diff options
Diffstat (limited to 'fs')
115 files changed, 2220 insertions, 749 deletions
diff --git a/fs/backing-file.c b/fs/backing-file.c index 080c99696cd0..cc101143f921 100644 --- a/fs/backing-file.c +++ b/fs/backing-file.c @@ -35,7 +35,7 @@ struct file *backing_file_open(const struct file *user_file, int flags, const struct path *real_path, const struct cred *cred) { - const struct path *user_path = &user_file->f_path; + const struct path *user_path = file_user_path(user_file); struct file *f; int error; diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c index 460326d34143..19a1259b3b2f 100644 --- a/fs/btrfs/direct-io.c +++ b/fs/btrfs/direct-io.c @@ -281,17 +281,24 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, em2 = btrfs_create_dio_extent(BTRFS_I(inode), dio_data, start, &file_extent, type); btrfs_dec_nocow_writers(bg); - if (type == BTRFS_ORDERED_PREALLOC) { - btrfs_free_extent_map(em); - *map = em2; - em = em2; - } - if (IS_ERR(em2)) { ret = PTR_ERR(em2); + btrfs_free_extent_map(em); + *map = NULL; goto out; } + /* + * True NOCOW writes don't need to create a new extent map, + * while PREALLOC writes must replace the existing one. + */ + if (em2) { + ASSERT(type == BTRFS_ORDERED_PREALLOC); + btrfs_free_extent_map(em); + *map = em2; + em = em2; + } + dio_data->nocow_done = true; } else { /* Our caller expects us to free the input extent map. */ diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index f032f0858f40..45c4d4a3b29b 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/page-flags.h> +#include <linux/rmap.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/blkdev.h> @@ -299,6 +300,25 @@ static noinline void unlock_delalloc_folio(const struct inode *inode, PAGE_UNLOCK); } +#ifdef CONFIG_BTRFS_DEBUG +/* + * Writeback must write-protect a folio when locking it for IO, before + * anything consumes its data (zeroing, inline copy, compression, + * checksumming). If this fails, then an mmap writer would be able to + * modify the data concurrently while we need it to be stable. + */ +void btrfs_check_folio_write_protected(struct folio *folio) +{ + if (folio_mkclean(folio)) { + const struct btrfs_inode *inode = BTRFS_I(folio->mapping->host); + + DEBUG_WARN("writable mmap PTEs, root %llu ino %llu pos %llu order %u", + btrfs_root_id(inode->root), btrfs_ino(inode), folio_pos(folio), + folio_order(folio)); + } +} +#endif + static noinline int lock_delalloc_folios(struct inode *inode, struct folio *locked_folio, u64 start, u64 end) @@ -332,6 +352,8 @@ static noinline int lock_delalloc_folios(struct inode *inode, folio_unlock(folio); goto out; } + /* Locked for writeback; revoke writable mmap PTEs before using the data. */ + folio_mkclean(folio); range_start = max_t(u64, folio_pos(folio), start); range_len = min_t(u64, folio_next_pos(folio), end + 1) - range_start; btrfs_folio_set_lock(fs_info, folio, range_start, range_len); @@ -1893,6 +1915,13 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, ASSERT(end <= folio_end, "start=%llu len=%u folio_start=%llu folio_size=%zu", start, len, folio_start, folio_size(folio)); + /* + * We are about to checksum and write out the data, so it must not be + * mmap writeable, or we could corrupt the data and end up with invalid + * checksums. + */ + btrfs_check_folio_write_protected(folio); + /* Truncate the submit bitmap to the current range. */ if (start > folio_start) bitmap_clear(bio_ctrl->submit_bitmap, 0, @@ -2703,6 +2732,8 @@ retry: continue; } + /* Locked for writeback; revoke writable mmap PTEs before using the data. */ + folio_mkclean(folio); ret = extent_writepage(folio, bio_ctrl); if (ret < 0) { done = true; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 9896e15ddc40..869925337699 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -255,6 +255,11 @@ bool try_release_extent_mapping(struct folio *folio, gfp_t mask); int try_release_extent_buffer(struct folio *folio); int btrfs_read_folio(struct file *file, struct folio *folio); +#ifdef CONFIG_BTRFS_DEBUG +void btrfs_check_folio_write_protected(struct folio *folio); +#else +static inline void btrfs_check_folio_write_protected(struct folio *folio) { } +#endif void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2534cd9284d5..39a01f9cf6b5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -775,19 +775,28 @@ static inline void inode_should_defrag(struct btrfs_inode *inode, static int extent_range_clear_dirty_for_io(struct btrfs_inode *inode, u64 start, u64 end) { + pgoff_t index = start >> PAGE_SHIFT; const pgoff_t end_index = end >> PAGE_SHIFT; struct folio *folio; int ret = 0; - for (pgoff_t index = start >> PAGE_SHIFT; index <= end_index; index++) { + while (index <= end_index) { folio = filemap_get_folio(inode->vfs_inode.i_mapping, index); if (IS_ERR(folio)) { if (!ret) ret = PTR_ERR(folio); + index++; continue; } + /* + * We are about to compress the folio, so it must not be mmap + * writeable or we could corrupt the data as we attempt to + * compress it. + */ + btrfs_check_folio_write_protected(folio); btrfs_folio_clamp_clear_dirty(inode->root->fs_info, folio, start, end + 1 - start); + index = folio_next_index(folio); folio_put(folio); } return ret; @@ -877,11 +886,6 @@ static void compress_file_range(struct btrfs_work *work) inode_should_defrag(inode, start, end, end - start + 1, SZ_16K); - /* - * We need to call clear_page_dirty_for_io on each page in the range. - * Otherwise applications with the file mmap'd can wander in and change - * the page contents while we are compressing them. - */ ret = extent_range_clear_dirty_for_io(inode, start, end); /* @@ -2317,6 +2321,13 @@ static int run_delalloc_inline(struct btrfs_inode *inode, struct folio *locked_f int ret; ASSERT(folio_pos(locked_folio) == 0); + /* + * If an mmap writer could modify the folio while we copy it into an + * inline extent we might see only part of their modification then + * wrongly mark it clean again after copying, losing that write. So the + * folio must be write protected here. + */ + btrfs_check_folio_write_protected(locked_folio); if (btrfs_inode_can_compress(inode) && inode_need_compress(inode, 0, blocksize, true)) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index baa645e98812..a537036303a4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -356,14 +356,21 @@ int btrfs_fileattr_set(struct mnt_idmap *idmap, inode_flags |= BTRFS_INODE_NODATACOW; } } else { - /* - * Revert back under same assumptions as above - */ - if (S_ISREG(inode->vfs_inode.i_mode)) { - if (inode->vfs_inode.i_size == 0) - inode_flags &= ~(BTRFS_INODE_NODATACOW | - BTRFS_INODE_NODATASUM); - } else { + /* We can only change NODATACOW for zero-sized regular file. */ + if (S_ISREG(inode->vfs_inode.i_mode) && (inode->vfs_inode.i_size == 0)) { + inode_flags &= ~BTRFS_INODE_NODATACOW; + /* + * There is currently no way to change NODATASUM flag + * through fileattr API. If we unconditionally keep the + * current NODATASUM flag, chattr +C then chattr -C will + * keep the NODATASUM flag, and no way to remove that + * flag. + * + * So respect the current mount option for NODATASUM flag. + */ + if (!btrfs_test_opt(fs_info, NODATASUM)) + inode_flags &= ~BTRFS_INODE_NODATASUM; + } else if (!S_ISREG(inode->vfs_inode.i_mode)) { inode_flags &= ~BTRFS_INODE_NODATACOW; } } diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fc5c14b5adad..4eca2b5e4a92 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -5555,6 +5555,24 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) return ret; } +static void release_recovered_fs_roots(struct list_head *roots, bool drop_reloc_refs) +{ + struct btrfs_root *root; + struct btrfs_root *next; + + list_for_each_entry_safe(root, next, roots, reloc_dirty_list) { + list_del_init(&root->reloc_dirty_list); + if (drop_reloc_refs) { + struct btrfs_root *reloc_root = root->reloc_root; + + ASSERT(reloc_root); + root->reloc_root = NULL; + btrfs_put_root(reloc_root); + } + btrfs_put_root(root); + } +} + /* * recover relocation interrupted by system crash. * @@ -5564,6 +5582,7 @@ static noinline_for_stack int mark_garbage_root(struct btrfs_root *root) int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) { LIST_HEAD(reloc_roots); + LIST_HEAD(recovered_roots); struct btrfs_key key; struct btrfs_root *fs_root; struct btrfs_root *reloc_root; @@ -5680,7 +5699,7 @@ int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) ret = PTR_ERR(fs_root); list_add_tail(&reloc_root->root_list, &reloc_roots); btrfs_end_transaction(trans); - goto out_unset; + goto out_drop_reloc_refs; } ret = __add_reloc_root(reloc_root, rc); @@ -5689,15 +5708,17 @@ int btrfs_recover_relocation(struct btrfs_fs_info *fs_info) list_add_tail(&reloc_root->root_list, &reloc_roots); btrfs_put_root(fs_root); btrfs_end_transaction(trans); - goto out_unset; + goto out_drop_reloc_refs; } + ASSERT(list_empty(&fs_root->reloc_dirty_list)); fs_root->reloc_root = btrfs_grab_root(reloc_root); - btrfs_put_root(fs_root); + list_add_tail(&fs_root->reloc_dirty_list, &recovered_roots); } ret = btrfs_commit_transaction(trans); if (ret) - goto out_unset; + goto out_drop_reloc_refs; + release_recovered_fs_roots(&recovered_roots, false); merge_reloc_roots(rc); @@ -5713,6 +5734,8 @@ out_clean: ret2 = clean_dirty_subvols(rc); if (ret2 < 0 && !ret) ret = ret2; +out_drop_reloc_refs: + release_recovered_fs_roots(&recovered_roots, true); out_unset: unset_reloc_control(rc); reloc_chunk_end(fs_info); diff --git a/fs/buffer.c b/fs/buffer.c index 9af5f061a1f8..955ab07b34eb 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2177,6 +2177,7 @@ void block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; + bool uptodate = folio_test_uptodate(folio); unsigned blocksize; struct buffer_head *bh, *head; @@ -2199,6 +2200,8 @@ void block_commit_write(struct folio *folio, size_t from, size_t to) clear_buffer_new(bh); block_start = block_end; + if (uptodate && block_start >= to) + break; bh = bh->b_this_page; } while (bh != head); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index ecf33b66610c..e9f561bedf47 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1426,6 +1426,16 @@ void ceph_shift_unused_folios_left(struct folio_batch *fbatch) fbatch->nr = n; } +static void ceph_undo_wrbuffer_claim(struct inode *inode, struct folio *folio) +{ + struct ceph_snap_context *snapc = folio_detach_private(folio); + + if (!snapc) + return; + ceph_put_wrbuffer_cap_refs(ceph_inode(inode), 1, snapc); + ceph_put_snap_context(snapc); +} + static int ceph_submit_write(struct address_space *mapping, struct writeback_control *wbc, @@ -1489,6 +1499,7 @@ new_request: if (!page) continue; + ceph_undo_wrbuffer_claim(inode, page_folio(page)); redirty_page_for_writepage(wbc, page); unlock_page(page); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index d7283fb54cec..bb5ef0eacd8f 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -979,6 +979,27 @@ int __ceph_caps_revoking_other(struct ceph_inode_info *ci, return 0; } +/* + * Return true if any cap of this inode holds caps which the MDS has + * revoked, but which we have not released yet. + */ +static bool __ceph_is_any_revoking(const struct ceph_inode_info *ci) +{ + const struct rb_node *p; + + lockdep_assert_held(&ci->i_ceph_lock); + + for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) { + const struct ceph_cap *cap = + rb_entry(p, struct ceph_cap, ci_node); + + if (cap->implemented & ~cap->issued) + return true; + } + + return false; +} + int __ceph_caps_used(struct ceph_inode_info *ci) { int used = 0; @@ -1421,6 +1442,9 @@ static void __prep_cap(struct cap_msg_args *arg, struct ceph_cap *cap, cap->implemented &= cap->issued | used; cap->mds_wanted = want; + if ((ci->i_ceph_flags & CEPH_I_FLUSH_FORCE) != 0 && !__ceph_is_any_revoking(ci)) + clear_bit(CEPH_I_FLUSH_FORCE_BIT, &ci->i_ceph_flags); + arg->session = cap->session; arg->ino = ceph_vino(inode).ino; arg->cid = cap->cap_id; @@ -2038,6 +2062,14 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) if (ci->i_ceph_flags & CEPH_I_FLUSH) flags |= CHECK_CAPS_FLUSH; + /* + * A revoke whose response was deferred (see handle_cap_grant()) must + * still be acknowledged. Replay the forced flush here so that even a + * check triggered by writeback/invalidation completion sends a cap + * message to the MDS. + */ + if (ci->i_ceph_flags & CEPH_I_FLUSH_FORCE) + flags |= CHECK_CAPS_FLUSH_FORCE; retry: /* Caps wanted by virtue of active open files. */ file_wanted = __ceph_caps_file_wanted(ci); @@ -2589,9 +2621,14 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } } - list_for_each_entry(cf, &ci->i_cap_flush_list, i_list) { - if (cf->tid < first_tid) + cf = list_first_entry(&ci->i_cap_flush_list, struct ceph_cap_flush, i_list); + while (&cf->i_list != &ci->i_cap_flush_list) { + struct ceph_cap_flush *next; + + if (cf->tid < first_tid) { + cf = list_next_entry(cf, i_list); continue; + } cap = ci->i_auth_cap; if (!(cap && cap->session == session)) { @@ -2601,6 +2638,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } first_tid = cf->tid + 1; + next = list_next_entry(cf, i_list); if (!cf->is_capsnap) { struct cap_msg_args arg; @@ -2641,6 +2679,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc, } spin_lock(&ci->i_ceph_lock); + cf = next; } } @@ -3757,13 +3796,30 @@ static void handle_cap_grant(struct inode *inode, BUG_ON(cap->issued & ~cap->implemented); /* don't let check_caps skip sending a response to MDS for revoke msgs */ - if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { - cap->mds_wanted = 0; - flags |= CHECK_CAPS_FLUSH_FORCE; - if (cap == ci->i_auth_cap) - check_caps = 1; /* check auth cap only */ - else - check_caps = 2; /* check all caps */ + if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + if (revoke_wait) { + /* + * We can't ack the revoke yet: the response is deferred + * until the writeback or cache invalidation queued above + * completes. Set the CEPH_I_FLUSH_FORCE flag to remember + * that a forced cap message is owed so that deferred + * completion (ceph_put_wrbuffer_cap_refs() or the + * invalidate worker, both of which call ceph_check_caps()) + * actually sends one, even if by then the revoked caps look + * unused, the inode is retaining caps, or the MDS has + * re-granted them. Without this, the cap message is never + * sent and the MDS hangs ("isn't responding to + * mclientcaps(revoke)"). + */ + set_bit(CEPH_I_FLUSH_FORCE_BIT, &ci->i_ceph_flags); + } else { + cap->mds_wanted = 0; + flags |= CHECK_CAPS_FLUSH_FORCE; + if (cap == ci->i_auth_cap) + check_caps = 1; /* check auth cap only */ + else + check_caps = 2; /* check all caps */ + } } if (extra_info->inline_version > 0 && diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index ef9e92e362d3..40326517481c 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1764,11 +1764,11 @@ static int __dir_lease_check(const struct dentry *dentry, if (ret > 0) { if (time_before(jiffies, di->time + lwc->dir_lease_ttl)) return STOP; + if (!lwc->expire_dir_lease) + return KEEP; /* Move dentry to tail of dir lease list if we don't want * to delete it. So dentries in the list are checked in a * round robin manner */ - if (!lwc->expire_dir_lease) - return TOUCH; if (dentry->d_lockref.count > 0 || (di->flags & CEPH_DENTRY_REFERENCED)) return TOUCH; @@ -1795,7 +1795,7 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.dir_lease = false; lwc.nr_to_scan = CEPH_CAPS_PER_RELEASE * 2; freed = __dentry_leases_walk(mdsc, &lwc); - if (!lwc.nr_to_scan) /* more invalid leases */ + if (freed > 0 && !lwc.nr_to_scan) /* more invalid leases */ return -EAGAIN; if (lwc.nr_to_scan < CEPH_CAPS_PER_RELEASE) @@ -1805,6 +1805,10 @@ int ceph_trim_dentries(struct ceph_mds_client *mdsc) lwc.expire_dir_lease = freed < count; lwc.dir_lease_ttl = mdsc->fsc->mount_options->caps_wanted_delay_max * HZ; freed +=__dentry_leases_walk(mdsc, &lwc); + if (freed == 0 && count == 0) + /* no progress possible currently, retry futile */ + return 0; + if (!lwc.nr_to_scan) /* more to check */ return -EAGAIN; diff --git a/fs/ceph/export.c b/fs/ceph/export.c index b2f2af104679..debb9634b9e3 100644 --- a/fs/ceph/export.c +++ b/fs/ceph/export.c @@ -442,6 +442,16 @@ static struct dentry *ceph_fh_to_parent(struct super_block *sb, return dentry; } +static int ceph_export_copy_name(char *name, const char *src, u32 len) +{ + if (len > NAME_MAX) + return -ENAMETOOLONG; + + memcpy(name, src, len); + name[len] = '\0'; + return 0; +} + static int __get_snap_name(struct dentry *parent, char *name, struct dentry *child) { @@ -513,9 +523,8 @@ static int __get_snap_name(struct dentry *parent, char *name, BUG_ON(!rde->inode.in); if (ceph_snap(inode) == le64_to_cpu(rde->inode.in->snapid)) { - memcpy(name, rde->name, rde->name_len); - name[rde->name_len] = '\0'; - err = 0; + err = ceph_export_copy_name(name, rde->name, + rde->name_len); goto out; } } @@ -580,8 +589,8 @@ static int ceph_get_name(struct dentry *parent, char *name, rinfo = &req->r_reply_info; if (!IS_ENCRYPTED(dir)) { - memcpy(name, rinfo->dname, rinfo->dname_len); - name[rinfo->dname_len] = 0; + err = ceph_export_copy_name(name, rinfo->dname, + rinfo->dname_len); } else { struct fscrypt_str oname = FSTR_INIT(NULL, 0); struct ceph_fname fname = { .dir = dir, @@ -595,10 +604,9 @@ static int ceph_get_name(struct dentry *parent, char *name, goto out; err = ceph_fname_to_usr(&fname, NULL, &oname, NULL); - if (!err) { - memcpy(name, oname.name, oname.len); - name[oname.len] = 0; - } + if (!err) + err = ceph_export_copy_name(name, oname.name, + oname.len); ceph_fname_free_buffer(dir, &oname); } out: diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 3c692ad02c85..ec886ca9b526 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -615,10 +615,36 @@ bad: #define DELEGATED_INO_AVAILABLE xa_mk_value(1) +static int ceph_insert_deleg_ino(struct ceph_mds_session *s, u64 ino) +{ + struct ceph_client *cl = s->s_mdsc->fsc->client; + int err; + + /* + * Cap how many delegated inodes a single session may hold. This is + * the only place that grows the count, so atomic_add_unless() bounds + * it at exactly CEPH_MAX_DELEG_INOS; s_num_deleg_inos can never exceed + * that. + */ + if (!atomic_add_unless(&s->s_num_deleg_inos, 1, CEPH_MAX_DELEG_INOS)) { + pr_warn_ratelimited_client(cl, + "MDS session already holds %d delegated inodes\n", + CEPH_MAX_DELEG_INOS); + return -EOVERFLOW; + } + + err = xa_insert(&s->s_delegated_inos, ino, DELEGATED_INO_AVAILABLE, + GFP_KERNEL); + if (err) + atomic_dec(&s->s_num_deleg_inos); + return err; +} + static int ceph_parse_deleg_inos(void **p, void *end, struct ceph_mds_session *s) { struct ceph_client *cl = s->s_mdsc->fsc->client; + u64 msg_deleg_inos = 0; u32 sets; ceph_decode_32_safe(p, end, sets, bad); @@ -636,16 +662,34 @@ static int ceph_parse_deleg_inos(void **p, void *end, start, len); continue; } + + /* + * Bound the number of inodes one reply may delegate. + * ceph_insert_deleg_ino() separately caps the per-session + * population, so this only has to stop one reply from spinning + * the insert loop under an attacker-controlled len. + */ + if (len > (u64)CEPH_MAX_DELEG_INOS || + msg_deleg_inos > (u64)CEPH_MAX_DELEG_INOS - len) { + pr_warn_ratelimited_client(cl, + "MDS reply delegates too many inodes (have %llu, +%llu, max %d)\n", + msg_deleg_inos, len, CEPH_MAX_DELEG_INOS); + return -EIO; + } + msg_deleg_inos += len; + while (len--) { - int err = xa_insert(&s->s_delegated_inos, start++, - DELEGATED_INO_AVAILABLE, - GFP_KERNEL); + int err = ceph_insert_deleg_ino(s, start++); + if (!err) { doutc(cl, "added delegated inode 0x%llx\n", start - 1); } else if (err == -EBUSY) { pr_warn_client(cl, "MDS delegated inode 0x%llx more than once.\n", start - 1); + } else if (err == -EOVERFLOW) { + /* ceph_insert_deleg_ino() already warned. */ + return -EIO; } else { return err; } @@ -663,16 +707,17 @@ u64 ceph_get_deleg_ino(struct ceph_mds_session *s) xa_for_each(&s->s_delegated_inos, ino, val) { val = xa_erase(&s->s_delegated_inos, ino); - if (val == DELEGATED_INO_AVAILABLE) + if (val == DELEGATED_INO_AVAILABLE) { + atomic_dec(&s->s_num_deleg_inos); return ino; + } } return 0; } int ceph_restore_deleg_ino(struct ceph_mds_session *s, u64 ino) { - return xa_insert(&s->s_delegated_inos, ino, DELEGATED_INO_AVAILABLE, - GFP_KERNEL); + return ceph_insert_deleg_ino(s, ino); } #else /* BITS_PER_LONG == 64 */ /* @@ -1059,6 +1104,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, INIT_LIST_HEAD(&s->s_waiting); INIT_LIST_HEAD(&s->s_unsafe); xa_init(&s->s_delegated_inos); + atomic_set(&s->s_num_deleg_inos, 0); INIT_LIST_HEAD(&s->s_cap_releases); INIT_WORK(&s->s_cap_release_work, ceph_cap_release_work); @@ -4441,7 +4487,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for path\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.path, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.path, + _len, bad); /* Remove the tailing '/' */ while (_len && cap_auths[i].match.path[_len - 1] == '/') { @@ -4458,7 +4506,9 @@ static void handle_session(struct ceph_mds_session *session, pr_err_client(cl, "No memory for fs_name\n"); goto fail; } - ceph_decode_copy(&p, cap_auths[i].match.fs_name, _len); + ceph_decode_copy_safe(&p, end, + cap_auths[i].match.fs_name, + _len, bad); } ceph_decode_8_safe(&p, end, cap_auths[i].match.root_squash, bad); @@ -5106,6 +5156,7 @@ static int send_mds_reconnect(struct ceph_mds_client *mdsc, /* Serialized by s_mutex against concurrent ceph_get_deleg_ino(). */ xa_destroy(&session->s_delegated_inos); + atomic_set(&session->s_num_deleg_inos, 0); if (session->s_state == CEPH_MDS_SESSION_CLOSED || session->s_state == CEPH_MDS_SESSION_REJECTED) { pr_info_client(cl, "mds%d skipping reconnect, session %s\n", @@ -5834,9 +5885,11 @@ static void check_new_map(struct ceph_mds_client *mdsc, ceph_mdsmap_get_addr(newmap, i), sizeof(struct ceph_entity_addr))) { /* just close it */ + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); mutex_lock(&s->s_mutex); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); ceph_con_close(&s->s_con); mutex_unlock(&s->s_mutex); s->s_state = CEPH_MDS_SESSION_RESTARTING; @@ -5851,6 +5904,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, newstate >= CEPH_MDS_STATE_RECONNECT) { int rc; + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); clear_bit(i, targets); rc = send_mds_reconnect(mdsc, s); @@ -5859,6 +5913,7 @@ static void check_new_map(struct ceph_mds_client *mdsc, "mds%d reconnect failed: %d\n", i, rc); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); } /* @@ -5871,9 +5926,11 @@ static void check_new_map(struct ceph_mds_client *mdsc, pr_info_client(cl, "mds%d recovery completed\n", s->s_mds); kick_requests(mdsc, i); + ceph_get_mds_session(s); mutex_unlock(&mdsc->mutex); mutex_lock(&s->s_mutex); mutex_lock(&mdsc->mutex); + ceph_put_mds_session(s); ceph_kick_flushing_caps(mdsc, s); mutex_unlock(&s->s_mutex); wake_up_session_caps(s, RECONNECT); diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 0ece4c9e3529..3c62e3c3530b 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -300,6 +300,7 @@ struct ceph_mds_session { struct list_head s_waiting; /* waiting requests */ struct list_head s_unsafe; /* unsafe requests */ struct xarray s_delegated_inos; + atomic_t s_num_deleg_inos; }; /* diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c index 450a4dc9662e..53079ef34c3a 100644 --- a/fs/ceph/mdsmap.c +++ b/fs/ceph/mdsmap.c @@ -3,6 +3,7 @@ #include <linux/bug.h> #include <linux/err.h> +#include <linux/overflow.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/types.h> @@ -126,6 +127,7 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, u8 mdsmap_v; u16 mdsmap_ev; u32 target; + size_t export_targets_len; m = kzalloc_obj(*m, GFP_NOFS); if (!m) @@ -224,8 +226,11 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, *p += namelen; if (info_v >= 2) { ceph_decode_32_safe(p, end, num_export_targets, bad); + export_targets_len = size_mul(num_export_targets, + sizeof(u32)); + ceph_decode_need(p, end, export_targets_len, bad); pexport_targets = *p; - *p += num_export_targets * sizeof(u32); + *p += export_targets_len; } else { num_export_targets = 0; } @@ -264,6 +269,10 @@ struct ceph_mdsmap *ceph_mdsmap_decode(struct ceph_mds_client *mdsc, void **p, goto nomem; for (j = 0; j < num_export_targets; j++) { target = ceph_decode_32(&pexport_targets); + if (target >= CEPH_MAX_MDS) { + err = -EIO; + goto corrupt; + } info->export_targets[j] = target; } } else { diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 1d6aab060780..38f86294182c 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -641,6 +641,15 @@ static inline int ceph_ino_compare(struct inode *inode, void *data) #define CEPH_MDS_INO_LOG_OFFSET (2 * CEPH_MAX_MDS) #define CEPH_INO_SYSTEM_BASE ((6*CEPH_MAX_MDS) + (CEPH_MAX_MDS * CEPH_NUM_STRAY)) +/* + * Upper bound on the number of delegated inodes a single MDS session may + * hold. The MDS normally hands out a small preallocation window (the + * userspace mds_client_prealloc_inos option defaults to 1000) and refills + * it as the client consumes entries. This leaves generous headroom while + * bounding the CPU and memory a malformed delegation interval can consume. + */ +#define CEPH_MAX_DELEG_INOS 8192 + static inline bool ceph_vino_is_reserved(const struct ceph_vino vino) { if (vino.ino >= CEPH_INO_SYSTEM_BASE || @@ -687,6 +696,10 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ASYNC_CREATE_BIT (12) /* async create in flight for this */ #define CEPH_I_SHUTDOWN_BIT (13) /* inode is no longer usable */ #define CEPH_I_ASYNC_CHECK_CAPS_BIT (14) /* check caps after async creating finishes */ +#define CEPH_I_FLUSH_FORCE_BIT (15) /* a revoke's response was deferred; + * force a cap message to the MDS once + * the deferred work completes + */ #define CEPH_I_DIR_ORDERED (1 << CEPH_I_DIR_ORDERED_BIT) #define CEPH_I_FLUSH (1 << CEPH_I_FLUSH_BIT) @@ -699,6 +712,7 @@ static inline struct inode *ceph_find_inode(struct super_block *sb, #define CEPH_I_ODIRECT (1 << CEPH_I_ODIRECT_BIT) #define CEPH_I_ASYNC_CREATE (1 << CEPH_I_ASYNC_CREATE_BIT) #define CEPH_I_SHUTDOWN (1 << CEPH_I_SHUTDOWN_BIT) +#define CEPH_I_FLUSH_FORCE (1 << CEPH_I_FLUSH_FORCE_BIT) /* * Masks of ceph inode work. diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 860fc8e1867d..cc4ffbbcb719 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -848,6 +848,7 @@ start: name = p; p += len; ceph_decode_32_safe(&p, end, len, bad); + ceph_decode_need(&p, end, len, bad); val = p; p += len; diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index edd6aafbfbaa..08de6652a4f3 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -273,7 +273,8 @@ static int debugfs_locked_down(struct inode *inode, (!real_fops || (!real_fops->unlocked_ioctl && !real_fops->compat_ioctl && - !real_fops->mmap))) + !real_fops->mmap && + !real_fops->mmap_prepare))) return 0; if (security_locked_down(LOCKDOWN_DEBUGFS)) diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 74b02b55e3f6..e67119b6029c 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1197,7 +1197,7 @@ static int ecryptfs_read_headers_virt(char *page_virt, } else set_default_header_data(crypt_stat); rc = ecryptfs_parse_packet_set(crypt_stat, (page_virt + offset), - ecryptfs_dentry); + PAGE_SIZE - offset, ecryptfs_dentry); out: return rc; } diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index f4f56a92bd56..7d2488a10b17 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -580,7 +580,8 @@ int ecryptfs_generate_key_packet_set(char *dest_base, size_t *len, size_t max); int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, - unsigned char *src, struct dentry *ecryptfs_dentry); + unsigned char *src, size_t src_size, + struct dentry *ecryptfs_dentry); int ecryptfs_truncate(struct dentry *dentry, loff_t new_length); ssize_t ecryptfs_getxattr_lower(struct dentry *lower_dentry, struct inode *lower_inode, diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index ebebc9551f1f..51651314b7a6 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -894,6 +894,12 @@ ecryptfs_parse_tag_70_packet(char **filename, size_t *filename_size, "rc = [%d]\n", __func__, rc); goto out; } + if (s->parsed_tag_70_packet_size < (ECRYPTFS_SIG_SIZE + 2)) { + ecryptfs_printk(KERN_WARNING, "Invalid packet size [%zd]\n", + s->parsed_tag_70_packet_size); + rc = -EINVAL; + goto out; + } s->block_aligned_filename_size = (s->parsed_tag_70_packet_size - ECRYPTFS_SIG_SIZE - 1); if ((1 + s->packet_size_len + s->parsed_tag_70_packet_size) @@ -1384,10 +1390,20 @@ parse_tag_3_packet(struct ecryptfs_crypt_stat *crypt_stat, } (*new_auth_tok)->session_key.encrypted_key_size = (body_size - (ECRYPTFS_SALT_SIZE + 5)); + /* + * Although encrypted_key_size is copied into the + * encrypted_key[ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES] buffer here, + * it later bounds operations on a smaller buffer: + * decrypt_passphrase_encrypted_session_key() sets decrypted_key_size = + * encrypted_key_size and decrypts into + * decrypted_key[ECRYPTFS_MAX_KEY_BYTES], then memcpy's into + * crypt_stat->key[ECRYPTFS_MAX_KEY_BYTES]. Limit to + * ECRYPTFS_MAX_KEY_BYTES to protect those smaller buffers. + */ if ((*new_auth_tok)->session_key.encrypted_key_size - > ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES) { + > ECRYPTFS_MAX_KEY_BYTES) { printk(KERN_WARNING "Tag 3 packet contains key larger " - "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n"); + "than ECRYPTFS_MAX_KEY_BYTES\n"); rc = -EINVAL; goto out_free; } @@ -1537,7 +1553,7 @@ parse_tag_11_packet(unsigned char *data, unsigned char *contents, } (*packet_size) += length_size; (*tag_11_contents_size) = (body_size - 14); - if (unlikely((*packet_size) + body_size + 1 > max_packet_size)) { + if (unlikely((*packet_size) + body_size > max_packet_size)) { printk(KERN_ERR "Packet size exceeds max\n"); rc = -EINVAL; goto out; @@ -1704,6 +1720,7 @@ out: * ecryptfs_parse_packet_set * @crypt_stat: The cryptographic context * @src: Virtual address of region of memory containing the packets + * @src_size: Size of the packet set buffer * @ecryptfs_dentry: The eCryptfs dentry associated with the packet set * * Get crypt_stat to have the file's session key if the requisite key @@ -1714,7 +1731,7 @@ out: * conditions. */ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, - unsigned char *src, + unsigned char *src, size_t src_size, struct dentry *ecryptfs_dentry) { size_t i = 0; @@ -1736,7 +1753,11 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, * added the our &auth_tok_list */ next_packet_is_auth_tok_packet = 1; while (next_packet_is_auth_tok_packet) { - size_t max_packet_size = ((PAGE_SIZE - 8) - i); + size_t max_packet_size; + + if (i >= src_size) + break; + max_packet_size = src_size - i; switch (src[i]) { case ECRYPTFS_TAG_3_PACKET_TYPE: @@ -1751,12 +1772,16 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } rc = parse_tag_11_packet((unsigned char *)&src[i], sig_tmp_space, ECRYPTFS_SIG_SIZE, &tag_11_contents_size, &tag_11_packet_size, - max_packet_size); + src_size - i); if (rc) { ecryptfs_printk(KERN_ERR, "No valid " "(ecryptfs-specific) literal " @@ -1768,6 +1793,10 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += tag_11_packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } if (ECRYPTFS_SIG_SIZE != tag_11_contents_size) { ecryptfs_printk(KERN_ERR, "Expected " "signature of size [%d]; " @@ -1793,6 +1822,10 @@ int ecryptfs_parse_packet_set(struct ecryptfs_crypt_stat *crypt_stat, goto out_wipe_list; } i += packet_size; + if (i > src_size) { + rc = -EIO; + goto out_wipe_list; + } crypt_stat->flags |= ECRYPTFS_ENCRYPTED; break; case ECRYPTFS_TAG_11_PACKET_TYPE: diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index 03c60f0850ca..73c7b8215e66 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -166,6 +166,7 @@ int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon) mutex_unlock(&daemon->mux); goto out; } + mutex_lock(&ecryptfs_msg_ctx_lists_mux); list_for_each_entry_safe(msg_ctx, msg_ctx_tmp, &daemon->msg_ctx_out_queue, daemon_out_list) { list_del(&msg_ctx->daemon_out_list); @@ -174,6 +175,7 @@ int ecryptfs_exorcise_daemon(struct ecryptfs_daemon *daemon) "the out queue of a dying daemon\n", __func__); ecryptfs_msg_ctx_alloc_to_free(msg_ctx); } + mutex_unlock(&ecryptfs_msg_ctx_lists_mux); hlist_del(&daemon->euid_chain); mutex_unlock(&daemon->mux); kfree_sensitive(daemon); @@ -284,9 +286,16 @@ ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type, mutex_unlock(&ecryptfs_msg_ctx_lists_mux); rc = ecryptfs_send_miscdev(data, data_len, *msg_ctx, msg_type, 0, daemon); - if (rc) + if (rc) { printk(KERN_ERR "%s: Error attempting to send message to " "userspace daemon; rc = [%d]\n", __func__, rc); + mutex_lock(&ecryptfs_msg_ctx_lists_mux); + mutex_lock(&(*msg_ctx)->mux); + ecryptfs_msg_ctx_alloc_to_free(*msg_ctx); + mutex_unlock(&(*msg_ctx)->mux); + mutex_unlock(&ecryptfs_msg_ctx_lists_mux); + *msg_ctx = NULL; + } out: return rc; } diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index 5a7d08149922..68804399a5df 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -360,7 +360,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, u32 seq; size_t packet_size, packet_size_length; char *data; - unsigned char packet_size_peek[ECRYPTFS_MAX_PKT_LEN_SIZE]; + unsigned char packet_size_peek[ECRYPTFS_MAX_PKT_LEN_SIZE] = { }; ssize_t rc; if (count == 0) { @@ -376,7 +376,8 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, } if (copy_from_user(packet_size_peek, &buf[PKT_LEN_OFFSET], - sizeof(packet_size_peek))) { + min_t(size_t, count - PKT_LEN_OFFSET, + sizeof(packet_size_peek)))) { printk(KERN_WARNING "%s: Error while inspecting packet size\n", __func__); return -EFAULT; diff --git a/fs/ecryptfs/super.c b/fs/ecryptfs/super.c index 3bc21d677564..686b2b4a9cb5 100644 --- a/fs/ecryptfs/super.c +++ b/fs/ecryptfs/super.c @@ -150,6 +150,13 @@ static int ecryptfs_show_options(struct seq_file *m, struct dentry *root) if (mount_crypt_stat->global_default_cipher_key_size) seq_printf(m, ",ecryptfs_key_bytes=%zd", mount_crypt_stat->global_default_cipher_key_size); + if (mount_crypt_stat->flags & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES) { + seq_printf(m, ",ecryptfs_fn_cipher=%s", + mount_crypt_stat->global_default_fn_cipher_name); + if (mount_crypt_stat->global_default_fn_cipher_key_bytes) + seq_printf(m, ",ecryptfs_fn_key_bytes=%zd", + mount_crypt_stat->global_default_fn_cipher_key_bytes); + } if (mount_crypt_stat->flags & ECRYPTFS_PLAINTEXT_PASSTHROUGH_ENABLED) seq_printf(m, ",ecryptfs_passthrough"); if (mount_crypt_stat->flags & ECRYPTFS_XATTR_METADATA_ENABLED) diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 733c19571f1c..8d33f11db2a1 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -89,12 +89,30 @@ static int efivarfs_statfs(struct dentry *dentry, struct kstatfs *buf) /* Some UEFI firmware does not implement QueryVariableInfo() */ storage_space = remaining_space = 0; if (efi_rt_services_supported(EFI_RT_SUPPORTED_QUERY_VARIABLE_INFO)) { - status = efivar_query_variable_info(attr, &storage_space, - &remaining_space, - &max_variable_size); - if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED) - pr_warn_ratelimited("query_variable_info() failed: 0x%lx\n", - status); + static DEFINE_RATELIMIT_STATE(_rs, 2 * HZ, 5); + static u64 storage, remaining; + static DEFINE_SPINLOCK(lock); + + if (!__ratelimit(&_rs)) { + ratelimit_set_flags(&_rs, RATELIMIT_MSG_ON_RELEASE); + + spin_lock(&lock); + storage_space = storage; + remaining_space = remaining; + spin_unlock(&lock); + } else { + status = efivar_query_variable_info(attr, &storage_space, + &remaining_space, + &max_variable_size); + if (status != EFI_SUCCESS && status != EFI_UNSUPPORTED) + pr_warn("query_variable_info() failed: 0x%lx\n", + status); + + spin_lock(&lock); + storage = storage_space; + remaining = remaining_space; + spin_unlock(&lock); + } } /* diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c index a0ce9226bc02..6b9bfa2ef3b6 100644 --- a/fs/erofs/zutil.c +++ b/fs/erofs/zutil.c @@ -79,6 +79,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages) for (i = 0; i < z_erofs_gbuf_count; ++i) { gbuf = &z_erofs_gbufpool[i]; + if (gbuf->nrpages >= nrpages) + continue; tmp_pages = kzalloc_objs(*tmp_pages, nrpages); if (!tmp_pages) goto out; diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 29808629cce5..269b1c9fba5f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1258,12 +1258,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) filemap_invalidate_unlock(inode->i_mapping); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); - if (inode_needs_sync(inode)) { - mmb_sync(&EXT2_I(inode)->i_metadata_bhs); + mark_inode_dirty(inode); + if (inode_needs_sync(inode)) sync_inode_metadata(inode, 1); - } else { - mark_inode_dirty(inode); - } return 0; } diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index e55d16abf422..be63f89402a3 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -777,6 +777,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, /* Update the inode. */ EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; inode_set_ctime_current(inode); + mark_inode_dirty(inode); if (IS_SYNC(inode)) { error = sync_inode_metadata(inode, 1); /* In case sync failed due to ENOSPC the inode was actually @@ -789,8 +790,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh, } goto cleanup; } - } else - mark_inode_dirty(inode); + } error = 0; if (old_bh && old_bh != new_bh) { diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 3027ef53af21..2a0fea26a99a 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -133,7 +133,11 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) ret = fat_ent_read(inode, &fatent, last); if (ret >= 0) { int wait = inode_needs_sync(inode); + int old = ret; + ret = fat_ent_write(inode, &fatent, new_dclus, wait); + if (ret < 0) + fat_ent_write(inode, &fatent, old, wait); fatent_brelse(&fatent); } if (ret < 0) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 95df51880db2..e7da62a7293d 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -75,6 +75,9 @@ void fuse_chan_set_initialized(struct fuse_chan *fch, struct fuse_chan_param *pa fch->minor = param->minor; fch->max_write = param->max_write; fch->max_pages = param->max_pages; + + if (param->io_uring_enabled) + fuse_uring_conn_init(fch); } /* Make sure stores before this are seen on another CPU */ @@ -415,11 +418,6 @@ void fuse_chan_set_fc(struct fuse_chan *fch, struct fuse_conn *fc) fch->conn = fc; } -void fuse_chan_io_uring_enable(struct fuse_chan *fch) -{ - fch->io_uring = 1; -} - void fuse_pqueue_init(struct fuse_pqueue *fpq) { spin_lock_init(&fpq->lock); diff --git a/fs/fuse/dev.h b/fs/fuse/dev.h index aed69fd14c41..8d25378c0918 100644 --- a/fs/fuse/dev.h +++ b/fs/fuse/dev.h @@ -22,6 +22,7 @@ struct fuse_chan_param { unsigned int minor; unsigned int max_write; unsigned int max_pages; + bool io_uring_enabled; }; struct fuse_chan *fuse_chan_new(void); @@ -34,7 +35,6 @@ void fuse_chan_max_background_set(struct fuse_chan *fch, unsigned int val); unsigned int fuse_chan_num_waiting(struct fuse_chan *fch); void fuse_chan_set_fc(struct fuse_chan *fch, struct fuse_conn *fc); void fuse_chan_set_initialized(struct fuse_chan *fch, struct fuse_chan_param *param); -void fuse_chan_io_uring_enable(struct fuse_chan *fch); ssize_t fuse_chan_send(struct fuse_chan *fch, struct fuse_args *args); int fuse_chan_send_bg(struct fuse_chan *fch, struct fuse_args *args, gfp_t gfp_flags); int fuse_chan_send_notify_reply(struct fuse_chan *fch, struct fuse_args *args, u64 unique); diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c index 6872266bae1b..82da15a9cc78 100644 --- a/fs/fuse/dev_uring.c +++ b/fs/fuse/dev_uring.c @@ -238,7 +238,6 @@ static struct fuse_ring *fuse_uring_create(struct fuse_chan *fch) { struct fuse_ring *ring; size_t nr_queues = num_possible_cpus(); - struct fuse_ring *res = NULL; size_t max_payload_size; ring = kzalloc_obj(*ring, GFP_KERNEL_ACCOUNT); @@ -258,12 +257,6 @@ static struct fuse_ring *fuse_uring_create(struct fuse_chan *fch) spin_unlock(&fch->lock); goto out_err; } - if (fch->ring) { - /* race, another thread created the ring in the meantime */ - spin_unlock(&fch->lock); - res = fch->ring; - goto out_err; - } init_waitqueue_head(&ring->stop_waitq); @@ -278,7 +271,13 @@ static struct fuse_ring *fuse_uring_create(struct fuse_chan *fch) out_err: kfree(ring->queues); kfree(ring); - return res; + return NULL; +} + +void fuse_uring_conn_init(struct fuse_chan *fch) +{ + if (fuse_uring_create(fch)) + fch->io_uring = 1; } static struct fuse_ring_queue *fuse_uring_create_queue(struct fuse_ring *ring, @@ -746,6 +745,7 @@ static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent, { struct fuse_ring_queue *queue = ent->queue; struct fuse_ring *ring = queue->ring; + struct fuse_in_header in_header; int err; err = -EIO; @@ -767,8 +767,9 @@ static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent, } /* copy fuse_in_header */ - return copy_header_to_ring(ent, FUSE_URING_HEADER_IN_OUT, &req->in.h, - sizeof(req->in.h)); + in_header = req->in.h; + return copy_header_to_ring(ent, FUSE_URING_HEADER_IN_OUT, &in_header, + sizeof(in_header)); } static int fuse_uring_prepare_send(struct fuse_ring_ent *ent, @@ -873,11 +874,13 @@ static void fuse_uring_commit(struct fuse_ring_ent *ent, struct fuse_req *req, unsigned int issue_flags) { struct fuse_ring *ring = ent->queue->ring; + struct fuse_out_header out_header; ssize_t err = -EFAULT; - if (copy_header_from_ring(ent, FUSE_URING_HEADER_IN_OUT, &req->out.h, - sizeof(req->out.h))) + if (copy_header_from_ring(ent, FUSE_URING_HEADER_IN_OUT, &out_header, + sizeof(out_header))) goto out; + req->out.h = out_header; err = fuse_uring_out_header_has_err(&req->out.h, req); if (err) { @@ -1178,15 +1181,10 @@ static int fuse_uring_register(struct io_uring_cmd *cmd, struct fuse_ring *ring = smp_load_acquire(&fch->ring); struct fuse_ring_queue *queue; struct fuse_ring_ent *ent; - int err; unsigned int qid = READ_ONCE(cmd_req->qid); - err = -ENOMEM; - if (!ring) { - ring = fuse_uring_create(fch); - if (!ring) - return err; - } + if (!ring) + return -EINVAL; if (qid >= ring->nr_queues) { pr_info_ratelimited("fuse: Invalid ring qid %u\n", qid); @@ -1197,7 +1195,7 @@ static int fuse_uring_register(struct io_uring_cmd *cmd, if (!queue) { queue = fuse_uring_create_queue(ring, qid); if (!queue) - return err; + return -ENOMEM; } /* diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h index 55f8d04e4b0b..d721a4fc0215 100644 --- a/fs/fuse/dev_uring_i.h +++ b/fs/fuse/dev_uring_i.h @@ -135,6 +135,7 @@ struct fuse_ring { bool ready; }; +void fuse_uring_conn_init(struct fuse_chan *fch); void fuse_uring_stop_queues(struct fuse_ring *ring); void fuse_uring_abort_end_requests(struct fuse_ring *ring); int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); @@ -174,6 +175,10 @@ static inline bool fuse_uring_ready(struct fuse_chan *fch) #else /* CONFIG_FUSE_IO_URING */ +static inline void fuse_uring_conn_init(struct fuse_chan *fch) +{ +} + static inline void fuse_uring_abort(struct fuse_chan *fch) { } diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d975073c6029..ce4891a04a37 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1272,6 +1272,7 @@ static void process_init_reply(struct fuse_args *args, int error) struct fuse_mount *fm = ia->fm; struct fuse_conn *fc = fm->fc; struct fuse_init_out *arg = &ia->out; + bool io_uring_enabled = false; bool ok = true; if (error || arg->major != FUSE_KERNEL_VERSION) @@ -1402,7 +1403,7 @@ static void process_init_reply(struct fuse_args *args, int error) ok = false; } if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled()) - fuse_chan_io_uring_enable(fc->chan); + io_uring_enabled = true; if (flags & FUSE_REQUEST_TIMEOUT) timeout = arg->request_timeout; @@ -1432,6 +1433,7 @@ static void process_init_reply(struct fuse_args *args, int error) .minor = fc->minor, .max_write = fc->max_write, .max_pages = fc->max_pages, + .io_uring_enabled = io_uring_enabled, }; fuse_chan_set_initialized(fc->chan, &cp); } diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c index dc8ac7e370a5..30ef78a66b4f 100644 --- a/fs/iomap/bio.c +++ b/fs/iomap/bio.c @@ -179,7 +179,7 @@ int iomap_bio_read_folio_range_sync(const struct iomap_iter *iter, if (srcmap->flags & IOMAP_F_INTEGRITY) fs_bio_integrity_alloc(&bio); error = submit_bio_wait(&bio); - if (srcmap->flags & IOMAP_F_INTEGRITY) { + if (bio_integrity(&bio)) { if (!error) error = fs_bio_integrity_verify(&bio, sector, len); fs_bio_integrity_free(&bio); diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index e2cd5f92babe..01daed391856 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -358,6 +358,7 @@ static ssize_t iomap_dio_bio_iter_one(struct iomap_iter *iter, iomap_max_bio_size(&iter->iomap), alignment); else ret = bio_iov_iter_get_pages(bio, dio->submit.iter, + bdev_dma_alignment(bio->bi_bdev), alignment - 1); if (unlikely(ret)) goto out_put_bio; diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c index 1508e2f54462..513273712010 100644 --- a/fs/jbd2/checkpoint.c +++ b/fs/jbd2/checkpoint.c @@ -358,15 +358,16 @@ int jbd2_cleanup_journal_tail(journal_t *journal) /* * journal_shrink_one_cp_list * - * Find all the written-back checkpoint buffers in the given list - * and try to release them. If the whole transaction is released, set - * the 'released' parameter. Return the number of released checkpointed - * buffers. + * Find written-back checkpoint buffers in the given list and try to release + * them. If 'nr_to_scan' is set, scan at most that many buffers. If the whole + * transaction is released, set the 'released' parameter. Return the number of + * released checkpointed buffers. * * Called with j_list_lock held. */ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, enum jbd2_shrink_type type, + unsigned long *nr_to_scan, bool *released) { struct journal_head *last_jh; @@ -375,13 +376,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, int ret; *released = false; - if (!jh) + if (!jh || (nr_to_scan && !*nr_to_scan)) return 0; last_jh = jh->b_cpprev; do { jh = next_jh; next_jh = jh->b_cpnext; + if (nr_to_scan) + (*nr_to_scan)--; if (type == JBD2_SHRINK_DESTROY) { ret = __jbd2_journal_remove_checkpoint(jh); @@ -389,7 +392,7 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, ret = jbd2_journal_try_remove_checkpoint(jh); if (ret < 0) { if (type == JBD2_SHRINK_BUSY_SKIP) - continue; + goto next; break; } } @@ -400,9 +403,10 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh, break; } +next: if (need_resched()) break; - } while (jh != last_jh); + } while (jh != last_jh && (!nr_to_scan || *nr_to_scan)); return nr_freed; } @@ -424,7 +428,6 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, tid_t first_tid = 0, last_tid = 0, next_tid = 0; tid_t tid = 0; unsigned long nr_freed = 0; - unsigned long freed; bool first_set = false; again: @@ -457,10 +460,9 @@ again: next_transaction = transaction->t_cpnext; tid = transaction->t_tid; - freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list, - JBD2_SHRINK_BUSY_SKIP, &released); - nr_freed += freed; - (*nr_to_scan) -= min(*nr_to_scan, freed); + nr_freed += journal_shrink_one_cp_list(transaction->t_checkpoint_list, + JBD2_SHRINK_BUSY_SKIP, + nr_to_scan, &released); if (*nr_to_scan == 0) break; if (need_resched() || spin_needbreak(&journal->j_list_lock)) @@ -516,7 +518,7 @@ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, transaction = next_transaction; next_transaction = transaction->t_cpnext; journal_shrink_one_cp_list(transaction->t_checkpoint_list, - type, &released); + type, NULL, &released); /* * This function only frees up some memory if possible so we * dont have an obligation to finish processing. Bail out if diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index f06faf577cea..f8018bfe9c64 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -487,9 +487,12 @@ static const struct file_lock_operations nlmclnt_lock_ops = { static void nlmclnt_locks_init_private(struct file_lock *fl, struct nlm_host *host) { fl->fl_u.nfs_fl.state = 0; + fl->fl_ops = NULL; fl->fl_u.nfs_fl.owner = nlmclnt_find_lockowner(host, fl->c.flc_owner); INIT_LIST_HEAD(&fl->fl_u.nfs_fl.list); + if (!fl->fl_u.nfs_fl.owner) + return; fl->fl_ops = &nlmclnt_lock_ops; } diff --git a/fs/lockd/lockd.h b/fs/lockd/lockd.h index e418a50c4180..14cc952fe81a 100644 --- a/fs/lockd/lockd.h +++ b/fs/lockd/lockd.h @@ -314,7 +314,7 @@ void nsm_release(struct nsm_handle *nsm); * This is used in garbage collection and resource reclaim * A return value != 0 means destroy the lock/block/share */ -typedef int (*nlm_host_match_fn_t)(void *cur, struct nlm_host *ref); +typedef int (*nlm_host_match_fn_t)(void *owner, struct nlm_host *ref); /* * Server-side lock handling diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 490551369ef2..ee90e743064a 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -47,7 +47,7 @@ static struct svc_program nlmsvc_program; -const struct nlmsvc_binding *nlmsvc_ops; +const struct nlmsvc_binding __rcu *nlmsvc_ops; EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); @@ -142,7 +142,7 @@ lockd(void *vrqstp) nlmsvc_retry_blocked(rqstp); svc_recv(rqstp, 0); } - if (nlmsvc_ops) + if (rcu_access_pointer(nlmsvc_ops)) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); cancel_delayed_work_sync(&ln->grace_period_end); diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 78e675470c4b..b73004a7987e 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -128,7 +128,7 @@ nlm4svc_lookup_host(struct svc_rqst *rqstp, string caller, bool monitored) { struct nlm_host *host; - if (!nlmsvc_ops) + if (!rcu_access_pointer(nlmsvc_ops)) return NULL; host = nlmsvc_lookup_host(rqstp, caller.data, caller.len); if (!host) @@ -872,7 +872,8 @@ static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp) struct nlm4_testargs_wrapper *argp = rqstp->rq_argp; struct nlm_host *host; - host = nlm4svc_lookup_host(rqstp, argp->xdrgen.alock.caller_name, false); + host = nlmsvc_lookup_host(rqstp, argp->xdrgen.alock.caller_name.data, + argp->xdrgen.alock.caller_name.len); if (!host) return rpc_system_err; @@ -894,7 +895,7 @@ static __be32 nlm4svc_proc_granted_res(struct svc_rqst *rqstp) { struct nlm4_res_wrapper *argp = rqstp->rq_argp; - if (!nlmsvc_ops) + if (!rcu_access_pointer(nlmsvc_ops)) return rpc_success; if (nlm4_netobj_to_cookie(&argp->cookie, &argp->xdrgen.cookie)) diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index 386a881b520f..d410b8c69893 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -133,7 +133,7 @@ nlm3svc_lookup_host(struct svc_rqst *rqstp, string caller, bool monitored) { struct nlm_host *host; - if (!nlmsvc_ops) + if (!rcu_access_pointer(nlmsvc_ops)) return NULL; host = nlmsvc_lookup_host(rqstp, caller.data, caller.len); if (!host) @@ -924,7 +924,7 @@ static __be32 nlmsvc_proc_granted_res(struct svc_rqst *rqstp) { struct nlm_res_wrapper *argp = rqstp->rq_argp; - if (!nlmsvc_ops) + if (!rcu_access_pointer(nlmsvc_ops)) return rpc_success; if (nlm_netobj_to_cookie(&argp->cookie, &argp->xdrgen.cookie)) diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c index a0d1a6fbf61e..ffab76278bb2 100644 --- a/fs/lockd/svcsubs.c +++ b/fs/lockd/svcsubs.c @@ -90,22 +90,35 @@ int lock_to_openmode(struct file_lock *lock) static __be32 nlm_do_fopen(struct svc_rqst *rqstp, struct nlm_file *file, int mode) { + const struct nlmsvc_binding *ops; __be32 nlmerr = nlm__int__failed; __be32 deferred = 0; int error; int m; + rcu_read_lock(); + ops = rcu_dereference(nlmsvc_ops); + if (!ops || !try_module_get(ops->owner)) { + rcu_read_unlock(); + return nlm__int__failed; + } + rcu_read_unlock(); + for (m = O_RDONLY; m <= O_WRONLY; m++) { struct file **fp = &file->f_file[m]; if (mode != O_RDWR && mode != m) continue; - if (*fp) + if (*fp) { + module_put(ops->owner); return nlm_granted; + } - error = nlmsvc_ops->fopen(rqstp, &file->f_handle, fp, m); - if (!error) + error = ops->fopen(rqstp, &file->f_handle, fp, m); + if (!error) { + module_put(ops->owner); return nlm_granted; + } dprintk("lockd: open failed (errno %d)\n", error); switch (error) { @@ -122,6 +135,7 @@ static __be32 nlm_do_fopen(struct svc_rqst *rqstp, } } + module_put(ops->owner); return deferred ? deferred : nlmerr; } @@ -186,6 +200,33 @@ out_free: } /* + * Release the struct file references held by a nlm_file. + */ +static void nlm_release_files(struct nlm_file *file) +{ + const struct nlmsvc_binding *ops; + bool have_ops; + + rcu_read_lock(); + ops = rcu_dereference(nlmsvc_ops); + have_ops = ops && try_module_get(ops->owner); + rcu_read_unlock(); + + if (have_ops) { + if (file->f_file[O_RDONLY]) + ops->fclose(file->f_file[O_RDONLY]); + if (file->f_file[O_WRONLY]) + ops->fclose(file->f_file[O_WRONLY]); + module_put(ops->owner); + } else { + if (file->f_file[O_RDONLY]) + fput(file->f_file[O_RDONLY]); + if (file->f_file[O_WRONLY]) + fput(file->f_file[O_WRONLY]); + } +} + +/* * Delete a file after having released all locks, blocks and shares */ static inline void @@ -194,10 +235,7 @@ nlm_delete_file(struct nlm_file *file) nlm_debug_print_file("closing file", file); if (!hlist_unhashed(&file->f_list)) { hlist_del(&file->f_list); - if (file->f_file[O_RDONLY]) - nlmsvc_ops->fclose(file->f_file[O_RDONLY]); - if (file->f_file[O_WRONLY]) - nlmsvc_ops->fclose(file->f_file[O_WRONLY]); + nlm_release_files(file); kfree(file); } else { printk(KERN_WARNING "lockd: attempt to release unknown file!\n"); @@ -312,12 +350,10 @@ nlm_file_inuse(struct nlm_file *file) return 0; } -static void nlm_close_files(struct nlm_file *file) +static void nlm_file_release(struct nlm_file *file) { - if (file->f_file[O_RDONLY]) - nlmsvc_ops->fclose(file->f_file[O_RDONLY]); - if (file->f_file[O_WRONLY]) - nlmsvc_ops->fclose(file->f_file[O_WRONLY]); + if (!nlm_file_inuse(file)) + nlm_delete_file(file); } /* @@ -327,32 +363,41 @@ static int nlm_traverse_files(void *data, nlm_host_match_fn_t match, int (*is_failover_file)(void *data, struct nlm_file *file)) { - struct hlist_node *next; - struct nlm_file *file; + struct nlm_file *file, *next; int i, ret = 0; mutex_lock(&nlm_file_mutex); for (i = 0; i < FILE_NRHASH; i++) { - hlist_for_each_entry_safe(file, next, &nlm_files[i], f_list) { - if (is_failover_file && !is_failover_file(data, file)) - continue; + file = hlist_entry_safe(nlm_files[i].first, + struct nlm_file, f_list); + if (file) file->f_count++; - mutex_unlock(&nlm_file_mutex); - - /* Traverse locks, blocks and shares of this file - * and update file->f_locks count */ - if (nlm_inspect_file(data, file, match)) - ret = 1; + while (file) { + /* + * Pin the next neighbour before we drop the mutex + * for nlm_inspect_file(); a concurrent + * nlm_release_file() under the same mutex would + * otherwise be free to unlink and kfree it during + * the unlock window, leaving us to dereference a + * freed slab when we walked to next afterwards. + */ + next = hlist_entry_safe(file->f_list.next, + struct nlm_file, f_list); + if (next) + next->f_count++; + + if (!is_failover_file || is_failover_file(data, file)) { + mutex_unlock(&nlm_file_mutex); + + if (nlm_inspect_file(data, file, match)) + ret = 1; + + mutex_lock(&nlm_file_mutex); + } - mutex_lock(&nlm_file_mutex); file->f_count--; - /* No more references to this file. Let go of it. */ - if (list_empty(&file->f_blocks) && !file->f_locks - && !file->f_shares && !file->f_count) { - hlist_del(&file->f_list); - nlm_close_files(file); - kfree(file); - } + nlm_file_release(file); + file = next; } } mutex_unlock(&nlm_file_mutex); @@ -512,7 +557,7 @@ EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb); static int nlmsvc_match_ip(void *datap, struct nlm_host *host) { - return rpc_cmp_addr(nlm_srcaddr(host), datap); + return rpc_cmp_addr(nlm_srcaddr(datap), (struct sockaddr *)host); } /** diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index ff4e9fd38e83..bc282b744f34 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -231,8 +231,9 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) cb_info->users++; err_net: if (!cb_info->users) { + xprt_svc_shutdown_bc(xprt); svc_set_num_threads(cb_info->serv, 0, 0); - svc_destroy(&cb_info->serv); + xprt_svc_destroy_nullify_bc(xprt, &cb_info->serv); } err_create: mutex_unlock(&nfs_callback_mutex); @@ -254,6 +255,7 @@ void nfs_callback_down(int minorversion, struct net *net, struct rpc_xprt *xprt) mutex_lock(&nfs_callback_mutex); serv = cb_info->serv; + xprt_svc_shutdown_bc(xprt); nfs_callback_down_net(minorversion, serv, net); cb_info->users--; if (cb_info->users == 0) { diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 71c271a1700a..819e435c3a42 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -915,20 +915,22 @@ static int nfs4_server_common_setup(struct nfs_server *server, return error; /* data servers support only a subset of NFSv4.1 */ - if (is_ds_only_client(server->nfs_client)) - return -EPROTONOSUPPORT; + if (is_ds_only_client(server->nfs_client)) { + error = -EPROTONOSUPPORT; + goto out_free_delegation_hash; + } /* We must ensure the session is initialised first */ error = nfs4_init_session(server->nfs_client); if (error < 0) - return error; + goto out_free_delegation_hash; nfs_server_set_init_caps(server); /* Probe the root fh to retrieve its FSID and filehandle */ error = nfs4_get_rootfh(server, mntfh, auth_probe); if (error < 0) - return error; + goto out_free_delegation_hash; dprintk("Server FSID: %llx:%llx\n", (unsigned long long) server->fsid.major, @@ -937,7 +939,7 @@ static int nfs4_server_common_setup(struct nfs_server *server, error = nfs_probe_server(server, mntfh); if (error < 0) - return error; + goto out_free_delegation_hash; nfs4_session_limit_rwsize(server); nfs4_session_limit_xasize(server); @@ -949,6 +951,11 @@ static int nfs4_server_common_setup(struct nfs_server *server, server->mount_time = jiffies; server->destroy = nfs4_destroy_server; return 0; + +out_free_delegation_hash: + kfree(server->delegation_hash_table); + server->delegation_hash_table = NULL; + return error; } /* diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 7715e2bd5871..b1a30a16287f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1389,7 +1389,7 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo) return false; return pnfs_mark_layout_stateid_return(lo, &lo->plh_return_segs, lo->plh_return_iomode, - lo->plh_return_seq) != EBUSY; + lo->plh_return_seq) != -EBUSY; } static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) @@ -2643,6 +2643,7 @@ out_forget: spin_unlock(&ino->i_lock); lseg->pls_layout = lo; NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + pnfs_free_lseg_list(&free_me); return ERR_PTR(-EAGAIN); } diff --git a/fs/nfs_common/nfslocalio.c b/fs/nfs_common/nfslocalio.c index dd715cdb6c04..85aa03a7b020 100644 --- a/fs/nfs_common/nfslocalio.c +++ b/fs/nfs_common/nfslocalio.c @@ -292,8 +292,22 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *uuid, localio = nfs_to->nfsd_open_local_fh(net, uuid->dom, rpc_clnt, cred, nfs_fh, pnf, fmode); if (!IS_ERR(localio) && nfs_uuid_add_file(uuid, nfl) < 0) { - /* Delete the cached file when racing with nfs_uuid_put() */ + /* + * Delete the cached file when racing with nfs_uuid_put(). + * Since nfl->nfs_uuid was never published via + * rcu_assign_pointer(), nfs_close_local_fh() will early-return + * and cannot clean up after us. Drop the slot's file ref and + * its paired net ref, then drop the caller-owned nfsd_file ref + * (+1) and the entry-time nfsd_net ref carried via nf->nf_net, + * and return -ENXIO so the caller never dereferences the + * now-cleared localio. + */ + struct nfsd_file __rcu *tmp = + (struct nfsd_file __force __rcu *)localio; + nfs_to_nfsd_file_put_local(pnf); + nfs_to_nfsd_file_put_local(&tmp); + localio = ERR_PTR(-ENXIO); } nfs_to_nfsd_net_put(net); diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 24511c3208db..1ea2bfd51825 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -55,6 +55,17 @@ /* We only care about NFSD_MAY_READ/WRITE for this cache */ #define NFSD_FILE_MAY_MASK (NFSD_MAY_READ|NFSD_MAY_WRITE|NFSD_MAY_LOCALIO) +/* If the shrinker runs between calls to list_lru_walk_node() in + * nfsd_file_gc(), the "remaining" count will be wrong. This could + * result in premature freeing of some files. This may not matter much + * but is easy to fix with this spinlock which temporarily disables + * the shrinker. + * + * It also serializes callers of nfsd_file_dispose_list_delayed() + * against per-net shutdown. + */ +static DEFINE_SPINLOCK(nfsd_gc_lock); + static DEFINE_PER_CPU(unsigned long, nfsd_file_cache_hits); static DEFINE_PER_CPU(unsigned long, nfsd_file_acquisitions); static DEFINE_PER_CPU(unsigned long, nfsd_file_allocations); @@ -62,11 +73,6 @@ static DEFINE_PER_CPU(unsigned long, nfsd_file_releases); static DEFINE_PER_CPU(unsigned long, nfsd_file_total_age); static DEFINE_PER_CPU(unsigned long, nfsd_file_evictions); -struct nfsd_fcache_disposal { - spinlock_t lock; - struct list_head freeme; -}; - static struct kmem_cache *nfsd_file_slab; static struct kmem_cache *nfsd_file_mark_slab; static struct list_lru nfsd_file_lru; @@ -327,8 +333,11 @@ static void nfsd_file_lru_add(struct nfsd_file *nf) refcount_inc(&nf->nf_ref); if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) trace_nfsd_file_lru_add(nf); - else - WARN_ON(1); + else { + refcount_dec(&nf->nf_ref); + WARN_ON_ONCE(1); + return; + } nfsd_file_schedule_laundrette(); } @@ -419,25 +428,31 @@ nfsd_file_dispose_list(struct list_head *dispose) } /** - * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list + * nfsd_file_dispose_list_delayed - queue dead files for nfsd thread disposal * @dispose: list of nfsd_files to be disposed * - * Transfers each file to the "freeme" list for its nfsd_net, to eventually - * be disposed of by the per-net garbage collector. + * Transfers each file to the dispose list in its nfsd_net and wakes an nfsd + * thread to do the actual close. This keeps the cost of fput() in the nfsd + * threads rather than in the shrinker or GC worker. + * + * All callers must hold nfsd_gc_lock, so that nfsd_file_cache_shutdown_net() + * can synchronize against them before draining the per-net dispose list. + * This guarantees nf_net is still live when we call net_generic(). */ static void nfsd_file_dispose_list_delayed(struct list_head *dispose) { - while(!list_empty(dispose)) { + lockdep_assert_held(&nfsd_gc_lock); + + while (!list_empty(dispose)) { struct nfsd_file *nf = list_first_entry(dispose, struct nfsd_file, nf_gc); struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; struct svc_serv *serv; - spin_lock(&l->lock); - list_move_tail(&nf->nf_gc, &l->freeme); - spin_unlock(&l->lock); + spin_lock(&nn->fcache_dispose_lock); + list_move_tail(&nf->nf_gc, &nn->fcache_dispose_list); + spin_unlock(&nn->fcache_dispose_lock); /* * The filecache laundrette is shut down after the @@ -461,21 +476,28 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) */ void nfsd_file_net_dispose(struct nfsd_net *nn) { - struct nfsd_fcache_disposal *l = nn->fcache_disposal; - - if (!list_empty(&l->freeme)) { + if (!list_empty(&nn->fcache_dispose_list)) { LIST_HEAD(dispose); int i; - spin_lock(&l->lock); - for (i = 0; i < 8 && !list_empty(&l->freeme); i++) - list_move(l->freeme.next, &dispose); - spin_unlock(&l->lock); - if (!list_empty(&l->freeme)) - /* Wake up another thread to share the work + spin_lock(&nn->fcache_dispose_lock); + for (i = 0; i < 8 && !list_empty(&nn->fcache_dispose_list); i++) + list_move(nn->fcache_dispose_list.next, &dispose); + spin_unlock(&nn->fcache_dispose_lock); + if (!list_empty(&nn->fcache_dispose_list)) { + /* + * Wake up another thread to share the work * *before* doing any actual disposing. + * + * The filecache laundrette is shut down after + * the nn->nfsd_serv pointer is cleared, but + * before the svc_serv is freed. */ - svc_wake_up(nn->nfsd_serv); + struct svc_serv *serv = nn->nfsd_serv; + + if (serv) + svc_wake_up(serv); + } nfsd_file_dispose_list(&dispose); } } @@ -552,13 +574,6 @@ nfsd_file_gc_cb(struct list_head *item, struct list_lru_one *lru, return nfsd_file_lru_cb(item, lru, arg); } -/* If the shrinker runs between calls to list_lru_walk_node() in - * nfsd_file_gc(), the "remaining" count will be wrong. This could - * result in premature freeing of some files. This may not matter much - * but is easy to fix with this spinlock which temporarily disables - * the shrinker. - */ -static DEFINE_SPINLOCK(nfsd_gc_lock); static void nfsd_file_gc(void) { @@ -581,9 +596,9 @@ nfsd_file_gc(void) remaining = 0; } } + nfsd_file_dispose_list_delayed(&dispose); spin_unlock(&nfsd_gc_lock); trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru)); - nfsd_file_dispose_list_delayed(&dispose); } static void @@ -611,9 +626,9 @@ nfsd_file_lru_scan(struct shrinker *s, struct shrink_control *sc) ret = list_lru_shrink_walk(&nfsd_file_lru, sc, nfsd_file_lru_cb, &dispose); + nfsd_file_dispose_list_delayed(&dispose); spin_unlock(&nfsd_gc_lock); trace_nfsd_file_shrinker_removed(ret, list_lru_count(&nfsd_file_lru)); - nfsd_file_dispose_list_delayed(&dispose); return ret; } @@ -686,11 +701,11 @@ nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) } /** - * nfsd_file_close_inode - attempt a delayed close of a nfsd_file + * nfsd_file_close_inode - attempt a deferred close of a nfsd_file * @inode: inode of the file to attempt to remove * * Close out any open nfsd_files that can be reaped for @inode. The - * actual freeing is deferred to the dispose_list_delayed infrastructure. + * actual freeing is deferred to the nfsd service threads. * * This is used by the fsnotify callbacks and setlease notifier. */ @@ -699,8 +714,10 @@ nfsd_file_close_inode(struct inode *inode) { LIST_HEAD(dispose); + spin_lock(&nfsd_gc_lock); nfsd_file_queue_for_close(inode, &dispose); nfsd_file_dispose_list_delayed(&dispose); + spin_unlock(&nfsd_gc_lock); } /** @@ -940,42 +957,14 @@ __nfsd_file_cache_purge(struct net *net) nfsd_file_dispose_list(&dispose); } -static struct nfsd_fcache_disposal * -nfsd_alloc_fcache_disposal(void) -{ - struct nfsd_fcache_disposal *l; - - l = kmalloc_obj(*l); - if (!l) - return NULL; - spin_lock_init(&l->lock); - INIT_LIST_HEAD(&l->freeme); - return l; -} - -static void -nfsd_free_fcache_disposal(struct nfsd_fcache_disposal *l) -{ - nfsd_file_dispose_list(&l->freeme); - kfree(l); -} - -static void -nfsd_free_fcache_disposal_net(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - struct nfsd_fcache_disposal *l = nn->fcache_disposal; - - nfsd_free_fcache_disposal(l); -} - int nfsd_file_cache_start_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nn->fcache_disposal = nfsd_alloc_fcache_disposal(); - return nn->fcache_disposal ? 0 : -ENOMEM; + spin_lock_init(&nn->fcache_dispose_lock); + INIT_LIST_HEAD(&nn->fcache_dispose_list); + return 0; } /** @@ -994,8 +983,18 @@ nfsd_file_cache_purge(struct net *net) void nfsd_file_cache_shutdown_net(struct net *net) { + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + nfsd_file_cache_purge(net); - nfsd_free_fcache_disposal_net(net); + /* + * Ensure any in-progress shrinker, GC, or fsnotify/lease callback + * (all of which hold nfsd_gc_lock while calling + * nfsd_file_dispose_list_delayed()) has fully completed before + * draining the per-net dispose list. + */ + spin_lock(&nfsd_gc_lock); + spin_unlock(&nfsd_gc_lock); + nfsd_file_dispose_list(&nn->fcache_dispose_list); } void @@ -1227,7 +1226,7 @@ open_file: nf->nf_mark = nfsd_file_mark_find_or_create(inode); if (type != S_IFREG || nf->nf_mark) { - if (file) { + if (file && (file->f_mode & FMODE_OPENED)) { get_file(file); nf->nf_file = file; status = nfs_ok; @@ -1374,12 +1373,12 @@ nfsd_file_acquire_local(struct net *net, struct svc_cred *cred, * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file just created * @may_flags: NFSD_MAY_ settings for the file - * @file: cached, already-open file (may be NULL) + * @file: cached, already-open file (may be NULL or not yet opened) * @pnf: OUT: new or found "struct nfsd_file" object * * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, - * and @file is non-NULL, use it to instantiate a new nfsd_file instead of - * opening a new one. + * and @file has FMODE_OPENED set, use it to instantiate a new nfsd_file + * instead of opening a new one. * * Return values: * %nfs_ok - @pnf points to an nfsd_file with its reference diff --git a/fs/nfsd/flexfilelayoutxdr.c b/fs/nfsd/flexfilelayoutxdr.c index f9f7e38cba13..374e52d3064a 100644 --- a/fs/nfsd/flexfilelayoutxdr.c +++ b/fs/nfsd/flexfilelayoutxdr.c @@ -30,19 +30,24 @@ nfsd4_ff_encode_layoutget(struct xdr_stream *xdr, struct ff_idmap uid; struct ff_idmap gid; - fh_len = 4 + fl->fh.size; + fh_len = 4 + xdr_align_size(fl->fh.size); uid.len = sprintf(uid.buf, "%u", from_kuid(&init_user_ns, fl->uid)); gid.len = sprintf(gid.buf, "%u", from_kgid(&init_user_ns, fl->gid)); - /* 8 + len for recording the length, name, and padding */ - ds_len = 20 + sizeof(stateid_opaque_t) + 4 + fh_len + - 8 + uid.len + 8 + gid.len; + /* data server entry: deviceid + efficiency + stateid + fh list + + * user + group + flags + stats_collect_hint + */ + ds_len = 16 + 4 + 4 + sizeof(stateid_opaque_t) + 4 + fh_len + + 4 + xdr_align_size(uid.len) + + 4 + xdr_align_size(gid.len) + + 4 + 4; + /* mirror: ds_count + ds */ mirror_len = 4 + ds_len; - /* The layout segment */ - len = 20 + mirror_len; + /* stripe_unit + mirror_count + mirror */ + len = 12 + mirror_len; p = xdr_reserve_space(xdr, sizeof(__be32) + len); if (!p) @@ -94,7 +99,8 @@ nfsd4_ff_encode_getdeviceinfo(struct xdr_stream *xdr, } /* len + padding for two strings */ - addr_len = 16 + da->netaddr.netid_len + da->netaddr.addr_len; + addr_len = 8 + xdr_align_size(da->netaddr.netid_len) + + xdr_align_size(da->netaddr.addr_len); ver_len = 20; len = 4 + ver_len + 4 + addr_len; diff --git a/fs/nfsd/localio.c b/fs/nfsd/localio.c index be710d809a3b..c3eb0557b3e1 100644 --- a/fs/nfsd/localio.c +++ b/fs/nfsd/localio.c @@ -97,11 +97,15 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, } nfsd_file_get(localio); again: + rcu_read_lock(); new = unrcu_pointer(cmpxchg(pnf, NULL, RCU_INITIALIZER(localio))); if (new) { /* Some other thread installed an nfsd_file */ - if (nfsd_file_get(new) == NULL) + if (nfsd_file_get(new) == NULL) { + rcu_read_unlock(); goto again; + } + rcu_read_unlock(); /* * Drop the ref we were going to install (both file and * net) and the one we were going to return (only file). @@ -110,6 +114,8 @@ nfsd_open_local_fh(struct net *net, struct auth_domain *dom, nfsd_net_put(net); nfsd_file_put(localio); localio = new; + } else { + rcu_read_unlock(); } } else nfsd_net_put(net); diff --git a/fs/nfsd/lockd.c b/fs/nfsd/lockd.c index 6fe1325815e0..72a5b499839d 100644 --- a/fs/nfsd/lockd.c +++ b/fs/nfsd/lockd.c @@ -92,6 +92,7 @@ nlm_fclose(struct file *filp) } static const struct nlmsvc_binding nfsd_nlm_ops = { + .owner = THIS_MODULE, .fopen = nlm_fopen, /* open file for locking */ .fclose = nlm_fclose, /* close file */ }; @@ -100,11 +101,12 @@ void nfsd_lockd_init(void) { dprintk("nfsd: initializing lockd\n"); - nlmsvc_ops = &nfsd_nlm_ops; + rcu_assign_pointer(nlmsvc_ops, &nfsd_nlm_ops); } void nfsd_lockd_shutdown(void) { - nlmsvc_ops = NULL; + RCU_INIT_POINTER(nlmsvc_ops, NULL); + synchronize_rcu(); } diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 27da1a3edacb..a7bd7b67fa4f 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -28,6 +28,16 @@ struct cld_net; struct nfsd_net_cb; struct nfsd4_client_tracking_ops; +enum nfsd_net_flag { + NFSD_NET_GRACE_ENDED, + NFSD_NET_GRACE_END_FORCED, + NFSD_NET_IN_GRACE, + NFSD_NET_SOMEBODY_RECLAIMED, + NFSD_NET_TRACK_RECLAIM_COMPLETES, + NFSD_NET_UP, + NFSD_NET_LOCKD_UP, +}; + enum { /* cache misses due only to checksum comparison failures */ NFSD_STATS_PAYLOAD_MISSES, @@ -66,9 +76,9 @@ struct nfsd_net { struct cache_detail *nametoid_cache; struct lock_manager nfsd4_manager; - bool grace_ended; - bool grace_end_forced; + unsigned long flags; time64_t boot_time; + time64_t boot_time_bt; /* same instant in CLOCK_BOOTTIME */ struct dentry *nfsd_client_dir; @@ -84,6 +94,7 @@ struct nfsd_net { */ struct list_head *reclaim_str_hashtbl; int reclaim_str_hashtbl_size; + struct rw_semaphore reclaim_str_hashtbl_lock; struct list_head *conf_id_hashtbl; struct rb_root conf_name_tree; struct list_head *unconf_id_hashtbl; @@ -96,12 +107,16 @@ struct nfsd_net { * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time * for last close replay. * - * All of the above fields are protected by the client_mutex. + * reclaim_str_hashtbl[], reclaim_str_hashtbl_size are protected by + * reclaim_str_hashtbl_lock. + * + * All of the remaining fields are protected by the client_lock. */ struct list_head client_lru; struct list_head close_lru; - /* protects del_recall_lru and delegation hash/unhash */ + /* protects del_recall_lru and delegation hash/unhash; + * nests outside client_lock */ spinlock_t deleg_lock ____cacheline_aligned; struct list_head del_recall_lru; @@ -110,26 +125,21 @@ struct nfsd_net { struct delayed_work laundromat_work; - /* client_lock protects the client lru list and session hash table */ + /* client_lock protects the client lru list and session hash + * table; nests inside deleg_lock */ spinlock_t client_lock; /* protects blocked_locks_lru */ spinlock_t blocked_locks_lock; struct file *rec_file; - bool in_grace; const struct nfsd4_client_tracking_ops *client_tracking_ops; time64_t nfsd4_lease; time64_t nfsd4_grace; - bool somebody_reclaimed; - bool track_reclaim_completes; atomic_t nr_reclaim_complete; - bool nfsd_net_up; - bool lockd_up; - seqlock_t writeverf_lock; unsigned char writeverf[8]; @@ -209,7 +219,8 @@ struct nfsd_net { /* utsname taken from the process that starts the server */ char nfsd_name[UNX_MAXNODENAME+1]; - struct nfsd_fcache_disposal *fcache_disposal; + spinlock_t fcache_dispose_lock; + struct list_head fcache_dispose_list; siphash_key_t siphash_key; diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 76305b86c1a9..2998640f259d 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -115,14 +115,19 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, - argp->acl_access); - if (error) - goto out_drop_lock; - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, - argp->acl_default); - if (error) - goto out_drop_lock; + error = 0; + if (argp->mask & NFS_ACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_ACCESS, argp->acl_access); + if (error) + goto out_drop_lock; + } + if (argp->mask & NFS_DFACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_DEFAULT, argp->acl_default); + if (error) + goto out_drop_lock; + } inode_unlock(inode); @@ -248,22 +253,21 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) if (!svcxdr_encode_stat(xdr, resp->status)) return false; - - if (dentry == NULL || d_really_is_negative(dentry)) - return true; - inode = d_inode(dentry); - - if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return false; - if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return false; - - if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, - resp->mask & NFS_ACL, 0)) - return false; - if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, - resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return false; + switch (resp->status) { + case nfs_ok: + inode = d_inode(dentry); + if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) + return false; + if (xdr_stream_encode_u32(xdr, resp->mask) < 0) + return false; + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, + resp->mask & NFS_ACL, 0)) + return false; + if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, + resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) + return false; + break; + } return true; } diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index e87731380be8..a87f9d7f32be 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -105,12 +105,17 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, - argp->acl_access); - if (error) - goto out_drop_lock; - error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, - argp->acl_default); + error = 0; + if (argp->mask & NFS_ACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_ACCESS, argp->acl_access); + if (error) + goto out_drop_lock; + } + if (argp->mask & NFS_DFACL) { + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, + ACL_TYPE_DEFAULT, argp->acl_default); + } out_drop_lock: inode_unlock(inode); diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index aeda7a802bdf..617a70d13292 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -29,6 +29,25 @@ static int nfs3_ftypes[] = { S_IFIFO, /* NF3FIFO */ }; +/* + * Reject a client-supplied atime or mtime whose nanoseconds field is out + * of range. Such a value is well-formed on the wire but is not a valid + * timespec64, and storing it verbatim can corrupt on-disk timestamps. + * tv_nsec is a long, so it is cast to unsigned long (the same width) to + * catch both an over-large value and one that became negative when an + * out-of-range u32 wire nseconds was assigned to a 32-bit long. + */ +static bool nfsd3_time_in_range(const struct iattr *iap) +{ + if ((iap->ia_valid & ATTR_ATIME_SET) && + (unsigned long)iap->ia_atime.tv_nsec >= NSEC_PER_SEC) + return false; + if ((iap->ia_valid & ATTR_MTIME_SET) && + (unsigned long)iap->ia_mtime.tv_nsec >= NSEC_PER_SEC) + return false; + return true; +} + static __be32 nfsd3_map_status(__be32 status) { switch (status) { @@ -101,9 +120,14 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } if (argp->check_guard) guardtime = &argp->guardtime; resp->status = nfsd_setattr(rqstp, &resp->fh, &attrs, guardtime); +out: resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -265,6 +289,8 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, trace_nfsd_vfs_create(rqstp, fhp, S_IFREG, argp->name, argp->len); + if (!nfsd3_time_in_range(iap)) + return nfserr_inval; if (isdotent(argp->name, argp->len)) return nfserr_exist; if (!(iap->ia_valid & ATTR_MODE)) @@ -400,8 +426,13 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp) argp->attrs.ia_valid &= ~ATTR_SIZE; fh_copy(&resp->dirfh, &argp->fh); fh_init(&resp->fh, NFS3_FHSIZE); + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, S_IFDIR, 0, &resp->fh); +out: resp->status = nfsd3_map_status(resp->status); return rpc_success; } @@ -415,6 +446,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp) .na_iattr = &argp->attrs, }; + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } if (argp->tlen == 0) { resp->status = nfserr_inval; goto out; @@ -471,6 +506,11 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp) goto out; } + if (!nfsd3_time_in_range(&argp->attrs)) { + resp->status = nfserr_inval; + goto out; + } + type = nfs3_ftypes[argp->ftype]; resp->status = nfsd_create(rqstp, &resp->dirfh, argp->name, argp->len, &attrs, type, rdev, &resp->fh); diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 50827405468d..7c868afc329e 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -108,6 +108,8 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, if (!xdrgen_decode_fattr4_time_deleg_access(xdr, &access)) return -EIO; + if (access.nseconds >= NSEC_PER_SEC) + return -EIO; fattr->ncf_cb_atime.tv_sec = access.seconds; fattr->ncf_cb_atime.tv_nsec = access.nseconds; @@ -117,6 +119,8 @@ static int decode_cb_fattr4(struct xdr_stream *xdr, uint32_t *bitmap, if (!xdrgen_decode_fattr4_time_deleg_modify(xdr, &modify)) return -EIO; + if (modify.nseconds >= NSEC_PER_SEC) + return -EIO; fattr->ncf_cb_mtime.tv_sec = modify.seconds; fattr->ncf_cb_mtime.tv_nsec = modify.nseconds; @@ -456,13 +460,20 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, const struct nfsd4_callback *cb, struct nfs4_cb_compound_hdr *hdr) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; struct nfsd4_referring_call_list *rcl; __be32 *p; if (hdr->minorversion == 0) return; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + return; + } + encode_nfs_cb_opnum4(xdr, OP_CB_SEQUENCE); encode_sessionid4(xdr, session); @@ -478,6 +489,7 @@ static void encode_cb_sequence4args(struct xdr_stream *xdr, encode_referring_call_list4(xdr, rcl); hdr->nops++; + rcu_read_unlock(); } static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) @@ -529,21 +541,32 @@ static void update_cb_slot_table(struct nfsd4_session *ses, u32 target) static int decode_cb_sequence4resok(struct xdr_stream *xdr, struct nfsd4_callback *cb) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; int status = -ESERVERFAULT; __be32 *p; u32 seqid, slotid, target; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + cb->cb_seq_status = -NFS4ERR_BADSESSION; + return -NFS4ERR_BADSESSION; + } + /* * If the server returns different values for sessionID, slotID or * sequence number, the server is looney tunes. */ p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4); - if (unlikely(p == NULL)) + if (unlikely(p == NULL)) { + rcu_read_unlock(); goto out_overflow; + } if (memcmp(p, session->se_sessionid.data, NFS4_MAX_SESSIONID_LEN)) { dprintk("NFS: %s Invalid session id\n", __func__); + rcu_read_unlock(); goto out; } p += XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN); @@ -551,12 +574,14 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, seqid = be32_to_cpup(p++); if (seqid != session->se_cb_seq_nr[cb->cb_held_slot]) { dprintk("NFS: %s Invalid sequence number\n", __func__); + rcu_read_unlock(); goto out; } slotid = be32_to_cpup(p++); if (slotid != cb->cb_held_slot) { dprintk("NFS: %s Invalid slotid\n", __func__); + rcu_read_unlock(); goto out; } @@ -564,6 +589,7 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr, target = be32_to_cpup(p++); update_cb_slot_table(session, target); + rcu_read_unlock(); status = 0; out: cb->cb_seq_status = status; @@ -1150,9 +1176,8 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c } else { if (!conn->cb_xprt || !ses) return -EINVAL; - clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; - args.prognumber = clp->cl_cb_session->se_cb_prog; + args.prognumber = ses->se_cb_prog; args.protocol = conn->cb_xprt->xpt_class->xcl_ident | XPRT_TRANSPORT_BC; args.authflavor = ses->se_cb_sec.flavor; @@ -1170,8 +1195,10 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c return -ENOMEM; } - if (clp->cl_minorversion != 0) + if (clp->cl_minorversion != 0) { clp->cl_cb_conn.cb_xprt = conn->cb_xprt; + rcu_assign_pointer(clp->cl_cb_session, ses); + } clp->cl_cb_client = client; clp->cl_cb_cred = cred; rcu_read_lock(); @@ -1278,18 +1305,33 @@ static int grab_slot(struct nfsd4_session *ses) static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd4_session *ses = clp->cl_cb_session; + struct nfsd4_session *ses; if (cb->cb_held_slot >= 0) return true; + + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (!ses) { + rcu_read_unlock(); + rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); + return false; + } cb->cb_held_slot = grab_slot(ses); if (cb->cb_held_slot < 0) { + rcu_read_unlock(); rpc_sleep_on(&clp->cl_cb_waitq, task, NULL); /* Race breaker */ - cb->cb_held_slot = grab_slot(ses); + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (ses) + cb->cb_held_slot = grab_slot(ses); + rcu_read_unlock(); if (cb->cb_held_slot < 0) return false; rpc_wake_up_queued_task(&clp->cl_cb_waitq, task); + } else { + rcu_read_unlock(); } return true; } @@ -1297,12 +1339,17 @@ static bool nfsd41_cb_get_slot(struct nfsd4_callback *cb, struct rpc_task *task) static void nfsd41_cb_release_slot(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; - struct nfsd4_session *ses = clp->cl_cb_session; + struct nfsd4_session *ses; if (cb->cb_held_slot >= 0) { - spin_lock(&ses->se_lock); - ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); - spin_unlock(&ses->se_lock); + rcu_read_lock(); + ses = rcu_dereference(clp->cl_cb_session); + if (ses) { + spin_lock(&ses->se_lock); + ses->se_cb_slot_avail |= BIT(cb->cb_held_slot); + spin_unlock(&ses->se_lock); + } + rcu_read_unlock(); cb->cb_held_slot = -1; rpc_wake_up_next(&clp->cl_cb_waitq); } @@ -1434,22 +1481,35 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata) trace_nfsd_cb_rpc_prepare(clp); cb->cb_seq_status = 1; cb->cb_status = 0; - if (minorversion && !nfsd41_cb_get_slot(cb, task)) - return; + if (minorversion) { + if (!rcu_access_pointer(clp->cl_cb_session)) { + rpc_exit(task, -EIO); + return; + } + if (!nfsd41_cb_get_slot(cb, task)) + return; + } rpc_call_start(task); } /* Returns true if CB_COMPOUND processing should continue */ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb) { - struct nfsd4_session *session = cb->cb_clp->cl_cb_session; + struct nfsd4_session *session; bool ret = false; if (cb->cb_held_slot < 0) goto requeue; + rcu_read_lock(); + session = rcu_dereference(cb->cb_clp->cl_cb_session); + if (!session) { + rcu_read_unlock(); + goto requeue; + } + /* This is the operation status code for CB_SEQUENCE */ - trace_nfsd_cb_seq_status(task, cb); + trace_nfsd_cb_seq_status(task, cb, session); switch (cb->cb_seq_status) { case 0: /* @@ -1481,12 +1541,16 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback fallthrough; case -NFS4ERR_BADSESSION: nfsd4_mark_cb_fault(cb->cb_clp); + rcu_read_unlock(); goto requeue; case -NFS4ERR_DELAY: cb->cb_seq_status = 1; - if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) + if (RPC_SIGNALLED(task) || !rpc_restart_call(task)) { + rcu_read_unlock(); goto requeue; + } rpc_delay(task, 2 * HZ); + rcu_read_unlock(); return false; case -NFS4ERR_SEQ_MISORDERED: case -NFS4ERR_BADSLOT: @@ -1498,11 +1562,13 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback */ nfsd4_mark_cb_fault(cb->cb_clp); cb->cb_held_slot = -1; + rcu_read_unlock(); goto retry_nowait; default: nfsd4_mark_cb_fault(cb->cb_clp); } - trace_nfsd_cb_free_slot(task, cb); + trace_nfsd_cb_free_slot(task, cb, session); + rcu_read_unlock(); nfsd41_cb_release_slot(cb); return ret; retry_nowait: @@ -1624,7 +1690,15 @@ static struct nfsd4_conn * __nfsd4_find_backchannel(struct nfs4_client *clp) * Note there isn't a lot of locking in this code; instead we depend on * the fact that it is run from clp->cl_callback_wq, which won't run two * work items at once. So, for example, clp->cl_callback_wq handles all - * access of cl_cb_client and all calls to rpc_create or rpc_shutdown_client. + * access of cl_cb_client, and all calls to rpc_create or + * rpc_shutdown_client. + * + * cl_cb_session is written only from cl_callback_wq (via + * rcu_assign_pointer) and read from rpciod under rcu_read_lock (via + * rcu_dereference) by encode_cb_sequence4args(), decode_cb_sequence4resok(), + * nfsd4_cb_sequence_done(), and the cb-slot helpers. Sessions are freed + * with kfree_rcu() so that rpciod readers in an RCU read-side critical + * section never dereference a freed session. */ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) { @@ -1676,6 +1750,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) nfsd4_mark_cb_down(clp); if (c) svc_xprt_put(c->cn_xprt); + rcu_assign_pointer(clp->cl_cb_session, ses); return; } } diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index f34320e4c2f4..279ff1e9dffb 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -247,13 +247,20 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, nfsd4_init_cb(&ls->ls_recall, clp, &nfsd4_cb_layout_ops, NFSPROC4_CLNT_CB_LAYOUT); - if (parent->sc_type == SC_TYPE_DELEG) + if (parent->sc_type == SC_TYPE_DELEG) { + spin_lock(&fp->fi_lock); ls->ls_file = nfsd_file_get(fp->fi_deleg_file); - else + spin_unlock(&fp->fi_lock); + } else { ls->ls_file = find_any_file(fp); - BUG_ON(!ls->ls_file); + } + if (!ls->ls_file) { + nfs4_put_stid(stp); + return NULL; + } ls->ls_fenced = false; + ls->ls_fence_inflight = false; ls->ls_fence_delay = 0; INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker); @@ -791,15 +798,6 @@ nfsd4_layout_fence_worker(struct work_struct *work) struct nfs4_client *clp; struct nfsd_net *nn; - /* - * The workqueue clears WORK_STRUCT_PENDING before invoking - * this callback. Re-arm immediately so that - * delayed_work_pending() returns true while the fence - * operation is in progress, preventing - * lm_breaker_timedout() from taking a duplicate reference. - */ - mod_delayed_work(system_dfl_wq, &ls->ls_fence_work, 0); - spin_lock(&ls->ls_lock); if (list_empty(&ls->ls_layouts)) { spin_unlock(&ls->ls_lock); @@ -809,6 +807,9 @@ dispose: nfsd4_close_layout(ls); ls->ls_fenced = true; + spin_lock(&ls->ls_lock); + ls->ls_fence_inflight = false; + spin_unlock(&ls->ls_lock); nfs4_put_stid(&ls->ls_stid); return; } @@ -894,18 +895,26 @@ nfsd4_layout_lm_breaker_timedout(struct file_lease *fl) if ((!nfsd4_layout_ops[ls->ls_layout_type]->fence_client) || ls->ls_fenced) return true; - if (delayed_work_pending(&ls->ls_fence_work)) - return false; /* * Make sure layout has not been returned yet before - * taking a reference count on the layout stateid. + * taking a reference count on the layout stateid. The + * ls_fence_inflight flag is set together with the sc_count + * increment under ls_lock so that a fence worker invocation + * already in progress (which has cleared WORK_STRUCT_PENDING + * but not yet reached dispose:) cannot be coalesced with a + * fresh schedule that takes an extra unmatched reference. */ spin_lock(&ls->ls_lock); + if (ls->ls_fence_inflight) { + spin_unlock(&ls->ls_lock); + return false; + } if (list_empty(&ls->ls_layouts) || !refcount_inc_not_zero(&ls->ls_stid.sc_count)) { spin_unlock(&ls->ls_lock); return true; } + ls->ls_fence_inflight = true; spin_unlock(&ls->ls_lock); mod_delayed_work(system_dfl_wq, &ls->ls_fence_work, 0); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 8561540ab2db..e3c3249e63be 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -306,10 +306,6 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; } - status = fh_compose(resfhp, fhp->fh_export, child, fhp); - if (status != nfs_ok) - goto out; - v_mtime = 0; v_atime = 0; if (nfsd4_create_is_exclusive(open->op_createmode)) { @@ -335,6 +331,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (status != nfs_ok) goto out; + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + switch (open->op_createmode) { case NFS4_CREATE_UNCHECKED: if (!d_is_reg(child)) @@ -385,6 +385,10 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, open->op_created = true; fh_fill_post_attrs(fhp); + status = fh_compose(resfhp, fhp->fh_export, child, fhp); + if (status != nfs_ok) + goto out; + /* A newly created file already has a file size of zero. */ if ((iap->ia_valid & ATTR_SIZE) && (iap->ia_size == 0)) iap->ia_valid &= ~ATTR_SIZE; @@ -663,7 +667,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, pr_warn("nfsd4_process_open2 failed to open newly-created file: status=%u\n", be32_to_cpu(status)); if (reclaim && !status) - nn->somebody_reclaimed = true; + set_bit(NFSD_NET_SOMEBODY_RECLAIMED, &nn->flags); out: if (open->op_filp) { fput(open->op_filp); @@ -677,8 +681,6 @@ out: nfsd4_cleanup_open_state(cstate, open); nfsd4_bump_seqid(cstate, status); out_err: - posix_acl_release(open->op_dpacl); - posix_acl_release(open->op_pacl); return status; } @@ -700,6 +702,13 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat return nfsd4_open(rqstp, cstate, &op->u); } +static void +nfsd4_open_release(union nfsd4_op_u *u) +{ + posix_acl_release(u->open.op_dpacl); + posix_acl_release(u->open.op_pacl); +} + /* * filehandle-manipulating ops. */ @@ -839,6 +848,20 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out_aftermask; + /* Sanitize cr_type to avoid returning ATTRNOTSUPP. */ + switch (create->cr_type) { + case NF4LNK: + case NF4BLK: + case NF4CHR: + case NF4SOCK: + case NF4FIFO: + case NF4DIR: + break; + default: + status = nfserr_badtype; + goto out_aftermask; + } + if (create->cr_acl) { if (attrs.na_dpacl || attrs.na_pacl) { status = nfserr_inval; @@ -846,6 +869,8 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } status = nfsd4_acl_to_attr(create->cr_type, create->cr_acl, &attrs); + if (status != nfs_ok) + goto out_aftermask; } current->fs->umask = create->cr_umask; switch (create->cr_type) { @@ -1253,7 +1278,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (deleg_attrs) { status = nfserr_bad_stateid; - if (st->sc_type & SC_TYPE_DELEG) { + if (st && (st->sc_type & SC_TYPE_DELEG)) { struct nfs4_delegation *dp = delegstateid(st); /* Only for *_ATTRS_DELEG flavors */ @@ -1494,6 +1519,9 @@ static void nfs4_put_copy(struct nfsd4_copy *copy) { if (!refcount_dec_and_test(©->refcount)) return; + /* Drop the task_struct pinned in nfsd4_copy(); NULL on sync copies. */ + if (copy->copy_task) + put_task_struct(copy->copy_task); kfree(copy->cp_src); kfree(copy); } @@ -1503,20 +1531,18 @@ static void release_copy_files(struct nfsd4_copy *copy); static void nfsd4_stop_copy(struct nfsd4_copy *copy) { trace_nfsd_copy_async_cancel(copy); - if (!test_and_set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags)) { - kthread_stop(copy->copy_task); - if (!test_bit(NFSD4_COPY_F_CB_ERROR, ©->cp_flags)) - copy->nfserr = nfs_ok; - set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); - } - /* - * The copy was removed from async_copies before this function - * was called, so the reaper cannot clean it up. Release files - * here regardless of who won the STOPPED race. If the thread - * set STOPPED, it has finished using the files. If STOPPED - * was set here, kthread_stop() waited for the thread to exit. + * Join the kthread before releasing its resources. The task_struct is + * pinned in nfsd4_copy(), so kthread_stop() is safe even after the + * one-shot kthread has exited. The caller already unlinked the copy, + * so this runs once per copy. */ + set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags); + kthread_stop(copy->copy_task); + if (!test_bit(NFSD4_COPY_F_CB_ERROR, ©->cp_flags)) + copy->nfserr = nfs_ok; + set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); + release_copy_files(copy); nfs4_put_copy(copy); } @@ -1530,7 +1556,13 @@ static struct nfsd4_copy *nfsd4_unhash_copy(struct nfs4_client *clp) copy = list_first_entry(&clp->async_copies, struct nfsd4_copy, copies); refcount_inc(©->refcount); - copy->cp_clp = NULL; + /* + * Unlinking hides the copy from the reaper, so drop its + * s2s_cp_stateids entry here while cp_clp is still valid. + */ + nfs4_free_copy_state(copy); + /* Pairs with smp_load_acquire() in nfsd4_send_cb_offload(). */ + smp_store_release(©->cp_clp, NULL); if (!list_empty(©->copies)) list_del_init(©->copies); } @@ -1542,8 +1574,11 @@ void nfsd4_shutdown_copy(struct nfs4_client *clp) { struct nfsd4_copy *copy; - while ((copy = nfsd4_unhash_copy(clp)) != NULL) + while ((copy = nfsd4_unhash_copy(clp)) != NULL) { nfsd4_stop_copy(copy); + /* Reaper can't reach the unhashed copy; drop its membership ref. */ + nfs4_put_copy(copy); + } } static bool nfsd4_copy_on_sb(const struct nfsd4_copy *copy, @@ -1606,7 +1641,11 @@ void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb) struct nfs4_client *clp = copy->cp_clp; list_del_init(©->copies); + /* Reaper can't reach it; drop the s2s entry while cp_clp is valid. */ + nfs4_free_copy_state(copy); nfsd4_stop_copy(copy); + /* Drop the membership ref the reaper would have dropped. */ + nfs4_put_copy(copy); nfsd4_put_client(clp); } } @@ -1901,6 +1940,8 @@ static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) set_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags); nfsd4_put_client(cb->cb_clp); + /* Drop the copy reference taken in nfsd4_send_cb_offload(). */ + nfs4_put_copy(copy); } static int nfsd4_cb_offload_done(struct nfsd4_callback *cb, @@ -1950,6 +1991,7 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, /* See RFC 7862 p.67: */ if (bytes_total == 0) bytes_total = ULLONG_MAX; + since = READ_ONCE(dst->f_wb_err); do { /* Only async copies can be stopped here */ if (kthread_should_stop()) @@ -1965,13 +2007,14 @@ static ssize_t _nfsd_copy_file_range(struct nfsd4_copy *copy, } while (bytes_total > 0 && nfsd4_copy_is_async(copy)); /* for a non-zero asynchronous copy do a commit of data */ if (nfsd4_copy_is_async(copy) && copy->cp_res.wr_bytes_written > 0) { - since = READ_ONCE(dst->f_wb_err); end = copy->cp_dst_pos + copy->cp_res.wr_bytes_written - 1; status = vfs_fsync_range(dst, copy->cp_dst_pos, end, 0); if (!status) status = filemap_check_wb_err(dst->f_mapping, since); if (!status) set_bit(NFSD4_COPY_F_COMMITTED, ©->cp_flags); + else if (status != -EAGAIN && status != -ESTALE) + nfsd_reset_write_verifier(copy->cp_nn); } return bytes_copied; } @@ -2030,28 +2073,29 @@ static void release_copy_files(struct nfsd4_copy *copy) } } +/* + * Called from the reaper and from nfsd4_copy()'s error path; in both + * cases the copy is already unreachable from clp->async_copies. + */ static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); release_copy_files(copy); - if (copy->cp_clp) { - spin_lock(©->cp_clp->async_lock); - if (!list_empty(©->copies)) - list_del_init(©->copies); - spin_unlock(©->cp_clp->async_lock); - } nfs4_put_copy(copy); } static void nfsd4_send_cb_offload(struct nfsd4_copy *copy) { struct nfsd4_cb_offload *cbo = ©->cp_cb_offload; - struct nfs4_client *clp = copy->cp_clp; + struct nfs4_client *clp; /* - * cp_clp is NULL when called via nfsd4_shutdown_copy() during - * client destruction. Skip the callback; the client is gone. + * Pairs with smp_store_release(&cp_clp) in find_async_copy() and + * nfsd4_unhash_copy(); the set_bit/clear_bit writers are unordered. + * cp_clp is NULL once the copy was canceled; skip the callback, the + * canceling path owns the notification. */ + clp = smp_load_acquire(©->cp_clp); if (!clp) { set_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags); return; @@ -2063,10 +2107,12 @@ static void nfsd4_send_cb_offload(struct nfsd4_copy *copy) cbo->co_retries = 5; /* - * Hold a reference on the client while the callback is in flight. - * Released in nfsd4_cb_offload_release(). + * Hold the client and the copy across the in-flight callback; co_cb is + * embedded in the copy, so it must outlive the callback. Both are + * dropped in nfsd4_cb_offload_release(). */ kref_get(&clp->cl_nfsdfs.cl_ref); + refcount_inc(©->refcount); nfsd4_init_cb(&cbo->co_cb, clp, &nfsd4_cb_offload_ops, NFSPROC4_CLNT_CB_OFFLOAD); @@ -2118,16 +2164,20 @@ static int nfsd4_do_async_copy(void *data) do_callback: if (!test_bit(NFSD4_COPY_F_CB_ERROR, ©->cp_flags)) copy->nfserr = nfserr; - /* The kthread exits forthwith. Ensure that a subsequent - * OFFLOAD_CANCEL won't try to kill it again. */ - set_bit(NFSD4_COPY_F_STOPPED, ©->cp_flags); - + /* + * Don't set NFSD4_COPY_F_STOPPED here: it tells a teardown caller it + * may skip kthread_stop(), which would then release nf_dst and the + * client while still in use. Only nfsd4_stop_copy() sets it, after + * joining. + */ set_bit(NFSD4_COPY_F_COMPLETED, ©->cp_flags); trace_nfsd_copy_async_done(copy); atomic_dec(©->cp_nn->pending_async_copies); if (copy->cp_res.wr_bytes_written > 0 && copy->attr_update) nfsd_update_cmtime_attr(copy->nf_dst->nf_file, 0); nfsd4_send_cb_offload(copy); + /* Drop the kthread's reference (taken in nfsd4_copy()); copy may be freed after this. */ + nfs4_put_copy(copy); return 0; } @@ -2153,21 +2203,21 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); if (status) { - trace_nfsd_copy_done(copy, status); - return nfserr_offload_denied; + status = nfserr_offload_denied; + goto out; } } else { trace_nfsd_copy_intra(copy); status = nfsd4_setup_intra_ssc(rqstp, cstate, copy); - if (status) { - trace_nfsd_copy_done(copy, status); - return status; - } + if (status) + goto out; } memcpy(©->fh, &cstate->current_fh.fh_handle, sizeof(struct knfsd_fh)); if (nfsd4_copy_is_async(copy)) { + struct task_struct *task; + async_copy = kzalloc_obj(struct nfsd4_copy); if (!async_copy) goto out_err; @@ -2182,11 +2232,12 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, async_copy->cp_src = kmalloc_obj(*async_copy->cp_src); if (!async_copy->cp_src) goto out_dec_async_copy_err; - if (!nfs4_init_copy_state(nn, copy)) + dup_copy_fields(copy, async_copy); + + if (!nfs4_init_copy_state(nn, async_copy)) goto out_dec_async_copy_err; - memcpy(&result->cb_stateid, ©->cp_stateid.cs_stid, + memcpy(&result->cb_stateid, &async_copy->cp_stateid.cs_stid, sizeof(result->cb_stateid)); - dup_copy_fields(copy, async_copy); if ((READ_ONCE(copy->nf_dst->nf_file->f_mode) & FMODE_NOCMTIME) != 0) async_copy->attr_update = true; @@ -2195,15 +2246,27 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, NFS4_MAX_SESSIONID_LEN); async_copy->cp_cb_offload.co_referring_slotid = cstate->slot->sl_index; async_copy->cp_cb_offload.co_referring_seqno = cstate->slot->sl_seqid; - async_copy->copy_task = kthread_create(nfsd4_do_async_copy, - async_copy, "%s", "copy thread"); - if (IS_ERR(async_copy->copy_task)) + task = kthread_create(nfsd4_do_async_copy, async_copy, + "%s", "copy thread"); + if (IS_ERR(task)) goto out_dec_async_copy_err; + /* + * Pin the task_struct so kthread_stop() is safe after this + * one-shot kthread exits. Released by nfs4_put_copy(). + */ + get_task_struct(task); + async_copy->copy_task = task; + /* + * Take the kthread's ref and wake it before publishing, so the + * publisher touches async_copy no further and teardown can + * drain it. + */ + refcount_inc(&async_copy->refcount); + wake_up_process(async_copy->copy_task); spin_lock(&async_copy->cp_clp->async_lock); list_add(&async_copy->copies, &async_copy->cp_clp->async_copies); spin_unlock(&async_copy->cp_clp->async_lock); - wake_up_process(async_copy->copy_task); status = nfs_ok; } else { status = nfsd4_do_copy(copy, copy->nf_src->nf_file, @@ -2257,8 +2320,18 @@ find_async_copy(struct nfs4_client *clp, stateid_t *stateid) spin_lock(&clp->async_lock); copy = find_async_copy_locked(clp, stateid); - if (copy) + if (copy) { refcount_inc(©->refcount); + nfs4_free_copy_state(copy); + /* + * Mirror nfsd4_unhash_copy(): unlink and clear cp_clp under + * async_lock so the reaper can't reach it. Caller drops the + * membership ref after nfsd4_stop_copy(). + */ + smp_store_release(©->cp_clp, NULL); + if (!list_empty(©->copies)) + list_del_init(©->copies); + } spin_unlock(&clp->async_lock); return copy; } @@ -2277,8 +2350,11 @@ nfsd4_offload_cancel(struct svc_rqst *rqstp, struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); return manage_cpntf_state(nn, &os->stateid, clp, NULL); - } else + } else { nfsd4_stop_copy(copy); + /* find_async_copy() unlinked it from the reaper; drop the membership ref. */ + nfs4_put_copy(copy); + } return nfs_ok; } @@ -2292,7 +2368,6 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct nfs4_stid *stid = NULL; struct nfs4_cpntf_state *cps; - struct nfs4_client *clp = cstate->clp; status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, &cn->cpn_src_stateid, RD_STATE, NULL, @@ -2306,12 +2381,14 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cn->cpn_lease_time.tv_nsec = 0; status = nfserrno(-ENOMEM); + /* + * The returned cps is published and fully initialized, and carries an + * extra reference for us; drop it once we are done with it. + */ cps = nfs4_alloc_init_cpntf_state(nn, stid); if (!cps) goto out; memcpy(&cn->cpn_cnr_stateid, &cps->cp_stateid.cs_stid, sizeof(stateid_t)); - memcpy(&cps->cp_p_stateid, &stid->sc_stateid, sizeof(stateid_t)); - memcpy(&cps->cp_p_clid, &clp->cl_clientid, sizeof(clientid_t)); /* For now, only return one server address in cpn_src, the * address used by the client to connect to this server. @@ -2320,10 +2397,11 @@ nfsd4_copy_notify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfsd4_set_netaddr((struct sockaddr *)&rqstp->rq_daddr, &cn->cpn_src->u.nl4_addr); WARN_ON_ONCE(status); - if (status) { - nfs4_put_cpntf_state(nn, cps); - goto out; - } + /* + * Drop our extra reference. The membership reference keeps the entry + * alive for a later inter-server READ, or until the laundromat reaps it. + */ + nfs4_put_cpntf_state(nn, cps); out: nfs4_put_stid(stid); return status; @@ -3119,9 +3197,22 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) op->status = nfsd4_open_omfg(rqstp, cstate, op); goto encode_op; } - if (!current_fh->fh_dentry && - !HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) { - if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { + if (!current_fh->fh_dentry) { + if (HAS_FH_FLAG(current_fh, NFSD4_FH_FOREIGN)) { + /* + * FOREIGN fh from inter-SSC PUTFH: only + * SAVEFH may proceed with a NULL fh_dentry. + * Per RFC 7862 S15.2.3, validation of a + * foreign fh is deferred to the operation + * that consumes it, and NFS4ERR_STALE is + * returned at that point. + */ + if (op->opnum != OP_SAVEFH && + !(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { + op->status = nfserr_stale; + goto encode_op; + } + } else if (!(op->opdesc->op_flags & ALLOWED_WITHOUT_FH)) { op->status = nfserr_nofilehandle; goto encode_op; } @@ -3185,6 +3276,9 @@ encode_op: status = op->status; } + if (op->opdesc && op->opdesc->op_release) + op->opdesc->op_release(&op->u); + trace_nfsd_compound_status(args->client_opcnt, resp->opcnt, status, nfsd4_op_name(op->opnum)); @@ -3507,7 +3601,7 @@ static u32 nfsd4_get_dir_delegation_rsize(const struct svc_rqst *rqstp, op_encode_stateid_maxsz + 2 /* gddr_notification */ + 2 /* gddr_child_attributes */ + - 2 /* gddr_dir_attributes */); + 2 /* gddr_dir_attributes */) * sizeof(__be32); } #ifdef CONFIG_NFSD_PNFS @@ -3684,6 +3778,7 @@ static const struct nfsd4_operation nfsd4_ops[] = { }, [OP_OPEN] = { .op_func = nfsd4_open, + .op_release = nfsd4_open_release, .op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING, .op_name = "OP_OPEN", .op_rsize_bop = nfsd4_open_rsize, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 6ea25a52d2f4..d513971fb119 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -167,7 +167,7 @@ out_end: end_creating(dentry); out: if (status == 0) { - if (nn->in_grace) + if (test_bit(NFSD_NET_IN_GRACE, &nn->flags)) __nfsd4_create_reclaim_record_grace(clp, dname, nn); vfs_fsync(nn->rec_file, 0); } else { @@ -285,10 +285,12 @@ __nfsd4_remove_reclaim_record_grace(const char *dname, int len, return; } name.len = len; + down_write(&nn->reclaim_str_hashtbl_lock); crp = nfsd4_find_reclaim_client(name, nn); - kfree(name.data); if (crp) nfs4_remove_reclaim_record(crp, nn); + up_write(&nn->reclaim_str_hashtbl_lock); + kfree(name.data); } static void @@ -317,7 +319,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) nfs4_reset_creds(original_cred); if (status == 0) { vfs_fsync(nn->rec_file, 0); - if (nn->in_grace) + if (test_bit(NFSD_NET_IN_GRACE, &nn->flags)) __nfsd4_remove_reclaim_record_grace(dname, HEXDIR_LEN, nn); } @@ -373,7 +375,7 @@ nfsd4_recdir_purge_old(struct nfsd_net *nn) { int status; - nn->in_grace = false; + clear_bit(NFSD_NET_IN_GRACE, &nn->flags); if (!nn->rec_file) return; status = mnt_want_write_file(nn->rec_file); @@ -455,7 +457,7 @@ nfsd4_init_recdir(struct net *net) nfs4_reset_creds(original_cred); if (!status) - nn->in_grace = true; + set_bit(NFSD_NET_IN_GRACE, &nn->flags); return status; } @@ -484,6 +486,7 @@ nfs4_legacy_state_init(struct net *net) for (i = 0; i < CLIENT_HASH_SIZE; i++) INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]); nn->reclaim_str_hashtbl_size = 0; + init_rwsem(&nn->reclaim_str_hashtbl_lock); return 0; } @@ -598,13 +601,16 @@ nfsd4_check_legacy_client(struct nfs4_client *clp) goto out_enoent; } name.len = HEXDIR_LEN; + down_read(&nn->reclaim_str_hashtbl_lock); crp = nfsd4_find_reclaim_client(name, nn); - kfree(name.data); if (crp) { set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags); crp->cr_clp = clp; - return 0; } + up_read(&nn->reclaim_str_hashtbl_lock); + kfree(name.data); + if (crp) + return 0; out_enoent: return -ENOENT; @@ -1176,6 +1182,7 @@ nfsd4_cld_check(struct nfs4_client *clp) return 0; /* look for it in the reclaim hashtable otherwise */ + down_read(&nn->reclaim_str_hashtbl_lock); crp = nfsd4_find_reclaim_client(clp->cl_name, nn); if (crp) goto found; @@ -1191,6 +1198,7 @@ nfsd4_cld_check(struct nfs4_client *clp) if (!name.data) { dprintk("%s: failed to allocate memory for name.data!\n", __func__); + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; } name.len = HEXDIR_LEN; @@ -1201,9 +1209,11 @@ nfsd4_cld_check(struct nfs4_client *clp) } #endif + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; found: crp->cr_clp = clp; + up_read(&nn->reclaim_str_hashtbl_lock); return 0; } @@ -1215,6 +1225,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) struct cld_net *cn = nn->cld_net; #endif struct nfs4_client_reclaim *crp; + unsigned int princhashlen; char *principal = NULL; /* did we already find that this client is stable? */ @@ -1222,6 +1233,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) return 0; /* look for it in the reclaim hashtable otherwise */ + down_read(&nn->reclaim_str_hashtbl_lock); crp = nfsd4_find_reclaim_client(clp->cl_name, nn); if (crp) goto found; @@ -1237,6 +1249,7 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) if (!name.data) { dprintk("%s: failed to allocate memory for name.data\n", __func__); + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; } name.len = HEXDIR_LEN; @@ -1247,23 +1260,31 @@ nfsd4_cld_check_v2(struct nfs4_client *clp) } #endif + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; found: - if (crp->cr_princhash.len) { + princhashlen = crp->cr_princhash.len; + if (princhashlen) { u8 digest[SHA256_DIGEST_SIZE]; + u8 *pdata; if (clp->cl_cred.cr_raw_principal) principal = clp->cl_cred.cr_raw_principal; else if (clp->cl_cred.cr_principal) principal = clp->cl_cred.cr_principal; - if (principal == NULL) + if (principal == NULL) { + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; + } sha256(principal, strlen(principal), digest); - if (memcmp(crp->cr_princhash.data, digest, - crp->cr_princhash.len)) + pdata = crp->cr_princhash.data; + if (memcmp(pdata, digest, princhashlen)) { + up_read(&nn->reclaim_str_hashtbl_lock); return -ENOENT; + } } crp->cr_clp = clp; + up_read(&nn->reclaim_str_hashtbl_lock); return 0; } @@ -1362,7 +1383,8 @@ nfs4_cld_state_init(struct net *net) for (i = 0; i < CLIENT_HASH_SIZE; i++) INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]); nn->reclaim_str_hashtbl_size = 0; - nn->track_reclaim_completes = true; + init_rwsem(&nn->reclaim_str_hashtbl_lock); + set_bit(NFSD_NET_TRACK_RECLAIM_COMPLETES, &nn->flags); atomic_set(&nn->nr_reclaim_complete, 0); return 0; @@ -1373,7 +1395,7 @@ nfs4_cld_state_shutdown(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nn->track_reclaim_completes = false; + clear_bit(NFSD_NET_TRACK_RECLAIM_COMPLETES, &nn->flags); kfree(nn->reclaim_str_hashtbl); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a42f34842d77..386ca748522b 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -939,7 +939,7 @@ out_free: * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, - unsigned char cs_type) + unsigned char cs_type, struct nfs4_stid *p_stid) { int new_id; @@ -949,19 +949,34 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); - stid->cs_stid.si_opaque.so_id = new_id; - stid->cs_stid.si_generation = 1; + if (new_id >= 0) { + stid->cs_stid.si_opaque.so_id = new_id; + stid->cs_stid.si_generation = 1; + /* + * Set cs_type and link onto sc_cp_list under the same lock + * that installed the IDR entry, so a concurrent + * manage_cpntf_state() sees either no entry or a fully + * linked cp_list. + */ + stid->cs_type = cs_type; + if (p_stid) { + struct nfs4_cpntf_state *cps = + container_of(stid, struct nfs4_cpntf_state, + cp_stateid); + + list_add(&cps->cp_list, &p_stid->sc_cp_list); + } + } spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; - stid->cs_type = cs_type; return 1; } int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) { - return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); + return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID, NULL); } struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, @@ -972,13 +987,21 @@ struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, cps = kzalloc_obj(struct nfs4_cpntf_state); if (!cps) return NULL; + /* So a stale list_del_init() before linking is a no-op. */ + INIT_LIST_HEAD(&cps->cp_list); cps->cpntf_time = ktime_get_boottime_seconds(); - refcount_set(&cps->cp_stateid.cs_count, 1); - if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) + /* + * Fully initialize the entry before nfs4_init_cp_state() publishes it, + * since a concurrent OFFLOAD_CANCEL could then free it. Take an extra + * reference for the caller (dropped with nfs4_put_cpntf_state()). + */ + memcpy(&cps->cp_p_stateid, &p_stid->sc_stateid, sizeof(stateid_t)); + memcpy(&cps->cp_p_clid, &p_stid->sc_client->cl_clientid, + sizeof(clientid_t)); + refcount_set(&cps->cp_stateid.cs_count, 2); + if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID, + p_stid)) goto out_free; - spin_lock(&nn->s2s_cp_lock); - list_add(&cps->cp_list, &p_stid->sc_cp_list); - spin_unlock(&nn->s2s_cp_lock); return cps; out_free: kfree(cps); @@ -998,18 +1021,66 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) spin_unlock(&nn->s2s_cp_lock); } +/* + * Drop the parent's reference on an already-unlinked cpntf entry. If a + * concurrent holder still owns a reference, its nfs4_put_cpntf_state() does + * the final free. + * + * nn->s2s_cp_lock must be held. + */ +static void put_cpntf_state_unlinked_locked(struct nfs4_cpntf_state *cps) +{ + WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); + WARN_ON_ONCE(!list_empty(&cps->cp_list)); + + if (refcount_dec_and_test(&cps->cp_stateid.cs_count)) + kfree(cps); +} + +/* + * Unhash from the IDR and sc_cp_list. Gated on list_empty() to avoid + * evicting a recycled so_id. + */ +static void nfsd4_unhash_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + lockdep_assert_held(&nn->s2s_cp_lock); + + if (!list_empty(&cps->cp_list)) { + list_del_init(&cps->cp_list); + idr_remove(&nn->s2s_cp_stateids, cps->cp_stateid.cs_stid.si_opaque.so_id); + } +} + +/* + * Revoke a copy-notify stateid: unlink it from the IDR and sc_cp_list first + * so no new finder can discover it, then drop the membership reference. Every + * revoke path (cancel, laundromat, drain) must use this rather than + * _free_cpntf_state_locked(), which unlinks only at refcount zero and so could + * let a second revoke free the entry under a concurrent reader. + * + * nn->s2s_cp_lock must be held. + */ +static void revoke_cpntf_state_locked(struct nfsd_net *nn, + struct nfs4_cpntf_state *cps) +{ + nfsd4_unhash_cpntf_state(nn, cps); + put_cpntf_state_unlinked_locked(cps); +} + static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) { - struct nfs4_cpntf_state *cps; + struct nfs4_cpntf_state *cps, *tmp; struct nfsd_net *nn; nn = net_generic(net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); - while (!list_empty(&stid->sc_cp_list)) { - cps = list_first_entry(&stid->sc_cp_list, - struct nfs4_cpntf_state, cp_list); - _free_cpntf_state_locked(nn, cps); - } + /* + * Revoke unlinks each entry before dropping the parent's reference, so + * the drain terminates in one pass per entry regardless of cs_count; a + * concurrent holder does the final kfree via nfs4_put_cpntf_state(). + */ + list_for_each_entry_safe(cps, tmp, &stid->sc_cp_list, cp_list) + revoke_cpntf_state_locked(nn, cps); spin_unlock(&nn->s2s_cp_lock); } @@ -1889,9 +1960,19 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) struct nfs4_client *clp; retry: list_for_each_entry(clp, head, cl_idhash) { - struct nfs4_stid *stid = find_one_sb_stid(clp, sb, - sc_types); + struct nfs4_stid *stid; + + /* + * force_expire_client() ignores cl_rpc_users once + * its wait_event() has passed, so pinning cannot + * keep an already-expiring client alive; the + * expiry path revokes its states instead. + */ + if (is_client_expired(clp)) + continue; + stid = find_one_sb_stid(clp, sb, sc_types); if (stid) { + atomic_inc(&clp->cl_rpc_users); spin_unlock(&nn->client_lock); revoke_one_stid(nn, clp, stid); nfs4_put_stid(stid); @@ -1904,6 +1985,9 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) */ nn->nfs40_last_revoke = ktime_get_boottime_seconds(); + if (atomic_dec_and_test(&clp->cl_rpc_users) && + is_client_expired(clp)) + wake_up_all(&expiry_wq); goto retry; } } @@ -2295,7 +2379,7 @@ static void __free_session(struct nfsd4_session *ses) { free_session_slots(ses, 0); xa_destroy(&ses->se_slots); - kfree(ses); + kfree_rcu(ses, rcu_head); } static void free_session(struct nfsd4_session *ses) @@ -2641,14 +2725,24 @@ __destroy_client(struct nfs4_client *clp) release_openowner(oo); } for (i = 0; i < OWNER_HASH_SIZE; i++) { - struct nfs4_stateowner *so, *tmp; + struct nfs4_stateowner *so; - list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], - so_strhash) { + spin_lock(&clp->cl_lock); + while (!list_empty(&clp->cl_ownerstr_hashtbl[i])) { + so = list_first_entry(&clp->cl_ownerstr_hashtbl[i], + struct nfs4_stateowner, so_strhash); /* Should be no openowners at this point */ WARN_ON_ONCE(so->so_is_open_owner); + nfs4_get_stateowner(so); + unhash_lockowner_locked(lockowner(so)); + spin_unlock(&clp->cl_lock); + remove_blocked_locks(lockowner(so)); + nfs4_put_stateowner(so); + + spin_lock(&clp->cl_lock); } + spin_unlock(&clp->cl_lock); } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_copy(clp); @@ -2675,16 +2769,23 @@ static void inc_reclaim_complete(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - if (!nn->track_reclaim_completes) + if (!test_bit(NFSD_NET_TRACK_RECLAIM_COMPLETES, &nn->flags)) return; - if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) + + down_read(&nn->reclaim_str_hashtbl_lock); + if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) { + up_read(&nn->reclaim_str_hashtbl_lock); return; + } if (atomic_inc_return(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) { + up_read(&nn->reclaim_str_hashtbl_lock); printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", clp->net->ns.inum); nfsd4_end_grace(nn); + return; } + up_read(&nn->reclaim_str_hashtbl_lock); } static void expire_client(struct nfs4_client *clp) @@ -3259,6 +3360,11 @@ static void force_expire_client(struct nfs4_client *clp) trace_nfsd_clid_admin_expired(&clp->cl_clientid); + /* + * cl_time is cleared under client_lock before the wait so a + * revocation walk pinning cl_rpc_users under it either skips + * this client or is seen by this wait_event(). + */ spin_lock(&nn->client_lock); clp->cl_time = 0; spin_unlock(&nn->client_lock); @@ -3414,7 +3520,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name, clp->cl_time = ktime_get_boottime_seconds(); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); - clp->cl_cb_session = NULL; + RCU_INIT_POINTER(clp->cl_cb_session, NULL); clp->net = net; clp->cl_nfsd_dentry = nfsd_client_mkdir( nn, &clp->cl_nfsdfs, @@ -4496,6 +4602,19 @@ static void nfsd4_construct_sequence_response(struct nfsd4_session *session, seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; } +static bool nfsd4_slots_inuse(struct nfsd4_session *ses, int from) +{ + int i; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + if (slot->sl_flags & NFSD4_SLOT_INUSE) + return true; + } + return false; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -4575,7 +4694,9 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (session->se_target_maxslots < session->se_fchannel.maxreqs && slot->sl_generation == session->se_slot_gen && - seq->maxslots <= session->se_target_maxslots) + seq->maxslots <= session->se_target_maxslots && + seq->slotid < session->se_target_maxslots && + !nfsd4_slots_inuse(session, session->se_target_maxslots)) /* Client acknowledged our reduce maxreqs */ free_session_slots(session, session->se_target_maxslots); @@ -5018,8 +5139,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfsd4_lease = 90; /* default lease time */ nn->nfsd4_grace = 90; - nn->somebody_reclaimed = false; - nn->track_reclaim_completes = false; nn->clverifier_counter = get_random_u32(); nn->clientid_base = get_random_u32(); nn->clientid_counter = nn->clientid_base + 1; @@ -5172,6 +5291,7 @@ static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) case SC_TYPE_DELEG: dp = delegstateid(s); list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); break; @@ -5615,8 +5735,10 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp) refcount_inc(&dp->dl_stid.sc_count); queued = nfsd4_run_cb(&dp->dl_recall); WARN_ON_ONCE(!queued); - if (!queued) + if (!queued) { refcount_dec(&dp->dl_stid.sc_count); + clear_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags); + } } /* Called from break_lease() with flc_lock held. */ @@ -6728,12 +6850,21 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static void nfsd4_end_grace(struct nfsd_net *nn) { - /* do nothing if grace period already ended */ - if (nn->grace_ended) + /* + * nfsd4_end_grace() can be entered concurrently from the + * laundromat workqueue and from an nfsd compound thread + * handling RECLAIM_COMPLETE. Without serialization, both + * callers can observe NFSD_NET_GRACE_ENDED clear and proceed + * into nfsd4_record_grace_done(). For tracking ops whose + * grace_done drains reclaim_str_hashtbl, that results in + * list corruption and a double free of every + * nfs4_client_reclaim entry. Use an atomic test-and-set so + * exactly one caller proceeds. + */ + if (test_and_set_bit(NFSD_NET_GRACE_ENDED, &nn->flags)) return; trace_nfsd_grace_complete(nn); - nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 * client will still be allowed to reclaim after it comes back up, @@ -6774,10 +6905,10 @@ bool nfsd4_force_end_grace(struct nfsd_net *nn) { if (!nn->client_tracking_ops) return false; - if (READ_ONCE(nn->grace_ended)) + if (test_bit(NFSD_NET_GRACE_ENDED, &nn->flags)) return false; /* laundromat_work must be initialised now, though it might be disabled */ - WRITE_ONCE(nn->grace_end_forced, true); + set_bit(NFSD_NET_GRACE_END_FORCED, &nn->flags); /* mod_delayed_work() doesn't queue work after * nfs4_state_shutdown_net() has called disable_delayed_work_sync() */ @@ -6791,18 +6922,22 @@ bool nfsd4_force_end_grace(struct nfsd_net *nn) */ static bool clients_still_reclaiming(struct nfsd_net *nn) { - time64_t double_grace_period_end = nn->boot_time + + time64_t double_grace_period_end = nn->boot_time_bt + 2 * nn->nfsd4_lease; - if (READ_ONCE(nn->grace_end_forced)) + if (test_bit(NFSD_NET_GRACE_END_FORCED, &nn->flags)) return false; - if (nn->track_reclaim_completes && - atomic_read(&nn->nr_reclaim_complete) == - nn->reclaim_str_hashtbl_size) - return false; - if (!nn->somebody_reclaimed) + if (test_bit(NFSD_NET_TRACK_RECLAIM_COMPLETES, &nn->flags)) { + int size; + + down_read(&nn->reclaim_str_hashtbl_lock); + size = nn->reclaim_str_hashtbl_size; + up_read(&nn->reclaim_str_hashtbl_lock); + if (atomic_read(&nn->nr_reclaim_complete) == size) + return false; + } + if (!test_and_clear_bit(NFSD_NET_SOMEBODY_RECLAIMED, &nn->flags)) return false; - nn->somebody_reclaimed = false; /* * If we've given them *two* lease times to reclaim, and they're * still not done, give up: @@ -6859,30 +6994,36 @@ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; - struct nfsd4_ssc_umount_item *ni = NULL; - struct nfsd4_ssc_umount_item *tmp; + struct nfsd4_ssc_umount_item *ni; +restart: spin_lock(&nn->nfsd_ssc_lock); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (time_after(jiffies, ni->nsui_expire)) { - if (refcount_read(&ni->nsui_refcnt) > 1) - continue; + list_for_each_entry(ni, &nn->nfsd_ssc_mount_list, nsui_list) { + if (!time_after(jiffies, ni->nsui_expire)) + break; + if (refcount_read(&ni->nsui_refcnt) > 1) + continue; - /* mark being unmount */ - ni->nsui_busy = true; - spin_unlock(&nn->nfsd_ssc_lock); - mntput(ni->nsui_vfsmount); - spin_lock(&nn->nfsd_ssc_lock); + /* Prevent concurrent setup during unmount */ + ni->nsui_busy = true; + spin_unlock(&nn->nfsd_ssc_lock); + mntput(ni->nsui_vfsmount); + spin_lock(&nn->nfsd_ssc_lock); - /* waiters need to start from begin of list */ - list_del(&ni->nsui_list); - kfree(ni); + /* Force concurrent scanners to restart */ + list_del(&ni->nsui_list); + kfree(ni); - /* wakeup ssc_connect waiters */ - do_wakeup = true; - continue; - } - break; + /* wakeup ssc_connect waiters */ + do_wakeup = true; + /* + * Concurrent nfsd4_ssc_cancel_dul() can free any item + * on the list under nfsd_ssc_lock while mntput() runs + * above. Restart from the head; the list is short and + * the expire worker is periodic, so this is cheap. + */ + spin_unlock(&nn->nfsd_ssc_lock); + goto restart; } if (do_wakeup) wake_up_all(&nn->nfsd_ssc_waitq); @@ -7032,16 +7173,22 @@ retry: if (atomic_read(&clp->cl_admin_revoked) == 0) continue; + if (is_client_expired(clp)) + continue; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { refcount_inc(&stid->sc_count); + atomic_inc(&clp->cl_rpc_users); spin_unlock(&nn->client_lock); /* this function drops ->cl_lock */ nfsd4_drop_revoked_stid(stid); nfs4_put_stid(stid); spin_lock(&nn->client_lock); + if (atomic_dec_and_test(&clp->cl_rpc_users) && + is_client_expired(clp)) + wake_up_all(&expiry_wq); goto retry; } spin_unlock(&clp->cl_lock); @@ -7062,6 +7209,7 @@ nfs4_laundromat(struct nfsd_net *nn) .new_timeo = nn->nfsd4_lease }; struct nfs4_cpntf_state *cps; + struct nfs4_client *clp; copy_stateid_t *cps_t; int i; @@ -7076,7 +7224,7 @@ nfs4_laundromat(struct nfsd_net *nn) cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) - _free_cpntf_state_locked(nn, cps); + revoke_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); nfsd4_async_copy_reaper(nn); @@ -7090,6 +7238,18 @@ nfs4_laundromat(struct nfsd_net *nn) dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; + clp = dp->dl_stid.sc_client; + spin_lock(&nn->client_lock); + if (is_client_expired(clp)) { + spin_unlock(&nn->client_lock); + continue; + } + /* + * Pin without reviving: get_client_locked() would + * flip a courtesy client back to NFSD4_ACTIVE. + */ + atomic_inc(&clp->cl_rpc_users); + spin_unlock(&nn->client_lock); refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); @@ -7098,8 +7258,18 @@ nfs4_laundromat(struct nfsd_net *nn) while (!list_empty(&reaplist)) { dp = list_first_entry(&reaplist, struct nfs4_delegation, dl_recall_lru); + clp = dp->dl_stid.sc_client; list_del_init(&dp->dl_recall_lru); revoke_delegation(dp); + /* + * Unpin without renewing: put_client_renew() would + * renew the reaped client's lease. + */ + if (atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) { + if (is_client_expired(clp)) + wake_up_all(&expiry_wq); + spin_unlock(&nn->client_lock); + } } spin_lock(&nn->client_lock); @@ -7195,12 +7365,12 @@ deleg_reaper(struct nfsd_net *nn) continue; if (atomic_read(&clp->cl_delegs_in_recall)) continue; - if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) - continue; if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) continue; if (clp->cl_cb_state != NFSD4_CB_UP) continue; + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) + continue; /* release in nfsd4_cb_recall_any_release */ kref_get(&clp->cl_nfsdfs.cl_ref); @@ -7463,16 +7633,14 @@ nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, out: return status; } -static void -_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) + +static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); - if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) - return; - list_del(&cps->cp_list); - idr_remove(&nn->s2s_cp_stateids, - cps->cp_stateid.cs_stid.si_opaque.so_id); - kfree(cps); + if (refcount_dec_and_test(&cps->cp_stateid.cs_count)) { + nfsd4_unhash_cpntf_state(nn, cps); + kfree(cps); + } } /* * A READ from an inter server to server COPY will have a @@ -7497,10 +7665,20 @@ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, state = NULL; goto unlock; } - if (!clp) + if (!clp) { refcount_inc(&state->cp_stateid.cs_count); - else - _free_cpntf_state_locked(nn, state); + } else if (memcmp(&clp->cl_clientid, &state->cp_p_clid, + sizeof(clientid_t))) { + /* + * OFFLOAD_CANCEL: only the creating client may cancel. + * so_id is guessable, so without this check any client + * could free another's cpntf state. + */ + state = NULL; + goto unlock; + } else { + revoke_cpntf_state_locked(nn, state); + } } unlock: spin_unlock(&nn->s2s_cp_lock); @@ -7787,7 +7965,7 @@ retry: return status; stp = openlockstateid(s); if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { - nfs4_put_stateowner(stp->st_stateowner); + nfs4_put_stid(&stp->st_stid); goto retry; } @@ -8036,6 +8214,10 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + status = nfs4_check_fh(&cstate->current_fh, &dp->dl_stid); + if (status) + goto put_stateid; + trace_nfsd_deleg_return(stateid); destroy_delegation(dp); smp_mb__after_atomic(); @@ -8506,6 +8688,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_no_grace; if (!locks_in_grace(net) && lock->lk_reclaim) goto out; + if (lock->lk_reclaim && + test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags)) + goto out; if (lock->lk_reclaim) flags |= FL_RECLAIM; @@ -8542,10 +8727,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && - nfsd4_has_session(cstate) && - locks_can_async_lock(nf->nf_file->f_op)) - flags |= FL_SLEEP; + if ((lock->lk_type == NFS4_READW_LT || + lock->lk_type == NFS4_WRITEW_LT) && + nfsd4_has_session(cstate) && + locks_can_async_lock(nf->nf_file->f_op)) + flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { @@ -8587,7 +8773,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; if (lock->lk_reclaim) - nn->somebody_reclaimed = true; + set_bit(NFSD_NET_SOMEBODY_RECLAIMED, &nn->flags); break; case FILE_LOCK_DEFERRED: kref_put(&nbl->nbl_kref, free_nbl); @@ -8963,9 +9149,13 @@ bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; + bool found; + down_read(&nn->reclaim_str_hashtbl_lock); crp = nfsd4_find_reclaim_client(name, nn); - return (crp && crp->cr_clp); + found = (crp && crp->cr_clp); + up_read(&nn->reclaim_str_hashtbl_lock); + return found; } /* @@ -8978,10 +9168,39 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, unsigned int strhashval; struct nfs4_client_reclaim *crp; + down_write(&nn->reclaim_str_hashtbl_lock); + + /* + * A reclaim record for this client name may already exist (for + * example, populated at boot from the recovery directory before + * an in-grace RECLAIM_COMPLETE or an nfsdcld downcall delivers + * the same name). Dedup here so reclaim_str_hashtbl_size stays + * equal to the number of distinct client names; inc_reclaim_complete + * relies on that equality to end the grace period via the fast path. + */ + crp = nfsd4_find_reclaim_client(name, nn); + if (crp) { + if (princhash.len && crp->cr_princhash.len == 0) { + void *pdata = kmemdup(princhash.data, princhash.len, + GFP_KERNEL); + if (pdata) { + crp->cr_princhash.data = pdata; + crp->cr_princhash.len = princhash.len; + } else { + dprintk("%s: failed to allocate memory for princhash.data!\n", + __func__); + crp = NULL; + } + } + up_write(&nn->reclaim_str_hashtbl_lock); + return crp; + } + name.data = kmemdup(name.data, name.len, GFP_KERNEL); if (!name.data) { dprintk("%s: failed to allocate memory for name.data!\n", __func__); + up_write(&nn->reclaim_str_hashtbl_lock); return NULL; } if (princhash.len) { @@ -8990,6 +9209,7 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, dprintk("%s: failed to allocate memory for princhash.data!\n", __func__); kfree(name.data); + up_write(&nn->reclaim_str_hashtbl_lock); return NULL; } } else @@ -9009,6 +9229,7 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, kfree(name.data); kfree(princhash.data); } + up_write(&nn->reclaim_str_hashtbl_lock); return crp; } @@ -9028,6 +9249,7 @@ nfs4_release_reclaim(struct nfsd_net *nn) struct nfs4_client_reclaim *crp = NULL; int i; + down_write(&nn->reclaim_str_hashtbl_lock); for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->reclaim_str_hashtbl[i])) { crp = list_entry(nn->reclaim_str_hashtbl[i].next, @@ -9036,6 +9258,7 @@ nfs4_release_reclaim(struct nfsd_net *nn) } } WARN_ON_ONCE(nn->reclaim_str_hashtbl_size); + up_write(&nn->reclaim_str_hashtbl_lock); } /* @@ -9113,8 +9336,9 @@ static int nfs4_state_create_net(struct net *net) nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); - nn->grace_ended = false; - nn->grace_end_forced = false; + nn->boot_time_bt = ktime_get_boottime_seconds(); + clear_bit(NFSD_NET_GRACE_ENDED, &nn->flags); + clear_bit(NFSD_NET_GRACE_END_FORCED, &nn->flags); nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); @@ -9200,7 +9424,8 @@ nfs4_state_start_net(struct net *net) nfsd4_client_tracking_init(net); /* safe for laundromat to run now */ enable_delayed_work(&nn->laundromat_work); - if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) + if (test_bit(NFSD_NET_TRACK_RECLAIM_COMPLETES, &nn->flags) && + nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index e17488a911f7..6a0a97d39bf6 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -449,9 +449,18 @@ nfsd4_decode_posixacl(struct nfsd4_compoundargs *argp, struct posix_acl **acl) if (xdr_stream_decode_u32(argp->xdr, &count) < 0) return nfserr_bad_xdr; + /* + * The NFSv4 POSIX ACL draft doesn't define a max number of ACE's, but + * the NFSACL spec does. For NFSv4, cap the number of entries to the v3 + * limit, as we want to ensure that ACLs set via NFSv4 POSIX ACL + * extensions are retrievable via NFSACL. + */ + if (count > NFS_ACL_MAX_ENTRIES) + return nfserr_inval; + *acl = posix_acl_alloc(count, GFP_KERNEL); if (*acl == NULL) - return nfserr_resource; + return nfserr_jukebox; (*acl)->a_count = count; for (ace = (*acl)->a_entries; ace < (*acl)->a_entries + count; ace++) { @@ -628,6 +637,8 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, if (!xdrgen_decode_fattr4_time_deleg_access(argp->xdr, &access)) return nfserr_bad_xdr; + if (access.nseconds >= NSEC_PER_SEC) + return nfserr_inval; iattr->ia_atime.tv_sec = access.seconds; iattr->ia_atime.tv_nsec = access.nseconds; iattr->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET | ATTR_DELEG; @@ -637,6 +648,8 @@ nfsd4_decode_fattr4(struct nfsd4_compoundargs *argp, u32 *bmval, u32 bmlen, if (!xdrgen_decode_fattr4_time_deleg_modify(argp->xdr, &modify)) return nfserr_bad_xdr; + if (modify.nseconds >= NSEC_PER_SEC) + return nfserr_inval; iattr->ia_mtime.tv_sec = modify.seconds; iattr->ia_mtime.tv_nsec = modify.nseconds; iattr->ia_ctime.tv_sec = modify.seconds; @@ -955,6 +968,10 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) case NF4LNK: if (xdr_stream_decode_u32(argp->xdr, &create->cr_datalen) < 0) return nfserr_bad_xdr; + if (create->cr_datalen == 0) + return nfserr_inval; + if (create->cr_datalen > NFS4_MAXPATHLEN) + return nfserr_nametoolong; p = xdr_inline_decode(argp->xdr, create->cr_datalen); if (!p) return nfserr_bad_xdr; @@ -2106,6 +2123,7 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, { struct nfs42_netaddr *naddr; __be32 *p; + u32 str_len; if (xdr_stream_decode_u32(argp->xdr, &ns->nl4_type) < 0) return nfserr_bad_xdr; @@ -2135,6 +2153,18 @@ static __be32 nfsd4_decode_nl4_server(struct nfsd4_compoundargs *argp, return nfserr_bad_xdr; memcpy(naddr->addr, p, naddr->addr_len); break; + case NL4_NAME: + case NL4_URL: + /* + * Well-formed XDR, but only NL4_NETADDR is supported. Consume + * the utf8str_cis to keep the stream aligned, then return + * NFS4ERR_NOTSUPP rather than the misleading NFS4ERR_BADXDR. + */ + if (xdr_stream_decode_u32(argp->xdr, &str_len) < 0) + return nfserr_bad_xdr; + if (!xdr_inline_decode(argp->xdr, str_len)) + return nfserr_bad_xdr; + return nfserr_notsupp; default: return nfserr_bad_xdr; } @@ -6390,9 +6420,6 @@ status: write_bytes_to_xdr_buf(xdr->buf, op_status_offset, &op->status, XDR_UNIT); release: - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); - /* * Account for pages consumed while encoding this operation. * The xdr_stream primitives don't manage rq_next_page. @@ -6424,9 +6451,12 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) { struct nfsd4_compoundargs *args = rqstp->rq_argp; + args->opcnt = 0; if (args->ops != args->iops) { - vfree(args->ops); + void *old_ops = args->ops; + args->ops = args->iops; + kvfree_rcu_mightsleep(old_ops); } while (args->to_free) { struct svcxdr_tmpbuf *tb = args->to_free; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 154468ceccdc..a9fa9dd410b2 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -200,14 +200,14 @@ int nfsd_reply_cache_init(struct nfsd_net *nn) nn->nfsd_reply_cache_shrinker->seeks = 1; nn->nfsd_reply_cache_shrinker->private_data = nn; - shrinker_register(nn->nfsd_reply_cache_shrinker); - for (i = 0; i < hashsize; i++) { INIT_LIST_HEAD(&nn->drc_hashtbl[i].lru_head); spin_lock_init(&nn->drc_hashtbl[i].cache_lock); } nn->drc_hashsize = hashsize; + shrinker_register(nn->nfsd_reply_cache_shrinker); + return 0; out_shrinker: kvfree(nn->drc_hashtbl); @@ -275,7 +275,7 @@ nfsd_prune_bucket_locked(struct nfsd_net *nn, struct nfsd_drc_bucket *b, nfsd_cacherep_unlink_locked(nn, b, rp); list_add(&rp->c_lru, dispose); - if (max && ++freed > max) + if (max && ++freed >= max) break; } } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index fa92e31d19d6..caf59421f8f4 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -296,14 +296,15 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) * 2. Is that directory a mount point, or * 3. Is that directory the root of an exported file system? */ - nfsd4_cancel_copy_by_sb(netns(file), path.dentry->d_sb); error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); mutex_lock(&nfsd_mutex); nn = net_generic(netns(file), nfsd_net_id); - if (nn->nfsd_serv) + if (nn->nfsd_serv) { + nfsd4_cancel_copy_by_sb(netns(file), path.dentry->d_sb); nfsd4_revoke_states(nn, path.dentry->d_sb); - else + } else { error = -EINVAL; + } mutex_unlock(&nfsd_mutex); path_put(&path); @@ -420,6 +421,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) char *mesg = buf; int rv; struct net *net = netns(file); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (size > 0) { int newthreads; @@ -430,7 +432,10 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return -EINVAL; trace_nfsd_ctl_threads(net, newthreads); mutex_lock(&nfsd_mutex); - rv = nfsd_svc(1, &newthreads, net, file->f_cred, NULL); + if (newthreads > 0 || nn->nfsd_serv != NULL) + rv = nfsd_svc(1, &newthreads, net, file->f_cred, NULL); + else + rv = 0; mutex_unlock(&nfsd_mutex); if (rv < 0) return rv; @@ -1111,7 +1116,7 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) } return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%c\n", - nn->grace_ended ? 'Y' : 'N'); + test_bit(NFSD_NET_GRACE_ENDED, &nn->flags) ? 'Y' : 'N'); } #endif @@ -1414,8 +1419,8 @@ static int create_proc_exports_entry(void) unsigned int nfsd_net_id; struct nfsd_genl_rqstp { - struct sockaddr rq_daddr; - struct sockaddr rq_saddr; + struct sockaddr_storage rq_daddr; + struct sockaddr_storage rq_saddr; unsigned long rq_flags; ktime_t rq_stime; __be32 rq_xid; @@ -1448,9 +1453,9 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME, ktime_to_us(genl_rqstp->rq_stime), NFSD_A_RPC_STATUS_PAD)) - return -ENOBUFS; + goto out_cancel; - switch (genl_rqstp->rq_saddr.sa_family) { + switch (genl_rqstp->rq_saddr.ss_family) { case AF_INET: { const struct sockaddr_in *s_in, *d_in; @@ -1464,7 +1469,7 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, s_in->sin_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin_port)) - return -ENOBUFS; + goto out_cancel; break; } case AF_INET6: { @@ -1480,7 +1485,7 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, s_in->sin6_port) || nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT, d_in->sin6_port)) - return -ENOBUFS; + goto out_cancel; break; } } @@ -1488,10 +1493,14 @@ static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb, for (i = 0; i < genl_rqstp->rq_opcnt; i++) if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS, genl_rqstp->rq_opnum[i])) - return -ENOBUFS; + goto out_cancel; genlmsg_end(skb, hdr); return 0; + +out_cancel: + genlmsg_cancel(skb, hdr); + return -ENOBUFS; } /** @@ -1519,18 +1528,28 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) { struct svc_rqst *rqstp; + long thread_skip = 0; if (i < cb->args[0]) /* already consumed */ continue; + /* + * The saved thread index only applies to the pool the dump + * was resumed in. Subsequent pools must start from thread 0, + * otherwise their first cb->args[1] threads are silently + * skipped. + */ + if (i == cb->args[0]) + thread_skip = cb->args[1]; + rqstp_index = 0; list_for_each_entry_rcu(rqstp, &nn->nfsd_serv->sv_pools[i].sp_all_threads, rq_all) { - struct nfsd_genl_rqstp genl_rqstp; + struct nfsd_genl_rqstp genl_rqstp = {}; unsigned int status_counter; - if (rqstp_index++ < cb->args[1]) /* already consumed */ + if (rqstp_index++ < thread_skip) /* already consumed */ continue; /* * Acquire rq_status_counter before parsing the rqst @@ -1551,9 +1570,9 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, genl_rqstp.rq_stime = rqstp->rq_stime; genl_rqstp.rq_opcnt = 0; memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp), - sizeof(struct sockaddr)); + sizeof(struct sockaddr_storage)); memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp), - sizeof(struct sockaddr)); + sizeof(struct sockaddr_storage)); #ifdef CONFIG_NFSD_V4 if (rqstp->rq_vers == NFS4_VERSION && @@ -1572,17 +1591,26 @@ int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb, #endif /* CONFIG_NFSD_V4 */ /* - * Acquire rq_status_counter before reporting the rqst - * fields to the user. + * Read-side load-load fence: order the field reads + * above before the counter re-read below, mirroring + * the smp_rmb() in the standard seqcount retry. The + * begin-side smp_load_acquire() above pairs with the + * smp_store_release() in nfsd_dispatch(). */ - if (smp_load_acquire(&rqstp->rq_status_counter) != - status_counter) + smp_rmb(); + if (READ_ONCE(rqstp->rq_status_counter) != status_counter) continue; ret = nfsd_genl_rpc_status_compose_msg(skb, cb, &genl_rqstp); - if (ret) + if (ret) { + if (skb->len) { + cb->args[0] = i; + cb->args[1] = rqstp_index - 1; + ret = skb->len; + } goto out; + } } } @@ -1944,6 +1972,60 @@ err_free_msg: } /** + * nfsd_nl_validate_listeners - sanity-check the listener list from userland + * @info: netlink metadata and command arguments + * + * Walk every NFSD_A_SERVER_SOCK_ADDR attribute and confirm that each entry + * is well-formed: it parses against the policy, carries both an address and + * a transport name, and the address is long enough for its family. Doing + * this up front lets the callers below assume every entry is valid and + * guarantees we make no changes when the request is malformed. + * + * Return: 0 if every entry is valid, or a negative errno otherwise. + */ +static int nfsd_nl_validate_listeners(struct genl_info *info) +{ + const struct nlattr *attr; + int rem; + + nlmsg_for_each_attr_type(attr, NFSD_A_SERVER_SOCK_ADDR, info->nlhdr, + GENL_HDRLEN, rem) { + struct nlattr *tb[NFSD_A_SOCK_MAX + 1]; + struct sockaddr *sa; + int err; + + err = nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, + nfsd_sock_nl_policy, info->extack); + if (err < 0) + return err; + + if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) + return -EINVAL; + + sa = nla_data(tb[NFSD_A_SOCK_ADDR]); + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(sa->sa_family)) + return -EINVAL; + + switch (sa->sa_family) { + case AF_INET: + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < + sizeof(struct sockaddr_in)) + return -EINVAL; + break; + case AF_INET6: + if (nla_len(tb[NFSD_A_SOCK_ADDR]) < + sizeof(struct sockaddr_in6)) + return -EINVAL; + break; + default: + return -EAFNOSUPPORT; + } + } + + return 0; +} + +/** * nfsd_nl_listener_set_doit - set the nfs running sockets * @skb: reply buffer * @info: netlink metadata and command arguments @@ -1961,6 +2043,15 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) bool delete = false; int err, rem; + /* + * Validate the entire listener list before making any changes, so a + * malformed request fails cleanly without creating a serv or touching + * the existing listeners. + */ + err = nfsd_nl_validate_listeners(info); + if (err) + return err; + mutex_lock(&nfsd_mutex); err = nfsd_create_serv(net); @@ -1987,16 +2078,11 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) const char *xcl_name; struct sockaddr *sa; + /* validated up front in nfsd_nl_validate_listeners() */ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; - if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) - continue; - - if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) - continue; - xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); @@ -2048,16 +2134,11 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) struct sockaddr *sa; int ret; + /* validated up front in nfsd_nl_validate_listeners() */ if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr, nfsd_sock_nl_policy, info->extack) < 0) continue; - if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME]) - continue; - - if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa)) - continue; - xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]); sa = nla_data(tb[NFSD_A_SOCK_ADDR]); @@ -2512,11 +2593,12 @@ static int __init init_nfsd(void) { int retval; - nfsd_debugfs_init(); - retval = nfsd4_init_slabs(); if (retval) return retval; + + nfsd_debugfs_init(); + retval = nfsd4_init_pnfs(); if (retval) goto out_free_slabs; @@ -2561,8 +2643,8 @@ out_free_lockd: out_free_pnfs: nfsd4_exit_pnfs(); out_free_slabs: - nfsd4_free_slabs(); nfsd_debugfs_exit(); + nfsd4_free_slabs(); return retval; } @@ -2577,9 +2659,9 @@ static void __exit exit_nfsd(void) unregister_pernet_subsys(&nfsd_net_ops); nfsd_drc_slab_free(); nfsd_lockd_shutdown(); - nfsd4_free_slabs(); nfsd4_exit_pnfs(); nfsd_debugfs_exit(); + nfsd4_free_slabs(); } MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>"); diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 429ca5c6ec08..ab53de1c280d 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -70,10 +70,8 @@ nfsd_mode_check(struct dentry *dentry, umode_t requested) if (requested == 0) /* the caller doesn't care */ return nfs_ok; if (mode == requested) { - if (mode == S_IFDIR && !d_can_lookup(dentry)) { - WARN_ON_ONCE(1); + if (mode == S_IFDIR && !d_can_lookup(dentry)) return nfserr_notdir; - } return nfs_ok; } if (mode == S_IFLNK) { @@ -344,15 +342,19 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct net *net, if (dentry->d_sb->s_export_op->flags & EXPORT_OP_NOWCC) fhp->fh_no_wcc = true; fhp->fh_64bit_cookies = true; - if (exp->ex_flags & NFSEXP_V4ROOT) + if (exp->ex_flags & NFSEXP_V4ROOT) { + dput(dentry); goto out; + } break; case NFS_FHSIZE: fhp->fh_no_wcc = true; if (EX_WGATHER(exp)) fhp->fh_use_wgather = true; - if (exp->ex_flags & NFSEXP_V4ROOT) + if (exp->ex_flags & NFSEXP_V4ROOT) { + dput(dentry); goto out; + } } fhp->fh_dentry = dentry; diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 8873033d1e82..a73d5c259cd9 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -82,6 +82,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) .na_iattr = iap, }; struct svc_fh *fhp; + int hosterr; dprintk("nfsd: SETATTR %s, valid=%x, size=%ld\n", SVCFH_fmt(&argp->fh), @@ -117,6 +118,12 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (resp->status != nfs_ok) goto out; + hosterr = fh_want_write(fhp); + if (hosterr) { + resp->status = nfserrno(hosterr); + goto out; + } + if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 4f1ab3222a4d..5e0a0c1cbb91 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -351,7 +351,7 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; - if (nn->nfsd_net_up) + if (test_bit(NFSD_NET_UP, &nn->flags)) return 0; ret = nfsd_startup_generic(); @@ -364,11 +364,11 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) goto out_socks; } - if (nfsd_needs_lockd(nn) && !nn->lockd_up) { + if (nfsd_needs_lockd(nn) && !test_bit(NFSD_NET_LOCKD_UP, &nn->flags)) { ret = lockd_up(net, cred); if (ret) goto out_socks; - nn->lockd_up = true; + set_bit(NFSD_NET_LOCKD_UP, &nn->flags); } ret = nfsd_file_cache_start_net(net); @@ -386,7 +386,7 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) if (ret) goto out_reply_cache; - nn->nfsd_net_up = true; + set_bit(NFSD_NET_UP, &nn->flags); return 0; out_reply_cache: @@ -394,9 +394,9 @@ out_reply_cache: out_filecache: nfsd_file_cache_shutdown_net(net); out_lockd: - if (nn->lockd_up) { + if (test_bit(NFSD_NET_LOCKD_UP, &nn->flags)) { lockd_down(net); - nn->lockd_up = false; + clear_bit(NFSD_NET_LOCKD_UP, &nn->flags); } out_socks: nfsd_shutdown_generic(); @@ -407,7 +407,7 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (nn->nfsd_net_up) { + if (test_bit(NFSD_NET_UP, &nn->flags)) { percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); wait_for_completion(&nn->nfsd_net_confirm_done); @@ -415,18 +415,18 @@ static void nfsd_shutdown_net(struct net *net) nfs4_state_shutdown_net(net); nfsd_reply_cache_shutdown(nn); nfsd_file_cache_shutdown_net(net); - if (nn->lockd_up) { + if (test_bit(NFSD_NET_LOCKD_UP, &nn->flags)) { lockd_down(net); - nn->lockd_up = false; + clear_bit(NFSD_NET_LOCKD_UP, &nn->flags); } wait_for_completion(&nn->nfsd_net_free_done); } percpu_ref_exit(&nn->nfsd_net_ref); - if (nn->nfsd_net_up) + if (test_bit(NFSD_NET_UP, &nn->flags)) nfsd_shutdown_generic(); - nn->nfsd_net_up = false; + clear_bit(NFSD_NET_UP, &nn->flags); } static DEFINE_SPINLOCK(nfsd_notifier_lock); @@ -815,7 +815,7 @@ nfsd_acl_init_request(struct svc_rqst *rqstp, ret->mismatch.lovers = NFSD_ACL_NRVERS; for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++) { - if (nfsd_support_acl_version(rqstp->rq_vers) && + if (nfsd_support_acl_version(i) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.lovers = i; break; @@ -825,7 +825,7 @@ nfsd_acl_init_request(struct svc_rqst *rqstp, return rpc_prog_unavail; ret->mismatch.hivers = NFSD_ACL_MINVERS; for (i = NFSD_ACL_NRVERS - 1; i >= NFSD_ACL_MINVERS; i--) { - if (nfsd_support_acl_version(rqstp->rq_vers) && + if (nfsd_support_acl_version(i) && nfsd_vers(nn, i, NFSD_TEST)) { ret->mismatch.hivers = i; break; @@ -960,6 +960,20 @@ nfsd(void *vrqstp) return 0; } +/* + * Set rq_status_counter back to an even value, indicating that the rqstp + * fields are no longer meaningful to a lockless reader. This pairs with the + * odd-valued store made once the request has been decoded, and must run on + * every return path that follows it so that the seq-lock like protocol used + * by nfsd_nl_rpc_status_get_dumpit() is not left permanently odd. The store + * also advances the counter so a concurrent reader detects the transition. + */ +static void nfsd_status_counter_set_idle(struct svc_rqst *rqstp) +{ + smp_store_release(&rqstp->rq_status_counter, + (rqstp->rq_status_counter | 1) + 1); +} + /** * nfsd_dispatch - Process an NFS or NFSACL or LOCALIO Request * @rqstp: incoming request @@ -1022,14 +1036,9 @@ int nfsd_dispatch(struct svc_rqst *rqstp) if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; - /* - * Release rq_status_counter setting it to an even value after the rpc - * request has been properly processed. - */ - smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); - nfsd_cache_update(rqstp, rp, ntli->ntli_cachetype, nfs_reply); out_cached_reply: + nfsd_status_counter_set_idle(rqstp); return 1; out_decode_err: @@ -1040,12 +1049,14 @@ out_decode_err: out_update_drop: nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); out_dropit: + nfsd_status_counter_set_idle(rqstp); return 0; out_encode_err: trace_nfsd_cant_encode_err(rqstp); nfsd_cache_update(rqstp, rp, RC_NOCACHE, NULL); *statp = rpc_system_err; + nfsd_status_counter_set_idle(rqstp); return 1; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index ae71e0621317..86c9dd4b334b 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -10,6 +10,16 @@ #include "auth.h" /* + * Sun convention: a sattr time-useconds field of one full second (an + * otherwise out-of-range value) means "set this time to the current + * server time." It's needed to make permissions checks for the "touch" + * program across NFSv2 mounts work correctly. See description of + * sattr in section 6.1 of "NFS Illustrated" by Brent Callaghan, + * Addison-Wesley, ISBN 0-201-32750-5 + */ +#define NFS2_SATTR_SET_TO_SERVER_TIME (1000000) + +/* * Mapping of S_IF* types to NFS file types */ static const u32 nfs_ftypes[] = { @@ -172,27 +182,29 @@ svcxdr_decode_sattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, tmp1 = be32_to_cpup(p++); tmp2 = be32_to_cpup(p++); if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { + /* + * Range test here to prevent the multiplication from + * wrapping to a valid (but incorrect) value on 32-bit + * platforms. + */ + if (tmp2 > NFS2_SATTR_SET_TO_SERVER_TIME) + return false; iap->ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; iap->ia_atime.tv_sec = tmp1; iap->ia_atime.tv_nsec = tmp2 * NSEC_PER_USEC; + if (tmp2 == NFS2_SATTR_SET_TO_SERVER_TIME) + iap->ia_valid &= ~ATTR_ATIME_SET; } tmp1 = be32_to_cpup(p++); tmp2 = be32_to_cpup(p++); if (tmp1 != (u32)-1 && tmp2 != (u32)-1) { + if (tmp2 > NFS2_SATTR_SET_TO_SERVER_TIME) + return false; iap->ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; iap->ia_mtime.tv_sec = tmp1; iap->ia_mtime.tv_nsec = tmp2 * NSEC_PER_USEC; - /* - * Passing the invalid value useconds=1000000 for mtime - * is a Sun convention for "set both mtime and atime to - * current server time". It's needed to make permissions - * checks for the "touch" program across v2 mounts to - * Solaris and Irix boxes work correctly. See description of - * sattr in section 6.1 of "NFS Illustrated" by - * Brent Callaghan, Addison-Wesley, ISBN 0-201-32750-5 - */ - if (tmp2 == 1000000) + if (tmp2 == NFS2_SATTR_SET_TO_SERVER_TIME) iap->ia_valid &= ~(ATTR_ATIME_SET|ATTR_MTIME_SET); } diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index dec83e92650d..f44ea672670f 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -384,6 +384,7 @@ struct nfsd4_session { u16 se_slot_gen; bool se_dead; u32 se_target_maxslots; + struct rcu_head rcu_head; }; /* formatted contents of nfs4_sessionid */ @@ -496,7 +497,7 @@ struct nfs4_client { #define NFSD4_CB_FAULT 3 int cl_cb_state; struct nfsd4_callback cl_cb_null; - struct nfsd4_session *cl_cb_session; + struct nfsd4_session __rcu *cl_cb_session; /* for all client information that callback code might need: */ spinlock_t cl_lock; @@ -754,6 +755,7 @@ struct nfs4_layout_stateid { struct delayed_work ls_fence_work; unsigned int ls_fence_delay; bool ls_fenced; + bool ls_fence_inflight; }; static inline struct nfs4_layout_stateid *layoutstateid(struct nfs4_stid *s) diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 1c5a1e50f946..33953d38314e 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -271,7 +271,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify, TP_CONDITION(rqstp != NULL), TP_STRUCT__entry( __field(unsigned int, netns_ino) - __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) __field(u32, xid) __field(u32, fh_hash) @@ -310,7 +310,7 @@ TRACE_EVENT_CONDITION(nfsd_fh_verify_err, TP_CONDITION(rqstp != NULL && error), TP_STRUCT__entry( __field(unsigned int, netns_ino) - __sockaddr(server, rqstp->rq_xprt->xpt_remotelen) + __sockaddr(server, rqstp->rq_xprt->xpt_locallen) __sockaddr(client, rqstp->rq_xprt->xpt_remotelen) __field(u32, xid) __field(u32, fh_hash) @@ -1727,9 +1727,10 @@ DEFINE_NFSD_CB_LIFETIME_EVENT(bc_shutdown); TRACE_EVENT(nfsd_cb_seq_status, TP_PROTO( const struct rpc_task *task, - const struct nfsd4_callback *cb + const struct nfsd4_callback *cb, + const struct nfsd4_session *session ), - TP_ARGS(task, cb), + TP_ARGS(task, cb, session), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) @@ -1741,8 +1742,6 @@ TRACE_EVENT(nfsd_cb_seq_status, __field(int, seq_status) ), TP_fast_assign( - const struct nfs4_client *clp = cb->cb_clp; - const struct nfsd4_session *session = clp->cl_cb_session; const struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)&session->se_sessionid; @@ -1768,9 +1767,10 @@ TRACE_EVENT(nfsd_cb_seq_status, TRACE_EVENT(nfsd_cb_free_slot, TP_PROTO( const struct rpc_task *task, - const struct nfsd4_callback *cb + const struct nfsd4_callback *cb, + const struct nfsd4_session *session ), - TP_ARGS(task, cb), + TP_ARGS(task, cb, session), TP_STRUCT__entry( __field(unsigned int, task_id) __field(unsigned int, client_id) @@ -1781,8 +1781,6 @@ TRACE_EVENT(nfsd_cb_free_slot, __field(u32, slot_seqno) ), TP_fast_assign( - const struct nfs4_client *clp = cb->cb_clp; - const struct nfsd4_session *session = clp->cl_cb_session; const struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)&session->se_sessionid; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 1e89c7ff9493..f73012bc742f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -137,8 +137,10 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, follow_flags = LOOKUP_AUTOMOUNT; err = follow_down(&path, follow_flags); - if (err < 0) + if (err < 0) { + path_put(&path); goto out; + } if (path.mnt == exp->ex_path.mnt && path.dentry == dentry && nfsd_mountpoint(dentry, exp) == 2) { /* This is only a mountpoint in some other namespace */ @@ -419,21 +421,22 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap) } static __be32 -nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp, - struct iattr *iap) +nfsd_may_truncate(struct svc_rqst *rqstp, struct svc_fh *fhp, + struct iattr *iap) { struct inode *inode = d_inode(fhp->fh_dentry); - if (iap->ia_size < inode->i_size) { - __be32 err; + if (iap->ia_size >= i_size_read(inode)) + return nfs_ok; - err = nfsd_permission(&rqstp->rq_cred, - fhp->fh_export, fhp->fh_dentry, - NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); - if (err) - return err; - } - return nfserrno(get_write_access(inode)); + return nfsd_permission(&rqstp->rq_cred, fhp->fh_export, fhp->fh_dentry, + NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE); +} + +static __be32 +nfsd_get_write_access(struct svc_fh *fhp) +{ + return nfserrno(get_write_access(d_inode(fhp->fh_dentry))); } static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) @@ -560,12 +563,17 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, * setattr call. */ if (size_change) { - err = nfsd_get_write_access(rqstp, fhp, iap); + err = nfsd_get_write_access(fhp); if (err) return err; } inode_lock(inode); + if (size_change) { + err = nfsd_may_truncate(rqstp, fhp, iap); + if (err) + goto out_unlock; + } err = fh_fill_pre_attrs(fhp); if (err) goto out_unlock; @@ -1374,6 +1382,7 @@ nfsd_direct_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file = nf->nf_file; unsigned int nsegs, i; ssize_t host_err; + size_t expected; nsegs = nfsd_write_dio_iters_init(nf, rqstp->rq_bvec, nvecs, kiocb, *cnt, segments); @@ -1395,11 +1404,13 @@ nfsd_direct_write(struct svc_rqst *rqstp, struct svc_fh *fhp, kiocb->ki_flags |= IOCB_DONTCACHE; } + expected = iov_iter_count(&segments[i].iter); + host_err = vfs_iocb_iter_write(file, kiocb, &segments[i].iter); if (host_err < 0) return host_err; *cnt += host_err; - if (host_err < segments[i].iter.count) + if (host_err < (ssize_t)expected) break; /* partial write */ } diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 5f0f1f283af0..83f6ea30cc8b 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -175,7 +175,7 @@ static int nilfs_bmap_do_delete(struct nilfs_bmap *bmap, __u64 key) return ret; } - return bmap->b_ops->bop_delete(bmap, key); + return bmap->b_ops->bop_delete(bmap, key, false); } /** diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index 4656df392722..a72f3c308a5d 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -63,7 +63,7 @@ struct nilfs_bmap_operations { int (*bop_lookup_contig)(const struct nilfs_bmap *, __u64, __u64 *, unsigned int); int (*bop_insert)(struct nilfs_bmap *, __u64, __u64); - int (*bop_delete)(struct nilfs_bmap *, __u64); + int (*bop_delete)(struct nilfs_bmap *bmap, __u64 key, bool deform); void (*bop_clear)(struct nilfs_bmap *); int (*bop_propagate)(struct nilfs_bmap *, struct buffer_head *); diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 64d5f7c5ab44..64bac66af25b 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1425,6 +1425,28 @@ static void nilfs_btree_shrink(struct nilfs_bmap *btree, path[level].bp_bh = NULL; } +/** + * nilfs_btree_discard - discard the last node for the mapping transformation + * @btree: bmap struct of btree + * @path: array of nilfs_btree_path struct + * @level: level of the B-tree node being operated on + * @keyp: argument for passing a key (unused) + * @ptrp: argument for passing a pointer (unused) + */ +static void nilfs_btree_discard(struct nilfs_bmap *btree, + struct nilfs_btree_path *path, int level, + __u64 *keyp, __u64 *ptrp) +{ + struct nilfs_btree_node *root = nilfs_btree_get_root(btree); + + nilfs_btree_node_delete(root, 0, NULL, NULL, + NILFS_BTREE_ROOT_NCHILDREN_MAX); + nilfs_btree_node_set_level(root, level); + + nilfs_btnode_delete(path[level].bp_bh); + path[level].bp_bh = NULL; +} + static void nilfs_btree_nop(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int level, __u64 *keyp, __u64 *ptrp) @@ -1435,7 +1457,7 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, struct nilfs_btree_path *path, int *levelp, struct nilfs_bmap_stats *stats, - struct inode *dat) + struct inode *dat, bool deform) { struct buffer_head *bh; struct nilfs_btree_node *node, *parent, *sib; @@ -1522,15 +1544,17 @@ static int nilfs_btree_prepare_delete(struct nilfs_bmap *btree, if (nilfs_btree_node_get_nchildren(node) - 1 <= NILFS_BTREE_ROOT_NCHILDREN_MAX) { path[level].bp_op = nilfs_btree_shrink; - stats->bs_nblocks += 2; - level++; - path[level].bp_op = nilfs_btree_nop; - goto shrink_root_child; + } else if (deform) { + path[level].bp_op = nilfs_btree_discard; } else { path[level].bp_op = nilfs_btree_do_delete; stats->bs_nblocks++; goto out; } + stats->bs_nblocks += 2; + level++; + path[level].bp_op = nilfs_btree_nop; + goto shrink_root_child; } } @@ -1581,7 +1605,7 @@ static void nilfs_btree_commit_delete(struct nilfs_bmap *btree, nilfs_bmap_set_dirty(btree); } -static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) +static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key, bool deform) { struct nilfs_btree_path *path; @@ -1601,7 +1625,8 @@ static int nilfs_btree_delete(struct nilfs_bmap *btree, __u64 key) dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL; - ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat); + ret = nilfs_btree_prepare_delete(btree, path, &level, &stats, dat, + deform); if (ret < 0) goto out; nilfs_btree_commit_delete(btree, path, level, dat); diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 8bd0b1374e25..b8643d3aa2f8 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -144,7 +144,7 @@ static int nilfs_direct_insert(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) return ret; } -static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key) +static int nilfs_direct_delete(struct nilfs_bmap *bmap, __u64 key, bool deform) { union nilfs_bmap_ptr_req req; struct inode *dat; @@ -234,7 +234,7 @@ int nilfs_direct_delete_and_convert(struct nilfs_bmap *bmap, /* no need to allocate any resource for conversion */ /* delete */ - ret = bmap->b_ops->bop_delete(bmap, key); + ret = bmap->b_ops->bop_delete(bmap, key, true); if (ret < 0) return ret; diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index a3555bebad63..b05b6d3abb87 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -600,8 +600,7 @@ static struct fanotify_event *fanotify_alloc_perm_event(const void *data, pevent->hdr.len = 0; pevent->state = FAN_EVENT_INIT; pevent->path = *path; - /* NULL ppos means no range info */ - pevent->ppos = range ? &range->pos : NULL; + pevent->pos = range ? range->pos : FANOTIFY_NO_RANGE; pevent->count = range ? range->count : 0; path_get(path); diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index a0619e7694d5..3710543dbf82 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -428,6 +428,8 @@ FANOTIFY_ME(struct fanotify_event *event) return container_of(event, struct fanotify_mnt_event, fae); } +#define FANOTIFY_NO_RANGE ((loff_t)-1) + /* * Structure for permission fanotify events. It gets allocated and freed in * fanotify_handle_event() since we wait there for user response. When the @@ -438,7 +440,7 @@ FANOTIFY_ME(struct fanotify_event *event) struct fanotify_perm_event { struct fanotify_event fae; struct path path; - const loff_t *ppos; /* optional file range info */ + loff_t pos; /* FANOTIFY_NO_RANGE if unavailable */ size_t count; u32 response; /* userspace answer to the event */ unsigned short state; /* state of the event */ @@ -468,7 +470,7 @@ static inline bool fanotify_event_has_access_range(struct fanotify_event *event) if (!(event->mask & FANOTIFY_PRE_CONTENT_EVENTS)) return false; - return FANOTIFY_PERM(event)->ppos; + return FANOTIFY_PERM(event)->pos != FANOTIFY_NO_RANGE; } static inline struct fanotify_event *FANOTIFY_E(struct fsnotify_event *fse) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index b604e3da58ad..7278286f5a6d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -675,12 +675,9 @@ static size_t copy_range_info_to_user(struct fanotify_event *event, if (WARN_ON_ONCE(info_len > count)) return -EFAULT; - if (WARN_ON_ONCE(!pevent->ppos)) - return -EINVAL; - info.hdr.info_type = FAN_EVENT_INFO_TYPE_RANGE; info.hdr.len = info_len; - info.offset = *(pevent->ppos); + info.offset = pevent->pos; info.count = pevent->count; if (copy_to_user(buf, &info, info_len)) @@ -1316,16 +1313,18 @@ static bool fanotify_mark_update_flags(struct fsnotify_mark *fsn_mark, static bool fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, __u32 mask, unsigned int fan_flags) { + __u32 old_mask; bool recalc; spin_lock(&fsn_mark->lock); - if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS)) + if (!(fan_flags & FANOTIFY_MARK_IGNORE_BITS)) { + old_mask = fsn_mark->mask; fsn_mark->mask |= mask; - else + recalc = old_mask != fsn_mark->mask; + } else { fsn_mark->ignore_mask |= mask; - - recalc = fsnotify_calc_mask(fsn_mark) & - ~fsnotify_conn_mask(fsn_mark->connector); + recalc = true; + } recalc |= fanotify_mark_update_flags(fsn_mark, fan_flags); spin_unlock(&fsn_mark->lock); diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index ed37491c1618..5f19c24ec187 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -539,7 +539,6 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, { struct fsnotify_mark *fsn_mark; struct inotify_inode_mark *i_mark; - __u32 old_mask, new_mask; int replace = !(arg & IN_MASK_ADD); int create = (arg & IN_MASK_CREATE); int ret; @@ -555,27 +554,15 @@ static int inotify_update_existing_watch(struct fsnotify_group *group, i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark); spin_lock(&fsn_mark->lock); - old_mask = fsn_mark->mask; if (replace) { fsn_mark->mask = 0; fsn_mark->flags &= ~INOTIFY_MARK_FLAGS; } fsn_mark->mask |= inotify_arg_to_mask(inode, arg); fsn_mark->flags |= inotify_arg_to_flags(arg); - new_mask = fsn_mark->mask; spin_unlock(&fsn_mark->lock); - if (old_mask != new_mask) { - /* more bits in old than in new? */ - int dropped = (old_mask & ~new_mask); - /* more bits in this fsn_mark than the inode's mask? */ - int do_inode = (new_mask & ~READ_ONCE(inode->i_fsnotify_mask)); - - /* update the inode with this new fsn_mark */ - if (dropped || do_inode) - fsnotify_recalc_mask(fsn_mark->connector); - - } + fsnotify_recalc_mask(fsn_mark->connector); /* return the wd */ ret = i_mark->wd; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 58f32aac5f61..0c147b99d4ee 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -693,6 +693,8 @@ static bool ntfs_non_resident_attr_value_is_valid(const struct attr_record *a) u32 attr_len; u32 min_len; u16 mp_offset; + u16 name_offset; + u32 name_end; attr_len = le32_to_cpu(a->length); min_len = offsetof(struct attr_record, data.non_resident.initialized_size) + @@ -701,7 +703,27 @@ static bool ntfs_non_resident_attr_value_is_valid(const struct attr_record *a) return false; mp_offset = le16_to_cpu(a->data.non_resident.mapping_pairs_offset); - return mp_offset >= min_len && mp_offset <= attr_len; + if (mp_offset < min_len || mp_offset > attr_len) + return false; + + if (a->name_length) { + name_offset = le16_to_cpu(a->name_offset); + + if (name_offset < min_len || name_offset >= attr_len) + return false; + + name_end = name_offset + a->name_length * sizeof(__le16); + if (name_end > attr_len || name_end > mp_offset) + return false; + } + + /* Ensure there's room for the compressed_size field if needed. */ + if (!(a->flags & (ATTR_IS_SPARSE | ATTR_COMPRESSION_MASK)) && + attr_len - mp_offset < + sizeof(a->data.non_resident.compressed_size)) + return false; + + return true; } static bool ntfs_attr_value_is_valid(struct ntfs_volume *vol, diff --git a/fs/ntfs/lcnalloc.c b/fs/ntfs/lcnalloc.c index 835a041023a2..aa2e017a4384 100644 --- a/fs/ntfs/lcnalloc.c +++ b/fs/ntfs/lcnalloc.c @@ -298,7 +298,12 @@ struct runlist_element *ntfs_cluster_alloc(struct ntfs_volume *vol, const s64 st clusters = count; rlpos = rlsize = 0; mapping = lcnbmp_vi->i_mapping; - i_size = i_size_read(lcnbmp_vi); + /* + * lcn_empty_bits_per_page is sized from nr_clusters, but $Bitmap can + * cover more clusters than that; bound the scan by the array. + */ + i_size = min_t(s64, i_size_read(lcnbmp_vi), + ((s64)vol->nr_clusters + 7) >> 3); while (1) { ntfs_debug("Start of outer while loop: done_zones 0x%x, search_zone %i, pass %i, zone_start 0x%llx, zone_end 0x%llx, bmp_initial_pos 0x%llx, bmp_pos 0x%llx, rlpos %i, rlsize %i.", done_zones, search_zone, pass, diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index 8e0fd400e7f7..00373e450ea7 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -772,6 +772,25 @@ struct runlist_element *ntfs_mapping_pairs_decompress(const struct ntfs_volume * return ERR_PTR(-EIO); } + /* + * An empty mapping-pairs array is valid only for a zero-length + * attribute. + */ + if (!*buf && + (vcn || + le64_to_cpu(attr->data.non_resident.highest_vcn) != + (u64)(vcn - 1) || + le64_to_cpu(attr->data.non_resident.allocated_size) || + le64_to_cpu(attr->data.non_resident.data_size) || + le64_to_cpu(attr->data.non_resident.initialized_size))) { + ntfs_error(vol->sb, "Invalid empty mapping pairs array."); + return ERR_PTR(-EIO); + } + if (!vcn && !*buf && old_runlist && old_runlist->rl) { + *new_rl_count = old_runlist->count; + return old_runlist->rl; + } + /* Current position in runlist array. */ rlpos = 0; /* Allocate first page and set current runlist size to one page. */ @@ -884,12 +903,41 @@ struct runlist_element *ntfs_mapping_pairs_decompress(const struct ntfs_volume * ntfs_error(vol->sb, "lcn == -1"); } #endif + /* Check lcn is within the volume. */ + if (unlikely(lcn >= (s64)vol->nr_clusters)) { + ntfs_error(vol->sb, + "LCN >= nr_clusters in mapping pairs array."); + goto err_out; + } + /* Check lcn is not below -1. */ if (unlikely(lcn < -1)) { ntfs_error(vol->sb, "Invalid s64 < -1 in mapping pairs array."); goto err_out; } + if (lcn >= 0) { + s64 run_end; + + /* + * Ensure that the run stays within the volume. + * A valid starting LCN is not sufficient because + * the run length comes from disk. + */ + if (unlikely(check_add_overflow(lcn, + rl[rlpos].length, + &run_end))) { + ntfs_error(vol->sb, + "Run length overflow in mapping pairs array."); + goto err_out; + } + if (unlikely(run_end > (s64)vol->nr_clusters)) { + ntfs_error(vol->sb, + "Run extends beyond volume boundary."); + goto err_out; + } + } + /* chkdsk accepts zero-sized runs only for holes */ if ((lcn != -1) && !rl[rlpos].length) { ntfs_error(vol->sb, diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 8abe7bee4c0d..cd8fa2c13370 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -645,7 +645,7 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, { unsigned int sectors_per_cluster, sectors_per_cluster_bits, nr_hidden_sects; int clusters_per_mft_record, clusters_per_index_record; - s64 ll; + u64 ll; vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector); vol->sector_size_bits = ffs(vol->sector_size) - 1; @@ -755,23 +755,23 @@ static bool parse_ntfs_boot_sector(struct ntfs_volume *vol, * the same as it is much faster on 32-bit CPUs. */ ll = le64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits; - if ((u64)ll >= 1ULL << 32) { + if (ll >= 1ULL << 32) { ntfs_error(vol->sb, "Cannot handle 64-bit clusters."); return false; } vol->nr_clusters = ll; ntfs_debug("vol->nr_clusters = 0x%llx", vol->nr_clusters); ll = le64_to_cpu(b->mft_lcn); - if (ll >= vol->nr_clusters) { - ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of volume. Weird.", + if (ll >= (u64)vol->nr_clusters) { + ntfs_error(vol->sb, "MFT LCN (%llu, 0x%llx) is beyond end of volume. Weird.", ll, ll); return false; } vol->mft_lcn = ll; ntfs_debug("vol->mft_lcn = 0x%llx", vol->mft_lcn); ll = le64_to_cpu(b->mftmirr_lcn); - if (ll >= vol->nr_clusters) { - ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end of volume. Weird.", + if (ll >= (u64)vol->nr_clusters) { + ntfs_error(vol->sb, "MFTMirr LCN (%llu, 0x%llx) is beyond end of volume. Weird.", ll, ll); return false; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 2b49bc077558..a751661cdca9 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2443,6 +2443,15 @@ int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, err = unc_size; else if (!unc_size || unc_size > frame_size) err = -EINVAL; + else if (unc_size < frame_size) { + /* + * Partial decompress: zero the [unc_size, frame_size) + * tail. decompress_lznt() leaves it untouched, so + * without this the freshly vmapped pages would expose + * uninitialized kernel memory to userspace. + */ + memset(frame_mem + unc_size, 0, frame_size - unc_size); + } } if (!err && valid_size < frame_vbo + frame_size) { size_t ok = valid_size - frame_vbo; diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index f038c799e7ac..c759841b7430 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -648,6 +648,14 @@ static inline void *enum_rstbl(struct RESTART_TABLE *t, void *c) } /* + * dp_range_ok - true if [j, j + count) fits in a page_lcns[cap] array. + */ +static inline bool dp_range_ok(size_t j, u32 count, u32 cap) +{ + return j < cap && count <= cap - j; +} + +/* * find_dp - Search for a @vcn in Dirty Page Table. */ static inline struct DIR_PAGE_ENTRY *find_dp(struct RESTART_TABLE *dptbl, @@ -789,6 +797,20 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes) return true; } +static bool check_dp_table(const struct RESTART_TABLE *dptbl) +{ + u32 rsize = le16_to_cpu(dptbl->size); + struct DIR_PAGE_ENTRY *dp = NULL; + + while ((dp = enum_rstbl((struct RESTART_TABLE *)dptbl, dp))) { + if (struct_size(dp, page_lcns, le32_to_cpu(dp->lcns_follow)) > + rsize) + return false; + } + + return true; +} + /* * free_rsttbl_idx - Free a previously allocated index a Restart Table. */ @@ -4295,6 +4317,11 @@ check_dirty_page_table: goto out; } + if (!check_dp_table(rt)) { + err = -EINVAL; + goto out; + } + dptbl = kmemdup(rt, t32, GFP_NOFS); if (!dptbl) { err = -ENOMEM; @@ -5087,6 +5114,13 @@ find_dirty_page: /* Shorten length by any Lcns which were deleted. */ saved_len = dlen; + if (!dp_range_ok(le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn), + le16_to_cpu(lrh->lcns_follow), + le32_to_cpu(dp->lcns_follow))) { + err = -EINVAL; + goto out; + } + for (i = le16_to_cpu(lrh->lcns_follow); i; i--) { size_t j; u32 alen, voff; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index d12784aaaa4b..ea68dc0887f6 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -43,6 +43,14 @@ static DECLARE_RWSEM(o2hb_callback_sem); * whenever any of the threads sees activity from the node in its region. */ static DEFINE_SPINLOCK(o2hb_live_lock); +/* + * Serializes region pin/unpin dependency management (o2hb_dependent_users + * and the o2nm_depend_item()/o2nm_undepend_item() calls). o2hb_region_pin() + * has to drop o2hb_live_lock across the sleeping o2nm_depend_item(), so the + * spinlock alone can no longer keep pin and unpin mutually exclusive; this + * mutex, taken outside o2hb_live_lock, does. + */ +static DEFINE_MUTEX(o2hb_dependency_mutex); static struct list_head o2hb_live_slots[O2NM_MAX_NODES]; static unsigned long o2hb_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)]; static LIST_HEAD(o2hb_node_events); @@ -138,7 +146,7 @@ static unsigned int o2hb_dependent_users; * In global heartbeat mode, we pin/unpin all o2hb regions. This solution * works for both file system and userdlm domains. */ -static int o2hb_region_pin(const char *region_uuid); +static int o2hb_region_pin(const char *region_uuid, bool from_callback); static void o2hb_region_unpin(const char *region_uuid); /* Only sets a new threshold if there are no active regions. @@ -2142,6 +2150,7 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, * If global heartbeat active and there are dependent users, * pin all regions if quorum region count <= CUT_OFF */ + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); if (!o2hb_dependent_users) @@ -2149,10 +2158,11 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group, if (bitmap_weight(o2hb_quorum_region_bitmap, O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) - o2hb_region_pin(NULL); + o2hb_region_pin(NULL, true); unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); } static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item, @@ -2290,48 +2300,113 @@ EXPORT_SYMBOL_GPL(o2hb_setup_callback); * In local, we only pin the matching region. In global we pin all the active * regions. */ -static int o2hb_region_pin(const char *region_uuid) +static int o2hb_region_pin(const char *region_uuid, bool from_callback) { - int ret = 0, found = 0; - struct o2hb_region *reg; + int ret = 0, found; + struct o2hb_region *reg, *pinned; char *uuid; assert_spin_locked(&o2hb_live_lock); - list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { - if (reg->hr_item_dropped) - continue; + do { + found = 0; + pinned = NULL; - uuid = config_item_name(®->hr_item); + list_for_each_entry(reg, &o2hb_all_regions, hr_all_item) { + if (reg->hr_item_dropped) + continue; - /* local heartbeat */ - if (region_uuid) { - if (strcmp(region_uuid, uuid)) + uuid = config_item_name(®->hr_item); + + /* local heartbeat */ + if (region_uuid) { + if (strcmp(region_uuid, uuid)) + continue; + found = 1; + } + + if (reg->hr_item_pinned || reg->hr_item_dropped) { + if (found) + break; continue; - found = 1; + } + + /* + * Found a region that needs pinning. Take a reference + * so it stays alive while we drop the lock below. + */ + pinned = reg; + config_item_get(®->hr_item); + break; } - if (reg->hr_item_pinned || reg->hr_item_dropped) - goto skip_pin; + if (!pinned) + break; + + uuid = config_item_name(&pinned->hr_item); + + /* + * o2nm_depend_item() -> configfs_depend_item() can sleep (it + * takes the configfs root inode rwsem), so it must not run + * under o2hb_live_lock. Drop the lock across it; @pinned is + * kept alive by the reference taken above. The region list may + * change while unlocked, so we rescan from the top afterwards. + */ + spin_unlock(&o2hb_live_lock); /* Ignore ENOENT only for local hb (userdlm domain) */ - ret = o2nm_depend_item(®->hr_item); + if (from_callback) + ret = o2nm_depend_item_unlocked(&pinned->hr_item); + else + ret = o2nm_depend_item(&pinned->hr_item); + + spin_lock(&o2hb_live_lock); if (!ret) { - mlog(ML_CLUSTER, "Pin region %s\n", uuid); - reg->hr_item_pinned = 1; - } else { - if (ret == -ENOENT && found) - ret = 0; - else { - mlog(ML_ERROR, "Pin region %s fails with %d\n", - uuid, ret); + /* + * o2hb_live_lock was dropped across o2nm_depend_item(). + * o2hb_set_quorum_device() runs in the heartbeat thread + * without o2hb_dependency_mutex, so for global heartbeat + * it may have crossed O2HB_PIN_CUT_OFF and unpinned the + * regions while we slept. If that happened this pin is + * no longer wanted; undo it and stop rather than + * resurrecting it on the rescan below. + */ + if (!region_uuid && + bitmap_weight(o2hb_quorum_region_bitmap, + O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF) { + o2nm_undepend_item(&pinned->hr_item); + spin_unlock(&o2hb_live_lock); + config_item_put(&pinned->hr_item); + spin_lock(&o2hb_live_lock); break; } + mlog(ML_CLUSTER, "Pin region %s\n", uuid); + pinned->hr_item_pinned = 1; + } else if (ret == -ENOENT && (found || !region_uuid)) { + /* + * For local hb (found): ignore ENOENT from userdlm + * domains as before. For global hb (!region_uuid): + * the region may have been detached from configfs + * while the lock was dropped — skip it and continue + * pinning the remaining regions. + */ + ret = 0; + } else { + mlog(ML_ERROR, "Pin region %s fails with %d\n", + uuid, ret); } -skip_pin: - if (found) - break; - } + + /* + * config_item_put() may drop the last reference and run + * o2hb_region_release(), which also grabs o2hb_live_lock and + * can sleep, so it must happen with the lock released. + */ + spin_unlock(&o2hb_live_lock); + config_item_put(&pinned->hr_item); + spin_lock(&o2hb_live_lock); + + /* local hb pins a single matching region */ + } while (!ret && !region_uuid); return ret; } @@ -2376,12 +2451,13 @@ static int o2hb_region_inc_user(const char *region_uuid) { int ret = 0; + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); /* local heartbeat */ if (!o2hb_global_heartbeat_active()) { - ret = o2hb_region_pin(region_uuid); - goto unlock; + ret = o2hb_region_pin(region_uuid, false); + goto unlock; } /* @@ -2393,16 +2469,23 @@ static int o2hb_region_inc_user(const char *region_uuid) goto unlock; if (bitmap_weight(o2hb_quorum_region_bitmap, - O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) - ret = o2hb_region_pin(NULL); + O2NM_MAX_REGIONS) <= O2HB_PIN_CUT_OFF) { + ret = o2hb_region_pin(NULL, false); + if (ret) { + o2hb_region_unpin(NULL); + o2hb_dependent_users--; + } + } unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); return ret; } static void o2hb_region_dec_user(const char *region_uuid) { + mutex_lock(&o2hb_dependency_mutex); spin_lock(&o2hb_live_lock); /* local heartbeat */ @@ -2421,6 +2504,7 @@ static void o2hb_region_dec_user(const char *region_uuid) unlock: spin_unlock(&o2hb_live_lock); + mutex_unlock(&o2hb_dependency_mutex); } int o2hb_register_callback(const char *region_uuid, diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c index 402563154550..21154e4baddf 100644 --- a/fs/ocfs2/cluster/nodemanager.c +++ b/fs/ocfs2/cluster/nodemanager.c @@ -777,6 +777,12 @@ int o2nm_depend_item(struct config_item *item) return configfs_depend_item(&o2nm_cluster_group.cs_subsys, item); } +int o2nm_depend_item_unlocked(struct config_item *item) +{ + return configfs_depend_item_unlocked(&o2nm_cluster_group.cs_subsys, + item); +} + void o2nm_undepend_item(struct config_item *item) { configfs_undepend_item(item); diff --git a/fs/ocfs2/cluster/nodemanager.h b/fs/ocfs2/cluster/nodemanager.h index 3490e77a952d..2f72f56996bd 100644 --- a/fs/ocfs2/cluster/nodemanager.h +++ b/fs/ocfs2/cluster/nodemanager.h @@ -64,6 +64,7 @@ void o2nm_node_get(struct o2nm_node *node); void o2nm_node_put(struct o2nm_node *node); int o2nm_depend_item(struct config_item *item); +int o2nm_depend_item_unlocked(struct config_item *item); void o2nm_undepend_item(struct config_item *item); int o2nm_depend_this_node(void); void o2nm_undepend_this_node(void); diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index d7fc3cccf2f4..5ee894966b12 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -625,6 +625,28 @@ static int ocfs2_validate_dx_root(struct super_block *sb, le16_to_cpu(el->l_count)); goto bail; } + } else { + struct ocfs2_dx_entry_list *dl_list = &dx_root->dr_entries; + + if (le16_to_cpu(dl_list->de_count) != + ocfs2_dx_entries_per_root(sb)) { + ret = ocfs2_error(sb, + "Dir Index Root # %llu has invalid de_count %u (expected %u)\n", + (unsigned long long)le64_to_cpu(dx_root->dr_blkno), + le16_to_cpu(dl_list->de_count), + ocfs2_dx_entries_per_root(sb)); + goto bail; + } + + if (le16_to_cpu(dl_list->de_num_used) > + le16_to_cpu(dl_list->de_count)) { + ret = ocfs2_error(sb, + "Dir Index Root # %llu has invalid de_num_used %u (de_count %u)\n", + (unsigned long long)le64_to_cpu(dx_root->dr_blkno), + le16_to_cpu(dl_list->de_num_used), + le16_to_cpu(dl_list->de_count)); + goto bail; + } } bail: @@ -664,10 +686,25 @@ static int ocfs2_validate_dx_leaf(struct super_block *sb, return ret; } - if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) { - ret = ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s\n", - 7, dx_leaf->dl_signature); - } + if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) + return ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s\n", + 7, dx_leaf->dl_signature); + + if (le16_to_cpu(dx_leaf->dl_list.de_count) != + ocfs2_dx_entries_per_leaf(sb)) + return ocfs2_error(sb, + "Dir Index Leaf # %llu has invalid de_count %u (expected %u)\n", + (unsigned long long)le64_to_cpu(dx_leaf->dl_blkno), + le16_to_cpu(dx_leaf->dl_list.de_count), + ocfs2_dx_entries_per_leaf(sb)); + + if (le16_to_cpu(dx_leaf->dl_list.de_num_used) > + le16_to_cpu(dx_leaf->dl_list.de_count)) + return ocfs2_error(sb, + "Dir Index Leaf # %llu has invalid de_num_used %u (de_count %u)\n", + (unsigned long long)le64_to_cpu(dx_leaf->dl_blkno), + le16_to_cpu(dx_leaf->dl_list.de_num_used), + le16_to_cpu(dx_leaf->dl_list.de_count)); return ret; } @@ -1917,7 +1954,7 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, i += le16_to_cpu(de->rec_len); } offset = i; - ctx->pos = (ctx->pos & ~(sb->s_blocksize - 1)) + ctx->pos = (ctx->pos & ~((loff_t)sb->s_blocksize - 1)) | offset; *f_version = inode_query_iversion(inode); } diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c index aee3b4c56dcc..612969867ff9 100644 --- a/fs/ocfs2/dlm/dlmmaster.c +++ b/fs/ocfs2/dlm/dlmmaster.c @@ -3099,6 +3099,12 @@ int dlm_migrate_request_handler(struct o2net_msg *msg, u32 len, void *data, name = migrate->name; namelen = migrate->namelen; + if (namelen > DLM_LOCKID_NAME_MAX) { + mlog(ML_ERROR, "%s: invalid name length %u in migrate request\n", + dlm->name, namelen); + ret = -EINVAL; + goto leave; + } hash = dlm_lockid_hash(name, namelen); /* preallocate.. if this fails, abort */ diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index 9b97bf73df22..9d4a2695b959 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -1357,6 +1357,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data, if (!dlm_grab(dlm)) return -EINVAL; + if (mres->lockname_len > DLM_LOCKID_NAME_MAX || + mres->num_locks > DLM_MAX_MIGRATABLE_LOCKS || + be16_to_cpu(msg->data_len) < struct_size(mres, ml, mres->num_locks)) { + mlog(ML_ERROR, "%s: invalid lockres migration message from %u\n", + dlm->name, mres->master); + dlm_put(dlm); + return -EINVAL; + } + if (!dlm_joined(dlm)) { mlog(ML_ERROR, "Domain %s not joined! " "lockres %.*s, master %u\n", diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7323bde70caa..d9f22b4a2654 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -116,6 +116,33 @@ static int ocfs2_validate_refcount_block(struct super_block *sb, le32_to_cpu(rb->rf_fs_generation)); goto out; } + + /* + * rf_records (rl_count/rl_used/rl_recs[]) is only meaningful when + * this block is not an interior tree block (OCFS2_REFCOUNT_TREE_FL); + * in that case the same union bytes hold an extent list (rf_list) + * instead, which is validated by ocfs2_validate_extent_block(). + */ + if (!(le32_to_cpu(rb->rf_flags) & OCFS2_REFCOUNT_TREE_FL)) { + if (le16_to_cpu(rb->rf_records.rl_count) != + ocfs2_refcount_recs_per_rb(sb)) { + rc = ocfs2_error(sb, + "Refcount block #%llu has an invalid rl_count of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(rb->rf_records.rl_count)); + goto out; + } + + if (le16_to_cpu(rb->rf_records.rl_used) > + le16_to_cpu(rb->rf_records.rl_count)) { + rc = ocfs2_error(sb, + "Refcount block #%llu has an invalid rl_used of %u (rl_count %u)\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(rb->rf_records.rl_used), + le16_to_cpu(rb->rf_records.rl_count)); + goto out; + } + } out: return rc; } @@ -3360,10 +3387,9 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context) cow_start += num_clusters; } - if (ocfs2_dealloc_has_cluster(&context->dealloc)) { + if (ocfs2_dealloc_has_cluster(&context->dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &context->dealloc); - } + ocfs2_run_deallocs(osb, &context->dealloc); return ret; } @@ -3846,10 +3872,9 @@ unlock: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); - if (!ret && ocfs2_dealloc_has_cluster(&dealloc)) { + if (!ret && ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); out: /* * Empty the extent map so that we may get the right extent @@ -4135,10 +4160,9 @@ out_unlock_refcount: ocfs2_unlock_refcount_tree(osb, ref_tree, 1); brelse(ref_root_bh); out: - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); return ret; } @@ -4691,10 +4715,9 @@ loff_t ocfs2_reflink_remap_blocks(struct inode *s_inode, } out: - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(osb, 1); - ocfs2_run_deallocs(osb, &dealloc); - } + ocfs2_run_deallocs(osb, &dealloc); return ret; } diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index a4a2b87a45fe..20c3aec6b987 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -2759,7 +2759,7 @@ static int _ocfs2_reclaim_suballoc_to_main(handle_t *handle, fe->i_clusters = cpu_to_le32(tmp_used - le16_to_cpu(cl->cl_cpg)); spin_lock(&OCFS2_I(alloc_inode)->ip_lock); - OCFS2_I(alloc_inode)->ip_clusters -= le32_to_cpu(fe->i_clusters); + OCFS2_I(alloc_inode)->ip_clusters = le32_to_cpu(fe->i_clusters); fe->i_size = cpu_to_le64(ocfs2_clusters_to_bytes(alloc_inode->i_sb, le32_to_cpu(fe->i_clusters))); spin_unlock(&OCFS2_I(alloc_inode)->ip_lock); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 5989351aff93..f1b3aaab6a71 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -7241,10 +7241,9 @@ out_unlock: ref_tree, 1); brelse(ref_root_bh); - if (ocfs2_dealloc_has_cluster(&dealloc)) { + if (ocfs2_dealloc_has_cluster(&dealloc)) ocfs2_schedule_truncate_log_flush(OCFS2_SB(old_inode->i_sb), 1); - ocfs2_run_deallocs(OCFS2_SB(old_inode->i_sb), &dealloc); - } + ocfs2_run_deallocs(OCFS2_SB(old_inode->i_sb), &dealloc); out: return ret; diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c index 33ee8cb32f83..e5c60da7e677 100644 --- a/fs/orangefs/devorangefs-req.c +++ b/fs/orangefs/devorangefs-req.c @@ -474,6 +474,7 @@ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, op->downcall.trailer_size, iter)) { gossip_err("%s: failed to copy trailer.\n", __func__); vfree(op->downcall.trailer_buf); + op->downcall.trailer_buf = NULL; goto Efault; } diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 69bd73a2b556..9f94919a6bc6 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -569,6 +569,7 @@ static int orangefs_prepare_cdm_array(char *debug_array_string) cds_delimiter = strchr(cds_head, '\n'); *cds_delimiter = '\0'; + cds_head = skip_spaces(cds_head); keyword_len = strcspn(cds_head, " "); cdm_array[i].keyword = kzalloc(keyword_len + 1, GFP_KERNEL); diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index a033743dbf51..a8d47b1e644b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -188,7 +188,6 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent, if (!err && ofs->casefold != ovl_dentry_casefolded(newdentry)) { pr_warn_ratelimited("wrong inherited casefold (%pd2)\n", newdentry); - end_creating(newdentry); err = -EINVAL; } break; diff --git a/fs/pidfs.c b/fs/pidfs.c index b57ecc96e967..a6a643f15d08 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -532,6 +532,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct task_struct *task __free(put_task) = NULL; struct nsproxy *nsp __free(put_nsproxy) = NULL; struct ns_common *ns_common = NULL; + int error; if (!pidfs_ioctl_valid(cmd)) return -ENOIOCTLCMD; @@ -555,20 +556,33 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (arg) return -EINVAL; + /* + * We're trying to open a file descriptor to the namespace so perform a + * filesystem cred ptrace check. Hold @task's exec_update_lock for the + * duration of the ptrace check and the namespace lookup so that the + * credentials used for the access decision match those of @task at the + * time its namespace is read, preventing a concurrent execve() from + * swapping the task's credentials in between the check and the use. We + * mirror nsfs behavior. + */ + error = down_read_killable(&task->signal->exec_update_lock); + if (error) + return error; + + if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) { + error = -EACCES; + goto out_unlock; + } + scoped_guard(task_lock, task) { nsp = task->nsproxy; if (nsp) get_nsproxy(nsp); } - if (!nsp) - return -ESRCH; /* just pretend it didn't exist */ - - /* - * We're trying to open a file descriptor to the namespace so perform a - * filesystem cred ptrace check. Also, we mirror nsfs behavior. - */ - if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) - return -EACCES; + if (!nsp) { + error = -ESRCH; /* just pretend it didn't exist */ + goto out_unlock; + } switch (cmd) { /* Namespaces that hang of nsproxy. */ @@ -650,11 +664,16 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) #endif break; default: - return -ENOIOCTLCMD; + error = -ENOIOCTLCMD; } - if (!ns_common) - return -EOPNOTSUPP; + if (!error && !ns_common) + error = -EOPNOTSUPP; + +out_unlock: + up_read(&task->signal->exec_update_lock); + if (error) + return error; /* open_namespace() unconditionally consumes the reference */ return open_namespace(ns_common); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index a1dacc7d8f74..cb3a397b109c 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -1413,8 +1413,19 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, */ lock_two_nondirectories(target_inode, src_inode); - if (len == 0) - len = src_inode->i_size - off; + if (len == 0) { + loff_t src_size = i_size_read(src_inode); + + if (off > src_size) { + rc = -EINVAL; + goto unlock; + } + len = src_size - off; + if (!len) { + rc = 0; + goto unlock; + } + } cifs_dbg(FYI, "clone range\n"); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index 854e672a4e37..651670c19c2b 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -147,6 +147,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, struct file *src_file, long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg); void cifs_setsize(struct inode *inode, loff_t offset); +void cifs_resize_file_locked(struct inode *inode, loff_t offset); struct fs_context; struct smb3_fs_context; diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 1f77512252e7..f5aad5f61dce 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -615,6 +615,11 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, tcon->tid = smb_buffer_response->Tid; bcc_ptr = pByteArea(smb_buffer_response); bytes_left = get_bcc(smb_buffer_response); + if (bytes_left < 2) { + rc = smb_EIO2(smb_eio_trace_tcon_bcc_too_small, + bytes_left, 2); + goto out; + } length = strnlen(bcc_ptr, bytes_left - 2); if (smb_buffer->Flags2 & SMBFLG2_UNICODE) is_unicode = true; @@ -670,6 +675,7 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses, reset_cifs_unix_caps(xid, tcon, NULL, NULL); } } +out: cifs_buf_release(smb_buffer); return rc; } diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 8cd93cd2f00f..86dba25b7a5a 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -122,6 +122,8 @@ static inline void free_tgts(struct cache_entry *ce) kfree(t->name); kfree(t); } + + WRITE_ONCE(ce->tgthint, NULL); } static inline void flush_cache_ent(struct cache_entry *ce) @@ -869,13 +871,22 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl goto out_free_path; } - if (ref) - rc = setup_referral(path, ce, ref, get_tgt_name(ce)); - else + if (ref) { + char *target = get_tgt_name(ce); + + if (IS_ERR(target)) { + rc = PTR_ERR(target); + goto out_unlock; + } + rc = setup_referral(path, ce, ref, target); + } else { rc = 0; + } + if (!rc && tgt_list) rc = get_targets(ce, tgt_list); +out_unlock: up_read(&htable_rw_lock); out_free_path: @@ -915,10 +926,17 @@ int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, goto out_unlock; } - if (ref) - rc = setup_referral(path, ce, ref, get_tgt_name(ce)); - else + if (ref) { + char *target = get_tgt_name(ce); + + if (IS_ERR(target)) { + rc = PTR_ERR(target); + goto out_unlock; + } + rc = setup_referral(path, ce, ref, target); + } else { rc = 0; + } if (!rc && tgt_list) rc = get_targets(ce, tgt_list); @@ -959,7 +977,8 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt t = READ_ONCE(ce->tgthint); - if (unlikely(!strcasecmp(it->it_name, t->name))) + /* Check 't' in case ce->tgthint was cleared by free_tgts() */ + if (t && unlikely(!strcasecmp(it->it_name, t->name))) goto out_unlock; list_for_each_entry(t, &ce->tlist, list) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index ac89c1ba56b1..389083f9ce00 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1016,6 +1016,7 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) if (!rc) { netfs_resize_file(&cinode->netfs, 0, true); cifs_setsize(inode, 0); + cifs_invalidate_cache(inode, 0); } } if (cfile) diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 0afff761aab9..aec8ed8881a6 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -3057,9 +3057,27 @@ void cifs_setsize(struct inode *inode, loff_t offset) inode->i_blocks = blocks; spin_unlock(&inode->i_lock); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + if (offset > old_size) + pagecache_isize_extended(inode, old_size, offset); truncate_pagecache(inode, offset); netfs_wait_for_outstanding_io(inode); - fscache_resize_cookie(cifs_inode_cookie(inode), offset); +} + +void cifs_resize_file_locked(struct inode *inode, loff_t offset) +{ + struct fscache_cookie *cookie = cifs_inode_cookie(inode); + + lockdep_assert_held_write(&inode->i_rwsem); + + netfs_resize_file(netfs_inode(inode), offset, true); + cifs_setsize(inode, offset); + + if (!cookie) + return; + + fscache_use_cookie(cookie, true); + fscache_resize_cookie(cookie, offset); + cifs_fscache_unuse_inode_cookie(inode, true); } int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, @@ -3100,6 +3118,7 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, size, false); cifs_dbg(FYI, "%s: set_file_size: rc = %d\n", __func__, rc); cifsFileInfo_put(open_file); + tcon = NULL; } } @@ -3125,10 +3144,8 @@ int cifs_file_set_size(const unsigned int xid, struct dentry *dentry, cifs_put_tlink(tlink); set_size_out: - if (rc == 0) { - netfs_resize_file(&cifsInode->netfs, size, true); - cifs_setsize(inode, size); - } + if (rc == 0) + cifs_resize_file_locked(inode, size); return rc; } @@ -3214,9 +3231,13 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) attrs->ia_valid &= ~(ATTR_CTIME | ATTR_MTIME); } - /* skip mode change if it's just for clearing setuid/setgid */ - if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) - attrs->ia_valid &= ~ATTR_MODE; + /* + * This function is only called when Unix extensions are in effect, + * so the mode is always sent to and stored on the server. Do not + * skip the mode change when clearing setuid/setgid bits: dropping + * ATTR_MODE here would leave those bits set on the server after a + * write, which is a security issue. + */ args = kmalloc_obj(*args); if (args == NULL) { @@ -3425,8 +3446,23 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) attrs->ia_valid &= ~(ATTR_UID | ATTR_GID); } - /* skip mode change if it's just for clearing setuid/setgid */ - if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) + /* + * Skip the mode change if it is only being done to clear the + * setuid/setgid bits *and* the mode is emulated via the DOS + * read-only attribute (the default, non-ACL case), which cannot + * represent the setuid/setgid bits anyway. + * + * When the mode is instead stored on the server - i.e. with the + * cifsacl or modefromsid mount options (via an ACL) or with the + * SMB3.1.1 POSIX extensions - the cleared mode must be pushed to + * the server. Dropping ATTR_MODE here would leave the setuid/ + * setgid bit set on the server after a write, which is a security + * issue (the bits are not stripped as they are on local + * filesystems). + */ + if ((attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && + !((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) || + cifs_sb_master_tcon(cifs_sb)->posix_extensions)) attrs->ia_valid &= ~ATTR_MODE; if (attrs->ia_valid & ATTR_MODE) { diff --git a/fs/smb/client/smb1misc.c b/fs/smb/client/smb1misc.c index ba56023010d8..cdfbbff24b72 100644 --- a/fs/smb/client/smb1misc.c +++ b/fs/smb/client/smb1misc.c @@ -80,7 +80,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; - size_t len = srv->total_read - srv->pdu_size; + /* total_read excludes the RFC1002 preamble */ + size_t len = srv->total_read; if (get_bcc(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index dc5a8c1da623..954c1a8ef724 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -717,7 +717,7 @@ static int cifs_query_path_info(const unsigned int xid, ea->ea_value_length = cpu_to_le16(SMB2_WSL_XATTR_DEV_SIZE); memcpy(&ea->ea_data[0], SMB2_WSL_XATTR_DEV, SMB2_WSL_XATTR_NAME_LEN + 1); data->wsl.eas_len += ALIGN(sizeof(*ea) + SMB2_WSL_XATTR_NAME_LEN + 1 + - SMB2_WSL_XATTR_MODE_SIZE, 4); + SMB2_WSL_XATTR_DEV_SIZE, 4); rc = 0; } else if (rc >= 0) { /* It is an error if EA $LXDEV has wrong size. */ diff --git a/fs/smb/client/smb1transport.c b/fs/smb/client/smb1transport.c index 966f2cf83a51..42e95cc1bd89 100644 --- a/fs/smb/client/smb1transport.c +++ b/fs/smb/client/smb1transport.c @@ -375,12 +375,31 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr, unsigned int *pdu_len) data_area_of_tgt = (char *)&pSMBt->hdr.Protocol + get_unaligned_le16(&pSMBt->t2_rsp.DataOffset); - /* validate target area */ data_area_of_src = (char *)&pSMBs->hdr.Protocol + get_unaligned_le16(&pSMBs->t2_rsp.DataOffset); data_area_of_tgt += total_in_tgt; + /* + * DataOffset fields are server-supplied and not validated against + * buffer bounds; check both data pointers before mutating the + * target header. + */ + if (data_area_of_tgt < (char *)target_hdr + + sizeof(struct smb_t2_rsp) + sizeof(__le16) || + data_area_of_tgt + total_in_src > + (char *)target_hdr + CIFSMaxBufSize + MAX_CIFS_HDR_SIZE) { + cifs_dbg(VFS, "%s: target data area out of bounds\n", __func__); + return -EPROTO; + } + if (data_area_of_src < second_buf + + sizeof(struct smb_t2_rsp) + sizeof(__le16) || + data_area_of_src + total_in_src > + second_buf + smbCalcSize((struct smb_hdr *)second_buf)) { + cifs_dbg(VFS, "%s: secondary data area out of bounds\n", __func__); + return -EPROTO; + } + total_in_tgt += total_in_src; /* is the result too big for the field? */ if (total_in_tgt > USHRT_MAX) { @@ -430,10 +449,18 @@ bool cifs_check_trans2(struct mid_q_entry *mid, struct TCP_Server_Info *server, char *buf, int malformed) { - if (malformed) - return false; - if (check2ndT2(buf) <= 0) + if (malformed || check2ndT2(buf) <= 0) { + /* mid->multiRsp blocks the server buf detach in handle_mid(); + * returning false here would leak resp_buf and leave a dangling + * server->smallbuf/bigbuf after the user thread frees resp_buf. + */ + if (mid->multiRsp) { + mid->multiEnd = true; + dequeue_mid(server, mid, true); + return true; + } return false; + } mid->multiRsp = true; if (mid->resp_buf) { /* merge response - fix up 1st*/ diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index f35b6488d810..fb2fccbe8667 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -61,7 +61,10 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) cifs_dbg(FYI, "%s: skipping unhandled error context: 0x%x\n", __func__, le32_to_cpu(p->ErrorId)); - len = ALIGN(le32_to_cpu(p->ErrorDataLength), 8); + len = le32_to_cpu(p->ErrorDataLength); + if (len > end - ((u8 *)p + sizeof(*p))) + return ERR_PTR(-EINVAL); + len = ALIGN(len, 8); if (len > end - ((u8 *)p + sizeof(*p))) return ERR_PTR(-EINVAL); diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 213bc298cdf2..2946391bb992 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -40,9 +40,11 @@ static struct reparse_data_buffer *reparse_buf_ptr(struct kvec *iov) buf = (struct reparse_data_buffer *)((u8 *)io + off); len = sizeof(*buf); - rdlen = le16_to_cpu(buf->ReparseDataLength); + if (count < len) + return ERR_PTR(smb_EIO2(smb_eio_trace_reparse_rdlen, count, 0)); - if (count < len || count < rdlen + len) + rdlen = le16_to_cpu(buf->ReparseDataLength); + if (count < rdlen + len) return ERR_PTR(smb_EIO2(smb_eio_trace_reparse_rdlen, count, rdlen)); return buf; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 192649fec25d..0e872d58fae7 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2222,8 +2222,7 @@ smb2_duplicate_extents(const unsigned int xid, rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); if (rc) goto duplicate_extents_out; - netfs_resize_file(netfs_inode(inode), dest_off + len, true); - cifs_setsize(inode, dest_off + len); + cifs_resize_file_locked(inode, dest_off + len); } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, @@ -3776,8 +3775,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, } new_eof = off + len; - netfs_resize_file(&cifsi->netfs, new_eof, true); - cifs_setsize(inode, new_eof); + cifs_resize_file_locked(inode, new_eof); qrc = SMB2_query_info(xid, tcon, cfile->fid.persistent_fid, @@ -3825,8 +3823,7 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon, if (rc) goto out; - netfs_resize_file(&cifsi->netfs, new_eof, true); - cifs_setsize(inode, new_eof); + cifs_resize_file_locked(inode, new_eof); qrc = SMB2_query_info(xid, tcon, cfile->fid.persistent_fid, diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 5b21ad3c15fb..12241abb8e2e 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -133,6 +133,7 @@ EM(smb_eio_trace_sym_slash, "sym_slash") \ EM(smb_eio_trace_sym_target_len, "sym_target_len") \ EM(smb_eio_trace_symlink_file_size, "symlink_file_size") \ + EM(smb_eio_trace_tcon_bcc_too_small, "tcon_bcc_too_small") \ EM(smb_eio_trace_tdis_in_reconnect, "tdis_in_reconnect") \ EM(smb_eio_trace_tx_chained_async, "tx_chained_async") \ EM(smb_eio_trace_tx_compress_failed, "tx_compress_failed") \ @@ -213,7 +214,7 @@ #define EM(a, b) a, #define E_(a, b) a -enum smb_eio_trace { smb_eio_traces } __mode(byte); +enum smb_eio_trace { smb_eio_traces }; enum smb3_rw_credits_trace { smb3_rw_credits_traces } __mode(byte); enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index a141025581af..9bd8dce660af 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -1722,7 +1722,7 @@ int ksmbd_reopen_durable_fd(struct ksmbd_work *work, struct ksmbd_file *fp) down_write(&ci->m_lock); list_for_each_entry_rcu(op, &ci->m_op_list, op_entry, lockdep_is_held(&ci->m_lock)) { - if (op->conn) + if (op->conn || op->o_fp != fp) continue; op->conn = ksmbd_conn_get(fp->conn); op->sess = work->sess; diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c index a52458435327..9ce620a31016 100644 --- a/fs/tracefs/event_inode.c +++ b/fs/tracefs/event_inode.c @@ -438,6 +438,8 @@ static inline struct eventfs_inode *init_ei(struct eventfs_inode *ei, const char if (!ei->name) return NULL; kref_init(&ei->kref); + INIT_LIST_HEAD(&ei->children); + INIT_LIST_HEAD(&ei->list); return ei; } @@ -725,8 +727,6 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode ei->entries = entries; ei->nr_entries = size; ei->data = data; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); scoped_guard(mutex, &eventfs_mutex) { if (!parent->is_freed) @@ -798,9 +798,6 @@ struct eventfs_inode *eventfs_create_events_dir(const char *name, struct dentry ei->attr.uid = uid; ei->attr.gid = gid; - INIT_LIST_HEAD(&ei->children); - INIT_LIST_HEAD(&ei->list); - ti = get_tracefs(inode); ti->flags |= TRACEFS_EVENT_INODE; ti->private = ei; diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c index a4a0158f712d..1f770795ee70 100644 --- a/fs/ubifs/auth.c +++ b/fs/ubifs/auth.c @@ -217,7 +217,7 @@ int ubifs_sb_verify_signature(struct ubifs_info *c, signode = snod->node; - if (le32_to_cpu(signode->len) > snod->len + sizeof(struct ubifs_sig_node)) { + if (le32_to_cpu(signode->len) > snod->len - sizeof(struct ubifs_sig_node)) { ubifs_err(c, "invalid signature len %d", le32_to_cpu(signode->len)); err = -EINVAL; goto out_destroy; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 67bcf83758c8..c519644acfd7 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -531,7 +531,7 @@ static int udf_do_extend_file(struct inode *inode, sb->s_blocksize - 1) & ~(sb->s_blocksize - 1)); iinfo->i_lenExtents = (iinfo->i_lenExtents + sb->s_blocksize - 1) & - ~(sb->s_blocksize - 1); + ~((u64)sb->s_blocksize - 1); } add = 0; diff --git a/fs/udf/partition.c b/fs/udf/partition.c index 2b85c9501bed..ad8dcedca263 100644 --- a/fs/udf/partition.c +++ b/fs/udf/partition.c @@ -55,7 +55,7 @@ uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block, map = &sbi->s_partmaps[partition]; vdata = &map->s_type_specific.s_virtual; - if (block > vdata->s_num_entries) { + if (block >= vdata->s_num_entries) { udf_debug("Trying to access block beyond end of VAT (%u max %u)\n", block, vdata->s_num_entries); return 0xFFFFFFFF; |