr = nfsd42_encode_write_res(resp, ©->cp_res, @@ -4762,8 +4875,9 @@ nfsd4_encode_copy(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_offload_status *os) + union nfsd4_op_u *u) { + struct nfsd4_offload_status *os = &u->offload_status; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4777,156 +4891,83 @@ nfsd4_encode_offload_status(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_read_plus_data(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof, - loff_t *pos) + struct nfsd4_read *read) { - struct xdr_stream *xdr = resp->xdr; + bool splice_ok = test_bit(RQ_SPLICE_OK, &resp->rqstp->rq_flags); struct file *file = read->rd_nf->nf_file; - int starting_len = xdr->buf->len; - loff_t hole_pos; - __be32 nfserr; - __be32 *p, tmp; - __be64 tmp64; - - hole_pos = pos ? *pos : vfs_llseek(file, read->rd_offset, SEEK_HOLE); - if (hole_pos > read->rd_offset) - *maxcount = min_t(unsigned long, *maxcount, hole_pos - read->rd_offset); - *maxcount = min_t(unsigned long, *maxcount, (xdr->buf->buflen - xdr->buf->len)); + struct xdr_stream *xdr = resp->xdr; + unsigned long maxcount; + __be32 nfserr, *p; /* Content type, offset, byte count */ p = xdr_reserve_space(xdr, 4 + 8 + 4); if (!p) - return nfserr_resource; + return nfserr_io; + if (resp->xdr->buf->page_len && splice_ok) { + WARN_ON_ONCE(splice_ok); + return nfserr_serverfault; + } - read->rd_vlen = xdr_reserve_space_vec(xdr, resp->rqstp->rq_vec, *maxcount); - if (read->rd_vlen < 0) - return nfserr_resource; + maxcount = min_t(unsigned long, read->rd_length, + (xdr->buf->buflen - xdr->buf->len)); - nfserr = nfsd_readv(resp->rqstp, read->rd_fhp, file, read->rd_offset, - resp->rqstp->rq_vec, read->rd_vlen, maxcount, eof); + if (file->f_op->splice_read && splice_ok) + nfserr = nfsd4_encode_splice_read(resp, read, file, maxcount); + else + nfserr = nfsd4_encode_readv(resp, read, file, maxcount); if (nfserr) return nfserr; - xdr_truncate_encode(xdr, starting_len + 16 + xdr_align_size(*maxcount)); - - tmp = htonl(NFS4_CONTENT_DATA); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp64 = cpu_to_be64(read->rd_offset); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp64, 8); - tmp = htonl(*maxcount); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 12, &tmp, 4); - - tmp = xdr_zero; - write_bytes_to_xdr_buf(xdr->buf, starting_len + 16 + *maxcount, &tmp, - xdr_pad_size(*maxcount)); - return nfs_ok; -} - -static __be32 -nfsd4_encode_read_plus_hole(struct nfsd4_compoundres *resp, - struct nfsd4_read *read, - unsigned long *maxcount, u32 *eof) -{ - struct file *file = read->rd_nf->nf_file; - loff_t data_pos = vfs_llseek(file, read->rd_offset, SEEK_DATA); - loff_t f_size = i_size_read(file_inode(file)); - unsigned long count; - __be32 *p; - - if (data_pos == -ENXIO) - data_pos = f_size; - else if (data_pos <= read->rd_offset || (data_pos < f_size && data_pos % PAGE_SIZE)) - return nfsd4_encode_read_plus_data(resp, read, maxcount, eof, &f_size); - count = data_pos - read->rd_offset; - /* Content type, offset, byte count */ - p = xdr_reserve_space(resp->xdr, 4 + 8 + 8); - if (!p) - return nfserr_resource; - - *p++ = htonl(NFS4_CONTENT_HOLE); + *p++ = cpu_to_be32(NFS4_CONTENT_DATA); p = xdr_encode_hyper(p, read->rd_offset); - p = xdr_encode_hyper(p, count); + *p = cpu_to_be32(read->rd_length); - *eof = (read->rd_offset + count) >= f_size; - *maxcount = min_t(unsigned long, count, *maxcount); return nfs_ok; } static __be32 nfsd4_encode_read_plus(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_read *read) + union nfsd4_op_u *u) { - unsigned long maxcount, count; + struct nfsd4_read *read = &u->read; + struct file *file = read->rd_nf->nf_file; struct xdr_stream *xdr = resp->xdr; - struct file *file; int starting_len = xdr->buf->len; - int last_segment = xdr->buf->len; - int segments = 0; - __be32 *p, tmp; - bool is_data; - loff_t pos; - u32 eof; + u32 segments = 0; + __be32 *p; if (nfserr) return nfserr; - file = read->rd_nf->nf_file; /* eof flag, segment count */ p = xdr_reserve_space(xdr, 4 + 4); if (!p) - return nfserr_resource; + return nfserr_io; xdr_commit_encode(xdr); - maxcount = min_t(unsigned long, read->rd_length, - (xdr->buf->buflen - xdr->buf->len)); - count = maxcount; - - eof = read->rd_offset >= i_size_read(file_inode(file)); - if (eof) + read->rd_eof = read->rd_offset >= i_size_read(file_inode(file)); + if (read->rd_eof) goto out; - pos = vfs_llseek(file, read->rd_offset, SEEK_HOLE); - is_data = pos > read->rd_offset; - - while (count > 0 && !eof) { - maxcount = count; - if (is_data) - nfserr = nfsd4_encode_read_plus_data(resp, read, &maxcount, &eof, - segments == 0 ? &pos : NULL); - else - nfserr = nfsd4_encode_read_plus_hole(resp, read, &maxcount, &eof); - if (nfserr) - goto out; - count -= maxcount; - read->rd_offset += maxcount; - is_data = !is_data; - last_segment = xdr->buf->len; - segments++; - } - -out: - if (nfserr && segments == 0) + nfserr = nfsd4_encode_read_plus_data(resp, read); + if (nfserr) { xdr_truncate_encode(xdr, starting_len); - else { - if (nfserr) { - xdr_truncate_encode(xdr, last_segment); - nfserr = nfs_ok; - eof = 0; - } - tmp = htonl(eof); - write_bytes_to_xdr_buf(xdr->buf, starting_len, &tmp, 4); - tmp = htonl(segments); - write_bytes_to_xdr_buf(xdr->buf, starting_len + 4, &tmp, 4); + return nfserr; } + segments++; + +out: + p = xdr_encode_bool(p, read->rd_eof); + *p = cpu_to_be32(segments); return nfserr; } static __be32 nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_copy_notify *cn) + union nfsd4_op_u *u) { + struct nfsd4_copy_notify *cn = &u->copy_notify; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -4960,8 +5001,9 @@ nfsd4_encode_copy_notify(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_seek *seek) + union nfsd4_op_u *u) { + struct nfsd4_seek *seek = &u->seek; __be32 *p; p = xdr_reserve_space(resp->xdr, 4 + 8); @@ -4972,7 +5014,8 @@ nfsd4_encode_seek(struct nfsd4_compoundres *resp, __be32 nfserr, } static __be32 -nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, void *p) +nfsd4_encode_noop(struct nfsd4_compoundres *resp, __be32 nfserr, + union nfsd4_op_u *p) { return nfserr; } @@ -5023,8 +5066,9 @@ nfsd4_vbuf_to_stream(struct xdr_stream *xdr, char *buf, u32 buflen) static __be32 nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_getxattr *getxattr) + union nfsd4_op_u *u) { + struct nfsd4_getxattr *getxattr = &u->getxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p, err; @@ -5047,8 +5091,9 @@ nfsd4_encode_getxattr(struct nfsd4_compoundres *resp, __be32 nfserr, static __be32 nfsd4_encode_setxattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_setxattr *setxattr) + union nfsd4_op_u *u) { + struct nfsd4_setxattr *setxattr = &u->setxattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5088,8 +5133,9 @@ nfsd4_listxattr_validate_cookie(struct nfsd4_listxattrs *listxattrs, static __be32 nfsd4_encode_listxattrs(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_listxattrs *listxattrs) + union nfsd4_op_u *u) { + struct nfsd4_listxattrs *listxattrs = &u->listxattrs; struct xdr_stream *xdr = resp->xdr; u32 cookie_offset, count_offset, eof; u32 left, xdrleft, slen, count; @@ -5199,8 +5245,9 @@ out: static __be32 nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, - struct nfsd4_removexattr *removexattr) + union nfsd4_op_u *u) { + struct nfsd4_removexattr *removexattr = &u->removexattr; struct xdr_stream *xdr = resp->xdr; __be32 *p; @@ -5212,7 +5259,7 @@ nfsd4_encode_removexattr(struct nfsd4_compoundres *resp, __be32 nfserr, return 0; } -typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); +typedef __be32(*nfsd4_enc)(struct nfsd4_compoundres *, __be32, union nfsd4_op_u *u); /* * Note: nfsd4_enc_ops vector is shared for v4.0 and v4.1 @@ -5220,93 +5267,93 @@ typedef __be32(* nfsd4_enc)(struct nfsd4_compoundres *, __be32, void *); * done in the decoding phase. */ static const nfsd4_enc nfsd4_enc_ops[] = { - [OP_ACCESS] = (nfsd4_enc)nfsd4_encode_access, - [OP_CLOSE] = (nfsd4_enc)nfsd4_encode_close, - [OP_COMMIT] = (nfsd4_enc)nfsd4_encode_commit, - [OP_CREATE] = (nfsd4_enc)nfsd4_encode_create, - [OP_DELEGPURGE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DELEGRETURN] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETATTR] = (nfsd4_enc)nfsd4_encode_getattr, - [OP_GETFH] = (nfsd4_enc)nfsd4_encode_getfh, - [OP_LINK] = (nfsd4_enc)nfsd4_encode_link, - [OP_LOCK] = (nfsd4_enc)nfsd4_encode_lock, - [OP_LOCKT] = (nfsd4_enc)nfsd4_encode_lockt, - [OP_LOCKU] = (nfsd4_enc)nfsd4_encode_locku, - [OP_LOOKUP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LOOKUPP] = (nfsd4_enc)nfsd4_encode_noop, - [OP_NVERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN] = (nfsd4_enc)nfsd4_encode_open, - [OP_OPENATTR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OPEN_CONFIRM] = (nfsd4_enc)nfsd4_encode_open_confirm, - [OP_OPEN_DOWNGRADE] = (nfsd4_enc)nfsd4_encode_open_downgrade, - [OP_PUTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTPUBFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_PUTROOTFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_READ] = (nfsd4_enc)nfsd4_encode_read, - [OP_READDIR] = (nfsd4_enc)nfsd4_encode_readdir, - [OP_READLINK] = (nfsd4_enc)nfsd4_encode_readlink, - [OP_REMOVE] = (nfsd4_enc)nfsd4_encode_remove, - [OP_RENAME] = (nfsd4_enc)nfsd4_encode_rename, - [OP_RENEW] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RESTOREFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SAVEFH] = (nfsd4_enc)nfsd4_encode_noop, - [OP_SECINFO] = (nfsd4_enc)nfsd4_encode_secinfo, - [OP_SETATTR] = (nfsd4_enc)nfsd4_encode_setattr, - [OP_SETCLIENTID] = (nfsd4_enc)nfsd4_encode_setclientid, - [OP_SETCLIENTID_CONFIRM] = (nfsd4_enc)nfsd4_encode_noop, - [OP_VERIFY] = (nfsd4_enc)nfsd4_encode_noop, - [OP_WRITE] = (nfsd4_enc)nfsd4_encode_write, - [OP_RELEASE_LOCKOWNER] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ACCESS] = nfsd4_encode_access, + [OP_CLOSE] = nfsd4_encode_close, + [OP_COMMIT] = nfsd4_encode_commit, + [OP_CREATE] = nfsd4_encode_create, + [OP_DELEGPURGE] = nfsd4_encode_noop, + [OP_DELEGRETURN] = nfsd4_encode_noop, + [OP_GETATTR] = nfsd4_encode_getattr, + [OP_GETFH] = nfsd4_encode_getfh, + [OP_LINK] = nfsd4_encode_link, + [OP_LOCK] = nfsd4_encode_lock, + [OP_LOCKT] = nfsd4_encode_lockt, + [OP_LOCKU] = nfsd4_encode_locku, + [OP_LOOKUP] = nfsd4_encode_noop, + [OP_LOOKUPP] = nfsd4_encode_noop, + [OP_NVERIFY] = nfsd4_encode_noop, + [OP_OPEN] = nfsd4_encode_open, + [OP_OPENATTR] = nfsd4_encode_noop, + [OP_OPEN_CONFIRM] = nfsd4_encode_open_confirm, + [OP_OPEN_DOWNGRADE] = nfsd4_encode_open_downgrade, + [OP_PUTFH] = nfsd4_encode_noop, + [OP_PUTPUBFH] = nfsd4_encode_noop, + [OP_PUTROOTFH] = nfsd4_encode_noop, + [OP_READ] = nfsd4_encode_read, + [OP_READDIR] = nfsd4_encode_readdir, + [OP_READLINK] = nfsd4_encode_readlink, + [OP_REMOVE] = nfsd4_encode_remove, + [OP_RENAME] = nfsd4_encode_rename, + [OP_RENEW] = nfsd4_encode_noop, + [OP_RESTOREFH] = nfsd4_encode_noop, + [OP_SAVEFH] = nfsd4_encode_noop, + [OP_SECINFO] = nfsd4_encode_secinfo, + [OP_SETATTR] = nfsd4_encode_setattr, + [OP_SETCLIENTID] = nfsd4_encode_setclientid, + [OP_SETCLIENTID_CONFIRM] = nfsd4_encode_noop, + [OP_VERIFY] = nfsd4_encode_noop, + [OP_WRITE] = nfsd4_encode_write, + [OP_RELEASE_LOCKOWNER] = nfsd4_encode_noop, /* NFSv4.1 operations */ - [OP_BACKCHANNEL_CTL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_BIND_CONN_TO_SESSION] = (nfsd4_enc)nfsd4_encode_bind_conn_to_session, - [OP_EXCHANGE_ID] = (nfsd4_enc)nfsd4_encode_exchange_id, - [OP_CREATE_SESSION] = (nfsd4_enc)nfsd4_encode_create_session, - [OP_DESTROY_SESSION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_FREE_STATEID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GET_DIR_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, + [OP_BACKCHANNEL_CTL] = nfsd4_encode_noop, + [OP_BIND_CONN_TO_SESSION] = nfsd4_encode_bind_conn_to_session, + [OP_EXCHANGE_ID] = nfsd4_encode_exchange_id, + [OP_CREATE_SESSION] = nfsd4_encode_create_session, + [OP_DESTROY_SESSION] = nfsd4_encode_noop, + [OP_FREE_STATEID] = nfsd4_encode_noop, + [OP_GET_DIR_DELEGATION] = nfsd4_encode_noop, #ifdef CONFIG_NFSD_PNFS - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_getdeviceinfo, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_layoutcommit, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_layoutget, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_layoutreturn, + [OP_GETDEVICEINFO] = nfsd4_encode_getdeviceinfo, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_layoutcommit, + [OP_LAYOUTGET] = nfsd4_encode_layoutget, + [OP_LAYOUTRETURN] = nfsd4_encode_layoutreturn, #else - [OP_GETDEVICEINFO] = (nfsd4_enc)nfsd4_encode_noop, - [OP_GETDEVICELIST] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTCOMMIT] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTGET] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTRETURN] = (nfsd4_enc)nfsd4_encode_noop, + [OP_GETDEVICEINFO] = nfsd4_encode_noop, + [OP_GETDEVICELIST] = nfsd4_encode_noop, + [OP_LAYOUTCOMMIT] = nfsd4_encode_noop, + [OP_LAYOUTGET] = nfsd4_encode_noop, + [OP_LAYOUTRETURN] = nfsd4_encode_noop, #endif - [OP_SECINFO_NO_NAME] = (nfsd4_enc)nfsd4_encode_secinfo_no_name, - [OP_SEQUENCE] = (nfsd4_enc)nfsd4_encode_sequence, - [OP_SET_SSV] = (nfsd4_enc)nfsd4_encode_noop, - [OP_TEST_STATEID] = (nfsd4_enc)nfsd4_encode_test_stateid, - [OP_WANT_DELEGATION] = (nfsd4_enc)nfsd4_encode_noop, - [OP_DESTROY_CLIENTID] = (nfsd4_enc)nfsd4_encode_noop, - [OP_RECLAIM_COMPLETE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_SECINFO_NO_NAME] = nfsd4_encode_secinfo_no_name, + [OP_SEQUENCE] = nfsd4_encode_sequence, + [OP_SET_SSV] = nfsd4_encode_noop, + [OP_TEST_STATEID] = nfsd4_encode_test_stateid, + [OP_WANT_DELEGATION] = nfsd4_encode_noop, + [OP_DESTROY_CLIENTID] = nfsd4_encode_noop, + [OP_RECLAIM_COMPLETE] = nfsd4_encode_noop, /* NFSv4.2 operations */ - [OP_ALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_COPY] = (nfsd4_enc)nfsd4_encode_copy, - [OP_COPY_NOTIFY] = (nfsd4_enc)nfsd4_encode_copy_notify, - [OP_DEALLOCATE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_IO_ADVISE] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTERROR] = (nfsd4_enc)nfsd4_encode_noop, - [OP_LAYOUTSTATS] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_CANCEL] = (nfsd4_enc)nfsd4_encode_noop, - [OP_OFFLOAD_STATUS] = (nfsd4_enc)nfsd4_encode_offload_status, - [OP_READ_PLUS] = (nfsd4_enc)nfsd4_encode_read_plus, - [OP_SEEK] = (nfsd4_enc)nfsd4_encode_seek, - [OP_WRITE_SAME] = (nfsd4_enc)nfsd4_encode_noop, - [OP_CLONE] = (nfsd4_enc)nfsd4_encode_noop, + [OP_ALLOCATE] = nfsd4_encode_noop, + [OP_COPY] = nfsd4_encode_copy, + [OP_COPY_NOTIFY] = nfsd4_encode_copy_notify, + [OP_DEALLOCATE] = nfsd4_encode_noop, + [OP_IO_ADVISE] = nfsd4_encode_noop, + [OP_LAYOUTERROR] = nfsd4_encode_noop, + [OP_LAYOUTSTATS] = nfsd4_encode_noop, + [OP_OFFLOAD_CANCEL] = nfsd4_encode_noop, + [OP_OFFLOAD_STATUS] = nfsd4_encode_offload_status, + [OP_READ_PLUS] = nfsd4_encode_read_plus, + [OP_SEEK] = nfsd4_encode_seek, + [OP_WRITE_SAME] = nfsd4_encode_noop, + [OP_CLONE] = nfsd4_encode_noop, /* RFC 8276 extended atributes operations */ - [OP_GETXATTR] = (nfsd4_enc)nfsd4_encode_getxattr, - [OP_SETXATTR] = (nfsd4_enc)nfsd4_encode_setxattr, - [OP_LISTXATTRS] = (nfsd4_enc)nfsd4_encode_listxattrs, - [OP_REMOVEXATTR] = (nfsd4_enc)nfsd4_encode_removexattr, + [OP_GETXATTR] = nfsd4_encode_getxattr, + [OP_SETXATTR] = nfsd4_encode_setxattr, + [OP_LISTXATTRS] = nfsd4_encode_listxattrs, + [OP_REMOVEXATTR] = nfsd4_encode_removexattr, }; /* diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 573de0d49..76a60e7a7 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -581,7 +581,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET; switch(num) { +#ifdef CONFIG_NFSD_V2 case 2: +#endif case 3: nfsd_vers(nn, num, cmd); break; @@ -601,7 +603,9 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size) } break; default: - return -EINVAL; + /* Ignore requests to disable non-existent versions */ + if (cmd == NFSD_SET) + return -EINVAL; } vers += len + 1; } while ((len = qword_get(&mesg, vers, size)) > 0); @@ -1448,9 +1452,7 @@ 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; @@ -1460,8 +1462,6 @@ 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); @@ -1477,7 +1477,6 @@ 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 09726c5b9..fa0144a74 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -64,8 +64,7 @@ struct readdir_cd { extern struct svc_program nfsd_program; -extern const struct svc_version nfsd_version2, nfsd_version3, - nfsd_version4; +extern const struct svc_version nfsd_version2, nfsd_version3, nfsd_version4; extern struct mutex nfsd_mutex; extern spinlock_t nfsd_drc_lock; extern unsigned long nfsd_drc_max_mem; @@ -505,8 +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) @@ -514,8 +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/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index c3ae6414f..513e028b0 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -220,7 +220,7 @@ __be32 fh_update(struct svc_fh *); void fh_put(struct svc_fh *); static __inline__ struct svc_fh * -fh_copy(struct svc_fh *dst, struct svc_fh *src) +fh_copy(struct svc_fh *dst, const struct svc_fh *src) { WARN_ON(src->fh_dentry); @@ -229,7 +229,7 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src) } static inline void -fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src) +fh_copy_shallow(struct knfsd_fh *dst, const struct knfsd_fh *src) { dst->fh_size = src->fh_size; memcpy(&dst->fh_raw, &src->fh_raw, src->fh_size); @@ -243,7 +243,8 @@ fh_init(struct svc_fh *fhp, int maxsize) return fhp; } -static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_size != fh2->fh_size) return false; @@ -252,7 +253,8 @@ static inline bool fh_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) return true; } -static inline bool fh_fsid_match(struct knfsd_fh *fh1, struct knfsd_fh *fh2) +static inline bool fh_fsid_match(const struct knfsd_fh *fh1, + const struct knfsd_fh *fh2) { if (fh1->fh_fsid_type != fh2->fh_fsid_type) return false; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 82b3ddeac..9744443c3 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - return rpc_drop_reply; + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -848,65 +848,3 @@ const struct svc_version nfsd_version2 = { .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS2_SVC_XDRSIZE, }; - -/* - * Map errnos to NFS errnos. - */ -__be32 -nfserrno (int errno) -{ - static struct { - __be32 nfserr; - int syserr; - } nfs_errtbl[] = { - { nfs_ok, 0 }, - { nfserr_perm, -EPERM }, - { nfserr_noent, -ENOENT }, - { nfserr_io, -EIO }, - { nfserr_nxio, -ENXIO }, - { nfserr_fbig, -E2BIG }, - { nfserr_stale, -EBADF }, - { nfserr_acces, -EACCES }, - { nfserr_exist, -EEXIST }, - { nfserr_xdev, -EXDEV }, - { nfserr_mlink, -EMLINK }, - { nfserr_nodev, -ENODEV }, - { nfserr_notdir, -ENOTDIR }, - { nfserr_isdir, -EISDIR }, - { nfserr_inval, -EINVAL }, - { nfserr_fbig, -EFBIG }, - { nfserr_nospc, -ENOSPC }, - { nfserr_rofs, -EROFS }, - { nfserr_mlink, -EMLINK }, - { nfserr_nametoolong, -ENAMETOOLONG }, - { nfserr_notempty, -ENOTEMPTY }, -#ifdef EDQUOT - { nfserr_dquot, -EDQUOT }, -#endif - { nfserr_stale, -ESTALE }, - { nfserr_jukebox, -ETIMEDOUT }, - { nfserr_jukebox, -ERESTARTSYS }, - { nfserr_jukebox, -EAGAIN }, - { nfserr_jukebox, -EWOULDBLOCK }, - { nfserr_jukebox, -ENOMEM }, - { nfserr_io, -ETXTBSY }, - { nfserr_notsupp, -EOPNOTSUPP }, - { nfserr_toosmall, -ETOOSMALL }, - { nfserr_serverfault, -ESERVERFAULT }, - { nfserr_serverfault, -ENFILE }, - { nfserr_io, -EREMOTEIO }, - { nfserr_stale, -EOPENSTALE }, - { nfserr_io, -EUCLEAN }, - { nfserr_perm, -ENOKEY }, - { nfserr_no_grace, -ENOGRACE}, - }; - int i; - - for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { - if (nfs_errtbl[i].syserr == errno) - return nfs_errtbl[i].nfserr; - } - WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); - return nfserr_io; -} - diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index c7695ebd2..0c7563605 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -91,8 +91,12 @@ unsigned long nfsd_drc_mem_used; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) static struct svc_stat nfsd_acl_svcstats; static const struct svc_version *nfsd_acl_version[] = { +# if defined(CONFIG_NFSD_V2_ACL) [2] = &nfsd_acl_version2, +# endif +# if defined(CONFIG_NFSD_V3_ACL) [3] = &nfsd_acl_version3, +# endif }; #define NFSD_ACL_MINVERS 2 @@ -116,7 +120,9 @@ static struct svc_stat nfsd_acl_svcstats = { #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */ static const struct svc_version *nfsd_version[] = { +#if defined(CONFIG_NFSD_V2) [2] = &nfsd_version2, +#endif [3] = &nfsd_version3, #if defined(CONFIG_NFSD_V4) [4] = &nfsd_version4, @@ -1065,7 +1071,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); - if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) + if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e2daef3cc..e94634d30 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -368,6 +368,7 @@ struct nfs4_client { #define NFSD4_CLIENT_UPCALL_LOCK (5) /* upcall serialization */ #define NFSD4_CLIENT_CB_FLAG_MASK (1 << NFSD4_CLIENT_CB_UPDATE | \ 1 << NFSD4_CLIENT_CB_KILL) +#define NFSD4_CLIENT_CB_RECALL_ANY (6) unsigned long cl_flags; const struct cred *cl_cb_cred; struct rpc_clnt *cl_cb_client; @@ -411,6 +412,10 @@ struct nfs4_client { unsigned int cl_state; atomic_t cl_delegs_in_recall; + + struct nfsd4_cb_recall_any *cl_ra; + time64_t cl_ra_time; + struct list_head cl_ra_cblist; }; /* struct nfs4_client_reset @@ -536,16 +541,13 @@ struct nfs4_clnt_odstate { * inode can have multiple filehandles associated with it, so there is * (potentially) a many to one relationship between this struct and struct * inode. - * - * These are hashed by filehandle in the file_hashtbl, which is protected by - * the global state_lock spinlock. */ struct nfs4_file { refcount_t fi_ref; struct inode * fi_inode; bool fi_aliased; spinlock_t fi_lock; - struct hlist_node fi_hash; /* hash on fi_fhandle */ + struct rhlist_head fi_rlist; struct list_head fi_stateids; union { struct list_head fi_delegations; @@ -639,6 +641,7 @@ enum nfsd4_cb_op { NFSPROC4_CLNT_CB_OFFLOAD, NFSPROC4_CLNT_CB_SEQUENCE, NFSPROC4_CLNT_CB_NOTIFY_LOCK, + NFSPROC4_CLNT_CB_RECALL_ANY, }; /* Returns true iff a is later than b: */ diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 132335011..4183819ea 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,9 +9,12 @@ #define _NFSD_TRACE_H #include +#include +#include #include "export.h" #include "nfsfh.h" +#include "xdr4.h" #define NFSD_TRACE_PROC_RES_FIELDS \ __field(unsigned int, netns_ino) \ @@ -604,6 +607,7 @@ DEFINE_STATEID_EVENT(layout_recall_release); DEFINE_STATEID_EVENT(open); DEFINE_STATEID_EVENT(deleg_read); +DEFINE_STATEID_EVENT(deleg_return); DEFINE_STATEID_EVENT(deleg_recall); DECLARE_EVENT_CLASS(nfsd_stateseqid_class, @@ -636,6 +640,61 @@ DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ DEFINE_STATESEQID_EVENT(preprocess); DEFINE_STATESEQID_EVENT(open_confirm); +TRACE_DEFINE_ENUM(NFS4_OPEN_STID); +TRACE_DEFINE_ENUM(NFS4_LOCK_STID); +TRACE_DEFINE_ENUM(NFS4_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_STID); +TRACE_DEFINE_ENUM(NFS4_REVOKED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_CLOSED_DELEG_STID); +TRACE_DEFINE_ENUM(NFS4_LAYOUT_STID); + +#define show_stid_type(x) \ + __print_flags(x, "|", \ + { NFS4_OPEN_STID, "OPEN" }, \ + { NFS4_LOCK_STID, "LOCK" }, \ + { NFS4_DELEG_STID, "DELEG" }, \ + { NFS4_CLOSED_STID, "CLOSED" }, \ + { NFS4_REVOKED_DELEG_STID, "REVOKED" }, \ + { NFS4_CLOSED_DELEG_STID, "CLOSED_DELEG" }, \ + { NFS4_LAYOUT_STID, "LAYOUT" }) + +DECLARE_EVENT_CLASS(nfsd_stid_class, + TP_PROTO( + const struct nfs4_stid *stid + ), + TP_ARGS(stid), + TP_STRUCT__entry( + __field(unsigned long, sc_type) + __field(int, sc_count) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + const stateid_t *stp = &stid->sc_stateid; + + __entry->sc_type = stid->sc_type; + __entry->sc_count = refcount_read(&stid->sc_count); + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("client %08x:%08x stateid %08x:%08x ref=%d type=%s", + __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation, + __entry->sc_count, show_stid_type(__entry->sc_type) + ) +); + +#define DEFINE_STID_EVENT(name) \ +DEFINE_EVENT(nfsd_stid_class, nfsd_stid_##name, \ + TP_PROTO(const struct nfs4_stid *stid), \ + TP_ARGS(stid)) + +DEFINE_STID_EVENT(revoke); + DECLARE_EVENT_CLASS(nfsd_clientid_class, TP_PROTO(const clientid_t *clid), TP_ARGS(clid), @@ -1436,6 +1495,32 @@ TRACE_EVENT(nfsd_cb_offload, __entry->fh_hash, __entry->count, __entry->status) ); +TRACE_EVENT(nfsd_cb_recall_any, + TP_PROTO( + const struct nfsd4_cb_recall_any *ra + ), + TP_ARGS(ra), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, keep) + __field(unsigned long, bmval0) + __sockaddr(addr, ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen) + ), + TP_fast_assign( + __entry->cl_boot = ra->ra_cb.cb_clp->cl_clientid.cl_boot; + __entry->cl_id = ra->ra_cb.cb_clp->cl_clientid.cl_id; + __entry->keep = ra->ra_keep; + __entry->bmval0 = ra->ra_bmval[0]; + __assign_sockaddr(addr, &ra->ra_cb.cb_clp->cl_addr, + ra->ra_cb.cb_clp->cl_cb_conn.cb_addrlen); + ), + TP_printk("addr=%pISpc client %08x:%08x keep=%u bmval0=%s", + __get_sockaddr(addr), __entry->cl_boot, __entry->cl_id, + __entry->keep, show_rca_mask(__entry->bmval0) + ) +); + DECLARE_EVENT_CLASS(nfsd_cb_done_class, TP_PROTO( const stateid_t *stp, @@ -1475,6 +1560,27 @@ DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_notify_lock_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_layout_done); DEFINE_NFSD_CB_DONE_EVENT(nfsd_cb_offload_done); +TRACE_EVENT(nfsd_cb_recall_any_done, + TP_PROTO( + const struct nfsd4_callback *cb, + const struct rpc_task *task + ), + TP_ARGS(cb, task), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + ), + TP_fast_assign( + __entry->status = task->tk_status; + __entry->cl_boot = cb->cb_clp->cl_clientid.cl_boot; + __entry->cl_id = cb->cb_clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x status=%d", + __entry->cl_boot, __entry->cl_id, __entry->status + ) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eccc6ce55..5d6a61d47 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -49,6 +49,69 @@ #define NFSDDBG_FACILITY NFSDDBG_FILEOP +/** + * nfserrno - Map Linux errnos to NFS errnos + * @errno: POSIX(-ish) error code to be mapped + * + * Returns the appropriate (net-endian) nfserr_* (or nfs_ok if errno is 0). If + * it's an error we don't expect, log it once and return nfserr_io. + */ +__be32 +nfserrno (int errno) +{ + static struct { + __be32 nfserr; + int syserr; + } nfs_errtbl[] = { + { nfs_ok, 0 }, + { nfserr_perm, -EPERM }, + { nfserr_noent, -ENOENT }, + { nfserr_io, -EIO }, + { nfserr_nxio, -ENXIO }, + { nfserr_fbig, -E2BIG }, + { nfserr_stale, -EBADF }, + { nfserr_acces, -EACCES }, + { nfserr_exist, -EEXIST }, + { nfserr_xdev, -EXDEV }, + { nfserr_mlink, -EMLINK }, + { nfserr_nodev, -ENODEV }, + { nfserr_notdir, -ENOTDIR }, + { nfserr_isdir, -EISDIR }, + { nfserr_inval, -EINVAL }, + { nfserr_fbig, -EFBIG }, + { nfserr_nospc, -ENOSPC }, + { nfserr_rofs, -EROFS }, + { nfserr_mlink, -EMLINK }, + { nfserr_nametoolong, -ENAMETOOLONG }, + { nfserr_notempty, -ENOTEMPTY }, + { nfserr_dquot, -EDQUOT }, + { nfserr_stale, -ESTALE }, + { nfserr_jukebox, -ETIMEDOUT }, + { nfserr_jukebox, -ERESTARTSYS }, + { nfserr_jukebox, -EAGAIN }, + { nfserr_jukebox, -EWOULDBLOCK }, + { nfserr_jukebox, -ENOMEM }, + { nfserr_io, -ETXTBSY }, + { nfserr_notsupp, -EOPNOTSUPP }, + { nfserr_toosmall, -ETOOSMALL }, + { nfserr_serverfault, -ESERVERFAULT }, + { nfserr_serverfault, -ENFILE }, + { nfserr_io, -EREMOTEIO }, + { nfserr_stale, -EOPENSTALE }, + { nfserr_io, -EUCLEAN }, + { nfserr_perm, -ENOKEY }, + { nfserr_no_grace, -ENOGRACE}, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(nfs_errtbl); i++) { + if (nfs_errtbl[i].syserr == errno) + return nfs_errtbl[i].nfserr; + } + WARN_ONCE(1, "nfsd: non-standard errno: %d\n", errno); + return nfserr_io; +} + /* * Called from nfsd_lookup and encode_dirent. Check if we have crossed * a mount point. @@ -1317,7 +1380,6 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask(); err = 0; - host_err = 0; switch (type) { case S_IFREG: host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index 9744b0411..dbdfef7ae 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -60,6 +60,7 @@ static inline void nfsd_attrs_free(struct nfsd_attrs *attrs) posix_acl_release(attrs->na_dpacl); } +__be32 nfserrno (int errno); int nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct svc_export **expp); __be32 nfsd_lookup(struct svc_rqst *, struct svc_fh *, diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 36c3340c1..510978e60 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -896,5 +896,10 @@ struct nfsd4_operation { union nfsd4_op_u *); }; +struct nfsd4_cb_recall_any { + struct nfsd4_callback ra_cb; + u32 ra_keep; + u32 ra_bmval[1]; +}; #endif diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h index 547cf07cf..0d39af1b0 100644 --- a/fs/nfsd/xdr4cb.h +++ b/fs/nfsd/xdr4cb.h @@ -48,3 +48,9 @@ #define NFS4_dec_cb_offload_sz (cb_compound_dec_hdr_sz + \ cb_sequence_dec_sz + \ op_dec_sz) +#define NFS4_enc_cb_recall_any_sz (cb_compound_enc_hdr_sz + \ + cb_sequence_enc_sz + \ + 1 + 1 + 1) +#define NFS4_dec_cb_recall_any_sz (cb_compound_dec_hdr_sz + \ + cb_sequence_dec_sz + \ + op_dec_sz) diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index 9930fa901..1e7f653c1 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -40,8 +40,21 @@ static inline struct nilfs_dat_info *NILFS_DAT_I(struct inode *dat) static int nilfs_dat_prepare_entry(struct inode *dat, struct nilfs_palloc_req *req, int create) { - return nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, - create, &req->pr_entry_bh); + int ret; + + ret = nilfs_palloc_get_entry_block(dat, req->pr_entry_nr, + create, &req->pr_entry_bh); + if (unlikely(ret == -ENOENT)) { + nilfs_err(dat->i_sb, + "DAT doesn't have a block to manage vblocknr = %llu", + (unsigned long long)req->pr_entry_nr); + /* + * Return internal code -EINVAL to notify bmap layer of + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } static void nilfs_dat_commit_entry(struct inode *dat, @@ -123,11 +136,7 @@ static void nilfs_dat_commit_free(struct inode *dat, int nilfs_dat_prepare_start(struct inode *dat, struct nilfs_palloc_req *req) { - int ret; - - ret = nilfs_dat_prepare_entry(dat, req, 0); - WARN_ON(ret == -ENOENT); - return ret; + return nilfs_dat_prepare_entry(dat, req, 0); } void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req, @@ -154,10 +163,8 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req) int ret; ret = nilfs_dat_prepare_entry(dat, req, 0); - if (ret < 0) { - WARN_ON(ret == -ENOENT); + if (ret < 0) return ret; - } kaddr = kmap_atomic(req->pr_entry_bh->b_page); entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr, diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index a265d391f..822e8d95d 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -105,7 +105,13 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf) nilfs_transaction_commit(inode->i_sb); mapped: - wait_for_stable_page(page); + /* + * Since checksumming including data blocks is performed to determine + * the validity of the log to be written and used for recovery, it is + * necessary to wait for writeback to finish here, regardless of the + * stable write requirement of the backing device. + */ + wait_on_page_writeback(page); out: sb_end_pagefault(inode->i_sb); return block_page_mkwrite_return(ret); diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 0955b6579..a9b8d77c8 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -472,9 +472,10 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs, static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, struct nilfs_recovery_block *rb, - struct page *page) + loff_t pos, struct page *page) { struct buffer_head *bh_org; + size_t from = pos & ~PAGE_MASK; void *kaddr; bh_org = __bread(nilfs->ns_bdev, rb->blocknr, nilfs->ns_blocksize); @@ -482,7 +483,7 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs, return -EIO; kaddr = kmap_atomic(page); - memcpy(kaddr + bh_offset(bh_org), bh_org->b_data, bh_org->b_size); + memcpy(kaddr + from, bh_org->b_data, bh_org->b_size); kunmap_atomic(kaddr); brelse(bh_org); return 0; @@ -521,7 +522,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs, goto failed_inode; } - err = nilfs_recovery_copy_block(nilfs, rb, page); + err = nilfs_recovery_copy_block(nilfs, rb, pos, page); if (unlikely(err)) goto failed_page; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index a4a147a98..0a8461396 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1702,7 +1702,6 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - set_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { if (bh->b_page != bd_page) { lock_page(bd_page); @@ -1713,6 +1712,7 @@ static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci) } break; } + set_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_begin_page_io(fs_page); fs_page = bh->b_page; @@ -1798,7 +1798,6 @@ static void nilfs_abort_logs(struct list_head *logs, int err) list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) { - clear_buffer_async_write(bh); if (bh == segbuf->sb_super_root) { clear_buffer_uptodate(bh); if (bh->b_page != bd_page) { @@ -1807,6 +1806,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err) } break; } + clear_buffer_async_write(bh); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, err); fs_page = bh->b_page; @@ -1894,8 +1894,9 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) BIT(BH_Delay) | BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Redirected)); - set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh == segbuf->sb_super_root) { + set_buffer_uptodate(bh); + clear_buffer_dirty(bh); if (bh->b_page != bd_page) { end_page_writeback(bd_page); bd_page = bh->b_page; @@ -1903,6 +1904,7 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci) update_sr = true; break; } + set_mask_bits(&bh->b_state, clear_bits, set_bits); if (bh->b_page != fs_page) { nilfs_end_page_io(fs_page, 0); fs_page = bh->b_page; diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 2215179c9..2618bf5a3 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1658,8 +1658,10 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) - return -ENOENT; + if (!attr_b) { + err = -ENOENT; + goto out; + } attr = attr_b; le = le_b; @@ -1740,13 +1742,15 @@ ins_ext: ok: run_truncate_around(run, vcn); out: - if (new_valid > data_size) - new_valid = data_size; + if (attr_b) { + if (new_valid > data_size) + new_valid = data_size; - valid_size = le64_to_cpu(attr_b->nres.valid_size); - if (new_valid != valid_size) { - attr_b->nres.valid_size = cpu_to_le64(valid_size); - mi_b->dirty = true; + valid_size = le64_to_cpu(attr_b->nres.valid_size); + if (new_valid != valid_size) { + attr_b->nres.valid_size = cpu_to_le64(valid_size); + mi_b->dirty = true; + } } return err; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 0c6a68e71..723e49ec8 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -127,12 +127,13 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, { size_t off; u16 sz; + const unsigned le_min_size = le_size(0); if (!le) { le = ni->attr_list.le; } else { sz = le16_to_cpu(le->size); - if (sz < sizeof(struct ATTR_LIST_ENTRY)) { + if (sz < le_min_size) { /* Impossible 'cause we should not return such le. */ return NULL; } @@ -141,7 +142,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, /* Check boundary. */ off = PtrOffset(ni->attr_list.le, le); - if (off + sizeof(struct ATTR_LIST_ENTRY) > ni->attr_list.size) { + if (off + le_min_size > ni->attr_list.size) { /* The regular end of list. */ return NULL; } @@ -149,8 +150,7 @@ struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, sz = le16_to_cpu(le->size); /* Check le for errors. */ - if (sz < sizeof(struct ATTR_LIST_ENTRY) || - off + sz > ni->attr_list.size || + if (sz < le_min_size || off + sz > ni->attr_list.size || sz < le->name_off + le->name_len * sizeof(short)) { return NULL; } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index d4d9f4ffb..72cdfa872 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,11 +309,31 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ - if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) - dt_type = DT_LNK; - else - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* + * NTFS: symlinks are "dir + reparse" or "file + reparse" + * Unfortunately reparse attribute is used for many purposes (several dozens). + * It is not possible here to know is this name symlink or not. + * To get exactly the type of name we should to open inode (read mft). + * getattr for opened file (fstat) correctly returns symlink. + */ + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + + /* + * It is not reliable to detect the type of name using duplicated information + * stored in parent directory. + * The only correct way to get the type of name - read MFT record and find ATTR_STD. + * The code below is not good idea. + * It does additional locks/reads just to get the type of name. + * Should we use additional mount option to enable branch below? + */ + if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) && + ino != ni->mi.rno) { + struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL); + if (!IS_ERR_OR_NULL(inode)) { + dt_type = fs_umode_to_dtype(inode->i_mode); + iput(inode); + } + } return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } @@ -495,11 +515,9 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, struct INDEX_HDR *hdr; const struct ATTR_FILE_NAME *fname; u32 e_size, off, end; - u64 vbo = 0; size_t drs = 0, fles = 0, bit = 0; - loff_t i_size = ni->vfs_inode.i_size; struct indx_node *node = NULL; - u8 index_bits = ni->dir.index_bits; + size_t max_indx = ni->vfs_inode.i_size >> ni->dir.index_bits; if (is_empty) *is_empty = true; @@ -543,7 +561,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, fles += 1; } - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_used_bit(&ni->dir, ni, &bit); @@ -553,8 +571,7 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, if (bit == MINUS_ONE_T) goto out; - vbo = (u64)bit << index_bits; - if (vbo >= i_size) + if (bit >= max_indx) goto out; err = indx_read(&ni->dir, ni, bit << ni->dir.idx2vbn_bits, @@ -564,7 +581,6 @@ static int ntfs_dir_count(struct inode *dir, bool *is_empty, size_t *dirs, hdr = &node->index->ihdr; bit += 1; - vbo = (u64)bit << ni->dir.idx2vbn_bits; } out: diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index f31c0389a..14efe46df 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -1110,6 +1110,8 @@ out: iocb->ki_pos += written; if (iocb->ki_pos > ni->i_valid) ni->i_valid = iocb->ki_pos; + if (iocb->ki_pos > i_size) + i_size_write(inode, iocb->ki_pos); return written; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index bb7e33c24..d26026090 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -102,7 +102,7 @@ void ni_clear(struct ntfs_inode *ni) { struct rb_node *node; - if (!ni->vfs_inode.i_nlink && is_rec_inuse(ni->mi.mrec)) + if (!ni->vfs_inode.i_nlink && ni->mi.mrec && is_rec_inuse(ni->mi.mrec)) ni_delete_all(ni); al_destroy(ni); @@ -3255,6 +3255,9 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) return 0; } + if (!ni->mi.mrec) + goto out; + if (is_rec_inuse(ni->mi.mrec) && !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING) && inode->i_nlink) { bool modified = false; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 710cb5aa5..d53ef128f 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -465,7 +465,7 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) { const struct RESTART_AREA *ra; u16 cl, fl, ul; - u32 off, l_size, file_dat_bits, file_size_round; + u32 off, l_size, seq_bits; u16 ro = le16_to_cpu(rhdr->ra_off); u32 sys_page = le32_to_cpu(rhdr->sys_page_size); @@ -511,13 +511,15 @@ static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) /* Make sure the sequence number bits match the log file size. */ l_size = le64_to_cpu(ra->l_size); - file_dat_bits = sizeof(u64) * 8 - le32_to_cpu(ra->seq_num_bits); - file_size_round = 1u << (file_dat_bits + 3); - if (file_size_round != l_size && - (file_size_round < l_size || (file_size_round / 2) > l_size)) { - return false; + seq_bits = sizeof(u64) * 8 + 3; + while (l_size) { + l_size >>= 1; + seq_bits -= 1; } + if (seq_bits != ra->seq_num_bits) + return false; + /* The log page data offset and record header length must be quad-aligned. */ if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) || !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8)) diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 873b1434a..4c2d079b3 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -976,6 +976,30 @@ static inline __le32 security_hash(const void *sd, size_t bytes) return cpu_to_le32(hash); } +/* + * simple wrapper for sb_bread_unmovable. + */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block) +{ + struct ntfs_sb_info *sbi = sb->s_fs_info; + struct buffer_head *bh; + + if (unlikely(block >= sbi->volume.blocks)) { + /* prevent generic message "attempt to access beyond end of device" */ + ntfs_err(sb, "try to read out of volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; + } + + bh = sb_bread_unmovable(sb, block); + if (bh) + return bh; + + ntfs_err(sb, "failed to read volume at offset 0x%llx", + (u64)block << sb->s_blocksize_bits); + return NULL; +} + int ntfs_sb_read(struct super_block *sb, u64 lbo, size_t bytes, void *buffer) { struct block_device *bdev = sb->s_bdev; @@ -1650,6 +1674,7 @@ struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST rno, bool dir) out: if (err) { + make_bad_inode(inode); iput(inode); ni = ERR_PTR(err); } @@ -1842,10 +1867,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sdh->type != ATTR_ZERO || + if(!(root_sdh = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sdh->type != ATTR_ZERO || root_sdh->rule != NTFS_COLLATION_TYPE_SECURITY_HASH || - offsetof(struct INDEX_ROOT, ihdr) + root_sdh->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sdh->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } @@ -1861,10 +1888,12 @@ int ntfs_security_init(struct ntfs_sb_info *sbi) goto out; } - root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT)); - if (root_sii->type != ATTR_ZERO || + if(!(root_sii = resident_data_ex(attr, sizeof(struct INDEX_ROOT))) || + root_sii->type != ATTR_ZERO || root_sii->rule != NTFS_COLLATION_TYPE_UINT || - offsetof(struct INDEX_ROOT, ihdr) + root_sii->ihdr.used > attr->res.data_size) { + offsetof(struct INDEX_ROOT, ihdr) + + le32_to_cpu(root_sii->ihdr.used) > + le32_to_cpu(attr->res.data_size)) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index b89a33f57..eee01db6e 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -998,6 +998,7 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le = NULL; struct ATTRIB *a; const struct INDEX_NAMES *in = &s_index_names[indx->type]; + struct INDEX_ROOT *root = NULL; a = ni_find_attr(ni, NULL, &le, ATTR_ROOT, in->name, in->name_len, NULL, mi); @@ -1007,7 +1008,15 @@ struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, if (attr) *attr = a; - return resident_data_ex(a, sizeof(struct INDEX_ROOT)); + root = resident_data_ex(a, sizeof(struct INDEX_ROOT)); + + /* length check */ + if (root && offsetof(struct INDEX_ROOT, ihdr) + le32_to_cpu(root->ihdr.used) > + le32_to_cpu(a->res.data_size)) { + return NULL; + } + + return root; } static int indx_write(struct ntfs_index *indx, struct ntfs_inode *ni, @@ -1097,7 +1106,8 @@ ok: } /* check for index header length */ - if (offsetof(struct INDEX_BUFFER, ihdr) + ib->ihdr.used > bytes) { + if (offsetof(struct INDEX_BUFFER, ihdr) + le32_to_cpu(ib->ihdr.used) > + bytes) { err = -EINVAL; goto out; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index dc937089a..42dd9fdaf 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -402,7 +402,6 @@ end_enum: goto out; if (!is_match && name) { - /* Reuse rec as buffer for ascii name. */ err = -ENOENT; goto out; } @@ -417,6 +416,7 @@ end_enum: if (names != le16_to_cpu(rec->hard_links)) { /* Correct minor error on the fly. Do not mark inode as dirty. */ + ntfs_inode_warn(inode, "Correct links count -> %u.", names); rec->hard_links = cpu_to_le16(names); ni->mi.dirty = true; } diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 0f38d5581..ba26a465b 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -517,12 +517,10 @@ struct ATTR_LIST_ENTRY { __le64 vcn; // 0x08: Starting VCN of this attribute. struct MFT_REF ref; // 0x10: MFT record number with attribute. __le16 id; // 0x18: struct ATTRIB ID. - __le16 name[3]; // 0x1A: Just to align. To get real name can use bNameOffset. + __le16 name[]; // 0x1A: Just to align. To get real name can use name_off. }; // sizeof(0x20) -static_assert(sizeof(struct ATTR_LIST_ENTRY) == 0x20); - static inline u32 le_size(u8 name_len) { return ALIGN(offsetof(struct ATTR_LIST_ENTRY, name) + diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8c9abaf13..0f9bec29f 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -467,7 +467,7 @@ bool al_delete_le(struct ntfs_inode *ni, enum ATTR_TYPE type, CLST vcn, int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { - return (size + 1023) & ~(size_t)1023; + return size_add(size, 1023) & ~(size_t)1023; } /* Globals from bitfunc.c */ @@ -580,6 +580,7 @@ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ +struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block); bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple); @@ -1012,19 +1013,6 @@ static inline u64 bytes_to_block(const struct super_block *sb, u64 size) return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } -static inline struct buffer_head *ntfs_bread(struct super_block *sb, - sector_t block) -{ - struct buffer_head *bh = sb_bread(sb, block); - - if (bh) - return bh; - - ntfs_err(sb, "failed to read volume at offset 0x%llx", - (u64)block << sb->s_blocksize_bits); - return NULL; -} - static inline struct ntfs_inode *ntfs_i(struct inode *inode) { return container_of(inode, struct ntfs_inode, vfs_inode); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index ba336c728..a8d4ed7bc 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -226,11 +226,6 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* overflow check */ - return NULL; - } - attr = Add2Ptr(attr, asize); off += asize; } @@ -253,8 +248,8 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if ((t32 & 0xf) || (t32 > 0x100)) return NULL; - /* Check boundary. */ - if (off + asize > used) + /* Check overflow and boundary. */ + if (off + asize < off || off + asize > used) return NULL; /* Check size of attribute. */ @@ -491,8 +486,20 @@ bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, return false; if (ni && is_attr_indexed(attr)) { - le16_add_cpu(&ni->mi.mrec->hard_links, -1); - ni->mi.dirty = true; + u16 links = le16_to_cpu(ni->mi.mrec->hard_links); + struct ATTR_FILE_NAME *fname = + attr->type != ATTR_NAME ? + NULL : + resident_data_ex(attr, + SIZEOF_ATTRIBUTE_FILENAME); + if (fname && fname->type == FILE_NAME_DOS) { + /* Do not decrease links count deleting DOS name. */ + } else if (!links) { + /* minor error. Not critical. */ + } else { + ni->mi.mrec->hard_links = cpu_to_le16(links - 1); + ni->mi.dirty = true; + } } used -= asize; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index df15e00c2..d98cf7b38 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -217,6 +217,9 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, if (!ea->name_len) break; + if (ea->name_len > ea_size) + break; + if (buffer) { /* Check if we can use field ea->name */ if (off + ea_size > size) diff --git a/fs/proc/array.c b/fs/proc/array.c index 49283b810..d210b2f8b 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -467,13 +467,13 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, int permitted; struct mm_struct *mm; unsigned long long start_time; - unsigned long cmin_flt = 0, cmaj_flt = 0; - unsigned long min_flt = 0, maj_flt = 0; - u64 cutime, cstime, utime, stime; - u64 cgtime, gtime; + unsigned long cmin_flt, cmaj_flt, min_flt, maj_flt; + u64 cutime, cstime, cgtime, utime, stime, gtime; unsigned long rsslim = 0; unsigned long flags; int exit_code = task->exit_code; + struct signal_struct *sig = task->signal; + unsigned int seq = 1; state = *get_task_state(task); vsize = eip = esp = 0; @@ -501,12 +501,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, sigemptyset(&sigign); sigemptyset(&sigcatch); - cutime = cstime = utime = stime = 0; - cgtime = gtime = 0; if (lock_task_sighand(task, &flags)) { - struct signal_struct *sig = task->signal; - if (sig->tty) { struct pid *pgrp = tty_get_pgrp(sig->tty); tty_pgrp = pid_nr_ns(pgrp, ns); @@ -517,27 +513,9 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, num_threads = get_nr_threads(task); collect_sigign_sigcatch(task, &sigign, &sigcatch); - cmin_flt = sig->cmin_flt; - cmaj_flt = sig->cmaj_flt; - cutime = sig->cutime; - cstime = sig->cstime; - cgtime = sig->cgtime; rsslim = READ_ONCE(sig->rlim[RLIMIT_RSS].rlim_cur); - /* add up live thread stats at the group level */ if (whole) { - struct task_struct *t = task; - do { - min_flt += t->min_flt; - maj_flt += t->maj_flt; - gtime += task_gtime(t); - } while_each_thread(task, t); - - min_flt += sig->min_flt; - maj_flt += sig->maj_flt; - thread_group_cputime_adjusted(task, &utime, &stime); - gtime += sig->gtime; - if (sig->flags & (SIGNAL_GROUP_EXIT | SIGNAL_STOP_STOPPED)) exit_code = sig->group_exit_code; } @@ -551,10 +529,41 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, if (permitted && (!whole || num_threads < 2)) wchan = !task_is_running(task); - if (!whole) { + + do { + seq++; /* 2 on the 1st/lockless path, otherwise odd */ + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + + cmin_flt = sig->cmin_flt; + cmaj_flt = sig->cmaj_flt; + cutime = sig->cutime; + cstime = sig->cstime; + cgtime = sig->cgtime; + + if (whole) { + struct task_struct *t; + + min_flt = sig->min_flt; + maj_flt = sig->maj_flt; + gtime = sig->gtime; + + rcu_read_lock(); + __for_each_thread(sig, t) { + min_flt += t->min_flt; + maj_flt += t->maj_flt; + gtime += task_gtime(t); + } + rcu_read_unlock(); + } + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + + if (whole) { + thread_group_cputime_adjusted(task, &utime, &stime); + } else { + task_cputime_adjusted(task, &utime, &stime); min_flt = task->min_flt; maj_flt = task->maj_flt; - task_cputime_adjusted(task, &utime, &stime); gtime = task_gtime(task); } diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index f3fa3625d..e15b46313 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -519,6 +519,7 @@ static int ramoops_init_przs(const char *name, } zone_sz = mem_sz / *cnt; + zone_sz = ALIGN_DOWN(zone_sz, 2); if (!zone_sz) { dev_err(dev, "%s zone size == 0\n", name); goto fail; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 5a132c1e6..fd082151c 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -149,7 +149,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -EOPNOTSUPP; ses = tcon->ses; - server = ses->server; + server = cifs_pick_channel(ses); cfids = tcon->cfids; if (!server->ops->new_lease_key) @@ -268,10 +268,12 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, if (o_rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) goto oshr_free; - smb2_parse_contexts(server, o_rsp, + rc = smb2_parse_contexts(server, rsp_iov, &oparms.fid->epoch, - oparms.fid->lease_key, &oplock, - NULL, NULL); + oparms.fid->lease_key, + &oplock, NULL, NULL); + if (rc) + goto oshr_free; if (!(oplock & SMB2_LEASE_READ_CACHING_HE)) goto oshr_free; qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base; diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c index d0ac2648c..d3d4cf632 100644 --- a/fs/smb/client/cifsencrypt.c +++ b/fs/smb/client/cifsencrypt.c @@ -444,7 +444,7 @@ static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash, len = cifs_strtoUTF16(user, ses->user_name, len, nls_cp); UniStrupr(user); } else { - memset(user, '\0', 2); + *(u16 *)user = 0; } rc = crypto_shash_update(ses->server->secmech.hmacmd5, diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 7f1aea4c1..58bb54994 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -86,7 +86,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 5 +#define MAX_COMPOUND 7 /* * Default number of credits to keep available for SMB3. diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index f4818599c..4d5302b58 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -209,7 +209,7 @@ cifs_parse_security_flavors(struct fs_context *fc, char *value, struct smb3_fs_c switch (match_token(value, cifs_secflavor_tokens, args)) { case Opt_sec_krb5p: - cifs_errorf(fc, "sec=krb5p is not supported!\n"); + cifs_errorf(fc, "sec=krb5p is not supported. Use sec=krb5,seal instead\n"); return 1; case Opt_sec_krb5i: ctx->sign = true; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 2d75ba5aa..5990bdbae 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -304,14 +304,16 @@ cifs_dir_info_to_fattr(struct cifs_fattr *fattr, FILE_DIRECTORY_INFO *info, } static void cifs_fulldir_info_to_fattr(struct cifs_fattr *fattr, - SEARCH_ID_FULL_DIR_INFO *info, + const void *info, struct cifs_sb_info *cifs_sb) { + const FILE_FULL_DIRECTORY_INFO *di = info; + __dir_info_to_fattr(fattr, info); - /* See MS-FSCC 2.4.19 FileIdFullDirectoryInformation */ + /* See MS-FSCC 2.4.14, 2.4.19 */ if (fattr->cf_cifsattrs & ATTR_REPARSE) - fattr->cf_cifstag = le32_to_cpu(info->EaSize); + fattr->cf_cifstag = le32_to_cpu(di->EaSize); cifs_fill_common_info(fattr, cifs_sb); } @@ -425,7 +427,7 @@ ffirst_retry: } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; } else /* not srvinos - BB fixme add check for backlevel? */ { - cifsFile->srch_inf.info_level = SMB_FIND_FILE_DIRECTORY_INFO; + cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO; } search_flags = CIFS_SEARCH_CLOSE_AT_END | CIFS_SEARCH_RETURN_RESUME; @@ -1019,10 +1021,9 @@ static int cifs_filldir(char *find_entry, struct file *file, (FIND_FILE_STANDARD_INFO *)find_entry, cifs_sb); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: case SMB_FIND_FILE_ID_FULL_DIR_INFO: - cifs_fulldir_info_to_fattr(&fattr, - (SEARCH_ID_FULL_DIR_INFO *)find_entry, - cifs_sb); + cifs_fulldir_info_to_fattr(&fattr, find_entry, cifs_sb); break; default: cifs_dir_info_to_fattr(&fattr, diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 634035bcb..b8e14bcd2 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -248,6 +248,8 @@ int cifs_try_adding_channels(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses) &iface->sockaddr, rc); kref_put(&iface->refcount, release_iface); + /* failure to add chan should increase weight */ + iface->weight_fulfilled++; continue; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 5a157000b..34d126200 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -613,7 +613,7 @@ parse_server_interfaces(struct network_interface_info_ioctl_rsp *buf, goto out; } - while (bytes_left >= sizeof(*p)) { + while (bytes_left >= (ssize_t)sizeof(*p)) { memset(&tmp_iface, 0, sizeof(tmp_iface)); tmp_iface.speed = le64_to_cpu(p->LinkSpeed); tmp_iface.rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index e65f998ea..4c1231496 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -2145,17 +2145,18 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, posix->nlink, posix->mode, posix->reparse_tag); } -void -smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, __u8 *oplock, - struct smb2_file_all_info *buf, - struct create_posix_rsp *posix) +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix) { - char *data_offset; + struct smb2_create_rsp *rsp = rsp_iov->iov_base; struct create_context *cc; - unsigned int next; - unsigned int remaining; + size_t rem, off, len; + size_t doff, dlen; + size_t noff, nlen; char *name; static const char smb3_create_tag_posix[] = { 0x93, 0xAD, 0x25, 0x50, 0x9C, @@ -2164,45 +2165,63 @@ smb2_parse_contexts(struct TCP_Server_Info *server, }; *oplock = 0; - data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); - remaining = le32_to_cpu(rsp->CreateContextsLength); - cc = (struct create_context *)data_offset; + + off = le32_to_cpu(rsp->CreateContextsOffset); + rem = le32_to_cpu(rsp->CreateContextsLength); + if (check_add_overflow(off, rem, &len) || len > rsp_iov->iov_len) + return -EINVAL; + cc = (struct create_context *)((u8 *)rsp + off); /* Initialize inode number to 0 in case no valid data in qfid context */ if (buf) buf->IndexNumber = 0; - while (remaining >= sizeof(struct create_context)) { - name = le16_to_cpu(cc->NameOffset) + (char *)cc; - if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) - *oplock = server->ops->parse_lease_buf(cc, epoch, - lease_key); - else if (buf && (le16_to_cpu(cc->NameLength) == 4) && - strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) - parse_query_id_ctxt(cc, buf); - else if ((le16_to_cpu(cc->NameLength) == 16)) { - if (posix && - memcmp(name, smb3_create_tag_posix, 16) == 0) + while (rem >= sizeof(*cc)) { + doff = le16_to_cpu(cc->DataOffset); + dlen = le32_to_cpu(cc->DataLength); + if (check_add_overflow(doff, dlen, &len) || len > rem) + return -EINVAL; + + noff = le16_to_cpu(cc->NameOffset); + nlen = le16_to_cpu(cc->NameLength); + if (noff + nlen > doff) + return -EINVAL; + + name = (char *)cc + noff; + switch (nlen) { + case 4: + if (!strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4)) { + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + } else if (buf && + !strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4)) { + parse_query_id_ctxt(cc, buf); + } + break; + case 16: + if (posix && !memcmp(name, smb3_create_tag_posix, 16)) parse_posix_ctxt(cc, buf, posix); + break; + default: + cifs_dbg(FYI, "%s: unhandled context (nlen=%zu dlen=%zu)\n", + __func__, nlen, dlen); + if (IS_ENABLED(CONFIG_CIFS_DEBUG2)) + cifs_dump_mem("context data: ", cc, dlen); + break; } - /* else { - cifs_dbg(FYI, "Context not matched with len %d\n", - le16_to_cpu(cc->NameLength)); - cifs_dump_mem("Cctxt name: ", name, 4); - } */ - - next = le32_to_cpu(cc->Next); - if (!next) + + off = le32_to_cpu(cc->Next); + if (!off) break; - remaining -= next; - cc = (struct create_context *)((char *)cc + next); + if (check_sub_overflow(rem, off, &rem)) + return -EINVAL; + cc = (struct create_context *)((u8 *)cc + off); } if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) *oplock = rsp->OplockLevel; - return; + return 0; } static int @@ -3082,8 +3101,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, } - smb2_parse_contexts(server, rsp, &oparms->fid->epoch, - oparms->fid->lease_key, oplock, buf, posix); + rc = smb2_parse_contexts(server, &rsp_iov, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf, posix); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); @@ -4991,6 +5010,9 @@ int SMB2_query_directory_init(const unsigned int xid, case SMB_FIND_FILE_POSIX_INFO: req->FileInformationClass = SMB_FIND_FILE_POSIX_INFO; break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + req->FileInformationClass = FILE_FULL_DIRECTORY_INFORMATION; + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", info_level); @@ -5060,6 +5082,9 @@ smb2_parse_query_directory(struct cifs_tcon *tcon, /* note that posix payload are variable size */ info_buf_size = sizeof(struct smb2_posix_info); break; + case SMB_FIND_FILE_FULL_DIRECTORY_INFO: + info_buf_size = sizeof(FILE_FULL_DIRECTORY_INFO); + break; default: cifs_tcon_dbg(VFS, "info level %u isn't supported\n", srch_inf->info_level); diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index be21b5d26..b325fde01 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -249,11 +249,13 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern void smb2_parse_contexts(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key, - __u8 *oplock, struct smb2_file_all_info *buf, - struct create_posix_rsp *posix); +int smb2_parse_contexts(struct TCP_Server_Info *server, + struct kvec *rsp_iov, + unsigned int *epoch, + char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf, + struct create_posix_rsp *posix); + extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 8a1dd8407..df44acaec 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -427,10 +427,17 @@ unmask: server->conn_id, server->hostname); } smbd_done: - if (rc < 0 && rc != -EINTR) + /* + * there's hardly any use for the layers above to know the + * actual error code here. All they should do at this point is + * to retry the connection and hope it goes away. + */ + if (rc < 0 && rc != -EINTR && rc != -EAGAIN) { cifs_server_dbg(VFS, "Error %d sending data on socket to server\n", rc); - else if (rc > 0) + rc = -ECONNABORTED; + cifs_signal_cifsd_for_reconnect(server, false); + } else if (rc > 0) rc = 0; out: cifs_in_send_dec(server); @@ -449,8 +456,8 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, if (!(flags & CIFS_TRANSFORM_REQ)) return __smb_send_rqst(server, num_rqst, rqst); - if (num_rqst > MAX_COMPOUND - 1) - return -ENOMEM; + if (WARN_ON_ONCE(num_rqst > MAX_COMPOUND - 1)) + return -EIO; if (!server->ops->init_transform_rq) { cifs_server_dbg(VFS, "Encryption requested but transform callback is missing\n"); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 4cfa45c27..66d25d0e3 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -6171,8 +6171,10 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, @@ -6382,8 +6384,10 @@ int smb2_read(struct ksmbd_work *work) err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); - if (err) + if (err) { + kvfree(aux_payload_buf); goto out; + } ksmbd_fd_put(work, fp); return 0; diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 63cd50840..8d5f4a5a7 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -349,7 +349,12 @@ static int zonefs_file_write_dio_end_io(struct kiocb *iocb, ssize_t size, struct zonefs_inode_info *zi = ZONEFS_I(inode); if (error) { - zonefs_io_error(inode, true); + /* + * For Sync IOs, error recovery is called from + * zonefs_file_dio_write(). + */ + if (!is_sync_kiocb(iocb)) + zonefs_io_error(inode, true); return error; } @@ -577,6 +582,14 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EINVAL; goto inode_unlock; } + /* + * Advance the zone write pointer offset. This assumes that the + * IO will succeed, which is OK to do because we do not allow + * partial writes (IOMAP_DIO_PARTIAL is not set) and if the IO + * fails, the error path will correct the write pointer offset. + */ + z->z_wpoffset += count; + zonefs_inode_account_active(inode); mutex_unlock(&zi->i_truncate_mutex); append = sync; } @@ -596,20 +609,19 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = -EBUSY; } - if (zonefs_zone_is_seq(z) && - (ret > 0 || ret == -EIOCBQUEUED)) { - if (ret > 0) - count = ret; - - /* - * Update the zone write pointer offset assuming the write - * operation succeeded. If it did not, the error recovery path - * will correct it. Also do active seq file accounting. - */ - mutex_lock(&zi->i_truncate_mutex); - z->z_wpoffset += count; - zonefs_inode_account_active(inode); - mutex_unlock(&zi->i_truncate_mutex); + /* + * For a failed IO or partial completion, trigger error recovery + * to update the zone write pointer offset to a correct value. + * For asynchronous IOs, zonefs_file_write_dio_end_io() may already + * have executed error recovery if the IO already completed when we + * reach here. However, we cannot know that and execute error recovery + * again (that will not change anything). + */ + if (zonefs_zone_is_seq(z)) { + if (ret > 0 && ret != count) + ret = -EIO; + if (ret < 0 && ret != -EIOCBQUEUED) + zonefs_io_error(inode, true); } inode_unlock: diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 270ded209..f6b701261 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -245,16 +245,18 @@ static void zonefs_inode_update_mode(struct inode *inode) z->z_flags &= ~ZONEFS_ZONE_INIT_MODE; } -struct zonefs_ioerr_data { - struct inode *inode; - bool write; -}; - static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, void *data) { - struct zonefs_ioerr_data *err = data; - struct inode *inode = err->inode; + struct blk_zone *z = data; + + *z = *zone; + return 0; +} + +static void zonefs_handle_io_error(struct inode *inode, struct blk_zone *zone, + bool write) +{ struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; struct zonefs_sb_info *sbi = ZONEFS_SB(sb); @@ -269,8 +271,8 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(sb, z, zone); isize = i_size_read(inode); if (!(z->z_flags & (ZONEFS_ZONE_READONLY | ZONEFS_ZONE_OFFLINE)) && - !err->write && isize == data_size) - return 0; + !write && isize == data_size) + return; /* * At this point, we detected either a bad zone or an inconsistency @@ -291,7 +293,7 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, * In all cases, warn about inode size inconsistency and handle the * IO error according to the zone condition and to the mount options. */ - if (zonefs_zone_is_seq(z) && isize != data_size) + if (isize != data_size) zonefs_warn(sb, "inode %lu: invalid size %lld (should be %lld)\n", inode->i_ino, isize, data_size); @@ -351,8 +353,6 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, zonefs_i_size_write(inode, data_size); z->z_wpoffset = data_size; zonefs_inode_account_active(inode); - - return 0; } /* @@ -366,23 +366,25 @@ void __zonefs_io_error(struct inode *inode, bool write) { struct zonefs_zone *z = zonefs_inode_zone(inode); struct super_block *sb = inode->i_sb; - struct zonefs_sb_info *sbi = ZONEFS_SB(sb); unsigned int noio_flag; - unsigned int nr_zones = 1; - struct zonefs_ioerr_data err = { - .inode = inode, - .write = write, - }; + struct blk_zone zone; int ret; /* - * The only files that have more than one zone are conventional zone - * files with aggregated conventional zones, for which the inode zone - * size is always larger than the device zone size. + * Conventional zone have no write pointer and cannot become read-only + * or offline. So simply fake a report for a single or aggregated zone + * and let zonefs_handle_io_error() correct the zone inode information + * according to the mount options. */ - if (z->z_size > bdev_zone_sectors(sb->s_bdev)) - nr_zones = z->z_size >> - (sbi->s_zone_sectors_shift + SECTOR_SHIFT); + if (!zonefs_zone_is_seq(z)) { + zone.start = z->z_sector; + zone.len = z->z_size >> SECTOR_SHIFT; + zone.wp = zone.start + zone.len; + zone.type = BLK_ZONE_TYPE_CONVENTIONAL; + zone.cond = BLK_ZONE_COND_NOT_WP; + zone.capacity = zone.len; + goto handle_io_error; + } /* * Memory allocations in blkdev_report_zones() can trigger a memory @@ -393,12 +395,20 @@ void __zonefs_io_error(struct inode *inode, bool write) * the GFP_NOIO context avoids both problems. */ noio_flag = memalloc_noio_save(); - ret = blkdev_report_zones(sb->s_bdev, z->z_sector, nr_zones, - zonefs_io_error_cb, &err); - if (ret != nr_zones) + ret = blkdev_report_zones(sb->s_bdev, z->z_sector, 1, + zonefs_io_error_cb, &zone); + memalloc_noio_restore(noio_flag); + + if (ret != 1) { zonefs_err(sb, "Get inode %lu zone information failed %d\n", inode->i_ino, ret); - memalloc_noio_restore(noio_flag); + zonefs_warn(sb, "remounting filesystem read-only\n"); + sb->s_flags |= SB_RDONLY; + return; + } + +handle_io_error: + zonefs_handle_io_error(inode, &zone, write); } static struct kmem_cache *zonefs_inode_cachep; -- cgit v1.2.3