From a1865fbd182b17f2d2f465f557af5b45501c5f1c Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 20:47:48 +0200 Subject: Adding upstream version 6.7.12. Signed-off-by: Daniel Baumann --- fs/afs/dir.c | 10 -- fs/aio.c | 10 +- fs/bcachefs/btree_iter.c | 4 +- fs/bcachefs/chardev.c | 3 +- fs/bcachefs/errcode.h | 1 + fs/bcachefs/mean_and_variance.h | 2 +- fs/bcachefs/super-io.c | 27 ++- fs/btrfs/block-group.c | 3 +- fs/btrfs/block-rsv.c | 2 +- fs/btrfs/block-rsv.h | 32 ++++ fs/btrfs/extent_io.c | 75 ++++++-- fs/btrfs/qgroup.c | 10 +- fs/btrfs/scrub.c | 12 +- fs/btrfs/space-info.c | 26 +-- fs/btrfs/volumes.c | 69 ++++++-- fs/btrfs/zoned.c | 9 + fs/ceph/caps.c | 65 ++++--- fs/ceph/file.c | 23 +-- fs/ceph/mds_client.c | 48 ++++++ fs/ceph/mds_client.h | 5 + fs/debugfs/inode.c | 25 ++- fs/dlm/user.c | 10 +- fs/erofs/data.c | 1 + fs/erofs/fscache.c | 20 ++- fs/erofs/internal.h | 1 - fs/erofs/super.c | 30 +--- fs/eventfd.c | 11 +- fs/exec.c | 1 + fs/ext2/ext2.h | 2 +- fs/ext2/super.c | 2 +- fs/ext4/ext4.h | 2 +- fs/ext4/mballoc.c | 17 +- fs/ext4/resize.c | 3 +- fs/ext4/super.c | 2 +- fs/f2fs/checkpoint.c | 5 +- fs/f2fs/compress.c | 43 +++-- fs/f2fs/data.c | 73 ++++---- fs/f2fs/dir.c | 5 +- fs/f2fs/f2fs.h | 110 +++++++++--- fs/f2fs/file.c | 94 +++++----- fs/f2fs/gc.c | 7 +- fs/f2fs/inode.c | 57 ++----- fs/f2fs/namei.c | 25 ++- fs/f2fs/node.c | 20 ++- fs/f2fs/recovery.c | 33 ++-- fs/f2fs/segment.c | 29 ++-- fs/f2fs/segment.h | 17 +- fs/f2fs/super.c | 17 +- fs/fat/nfs.c | 6 + fs/fcntl.c | 12 +- fs/fhandle.c | 2 +- fs/fuse/dir.c | 6 +- fs/fuse/file.c | 8 +- fs/fuse/fuse_i.h | 1 - fs/fuse/inode.c | 7 +- fs/iomap/buffered-io.c | 18 +- fs/jfs/jfs_incore.h | 2 +- fs/jfs/super.c | 2 +- fs/nfs/direct.c | 11 +- fs/nfs/flexfilelayout/flexfilelayout.c | 2 +- fs/nfs/fscache.c | 9 +- fs/nfs/nfs42.h | 7 +- fs/nfs/nfs4proc.c | 16 +- fs/nfs/nfsroot.c | 4 +- fs/nfs/pnfs_nfs.c | 44 ++++- fs/nfs/read.c | 2 + fs/nfs/write.c | 2 +- fs/nfsd/trace.h | 2 +- fs/nilfs2/btree.c | 9 +- fs/nilfs2/direct.c | 9 +- fs/nilfs2/inode.c | 2 +- fs/ocfs2/inode.h | 2 +- fs/ocfs2/super.c | 2 +- fs/overlayfs/params.c | 14 +- fs/pstore/inode.c | 76 ++++----- fs/quota/dquot.c | 159 ++++++++++------- fs/reiserfs/reiserfs.h | 2 +- fs/reiserfs/super.c | 2 +- fs/select.c | 2 +- fs/smb/client/cached_dir.c | 3 +- fs/smb/client/cifs_debug.c | 2 + fs/smb/client/cifsglob.h | 5 + fs/smb/client/cifsproto.h | 8 +- fs/smb/client/connect.c | 6 +- fs/smb/client/file.c | 303 ++++++++++++++++++--------------- fs/smb/client/fs_context.c | 27 ++- fs/smb/client/inode.c | 17 +- fs/smb/client/readdir.c | 133 ++++++--------- fs/smb/client/sess.c | 45 +++-- fs/smb/client/smb2ops.c | 2 + fs/smb/client/smb2pdu.c | 10 +- fs/smb/server/smb2misc.c | 26 ++- fs/smb/server/smb2pdu.c | 228 ++++++++++++++++--------- fs/smb/server/smb_common.c | 11 +- fs/smb/server/vfs.c | 12 +- fs/ubifs/file.c | 13 +- 96 files changed, 1438 insertions(+), 953 deletions(-) (limited to 'fs') diff --git a/fs/afs/dir.c b/fs/afs/dir.c index c097da6e9c..7761f25a77 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -474,16 +474,6 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; } - /* Don't expose silly rename entries to userspace. */ - if (nlen > 6 && - dire->u.name[0] == '.' && - ctx->actor != afs_lookup_filldir && - ctx->actor != afs_lookup_one_filldir && - 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, ntohl(dire->u.vnode), diff --git a/fs/aio.c b/fs/aio.c index 3235d4e6cc..be12d7c049 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -590,8 +590,8 @@ static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { - struct aio_kiocb *req = container_of(iocb, struct aio_kiocb, rw); - struct kioctx *ctx = req->ki_ctx; + struct aio_kiocb *req; + struct kioctx *ctx; unsigned long flags; /* @@ -601,9 +601,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) if (!(iocb->ki_flags & IOCB_AIO_RW)) return; + req = container_of(iocb, struct aio_kiocb, rw); + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; + ctx = req->ki_ctx; + spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; @@ -1173,7 +1177,7 @@ static void aio_complete(struct aio_kiocb *iocb) * from IRQ context. */ if (iocb->ki_eventfd) - eventfd_signal(iocb->ki_eventfd, 1); + eventfd_signal(iocb->ki_eventfd); /* * We have to order our ring_info tail store above and test diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index da594e0067..816ecc3375 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2094,7 +2094,9 @@ struct bkey_s_c bch2_btree_iter_peek_upto(struct btree_iter *iter, struct bpos e * isn't monotonically increasing before FILTER_SNAPSHOTS, and * that's what we check against in extents mode: */ - if (k.k->p.inode > end.inode) + if (unlikely(!(iter->flags & BTREE_ITER_IS_EXTENTS) + ? bkey_gt(k.k->p, end) + : k.k->p.inode > end.inode)) goto end; if (iter->update_path && diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c index 4bb88aefed..64000c8da5 100644 --- a/fs/bcachefs/chardev.c +++ b/fs/bcachefs/chardev.c @@ -392,10 +392,9 @@ static long bch2_ioctl_data(struct bch_fs *c, goto err; } - fd_install(fd, file); - get_task_struct(ctx->thread); wake_up_process(ctx->thread); + fd_install(fd, file); return fd; err: diff --git a/fs/bcachefs/errcode.h b/fs/bcachefs/errcode.h index 9ce29681ee..ac90faccdc 100644 --- a/fs/bcachefs/errcode.h +++ b/fs/bcachefs/errcode.h @@ -224,6 +224,7 @@ x(BCH_ERR_invalid, invalid_bkey) \ x(BCH_ERR_operation_blocked, nocow_lock_blocked) \ x(EIO, btree_node_read_err) \ + x(EIO, sb_not_downgraded) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_fixable) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_want_retry) \ x(BCH_ERR_btree_node_read_err, btree_node_read_err_must_retry) \ diff --git a/fs/bcachefs/mean_and_variance.h b/fs/bcachefs/mean_and_variance.h index 647505010b..056e797383 100644 --- a/fs/bcachefs/mean_and_variance.h +++ b/fs/bcachefs/mean_and_variance.h @@ -14,7 +14,7 @@ * type */ -#ifdef __SIZEOF_INT128__ +#if defined(__SIZEOF_INT128__) && defined(__KERNEL__) && !defined(CONFIG_PARISC) typedef struct { unsigned __int128 v; diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c index 4c98d8cc2a..c925dc5742 100644 --- a/fs/bcachefs/super-io.c +++ b/fs/bcachefs/super-io.c @@ -966,6 +966,18 @@ int bch2_write_super(struct bch_fs *c) if (!BCH_SB_INITIALIZED(c->disk_sb.sb)) goto out; + if (le16_to_cpu(c->disk_sb.sb->version) > bcachefs_metadata_version_current) { + struct printbuf buf = PRINTBUF; + prt_printf(&buf, "attempting to write superblock that wasn't version downgraded ("); + bch2_version_to_text(&buf, le16_to_cpu(c->disk_sb.sb->version)); + prt_str(&buf, " > "); + bch2_version_to_text(&buf, bcachefs_metadata_version_current); + prt_str(&buf, ")"); + bch2_fs_fatal_error(c, "%s", buf.buf); + printbuf_exit(&buf); + return -BCH_ERR_sb_not_downgraded; + } + for_each_online_member(ca, c, i) { __set_bit(ca->dev_idx, sb_written.d); ca->sb_write_error = 0; @@ -1073,13 +1085,22 @@ bool bch2_check_version_downgrade(struct bch_fs *c) /* * Downgrade, if superblock is at a higher version than currently * supported: + * + * c->sb will be checked before we write the superblock, so update it as + * well: */ - if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) + if (BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb) > bcachefs_metadata_version_current) { SET_BCH_SB_VERSION_UPGRADE_COMPLETE(c->disk_sb.sb, bcachefs_metadata_version_current); - if (c->sb.version > bcachefs_metadata_version_current) + c->sb.version_upgrade_complete = bcachefs_metadata_version_current; + } + if (c->sb.version > bcachefs_metadata_version_current) { c->disk_sb.sb->version = cpu_to_le16(bcachefs_metadata_version_current); - if (c->sb.version_min > bcachefs_metadata_version_current) + c->sb.version = bcachefs_metadata_version_current; + } + if (c->sb.version_min > bcachefs_metadata_version_current) { c->disk_sb.sb->version_min = cpu_to_le16(bcachefs_metadata_version_current); + c->sb.version_min = bcachefs_metadata_version_current; + } c->disk_sb.sb->compat[0] &= cpu_to_le64((1ULL << BCH_COMPAT_NR) - 1); return ret; } diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index aca24186d6..52bab8cf78 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1562,7 +1562,8 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info) * 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) { + if (space_info->total_bytes - block_group->length < used && + block_group->zone_unusable < block_group->length) { /* * Add a reference for the list, compensate for the ref * drop under the "next" label for the diff --git a/fs/btrfs/block-rsv.c b/fs/btrfs/block-rsv.c index ceb5f586a2..1043a81423 100644 --- a/fs/btrfs/block-rsv.c +++ b/fs/btrfs/block-rsv.c @@ -494,7 +494,7 @@ struct btrfs_block_rsv *btrfs_use_block_rsv(struct btrfs_trans_handle *trans, block_rsv = get_block_rsv(trans, root); - if (unlikely(block_rsv->size == 0)) + if (unlikely(btrfs_block_rsv_size(block_rsv) == 0)) goto try_reserve; again: ret = btrfs_block_rsv_use_bytes(block_rsv, blocksize); diff --git a/fs/btrfs/block-rsv.h b/fs/btrfs/block-rsv.h index b0bd12b865..43a9a6b5a7 100644 --- a/fs/btrfs/block-rsv.h +++ b/fs/btrfs/block-rsv.h @@ -101,4 +101,36 @@ static inline bool btrfs_block_rsv_full(const struct btrfs_block_rsv *rsv) return data_race(rsv->full); } +/* + * Get the reserved mount of a block reserve in a context where getting a stale + * value is acceptable, instead of accessing it directly and trigger data race + * warning from KCSAN. + */ +static inline u64 btrfs_block_rsv_reserved(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->reserved; + spin_unlock(&rsv->lock); + + return ret; +} + +/* + * Get the size of a block reserve in a context where getting a stale value is + * acceptable, instead of accessing it directly and trigger data race warning + * from KCSAN. + */ +static inline u64 btrfs_block_rsv_size(struct btrfs_block_rsv *rsv) +{ + u64 ret; + + spin_lock(&rsv->lock); + ret = rsv->size; + spin_unlock(&rsv->lock); + + return ret; +} + #endif /* BTRFS_BLOCK_RSV_H */ diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index eade0432bd..87082f9732 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2734,16 +2734,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode, * it beyond i_size. */ while (cur_offset < end && cur_offset < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; u64 prealloc_start; + u64 lockstart; + u64 lockend; u64 prealloc_len = 0; bool delalloc; + lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize); + lockend = round_up(end, inode->root->fs_info->sectorsize); + + /* + * We are only locking for the delalloc range because that's the + * only thing that can change here. With fiemap we have a lock + * on the inode, so no buffered or direct writes can happen. + * + * However mmaps and normal page writeback will cause this to + * change arbitrarily. We have to lock the extent lock here to + * make sure that nobody messes with the tree while we're doing + * btrfs_find_delalloc_in_range. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end, delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) break; @@ -2911,15 +2929,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { const u64 ino = btrfs_ino(inode); - struct extent_state *cached_state = NULL; struct extent_state *delalloc_cached_state = NULL; struct btrfs_path *path; struct fiemap_cache cache = { 0 }; struct btrfs_backref_share_check_ctx *backref_ctx; u64 last_extent_end; u64 prev_extent_end; - u64 lockstart; - u64 lockend; + u64 range_start; + u64 range_end; + const u64 sectorsize = inode->root->fs_info->sectorsize; bool stopped = false; int ret; @@ -2930,12 +2948,11 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - lockstart = round_down(start, inode->root->fs_info->sectorsize); - lockend = round_up(start + len, inode->root->fs_info->sectorsize); - prev_extent_end = lockstart; + range_start = round_down(start, sectorsize); + range_end = round_up(start + len, sectorsize); + prev_extent_end = range_start; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) @@ -2943,7 +2960,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, btrfs_release_path(path); path->reada = READA_FORWARD; - ret = fiemap_search_slot(inode, path, lockstart); + ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -2955,7 +2972,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto check_eof_delalloc; } - while (prev_extent_end < lockend) { + while (prev_extent_end < range_end) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_file_extent_item *ei; struct btrfs_key key; @@ -2978,19 +2995,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, * The first iteration can leave us at an extent item that ends * before our range's start. Move to the next item. */ - if (extent_end <= lockstart) + if (extent_end <= range_start) goto next_item; backref_ctx->curr_leaf_bytenr = leaf->start; /* We have in implicit hole (NO_HOLES feature enabled). */ if (prev_extent_end < key.offset) { - const u64 range_end = min(key.offset, lockend) - 1; + const u64 hole_end = min(key.offset, range_end) - 1; ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, - prev_extent_end, range_end); + prev_extent_end, hole_end); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -3000,7 +3017,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } /* We've reached the end of the fiemap range, stop. */ - if (key.offset >= lockend) { + if (key.offset >= range_end) { stopped = true; break; } @@ -3094,29 +3111,41 @@ check_eof_delalloc: btrfs_free_path(path); path = NULL; - if (!stopped && prev_extent_end < lockend) { + if (!stopped && prev_extent_end < range_end) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, - 0, 0, 0, prev_extent_end, lockend - 1); + 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) goto out_unlock; - prev_extent_end = lockend; + prev_extent_end = range_end; } if (cache.cached && cache.offset + cache.len >= last_extent_end) { const u64 i_size = i_size_read(&inode->vfs_inode); if (prev_extent_end < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; + u64 lockstart; + u64 lockend; bool delalloc; + lockstart = round_down(prev_extent_end, sectorsize); + lockend = round_up(i_size, sectorsize); + + /* + * See the comment in fiemap_process_hole as to why + * we're doing the locking here. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, prev_extent_end, i_size - 1, &delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) cache.flags |= FIEMAP_EXTENT_LAST; } else { @@ -3127,7 +3156,6 @@ check_eof_delalloc: ret = emit_last_fiemap_cache(fieinfo, &cache); out_unlock: - unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); out: free_extent_state(delalloc_cached_state); @@ -4024,6 +4052,19 @@ int read_extent_buffer_pages(struct extent_buffer *eb, int wait, int mirror_num, if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) goto done; + /* + * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above + * test_and_set_bit(EXTENT_BUFFER_READING), someone else could have + * started and finished reading the same eb. In this case, UPTODATE + * will now be set, and we shouldn't read it in again. + */ + if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) { + clear_bit(EXTENT_BUFFER_READING, &eb->bflags); + smp_mb__after_atomic(); + wake_up_bit(&eb->bflags, EXTENT_BUFFER_READING); + return 0; + } + clear_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = 0; check_buffer_tree_ref(eb); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index bbfa44b89b..1dcf5bb8df 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2959,11 +2959,6 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) ctx.roots = NULL; } - /* Free the reserved data space */ - btrfs_qgroup_free_refroot(fs_info, - record->data_rsv_refroot, - record->data_rsv, - BTRFS_QGROUP_RSV_DATA); /* * Use BTRFS_SEQ_LAST as time_seq to do special search, * which doesn't lock tree or delayed_refs and search @@ -2987,6 +2982,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) record->old_roots = NULL; new_roots = NULL; } + /* Free the reserved data space */ + btrfs_qgroup_free_refroot(fs_info, + record->data_rsv_refroot, + record->data_rsv, + BTRFS_QGROUP_RSV_DATA); cleanup: ulist_free(record->old_roots); ulist_free(new_roots); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 443d2519f0..258b3e5585 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2809,7 +2809,17 @@ static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, gen = btrfs_get_last_trans_committed(fs_info); for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { - bytenr = btrfs_sb_offset(i); + ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); + if (ret == -ENOENT) + break; + + if (ret) { + spin_lock(&sctx->stat_lock); + sctx->stat.super_errors++; + spin_unlock(&sctx->stat_lock); + continue; + } + if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 571bb13587..3b54eb5834 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -856,7 +856,7 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info, static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info) { - u64 global_rsv_size = fs_info->global_block_rsv.reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(&fs_info->global_block_rsv); u64 ordered, delalloc; u64 thresh; u64 used; @@ -956,8 +956,8 @@ static bool need_preemptive_reclaim(struct btrfs_fs_info *fs_info, ordered = percpu_counter_read_positive(&fs_info->ordered_bytes) >> 1; delalloc = percpu_counter_read_positive(&fs_info->delalloc_bytes); if (ordered >= delalloc) - used += fs_info->delayed_refs_rsv.reserved + - fs_info->delayed_block_rsv.reserved; + used += btrfs_block_rsv_reserved(&fs_info->delayed_refs_rsv) + + btrfs_block_rsv_reserved(&fs_info->delayed_block_rsv); else used += space_info->bytes_may_use - global_rsv_size; @@ -1173,7 +1173,7 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) enum btrfs_flush_state flush; u64 delalloc_size = 0; u64 to_reclaim, block_rsv_size; - u64 global_rsv_size = global_rsv->reserved; + const u64 global_rsv_size = btrfs_block_rsv_reserved(global_rsv); loops++; @@ -1185,9 +1185,9 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * assume it's tied up in delalloc reservations. */ block_rsv_size = global_rsv_size + - delayed_block_rsv->reserved + - delayed_refs_rsv->reserved + - trans_rsv->reserved; + btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv) + + btrfs_block_rsv_reserved(trans_rsv); if (block_rsv_size < space_info->bytes_may_use) delalloc_size = space_info->bytes_may_use - block_rsv_size; @@ -1207,16 +1207,16 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) to_reclaim = delalloc_size; flush = FLUSH_DELALLOC; } else if (space_info->bytes_pinned > - (delayed_block_rsv->reserved + - delayed_refs_rsv->reserved)) { + (btrfs_block_rsv_reserved(delayed_block_rsv) + + btrfs_block_rsv_reserved(delayed_refs_rsv))) { to_reclaim = space_info->bytes_pinned; flush = COMMIT_TRANS; - } else if (delayed_block_rsv->reserved > - delayed_refs_rsv->reserved) { - to_reclaim = delayed_block_rsv->reserved; + } else if (btrfs_block_rsv_reserved(delayed_block_rsv) > + btrfs_block_rsv_reserved(delayed_refs_rsv)) { + to_reclaim = btrfs_block_rsv_reserved(delayed_block_rsv); flush = FLUSH_DELAYED_ITEMS_NR; } else { - to_reclaim = delayed_refs_rsv->reserved; + to_reclaim = btrfs_block_rsv_reserved(delayed_refs_rsv); flush = FLUSH_DELAYED_REFS_NR; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f627674b37..fd30dc3d59 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -683,6 +683,16 @@ static int btrfs_open_one_device(struct btrfs_fs_devices *fs_devices, device->bdev = bdev_handle->bdev; clear_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); + if (device->devt != device->bdev->bd_dev) { + btrfs_warn(NULL, + "device %s maj:min changed from %d:%d to %d:%d", + device->name->str, MAJOR(device->devt), + MINOR(device->devt), MAJOR(device->bdev->bd_dev), + MINOR(device->bdev->bd_dev)); + + device->devt = device->bdev->bd_dev; + } + fs_devices->open_devices++; if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && device->devid != BTRFS_DEV_REPLACE_DEVID) { @@ -1290,6 +1300,47 @@ int btrfs_forget_devices(dev_t devt) return ret; } +static bool btrfs_skip_registration(struct btrfs_super_block *disk_super, + const char *path, dev_t devt, + bool mount_arg_dev) +{ + struct btrfs_fs_devices *fs_devices; + + /* + * Do not skip device registration for mounted devices with matching + * maj:min but different paths. Booting without initrd relies on + * /dev/root initially, later replaced with the actual root device. + * A successful scan ensures grub2-probe selects the correct device. + */ + list_for_each_entry(fs_devices, &fs_uuids, fs_list) { + struct btrfs_device *device; + + mutex_lock(&fs_devices->device_list_mutex); + + if (!fs_devices->opened) { + mutex_unlock(&fs_devices->device_list_mutex); + continue; + } + + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (device->bdev && (device->bdev->bd_dev == devt) && + strcmp(device->name->str, path) != 0) { + mutex_unlock(&fs_devices->device_list_mutex); + + /* Do not skip registration. */ + return false; + } + } + mutex_unlock(&fs_devices->device_list_mutex); + } + + if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && + !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) + return true; + + return false; +} + /* * Look for a btrfs signature on a device. This may be called out of the mount path * and we are not allowed to call set_blocksize during the scan. The superblock @@ -1346,18 +1397,14 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, blk_mode_t flags, goto error_bdev_put; } - if (!mount_arg_dev && btrfs_super_num_devices(disk_super) == 1 && - !(btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_SEEDING)) { - dev_t devt; + if (btrfs_skip_registration(disk_super, path, bdev_handle->bdev->bd_dev, + mount_arg_dev)) { + pr_debug("BTRFS: skip registering single non-seed device %s (%d:%d)\n", + path, MAJOR(bdev_handle->bdev->bd_dev), + MINOR(bdev_handle->bdev->bd_dev)); - ret = lookup_bdev(path, &devt); - if (ret) - btrfs_warn(NULL, "lookup bdev failed for path %s: %d", - path, ret); - else - btrfs_free_stale_devices(devt, NULL); + btrfs_free_stale_devices(bdev_handle->bdev->bd_dev, NULL); - pr_debug("BTRFS: skip registering single non-seed device %s\n", path); device = NULL; goto free_disk_super; } @@ -1392,7 +1439,7 @@ static bool contains_pending_extent(struct btrfs_device *device, u64 *start, if (in_range(physical_start, *start, len) || in_range(*start, physical_start, - physical_end - physical_start)) { + physical_end + 1 - physical_start)) { *start = physical_end + 1; return true; } diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 3779e76a15..524532f992 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1661,6 +1661,15 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new) } out: + /* Reject non SINGLE data profiles without RST */ + if ((map->type & BTRFS_BLOCK_GROUP_DATA) && + (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) && + !fs_info->stripe_root) { + btrfs_err(fs_info, "zoned: data %s needs raid-stripe-tree", + btrfs_bg_type_to_raid_name(map->type)); + return -EINVAL; + } + if (cache->alloc_offset > cache->zone_capacity) { btrfs_err(fs_info, "zoned: invalid write pointer %llu (larger than zone capacity %llu) in block group %llu", diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index ad1f46c66f..7fb4aae974 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2156,6 +2156,30 @@ retry: ceph_cap_string(cap->implemented), ceph_cap_string(revoking)); + /* completed revocation? going down and there are no caps? */ + if (revoking) { + if ((revoking & cap_used) == 0) { + doutc(cl, "completed revocation of %s\n", + ceph_cap_string(cap->implemented & ~cap->issued)); + goto ack; + } + + /* + * If the "i_wrbuffer_ref" was increased by mmap or generic + * cache write just before the ceph_check_caps() is called, + * the Fb capability revoking will fail this time. Then we + * must wait for the BDI's delayed work to flush the dirty + * pages and to release the "i_wrbuffer_ref", which will cost + * at most 5 seconds. That means the MDS needs to wait at + * most 5 seconds to finished the Fb capability's revocation. + * + * Let's queue a writeback for it. + */ + if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref && + (revoking & CEPH_CAP_FILE_BUFFER)) + queue_writeback = true; + } + if (cap == ci->i_auth_cap && (cap->issued & CEPH_CAP_FILE_WR)) { /* request larger max_size from MDS? */ @@ -2183,30 +2207,6 @@ retry: } } - /* completed revocation? going down and there are no caps? */ - if (revoking) { - if ((revoking & cap_used) == 0) { - doutc(cl, "completed revocation of %s\n", - ceph_cap_string(cap->implemented & ~cap->issued)); - goto ack; - } - - /* - * If the "i_wrbuffer_ref" was increased by mmap or generic - * cache write just before the ceph_check_caps() is called, - * the Fb capability revoking will fail this time. Then we - * must wait for the BDI's delayed work to flush the dirty - * pages and to release the "i_wrbuffer_ref", which will cost - * at most 5 seconds. That means the MDS needs to wait at - * most 5 seconds to finished the Fb capability's revocation. - * - * Let's queue a writeback for it. - */ - if (S_ISREG(inode->i_mode) && ci->i_wrbuffer_ref && - (revoking & CEPH_CAP_FILE_BUFFER)) - queue_writeback = true; - } - /* want more caps from mds? */ if (want & ~cap->mds_wanted) { if (want & ~(cap->mds_wanted | cap->issued)) @@ -4772,7 +4772,22 @@ int ceph_drop_caps_for_unlink(struct inode *inode) if (__ceph_caps_dirty(ci)) { struct ceph_mds_client *mdsc = ceph_inode_to_fs_client(inode)->mdsc; - __cap_delay_requeue_front(mdsc, ci); + + doutc(mdsc->fsc->client, "%p %llx.%llx\n", inode, + ceph_vinop(inode)); + spin_lock(&mdsc->cap_unlink_delay_lock); + ci->i_ceph_flags |= CEPH_I_FLUSH; + if (!list_empty(&ci->i_cap_delay_list)) + list_del_init(&ci->i_cap_delay_list); + list_add_tail(&ci->i_cap_delay_list, + &mdsc->cap_unlink_delay_list); + spin_unlock(&mdsc->cap_unlink_delay_lock); + + /* + * Fire the work immediately, because the MDS maybe + * waiting for caps release. + */ + ceph_queue_cap_unlink_work(mdsc); } } spin_unlock(&ci->i_ceph_lock); diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 3b5aae29e9..523debc6f2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1135,7 +1135,12 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, } idx = 0; - left = ret > 0 ? ret : 0; + if (ret <= 0) + left = 0; + else if (off + ret > i_size) + left = i_size - off; + else + left = ret; while (left > 0) { size_t plen, copied; @@ -1164,15 +1169,13 @@ ssize_t __ceph_sync_read(struct inode *inode, loff_t *ki_pos, } if (ret > 0) { - if (off > *ki_pos) { - if (off >= i_size) { - *retry_op = CHECK_EOF; - ret = i_size - *ki_pos; - *ki_pos = i_size; - } else { - ret = off - *ki_pos; - *ki_pos = off; - } + if (off >= i_size) { + *retry_op = CHECK_EOF; + ret = i_size - *ki_pos; + *ki_pos = i_size; + } else { + ret = off - *ki_pos; + *ki_pos = off; } if (last_objver) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 2eb66dd7d0..950360b075 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2470,6 +2470,50 @@ void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr) } } +void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc) +{ + struct ceph_client *cl = mdsc->fsc->client; + if (mdsc->stopping) + return; + + if (queue_work(mdsc->fsc->cap_wq, &mdsc->cap_unlink_work)) { + doutc(cl, "caps unlink work queued\n"); + } else { + doutc(cl, "failed to queue caps unlink work\n"); + } +} + +static void ceph_cap_unlink_work(struct work_struct *work) +{ + struct ceph_mds_client *mdsc = + container_of(work, struct ceph_mds_client, cap_unlink_work); + struct ceph_client *cl = mdsc->fsc->client; + + doutc(cl, "begin\n"); + spin_lock(&mdsc->cap_unlink_delay_lock); + while (!list_empty(&mdsc->cap_unlink_delay_list)) { + struct ceph_inode_info *ci; + struct inode *inode; + + ci = list_first_entry(&mdsc->cap_unlink_delay_list, + struct ceph_inode_info, + i_cap_delay_list); + list_del_init(&ci->i_cap_delay_list); + + inode = igrab(&ci->netfs.inode); + if (inode) { + spin_unlock(&mdsc->cap_unlink_delay_lock); + doutc(cl, "on %p %llx.%llx\n", inode, + ceph_vinop(inode)); + ceph_check_caps(ci, CHECK_CAPS_FLUSH); + iput(inode); + spin_lock(&mdsc->cap_unlink_delay_lock); + } + } + spin_unlock(&mdsc->cap_unlink_delay_lock); + doutc(cl, "done\n"); +} + /* * requests */ @@ -5345,6 +5389,8 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) INIT_LIST_HEAD(&mdsc->cap_delay_list); INIT_LIST_HEAD(&mdsc->cap_wait_list); spin_lock_init(&mdsc->cap_delay_lock); + INIT_LIST_HEAD(&mdsc->cap_unlink_delay_list); + spin_lock_init(&mdsc->cap_unlink_delay_lock); INIT_LIST_HEAD(&mdsc->snap_flush_list); spin_lock_init(&mdsc->snap_flush_lock); mdsc->last_cap_flush_tid = 1; @@ -5353,6 +5399,7 @@ int ceph_mdsc_init(struct ceph_fs_client *fsc) spin_lock_init(&mdsc->cap_dirty_lock); init_waitqueue_head(&mdsc->cap_flushing_wq); INIT_WORK(&mdsc->cap_reclaim_work, ceph_cap_reclaim_work); + INIT_WORK(&mdsc->cap_unlink_work, ceph_cap_unlink_work); err = ceph_metric_init(&mdsc->metric); if (err) goto err_mdsmap; @@ -5626,6 +5673,7 @@ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) ceph_cleanup_global_and_empty_realms(mdsc); cancel_work_sync(&mdsc->cap_reclaim_work); + cancel_work_sync(&mdsc->cap_unlink_work); cancel_delayed_work_sync(&mdsc->delayed_work); /* cancel timer */ doutc(cl, "done\n"); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 40560af388..03f8ff0087 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -462,6 +462,8 @@ struct ceph_mds_client { unsigned long last_renew_caps; /* last time we renewed our caps */ struct list_head cap_delay_list; /* caps with delayed release */ spinlock_t cap_delay_lock; /* protects cap_delay_list */ + struct list_head cap_unlink_delay_list; /* caps with delayed release for unlink */ + spinlock_t cap_unlink_delay_lock; /* protects cap_unlink_delay_list */ struct list_head snap_flush_list; /* cap_snaps ready to flush */ spinlock_t snap_flush_lock; @@ -475,6 +477,8 @@ struct ceph_mds_client { struct work_struct cap_reclaim_work; atomic_t cap_reclaim_pending; + struct work_struct cap_unlink_work; + /* * Cap reservations * @@ -574,6 +578,7 @@ extern void ceph_flush_cap_releases(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern void ceph_queue_cap_reclaim_work(struct ceph_mds_client *mdsc); extern void ceph_reclaim_caps_nr(struct ceph_mds_client *mdsc, int nr); +extern void ceph_queue_cap_unlink_work(struct ceph_mds_client *mdsc); extern int ceph_iterate_session_caps(struct ceph_mds_session *session, int (*cb)(struct inode *, int mds, void *), void *arg); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 034a617cb1..a40da00654 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -751,13 +751,28 @@ static void __debugfs_file_removed(struct dentry *dentry) if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; - /* if we hit zero, just wait for all to finish */ - if (!refcount_dec_and_test(&fsd->active_users)) { - wait_for_completion(&fsd->active_users_drained); + /* if this was the last reference, we're done */ + if (refcount_dec_and_test(&fsd->active_users)) return; - } - /* if we didn't hit zero, try to cancel any we can */ + /* + * If there's still a reference, the code that obtained it can + * be in different states: + * - The common case of not using cancellations, or already + * after debugfs_leave_cancellation(), where we just need + * to wait for debugfs_file_put() which signals the completion; + * - inside a cancellation section, i.e. between + * debugfs_enter_cancellation() and debugfs_leave_cancellation(), + * in which case we need to trigger the ->cancel() function, + * and then wait for debugfs_file_put() just like in the + * previous case; + * - before debugfs_enter_cancellation() (but obviously after + * debugfs_file_get()), in which case we may not see the + * cancellation in the list on the first round of the loop, + * but debugfs_enter_cancellation() signals the completion + * after adding it, so this code gets woken up to call the + * ->cancel() function. + */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 695e691b38..9f9b684488 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -806,7 +806,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, struct dlm_lkb *lkb; DECLARE_WAITQUEUE(wait, current); struct dlm_callback *cb; - int rv, copy_lvb = 0; + int rv, ret, copy_lvb = 0; int old_mode, new_mode; if (count == sizeof(struct dlm_device_version)) { @@ -906,9 +906,9 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, trace_dlm_ast(lkb->lkb_resource->res_ls, lkb); } - rv = copy_result_to_user(lkb->lkb_ua, - test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags), - cb->flags, cb->mode, copy_lvb, buf, count); + ret = copy_result_to_user(lkb->lkb_ua, + test_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags), + cb->flags, cb->mode, copy_lvb, buf, count); kref_put(&cb->ref, dlm_release_callback); @@ -916,7 +916,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count, if (rv == DLM_DEQUEUE_CALLBACK_LAST) dlm_put_lkb(lkb); - return rv; + return ret; } static __poll_t device_poll(struct file *file, poll_table *wait) diff --git a/fs/erofs/data.c b/fs/erofs/data.c index c98aeda8ab..3d9721b3fa 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -447,5 +447,6 @@ const struct file_operations erofs_file_fops = { .llseek = generic_file_llseek, .read_iter = erofs_file_read_iter, .mmap = erofs_file_mmap, + .get_unmapped_area = thp_get_unmapped_area, .splice_read = filemap_splice_read, }; diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 87ff35bff8..afc37c9029 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -3,6 +3,7 @@ * Copyright (C) 2022, Alibaba Cloud * Copyright (C) 2022, Bytedance Inc. All rights reserved. */ +#include #include #include "internal.h" @@ -12,6 +13,18 @@ static LIST_HEAD(erofs_domain_list); static LIST_HEAD(erofs_domain_cookies_list); static struct vfsmount *erofs_pseudo_mnt; +static int erofs_anon_init_fs_context(struct fs_context *fc) +{ + return init_pseudo(fc, EROFS_SUPER_MAGIC) ? 0 : -ENOMEM; +} + +static struct file_system_type erofs_anon_fs_type = { + .owner = THIS_MODULE, + .name = "pseudo_erofs", + .init_fs_context = erofs_anon_init_fs_context, + .kill_sb = kill_anon_super, +}; + struct erofs_fscache_request { struct erofs_fscache_request *primary; struct netfs_cache_resources cache_resources; @@ -381,11 +394,12 @@ static int erofs_fscache_init_domain(struct super_block *sb) goto out; if (!erofs_pseudo_mnt) { - erofs_pseudo_mnt = kern_mount(&erofs_fs_type); - if (IS_ERR(erofs_pseudo_mnt)) { - err = PTR_ERR(erofs_pseudo_mnt); + struct vfsmount *mnt = kern_mount(&erofs_anon_fs_type); + if (IS_ERR(mnt)) { + err = PTR_ERR(mnt); goto out; } + erofs_pseudo_mnt = mnt; } domain->volume = sbi->volume; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index b0409badb0..410f5af623 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -385,7 +385,6 @@ struct erofs_map_dev { unsigned int m_deviceid; }; -extern struct file_system_type erofs_fs_type; extern const struct super_operations erofs_sops; extern const struct address_space_operations erofs_raw_access_aops; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 3789d62245..8a82d5cec1 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -573,13 +573,6 @@ static const struct export_operations erofs_export_ops = { .get_parent = erofs_get_parent, }; -static int erofs_fc_fill_pseudo_super(struct super_block *sb, struct fs_context *fc) -{ - static const struct tree_descr empty_descr = {""}; - - return simple_fill_super(sb, EROFS_SUPER_MAGIC, &empty_descr); -} - static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; @@ -706,11 +699,6 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) return 0; } -static int erofs_fc_anon_get_tree(struct fs_context *fc) -{ - return get_tree_nodev(fc, erofs_fc_fill_pseudo_super); -} - static int erofs_fc_get_tree(struct fs_context *fc) { struct erofs_fs_context *ctx = fc->fs_private; @@ -783,20 +771,10 @@ static const struct fs_context_operations erofs_context_ops = { .free = erofs_fc_free, }; -static const struct fs_context_operations erofs_anon_context_ops = { - .get_tree = erofs_fc_anon_get_tree, -}; - static int erofs_init_fs_context(struct fs_context *fc) { struct erofs_fs_context *ctx; - /* pseudo mount for anon inodes */ - if (fc->sb_flags & SB_KERNMOUNT) { - fc->ops = &erofs_anon_context_ops; - return 0; - } - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; @@ -818,12 +796,6 @@ static void erofs_kill_sb(struct super_block *sb) { struct erofs_sb_info *sbi; - /* pseudo mount for anon inodes */ - if (sb->s_flags & SB_KERNMOUNT) { - kill_anon_super(sb); - return; - } - if (erofs_is_fscache_mode(sb)) kill_anon_super(sb); else @@ -862,7 +834,7 @@ static void erofs_put_super(struct super_block *sb) erofs_fscache_unregister_fs(sb); } -struct file_system_type erofs_fs_type = { +static struct file_system_type erofs_fs_type = { .owner = THIS_MODULE, .name = "erofs", .init_fs_context = erofs_init_fs_context, diff --git a/fs/eventfd.c b/fs/eventfd.c index 33a918f956..d2f7d2d8a3 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -72,22 +72,19 @@ __u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask) } /** - * eventfd_signal - Adds @n to the eventfd counter. + * eventfd_signal - Increment the event counter * @ctx: [in] Pointer to the eventfd context. - * @n: [in] Value of the counter to be added to the eventfd internal counter. - * The value cannot be negative. * * This function is supposed to be called by the kernel in paths that do not * allow sleeping. In this function we allow the counter to reach the ULLONG_MAX * value, and we signal this as overflow condition by returning a EPOLLERR * to poll(2). * - * Returns the amount by which the counter was incremented. This will be less - * than @n if the counter has overflowed. + * Returns the amount by which the counter was incremented. */ -__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n) +__u64 eventfd_signal(struct eventfd_ctx *ctx) { - return eventfd_signal_mask(ctx, n, 0); + return eventfd_signal_mask(ctx, 1, 0); } EXPORT_SYMBOL_GPL(eventfd_signal); diff --git a/fs/exec.c b/fs/exec.c index 6d9ed2d765..7a1861a718 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -894,6 +894,7 @@ int transfer_args_to_stack(struct linux_binprm *bprm, goto out; } + bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 677a9ad45d..f38bdd46e4 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -674,7 +674,7 @@ struct ext2_inode_info { struct inode vfs_inode; struct list_head i_orphan; /* unlinked but open inodes */ #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif }; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 01f9addc8b..6d8587505c 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -320,7 +320,7 @@ static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, siz static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off); static int ext2_quota_on(struct super_block *sb, int type, int format_id, const struct path *path); -static struct dquot **ext2_get_dquots(struct inode *inode) +static struct dquot __rcu **ext2_get_dquots(struct inode *inode) { return EXT2_I(inode)->i_dquot; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a5d7848723..3205d46bc9 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1156,7 +1156,7 @@ struct ext4_inode_info { tid_t i_datasync_tid; #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif /* Precomputed uuid+inum+igen checksum for seeding inode checksums */ diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 7497a789d0..38ec0fdb33 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -5173,10 +5173,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) .fe_len = ac->ac_orig_goal_len, }; loff_t orig_goal_end = extent_logical_end(sbi, &ex); + loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex); - /* we can't allocate as much as normalizer wants. - * so, found space must get proper lstart - * to cover original request */ + /* + * We can't allocate as much as normalizer wants, so we try + * to get proper lstart to cover the original request, except + * when the goal doesn't cover the original request as below: + * + * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048 + * best_ex:0/200(200) -> adjusted: 1848/2048(200) + */ BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical); BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len); @@ -5188,7 +5194,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) * 1. Check if best ex can be kept at end of goal (before * cr_best_avail trimmed it) and still cover original start * 2. Else, check if best ex can be kept at start of goal and - * still cover original start + * still cover original end * 3. Else, keep the best ex at start of original request. */ ex.fe_len = ac->ac_b_ex.fe_len; @@ -5198,7 +5204,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) goto adjust_bex; ex.fe_logical = ac->ac_g_ex.fe_logical; - if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex)) + if (o_ex_end <= extent_logical_end(sbi, &ex)) goto adjust_bex; ex.fe_logical = ac->ac_o_ex.fe_logical; @@ -5206,7 +5212,6 @@ adjust_bex: ac->ac_b_ex.fe_logical = ex.fe_logical; BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical); - BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len); BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end); } diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e168a9f596..9a39596d2a 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1592,7 +1592,8 @@ exit_journal: int gdb_num = group / EXT4_DESC_PER_BLOCK(sb); int gdb_num_end = ((group + flex_gd->count - 1) / EXT4_DESC_PER_BLOCK(sb)); - int meta_bg = ext4_has_feature_meta_bg(sb); + int meta_bg = ext4_has_feature_meta_bg(sb) && + gdb_num >= le32_to_cpu(es->s_first_meta_bg); sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr - ext4_group_first_block_no(sb, 0); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c5fcf377ab..3f1fa5d182 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1600,7 +1600,7 @@ static ssize_t ext4_quota_write(struct super_block *sb, int type, static int ext4_quota_enable(struct super_block *sb, int type, int format_id, unsigned int flags); -static struct dquot **ext4_get_dquots(struct inode *inode) +static struct dquot __rcu **ext4_get_dquots(struct inode *inode) { return EXT4_I(inode)->i_dquot; } diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index b0597a539f..9afc8d24dc 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1587,8 +1587,9 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc) */ if (f2fs_sb_has_encrypt(sbi) || f2fs_sb_has_verity(sbi) || f2fs_sb_has_compression(sbi)) - invalidate_mapping_pages(META_MAPPING(sbi), - MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1); + f2fs_bug_on(sbi, + invalidate_inode_pages2_range(META_MAPPING(sbi), + MAIN_BLKADDR(sbi), MAX_BLKADDR(sbi) - 1)); f2fs_release_ino_entry(sbi, false); diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 62119f3f72..52f407b978 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -1371,8 +1371,6 @@ unlock_continue: add_compr_block_stat(inode, cc->valid_nr_cpages); set_inode_flag(cc->inode, FI_APPEND_WRITE); - if (cc->cluster_idx == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); f2fs_put_dnode(&dn); if (quota_inode) @@ -1420,6 +1418,8 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = (struct compress_io_ctx *)page_private(page); + enum count_type type = WB_DATA_TYPE(page, + f2fs_is_compressed_page(page)); int i; if (unlikely(bio->bi_status)) @@ -1427,7 +1427,7 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) f2fs_compress_free_page(page); - dec_page_count(sbi, F2FS_WB_DATA); + dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; @@ -1443,12 +1443,14 @@ void f2fs_compress_write_end_io(struct bio *bio, struct page *page) } static int f2fs_write_raw_pages(struct compress_ctx *cc, - int *submitted, + int *submitted_p, struct writeback_control *wbc, enum iostat_type io_type) { struct address_space *mapping = cc->inode->i_mapping; - int _submitted, compr_blocks, ret, i; + struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); + int submitted, compr_blocks, i; + int ret = 0; compr_blocks = f2fs_compressed_blocks(cc); @@ -1463,6 +1465,10 @@ static int f2fs_write_raw_pages(struct compress_ctx *cc, if (compr_blocks < 0) return compr_blocks; + /* overwrite compressed cluster w/ normal cluster */ + if (compr_blocks > 0) + f2fs_lock_op(sbi); + for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; @@ -1487,7 +1493,7 @@ continue_unlock: if (!clear_page_dirty_for_io(cc->rpages[i])) goto continue_unlock; - ret = f2fs_write_single_data_page(cc->rpages[i], &_submitted, + ret = f2fs_write_single_data_page(cc->rpages[i], &submitted, NULL, NULL, wbc, io_type, compr_blocks, false); if (ret) { @@ -1495,26 +1501,29 @@ continue_unlock: unlock_page(cc->rpages[i]); ret = 0; } else if (ret == -EAGAIN) { + ret = 0; /* * for quota file, just redirty left pages to * avoid deadlock caused by cluster update race * from foreground operation. */ if (IS_NOQUOTA(cc->inode)) - return 0; - ret = 0; + goto out; f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry_write; } - return ret; + goto out; } - *submitted += _submitted; + *submitted_p += submitted; } - f2fs_balance_fs(F2FS_M_SB(mapping), true); +out: + if (compr_blocks > 0) + f2fs_unlock_op(sbi); - return 0; + f2fs_balance_fs(sbi, true); + return ret; } int f2fs_write_multi_pages(struct compress_ctx *cc, @@ -1808,16 +1817,18 @@ void f2fs_put_page_dic(struct page *page, bool in_task) * check whether cluster blocks are contiguous, and add extent cache entry * only if cluster blocks are logically and physically contiguous. */ -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node) { - bool compressed = f2fs_data_blkaddr(dn) == COMPRESS_ADDR; + bool compressed = data_blkaddr(dn->inode, dn->node_page, + ofs_in_node) == COMPRESS_ADDR; int i = compressed ? 1 : 0; block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + i); + ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) break; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index bc3f05d43b..c611d064ae 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -48,7 +48,7 @@ void f2fs_destroy_bioset(void) bioset_exit(&f2fs_bioset); } -static bool __is_cp_guaranteed(struct page *page) +bool f2fs_is_cp_guaranteed(struct page *page) { struct address_space *mapping = page->mapping; struct inode *inode; @@ -65,8 +65,6 @@ static bool __is_cp_guaranteed(struct page *page) S_ISDIR(inode->i_mode)) return true; - if (f2fs_is_compressed_page(page)) - return false; if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) || page_private_gcing(page)) return true; @@ -338,7 +336,7 @@ static void f2fs_write_end_io(struct bio *bio) bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; - enum count_type type = WB_DATA_TYPE(page); + enum count_type type = WB_DATA_TYPE(page, false); if (page_private_dummy(page)) { clear_page_private_dummy(page); @@ -762,7 +760,7 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); inc_page_count(fio->sbi, is_read_io(fio->op) ? - __read_io_type(page) : WB_DATA_TYPE(fio->page)); + __read_io_type(page) : WB_DATA_TYPE(fio->page, false)); if (is_read_io(bio_op(bio))) f2fs_submit_read_bio(fio->sbi, bio, fio->type); @@ -973,7 +971,7 @@ alloc_new: if (fio->io_wbc) wbc_account_cgroup_owner(fio->io_wbc, fio->page, PAGE_SIZE); - inc_page_count(fio->sbi, WB_DATA_TYPE(page)); + inc_page_count(fio->sbi, WB_DATA_TYPE(page, false)); *fio->last_block = fio->new_blkaddr; *fio->bio = bio; @@ -1007,11 +1005,12 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp; struct page *bio_page; + enum count_type type; f2fs_bug_on(sbi, is_read_io(fio->op)); f2fs_down_write(&io->io_rwsem); - +next: #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && io->zone_pending_bio) { wait_for_completion_io(&io->zone_wait); @@ -1021,7 +1020,6 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio) } #endif -next: if (fio->in_list) { spin_lock(&io->io_lock); if (list_empty(&io->io_list)) { @@ -1046,7 +1044,8 @@ next: /* set submitted = true as a return value */ fio->submitted = 1; - inc_page_count(sbi, WB_DATA_TYPE(bio_page)); + type = WB_DATA_TYPE(bio_page, fio->compressed_page); + inc_page_count(sbi, type); if (io->bio && (!io_is_mergeable(sbi, io->bio, io, fio, io->last_block_in_bio, @@ -1059,7 +1058,8 @@ alloc_new: if (F2FS_IO_ALIGNED(sbi) && (fio->type == DATA || fio->type == NODE) && fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) { - dec_page_count(sbi, WB_DATA_TYPE(bio_page)); + dec_page_count(sbi, WB_DATA_TYPE(bio_page, + fio->compressed_page)); fio->retry = 1; goto skip; } @@ -1080,10 +1080,6 @@ alloc_new: io->last_block_in_bio = fio->new_blkaddr; trace_f2fs_submit_page_write(fio->page, fio); -skip: - if (fio->in_list) - goto next; -out: #ifdef CONFIG_BLK_DEV_ZONED if (f2fs_sb_has_blkzoned(sbi) && btype < META && is_end_zone_blkaddr(sbi, fio->new_blkaddr)) { @@ -1096,6 +1092,10 @@ out: __submit_merged_bio(io); } #endif +skip: + if (fio->in_list) + goto next; +out: if (is_sbi_flag_set(sbi, SBI_IS_SHUTDOWN) || !f2fs_is_checkpoint_ready(sbi)) __submit_merged_bio(io); @@ -1179,18 +1179,12 @@ static int f2fs_submit_page_read(struct inode *inode, struct page *page, return 0; } -static void __set_data_blkaddr(struct dnode_of_data *dn) +static void __set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - struct f2fs_node *rn = F2FS_NODE(dn->node_page); - __le32 *addr_array; - int base = 0; - - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); + __le32 *addr = get_dnode_addr(dn->inode, dn->node_page); - /* Get physical address of data block */ - addr_array = blkaddr_in_node(rn); - addr_array[base + dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); + dn->data_blkaddr = blkaddr; + addr[dn->ofs_in_node] = cpu_to_le32(dn->data_blkaddr); } /* @@ -1199,18 +1193,17 @@ static void __set_data_blkaddr(struct dnode_of_data *dn) * ->node_page * update block addresses in the node page */ -void f2fs_set_data_blkaddr(struct dnode_of_data *dn) +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { f2fs_wait_on_page_writeback(dn->node_page, NODE, true, true); - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, blkaddr); if (set_page_dirty(dn->node_page)) dn->node_changed = true; } void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr) { - dn->data_blkaddr = blkaddr; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, blkaddr); f2fs_update_read_extent_cache(dn); } @@ -1225,7 +1218,8 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return -EPERM; - if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count)))) + err = inc_valid_block_count(sbi, dn->inode, &count, true); + if (unlikely(err)) return err; trace_f2fs_reserve_new_blocks(dn->inode, dn->nid, @@ -1237,8 +1231,7 @@ int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count) block_t blkaddr = f2fs_data_blkaddr(dn); if (blkaddr == NULL_ADDR) { - dn->data_blkaddr = NEW_ADDR; - __set_data_blkaddr(dn); + __set_data_blkaddr(dn, NEW_ADDR); count--; } } @@ -1483,7 +1476,7 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) dn->data_blkaddr = f2fs_data_blkaddr(dn); if (dn->data_blkaddr == NULL_ADDR) { - err = inc_valid_block_count(sbi, dn->inode, &count); + err = inc_valid_block_count(sbi, dn->inode, &count, true); if (unlikely(err)) return err; } @@ -1492,11 +1485,9 @@ static int __allocate_data_block(struct dnode_of_data *dn, int seg_type) old_blkaddr = dn->data_blkaddr; f2fs_allocate_data_block(sbi, NULL, old_blkaddr, &dn->data_blkaddr, &sum, seg_type, NULL); - if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { - invalidate_mapping_pages(META_MAPPING(sbi), - old_blkaddr, old_blkaddr); - f2fs_invalidate_compress_page(sbi, old_blkaddr); - } + if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) + f2fs_invalidate_internal_cache(sbi, old_blkaddr); + f2fs_update_data_blkaddr(dn, dn->data_blkaddr); return 0; } @@ -2811,8 +2802,6 @@ got_it: f2fs_outplace_write_data(&dn, fio); trace_f2fs_do_write_data_page(page, OPU); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); out_writepage: f2fs_put_dnode(&dn); out: @@ -2850,7 +2839,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, .encrypted_page = NULL, .submitted = 0, .compr_blocks = compr_blocks, - .need_lock = LOCK_RETRY, + .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY, .post_read = f2fs_post_read_required(inode) ? 1 : 0, .io_type = io_type, .io_wbc = wbc, @@ -2895,9 +2884,6 @@ int f2fs_write_single_data_page(struct page *page, int *submitted, zero_user_segment(page, offset, PAGE_SIZE); write: - if (f2fs_is_drop_cache(inode)) - goto out; - /* Dentry/quota blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode) || quota_inode) { /* @@ -2934,6 +2920,7 @@ write: if (err == -EAGAIN) { err = f2fs_do_write_data_page(&fio); if (err == -EAGAIN) { + f2fs_bug_on(sbi, compr_blocks); fio.need_lock = LOCK_REQ; err = f2fs_do_write_data_page(&fio); } diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 042593aed1..1b937f7d04 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -830,13 +830,14 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name, return err; } -int f2fs_do_tmpfile(struct inode *inode, struct inode *dir) +int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, + struct f2fs_filename *fname) { struct page *page; int err = 0; f2fs_down_write(&F2FS_I(inode)->i_sem); - page = f2fs_init_inode_metadata(inode, dir, NULL, NULL); + page = f2fs_init_inode_metadata(inode, dir, fname, NULL); if (IS_ERR(page)) { err = PTR_ERR(page); goto fail; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 9043cedfa1..3b6133c865 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -75,6 +75,11 @@ struct f2fs_fault_info { extern const char *f2fs_fault_name[FAULT_MAX]; #define IS_FAULT_SET(fi, type) ((fi)->inject_type & BIT(type)) + +/* maximum retry count for injected failure */ +#define DEFAULT_FAILURE_RETRY_COUNT 8 +#else +#define DEFAULT_FAILURE_RETRY_COUNT 1 #endif /* @@ -774,8 +779,6 @@ enum { FI_UPDATE_WRITE, /* inode has in-place-update data */ FI_NEED_IPU, /* used for ipu per file */ FI_ATOMIC_FILE, /* indicate atomic file */ - FI_FIRST_BLOCK_WRITTEN, /* indicate #0 data block was written */ - FI_DROP_CACHE, /* drop dirty page cache */ FI_DATA_EXIST, /* indicate data exists */ FI_INLINE_DOTS, /* indicate inline dot dentries */ FI_SKIP_WRITES, /* should skip data page writeback */ @@ -824,7 +827,7 @@ struct f2fs_inode_info { spinlock_t i_size_lock; /* protect last_disk_size */ #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; /* quota space reservation, managed internally by quota code */ qsize_t i_reserved_quota; @@ -1075,7 +1078,8 @@ struct f2fs_sm_info { * f2fs monitors the number of several block types such as on-writeback, * dirty dentry blocks, dirty node blocks, and dirty meta blocks. */ -#define WB_DATA_TYPE(p) (__is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) +#define WB_DATA_TYPE(p, f) \ + (f || f2fs_is_cp_guaranteed(p) ? F2FS_WB_CP_DATA : F2FS_WB_DATA) enum count_type { F2FS_DIRTY_DENTS, F2FS_DIRTY_DATA, @@ -2246,7 +2250,7 @@ static inline bool __allow_reserved_blocks(struct f2fs_sb_info *sbi, static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool); static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, - struct inode *inode, blkcnt_t *count) + struct inode *inode, blkcnt_t *count, bool partial) { blkcnt_t diff = 0, release = 0; block_t avail_user_block_count; @@ -2286,6 +2290,11 @@ static inline int inc_valid_block_count(struct f2fs_sb_info *sbi, avail_user_block_count = 0; } if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) { + if (!partial) { + spin_unlock(&sbi->stat_lock); + goto enospc; + } + diff = sbi->total_valid_block_count - avail_user_block_count; if (diff > *count) diff = *count; @@ -3016,6 +3025,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode, case FI_INLINE_DOTS: case FI_PIN_FILE: case FI_COMPRESS_RELEASED: + case FI_ATOMIC_COMMITTED: f2fs_mark_inode_dirty_sync(inode, true); } } @@ -3272,22 +3282,13 @@ static inline bool f2fs_is_cow_file(struct inode *inode) return is_inode_flag_set(inode, FI_COW_FILE); } -static inline bool f2fs_is_first_block_written(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_FIRST_BLOCK_WRITTEN); -} - -static inline bool f2fs_is_drop_cache(struct inode *inode) -{ - return is_inode_flag_set(inode, FI_DROP_CACHE); -} - +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page); static inline void *inline_data_addr(struct inode *inode, struct page *page) { - struct f2fs_inode *ri = F2FS_INODE(page); - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, page); - return (void *)&(ri->i_addr[extra_size + DEF_INLINE_RESERVED_SIZE]); + return (void *)(addr + DEF_INLINE_RESERVED_SIZE); } static inline int f2fs_has_inline_dentry(struct inode *inode) @@ -3432,6 +3433,17 @@ static inline int get_inline_xattr_addrs(struct inode *inode) return F2FS_I(inode)->i_inline_xattr_size; } +static inline __le32 *get_dnode_addr(struct inode *inode, + struct page *node_page) +{ + int base = 0; + + if (IS_INODE(node_page) && f2fs_has_extra_attr(inode)) + base = get_extra_isize(inode); + + return blkaddr_in_node(F2FS_NODE(node_page)) + base; +} + #define f2fs_get_inode_mode(i) \ ((is_inode_flag_set(i, FI_ACL_MODE)) ? \ (F2FS_I(i)->i_acl_mode) : ((i)->i_mode)) @@ -3457,11 +3469,9 @@ bool f2fs_is_valid_blkaddr(struct f2fs_sb_info *sbi, static inline void verify_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type) { - if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) { + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, type)) f2fs_err(sbi, "invalid blkaddr: %u, type: %d, run fsck to fix.", blkaddr, type); - f2fs_bug_on(sbi, 1); - } } static inline bool __is_valid_data_blkaddr(block_t blkaddr) @@ -3563,7 +3573,8 @@ int f2fs_do_add_link(struct inode *dir, const struct qstr *name, struct inode *inode, nid_t ino, umode_t mode); void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, struct inode *dir, struct inode *inode); -int f2fs_do_tmpfile(struct inode *inode, struct inode *dir); +int f2fs_do_tmpfile(struct inode *inode, struct inode *dir, + struct f2fs_filename *fname); bool f2fs_empty_dir(struct inode *dir); static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode) @@ -3797,6 +3808,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi); */ int __init f2fs_init_bioset(void); void f2fs_destroy_bioset(void); +bool f2fs_is_cp_guaranteed(struct page *page); int f2fs_init_bio_entry_cache(void); void f2fs_destroy_bio_entry_cache(void); void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio, @@ -3815,7 +3827,7 @@ void f2fs_submit_page_write(struct f2fs_io_info *fio); struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi, block_t blk_addr, sector_t *sector); int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr); -void f2fs_set_data_blkaddr(struct dnode_of_data *dn); +void f2fs_set_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr); int f2fs_reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count); int f2fs_reserve_new_block(struct dnode_of_data *dn); @@ -4280,7 +4292,8 @@ struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc); void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task); void f2fs_put_page_dic(struct page *page, bool in_task); -unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn); +unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, + unsigned int ofs_in_node); int f2fs_init_compress_ctx(struct compress_ctx *cc); void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse); void f2fs_init_compress_info(struct f2fs_sb_info *sbi); @@ -4337,7 +4350,8 @@ static inline void f2fs_put_page_dic(struct page *page, bool in_task) { WARN_ON_ONCE(1); } -static inline unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn) { return 0; } +static inline unsigned int f2fs_cluster_blocks_are_contiguous( + struct dnode_of_data *dn, unsigned int ofs_in_node) { return 0; } static inline bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { return false; } static inline int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { return 0; } static inline void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { } @@ -4394,15 +4408,24 @@ static inline bool f2fs_disable_compressed_file(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); - if (!f2fs_compressed_file(inode)) + f2fs_down_write(&F2FS_I(inode)->i_sem); + + if (!f2fs_compressed_file(inode)) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; - if (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode)) + } + if (f2fs_is_mmap_file(inode) || + (S_ISREG(inode->i_mode) && F2FS_HAS_BLOCKS(inode))) { + f2fs_up_write(&F2FS_I(inode)->i_sem); return false; + } fi->i_flags &= ~F2FS_COMPR_FL; stat_dec_compr_inode(inode); clear_inode_flag(inode, FI_COMPRESSED_FILE); f2fs_mark_inode_dirty_sync(inode, true); + + f2fs_up_write(&F2FS_I(inode)->i_sem); return true; } @@ -4606,6 +4629,39 @@ static inline bool f2fs_is_readonly(struct f2fs_sb_info *sbi) return f2fs_sb_has_readonly(sbi) || f2fs_readonly(sbi->sb); } +static inline void f2fs_truncate_meta_inode_pages(struct f2fs_sb_info *sbi, + block_t blkaddr, unsigned int cnt) +{ + bool need_submit = false; + int i = 0; + + do { + struct page *page; + + page = find_get_page(META_MAPPING(sbi), blkaddr + i); + if (page) { + if (PageWriteback(page)) + need_submit = true; + f2fs_put_page(page, 0); + } + } while (++i < cnt && !need_submit); + + if (need_submit) + f2fs_submit_merged_write_cond(sbi, sbi->meta_inode, + NULL, 0, DATA); + + truncate_inode_pages_range(META_MAPPING(sbi), + F2FS_BLK_TO_BYTES((loff_t)blkaddr), + F2FS_BLK_END_BYTES((loff_t)(blkaddr + cnt - 1))); +} + +static inline void f2fs_invalidate_internal_cache(struct f2fs_sb_info *sbi, + block_t blkaddr) +{ + f2fs_truncate_meta_inode_pages(sbi, blkaddr, 1); + f2fs_invalidate_compress_page(sbi, blkaddr); +} + #define EFSBADCRC EBADMSG /* Bad CRC detected */ #define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index a05781e708..caeae900f7 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -557,20 +557,14 @@ static int f2fs_file_open(struct inode *inode, struct file *filp) void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; - int base = 0; bool compressed_cluster = false; int cluster_index = 0, valid_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; bool released = !atomic_read(&F2FS_I(dn->inode)->i_compr_blocks); - if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) - base = get_extra_isize(dn->inode); - - raw_node = F2FS_NODE(dn->node_page); - addr = blkaddr_in_node(raw_node) + base + ofs; + addr = get_dnode_addr(dn->inode, dn->node_page) + ofs; /* Assumption: truncation starts with cluster */ for (; count > 0; count--, addr++, dn->ofs_in_node++, cluster_index++) { @@ -588,8 +582,7 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) if (blkaddr == NULL_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); if (__is_valid_data_blkaddr(blkaddr)) { if (!f2fs_is_valid_blkaddr(sbi, blkaddr, @@ -599,9 +592,6 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count) valid_blocks++; } - if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) - clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); - f2fs_invalidate_blocks(sbi, blkaddr); if (!released || blkaddr != COMPRESS_ADDR) @@ -1488,8 +1478,7 @@ static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, } f2fs_invalidate_blocks(sbi, dn->data_blkaddr); - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NEW_ADDR); } f2fs_update_read_extent_cache_range(dn, start, 0, index - start); @@ -3469,8 +3458,7 @@ static int release_compress_blocks(struct dnode_of_data *dn, pgoff_t count) if (blkaddr != NEW_ADDR) continue; - dn->data_blkaddr = NULL_ADDR; - f2fs_set_data_blkaddr(dn); + f2fs_set_data_blkaddr(dn, NULL_ADDR); } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, false); @@ -3595,10 +3583,10 @@ out: return ret; } -static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) +static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count, + unsigned int *reserved_blocks) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); - unsigned int reserved_blocks = 0; int cluster_size = F2FS_I(dn->inode)->i_cluster_size; block_t blkaddr; int i; @@ -3621,41 +3609,53 @@ static int reserve_compress_blocks(struct dnode_of_data *dn, pgoff_t count) blkcnt_t reserved; int ret; - for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { - blkaddr = f2fs_data_blkaddr(dn); + for (i = 0; i < cluster_size; i++) { + blkaddr = data_blkaddr(dn->inode, dn->node_page, + dn->ofs_in_node + i); if (i == 0) { - if (blkaddr == COMPRESS_ADDR) - continue; - dn->ofs_in_node += cluster_size; - goto next; + if (blkaddr != COMPRESS_ADDR) { + dn->ofs_in_node += cluster_size; + goto next; + } + continue; } - if (__is_valid_data_blkaddr(blkaddr)) { + /* + * compressed cluster was not released due to it + * fails in release_compress_blocks(), so NEW_ADDR + * is a possible case. + */ + if (blkaddr == NEW_ADDR || + __is_valid_data_blkaddr(blkaddr)) { compr_blocks++; continue; } - - dn->data_blkaddr = NEW_ADDR; - f2fs_set_data_blkaddr(dn); } reserved = cluster_size - compr_blocks; - ret = inc_valid_block_count(sbi, dn->inode, &reserved); - if (ret) + + /* for the case all blocks in cluster were reserved */ + if (reserved == 1) + goto next; + + ret = inc_valid_block_count(sbi, dn->inode, &reserved, false); + if (unlikely(ret)) return ret; - if (reserved != cluster_size - compr_blocks) - return -ENOSPC; + for (i = 0; i < cluster_size; i++, dn->ofs_in_node++) { + if (f2fs_data_blkaddr(dn) == NULL_ADDR) + f2fs_set_data_blkaddr(dn, NEW_ADDR); + } f2fs_i_compr_blocks_update(dn->inode, compr_blocks, true); - reserved_blocks += reserved; + *reserved_blocks += reserved; next: count -= cluster_size; } - return reserved_blocks; + return 0; } static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) @@ -3679,9 +3679,6 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) if (ret) return ret; - if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) - goto out; - f2fs_balance_fs(sbi, true); inode_lock(inode); @@ -3691,6 +3688,9 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) goto unlock_inode; } + if (atomic_read(&F2FS_I(inode)->i_compr_blocks)) + goto unlock_inode; + f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); filemap_invalidate_lock(inode->i_mapping); @@ -3716,7 +3716,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) count = min(end_offset - dn.ofs_in_node, last_idx - page_idx); count = round_up(count, F2FS_I(inode)->i_cluster_size); - ret = reserve_compress_blocks(&dn, count); + ret = reserve_compress_blocks(&dn, count, &reserved_blocks); f2fs_put_dnode(&dn); @@ -3724,23 +3724,21 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg) break; page_idx += count; - reserved_blocks += ret; } filemap_invalidate_unlock(inode->i_mapping); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); - if (ret >= 0) { + if (!ret) { clear_inode_flag(inode, FI_COMPRESS_RELEASED); inode_set_ctime_current(inode); f2fs_mark_inode_dirty_sync(inode, true); } unlock_inode: inode_unlock(inode); -out: mnt_drop_write_file(filp); - if (ret >= 0) { + if (!ret) { ret = put_user(reserved_blocks, (u64 __user *)arg); } else if (reserved_blocks && atomic_read(&F2FS_I(inode)->i_compr_blocks)) { @@ -3989,16 +3987,20 @@ static int f2fs_ioc_set_compress_option(struct file *filp, unsigned long arg) sizeof(option))) return -EFAULT; - if (!f2fs_compressed_file(inode) || - option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || - option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || - option.algorithm >= COMPRESS_MAX) + if (option.log_cluster_size < MIN_COMPRESS_LOG_SIZE || + option.log_cluster_size > MAX_COMPRESS_LOG_SIZE || + option.algorithm >= COMPRESS_MAX) return -EINVAL; file_start_write(filp); inode_lock(inode); f2fs_down_write(&F2FS_I(inode)->i_sem); + if (!f2fs_compressed_file(inode)) { + ret = -EINVAL; + goto out; + } + if (f2fs_is_mmap_file(inode) || get_dirty_pages(inode)) { ret = -EBUSY; goto out; diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index f550cdeaa6..405a6077bd 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1380,9 +1380,8 @@ static int move_data_block(struct inode *inode, block_t bidx, memcpy(page_address(fio.encrypted_page), page_address(mpage), PAGE_SIZE); f2fs_put_page(mpage, 1); - invalidate_mapping_pages(META_MAPPING(fio.sbi), - fio.old_blkaddr, fio.old_blkaddr); - f2fs_invalidate_compress_page(fio.sbi, fio.old_blkaddr); + + f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr); set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) @@ -1405,8 +1404,6 @@ static int move_data_block(struct inode *inode, block_t bidx, f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); - if (page->index == 0) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); put_page_out: f2fs_put_page(fio.encrypted_page, 1); recover_block: diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 560bfcad1a..b31410c4af 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -61,49 +61,31 @@ void f2fs_set_inode_flags(struct inode *inode) S_ENCRYPTED|S_VERITY|S_CASEFOLD); } -static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri) +static void __get_inode_rdev(struct inode *inode, struct page *node_page) { - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { - if (ri->i_addr[extra_size]) - inode->i_rdev = old_decode_dev( - le32_to_cpu(ri->i_addr[extra_size])); + if (addr[0]) + inode->i_rdev = old_decode_dev(le32_to_cpu(addr[0])); else - inode->i_rdev = new_decode_dev( - le32_to_cpu(ri->i_addr[extra_size + 1])); + inode->i_rdev = new_decode_dev(le32_to_cpu(addr[1])); } } -static int __written_first_block(struct f2fs_sb_info *sbi, - struct f2fs_inode *ri) +static void __set_inode_rdev(struct inode *inode, struct page *node_page) { - block_t addr = le32_to_cpu(ri->i_addr[offset_in_addr(ri)]); - - if (!__is_valid_data_blkaddr(addr)) - return 1; - if (!f2fs_is_valid_blkaddr(sbi, addr, DATA_GENERIC_ENHANCE)) { - f2fs_handle_error(sbi, ERROR_INVALID_BLKADDR); - return -EFSCORRUPTED; - } - return 0; -} - -static void __set_inode_rdev(struct inode *inode, struct f2fs_inode *ri) -{ - int extra_size = get_extra_isize(inode); + __le32 *addr = get_dnode_addr(inode, node_page); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { - ri->i_addr[extra_size] = - cpu_to_le32(old_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 1] = 0; + addr[0] = cpu_to_le32(old_encode_dev(inode->i_rdev)); + addr[1] = 0; } else { - ri->i_addr[extra_size] = 0; - ri->i_addr[extra_size + 1] = - cpu_to_le32(new_encode_dev(inode->i_rdev)); - ri->i_addr[extra_size + 2] = 0; + addr[0] = 0; + addr[1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); + addr[2] = 0; } } } @@ -398,7 +380,6 @@ static int do_read_inode(struct inode *inode) struct page *node_page; struct f2fs_inode *ri; projid_t i_projid; - int err; /* Check if ino is within scope */ if (f2fs_check_nid_range(sbi, inode->i_ino)) @@ -478,17 +459,7 @@ static int do_read_inode(struct inode *inode) } /* get rdev by using inline_info */ - __get_inode_rdev(inode, ri); - - if (S_ISREG(inode->i_mode)) { - err = __written_first_block(sbi, ri); - if (err < 0) { - f2fs_put_page(node_page, 1); - return err; - } - if (!err) - set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN); - } + __get_inode_rdev(inode, node_page); if (!f2fs_need_inode_block_update(sbi, inode->i_ino)) fi->last_disk_size = inode->i_size; @@ -761,7 +732,7 @@ void f2fs_update_inode(struct inode *inode, struct page *node_page) } } - __set_inode_rdev(inode, ri); + __set_inode_rdev(inode, node_page); /* deleted inode */ if (inode->i_nlink == 0) diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 7f71bae2c8..9cdf3f36d1 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -853,7 +853,7 @@ out: static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode, bool is_whiteout, - struct inode **new_inode) + struct inode **new_inode, struct f2fs_filename *fname) { struct f2fs_sb_info *sbi = F2FS_I_SB(dir); struct inode *inode; @@ -881,7 +881,7 @@ static int __f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, if (err) goto out; - err = f2fs_do_tmpfile(inode, dir); + err = f2fs_do_tmpfile(inode, dir, fname); if (err) goto release_out; @@ -932,22 +932,24 @@ static int f2fs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, if (!f2fs_is_checkpoint_ready(sbi)) return -ENOSPC; - err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL); + err = __f2fs_tmpfile(idmap, dir, file, mode, false, NULL, NULL); return finish_open_simple(file, err); } static int f2fs_create_whiteout(struct mnt_idmap *idmap, - struct inode *dir, struct inode **whiteout) + struct inode *dir, struct inode **whiteout, + struct f2fs_filename *fname) { - return __f2fs_tmpfile(idmap, dir, NULL, - S_IFCHR | WHITEOUT_MODE, true, whiteout); + return __f2fs_tmpfile(idmap, dir, NULL, S_IFCHR | WHITEOUT_MODE, + true, whiteout, fname); } int f2fs_get_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct inode **new_inode) { - return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, false, new_inode); + return __f2fs_tmpfile(idmap, dir, NULL, S_IFREG, + false, new_inode, NULL); } static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, @@ -990,7 +992,14 @@ static int f2fs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } if (flags & RENAME_WHITEOUT) { - err = f2fs_create_whiteout(idmap, old_dir, &whiteout); + struct f2fs_filename fname; + + err = f2fs_setup_filename(old_dir, &old_dentry->d_name, + 0, &fname); + if (err) + return err; + + err = f2fs_create_whiteout(idmap, old_dir, &whiteout, &fname); if (err) return err; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9b546fd210..2ea9c99e7d 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -852,21 +852,29 @@ int f2fs_get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) if (is_inode_flag_set(dn->inode, FI_COMPRESSED_FILE) && f2fs_sb_has_readonly(sbi)) { - unsigned int c_len = f2fs_cluster_blocks_are_contiguous(dn); + unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size; + unsigned int ofs_in_node = dn->ofs_in_node; + pgoff_t fofs = index; + unsigned int c_len; block_t blkaddr; + /* should align fofs and ofs_in_node to cluster_size */ + if (fofs % cluster_size) { + fofs = round_down(fofs, cluster_size); + ofs_in_node = round_down(ofs_in_node, cluster_size); + } + + c_len = f2fs_cluster_blocks_are_contiguous(dn, ofs_in_node); if (!c_len) goto out; - blkaddr = f2fs_data_blkaddr(dn); + blkaddr = data_blkaddr(dn->inode, dn->node_page, ofs_in_node); if (blkaddr == COMPRESS_ADDR) blkaddr = data_blkaddr(dn->inode, dn->node_page, - dn->ofs_in_node + 1); + ofs_in_node + 1); f2fs_update_read_extent_tree_range_compressed(dn->inode, - index, blkaddr, - F2FS_I(dn->inode)->i_cluster_size, - c_len); + fofs, blkaddr, cluster_size, c_len); } out: return 0; diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index d0f24ccbd1..aad1d1a9b3 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -611,6 +611,19 @@ truncate_out: return 0; } +static int f2fs_reserve_new_block_retry(struct dnode_of_data *dn) +{ + int i, err = 0; + + for (i = DEFAULT_FAILURE_RETRY_COUNT; i > 0; i--) { + err = f2fs_reserve_new_block(dn); + if (!err) + break; + } + + return err; +} + static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode, struct page *page) { @@ -712,14 +725,8 @@ retry_dn: */ if (dest == NEW_ADDR) { f2fs_truncate_data_blocks_range(&dn, 1); - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; continue; @@ -727,16 +734,8 @@ retry_dn: /* dest is valid block, try to recover from src to dest */ if (f2fs_is_valid_blkaddr(sbi, dest, META_POR)) { - if (src == NULL_ADDR) { - do { - err = f2fs_reserve_new_block(&dn); - if (err == -ENOSPC) { - f2fs_bug_on(sbi, 1); - break; - } - } while (err && - IS_ENABLED(CONFIG_F2FS_FAULT_INJECTION)); + err = f2fs_reserve_new_block_retry(&dn); if (err) goto err; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 727d016318..7a0143825e 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -192,6 +192,9 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) if (!f2fs_is_atomic_file(inode)) return; + if (clean) + truncate_inode_pages_final(inode->i_mapping); + release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); clear_inode_flag(inode, FI_ATOMIC_REPLACE); @@ -201,7 +204,6 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) F2FS_I(inode)->atomic_write_task = NULL; if (clean) { - truncate_inode_pages_final(inode->i_mapping); f2fs_i_size_write(inode, fi->original_i_size); fi->original_i_size = 0; } @@ -248,7 +250,7 @@ retry: } else { blkcnt_t count = 1; - err = inc_valid_block_count(sbi, inode, &count); + err = inc_valid_block_count(sbi, inode, &count, true); if (err) { f2fs_put_dnode(&dn); return err; @@ -2495,8 +2497,7 @@ void f2fs_invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr) if (addr == NEW_ADDR || addr == COMPRESS_ADDR) return; - invalidate_mapping_pages(META_MAPPING(sbi), addr, addr); - f2fs_invalidate_compress_page(sbi, addr); + f2fs_invalidate_internal_cache(sbi, addr); /* add it into sit main buffer */ down_write(&sit_i->sentry_lock); @@ -3490,12 +3491,12 @@ void f2fs_allocate_data_block(struct f2fs_sb_info *sbi, struct page *page, locate_dirty_segment(sbi, GET_SEGNO(sbi, old_blkaddr)); locate_dirty_segment(sbi, GET_SEGNO(sbi, *new_blkaddr)); - if (IS_DATASEG(type)) + if (IS_DATASEG(curseg->seg_type)) atomic64_inc(&sbi->allocated_data_blocks); up_write(&sit_i->sentry_lock); - if (page && IS_NODESEG(type)) { + if (page && IS_NODESEG(curseg->seg_type)) { fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg)); f2fs_inode_chksum_set(sbi, page); @@ -3557,11 +3558,8 @@ static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio) reallocate: f2fs_allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr, &fio->new_blkaddr, sum, type, fio); - if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) { - invalidate_mapping_pages(META_MAPPING(fio->sbi), - fio->old_blkaddr, fio->old_blkaddr); - f2fs_invalidate_compress_page(fio->sbi, fio->old_blkaddr); - } + if (GET_SEGNO(fio->sbi, fio->old_blkaddr) != NULL_SEGNO) + f2fs_invalidate_internal_cache(fio->sbi, fio->old_blkaddr); /* writeout dirty page into bdev */ f2fs_submit_page_write(fio); @@ -3655,8 +3653,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio) } if (fio->post_read) - invalidate_mapping_pages(META_MAPPING(sbi), - fio->new_blkaddr, fio->new_blkaddr); + f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1); stat_inc_inplace_blocks(fio->sbi); @@ -3757,9 +3754,7 @@ void f2fs_do_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, update_sit_entry(sbi, new_blkaddr, 1); } if (GET_SEGNO(sbi, old_blkaddr) != NULL_SEGNO) { - invalidate_mapping_pages(META_MAPPING(sbi), - old_blkaddr, old_blkaddr); - f2fs_invalidate_compress_page(sbi, old_blkaddr); + f2fs_invalidate_internal_cache(sbi, old_blkaddr); if (!from_gc) update_segment_mtime(sbi, old_blkaddr, 0); update_sit_entry(sbi, old_blkaddr, -1); @@ -3848,7 +3843,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr, for (i = 0; i < len; i++) f2fs_wait_on_block_writeback(inode, blkaddr + i); - invalidate_mapping_pages(META_MAPPING(sbi), blkaddr, blkaddr + len - 1); + f2fs_truncate_meta_inode_pages(sbi, blkaddr, len); } static int read_compacted_summaries(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 8129be788b..c77a562831 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -573,23 +573,22 @@ static inline bool has_curseg_enough_space(struct f2fs_sb_info *sbi, unsigned int node_blocks, unsigned int dent_blocks) { - unsigned int segno, left_blocks; + unsigned segno, left_blocks; int i; - /* check current node segment */ + /* check current node sections in the worst case. */ for (i = CURSEG_HOT_NODE; i <= CURSEG_COLD_NODE; i++) { segno = CURSEG_I(sbi, i)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; - + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (node_blocks > left_blocks) return false; } - /* check current data segment */ + /* check current data section for dentry blocks. */ segno = CURSEG_I(sbi, CURSEG_HOT_DATA)->segno; - left_blocks = f2fs_usable_blks_in_seg(sbi, segno) - - get_seg_entry(sbi, segno)->ckpt_valid_blocks; + left_blocks = CAP_BLKS_PER_SEC(sbi) - + get_ckpt_valid_blocks(sbi, segno, true); if (dent_blocks > left_blocks) return false; return true; @@ -638,7 +637,7 @@ static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi, if (free_secs > upper_secs) return false; - else if (free_secs <= lower_secs) + if (free_secs <= lower_secs) return true; return !curseg_space; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 5dfbc6b4c0..4151293fc4 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -663,7 +663,7 @@ static int f2fs_set_lz4hc_level(struct f2fs_sb_info *sbi, const char *str) #ifdef CONFIG_F2FS_FS_ZSTD static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) { - unsigned int level; + int level; int len = 4; if (strlen(str) == len) { @@ -677,9 +677,15 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) f2fs_info(sbi, "wrong format, e.g. :"); return -EINVAL; } - if (kstrtouint(str + 1, 10, &level)) + if (kstrtoint(str + 1, 10, &level)) return -EINVAL; + /* f2fs does not support negative compress level now */ + if (level < 0) { + f2fs_info(sbi, "do not support negative compress level: %d", level); + return -ERANGE; + } + if (!f2fs_is_compress_level_valid(COMPRESS_ZSTD, level)) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; @@ -2776,7 +2782,7 @@ int f2fs_dquot_initialize(struct inode *inode) return dquot_initialize(inode); } -static struct dquot **f2fs_get_dquots(struct inode *inode) +static struct dquot __rcu **f2fs_get_dquots(struct inode *inode) { return F2FS_I(inode)->i_dquot; } @@ -3938,11 +3944,6 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi) return 0; zone_sectors = bdev_zone_sectors(bdev); - if (!is_power_of_2(zone_sectors)) { - f2fs_err(sbi, "F2FS does not support non power of 2 zone sizes\n"); - return -EINVAL; - } - if (sbi->blocks_per_blkz && sbi->blocks_per_blkz != SECTOR_TO_BLOCK(zone_sectors)) return -EINVAL; diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index c52e63e10d..509eea96a4 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; diff --git a/fs/fcntl.c b/fs/fcntl.c index c80a6acad7..3ff707bf27 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -268,7 +268,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg) } #endif -static bool rw_hint_valid(enum rw_hint hint) +static bool rw_hint_valid(u64 hint) { switch (hint) { case RWH_WRITE_LIFE_NOT_SET: @@ -288,19 +288,17 @@ static long fcntl_rw_hint(struct file *file, unsigned int cmd, { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; - enum rw_hint hint; - u64 h; + u64 hint; switch (cmd) { case F_GET_RW_HINT: - h = inode->i_write_hint; - if (copy_to_user(argp, &h, sizeof(*argp))) + hint = inode->i_write_hint; + if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; case F_SET_RW_HINT: - if (copy_from_user(&h, argp, sizeof(h))) + if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; - hint = (enum rw_hint) h; if (!rw_hint_valid(hint)) return -EINVAL; diff --git a/fs/fhandle.c b/fs/fhandle.c index 18b3ba8dc8..57a12614ad 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -36,7 +36,7 @@ static long do_sys_name_to_handle(const struct path *path, if (f_handle.handle_bytes > MAX_HANDLE_SZ) return -EINVAL; - handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes, + handle = kzalloc(sizeof(struct file_handle) + f_handle.handle_bytes, GFP_KERNEL); if (!handle) return -ENOMEM; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index d19cbf34c6..9307bb4393 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -391,6 +391,10 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name err = -EIO; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; + if (outarg->nodeid == FUSE_ROOT_ID && outarg->generation != 0) { + pr_warn_once("root generation should be zero\n"); + outarg->generation = 0; + } *inode = fuse_iget(sb, outarg->nodeid, outarg->generation, &outarg->attr, ATTR_TIMEOUT(outarg), @@ -1210,7 +1214,7 @@ static int fuse_do_statx(struct inode *inode, struct file *file, if (((sx->mask & STATX_SIZE) && !fuse_valid_size(sx->size)) || ((sx->mask & STATX_TYPE) && (!fuse_valid_type(sx->mode) || inode_wrong_type(inode, sx->mode)))) { - make_bad_inode(inode); + fuse_make_bad(inode); return -EIO; } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a660f1f215..cc9651a013 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2467,7 +2467,8 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) return fuse_dax_mmap(file, vma); if (ff->open_flags & FOPEN_DIRECT_IO) { - /* Can't provide the coherency needed for MAP_SHARED + /* + * Can't provide the coherency needed for MAP_SHARED * if FUSE_DIRECT_IO_ALLOW_MMAP isn't set. */ if ((vma->vm_flags & VM_MAYSHARE) && !fc->direct_io_allow_mmap) @@ -2475,7 +2476,10 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma) invalidate_inode_pages2(file->f_mapping); - return generic_file_mmap(file, vma); + if (!(vma->vm_flags & VM_MAYSHARE)) { + /* MAP_PRIVATE */ + return generic_file_mmap(file, vma); + } } if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE)) diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 1df83eebda..b5c241e169 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -939,7 +939,6 @@ static inline bool fuse_stale_inode(const struct inode *inode, int generation, static inline void fuse_make_bad(struct inode *inode) { - remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 2a6d44f917..b676c72c62 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -469,8 +469,11 @@ retry: } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ fuse_make_bad(inode); - iput(inode); - goto retry; + if (inode != d_inode(sb->s_root)) { + remove_inode_hash(inode); + iput(inode); + goto retry; + } } fi = get_fuse_inode(inode); spin_lock(&fi->lock); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index f72df2babe..fc5c647123 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1843,16 +1843,10 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, if (unlikely(error)) { /* * Let the filesystem know what portion of the current page - * failed to map. If the page hasn't been added to ioend, it - * won't be affected by I/O completion and we must unlock it - * now. + * failed to map. */ if (wpc->ops->discard_folio) wpc->ops->discard_folio(folio, pos); - if (!count) { - folio_unlock(folio); - goto done; - } } /* @@ -1861,6 +1855,16 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * all the dirty bits in the folio here. */ iomap_clear_range_dirty(folio, 0, folio_size(folio)); + + /* + * If the page hasn't been added to the ioend, it won't be affected by + * I/O completion and we must unlock it now. + */ + if (error && !count) { + folio_unlock(folio); + goto done; + } + folio_start_writeback(folio); folio_unlock(folio); diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h index dd4264aa9b..10934f9a11 100644 --- a/fs/jfs/jfs_incore.h +++ b/fs/jfs/jfs_incore.h @@ -92,7 +92,7 @@ struct jfs_inode_info { } link; } u; #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif u32 dev; /* will die when we get wide dev_t */ struct inode vfs_inode; diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 8d8e556bd6..ff135a43b5 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -824,7 +824,7 @@ out: return len - towrite; } -static struct dquot **jfs_get_dquots(struct inode *inode) +static struct dquot __rcu **jfs_get_dquots(struct inode *inode) { return JFS_IP(inode)->i_dquot; } diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 5918c67dae..b6f801e73b 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -668,10 +668,17 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq) LIST_HEAD(mds_list); nfs_init_cinfo_from_dreq(&cinfo, dreq); + nfs_commit_begin(cinfo.mds); nfs_scan_commit(dreq->inode, &mds_list, &cinfo); res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo); - if (res < 0) /* res == -ENOMEM */ - nfs_direct_write_reschedule(dreq); + if (res < 0) { /* res == -ENOMEM */ + spin_lock(&dreq->lock); + if (dreq->flags == 0) + dreq->flags = NFS_ODIRECT_RESCHED_WRITES; + spin_unlock(&dreq->lock); + } + if (nfs_commit_end(cinfo.mds)) + nfs_direct_write_complete(dreq); } static void nfs_direct_write_clear_reqs(struct nfs_direct_req *dreq) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index ef817a0475..3e724cb7ef 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2016,7 +2016,7 @@ static void ff_layout_cancel_io(struct pnfs_layout_segment *lseg) for (idx = 0; idx < flseg->mirror_array_cnt; idx++) { mirror = flseg->mirror_array[idx]; mirror_ds = mirror->mirror_ds; - if (!mirror_ds) + if (IS_ERR_OR_NULL(mirror_ds)) continue; ds = mirror->mirror_ds->ds; if (!ds) diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index b05717fe0d..60a3c28784 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -307,11 +307,11 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) struct inode *inode = sreq->rreq->inode; struct nfs_open_context *ctx = sreq->rreq->netfs_priv; struct page *page; + unsigned long idx; int err; pgoff_t start = (sreq->start + sreq->transferred) >> PAGE_SHIFT; pgoff_t last = ((sreq->start + sreq->len - sreq->transferred - 1) >> PAGE_SHIFT); - XA_STATE(xas, &sreq->rreq->mapping->i_pages, start); nfs_pageio_init_read(&pgio, inode, false, &nfs_async_read_completion_ops); @@ -322,19 +322,14 @@ static void nfs_netfs_issue_read(struct netfs_io_subrequest *sreq) pgio.pg_netfs = netfs; /* used in completion */ - xas_lock(&xas); - xas_for_each(&xas, page, last) { + xa_for_each_range(&sreq->rreq->mapping->i_pages, idx, page, start, last) { /* nfs_read_add_folio() may schedule() due to pNFS layout and other RPCs */ - xas_pause(&xas); - xas_unlock(&xas); err = nfs_read_add_folio(&pgio, ctx, page_folio(page)); if (err < 0) { netfs->error = err; goto out; } - xas_lock(&xas); } - xas_unlock(&xas); out: nfs_pageio_complete_read(&pgio); nfs_netfs_put(netfs); diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h index b59876b01a..0282d93c8b 100644 --- a/fs/nfs/nfs42.h +++ b/fs/nfs/nfs42.h @@ -55,11 +55,14 @@ int nfs42_proc_removexattr(struct inode *inode, const char *name); * They would be 7 bytes long in the eventual buffer ("user.x\0"), and * 8 bytes long XDR-encoded. * - * Include the trailing eof word as well. + * Include the trailing eof word as well and make the result a multiple + * of 4 bytes. */ static inline u32 nfs42_listxattr_xdrsize(u32 buflen) { - return ((buflen / (XATTR_USER_PREFIX_LEN + 2)) * 8) + 4; + u32 size = 8 * buflen / (XATTR_USER_PREFIX_LEN + 2) + 4; + + return (size + 3) & ~3; } #endif /* CONFIG_NFS_V4_2 */ #endif /* __LINUX_FS_NFS_NFS4_2_H */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 23819a7565..b2ff8c7a21 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -10615,29 +10615,33 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { static ssize_t nfs4_listxattr(struct dentry *dentry, char *list, size_t size) { ssize_t error, error2, error3; + size_t left = size; - error = generic_listxattr(dentry, list, size); + error = generic_listxattr(dentry, list, left); if (error < 0) return error; if (list) { list += error; - size -= error; + left -= error; } - error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, size); + error2 = nfs4_listxattr_nfs4_label(d_inode(dentry), list, left); if (error2 < 0) return error2; if (list) { list += error2; - size -= error2; + left -= error2; } - error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, size); + error3 = nfs4_listxattr_nfs4_user(d_inode(dentry), list, left); if (error3 < 0) return error3; - return error + error2 + error3; + error += error2 + error3; + if (size && error > size) + return -ERANGE; + return error; } static void nfs4_enable_swap(struct inode *inode) diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index 7600100ba2..432612d224 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -175,10 +175,10 @@ static int __init root_nfs_cat(char *dest, const char *src, size_t len = strlen(dest); if (len && dest[len - 1] != ',') - if (strlcat(dest, ",", destlen) > destlen) + if (strlcat(dest, ",", destlen) >= destlen) return -1; - if (strlcat(dest, src, destlen) > destlen) + if (strlcat(dest, src, destlen) >= destlen) return -1; return 0; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index afd23910f3..88e061bd71 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -919,6 +919,8 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr); list_for_each_entry(da, &ds->ds_addrs, da_node) { + char servername[48]; + dprintk("%s: DS %s: trying address %s\n", __func__, ds->ds_remotestr, da->da_remotestr); @@ -929,6 +931,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .dstaddr = (struct sockaddr *)&da->da_addr, .addrlen = da->da_addrlen, .servername = clp->cl_hostname, + .xprtsec = clp->cl_xprtsec, }; struct nfs4_add_xprt_data xprtdata = { .clp = clp, @@ -938,10 +941,45 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, .data = &xprtdata, }; - if (da->da_transport != clp->cl_proto) + if (da->da_transport != clp->cl_proto && + clp->cl_proto != XPRT_TRANSPORT_TCP_TLS) continue; + if (da->da_transport == XPRT_TRANSPORT_TCP && + mds_srv->nfs_client->cl_proto == + XPRT_TRANSPORT_TCP_TLS) { + struct sockaddr *addr = + (struct sockaddr *)&da->da_addr; + struct sockaddr_in *sin = + (struct sockaddr_in *)&da->da_addr; + struct sockaddr_in6 *sin6 = + (struct sockaddr_in6 *)&da->da_addr; + + /* for NFS with TLS we need to supply a correct + * servername of the trunked transport, not the + * servername of the main transport stored in + * clp->cl_hostname. And set the protocol to + * indicate to use TLS + */ + servername[0] = '\0'; + switch(addr->sa_family) { + case AF_INET: + snprintf(servername, sizeof(servername), + "%pI4", &sin->sin_addr.s_addr); + break; + case AF_INET6: + snprintf(servername, sizeof(servername), + "%pI6", &sin6->sin6_addr); + break; + default: + /* do not consider this address */ + continue; + } + xprt_args.ident = XPRT_TRANSPORT_TCP_TLS; + xprt_args.servername = servername; + } if (da->da_addr.ss_family != clp->cl_addr.ss_family) continue; + /** * Test this address for session trunking and * add as an alias @@ -953,6 +991,10 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, if (xprtdata.cred) put_cred(xprtdata.cred); } else { + if (da->da_transport == XPRT_TRANSPORT_TCP && + mds_srv->nfs_client->cl_proto == + XPRT_TRANSPORT_TCP_TLS) + da->da_transport = XPRT_TRANSPORT_TCP_TLS; clp = nfs4_set_ds_client(mds_srv, &da->da_addr, da->da_addrlen, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 7dc21a48e3..a142287d86 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -305,6 +305,8 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio, new = nfs_page_create_from_folio(ctx, folio, 0, aligned_len); if (IS_ERR(new)) { error = PTR_ERR(new); + if (nfs_netfs_folio_unlock(folio)) + folio_unlock(folio); goto out; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9e345d3c30..5c2ff4a31a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1663,7 +1663,7 @@ static int wait_on_commit(struct nfs_mds_commit_info *cinfo) !atomic_read(&cinfo->rpcs_out)); } -static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) +void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) { atomic_inc(&cinfo->rpcs_out); } diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index fbc0ccb404..4c7a296c41 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -843,7 +843,7 @@ DECLARE_EVENT_CLASS(nfsd_clid_class, __array(unsigned char, addr, sizeof(struct sockaddr_in6)) __field(unsigned long, flavor) __array(unsigned char, verifier, NFS4_VERIFIER_SIZE) - __string_len(name, name, clp->cl_name.len) + __string_len(name, clp->cl_name.data, clp->cl_name.len) ), TP_fast_assign( __entry->cl_boot = clp->cl_clientid.cl_boot; diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 13592e82ea..65659fa037 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -724,7 +724,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, dat = nilfs_bmap_get_dat(btree); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr = blocknr; } cnt = 1; @@ -743,7 +743,7 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - goto out; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt || ++cnt == maxblocks) @@ -781,6 +781,11 @@ static int nilfs_btree_lookup_contig(const struct nilfs_bmap *btree, out: nilfs_btree_free_path(path); return ret; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + goto out; } static void nilfs_btree_promote_key(struct nilfs_bmap *btree, diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 4c85914f2a..893ab36824 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -66,7 +66,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, dat = nilfs_bmap_get_dat(direct); ret = nilfs_dat_translate(dat, ptr, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr = blocknr; } @@ -79,7 +79,7 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, if (dat) { ret = nilfs_dat_translate(dat, ptr2, &blocknr); if (ret < 0) - return ret; + goto dat_error; ptr2 = blocknr; } if (ptr2 != ptr + cnt) @@ -87,6 +87,11 @@ static int nilfs_direct_lookup_contig(const struct nilfs_bmap *direct, } *ptrp = ptr; return cnt; + + dat_error: + if (ret == -ENOENT) + ret = -EINVAL; /* Notify bmap layer of metadata corruption */ + return ret; } static __u64 diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index f861f3a0bf..da97149f83 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -112,7 +112,7 @@ int nilfs_get_block(struct inode *inode, sector_t blkoff, "%s (ino=%lu): a race condition while inserting a data block at offset=%llu", __func__, inode->i_ino, (unsigned long long)blkoff); - err = 0; + err = -EAGAIN; } nilfs_transaction_abort(inode->i_sb); goto out; diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h index 82b28fdacc..accf03d476 100644 --- a/fs/ocfs2/inode.h +++ b/fs/ocfs2/inode.h @@ -65,7 +65,7 @@ struct ocfs2_inode_info tid_t i_sync_tid; tid_t i_datasync_tid; - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; }; /* diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 6b90642490..1259fe02cd 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -122,7 +122,7 @@ static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend); static int ocfs2_enable_quotas(struct ocfs2_super *osb); static void ocfs2_disable_quotas(struct ocfs2_super *osb); -static struct dquot **ocfs2_get_dquots(struct inode *inode) +static struct dquot __rcu **ocfs2_get_dquots(struct inode *inode) { return OCFS2_I(inode)->i_dquot; } diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 3fe2dde159..488f920f79 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -280,12 +280,20 @@ static int ovl_mount_dir_check(struct fs_context *fc, const struct path *path, { struct ovl_fs_context *ctx = fc->fs_private; - if (ovl_dentry_weird(path->dentry)) - return invalfc(fc, "filesystem on %s not supported", name); - if (!d_is_dir(path->dentry)) return invalfc(fc, "%s is not a directory", name); + /* + * Root dentries of case-insensitive capable filesystems might + * not have the dentry operations set, but still be incompatible + * with overlayfs. Check explicitly to prevent post-mount + * failures. + */ + if (sb_has_encoding(path->mnt->mnt_sb)) + return invalfc(fc, "case-insensitive capable filesystem on %s not supported", name); + + if (ovl_dentry_weird(path->dentry)) + return invalfc(fc, "filesystem on %s not supported", name); /* * Check whether upper path is read-only here to report failures diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index d41c20d1b5..4ca72b08d9 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -182,25 +182,21 @@ static int pstore_unlink(struct inode *dir, struct dentry *dentry) { struct pstore_private *p = d_inode(dentry)->i_private; struct pstore_record *record = p->record; - int rc = 0; if (!record->psi->erase) return -EPERM; /* Make sure we can't race while removing this file. */ - mutex_lock(&records_list_lock); - if (!list_empty(&p->list)) - list_del_init(&p->list); - else - rc = -ENOENT; - p->dentry = NULL; - mutex_unlock(&records_list_lock); - if (rc) - return rc; - - mutex_lock(&record->psi->read_mutex); - record->psi->erase(record); - mutex_unlock(&record->psi->read_mutex); + scoped_guard(mutex, &records_list_lock) { + if (!list_empty(&p->list)) + list_del_init(&p->list); + else + return -ENOENT; + p->dentry = NULL; + } + + scoped_guard(mutex, &record->psi->read_mutex) + record->psi->erase(record); return simple_unlink(dir, dentry); } @@ -292,19 +288,16 @@ static struct dentry *psinfo_lock_root(void) { struct dentry *root; - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); /* * Having no backend is fine -- no records appear. * Not being mounted is fine -- nothing to do. */ - if (!psinfo || !pstore_sb) { - mutex_unlock(&pstore_sb_lock); + if (!psinfo || !pstore_sb) return NULL; - } root = pstore_sb->s_root; inode_lock(d_inode(root)); - mutex_unlock(&pstore_sb_lock); return root; } @@ -313,29 +306,25 @@ int pstore_put_backend_records(struct pstore_info *psi) { struct pstore_private *pos, *tmp; struct dentry *root; - int rc = 0; root = psinfo_lock_root(); if (!root) return 0; - mutex_lock(&records_list_lock); - list_for_each_entry_safe(pos, tmp, &records_list, list) { - if (pos->record->psi == psi) { - list_del_init(&pos->list); - rc = simple_unlink(d_inode(root), pos->dentry); - if (WARN_ON(rc)) - break; - d_drop(pos->dentry); - dput(pos->dentry); - pos->dentry = NULL; + scoped_guard(mutex, &records_list_lock) { + list_for_each_entry_safe(pos, tmp, &records_list, list) { + if (pos->record->psi == psi) { + list_del_init(&pos->list); + d_invalidate(pos->dentry); + simple_unlink(d_inode(root), pos->dentry); + pos->dentry = NULL; + } } } - mutex_unlock(&records_list_lock); inode_unlock(d_inode(root)); - return rc; + return 0; } /* @@ -355,20 +344,20 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) if (WARN_ON(!inode_is_locked(d_inode(root)))) return -EINVAL; - rc = -EEXIST; + guard(mutex)(&records_list_lock); + /* Skip records that are already present in the filesystem. */ - mutex_lock(&records_list_lock); list_for_each_entry(pos, &records_list, list) { if (pos->record->type == record->type && pos->record->id == record->id && pos->record->psi == record->psi) - goto fail; + return -EEXIST; } rc = -ENOMEM; inode = pstore_get_inode(root->d_sb); if (!inode) - goto fail; + return -ENOMEM; inode->i_mode = S_IFREG | 0444; inode->i_fop = &pstore_file_operations; scnprintf(name, sizeof(name), "%s-%s-%llu%s", @@ -396,7 +385,6 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) d_add(dentry, inode); list_add(&private->list, &records_list); - mutex_unlock(&records_list_lock); return 0; @@ -404,8 +392,6 @@ fail_private: free_pstore_private(private); fail_inode: iput(inode); -fail: - mutex_unlock(&records_list_lock); return rc; } @@ -451,9 +437,8 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) return -ENOMEM; - mutex_lock(&pstore_sb_lock); - pstore_sb = sb; - mutex_unlock(&pstore_sb_lock); + scoped_guard(mutex, &pstore_sb_lock) + pstore_sb = sb; pstore_get_records(0); @@ -468,17 +453,14 @@ static struct dentry *pstore_mount(struct file_system_type *fs_type, static void pstore_kill_sb(struct super_block *sb) { - mutex_lock(&pstore_sb_lock); + guard(mutex)(&pstore_sb_lock); WARN_ON(pstore_sb && pstore_sb != sb); kill_litter_super(sb); pstore_sb = NULL; - mutex_lock(&records_list_lock); + guard(mutex)(&records_list_lock); INIT_LIST_HEAD(&records_list); - mutex_unlock(&records_list_lock); - - mutex_unlock(&pstore_sb_lock); } static struct file_system_type pstore_fs_type = { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 58b5de081b..6f2fa7889d 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -399,15 +399,17 @@ int dquot_mark_dquot_dirty(struct dquot *dquot) EXPORT_SYMBOL(dquot_mark_dquot_dirty); /* Dirtify all the dquots - this can block when journalling */ -static inline int mark_all_dquot_dirty(struct dquot * const *dquot) +static inline int mark_all_dquot_dirty(struct dquot __rcu * const *dquots) { int ret, err, cnt; + struct dquot *dquot; ret = err = 0; for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquot[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) /* Even in case of error we have to continue */ - ret = mark_dquot_dirty(dquot[cnt]); + ret = mark_dquot_dirty(dquot); if (!err) err = ret; } @@ -998,14 +1000,14 @@ out: } EXPORT_SYMBOL(dqget); -static inline struct dquot **i_dquot(struct inode *inode) +static inline struct dquot __rcu **i_dquot(struct inode *inode) { return inode->i_sb->s_op->get_dquots(inode); } static int dqinit_needed(struct inode *inode, int type) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1095,14 +1097,16 @@ static void remove_dquot_ref(struct super_block *sb, int type) */ spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { - struct dquot **dquots = i_dquot(inode); - struct dquot *dquot = dquots[type]; + struct dquot __rcu **dquots = i_dquot(inode); + struct dquot *dquot = srcu_dereference_check( + dquots[type], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) reserved = 1; #endif - dquots[type] = NULL; + rcu_assign_pointer(dquots[type], NULL); if (dquot) dqput(dquot); } @@ -1455,7 +1459,8 @@ static int inode_quota_active(const struct inode *inode) static int __dquot_initialize(struct inode *inode, int type) { int cnt, init_needed = 0; - struct dquot **dquots, *got[MAXQUOTAS] = {}; + struct dquot __rcu **dquots; + struct dquot *got[MAXQUOTAS] = {}; struct super_block *sb = inode->i_sb; qsize_t rsv; int ret = 0; @@ -1530,7 +1535,7 @@ static int __dquot_initialize(struct inode *inode, int type) if (!got[cnt]) continue; if (!dquots[cnt]) { - dquots[cnt] = got[cnt]; + rcu_assign_pointer(dquots[cnt], got[cnt]); got[cnt] = NULL; /* * Make quota reservation system happy if someone @@ -1538,12 +1543,16 @@ static int __dquot_initialize(struct inode *inode, int type) */ rsv = inode_get_rsv_space(inode); if (unlikely(rsv)) { + struct dquot *dquot = srcu_dereference_check( + dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + spin_lock(&inode->i_lock); /* Get reservation again under proper lock */ rsv = __inode_get_rsv_space(inode); - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquots[cnt]->dq_dqb.dqb_rsvspace += rsv; - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot->dq_dqb.dqb_rsvspace += rsv; + spin_unlock(&dquot->dq_dqb_lock); spin_unlock(&inode->i_lock); } } @@ -1565,7 +1574,7 @@ EXPORT_SYMBOL(dquot_initialize); bool dquot_initialize_needed(struct inode *inode) { - struct dquot **dquots; + struct dquot __rcu **dquots; int i; if (!inode_quota_active(inode)) @@ -1590,13 +1599,14 @@ EXPORT_SYMBOL(dquot_initialize_needed); static void __dquot_drop(struct inode *inode) { int cnt; - struct dquot **dquots = i_dquot(inode); + struct dquot __rcu **dquots = i_dquot(inode); struct dquot *put[MAXQUOTAS]; spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - put[cnt] = dquots[cnt]; - dquots[cnt] = NULL; + put[cnt] = srcu_dereference_check(dquots[cnt], &dquot_srcu, + lockdep_is_held(&dq_data_lock)); + rcu_assign_pointer(dquots[cnt], NULL); } spin_unlock(&dq_data_lock); dqput_all(put); @@ -1604,7 +1614,7 @@ static void __dquot_drop(struct inode *inode) void dquot_drop(struct inode *inode) { - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; int cnt; if (IS_NOQUOTA(inode)) @@ -1677,7 +1687,8 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; int reserve = flags & DQUOT_SPACE_RESERVE; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) { if (reserve) { @@ -1697,27 +1708,26 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; if (reserve) { - ret = dquot_add_space(dquots[cnt], 0, number, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, 0, number, flags, &warn[cnt]); } else { - ret = dquot_add_space(dquots[cnt], number, 0, flags, - &warn[cnt]); + ret = dquot_add_space(dquot, number, 0, flags, &warn[cnt]); } if (ret) { /* Back out changes we already did */ for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); if (reserve) - dquot_free_reserved_space(dquots[cnt], - number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); goto out_flush_warn; @@ -1747,7 +1757,8 @@ int dquot_alloc_inode(struct inode *inode) { int cnt, ret = 0, index; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; if (!inode_quota_active(inode)) return 0; @@ -1758,17 +1769,19 @@ int dquot_alloc_inode(struct inode *inode) index = srcu_read_lock(&dquot_srcu); spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - ret = dquot_add_inodes(dquots[cnt], 1, &warn[cnt]); + ret = dquot_add_inodes(dquot, 1, &warn[cnt]); if (ret) { for (cnt--; cnt >= 0; cnt--) { - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; /* Back out changes we already did */ - spin_lock(&dquots[cnt]->dq_dqb_lock); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + spin_lock(&dquot->dq_dqb_lock); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } goto warn_put_all; } @@ -1789,7 +1802,8 @@ EXPORT_SYMBOL(dquot_alloc_inode); */ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1805,9 +1819,8 @@ int dquot_claim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_rsvspace < number)) number = dquot->dq_dqb.dqb_rsvspace; @@ -1831,7 +1844,8 @@ EXPORT_SYMBOL(dquot_claim_space_nodirty); */ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) { - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int cnt, index; if (!inode_quota_active(inode)) { @@ -1847,9 +1861,8 @@ void dquot_reclaim_space_nodirty(struct inode *inode, qsize_t number) spin_lock(&inode->i_lock); /* Claim reserved quotas to allocated quotas */ for (cnt = 0; cnt < MAXQUOTAS; cnt++) { - if (dquots[cnt]) { - struct dquot *dquot = dquots[cnt]; - + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (dquot) { spin_lock(&dquot->dq_dqb_lock); if (WARN_ON_ONCE(dquot->dq_dqb.dqb_curspace < number)) number = dquot->dq_dqb.dqb_curspace; @@ -1875,7 +1888,8 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot **dquots; + struct dquot __rcu **dquots; + struct dquot *dquot; int reserve = flags & DQUOT_SPACE_RESERVE, index; if (!inode_quota_active(inode)) { @@ -1896,17 +1910,18 @@ void __dquot_free_space(struct inode *inode, qsize_t number, int flags) int wtype; warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_bdq_free(dquots[cnt], number); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_bdq_free(dquot, number); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); + prepare_warning(&warn[cnt], dquot, wtype); if (reserve) - dquot_free_reserved_space(dquots[cnt], number); + dquot_free_reserved_space(dquot, number); else - dquot_decr_space(dquots[cnt], number); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + dquot_decr_space(dquot, number); + spin_unlock(&dquot->dq_dqb_lock); } if (reserve) *inode_reserved_space(inode) -= number; @@ -1930,7 +1945,8 @@ void dquot_free_inode(struct inode *inode) { unsigned int cnt; struct dquot_warn warn[MAXQUOTAS]; - struct dquot * const *dquots; + struct dquot __rcu * const *dquots; + struct dquot *dquot; int index; if (!inode_quota_active(inode)) @@ -1941,16 +1957,16 @@ void dquot_free_inode(struct inode *inode) spin_lock(&inode->i_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { int wtype; - warn[cnt].w_type = QUOTA_NL_NOWARN; - if (!dquots[cnt]) + dquot = srcu_dereference(dquots[cnt], &dquot_srcu); + if (!dquot) continue; - spin_lock(&dquots[cnt]->dq_dqb_lock); - wtype = info_idq_free(dquots[cnt], 1); + spin_lock(&dquot->dq_dqb_lock); + wtype = info_idq_free(dquot, 1); if (wtype != QUOTA_NL_NOWARN) - prepare_warning(&warn[cnt], dquots[cnt], wtype); - dquot_decr_inodes(dquots[cnt], 1); - spin_unlock(&dquots[cnt]->dq_dqb_lock); + prepare_warning(&warn[cnt], dquot, wtype); + dquot_decr_inodes(dquot, 1); + spin_unlock(&dquot->dq_dqb_lock); } spin_unlock(&inode->i_lock); mark_all_dquot_dirty(dquots); @@ -1976,8 +1992,9 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) qsize_t cur_space; qsize_t rsv_space = 0; qsize_t inode_usage = 1; + struct dquot __rcu **dquots; struct dquot *transfer_from[MAXQUOTAS] = {}; - int cnt, ret = 0; + int cnt, index, ret = 0; char is_valid[MAXQUOTAS] = {}; struct dquot_warn warn_to[MAXQUOTAS]; struct dquot_warn warn_from_inodes[MAXQUOTAS]; @@ -2008,6 +2025,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) } cur_space = __inode_get_bytes(inode); rsv_space = __inode_get_rsv_space(inode); + dquots = i_dquot(inode); /* * Build the transfer_from list, check limits, and update usage in * the target structures. @@ -2022,7 +2040,8 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) if (!sb_has_quota_active(inode->i_sb, cnt)) continue; is_valid[cnt] = 1; - transfer_from[cnt] = i_dquot(inode)[cnt]; + transfer_from[cnt] = srcu_dereference_check(dquots[cnt], + &dquot_srcu, lockdep_is_held(&dq_data_lock)); ret = dquot_add_inodes(transfer_to[cnt], inode_usage, &warn_to[cnt]); if (ret) @@ -2061,13 +2080,21 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to) rsv_space); spin_unlock(&transfer_from[cnt]->dq_dqb_lock); } - i_dquot(inode)[cnt] = transfer_to[cnt]; + rcu_assign_pointer(dquots[cnt], transfer_to[cnt]); } spin_unlock(&inode->i_lock); spin_unlock(&dq_data_lock); - mark_all_dquot_dirty(transfer_from); - mark_all_dquot_dirty(transfer_to); + /* + * These arrays are local and we hold dquot references so we don't need + * the srcu protection but still take dquot_srcu to avoid warning in + * mark_all_dquot_dirty(). + */ + index = srcu_read_lock(&dquot_srcu); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_from); + mark_all_dquot_dirty((struct dquot __rcu **)transfer_to); + srcu_read_unlock(&dquot_srcu, index); + flush_warnings(warn_to); flush_warnings(warn_from_inodes); flush_warnings(warn_from_space); diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 725667880e..b655491645 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -97,7 +97,7 @@ struct reiserfs_inode_info { struct rw_semaphore i_xattr_sem; #endif #ifdef CONFIG_QUOTA - struct dquot *i_dquot[MAXQUOTAS]; + struct dquot __rcu *i_dquot[MAXQUOTAS]; #endif struct inode vfs_inode; diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 67b5510bed..7b3d5aeb2a 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -802,7 +802,7 @@ static ssize_t reiserfs_quota_write(struct super_block *, int, const char *, static ssize_t reiserfs_quota_read(struct super_block *, int, char *, size_t, loff_t); -static struct dquot **reiserfs_get_dquots(struct inode *inode) +static struct dquot __rcu **reiserfs_get_dquots(struct inode *inode) { return REISERFS_I(inode)->i_dquot; } diff --git a/fs/select.c b/fs/select.c index 0ee55af1a5..d4d881d439 100644 --- a/fs/select.c +++ b/fs/select.c @@ -476,7 +476,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in, wait->_key |= POLLOUT_SET; } -static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) +static noinline_for_stack int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time) { ktime_t expire, *to = NULL; struct poll_wqueues table; diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index 5730c65ffb..15e1215bc4 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -233,7 +233,8 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, .tcon = tcon, .path = path, .create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE), - .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES, + .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES | + FILE_READ_EA, .disposition = FILE_OPEN, .fid = pfid, }; diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index 60027f5aeb..04a6351a92 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -488,6 +488,8 @@ skip_rdma: ses->ses_count, ses->serverOS, ses->serverNOS, ses->capabilities, ses->ses_status); } + if (ses->expired_pwd) + seq_puts(m, "password no longer valid "); spin_unlock(&ses->ses_lock); seq_printf(m, "\n\tSecurity type: %s ", diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 462554917e..35a12413bb 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -339,6 +339,9 @@ struct smb_version_operations { /* informational QFS call */ void (*qfs_tcon)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *); + /* query for server interfaces */ + int (*query_server_interfaces)(const unsigned int, struct cifs_tcon *, + bool); /* check if a path is accessible or not */ int (*is_path_accessible)(const unsigned int, struct cifs_tcon *, struct cifs_sb_info *, const char *); @@ -1052,6 +1055,7 @@ struct cifs_ses { enum securityEnum sectype; /* what security flavor was specified? */ bool sign; /* is signing required? */ bool domainAuto:1; + bool expired_pwd; /* track if access denied or expired pwd so can know if need to update */ unsigned int flags; __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; @@ -1562,6 +1566,7 @@ struct cifsInodeInfo { spinlock_t deferred_lock; /* protection on deferred list */ bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ char *symlink_target; + __u32 reparse_tag; }; static inline struct cifsInodeInfo * diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 9516f57323..13131957d9 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -144,7 +144,8 @@ extern int cifs_reconnect(struct TCP_Server_Info *server, extern int checkSMB(char *buf, unsigned int len, struct TCP_Server_Info *srvr); extern bool is_valid_oplock_break(char *, struct TCP_Server_Info *); extern bool backup_cred(struct cifs_sb_info *); -extern bool is_size_safe_to_change(struct cifsInodeInfo *, __u64 eof); +extern bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 eof, + bool from_readdir); extern void cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, unsigned int bytes_written); extern struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *, int); @@ -201,7 +202,8 @@ extern void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb); extern void cifs_dir_info_to_fattr(struct cifs_fattr *, FILE_DIRECTORY_INFO *, struct cifs_sb_info *); -extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr); +extern int cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir); extern struct inode *cifs_iget(struct super_block *sb, struct cifs_fattr *fattr); @@ -652,7 +654,7 @@ cifs_chan_is_iface_active(struct cifs_ses *ses, struct TCP_Server_Info *server); void cifs_disable_secondary_channels(struct cifs_ses *ses); -int +void cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server); int SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon, bool in_mount); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index c3d805ecb7..bc8d09bab1 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -123,12 +123,16 @@ static void smb2_query_server_interfaces(struct work_struct *work) struct cifs_tcon *tcon = container_of(work, struct cifs_tcon, query_interfaces.work); + struct TCP_Server_Info *server = tcon->ses->server; /* * query server network interfaces, in case they change */ + if (!server->ops->query_server_interfaces) + return; + xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 4cbb5487bd..c711d5eb29 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -87,7 +87,7 @@ void cifs_pages_written_back(struct inode *inode, loff_t start, unsigned int len continue; if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -120,7 +120,7 @@ void cifs_pages_write_failed(struct inode *inode, loff_t start, unsigned int len continue; if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -151,7 +151,7 @@ void cifs_pages_write_redirty(struct inode *inode, loff_t start, unsigned int le xas_for_each(&xas, folio, end) { if (!folio_test_writeback(folio)) { WARN_ONCE(1, "bad %x @%llx page %lx %lx\n", - len, start, folio_index(folio), end); + len, start, folio->index, end); continue; } @@ -329,7 +329,7 @@ int cifs_posix_open(const char *full_path, struct inode **pinode, } } else { cifs_revalidate_mapping(*pinode); - rc = cifs_fattr_to_inode(*pinode, &fattr); + rc = cifs_fattr_to_inode(*pinode, &fattr, false); } posix_open_ret: @@ -2622,20 +2622,20 @@ static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) * dirty pages if possible, but don't sleep while doing so. */ static void cifs_extend_writeback(struct address_space *mapping, + struct xa_state *xas, long *_count, loff_t start, int max_pages, - size_t max_len, - unsigned int *_len) + loff_t max_len, + size_t *_len) { struct folio_batch batch; struct folio *folio; - unsigned int psize, nr_pages; - size_t len = *_len; - pgoff_t index = (start + len) / PAGE_SIZE; + unsigned int nr_pages; + pgoff_t index = (start + *_len) / PAGE_SIZE; + size_t len; bool stop = true; unsigned int i; - XA_STATE(xas, &mapping->i_pages, index); folio_batch_init(&batch); @@ -2646,54 +2646,64 @@ static void cifs_extend_writeback(struct address_space *mapping, */ rcu_read_lock(); - xas_for_each(&xas, folio, ULONG_MAX) { + xas_for_each(xas, folio, ULONG_MAX) { stop = true; - if (xas_retry(&xas, folio)) + if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) break; - if (folio_index(folio) != index) + if (folio->index != index) { + xas_reset(xas); break; + } + if (!folio_try_get_rcu(folio)) { - xas_reset(&xas); + xas_reset(xas); continue; } nr_pages = folio_nr_pages(folio); - if (nr_pages > max_pages) + if (nr_pages > max_pages) { + xas_reset(xas); break; + } /* Has the page moved or been split? */ - if (unlikely(folio != xas_reload(&xas))) { + if (unlikely(folio != xas_reload(xas))) { folio_put(folio); + xas_reset(xas); break; } if (!folio_trylock(folio)) { folio_put(folio); + xas_reset(xas); break; } - if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + if (!folio_test_dirty(folio) || + folio_test_writeback(folio)) { folio_unlock(folio); folio_put(folio); + xas_reset(xas); break; } max_pages -= nr_pages; - psize = folio_size(folio); - len += psize; + len = folio_size(folio); stop = false; - if (max_pages <= 0 || len >= max_len || *_count <= 0) - stop = true; index += nr_pages; + *_count -= nr_pages; + *_len += len; + if (max_pages <= 0 || *_len >= max_len || *_count <= 0) + stop = true; + if (!folio_batch_add(&batch, folio)) break; if (stop) break; } - if (!stop) - xas_pause(&xas); + xas_pause(xas); rcu_read_unlock(); /* Now, if we obtained any pages, we can shift them to being @@ -2709,18 +2719,13 @@ static void cifs_extend_writeback(struct address_space *mapping, */ if (!folio_clear_dirty_for_io(folio)) WARN_ON(1); - if (folio_start_writeback(folio)) - WARN_ON(1); - - *_count -= folio_nr_pages(folio); + folio_start_writeback(folio); folio_unlock(folio); } folio_batch_release(&batch); cond_resched(); } while (!stop); - - *_len = len; } /* @@ -2728,8 +2733,10 @@ static void cifs_extend_writeback(struct address_space *mapping, */ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, struct writeback_control *wbc, + struct xa_state *xas, struct folio *folio, - loff_t start, loff_t end) + unsigned long long start, + unsigned long long end) { struct inode *inode = mapping->host; struct TCP_Server_Info *server; @@ -2738,18 +2745,18 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, struct cifs_credits credits_on_stack; struct cifs_credits *credits = &credits_on_stack; struct cifsFileInfo *cfile = NULL; - unsigned int xid, wsize, len; - loff_t i_size = i_size_read(inode); - size_t max_len; + unsigned long long i_size = i_size_read(inode), max_len; + unsigned int xid, wsize; + size_t len = folio_size(folio); long count = wbc->nr_to_write; int rc; /* The folio should be locked, dirty and not undergoing writeback. */ - if (folio_start_writeback(folio)) - WARN_ON(1); + if (!folio_clear_dirty_for_io(folio)) + WARN_ON_ONCE(1); + folio_start_writeback(folio); count -= folio_nr_pages(folio); - len = folio_size(folio); xid = get_xid(); server = cifs_pick_channel(cifs_sb_master_tcon(cifs_sb)->ses); @@ -2779,9 +2786,10 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, wdata->server = server; cfile = NULL; - /* Find all consecutive lockable dirty pages, stopping when we find a - * page that is not immediately lockable, is not dirty or is missing, - * or we reach the end of the range. + /* Find all consecutive lockable dirty pages that have contiguous + * written regions, stopping when we find a page that is not + * immediately lockable, is not dirty or is missing, or we reach the + * end of the range. */ if (start < i_size) { /* Trim the write to the EOF; the extra data is ignored. Also @@ -2801,19 +2809,18 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, max_pages -= folio_nr_pages(folio); if (max_pages > 0) - cifs_extend_writeback(mapping, &count, start, + cifs_extend_writeback(mapping, xas, &count, start, max_pages, max_len, &len); } - len = min_t(loff_t, len, max_len); } - - wdata->bytes = len; + len = min_t(unsigned long long, len, i_size - start); /* We now have a contiguous set of dirty pages, each with writeback * set; the first page is still locked at this point, but all the rest * have been unlocked. */ folio_unlock(folio); + wdata->bytes = len; if (start < i_size) { iov_iter_xarray(&wdata->iter, ITER_SOURCE, &mapping->i_pages, @@ -2864,102 +2871,118 @@ err_xid: /* * write a region of pages back to the server */ -static int cifs_writepages_region(struct address_space *mapping, - struct writeback_control *wbc, - loff_t start, loff_t end, loff_t *_next) +static ssize_t cifs_writepages_begin(struct address_space *mapping, + struct writeback_control *wbc, + struct xa_state *xas, + unsigned long long *_start, + unsigned long long end) { - struct folio_batch fbatch; + struct folio *folio; + unsigned long long start = *_start; + ssize_t ret; int skips = 0; - folio_batch_init(&fbatch); - do { - int nr; - pgoff_t index = start / PAGE_SIZE; +search_again: + /* Find the first dirty page. */ + rcu_read_lock(); - nr = filemap_get_folios_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, &fbatch); - if (!nr) + for (;;) { + folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY); + if (xas_retry(xas, folio) || xa_is_value(folio)) + continue; + if (!folio) break; - for (int i = 0; i < nr; i++) { - ssize_t ret; - struct folio *folio = fbatch.folios[i]; + if (!folio_try_get_rcu(folio)) { + xas_reset(xas); + continue; + } -redo_folio: - start = folio_pos(folio); /* May regress with THPs */ + if (unlikely(folio != xas_reload(xas))) { + folio_put(folio); + xas_reset(xas); + continue; + } - /* At this point we hold neither the i_pages lock nor the - * page lock: the page may be truncated or invalidated - * (changing page->mapping to NULL), or even swizzled - * back from swapper_space to tmpfs file mapping - */ - if (wbc->sync_mode != WB_SYNC_NONE) { - ret = folio_lock_killable(folio); - if (ret < 0) - goto write_error; - } else { - if (!folio_trylock(folio)) - goto skip_write; - } + xas_pause(xas); + break; + } + rcu_read_unlock(); + if (!folio) + return 0; - if (folio_mapping(folio) != mapping || - !folio_test_dirty(folio)) { - start += folio_size(folio); - folio_unlock(folio); - continue; - } + start = folio_pos(folio); /* May regress with THPs */ - if (folio_test_writeback(folio) || - folio_test_fscache(folio)) { - folio_unlock(folio); - if (wbc->sync_mode == WB_SYNC_NONE) - goto skip_write; + /* At this point we hold neither the i_pages lock nor the page lock: + * the page may be truncated or invalidated (changing page->mapping to + * NULL), or even swizzled back from swapper_space to tmpfs file + * mapping + */ +lock_again: + if (wbc->sync_mode != WB_SYNC_NONE) { + ret = folio_lock_killable(folio); + if (ret < 0) + return ret; + } else { + if (!folio_trylock(folio)) + goto search_again; + } + + if (folio->mapping != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + goto search_again; + } - folio_wait_writeback(folio); + if (folio_test_writeback(folio) || + folio_test_fscache(folio)) { + folio_unlock(folio); + if (wbc->sync_mode != WB_SYNC_NONE) { + folio_wait_writeback(folio); #ifdef CONFIG_CIFS_FSCACHE - folio_wait_fscache(folio); + folio_wait_fscache(folio); #endif - goto redo_folio; - } - - if (!folio_clear_dirty_for_io(folio)) - /* We hold the page lock - it should've been dirty. */ - WARN_ON(1); - - ret = cifs_write_back_from_locked_folio(mapping, wbc, folio, start, end); - if (ret < 0) - goto write_error; - - start += ret; - continue; - -write_error: - folio_batch_release(&fbatch); - *_next = start; - return ret; + goto lock_again; + } -skip_write: - /* - * Too many skipped writes, or need to reschedule? - * Treat it as a write error without an error code. - */ + start += folio_size(folio); + if (wbc->sync_mode == WB_SYNC_NONE) { if (skips >= 5 || need_resched()) { ret = 0; - goto write_error; + goto out; } - - /* Otherwise, just skip that folio and go on to the next */ skips++; - start += folio_size(folio); - continue; } + goto search_again; + } - folio_batch_release(&fbatch); - cond_resched(); - } while (wbc->nr_to_write > 0); + ret = cifs_write_back_from_locked_folio(mapping, wbc, xas, folio, start, end); +out: + if (ret > 0) + *_start = start + ret; + return ret; +} - *_next = start; - return 0; +/* + * Write a region of pages back to the server + */ +static int cifs_writepages_region(struct address_space *mapping, + struct writeback_control *wbc, + unsigned long long *_start, + unsigned long long end) +{ + ssize_t ret; + + XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE); + + do { + ret = cifs_writepages_begin(mapping, wbc, &xas, _start, end); + if (ret > 0 && wbc->nr_to_write > 0) + cond_resched(); + } while (ret > 0 && wbc->nr_to_write > 0); + + return ret > 0 ? 0 : ret; } /* @@ -2968,7 +2991,7 @@ skip_write: static int cifs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - loff_t start, next; + loff_t start, end; int ret; /* We have to be careful as we can end up racing with setattr() @@ -2976,28 +2999,34 @@ static int cifs_writepages(struct address_space *mapping, * to prevent it. */ - if (wbc->range_cyclic) { + if (wbc->range_cyclic && mapping->writeback_index) { start = mapping->writeback_index * PAGE_SIZE; - ret = cifs_writepages_region(mapping, wbc, start, LLONG_MAX, &next); - if (ret == 0) { - mapping->writeback_index = next / PAGE_SIZE; - if (start > 0 && wbc->nr_to_write > 0) { - ret = cifs_writepages_region(mapping, wbc, 0, - start, &next); - if (ret == 0) - mapping->writeback_index = - next / PAGE_SIZE; - } + ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX); + if (ret < 0) + goto out; + + if (wbc->nr_to_write <= 0) { + mapping->writeback_index = start / PAGE_SIZE; + goto out; } + + start = 0; + end = mapping->writeback_index * PAGE_SIZE; + mapping->writeback_index = 0; + ret = cifs_writepages_region(mapping, wbc, &start, end); + if (ret == 0) + mapping->writeback_index = start / PAGE_SIZE; } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) { - ret = cifs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next); + start = 0; + ret = cifs_writepages_region(mapping, wbc, &start, LLONG_MAX); if (wbc->nr_to_write > 0 && ret == 0) - mapping->writeback_index = next / PAGE_SIZE; + mapping->writeback_index = start / PAGE_SIZE; } else { - ret = cifs_writepages_region(mapping, wbc, - wbc->range_start, wbc->range_end, &next); + start = wbc->range_start; + ret = cifs_writepages_region(mapping, wbc, &start, wbc->range_end); } +out: return ret; } @@ -4737,12 +4766,14 @@ static int is_inode_writable(struct cifsInodeInfo *cifs_inode) refreshing the inode only on increases in the file size but this is tricky to do without racing with writebehind page caching in the current Linux kernel design */ -bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) +bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, + bool from_readdir) { if (!cifsInode) return true; - if (is_inode_writable(cifsInode)) { + if (is_inode_writable(cifsInode) || + ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ struct cifs_sb_info *cifs_sb; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 6ecbf48d0f..e4a6b240d2 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -771,7 +771,7 @@ static void smb3_fs_context_free(struct fs_context *fc) */ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, struct smb3_fs_context *new_ctx, - struct smb3_fs_context *old_ctx) + struct smb3_fs_context *old_ctx, bool need_recon) { if (new_ctx->posix_paths != old_ctx->posix_paths) { cifs_errorf(fc, "can not change posixpaths during remount\n"); @@ -797,8 +797,15 @@ static int smb3_verify_reconfigure_ctx(struct fs_context *fc, } if (new_ctx->password && (!old_ctx->password || strcmp(new_ctx->password, old_ctx->password))) { - cifs_errorf(fc, "can not change password during remount\n"); - return -EINVAL; + if (need_recon == false) { + cifs_errorf(fc, + "can not change password of active session during remount\n"); + return -EINVAL; + } else if (old_ctx->sectype == Kerberos) { + cifs_errorf(fc, + "can not change password for Kerberos via remount\n"); + return -EINVAL; + } } if (new_ctx->domainname && (!old_ctx->domainname || strcmp(new_ctx->domainname, old_ctx->domainname))) { @@ -842,9 +849,14 @@ static int smb3_reconfigure(struct fs_context *fc) struct smb3_fs_context *ctx = smb3_fc2context(fc); struct dentry *root = fc->root; struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); + struct cifs_ses *ses = cifs_sb_master_tcon(cifs_sb)->ses; + bool need_recon = false; int rc; - rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx); + if (ses->expired_pwd) + need_recon = true; + + rc = smb3_verify_reconfigure_ctx(fc, ctx, cifs_sb->ctx, need_recon); if (rc) return rc; @@ -857,7 +869,12 @@ static int smb3_reconfigure(struct fs_context *fc) STEAL_STRING(cifs_sb, ctx, UNC); STEAL_STRING(cifs_sb, ctx, source); STEAL_STRING(cifs_sb, ctx, username); - STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + if (need_recon == false) + STEAL_STRING_SENSITIVE(cifs_sb, ctx, password); + else { + kfree_sensitive(ses->password); + ses->password = kstrdup(ctx->password, GFP_KERNEL); + } STEAL_STRING(cifs_sb, ctx, domainname); STEAL_STRING(cifs_sb, ctx, nodename); STEAL_STRING(cifs_sb, ctx, iocharset); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index eb54e48937..cb9e719e67 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -147,7 +147,8 @@ cifs_nlink_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) /* populate an inode with info from a cifs_fattr struct */ int -cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) +cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, + bool from_readdir) { struct cifsInodeInfo *cifs_i = CIFS_I(inode); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); @@ -182,6 +183,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) inode->i_mode = fattr->cf_mode; cifs_i->cifsAttrs = fattr->cf_cifsattrs; + cifs_i->reparse_tag = fattr->cf_cifstag; if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL) cifs_i->time = 0; @@ -198,7 +200,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) * Can't safely change the file size here if the client is writing to * it due to potential races. */ - if (is_size_safe_to_change(cifs_i, fattr->cf_eof)) { + if (is_size_safe_to_change(cifs_i, fattr->cf_eof, from_readdir)) { i_size_write(inode, fattr->cf_eof); /* @@ -209,7 +211,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) inode->i_blocks = (512 - 1 + fattr->cf_bytes) >> 9; } - if (S_ISLNK(fattr->cf_mode)) { + if (S_ISLNK(fattr->cf_mode) && fattr->cf_symlink_target) { kfree(cifs_i->symlink_target); cifs_i->symlink_target = fattr->cf_symlink_target; fattr->cf_symlink_target = NULL; @@ -367,7 +369,7 @@ static int update_inode_info(struct super_block *sb, CIFS_I(*inode)->time = 0; /* force reval */ return -ESTALE; } - return cifs_fattr_to_inode(*inode, fattr); + return cifs_fattr_to_inode(*inode, fattr, false); } #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY @@ -402,7 +404,7 @@ cifs_get_file_info_unix(struct file *filp) } else goto cifs_gfiunix_out; - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cifs_gfiunix_out: free_xid(xid); @@ -927,7 +929,7 @@ cifs_get_file_info(struct file *filp) fattr.cf_uniqueid = CIFS_I(inode)->uniqueid; fattr.cf_flags |= CIFS_FATTR_NEED_REVAL; /* if filetype is different, return error */ - rc = cifs_fattr_to_inode(inode, &fattr); + rc = cifs_fattr_to_inode(inode, &fattr, false); cgfi_exit: cifs_free_open_info(&data); free_xid(xid); @@ -1103,6 +1105,7 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, cifs_open_info_to_fattr(fattr, data, sb); out: + fattr->cf_cifstag = data->reparse.tag; free_rsp_buf(rsp_buftype, rsp_iov.iov_base); return rc; } @@ -1465,7 +1468,7 @@ retry_iget5_locked: } /* can't fail - see cifs_find_inode() */ - cifs_fattr_to_inode(inode, fattr); + cifs_fattr_to_inode(inode, fattr, false); if (sb->s_flags & SB_NOATIME) inode->i_flags |= S_NOATIME | S_NOCMTIME; if (inode->i_state & I_NEW) { diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index e23cd216bf..56033e4e4b 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -55,6 +55,23 @@ static inline void dump_cifs_file_struct(struct file *file, char *label) } #endif /* DEBUG2 */ +/* + * Match a reparse point inode if reparse tag and ctime haven't changed. + * + * Windows Server updates ctime of reparse points when their data have changed. + * The server doesn't allow changing reparse tags from existing reparse points, + * though it's worth checking. + */ +static inline bool reparse_inode_match(struct inode *inode, + struct cifs_fattr *fattr) +{ + struct timespec64 ctime = inode_get_ctime(inode); + + return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) && + CIFS_I(inode)->reparse_tag == fattr->cf_cifstag && + timespec64_equal(&ctime, &fattr->cf_ctime); +} + /* * Attempt to preload the dcache with the results from the FIND_FIRST/NEXT * @@ -71,6 +88,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, struct super_block *sb = parent->d_sb; struct cifs_sb_info *cifs_sb = CIFS_SB(sb); DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); + int rc; cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); @@ -82,9 +100,11 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, * We'll end up doing an on the wire call either way and * this spares us an invalidation. */ - if (fattr->cf_flags & CIFS_FATTR_NEED_REVAL) - return; retry: + if ((fattr->cf_cifsattrs & ATTR_REPARSE) || + (fattr->cf_flags & CIFS_FATTR_NEED_REVAL)) + return; + dentry = d_alloc_parallel(parent, name, &wq); } if (IS_ERR(dentry)) @@ -104,12 +124,34 @@ retry: if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) fattr->cf_uniqueid = CIFS_I(inode)->uniqueid; - /* update inode in place - * if both i_ino and i_mode didn't change */ - if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid && - cifs_fattr_to_inode(inode, fattr) == 0) { - dput(dentry); - return; + /* + * Update inode in place if both i_ino and i_mode didn't + * change. + */ + if (CIFS_I(inode)->uniqueid == fattr->cf_uniqueid) { + /* + * Query dir responses don't provide enough + * information about reparse points other than + * their reparse tags. Save an invalidation by + * not clobbering the existing mode, size and + * symlink target (if any) when reparse tag and + * ctime haven't changed. + */ + rc = 0; + if (fattr->cf_cifsattrs & ATTR_REPARSE) { + if (likely(reparse_inode_match(inode, fattr))) { + fattr->cf_mode = inode->i_mode; + fattr->cf_eof = CIFS_I(inode)->server_eof; + fattr->cf_symlink_target = NULL; + } else { + CIFS_I(inode)->time = 0; + rc = -ESTALE; + } + } + if (!rc && !cifs_fattr_to_inode(inode, fattr, true)) { + dput(dentry); + return; + } } } d_invalidate(dentry); @@ -127,29 +169,6 @@ retry: dput(dentry); } -static bool reparse_file_needs_reval(const struct cifs_fattr *fattr) -{ - if (!(fattr->cf_cifsattrs & ATTR_REPARSE)) - return false; - /* - * The DFS tags should be only intepreted by server side as per - * MS-FSCC 2.1.2.1, but let's include them anyway. - * - * Besides, if cf_cifstag is unset (0), then we still need it to be - * revalidated to know exactly what reparse point it is. - */ - switch (fattr->cf_cifstag) { - case IO_REPARSE_TAG_DFS: - case IO_REPARSE_TAG_DFSR: - case IO_REPARSE_TAG_SYMLINK: - case IO_REPARSE_TAG_NFS: - case IO_REPARSE_TAG_MOUNT_POINT: - case 0: - return true; - } - return false; -} - static void cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) { @@ -181,14 +200,6 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) } out_reparse: - /* - * We need to revalidate it further to make a decision about whether it - * is a symbolic link, DFS referral or a reparse point with a direct - * access like junctions, deduplicated files, NFS symlinks. - */ - if (reparse_file_needs_reval(fattr)) - fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; - /* non-unix readdir doesn't provide nlink */ fattr->cf_flags |= CIFS_FATTR_UNKNOWN_NLINK; @@ -269,9 +280,6 @@ cifs_posix_to_fattr(struct cifs_fattr *fattr, struct smb2_posix_info *info, fattr->cf_dtype = DT_REG; } - if (reparse_file_needs_reval(fattr)) - fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; - sid_to_id(cifs_sb, &parsed.owner, fattr, SIDOWNER); sid_to_id(cifs_sb, &parsed.group, fattr, SIDGROUP); } @@ -333,38 +341,6 @@ cifs_std_info_to_fattr(struct cifs_fattr *fattr, FIND_FILE_STANDARD_INFO *info, cifs_fill_common_info(fattr, cifs_sb); } -/* BB eventually need to add the following helper function to - resolve NT_STATUS_STOPPED_ON_SYMLINK return code when - we try to do FindFirst on (NTFS) directory symlinks */ -/* -int get_symlink_reparse_path(char *full_path, struct cifs_sb_info *cifs_sb, - unsigned int xid) -{ - __u16 fid; - int len; - int oplock = 0; - int rc; - struct cifs_tcon *ptcon = cifs_sb_tcon(cifs_sb); - char *tmpbuffer; - - rc = CIFSSMBOpen(xid, ptcon, full_path, FILE_OPEN, GENERIC_READ, - OPEN_REPARSE_POINT, &fid, &oplock, NULL, - cifs_sb->local_nls, - cifs_remap(cifs_sb); - if (!rc) { - tmpbuffer = kmalloc(maxpath); - rc = CIFSSMBQueryReparseLinkInfo(xid, ptcon, full_path, - tmpbuffer, - maxpath -1, - fid, - cifs_sb->local_nls); - if (CIFSSMBClose(xid, ptcon, fid)) { - cifs_dbg(FYI, "Error closing temporary reparsepoint open\n"); - } - } -} - */ - static int _initiate_cifs_search(const unsigned int xid, struct file *file, const char *full_path) @@ -433,13 +409,10 @@ ffirst_retry: &cifsFile->fid, search_flags, &cifsFile->srch_inf); - if (rc == 0) + if (rc == 0) { cifsFile->invalidHandle = false; - /* BB add following call to handle readdir on new NTFS symlink errors - else if STATUS_STOPPED_ON_SYMLINK - call get_symlink_reparse_path and retry with new path */ - else if ((rc == -EOPNOTSUPP) && - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { + } else if ((rc == -EOPNOTSUPP) && + (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; goto ffirst_retry; } diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 94c5d50aa3..5de32640f0 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -230,7 +230,7 @@ int cifs_try_adding_channels(struct cifs_ses *ses) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); break; } @@ -361,10 +361,9 @@ done: /* * update the iface for the channel if necessary. - * will return 0 when iface is updated, 1 if removed, 2 otherwise * Must be called with chan_lock held. */ -int +void cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) { unsigned int chan_index; @@ -373,20 +372,19 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) struct cifs_server_iface *old_iface = NULL; struct cifs_server_iface *last_iface = NULL; struct sockaddr_storage ss; - int rc = 0; spin_lock(&ses->chan_lock); chan_index = cifs_ses_get_chan_index(ses, server); if (chan_index == CIFS_INVAL_CHAN_INDEX) { spin_unlock(&ses->chan_lock); - return 0; + return; } if (ses->chans[chan_index].iface) { old_iface = ses->chans[chan_index].iface; if (old_iface->is_active) { spin_unlock(&ses->chan_lock); - return 1; + return; } } spin_unlock(&ses->chan_lock); @@ -398,8 +396,8 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) spin_lock(&ses->iface_lock); if (!ses->iface_count) { spin_unlock(&ses->iface_lock); - cifs_dbg(VFS, "server %s does not advertise interfaces\n", ses->server->hostname); - return 0; + cifs_dbg(ONCE, "server %s does not advertise interfaces\n", ses->server->hostname); + return; } last_iface = list_last_entry(&ses->iface_list, struct cifs_server_iface, @@ -439,7 +437,6 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) } if (list_entry_is_head(iface, &ses->iface_list, iface_head)) { - rc = 1; iface = NULL; cifs_dbg(FYI, "unable to find a suitable iface\n"); } @@ -454,7 +451,7 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) } spin_unlock(&ses->iface_lock); - return 0; + return; } /* now drop the ref to the current iface */ @@ -472,28 +469,24 @@ cifs_chan_update_iface(struct cifs_ses *ses, struct TCP_Server_Info *server) kref_put(&old_iface->refcount, release_iface); } else if (!chan_index) { /* special case: update interface for primary channel */ - if (iface) { - cifs_dbg(FYI, "referencing primary channel iface: %pIS\n", - &iface->sockaddr); - iface->num_channels++; - iface->weight_fulfilled++; - } + cifs_dbg(FYI, "referencing primary channel iface: %pIS\n", + &iface->sockaddr); + iface->num_channels++; + iface->weight_fulfilled++; } spin_unlock(&ses->iface_lock); - if (iface) { - spin_lock(&ses->chan_lock); - chan_index = cifs_ses_get_chan_index(ses, server); - if (chan_index == CIFS_INVAL_CHAN_INDEX) { - spin_unlock(&ses->chan_lock); - return 0; - } - - ses->chans[chan_index].iface = iface; + spin_lock(&ses->chan_lock); + chan_index = cifs_ses_get_chan_index(ses, server); + if (chan_index == CIFS_INVAL_CHAN_INDEX) { spin_unlock(&ses->chan_lock); + return; } - return rc; + ses->chans[chan_index].iface = iface; + spin_unlock(&ses->chan_lock); + + return; } /* diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index ba734395b0..4852afe392 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -5429,6 +5429,7 @@ struct smb_version_operations smb30_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, @@ -5543,6 +5544,7 @@ struct smb_version_operations smb311_operations = { .tree_connect = SMB2_tcon, .tree_disconnect = SMB2_tdis, .qfs_tcon = smb3_qfs_tcon, + .query_server_interfaces = SMB3_request_interfaces, .is_path_accessible = smb2_is_path_accessible, .can_echo = smb2_can_echo, .echo = SMB2_echo, diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 9d34a55fdb..4d7d0bdf7a 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -409,14 +409,15 @@ skip_sess_setup: spin_unlock(&ses->ses_lock); if (!rc && - (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { + (server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL) && + server->ops->query_server_interfaces) { mutex_unlock(&ses->session_mutex); /* * query server network interfaces, in case they change */ xid = get_xid(); - rc = SMB3_request_interfaces(xid, tcon, false); + rc = server->ops->query_server_interfaces(xid, tcon, false); free_xid(xid); if (rc == -EOPNOTSUPP && ses->chan_count > 1) { @@ -1536,6 +1537,11 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data) &sess_data->buf0_type, CIFS_LOG_ERROR | CIFS_SESS_OP, &rsp_iov); cifs_small_buf_release(sess_data->iov[0].iov_base); + if (rc == 0) + sess_data->ses->expired_pwd = false; + else if ((rc == -EACCES) || (rc == -EKEYEXPIRED) || (rc == -EKEYREVOKED)) + sess_data->ses->expired_pwd = true; + memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec)); return rc; diff --git a/fs/smb/server/smb2misc.c b/fs/smb/server/smb2misc.c index 03dded29a9..727cb49926 100644 --- a/fs/smb/server/smb2misc.c +++ b/fs/smb/server/smb2misc.c @@ -101,13 +101,17 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_sess_setup_req *)hdr)->SecurityBufferLength); break; case SMB2_TREE_CONNECT: - *off = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathOffset), + offsetof(struct smb2_tree_connect_req, Buffer)); *len = le16_to_cpu(((struct smb2_tree_connect_req *)hdr)->PathLength); break; case SMB2_CREATE: { unsigned short int name_off = - le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset); + max_t(unsigned short int, + le16_to_cpu(((struct smb2_create_req *)hdr)->NameOffset), + offsetof(struct smb2_create_req, Buffer)); unsigned short int name_len = le16_to_cpu(((struct smb2_create_req *)hdr)->NameLength); @@ -128,11 +132,15 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_QUERY_INFO: - *off = le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferOffset), + offsetof(struct smb2_query_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_query_info_req *)hdr)->InputBufferLength); break; case SMB2_SET_INFO: - *off = le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset); + *off = max_t(unsigned int, + le16_to_cpu(((struct smb2_set_info_req *)hdr)->BufferOffset), + offsetof(struct smb2_set_info_req, Buffer)); *len = le32_to_cpu(((struct smb2_set_info_req *)hdr)->BufferLength); break; case SMB2_READ: @@ -142,7 +150,7 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, case SMB2_WRITE: if (((struct smb2_write_req *)hdr)->DataOffset || ((struct smb2_write_req *)hdr)->Length) { - *off = max_t(unsigned int, + *off = max_t(unsigned short int, le16_to_cpu(((struct smb2_write_req *)hdr)->DataOffset), offsetof(struct smb2_write_req, Buffer)); *len = le32_to_cpu(((struct smb2_write_req *)hdr)->Length); @@ -153,7 +161,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, *len = le16_to_cpu(((struct smb2_write_req *)hdr)->WriteChannelInfoLength); break; case SMB2_QUERY_DIRECTORY: - *off = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset); + *off = max_t(unsigned short int, + le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameOffset), + offsetof(struct smb2_query_directory_req, Buffer)); *len = le16_to_cpu(((struct smb2_query_directory_req *)hdr)->FileNameLength); break; case SMB2_LOCK: @@ -168,7 +178,9 @@ static int smb2_get_data_area_len(unsigned int *off, unsigned int *len, break; } case SMB2_IOCTL: - *off = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset); + *off = max_t(unsigned int, + le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputOffset), + offsetof(struct smb2_ioctl_req, Buffer)); *len = le32_to_cpu(((struct smb2_ioctl_req *)hdr)->InputCount); break; default: diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0c97d3c860..88db6e207e 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1951,7 +1951,7 @@ int smb2_tree_connect(struct ksmbd_work *work) WORK_BUFFERS(work, req, rsp); - treename = smb_strndup_from_utf16(req->Buffer, + treename = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->PathOffset), le16_to_cpu(req->PathLength), true, conn->local_nls); if (IS_ERR(treename)) { @@ -2704,7 +2704,7 @@ int smb2_open(struct ksmbd_work *work) goto err_out2; } - name = smb2_get_name(req->Buffer, + name = smb2_get_name((char *)req + le16_to_cpu(req->NameOffset), le16_to_cpu(req->NameLength), work->conn->local_nls); if (IS_ERR(name)) { @@ -3828,11 +3828,16 @@ static int process_query_dir_entries(struct smb2_query_dir_private *priv) } ksmbd_kstat.kstat = &kstat; - if (priv->info_level != FILE_NAMES_INFORMATION) - ksmbd_vfs_fill_dentry_attrs(priv->work, - idmap, - dent, - &ksmbd_kstat); + if (priv->info_level != FILE_NAMES_INFORMATION) { + rc = ksmbd_vfs_fill_dentry_attrs(priv->work, + idmap, + dent, + &ksmbd_kstat); + if (rc) { + dput(dent); + continue; + } + } rc = smb2_populate_readdir_entry(priv->work->conn, priv->info_level, @@ -4075,7 +4080,7 @@ int smb2_query_dir(struct ksmbd_work *work) } srch_flag = req->Flags; - srch_ptr = smb_strndup_from_utf16(req->Buffer, + srch_ptr = smb_strndup_from_utf16((char *)req + le16_to_cpu(req->FileNameOffset), le16_to_cpu(req->FileNameLength), 1, conn->local_nls); if (IS_ERR(srch_ptr)) { @@ -4335,7 +4340,8 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp, sizeof(struct smb2_ea_info_req)) return -EINVAL; - ea_req = (struct smb2_ea_info_req *)req->Buffer; + ea_req = (struct smb2_ea_info_req *)((char *)req + + le16_to_cpu(req->InputBufferOffset)); } else { /* need to send all EAs, if no specific EA is requested*/ if (le32_to_cpu(req->Flags) & SL_RETURN_SINGLE_ENTRY) @@ -4480,6 +4486,7 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, struct smb2_file_basic_info *basic_info; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4487,9 +4494,12 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return -EACCES; } + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; + basic_info = (struct smb2_file_basic_info *)rsp->Buffer; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); basic_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); basic_info->LastAccessTime = cpu_to_le64(time); @@ -4504,27 +4514,31 @@ static int get_file_basic_info(struct smb2_query_info_rsp *rsp, return 0; } -static void get_file_standard_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_standard_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_standard_info *sinfo; unsigned int delete_pending; - struct inode *inode; struct kstat stat; + int ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; sinfo = (struct smb2_file_standard_info *)rsp->Buffer; delete_pending = ksmbd_inode_pending_delete(fp); - sinfo->AllocationSize = cpu_to_le64(inode->i_blocks << 9); + sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9); sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); sinfo->DeletePending = delete_pending; sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0; rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_standard_info)); + + return 0; } static void get_file_alignment_info(struct smb2_query_info_rsp *rsp, @@ -4546,11 +4560,11 @@ static int get_file_all_info(struct ksmbd_work *work, struct ksmbd_conn *conn = work->conn; struct smb2_file_all_info *file_info; unsigned int delete_pending; - struct inode *inode; struct kstat stat; int conv_len; char *filename; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { ksmbd_debug(SMB, "no right to read the attributes : 0x%x\n", @@ -4562,8 +4576,10 @@ static int get_file_all_info(struct ksmbd_work *work, if (IS_ERR(filename)) return PTR_ERR(filename); - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -4579,7 +4595,7 @@ static int get_file_all_info(struct ksmbd_work *work, file_info->Attributes = fp->f_ci->m_fattr; file_info->Pad1 = 0; file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending); @@ -4623,10 +4639,10 @@ static void get_file_alternate_info(struct ksmbd_work *work, cpu_to_le32(sizeof(struct smb2_file_alt_name_info) + conv_len); } -static void get_file_stream_info(struct ksmbd_work *work, - struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, - void *rsp_org) +static int get_file_stream_info(struct ksmbd_work *work, + struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, + void *rsp_org) { struct ksmbd_conn *conn = work->conn; struct smb2_file_stream_info *file_info; @@ -4637,9 +4653,13 @@ static void get_file_stream_info(struct ksmbd_work *work, int nbytes = 0, streamlen, stream_name_len, next, idx = 0; int buf_free_len; struct smb2_query_info_req *req = ksmbd_req_buf_next(work); + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_stream_info *)rsp->Buffer; buf_free_len = @@ -4720,29 +4740,37 @@ out: kvfree(xattr_list); rsp->OutputBufferLength = cpu_to_le32(nbytes); + + return 0; } -static void get_file_internal_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_internal_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_internal_info *file_info; struct kstat stat; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); file_info = (struct smb2_file_internal_info *)rsp->Buffer; file_info->IndexNumber = cpu_to_le64(stat.ino); rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_internal_info)); + + return 0; } static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_ntwrk_info *file_info; - struct inode *inode; struct kstat stat; u64 time; + int ret; if (!(fp->daccess & FILE_READ_ATTRIBUTES_LE)) { pr_err("no right to read the attributes : 0x%x\n", @@ -4750,10 +4778,12 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, return -EACCES; } - file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; - inode = file_inode(fp->filp); - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, inode, &stat); + file_info = (struct smb2_file_ntwrk_info *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); time = ksmbd_UnixTimeToNT(stat.atime); @@ -4763,8 +4793,7 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp, time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->Attributes = fp->f_ci->m_fattr; - file_info->AllocationSize = - cpu_to_le64(inode->i_blocks << 9); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size); file_info->Reserved = cpu_to_le32(0); rsp->OutputBufferLength = @@ -4804,14 +4833,17 @@ static void get_file_mode_info(struct smb2_query_info_rsp *rsp, cpu_to_le32(sizeof(struct smb2_file_mode_info)); } -static void get_file_compression_info(struct smb2_query_info_rsp *rsp, - struct ksmbd_file *fp, void *rsp_org) +static int get_file_compression_info(struct smb2_query_info_rsp *rsp, + struct ksmbd_file *fp, void *rsp_org) { struct smb2_file_comp_info *file_info; struct kstat stat; + int ret; - generic_fillattr(file_mnt_idmap(fp->filp), STATX_BASIC_STATS, - file_inode(fp->filp), &stat); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb2_file_comp_info *)rsp->Buffer; file_info->CompressedFileSize = cpu_to_le64(stat.blocks << 9); @@ -4823,6 +4855,8 @@ static void get_file_compression_info(struct smb2_query_info_rsp *rsp, rsp->OutputBufferLength = cpu_to_le32(sizeof(struct smb2_file_comp_info)); + + return 0; } static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, @@ -4844,7 +4878,7 @@ static int get_file_attribute_tag_info(struct smb2_query_info_rsp *rsp, return 0; } -static void find_file_posix_info(struct smb2_query_info_rsp *rsp, +static int find_file_posix_info(struct smb2_query_info_rsp *rsp, struct ksmbd_file *fp, void *rsp_org) { struct smb311_posix_qinfo *file_info; @@ -4852,24 +4886,31 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, struct mnt_idmap *idmap = file_mnt_idmap(fp->filp); vfsuid_t vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid_t vfsgid = i_gid_into_vfsgid(idmap, inode); + struct kstat stat; u64 time; int out_buf_len = sizeof(struct smb311_posix_qinfo) + 32; + int ret; + + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) + return ret; file_info = (struct smb311_posix_qinfo *)rsp->Buffer; file_info->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); file_info->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); file_info->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); file_info->ChangeTime = cpu_to_le64(time); file_info->DosAttributes = fp->f_ci->m_fattr; - file_info->Inode = cpu_to_le64(inode->i_ino); - file_info->EndOfFile = cpu_to_le64(inode->i_size); - file_info->AllocationSize = cpu_to_le64(inode->i_blocks << 9); - file_info->HardLinks = cpu_to_le32(inode->i_nlink); - file_info->Mode = cpu_to_le32(inode->i_mode & 0777); - file_info->DeviceId = cpu_to_le32(inode->i_rdev); + file_info->Inode = cpu_to_le64(stat.ino); + file_info->EndOfFile = cpu_to_le64(stat.size); + file_info->AllocationSize = cpu_to_le64(stat.blocks << 9); + file_info->HardLinks = cpu_to_le32(stat.nlink); + file_info->Mode = cpu_to_le32(stat.mode & 0777); + file_info->DeviceId = cpu_to_le32(stat.rdev); /* * Sids(32) contain two sids(Domain sid(16), UNIX group sid(16)). @@ -4882,6 +4923,8 @@ static void find_file_posix_info(struct smb2_query_info_rsp *rsp, SIDUNIX_GROUP, (struct smb_sid *)&file_info->Sids[16]); rsp->OutputBufferLength = cpu_to_le32(out_buf_len); + + return 0; } static int smb2_get_info_file(struct ksmbd_work *work, @@ -4930,7 +4973,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STANDARD_INFORMATION: - get_file_standard_info(rsp, fp, work->response_buf); + rc = get_file_standard_info(rsp, fp, work->response_buf); break; case FILE_ALIGNMENT_INFORMATION: @@ -4946,11 +4989,11 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_STREAM_INFORMATION: - get_file_stream_info(work, rsp, fp, work->response_buf); + rc = get_file_stream_info(work, rsp, fp, work->response_buf); break; case FILE_INTERNAL_INFORMATION: - get_file_internal_info(rsp, fp, work->response_buf); + rc = get_file_internal_info(rsp, fp, work->response_buf); break; case FILE_NETWORK_OPEN_INFORMATION: @@ -4974,7 +5017,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, break; case FILE_COMPRESSION_INFORMATION: - get_file_compression_info(rsp, fp, work->response_buf); + rc = get_file_compression_info(rsp, fp, work->response_buf); break; case FILE_ATTRIBUTE_TAG_INFORMATION: @@ -4985,7 +5028,7 @@ static int smb2_get_info_file(struct ksmbd_work *work, pr_err("client doesn't negotiate with SMB3.1.1 POSIX Extensions\n"); rc = -EOPNOTSUPP; } else { - find_file_posix_info(rsp, fp, work->response_buf); + rc = find_file_posix_info(rsp, fp, work->response_buf); } break; default: @@ -5398,7 +5441,6 @@ int smb2_close(struct ksmbd_work *work) struct smb2_close_rsp *rsp; struct ksmbd_conn *conn = work->conn; struct ksmbd_file *fp; - struct inode *inode; u64 time; int err = 0; @@ -5453,24 +5495,33 @@ int smb2_close(struct ksmbd_work *work) rsp->Reserved = 0; if (req->Flags == SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB) { + struct kstat stat; + int ret; + fp = ksmbd_lookup_fd_fast(work, volatile_id); if (!fp) { err = -ENOENT; goto out; } - inode = file_inode(fp->filp); + ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (ret) { + ksmbd_fd_put(work, fp); + goto out; + } + rsp->Flags = SMB2_CLOSE_FLAG_POSTQUERY_ATTRIB; - rsp->AllocationSize = S_ISDIR(inode->i_mode) ? 0 : - cpu_to_le64(inode->i_blocks << 9); - rsp->EndOfFile = cpu_to_le64(inode->i_size); + rsp->AllocationSize = S_ISDIR(stat.mode) ? 0 : + cpu_to_le64(stat.blocks << 9); + rsp->EndOfFile = cpu_to_le64(stat.size); rsp->Attributes = fp->f_ci->m_fattr; rsp->CreationTime = cpu_to_le64(fp->create_time); - time = ksmbd_UnixTimeToNT(inode_get_atime(inode)); + time = ksmbd_UnixTimeToNT(stat.atime); rsp->LastAccessTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_mtime(inode)); + time = ksmbd_UnixTimeToNT(stat.mtime); rsp->LastWriteTime = cpu_to_le64(time); - time = ksmbd_UnixTimeToNT(inode_get_ctime(inode)); + time = ksmbd_UnixTimeToNT(stat.ctime); rsp->ChangeTime = cpu_to_le64(time); ksmbd_fd_put(work, fp); } else { @@ -5759,15 +5810,21 @@ static int set_file_allocation_info(struct ksmbd_work *work, loff_t alloc_blks; struct inode *inode; + struct kstat stat; int rc; if (!(fp->daccess & FILE_WRITE_DATA_LE)) return -EACCES; + rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; + alloc_blks = (le64_to_cpu(file_alloc_info->AllocationSize) + 511) >> 9; inode = file_inode(fp->filp); - if (alloc_blks > inode->i_blocks) { + if (alloc_blks > stat.blocks) { smb_break_all_levII_oplock(work, fp, 1); rc = vfs_fallocate(fp->filp, FALLOC_FL_KEEP_SIZE, 0, alloc_blks * 512); @@ -5775,7 +5832,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, pr_err("vfs_fallocate is failed : %d\n", rc); return rc; } - } else if (alloc_blks < inode->i_blocks) { + } else if (alloc_blks < stat.blocks) { loff_t size; /* @@ -5930,6 +5987,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, struct ksmbd_share_config *share) { unsigned int buf_len = le32_to_cpu(req->BufferLength); + char *buffer = (char *)req + le16_to_cpu(req->BufferOffset); switch (req->FileInfoClass) { case FILE_BASIC_INFORMATION: @@ -5937,7 +5995,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_basic_info)) return -EINVAL; - return set_file_basic_info(fp, (struct smb2_file_basic_info *)req->Buffer, share); + return set_file_basic_info(fp, (struct smb2_file_basic_info *)buffer, share); } case FILE_ALLOCATION_INFORMATION: { @@ -5945,7 +6003,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_allocation_info(work, fp, - (struct smb2_file_alloc_info *)req->Buffer); + (struct smb2_file_alloc_info *)buffer); } case FILE_END_OF_FILE_INFORMATION: { @@ -5953,7 +6011,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_end_of_file_info(work, fp, - (struct smb2_file_eof_info *)req->Buffer); + (struct smb2_file_eof_info *)buffer); } case FILE_RENAME_INFORMATION: { @@ -5961,7 +6019,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_rename_info(work, fp, - (struct smb2_file_rename_info *)req->Buffer, + (struct smb2_file_rename_info *)buffer, buf_len); } case FILE_LINK_INFORMATION: @@ -5970,7 +6028,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return smb2_create_link(work, work->tcon->share_conf, - (struct smb2_file_link_info *)req->Buffer, + (struct smb2_file_link_info *)buffer, buf_len, fp->filp, work->conn->local_nls); } @@ -5980,7 +6038,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, return -EINVAL; return set_file_disposition_info(fp, - (struct smb2_file_disposition_info *)req->Buffer); + (struct smb2_file_disposition_info *)buffer); } case FILE_FULL_EA_INFORMATION: { @@ -5993,7 +6051,7 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_ea_info)) return -EINVAL; - return smb2_set_ea((struct smb2_ea_info *)req->Buffer, + return smb2_set_ea((struct smb2_ea_info *)buffer, buf_len, &fp->filp->f_path, true); } case FILE_POSITION_INFORMATION: @@ -6001,14 +6059,14 @@ static int smb2_set_info_file(struct ksmbd_work *work, struct ksmbd_file *fp, if (buf_len < sizeof(struct smb2_file_pos_info)) return -EINVAL; - return set_file_position_info(fp, (struct smb2_file_pos_info *)req->Buffer); + return set_file_position_info(fp, (struct smb2_file_pos_info *)buffer); } case FILE_MODE_INFORMATION: { if (buf_len < sizeof(struct smb2_file_mode_info)) return -EINVAL; - return set_file_mode_info(fp, (struct smb2_file_mode_info *)req->Buffer); + return set_file_mode_info(fp, (struct smb2_file_mode_info *)buffer); } } @@ -6089,7 +6147,7 @@ int smb2_set_info(struct ksmbd_work *work) } rc = smb2_set_info_sec(fp, le32_to_cpu(req->AdditionalInformation), - req->Buffer, + (char *)req + le16_to_cpu(req->BufferOffset), le32_to_cpu(req->BufferLength)); ksmbd_revert_fsids(work); break; @@ -7535,7 +7593,7 @@ static int fsctl_pipe_transceive(struct ksmbd_work *work, u64 id, struct smb2_ioctl_rsp *rsp) { struct ksmbd_rpc_command *rpc_resp; - char *data_buf = (char *)&req->Buffer[0]; + char *data_buf = (char *)req + le32_to_cpu(req->InputOffset); int nbytes = 0; rpc_resp = ksmbd_rpc_ioctl(work->sess, id, data_buf, @@ -7648,6 +7706,7 @@ int smb2_ioctl(struct ksmbd_work *work) u64 id = KSMBD_NO_FID; struct ksmbd_conn *conn = work->conn; int ret = 0; + char *buffer; if (work->next_smb2_rcv_hdr_off) { req = ksmbd_req_buf_next(work); @@ -7670,6 +7729,8 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } + buffer = (char *)req + le32_to_cpu(req->InputOffset); + cnt_code = le32_to_cpu(req->CtlCode); ret = smb2_calc_max_out_buf_len(work, 48, le32_to_cpu(req->MaxOutputResponse)); @@ -7727,7 +7788,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_validate_negotiate_info(conn, - (struct validate_negotiate_info_req *)&req->Buffer[0], + (struct validate_negotiate_info_req *)buffer, (struct validate_negotiate_info_rsp *)&rsp->Buffer[0], in_buf_len); if (ret < 0) @@ -7780,7 +7841,7 @@ int smb2_ioctl(struct ksmbd_work *work) rsp->VolatileFileId = req->VolatileFileId; rsp->PersistentFileId = req->PersistentFileId; fsctl_copychunk(work, - (struct copychunk_ioctl_req *)&req->Buffer[0], + (struct copychunk_ioctl_req *)buffer, le32_to_cpu(req->CtlCode), le32_to_cpu(req->InputCount), req->VolatileFileId, @@ -7793,8 +7854,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - ret = fsctl_set_sparse(work, id, - (struct file_sparse *)&req->Buffer[0]); + ret = fsctl_set_sparse(work, id, (struct file_sparse *)buffer); if (ret < 0) goto out; break; @@ -7817,7 +7877,7 @@ int smb2_ioctl(struct ksmbd_work *work) } zero_data = - (struct file_zero_data_information *)&req->Buffer[0]; + (struct file_zero_data_information *)buffer; off = le64_to_cpu(zero_data->FileOffset); bfz = le64_to_cpu(zero_data->BeyondFinalZero); @@ -7848,7 +7908,7 @@ int smb2_ioctl(struct ksmbd_work *work) } ret = fsctl_query_allocated_ranges(work, id, - (struct file_allocated_range_buffer *)&req->Buffer[0], + (struct file_allocated_range_buffer *)buffer, (struct file_allocated_range_buffer *)&rsp->Buffer[0], out_buf_len / sizeof(struct file_allocated_range_buffer), &nbytes); @@ -7892,7 +7952,7 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; } - dup_ext = (struct duplicate_extents_to_file *)&req->Buffer[0]; + dup_ext = (struct duplicate_extents_to_file *)buffer; fp_in = ksmbd_lookup_fd_slow(work, dup_ext->VolatileFileHandle, dup_ext->PersistentFileHandle); diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index 7c98bf6997..fcaf373cc0 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -457,10 +457,13 @@ int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, } ksmbd_kstat.kstat = &kstat; - ksmbd_vfs_fill_dentry_attrs(work, - idmap, - dentry, - &ksmbd_kstat); + rc = ksmbd_vfs_fill_dentry_attrs(work, + idmap, + dentry, + &ksmbd_kstat); + if (rc) + break; + rc = fn(conn, info_level, d_info, &ksmbd_kstat); if (rc) break; diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index 4277750a6d..a8936aba77 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1669,11 +1669,19 @@ int ksmbd_vfs_fill_dentry_attrs(struct ksmbd_work *work, struct dentry *dentry, struct ksmbd_kstat *ksmbd_kstat) { + struct ksmbd_share_config *share_conf = work->tcon->share_conf; u64 time; int rc; + struct path path = { + .mnt = share_conf->vfs_path.mnt, + .dentry = dentry, + }; - generic_fillattr(idmap, STATX_BASIC_STATS, d_inode(dentry), - ksmbd_kstat->kstat); + rc = vfs_getattr(&path, ksmbd_kstat->kstat, + STATX_BASIC_STATS | STATX_BTIME, + AT_STATX_SYNC_AS_STAT); + if (rc) + return rc; time = ksmbd_UnixTimeToNT(ksmbd_kstat->kstat->ctime); ksmbd_kstat->create_time = time; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 2d2b39f843..abf4a77584 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -261,9 +261,6 @@ static int write_begin_slow(struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } if (PagePrivate(page)) @@ -462,9 +459,6 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, return err; } } - - SetPageUptodate(page); - ClearPageError(page); } err = allocate_budget(c, page, ui, appending); @@ -474,10 +468,8 @@ static int ubifs_write_begin(struct file *file, struct address_space *mapping, * If we skipped reading the page because we were going to * write all of it, then it is not up to date. */ - if (skipped_read) { + if (skipped_read) ClearPageChecked(page); - ClearPageUptodate(page); - } /* * Budgeting failed which means it would have to force * write-back but didn't, because we set the @fast flag in the @@ -568,6 +560,9 @@ static int ubifs_write_end(struct file *file, struct address_space *mapping, goto out; } + if (len == PAGE_SIZE) + SetPageUptodate(page); + if (!PagePrivate(page)) { attach_page_private(page, (void *)1); atomic_long_inc(&c->dirty_pg_cnt); -- cgit v1.2.3