diff options
Diffstat (limited to 'fs')
68 files changed, 898 insertions, 493 deletions
diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 714fcca9af99..17548c1faf02 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -70,7 +70,6 @@ const struct inode_operations afs_dir_inode_operations = { .permission = afs_permission, .getattr = afs_getattr, .setattr = afs_setattr, - .listxattr = afs_listxattr, }; const struct address_space_operations afs_dir_aops = { diff --git a/fs/afs/file.c b/fs/afs/file.c index 85f5adf21aa0..960b64268623 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -43,7 +43,6 @@ const struct inode_operations afs_file_inode_operations = { .getattr = afs_getattr, .setattr = afs_setattr, .permission = afs_permission, - .listxattr = afs_listxattr, }; const struct address_space_operations afs_fs_aops = { diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 97cab12b0a6c..71c58723763d 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -181,10 +181,13 @@ void afs_wait_for_operation(struct afs_operation *op) if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) && op->ops->issue_yfs_rpc) op->ops->issue_yfs_rpc(op); - else + else if (op->ops->issue_afs_rpc) op->ops->issue_afs_rpc(op); + else + op->ac.error = -ENOTSUPP; - op->error = afs_wait_for_call_to_complete(op->call, &op->ac); + if (op->call) + op->error = afs_wait_for_call_to_complete(op->call, &op->ac); } switch (op->error) { diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1156b2df28d3..12be88716e4c 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -27,7 +27,6 @@ static const struct inode_operations afs_symlink_inode_operations = { .get_link = page_get_link, - .listxattr = afs_listxattr, }; static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index b626e38e9ab5..1627b1872812 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -1509,7 +1509,6 @@ extern int afs_launder_page(struct page *); * xattr.c */ extern const struct xattr_handler *afs_xattr_handlers[]; -extern ssize_t afs_listxattr(struct dentry *, char *, size_t); /* * yfsclient.c diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 052dab2f5c03..bbb2c210d139 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -32,7 +32,6 @@ const struct inode_operations afs_mntpt_inode_operations = { .lookup = afs_mntpt_lookup, .readlink = page_readlink, .getattr = afs_getattr, - .listxattr = afs_listxattr, }; const struct inode_operations afs_autocell_inode_operations = { diff --git a/fs/afs/write.c b/fs/afs/write.c index c9195fc67fd8..eb737ed63afb 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -851,8 +851,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) fscache_wait_on_page_write(vnode->cache, vmf->page); #endif - if (PageWriteback(vmf->page) && - wait_on_page_bit_killable(vmf->page, PG_writeback) < 0) + if (wait_on_page_writeback_killable(vmf->page)) return VM_FAULT_RETRY; if (lock_page_killable(vmf->page) < 0) diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c index c629caae5002..7751b0b3f81d 100644 --- a/fs/afs/xattr.c +++ b/fs/afs/xattr.c @@ -11,29 +11,6 @@ #include <linux/xattr.h> #include "internal.h" -static const char afs_xattr_list[] = - "afs.acl\0" - "afs.cell\0" - "afs.fid\0" - "afs.volume\0" - "afs.yfs.acl\0" - "afs.yfs.acl_inherited\0" - "afs.yfs.acl_num_cleaned\0" - "afs.yfs.vol_acl"; - -/* - * Retrieve a list of the supported xattrs. - */ -ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size) -{ - if (size == 0) - return sizeof(afs_xattr_list); - if (size < sizeof(afs_xattr_list)) - return -ERANGE; - memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list)); - return sizeof(afs_xattr_list); -} - /* * Deal with the result of a successful fetch ACL operation. */ @@ -231,6 +208,8 @@ static int afs_xattr_get_yfs(const struct xattr_handler *handler, else ret = -ERANGE; } + } else if (ret == -ENOTSUPP) { + ret = -ENODATA; } error_yacl: @@ -256,6 +235,7 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler, { struct afs_operation *op; struct afs_vnode *vnode = AFS_FS_I(inode); + int ret; if (flags == XATTR_CREATE || strcmp(name, "acl") != 0) @@ -270,7 +250,10 @@ static int afs_xattr_set_yfs(const struct xattr_handler *handler, return afs_put_operation(op); op->ops = &yfs_store_opaque_acl2_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + if (ret == -ENOTSUPP) + ret = -ENODATA; + return ret; } static const struct xattr_handler afs_xattr_yfs_handler = { diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index b634c42115ea..b4fb997eda16 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute subdir-ccflags-y += -Wmissing-prototypes subdir-ccflags-y += -Wold-style-definition subdir-ccflags-y += -Wmissing-include-dirs -subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable) -subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) -subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) -subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) +condflags := \ + $(call cc-option, -Wunused-but-set-variable) \ + $(call cc-option, -Wunused-const-variable) \ + $(call cc-option, -Wpacked-not-aligned) \ + $(call cc-option, -Wstringop-truncation) +subdir-ccflags-y += $(condflags) # The following turn off the warnings enabled by -Wextra subdir-ccflags-y += -Wno-missing-field-initializers subdir-ccflags-y += -Wno-sign-compare diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index d56730a67885..34b929bd5c1a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1365,7 +1365,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) "failed to read tree block %llu from get_old_root", logical); } else { + btrfs_tree_read_lock(old); eb = btrfs_clone_extent_buffer(old); + btrfs_tree_read_unlock(old); free_extent_buffer(old); } } else if (old_root) { diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 3a9c1e046ebe..d05f73530af7 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) struct btrfs_dev_replace_item *ptr; u64 src_devid; + if (!dev_root) + return 0; + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41b718cfea40..289f1f09481d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->dev_root = root; - btrfs_init_devices_late(fs_info); } + /* Initialize fs_info for all devices in any case */ + btrfs_init_devices_late(fs_info); /* If IGNOREDATACSUMS is set don't bother reading the csum root. */ if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) { @@ -3009,6 +3010,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } + /* + * btrfs_find_orphan_roots() is responsible for finding all the dead + * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load + * them into the fs_info->fs_roots_radix tree. This must be done before + * calling btrfs_orphan_cleanup() on the tree root. If we don't do it + * first, then btrfs_orphan_cleanup() will delete a dead root's orphan + * item before the root's tree is deleted - this means that if we unmount + * or crash before the deletion completes, on the next mount we will not + * delete what remains of the tree because the orphan item does not + * exists anymore, which is what tells us we have a pending deletion. + */ + ret = btrfs_find_orphan_roots(fs_info); + if (ret) + goto out; + ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto out; @@ -3068,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } - ret = btrfs_find_orphan_roots(fs_info); out: return ret; } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 78ad31a59e59..36a3c973fda1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3323,6 +3323,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, if (last_ref && btrfs_header_generation(buf) == trans->transid) { struct btrfs_block_group *cache; + bool must_pin = false; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ret = check_ref_cleanup(trans, buf->start); @@ -3340,7 +3341,27 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, goto out; } - if (btrfs_is_zoned(fs_info)) { + /* + * If this is a leaf and there are tree mod log users, we may + * have recorded mod log operations that point to this leaf. + * So we must make sure no one reuses this leaf's extent before + * mod log operations are applied to a node, otherwise after + * rewinding a node using the mod log operations we get an + * inconsistent btree, as the leaf's extent may now be used as + * a node or leaf for another different btree. + * We are safe from races here because at this point no other + * node or root points to this extent buffer, so if after this + * check a new tree mod log user joins, it will not be able to + * find a node pointing to this leaf and record operations that + * point to this leaf. + */ + if (btrfs_header_level(buf) == 0) { + read_lock(&fs_info->tree_mod_log_lock); + must_pin = !list_empty(&fs_info->tree_mod_seq_list); + read_unlock(&fs_info->tree_mod_log_lock); + } + + if (must_pin || btrfs_is_zoned(fs_info)) { btrfs_redirty_list_add(trans->transaction, buf); pin_down_extent(trans, cache, buf->start, buf->len, 1); btrfs_put_block_group(cache); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 191e358f1322..910769d5fcdb 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2886,6 +2886,35 @@ static void end_page_read(struct page *page, bool uptodate, u64 start, u32 len) } /* + * Find extent buffer for a givne bytenr. + * + * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking + * in endio context. + */ +static struct extent_buffer *find_extent_buffer_readpage( + struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr) +{ + struct extent_buffer *eb; + + /* + * For regular sectorsize, we can use page->private to grab extent + * buffer + */ + if (fs_info->sectorsize == PAGE_SIZE) { + ASSERT(PagePrivate(page) && page->private); + return (struct extent_buffer *)page->private; + } + + /* For subpage case, we need to lookup buffer radix tree */ + rcu_read_lock(); + eb = radix_tree_lookup(&fs_info->buffer_radix, + bytenr >> fs_info->sectorsize_bits); + rcu_read_unlock(); + ASSERT(eb); + return eb; +} + +/* * after a readpage IO is done, we need to: * clear the uptodate bits on error * set the uptodate bits if things worked @@ -2996,7 +3025,7 @@ static void end_bio_extent_readpage(struct bio *bio) } else { struct extent_buffer *eb; - eb = (struct extent_buffer *)page->private; + eb = find_extent_buffer_readpage(fs_info, page, start); set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags); eb->read_mirror = mirror; atomic_dec(&eb->io_pages); @@ -3020,7 +3049,7 @@ readpage_ok: */ if (page->index == end_index && i_size <= end) { u32 zero_start = max(offset_in_page(i_size), - offset_in_page(end)); + offset_in_page(start)); zero_user_segment(page, zero_start, offset_in_page(end) + 1); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 35bfa0533f23..a520775949a0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3099,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, * @bio_offset: offset to the beginning of the bio (in bytes) * @page: page where is the data to be verified * @pgoff: offset inside the page + * @start: logical offset in the file * * The length of such check is always one sector size. */ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, - u32 bio_offset, struct page *page, u32 pgoff) + u32 bio_offset, struct page *page, u32 pgoff, + u64 start) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); @@ -3130,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, kunmap_atomic(kaddr); return 0; zeroit: - btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff, - csum, csum_expected, io_bio->mirror_num); + btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, + io_bio->mirror_num); if (io_bio->device) btrfs_dev_stat_inc_and_print(io_bio->device, BTRFS_DEV_STAT_CORRUPTION_ERRS); @@ -3184,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset, pg_off += sectorsize, bio_offset += sectorsize) { int ret; - ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off); + ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off, + page_offset(page) + pg_off); if (ret < 0) return -EIO; } @@ -7910,7 +7913,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, io_bio, - bio_offset, bvec.bv_page, pgoff))) { + bio_offset, bvec.bv_page, + pgoff, start))) { clean_io_failure(fs_info, failure_tree, io_tree, start, bvec.bv_page, btrfs_ino(BTRFS_I(inode)), @@ -8169,10 +8173,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; - WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) && - fs_info->max_zone_append_size && - bio_op(bio) != REQ_OP_ZONE_APPEND); - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, file_offset); @@ -9008,7 +9008,7 @@ int __init btrfs_init_cachep(void) btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap", PAGE_SIZE, PAGE_SIZE, - SLAB_RED_ZONE, NULL); + SLAB_MEM_SPREAD, NULL); if (!btrfs_free_space_bitmap_cachep) goto fail; @@ -9877,6 +9877,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( struct btrfs_path *path; u64 start = ins->objectid; u64 len = ins->offset; + int qgroup_released; int ret; memset(&stack_fi, 0, sizeof(stack_fi)); @@ -9889,16 +9890,16 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE); /* Encryption and other encoding is reserved and all 0 */ - ret = btrfs_qgroup_release_data(inode, file_offset, len); - if (ret < 0) - return ERR_PTR(ret); + qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len); + if (qgroup_released < 0) + return ERR_PTR(qgroup_released); if (trans) { ret = insert_reserved_file_extent(trans, inode, file_offset, &stack_fi, - true, ret); + true, qgroup_released); if (ret) - return ERR_PTR(ret); + goto free_qgroup; return trans; } @@ -9909,21 +9910,35 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent( extent_info.file_offset = file_offset; extent_info.extent_buf = (char *)&stack_fi; extent_info.is_new_extent = true; - extent_info.qgroup_reserved = ret; + extent_info.qgroup_reserved = qgroup_released; extent_info.insertions = 0; path = btrfs_alloc_path(); - if (!path) - return ERR_PTR(-ENOMEM); + if (!path) { + ret = -ENOMEM; + goto free_qgroup; + } ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset, file_offset + len - 1, &extent_info, &trans); btrfs_free_path(path); if (ret) - return ERR_PTR(ret); - + goto free_qgroup; return trans; + +free_qgroup: + /* + * We have released qgroup data range at the beginning of the function, + * and normally qgroup_released bytes will be freed when committing + * transaction. + * But if we error out early, we have to free what we have released + * or we leak qgroup data reservation. + */ + btrfs_qgroup_free_refroot(inode->root->fs_info, + inode->root->root_key.objectid, qgroup_released, + BTRFS_QGROUP_RSV_DATA); + return ERR_PTR(ret); } static int __btrfs_prealloc_file_range(struct inode *inode, int mode, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 14ff388fd3bd..f0b9ef13153a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info, { struct btrfs_qgroup_list *list; - btrfs_sysfs_del_one_qgroup(fs_info, qgroup); list_del(&qgroup->dirty); while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info, list_del(&list->next_member); kfree(list); } - kfree(qgroup); } /* must be called with qgroup_lock held */ @@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) qgroup = rb_entry(n, struct btrfs_qgroup, node); rb_erase(n, &fs_info->qgroup_tree); __del_qgroup_rb(fs_info, qgroup); + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); + kfree(qgroup); } /* * We call btrfs_free_qgroup_config() when unmounting @@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) spin_lock(&fs_info->qgroup_lock); del_qgroup_rb(fs_info, qgroupid); spin_unlock(&fs_info->qgroup_lock); + + /* + * Remove the qgroup from sysfs now without holding the qgroup_lock + * spinlock, since the sysfs_remove_group() function needs to take + * the mutex kernfs_mutex through kernfs_remove_by_name_ns(). + */ + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); + kfree(qgroup); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c index 20fd4aa48a8c..06713a8fe26b 100644 --- a/fs/btrfs/reada.c +++ b/fs/btrfs/reada.c @@ -209,7 +209,7 @@ int btree_readahead_hook(struct extent_buffer *eb, int err) /* find extent */ spin_lock(&fs_info->reada_lock); re = radix_tree_lookup(&fs_info->reada_tree, - eb->start >> PAGE_SHIFT); + eb->start >> fs_info->sectorsize_bits); if (re) re->refcnt++; spin_unlock(&fs_info->reada_lock); @@ -240,7 +240,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, zone = NULL; spin_lock(&fs_info->reada_lock); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_SHIFT, 1); + logical >> fs_info->sectorsize_bits, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) { kref_get(&zone->refcnt); spin_unlock(&fs_info->reada_lock); @@ -283,13 +283,13 @@ static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical, spin_lock(&fs_info->reada_lock); ret = radix_tree_insert(&dev->reada_zones, - (unsigned long)(zone->end >> PAGE_SHIFT), - zone); + (unsigned long)(zone->end >> fs_info->sectorsize_bits), + zone); if (ret == -EEXIST) { kfree(zone); ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone, - logical >> PAGE_SHIFT, 1); + logical >> fs_info->sectorsize_bits, 1); if (ret == 1 && logical >= zone->start && logical <= zone->end) kref_get(&zone->refcnt); else @@ -315,7 +315,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info, u64 length; int real_stripes; int nzones = 0; - unsigned long index = logical >> PAGE_SHIFT; + unsigned long index = logical >> fs_info->sectorsize_bits; int dev_replace_is_ongoing; int have_zone = 0; @@ -497,7 +497,7 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info, struct reada_extent *re) { int i; - unsigned long index = re->logical >> PAGE_SHIFT; + unsigned long index = re->logical >> fs_info->sectorsize_bits; spin_lock(&fs_info->reada_lock); if (--re->refcnt) { @@ -538,11 +538,12 @@ static void reada_extent_put(struct btrfs_fs_info *fs_info, static void reada_zone_release(struct kref *kref) { struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt); + struct btrfs_fs_info *fs_info = zone->device->fs_info; - lockdep_assert_held(&zone->device->fs_info->reada_lock); + lockdep_assert_held(&fs_info->reada_lock); radix_tree_delete(&zone->device->reada_zones, - zone->end >> PAGE_SHIFT); + zone->end >> fs_info->sectorsize_bits); kfree(zone); } @@ -593,7 +594,7 @@ static int reada_add_block(struct reada_control *rc, u64 logical, static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock) { int i; - unsigned long index = zone->end >> PAGE_SHIFT; + unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits; for (i = 0; i < zone->ndevs; ++i) { struct reada_zone *peer; @@ -628,7 +629,7 @@ static int reada_pick_zone(struct btrfs_device *dev) (void **)&zone, index, 1); if (ret == 0) break; - index = (zone->end >> PAGE_SHIFT) + 1; + index = (zone->end >> dev->fs_info->sectorsize_bits) + 1; if (zone->locked) { if (zone->elems > top_locked_elems) { top_locked_elems = zone->elems; @@ -709,7 +710,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev) * plugging to speed things up */ ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_SHIFT, 1); + dev->reada_next >> fs_info->sectorsize_bits, 1); if (ret == 0 || re->logical > dev->reada_curr_zone->end) { ret = reada_pick_zone(dev); if (!ret) { @@ -718,7 +719,7 @@ static int reada_start_machine_dev(struct btrfs_device *dev) } re = NULL; ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re, - dev->reada_next >> PAGE_SHIFT, 1); + dev->reada_next >> fs_info->sectorsize_bits, 1); } if (ret == 0) { spin_unlock(&fs_info->reada_lock); @@ -885,7 +886,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) pr_cont(" curr off %llu", device->reada_next - zone->start); pr_cont("\n"); - index = (zone->end >> PAGE_SHIFT) + 1; + index = (zone->end >> fs_info->sectorsize_bits) + 1; } cnt = 0; index = 0; @@ -910,7 +911,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } pr_cont("\n"); - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; if (++cnt > 15) break; } @@ -926,7 +927,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) if (ret == 0) break; if (!re->scheduled) { - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; continue; } pr_debug("re: logical %llu size %u list empty %d scheduled %d", @@ -942,7 +943,7 @@ static void dump_devs(struct btrfs_fs_info *fs_info, int all) } } pr_cont("\n"); - index = (re->logical >> PAGE_SHIFT) + 1; + index = (re->logical >> fs_info->sectorsize_bits) + 1; } spin_unlock(&fs_info->reada_lock); } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2f1acc9aea9e..92a368627791 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3169,10 +3169,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_lock(&log_root_tree->log_mutex); - index2 = log_root_tree->log_transid % 2; - list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); - root_log_ctx.log_transid = log_root_tree->log_transid; - if (btrfs_is_zoned(fs_info)) { if (!log_root_tree->node) { ret = btrfs_alloc_log_tree_node(trans, log_root_tree); @@ -3183,6 +3179,10 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, } } + index2 = log_root_tree->log_transid % 2; + list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]); + root_log_ctx.log_transid = log_root_tree->log_transid; + /* * Now we are safe to update the log_root_tree because we're under the * log_mutex, and we're a current writer so we're holding the commit diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bc3b33efddc5..1c6810bbaf8b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device, int item_size; int i, ret, slot; + if (!device->fs_info->dev_root) + return 0; + key.objectid = BTRFS_DEV_STATS_OBJECTID; key.type = BTRFS_PERSISTENT_ITEM_KEY; key.offset = device->devid; diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index dfb14dbddf51..38bb7764b454 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -118,6 +118,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) cache->mnt = path.mnt; root = path.dentry; + ret = -EINVAL; + if (mnt_user_ns(path.mnt) != &init_user_ns) { + pr_warn("File cache on idmapped mounts not supported"); + goto error_unsupported; + } + /* check parameters */ ret = -EOPNOTSUPP; if (d_is_negative(root) || diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index e027c718ca01..8ffc40e84a59 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -24,17 +24,16 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; struct fscache_retrieval *op = monitor->op; - struct wait_bit_key *key = _key; + struct wait_page_key *key = _key; struct page *page = wait->private; ASSERT(key); _enter("{%lu},%u,%d,{%p,%u}", monitor->netfs_page->index, mode, sync, - key->flags, key->bit_nr); + key->page, key->bit_nr); - if (key->flags != &page->flags || - key->bit_nr != PG_locked) + if (key->page != page || key->bit_nr != PG_locked) return 0; _debug("--- monitor %p %lx ---", page, page->flags); diff --git a/fs/cifs/cifs_swn.c b/fs/cifs/cifs_swn.c index f2d730fffccb..d829b8bf833e 100644 --- a/fs/cifs/cifs_swn.c +++ b/fs/cifs/cifs_swn.c @@ -248,7 +248,7 @@ nlmsg_fail: /* * Try to find a matching registration for the tcon's server name and share name. - * Calls to this funciton must be protected by cifs_swnreg_idr_mutex. + * Calls to this function must be protected by cifs_swnreg_idr_mutex. * TODO Try to avoid memory allocations */ static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 9d29eb9660c2..d178cf85e926 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1118,7 +1118,6 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl, /* Retain old ACEs which we can retain */ for (i = 0; i < src_num_aces; ++i) { pntace = (struct cifs_ace *) (acl_base + size); - pnntace = (struct cifs_ace *) (nacl_base + nsize); if (!new_aces_set && (pntace->flags & INHERITED_ACE)) { /* Place the new ACEs in between existing explicit and inherited */ @@ -1131,14 +1130,17 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl, } /* If it's any one of the ACE we're replacing, skip! */ - if ((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) || + if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) || (compare_sids(&pntace->sid, pownersid) == 0) || (compare_sids(&pntace->sid, pgrpsid) == 0) || (compare_sids(&pntace->sid, &sid_everyone) == 0) || - (compare_sids(&pntace->sid, &sid_authusers) == 0)) { + (compare_sids(&pntace->sid, &sid_authusers) == 0))) { goto next_ace; } + /* update the pointer to the next ACE to populate*/ + pnntace = (struct cifs_ace *) (nacl_base + nsize); + nsize += cifs_copy_ace(pnntace, pntace, NULL); num_aces++; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 31fc8695abd6..67c056a9a519 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -919,8 +919,8 @@ struct cifs_ses { bool binding:1; /* are we binding the session? */ __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; - __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE]; - __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE]; + __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE]; + __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; __u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 64fe5a47b5e8..9adc74bd9f8f 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -147,6 +147,11 @@ */ #define SMB3_SIGN_KEY_SIZE (16) +/* + * Size of the smb3 encryption/decryption keys + */ +#define SMB3_ENC_DEC_KEY_SIZE (32) + #define CIFS_CLIENT_CHALLENGE_SIZE (8) #define CIFS_SERVER_CHALLENGE_SIZE (8) #define CIFS_HMAC_MD5_HASH_SIZE (16) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 26de4329d161..042e24aad410 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -165,6 +165,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode, goto posix_open_ret; } } else { + cifs_revalidate_mapping(*pinode); cifs_fattr_to_inode(*pinode, &fattr); } diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 892f51a21278..78889024a7ed 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -1196,9 +1196,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, pr_warn_once("Witness protocol support is experimental\n"); break; case Opt_rootfs: -#ifdef CONFIG_CIFS_ROOT - ctx->rootfs = true; +#ifndef CONFIG_CIFS_ROOT + cifs_dbg(VFS, "rootfs support requires CONFIG_CIFS_ROOT config option\n"); + goto cifs_parse_mount_err; #endif + ctx->rootfs = true; break; case Opt_posixpaths: if (result.negated) diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 7c61bc9573c0..f2df4422e54a 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2395,7 +2395,7 @@ int cifs_getattr(struct user_namespace *mnt_userns, const struct path *path, * We need to be sure that all dirty pages are written and the server * has actual ctime, mtime and file length. */ - if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE)) && + if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE | STATX_BLOCKS)) && !CIFS_CACHE_READ(CIFS_I(inode)) && inode->i_mapping && inode->i_mapping->nrpages != 0) { rc = filemap_fdatawait(inode->i_mapping); @@ -2585,6 +2585,14 @@ set_size_out: if (rc == 0) { cifsInode->server_eof = attrs->ia_size; cifs_setsize(inode, attrs->ia_size); + /* + * i_blocks is not related to (i_size / i_blksize), but instead + * 512 byte (2**9) size is required for calculating num blocks. + * Until we can query the server for actual allocation size, + * this is best estimate we have for blocks allocated for a file + * Number of blocks must be rounded up so size 1 is not 0 blocks + */ + inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9; /* * The man page of truncate says if the size changed, diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index 99a1951a01ec..d9a990c99121 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -58,6 +58,7 @@ #define SMB2_HMACSHA256_SIZE (32) #define SMB2_CMACAES_SIZE (16) #define SMB3_SIGNKEY_SIZE (16) +#define SMB3_GCM128_CRYPTKEY_SIZE (16) #define SMB3_GCM256_CRYPTKEY_SIZE (32) /* Maximum buffer size value we can send with 1 credit */ diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b50164e2c88d..aac384f69f74 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -754,8 +754,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) } } spin_unlock(&cifs_tcp_ses_lock); - cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); - return false; + cifs_dbg(FYI, "No file id matched, oplock break ignored\n"); + return true; } void diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 9bae7e8deb09..f703204fb185 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2038,6 +2038,7 @@ smb2_duplicate_extents(const unsigned int xid, { int rc; unsigned int ret_data_len; + struct inode *inode; struct duplicate_extents_to_file dup_ext_buf; struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink); @@ -2054,10 +2055,21 @@ smb2_duplicate_extents(const unsigned int xid, cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n", src_off, dest_off, len); - rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); - if (rc) - goto duplicate_extents_out; + inode = d_inode(trgtfile->dentry); + if (inode->i_size < dest_off + len) { + rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); + if (rc) + goto duplicate_extents_out; + /* + * Although also could set plausible allocation size (i_blocks) + * here in addition to setting the file size, in reflink + * it is likely that the target file is sparse. Its allocation + * size will be queried on next revalidate, but it is important + * to make sure that file's cached size is updated immediately + */ + cifs_setsize(inode, dest_off + len); + } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, @@ -4158,7 +4170,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) if (ses->Suid == ses_id) { ses_enc_key = enc ? ses->smb3encryptionkey : ses->smb3decryptionkey; - memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE); + memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); spin_unlock(&cifs_tcp_ses_lock); return 0; } @@ -4185,7 +4197,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, int rc = 0; struct scatterlist *sg; u8 sign[SMB2_SIGNATURE_SIZE] = {}; - u8 key[SMB3_SIGN_KEY_SIZE]; + u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; char *iv; unsigned int iv_len; @@ -4209,10 +4221,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, tfm = enc ? server->secmech.ccmaesencrypt : server->secmech.ccmaesdecrypt; - if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE); else - rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE); + rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE); if (rc) { cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index ebccd71cc60a..e6fa76ab70be 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label, { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; - __u8 L[4] = {0, 0, 0, 128}; + __u8 L128[4] = {0, 0, 0, 128}; + __u8 L256[4] = {0, 0, 1, 0}; int rc = 0; unsigned char prfhash[SMB2_HMACSHA256_SIZE]; unsigned char *hashptr = prfhash; @@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label, goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, - L, 4); + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) { + rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + L256, 4); + } else { + rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + L128, 4); + } if (rc) { cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__); goto smb3signkey_ret; @@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses, const struct derivation_triplet *ptriplet) { int rc; +#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS + struct TCP_Server_Info *server = ses->server; +#endif /* * All channels use the same encryption/decryption keys but @@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses, rc = generate_key(ses, ptriplet->encryption.label, ptriplet->encryption.context, ses->smb3encryptionkey, - SMB3_SIGN_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE); rc = generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, ses->smb3decryptionkey, - SMB3_SIGN_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE); if (rc) return rc; } @@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses, */ cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid), &ses->Suid); + cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type); cifs_dbg(VFS, "Session Key %*ph\n", SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); cifs_dbg(VFS, "Signing Key %*ph\n", SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); - cifs_dbg(VFS, "ServerIn Key %*ph\n", - SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey); - cifs_dbg(VFS, "ServerOut Key %*ph\n", - SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey); + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) { + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey); + } else { + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey); + } #endif return rc; } diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 007d99437c77..c1725b55f364 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1196,9 +1196,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, /* * Compounding is never used during session establish. */ - if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) + if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) { + mutex_lock(&server->srv_mutex); smb311_update_preauth_hash(ses, rqst[0].rq_iov, rqst[0].rq_nvec); + mutex_unlock(&server->srv_mutex); + } for (i = 0; i < num_rqst; i++) { rc = wait_for_response(server, midQ[i]); @@ -1266,7 +1269,9 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses, .iov_base = resp_iov[0].iov_base, .iov_len = resp_iov[0].iov_len }; + mutex_lock(&server->srv_mutex); smb311_update_preauth_hash(ses, &iov, 1); + mutex_unlock(&server->srv_mutex); } out: diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index f45f9feebe59..74a5172c2d83 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -626,27 +626,41 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, /** * ext4_should_retry_alloc() - check if a block allocation should be retried - * @sb: super block - * @retries: number of attemps has been made + * @sb: superblock + * @retries: number of retry attempts made so far * - * ext4_should_retry_alloc() is called when ENOSPC is returned, and if - * it is profitable to retry the operation, this function will wait - * for the current or committing transaction to complete, and then - * return TRUE. We will only retry once. + * ext4_should_retry_alloc() is called when ENOSPC is returned while + * attempting to allocate blocks. If there's an indication that a pending + * journal transaction might free some space and allow another attempt to + * succeed, this function will wait for the current or committing transaction + * to complete and then return TRUE. */ int ext4_should_retry_alloc(struct super_block *sb, int *retries) { - if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) || - (*retries)++ > 1 || - !EXT4_SB(sb)->s_journal) + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!sbi->s_journal) return 0; - smp_mb(); - if (EXT4_SB(sb)->s_mb_free_pending == 0) + if (++(*retries) > 3) { + percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit); return 0; + } + /* + * if there's no indication that blocks are about to be freed it's + * possible we just missed a transaction commit that did so + */ + smp_mb(); + if (sbi->s_mb_free_pending == 0) + return ext4_has_free_clusters(sbi, 1, 0); + + /* + * it's possible we've just missed a transaction commit here, + * so ignore the returned status + */ jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id); - jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal); + (void) jbd2_journal_force_commit_nested(sbi->s_journal); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 644fd69185d3..826a56e3bbd2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1484,6 +1484,7 @@ struct ext4_sb_info { struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; struct percpu_counter s_dirtyclusters_counter; + struct percpu_counter s_sra_exceeded_retry_limit; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; @@ -2793,6 +2794,8 @@ void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); +void __ext4_fc_track_create(handle_t *handle, struct inode *inode, + struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 77c7c8a54da7..77c84d6f1af6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4382,7 +4382,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, { struct inode *inode = file_inode(file); handle_t *handle; - int ret, ret2 = 0, ret3 = 0; + int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 6c4f19b0a556..7541d0b5d706 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -513,10 +513,10 @@ void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) __ext4_fc_track_link(handle, d_inode(dentry), dentry); } -void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) +void __ext4_fc_track_create(handle_t *handle, struct inode *inode, + struct dentry *dentry) { struct __track_dentry_update_args args; - struct inode *inode = d_inode(dentry); int ret; args.dentry = dentry; @@ -527,6 +527,11 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) trace_ext4_fc_track_create(inode, dentry, ret); } +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_create(handle, d_inode(dentry), dentry); +} + /* __track_fn for inode tracking */ static int __track_inode(struct inode *inode, void *arg, bool update) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 650c5acd2f2d..0948a43f1b3d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1938,13 +1938,13 @@ static int __ext4_journalled_writepage(struct page *page, if (!ret) ret = err; - if (!ext4_has_inline_data(inode)) - ext4_walk_page_buffers(NULL, page_bufs, 0, len, - NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: unlock_page(page); out_no_pagelock: + if (!inline_data && page_bufs) + ext4_walk_page_buffers(NULL, page_bufs, 0, len, + NULL, bput_one); brelse(inode_bh); return ret; } @@ -5026,7 +5026,7 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; - int err = 0, rc, block; + int err = 0, block; int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; @@ -5138,9 +5138,9 @@ static int ext4_do_update_inode(handle_t *handle, bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - rc = ext4_handle_dirty_metadata(handle, NULL, bh); - if (!err) - err = rc; + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_brelse; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); @@ -5387,8 +5387,10 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, inode->i_gid = attr->ia_gid; error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); - if (unlikely(error)) + if (unlikely(error)) { + ext4_fc_stop_update(inode); return error; + } } if (attr->ia_valid & ATTR_SIZE) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 99bf091fee10..a02fadf4fc84 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2709,8 +2709,15 @@ static int ext4_mb_init_backend(struct super_block *sb) } if (ext4_has_feature_flex_bg(sb)) { - /* a single flex group is supposed to be read by a single IO */ - sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex, + /* a single flex group is supposed to be read by a single IO. + * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is + * unsigned integer, so the maximum shift is 32. + */ + if (sbi->s_es->s_log_groups_per_flex >= 32) { + ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); + goto err_freesgi; + } + sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 686bf982c84e..883e2a7cd4ab 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3613,6 +3613,31 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval; } +static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, + unsigned ino, unsigned file_type) +{ + struct ext4_renament old = *ent; + int retval = 0; + + /* + * old->de could have moved from under us during make indexed dir, + * so the old->de may no longer valid and need to find it again + * before reset old inode info. + */ + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + if (IS_ERR(old.bh)) + retval = PTR_ERR(old.bh); + if (!old.bh) + retval = -ENOENT; + if (retval) { + ext4_std_error(old.dir->i_sb, retval); + return; + } + + ext4_setent(handle, &old, ino, file_type); + brelse(old.bh); +} + static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, const struct qstr *d_name) { @@ -3774,14 +3799,14 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, */ retval = -ENOENT; if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino) - goto end_rename; + goto release_bh; new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, &new.de, &new.inlined); if (IS_ERR(new.bh)) { retval = PTR_ERR(new.bh); new.bh = NULL; - goto end_rename; + goto release_bh; } if (new.bh) { if (!new.inode) { @@ -3798,15 +3823,13 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_rename; + goto release_bh; } } else { whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle); if (IS_ERR(whiteout)) { retval = PTR_ERR(whiteout); - whiteout = NULL; - goto end_rename; + goto release_bh; } } @@ -3850,6 +3873,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, retval = ext4_mark_inode_dirty(handle, whiteout); if (unlikely(retval)) goto end_rename; + } if (!new.bh) { retval = ext4_add_entry(handle, new.dentry, old.inode); @@ -3923,6 +3947,8 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, ext4_fc_track_unlink(handle, new.dentry); __ext4_fc_track_link(handle, old.inode, new.dentry); __ext4_fc_track_unlink(handle, old.inode, old.dentry); + if (whiteout) + __ext4_fc_track_create(handle, whiteout, old.dentry); } if (new.inode) { @@ -3937,19 +3963,21 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, end_rename: if (whiteout) { if (retval) { - ext4_setent(handle, &old, - old.inode->i_ino, old_file_type); + ext4_resetent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + ext4_orphan_add(handle, whiteout); } unlock_new_inode(whiteout); + ext4_journal_stop(handle); iput(whiteout); - + } else { + ext4_journal_stop(handle); } +release_bh: brelse(old.dir_bh); brelse(old.bh); brelse(new.bh); - if (handle) - ext4_journal_stop(handle); return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ad34a37278cd..b9693680463a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1210,6 +1210,7 @@ static void ext4_put_super(struct super_block *sb) percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) @@ -5012,6 +5013,9 @@ no_journal: err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) + err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, + GFP_KERNEL); + if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) { @@ -5124,6 +5128,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); failed_mount5: ext4_ext_release(sb); @@ -5149,8 +5154,8 @@ failed_mount_wq: failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: - del_timer_sync(&sbi->s_err_report); flush_work(&sbi->s_error_work); + del_timer_sync(&sbi->s_err_report); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 075aa3a19ff5..a3d08276d441 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -24,6 +24,7 @@ typedef enum { attr_session_write_kbytes, attr_lifetime_write_kbytes, attr_reserved_clusters, + attr_sra_exceeded_retry_limit, attr_inode_readahead, attr_trigger_test_error, attr_first_error_time, @@ -202,6 +203,7 @@ EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444); EXT4_ATTR_FUNC(session_write_kbytes, 0444); EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444); EXT4_ATTR_FUNC(reserved_clusters, 0644); +EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, ext4_sb_info, s_inode_readahead_blks); @@ -251,6 +253,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(session_write_kbytes), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(reserved_clusters), + ATTR_LIST(sra_exceeded_retry_limit), ATTR_LIST(inode_readahead_blks), ATTR_LIST(inode_goal), ATTR_LIST(mb_stats), @@ -374,6 +377,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj, return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); + case attr_sra_exceeded_retry_limit: + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long) + percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); case attr_inode_readahead: case attr_pointer_ui: if (!ptr) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 5b7ba8f71153..00e3cbde472e 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -201,55 +201,76 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc, struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_del() */ handle_t *handle; + struct ext4_iloc iloc; int err = 0; - int err2; - if (desc != NULL) { - /* Succeeded; write the verity descriptor. */ - err = ext4_write_verity_descriptor(inode, desc, desc_size, - merkle_tree_size); - - /* Write all pages before clearing VERITY_IN_PROGRESS. */ - if (!err) - err = filemap_write_and_wait(inode->i_mapping); - } + /* + * If an error already occurred (which fs/verity/ signals by passing + * desc == NULL), then only clean-up is needed. + */ + if (desc == NULL) + goto cleanup; - /* If we failed, truncate anything we wrote past i_size. */ - if (desc == NULL || err) - ext4_truncate(inode); + /* Append the verity descriptor. */ + err = ext4_write_verity_descriptor(inode, desc, desc_size, + merkle_tree_size); + if (err) + goto cleanup; /* - * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and - * deleting the inode from the orphan list, even if something failed. - * If everything succeeded, we'll also set the verity bit in the same - * transaction. + * Write all pages (both data and verity metadata). Note that this must + * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages + * beyond i_size won't be written properly. For crash consistency, this + * also must happen before the verity inode flag gets persisted. */ + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto cleanup; - ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + /* + * Finally, set the verity inode flag and remove the inode from the + * orphan list (in a single transaction). + */ handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); - return PTR_ERR(handle); + err = PTR_ERR(handle); + goto cleanup; } - err2 = ext4_orphan_del(handle, inode); - if (err2) - goto out_stop; + err = ext4_orphan_del(handle, inode); + if (err) + goto stop_and_cleanup; - if (desc != NULL && !err) { - struct ext4_iloc iloc; + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; - err = ext4_reserve_inode_write(handle, inode, &iloc); - if (err) - goto out_stop; - ext4_set_inode_flag(inode, EXT4_INODE_VERITY); - ext4_set_inode_flags(inode, false); - err = ext4_mark_iloc_dirty(handle, inode, &iloc); - } -out_stop: + ext4_set_inode_flag(inode, EXT4_INODE_VERITY); + ext4_set_inode_flags(inode, false); + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; + + ext4_journal_stop(handle); + + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return 0; + +stop_and_cleanup: ext4_journal_stop(handle); - return err ?: err2; +cleanup: + /* + * Verity failed to be enabled, so clean up by truncating any verity + * metadata that was written beyond i_size (both from cache and from + * disk), removing the inode from the orphan list (if it wasn't done + * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS. + */ + truncate_inode_pages(inode->i_mapping, inode->i_size); + ext4_truncate(inode); + ext4_orphan_del(NULL, inode); + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return err; } static int ext4_get_verity_descriptor_location(struct inode *inode, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 372208500f4e..6c1018223c54 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1462,6 +1462,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, if (!ce) return NULL; + WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && + !(current->flags & PF_MEMALLOC_NOFS)); + ea_data = kvmalloc(value_len, GFP_KERNEL); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); @@ -2327,6 +2330,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, error = -ENOSPC; goto cleanup; } + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); @@ -2400,7 +2404,7 @@ retry_inode: * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && - !i.in_inode) { + i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index c6636b4c4ccf..c0fee830a34e 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2229,19 +2229,21 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new) static long fuse_dev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - int err = -ENOTTY; + int res; + int oldfd; + struct fuse_dev *fud = NULL; - if (cmd == FUSE_DEV_IOC_CLONE) { - int oldfd; + if (_IOC_TYPE(cmd) != FUSE_DEV_IOC_MAGIC) + return -ENOTTY; - err = -EFAULT; - if (!get_user(oldfd, (__u32 __user *) arg)) { + switch (_IOC_NR(cmd)) { + case _IOC_NR(FUSE_DEV_IOC_CLONE): + res = -EFAULT; + if (!get_user(oldfd, (__u32 __user *)arg)) { struct file *old = fget(oldfd); - err = -EINVAL; + res = -EINVAL; if (old) { - struct fuse_dev *fud = NULL; - /* * Check against file->f_op because CUSE * uses the same ioctl handler. @@ -2252,14 +2254,18 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, if (fud) { mutex_lock(&fuse_mutex); - err = fuse_device_clone(fud->fc, file); + res = fuse_device_clone(fud->fc, file); mutex_unlock(&fuse_mutex); } fput(old); } } + break; + default: + res = -ENOTTY; + break; } - return err; + return res; } const struct file_operations fuse_dev_operations = { diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 68cca8d4db6e..63d97a15ffde 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -863,6 +863,7 @@ static inline u64 fuse_get_attr_version(struct fuse_conn *fc) static inline void fuse_make_bad(struct inode *inode) { + remove_inode_hash(inode); set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state); } diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 8868ac31a3c0..4ee6f734ba83 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1324,8 +1324,15 @@ static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc) /* virtiofs allocates and installs its own fuse devices */ ctx->fudptr = NULL; - if (ctx->dax) + if (ctx->dax) { + if (!fs->dax_dev) { + err = -EINVAL; + pr_err("virtio-fs: dax can't be enabled as filesystem" + " device does not support it.\n"); + goto err_free_fuse_devs; + } ctx->dax_dev = fs->dax_dev; + } err = fuse_fill_super_common(sb, ctx); if (err < 0) goto err_free_fuse_devs; diff --git a/fs/io-wq.c b/fs/io-wq.c index 0ae9ecadf295..433c4d3c3c1c 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -16,7 +16,6 @@ #include <linux/rculist_nulls.h> #include <linux/cpu.h> #include <linux/tracehook.h> -#include <linux/freezer.h> #include "../kernel/sched/sched.h" #include "io-wq.h" @@ -386,13 +385,14 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) return NULL; } -static void io_flush_signals(void) +static bool io_flush_signals(void) { - if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) { - if (current->task_works) - task_work_run(); - clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL); + if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { + __set_current_state(TASK_RUNNING); + tracehook_notify_signal(); + return true; } + return false; } static void io_assign_current_work(struct io_worker *worker, @@ -484,10 +484,12 @@ static int io_wqe_worker(void *data) worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); io_wqe_inc_running(worker); - sprintf(buf, "iou-wrk-%d", wq->task_pid); + snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task_pid); set_task_comm(current, buf); while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + long ret; + set_current_state(TASK_INTERRUPTIBLE); loop: raw_spin_lock_irq(&wqe->lock); @@ -497,11 +499,18 @@ loop: } __io_worker_idle(wqe, worker); raw_spin_unlock_irq(&wqe->lock); - io_flush_signals(); - if (schedule_timeout(WORKER_IDLE_TIMEOUT)) + if (io_flush_signals()) continue; - if (fatal_signal_pending(current)) + ret = schedule_timeout(WORKER_IDLE_TIMEOUT); + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; break; + } + if (ret) + continue; /* timed out, exit unless we're the fixed worker */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || !(worker->flags & IO_WORKER_F_FIXED)) @@ -702,15 +711,20 @@ static int io_wq_manager(void *data) char buf[TASK_COMM_LEN]; int node; - sprintf(buf, "iou-mgr-%d", wq->task_pid); + snprintf(buf, sizeof(buf), "iou-mgr-%d", wq->task_pid); set_task_comm(current, buf); do { set_current_state(TASK_INTERRUPTIBLE); io_wq_check_workers(wq); schedule_timeout(HZ); - if (fatal_signal_pending(current)) + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; set_bit(IO_WQ_BIT_EXIT, &wq->state); + } } while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)); io_wq_check_workers(wq); @@ -1057,7 +1071,11 @@ static void io_wq_destroy(struct io_wq *wq) for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; - WARN_ON_ONCE(!wq_list_empty(&wqe->work_list)); + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + io_wqe_cancel_pending_work(wqe, &match); kfree(wqe); } io_wq_put_hash(wq->hash); diff --git a/fs/io-wq.h b/fs/io-wq.h index 1ac2f3248088..80d590564ff9 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -2,7 +2,6 @@ #define INTERNAL_IO_WQ_H #include <linux/refcount.h> -#include <linux/io_uring.h> struct io_wq; @@ -21,6 +20,15 @@ enum io_wq_cancel { IO_WQ_CANCEL_NOTFOUND, /* work not found */ }; +struct io_wq_work_node { + struct io_wq_work_node *next; +}; + +struct io_wq_work_list { + struct io_wq_work_node *first; + struct io_wq_work_node *last; +}; + static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) diff --git a/fs/io_uring.c b/fs/io_uring.c index a4bce17af506..8be542050648 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,7 +78,6 @@ #include <linux/task_work.h> #include <linux/pagemap.h> #include <linux/io_uring.h> -#include <linux/freezer.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -258,7 +257,8 @@ enum { struct io_sq_data { refcount_t refs; - struct rw_semaphore rw_lock; + atomic_t park_pending; + struct mutex lock; /* ctx's that are using this sqd */ struct list_head ctx_list; @@ -273,6 +273,7 @@ struct io_sq_data { unsigned long state; struct completion exited; + struct callback_head *park_task_work; }; #define IO_IOPOLL_BATCH 8 @@ -402,7 +403,7 @@ struct io_ring_ctx { struct socket *ring_sock; #endif - struct idr io_buffer_idr; + struct xarray io_buffers; struct xarray personalities; u32 pers_next; @@ -454,6 +455,22 @@ struct io_ring_ctx { struct list_head tctx_list; }; +struct io_uring_task { + /* submission side */ + struct xarray xa; + struct wait_queue_head wait; + const struct io_ring_ctx *last; + struct io_wq *io_wq; + struct percpu_counter inflight; + atomic_t in_idle; + bool sqpoll; + + spinlock_t task_lock; + struct io_wq_work_list task_list; + unsigned long task_state; + struct callback_head task_work; +}; + /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in <linux/fs.h> @@ -680,6 +697,7 @@ enum { REQ_F_NO_FILE_TABLE_BIT, REQ_F_LTIMEOUT_ACTIVE_BIT, REQ_F_COMPLETE_INLINE_BIT, + REQ_F_REISSUE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -723,6 +741,8 @@ enum { REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT), /* completion is deferred through io_comp_state */ REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), }; struct async_poll { @@ -1077,8 +1097,6 @@ static bool io_match_task(struct io_kiocb *head, io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; - if (req->task->files == files) - return true; } return false; } @@ -1135,7 +1153,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->cq_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); - idr_init(&ctx->io_buffer_idr); + xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1); mutex_init(&ctx->uring_lock); init_waitqueue_head(&ctx->wait); @@ -1198,7 +1216,7 @@ static void io_prep_async_work(struct io_kiocb *req) if (req->flags & REQ_F_ISREG) { if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); - } else { + } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } @@ -1221,16 +1239,16 @@ static void io_queue_async_work(struct io_kiocb *req) BUG_ON(!tctx); BUG_ON(!tctx->io_wq); - trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, - &req->work, req->flags); /* init ->work of the whole link before punting */ io_prep_async_link(req); + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, + &req->work, req->flags); io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); } -static void io_kill_timeout(struct io_kiocb *req) +static void io_kill_timeout(struct io_kiocb *req, int status) { struct io_timeout_data *io = req->async_data; int ret; @@ -1240,31 +1258,11 @@ static void io_kill_timeout(struct io_kiocb *req) atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_cqring_fill_event(req, 0); + io_cqring_fill_event(req, status); io_put_req_deferred(req, 1); } } -/* - * Returns true if we found and killed one or more timeouts - */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) -{ - struct io_kiocb *req, *tmp; - int canceled = 0; - - spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, files)) { - io_kill_timeout(req); - canceled++; - } - } - spin_unlock_irq(&ctx->completion_lock); - return canceled != 0; -} - static void __io_queue_deferred(struct io_ring_ctx *ctx) { do { @@ -1309,7 +1307,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) break; list_del_init(&req->timeout.list); - io_kill_timeout(req); + io_kill_timeout(req, 0); } while (!list_empty(&ctx->timeout_list)); ctx->cq_last_tm_flush = seq; @@ -1550,14 +1548,17 @@ static void io_req_complete_post(struct io_kiocb *req, long res, io_put_task(req->task, 1); list_add(&req->compl.list, &cs->locked_free_list); cs->locked_free_nr++; - } else - req = NULL; + } else { + if (!percpu_ref_tryget(&ctx->refs)) + req = NULL; + } io_commit_cqring(ctx); spin_unlock_irqrestore(&ctx->completion_lock, flags); - io_cqring_ev_posted(ctx); - if (req) + if (req) { + io_cqring_ev_posted(ctx); percpu_ref_put(&ctx->refs); + } } static void io_req_complete_state(struct io_kiocb *req, long res, @@ -1925,17 +1926,44 @@ static int io_req_task_work_add(struct io_kiocb *req) return ret; } -static void io_req_task_work_add_fallback(struct io_kiocb *req, - task_work_func_t cb) +static bool io_run_task_work_head(struct callback_head **work_head) +{ + struct callback_head *work, *next; + bool executed = false; + + do { + work = xchg(work_head, NULL); + if (!work) + break; + + do { + next = work->next; + work->func(work); + work = next; + cond_resched(); + } while (work); + executed = true; + } while (1); + + return executed; +} + +static void io_task_work_add_head(struct callback_head **work_head, + struct callback_head *task_work) { - struct io_ring_ctx *ctx = req->ctx; struct callback_head *head; - init_task_work(&req->task_work, cb); do { - head = READ_ONCE(ctx->exit_task_work); - req->task_work.next = head; - } while (cmpxchg(&ctx->exit_task_work, head, &req->task_work) != head); + head = READ_ONCE(*work_head); + task_work->next = head; + } while (cmpxchg(work_head, head, task_work) != head); +} + +static void io_req_task_work_add_fallback(struct io_kiocb *req, + task_work_func_t cb) +{ + init_task_work(&req->task_work, cb); + io_task_work_add_head(&req->ctx->exit_task_work, &req->task_work); } static void __io_req_task_cancel(struct io_kiocb *req, int error) @@ -2476,13 +2504,14 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, { int cflags = 0; - if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req)) + if (req->rw.kiocb.ki_flags & IOCB_WRITE) + kiocb_end_write(req); + if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; return; + } if (res != req->result) req_set_fail_links(req); - - if (req->rw.kiocb.ki_flags & IOCB_WRITE) - kiocb_end_write(req); if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_rw_kbuf(req); __io_req_complete(req, issue_flags, res, cflags); @@ -2843,7 +2872,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, lockdep_assert_held(&req->ctx->uring_lock); - head = idr_find(&req->ctx->io_buffer_idr, bgid); + head = xa_load(&req->ctx->io_buffers, bgid); if (head) { if (!list_empty(&head->list)) { kbuf = list_last_entry(&head->list, struct io_buffer, @@ -2851,7 +2880,7 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, list_del(&kbuf->list); } else { kbuf = head; - idr_remove(&req->ctx->io_buffer_idr, bgid); + xa_erase(&req->ctx->io_buffers, bgid); } if (*len > kbuf->len) *len = kbuf->len; @@ -3259,11 +3288,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ret = io_iter_do_read(req, iter); - if (ret == -EIOCBQUEUED) { - if (req->async_data) - iov_iter_revert(iter, io_size - iov_iter_count(iter)); - goto out_free; - } else if (ret == -EAGAIN) { + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; @@ -3273,6 +3298,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = 0; + } else if (ret == -EIOCBQUEUED) { + goto out_free; } else if (ret <= 0 || ret == io_size || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) { /* read all, failed, already did sync or don't want to retry */ @@ -3385,6 +3412,9 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) else ret2 = -EINVAL; + if (req->flags & REQ_F_REISSUE) + ret2 = -EAGAIN; + /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. @@ -3394,8 +3424,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) /* no retry on NONBLOCK nor RWF_NOWAIT */ if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; - if (ret2 == -EIOCBQUEUED && req->async_data) - iov_iter_revert(iter, io_size - iov_iter_count(iter)); if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) @@ -3892,7 +3920,7 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx, struct io_buffer *buf, } i++; kfree(buf); - idr_remove(&ctx->io_buffer_idr, bgid); + xa_erase(&ctx->io_buffers, bgid); return i; } @@ -3910,7 +3938,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) lockdep_assert_held(&ctx->uring_lock); ret = -ENOENT; - head = idr_find(&ctx->io_buffer_idr, p->bgid); + head = xa_load(&ctx->io_buffers, p->bgid); if (head) ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs); if (ret < 0) @@ -3930,6 +3958,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) static int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + unsigned long size; struct io_provide_buf *p = &req->pbuf; u64 tmp; @@ -3943,7 +3972,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req, p->addr = READ_ONCE(sqe->addr); p->len = READ_ONCE(sqe->len); - if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs))) + size = (unsigned long)p->len * p->nbufs; + if (!access_ok(u64_to_user_ptr(p->addr), size)) return -EFAULT; p->bgid = READ_ONCE(sqe->buf_group); @@ -3993,21 +4023,14 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) lockdep_assert_held(&ctx->uring_lock); - list = head = idr_find(&ctx->io_buffer_idr, p->bgid); + list = head = xa_load(&ctx->io_buffers, p->bgid); ret = io_add_buffers(p, &head); - if (ret < 0) - goto out; - - if (!list) { - ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1, - GFP_KERNEL); - if (ret < 0) { + if (ret >= 0 && !list) { + ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL); + if (ret < 0) __io_remove_buffers(ctx, head, p->bgid, -1U); - goto out; - } } -out: if (ret < 0) req_set_fail_links(req); @@ -4345,6 +4368,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) struct io_async_msghdr iomsg, *kmsg; struct socket *sock; unsigned flags; + int min_ret = 0; int ret; sock = sock_from_file(req->file); @@ -4359,12 +4383,15 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) kmsg = &iomsg; } - flags = req->sr_msg.msg_flags; + flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; else if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags); if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) return io_setup_async_msg(req, kmsg); @@ -4375,7 +4402,7 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) + if (ret < min_ret) req_set_fail_links(req); __io_req_complete(req, issue_flags, ret, 0); return 0; @@ -4388,6 +4415,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) struct iovec iov; struct socket *sock; unsigned flags; + int min_ret = 0; int ret; sock = sock_from_file(req->file); @@ -4403,12 +4431,15 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) msg.msg_controllen = 0; msg.msg_namelen = 0; - flags = req->sr_msg.msg_flags; + flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; else if (issue_flags & IO_URING_F_NONBLOCK) flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + msg.msg_flags = flags; ret = sock_sendmsg(sock, &msg); if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN) @@ -4416,7 +4447,7 @@ static int io_send(struct io_kiocb *req, unsigned int issue_flags) if (ret == -ERESTARTSYS) ret = -EINTR; - if (ret < 0) + if (ret < min_ret) req_set_fail_links(req); __io_req_complete(req, issue_flags, ret, 0); return 0; @@ -4568,6 +4599,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) struct socket *sock; struct io_buffer *kbuf; unsigned flags; + int min_ret = 0; int ret, cflags = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -4593,12 +4625,15 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) 1, req->sr_msg.len); } - flags = req->sr_msg.msg_flags; + flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; else if (force_nonblock) flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&kmsg->msg.msg_iter); + ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg, kmsg->uaddr, flags); if (force_nonblock && ret == -EAGAIN) @@ -4612,7 +4647,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (kmsg->free_iov) kfree(kmsg->free_iov); req->flags &= ~REQ_F_NEED_CLEANUP; - if (ret < 0) + if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) req_set_fail_links(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; @@ -4627,6 +4662,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) struct socket *sock; struct iovec iov; unsigned flags; + int min_ret = 0; int ret, cflags = 0; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; @@ -4652,12 +4688,15 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) msg.msg_iocb = NULL; msg.msg_flags = 0; - flags = req->sr_msg.msg_flags; + flags = req->sr_msg.msg_flags | MSG_NOSIGNAL; if (flags & MSG_DONTWAIT) req->flags |= REQ_F_NOWAIT; else if (force_nonblock) flags |= MSG_DONTWAIT; + if (flags & MSG_WAITALL) + min_ret = iov_iter_count(&msg.msg_iter); + ret = sock_recvmsg(sock, &msg, flags); if (force_nonblock && ret == -EAGAIN) return -EAGAIN; @@ -4666,7 +4705,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) out_free: if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_recv_kbuf(req); - if (ret < 0) + if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)))) req_set_fail_links(req); __io_req_complete(req, issue_flags, ret, cflags); return 0; @@ -4763,7 +4802,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags) ret = -ENOMEM; goto out; } - io = req->async_data; memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } @@ -5526,7 +5564,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); - io_req_track_inflight(req); + if (is_timeout_link) + io_req_track_inflight(req); return 0; } @@ -6129,6 +6168,7 @@ static void io_wq_submit_work(struct io_wq_work *work) ret = -ECANCELED; if (!ret) { + req->flags &= ~REQ_F_REISSUE; do { ret = io_issue_sqe(req, 0); /* @@ -6204,7 +6244,6 @@ static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer) spin_unlock_irqrestore(&ctx->completion_lock, flags); if (prev) { - req_set_fail_links(prev); io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME); io_put_req_deferred(prev, 1); } else { @@ -6423,8 +6462,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) { fail_req: - io_put_req(req); - io_req_complete(req, ret); if (link->head) { /* fail even hard links since we don't submit */ link->head->flags |= REQ_F_FAIL_LINK; @@ -6432,6 +6469,8 @@ fail_req: io_req_complete(link->head, -ECANCELED); link->head = NULL; } + io_put_req(req); + io_req_complete(req, ret); return ret; } ret = io_req_prep(req, sqe); @@ -6684,7 +6723,7 @@ static int io_sq_thread(void *data) char buf[TASK_COMM_LEN]; DEFINE_WAIT(wait); - sprintf(buf, "iou-sqp-%d", sqd->task_pid); + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); current->pf_io_worker = NULL; @@ -6694,22 +6733,30 @@ static int io_sq_thread(void *data) set_cpus_allowed_ptr(current, cpu_online_mask); current->flags |= PF_NO_SETAFFINITY; - down_read(&sqd->rw_lock); - + mutex_lock(&sqd->lock); while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) { int ret; bool cap_entries, sqt_spin, needs_sched; - if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) { - up_read(&sqd->rw_lock); + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + bool did_sig = false; + + mutex_unlock(&sqd->lock); + if (signal_pending(current)) { + struct ksignal ksig; + + did_sig = get_signal(&ksig); + } cond_resched(); - down_read(&sqd->rw_lock); + mutex_lock(&sqd->lock); + if (did_sig) + break; io_run_task_work(); + io_run_task_work_head(&sqd->park_task_work); timeout = jiffies + sqd->sq_thread_idle; continue; } - if (fatal_signal_pending(current)) - break; sqt_spin = false; cap_entries = !list_is_singular(&sqd->ctx_list); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { @@ -6750,32 +6797,27 @@ static int io_sq_thread(void *data) list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_set_wakeup_flag(ctx); - up_read(&sqd->rw_lock); + mutex_unlock(&sqd->lock); schedule(); - down_read(&sqd->rw_lock); + mutex_lock(&sqd->lock); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); } finish_wait(&sqd->wait, &wait); + io_run_task_work_head(&sqd->park_task_work); timeout = jiffies + sqd->sq_thread_idle; } - up_read(&sqd->rw_lock); - down_write(&sqd->rw_lock); - /* - * someone may have parked and added a cancellation task_work, run - * it first because we don't want it in io_uring_cancel_sqpoll() - */ - io_run_task_work(); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_uring_cancel_sqpoll(ctx); sqd->thread = NULL; list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_set_wakeup_flag(ctx); - up_write(&sqd->rw_lock); + mutex_unlock(&sqd->lock); io_run_task_work(); + io_run_task_work_head(&sqd->park_task_work); complete(&sqd->exited); do_exit(0); } @@ -6821,7 +6863,7 @@ static int io_run_task_work_sig(void) return 1; if (!signal_pending(current)) return 0; - if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL)) + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) return -ERESTARTSYS; return -EINTR; } @@ -7075,23 +7117,28 @@ static int io_sqe_files_unregister(struct io_ring_ctx *ctx) } static void io_sq_thread_unpark(struct io_sq_data *sqd) - __releases(&sqd->rw_lock) + __releases(&sqd->lock) { WARN_ON_ONCE(sqd->thread == current); + /* + * Do the dance but not conditional clear_bit() because it'd race with + * other threads incrementing park_pending and setting the bit. + */ clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); - up_write(&sqd->rw_lock); + if (atomic_dec_return(&sqd->park_pending)) + set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_unlock(&sqd->lock); } static void io_sq_thread_park(struct io_sq_data *sqd) - __acquires(&sqd->rw_lock) + __acquires(&sqd->lock) { WARN_ON_ONCE(sqd->thread == current); + atomic_inc(&sqd->park_pending); set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); - down_write(&sqd->rw_lock); - /* set again for consistency, in case concurrent parks are happening */ - set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state); + mutex_lock(&sqd->lock); if (sqd->thread) wake_up_process(sqd->thread); } @@ -7100,17 +7147,19 @@ static void io_sq_thread_stop(struct io_sq_data *sqd) { WARN_ON_ONCE(sqd->thread == current); - down_write(&sqd->rw_lock); + mutex_lock(&sqd->lock); set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); if (sqd->thread) wake_up_process(sqd->thread); - up_write(&sqd->rw_lock); + mutex_unlock(&sqd->lock); wait_for_completion(&sqd->exited); } static void io_put_sq_data(struct io_sq_data *sqd) { if (refcount_dec_and_test(&sqd->refs)) { + WARN_ON_ONCE(atomic_read(&sqd->park_pending)); + io_sq_thread_stop(sqd); kfree(sqd); } @@ -7184,9 +7233,10 @@ static struct io_sq_data *io_get_sq_data(struct io_uring_params *p, if (!sqd) return ERR_PTR(-ENOMEM); + atomic_set(&sqd->park_pending, 0); refcount_set(&sqd->refs, 1); INIT_LIST_HEAD(&sqd->ctx_list); - init_rwsem(&sqd->rw_lock); + mutex_init(&sqd->lock); init_waitqueue_head(&sqd->wait); init_completion(&sqd->exited); return sqd; @@ -7866,22 +7916,17 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, ret = 0; io_sq_thread_park(sqd); + list_add(&ctx->sqd_list, &sqd->ctx_list); + io_sqd_update_thread_idle(sqd); /* don't attach to a dying SQPOLL thread, would be racy */ - if (attached && !sqd->thread) { + if (attached && !sqd->thread) ret = -ENXIO; - } else { - list_add(&ctx->sqd_list, &sqd->ctx_list); - io_sqd_update_thread_idle(sqd); - } io_sq_thread_unpark(sqd); - if (ret < 0) { - io_put_sq_data(sqd); - ctx->sq_data = NULL; - return ret; - } else if (attached) { + if (ret < 0) + goto err; + if (attached) return 0; - } if (p->flags & IORING_SETUP_SQ_AFF) { int cpu = p->sq_thread_cpu; @@ -8332,19 +8377,13 @@ static int io_eventfd_unregister(struct io_ring_ctx *ctx) return -ENXIO; } -static int __io_destroy_buffers(int id, void *p, void *data) -{ - struct io_ring_ctx *ctx = data; - struct io_buffer *buf = p; - - __io_remove_buffers(ctx, buf, id, -1U); - return 0; -} - static void io_destroy_buffers(struct io_ring_ctx *ctx) { - idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx); - idr_destroy(&ctx->io_buffer_idr); + struct io_buffer *buf; + unsigned long index; + + xa_for_each(&ctx->io_buffers, index, buf) + __io_remove_buffers(ctx, buf, index, -1U); } static void io_req_cache_free(struct list_head *list, struct task_struct *tsk) @@ -8386,11 +8425,13 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) { /* * Some may use context even when all refs and requests have been put, - * and they are free to do so while still holding uring_lock, see - * __io_req_task_submit(). Wait for them to finish. + * and they are free to do so while still holding uring_lock or + * completion_lock, see __io_req_task_submit(). Wait for them to finish. */ mutex_lock(&ctx->uring_lock); mutex_unlock(&ctx->uring_lock); + spin_lock_irq(&ctx->completion_lock); + spin_unlock_irq(&ctx->completion_lock); io_sq_thread_finish(ctx); io_sqe_buffers_unregister(ctx); @@ -8478,26 +8519,9 @@ static int io_unregister_personality(struct io_ring_ctx *ctx, unsigned id) return -EINVAL; } -static bool io_run_ctx_fallback(struct io_ring_ctx *ctx) +static inline bool io_run_ctx_fallback(struct io_ring_ctx *ctx) { - struct callback_head *work, *next; - bool executed = false; - - do { - work = xchg(&ctx->exit_task_work, NULL); - if (!work) - break; - - do { - next = work->next; - work->func(work); - work = next; - cond_resched(); - } while (work); - executed = true; - } while (1); - - return executed; + return io_run_task_work_head(&ctx->exit_task_work); } struct io_tctx_exit { @@ -8529,6 +8553,14 @@ static void io_ring_exit_work(struct work_struct *work) struct io_tctx_node *node; int ret; + /* prevent SQPOLL from submitting new requests */ + if (ctx->sq_data) { + io_sq_thread_park(ctx->sq_data); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(ctx->sq_data); + io_sq_thread_unpark(ctx->sq_data); + } + /* * If we're doing polled IO and end up having requests being * submitted async (out-of-line), then completions can come in while @@ -8565,6 +8597,28 @@ static void io_ring_exit_work(struct work_struct *work) io_ring_ctx_free(ctx); } +/* Returns true if we found and killed one or more timeouts */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + struct files_struct *files) +{ + struct io_kiocb *req, *tmp; + int canceled = 0; + + spin_lock_irq(&ctx->completion_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + if (io_match_task(req, tsk, files)) { + io_kill_timeout(req, -ECANCELED); + canceled++; + } + } + if (canceled != 0) + io_commit_cqring(ctx); + spin_unlock_irq(&ctx->completion_lock); + if (canceled != 0) + io_cqring_ev_posted(ctx); + return canceled != 0; +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; @@ -8879,7 +8933,7 @@ static void io_sqpoll_cancel_sync(struct io_ring_ctx *ctx) if (task) { init_completion(&work.completion); init_task_work(&work.task_work, io_sqpoll_cancel_cb); - WARN_ON_ONCE(task_work_add(task, &work.task_work, TWA_SIGNAL)); + io_task_work_add_head(&sqd->park_task_work, &work.task_work); wake_up_process(task); } io_sq_thread_unpark(sqd); @@ -8956,6 +9010,8 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c index a648dbf6991e..a5e478de1417 100644 --- a/fs/iomap/swapfile.c +++ b/fs/iomap/swapfile.c @@ -170,6 +170,16 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, return ret; } + /* + * If this swapfile doesn't contain even a single page-aligned + * contiguous range of blocks, reject this useless swapfile to + * prevent confusion later on. + */ + if (isi.nr_pages == 0) { + pr_warn("swapon: Cannot find a single usable page in file.\n"); + return -EINVAL; + } + *pagespan = 1 + isi.highest_ppage - isi.lowest_ppage; sis->max = isi.nr_pages; sis->pages = isi.nr_pages - 1; diff --git a/fs/locks.c b/fs/locks.c index 99ca97e81b7a..6125d2de39b8 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1808,9 +1808,6 @@ check_conflicting_open(struct file *filp, const long arg, int flags) if (flags & FL_LAYOUT) return 0; - if (flags & FL_DELEG) - /* We leave these checks to the caller. */ - return 0; if (arg == F_RDLCK) return inode_is_open_for_write(inode) ? -EAGAIN : 0; diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig index 821e5913faee..d6cff5fbe705 100644 --- a/fs/nfsd/Kconfig +++ b/fs/nfsd/Kconfig @@ -73,6 +73,7 @@ config NFSD_V4 select NFSD_V3 select FS_POSIX_ACL select SUNRPC_GSS + select CRYPTO select CRYPTO_MD5 select CRYPTO_SHA256 select GRACE_PERIOD diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 53fcbf79bdca..7629248fdd53 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -898,6 +898,8 @@ nfsd_file_find_locked(struct inode *inode, unsigned int may_flags, continue; if (!nfsd_match_cred(nf->nf_cred, current_cred())) continue; + if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) + continue; if (nfsd_file_get(nf) != NULL) return nf; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 052be5bf9ef5..7325592b456e 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -1189,6 +1189,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case -EIO: case -ETIMEDOUT: + case -EACCES: nfsd4_mark_cb_down(clp, task->tk_status); } break; diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index acdb3cd806a1..dd9f38d072dd 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1302,7 +1302,7 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct nfsd_file *src, struct nfsd_file *dst) { nfs42_ssc_close(src->nf_file); - /* 'src' is freed by nfsd4_do_async_copy */ + fput(src->nf_file); nfsd_file_put(dst); mntput(ss_mnt); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 423fd6683f3a..97447a64bad0 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4940,31 +4940,6 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, return fl; } -static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, - struct nfs4_file *fp) -{ - struct nfs4_clnt_odstate *co; - struct file *f = fp->fi_deleg_file->nf_file; - struct inode *ino = locks_inode(f); - int writes = atomic_read(&ino->i_writecount); - - if (fp->fi_fds[O_WRONLY]) - writes--; - if (fp->fi_fds[O_RDWR]) - writes--; - if (writes > 0) - return -EAGAIN; - spin_lock(&fp->fi_lock); - list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) { - if (co->co_client != clp) { - spin_unlock(&fp->fi_lock); - return -EAGAIN; - } - } - spin_unlock(&fp->fi_lock); - return 0; -} - static struct nfs4_delegation * nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) @@ -4984,12 +4959,9 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, nf = find_readable_file(fp); if (!nf) { - /* - * We probably could attempt another open and get a read - * delegation, but for now, don't bother until the - * client actually sends us one. - */ - return ERR_PTR(-EAGAIN); + /* We should always have a readable file here */ + WARN_ON_ONCE(1); + return ERR_PTR(-EBADF); } spin_lock(&state_lock); spin_lock(&fp->fi_lock); @@ -5019,19 +4991,11 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (!fl) goto out_clnt_odstate; - status = nfsd4_check_conflicting_opens(clp, fp); - if (status) { - locks_free_lock(fl); - goto out_clnt_odstate; - } status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL); if (fl) locks_free_lock(fl); if (status) goto out_clnt_odstate; - status = nfsd4_check_conflicting_opens(clp, fp); - if (status) - goto out_clnt_odstate; spin_lock(&state_lock); spin_lock(&fp->fi_lock); @@ -5113,6 +5077,17 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; + /* + * Also, if the file was opened for write or + * create, there's a good chance the client's + * about to write to it, resulting in an + * immediate recall (since we don't support + * write delegations): + */ + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) + goto out_no_deleg; + if (open->op_create == NFS4_OPEN_CREATE) + goto out_no_deleg; break; default: goto out_no_deleg; @@ -5389,7 +5364,7 @@ nfs4_laundromat(struct nfsd_net *nn) idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID && - cps->cpntf_time > cutoff) + cps->cpntf_time < cutoff) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index 9b3b06da568c..e47fde1182de 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -44,7 +44,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec); static inline int reiserfs_xattrs_initialized(struct super_block *sb) { - return REISERFS_SB(sb)->priv_root != NULL; + return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root; } #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) diff --git a/fs/select.c b/fs/select.c index 37aaa8317f3a..945896d0ac9e 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1055,10 +1055,9 @@ static long do_restart_poll(struct restart_block *restart_block) ret = do_sys_poll(ufds, nfds, to); - if (ret == -ERESTARTNOHAND) { - restart_block->fn = do_restart_poll; - ret = -ERESTART_RESTARTBLOCK; - } + if (ret == -ERESTARTNOHAND) + ret = set_restart_fn(restart_block, do_restart_poll); + return ret; } @@ -1080,7 +1079,6 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, struct restart_block *restart_block; restart_block = ¤t->restart_block; - restart_block->fn = do_restart_poll; restart_block->poll.ufds = ufds; restart_block->poll.nfds = nfds; @@ -1091,7 +1089,7 @@ SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds, } else restart_block->poll.has_timeout = 0; - ret = -ERESTART_RESTARTBLOCK; + ret = set_restart_fn(restart_block, do_restart_poll); } return ret; } diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index eb02072d28dd..723763746238 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end + || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= lookup_table_start || + (lookup_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index 11581bf31af4..ea5387679723 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 8d64edb80ebf..b3fdc8212c5f 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -17,6 +17,7 @@ /* size of metadata (inode and directory) blocks */ #define SQUASHFS_METADATA_SIZE 8192 +#define SQUASHFS_BLOCK_OFFSET 2 /* default size of block device I/O */ #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index ead66670b41a..087cab8c78f4 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 46a861d55e48..f93370bd7b1e 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1007,9 +1007,10 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, - XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, - &udqp, &gdqp, &pdqp); + error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns), + fsgid_into_mnt(mnt_userns), prid, + XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, + &udqp, &gdqp, &pdqp); if (error) return error; @@ -1157,9 +1158,10 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, - XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, - &udqp, &gdqp, &pdqp); + error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns), + fsgid_into_mnt(mnt_userns), prid, + XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, + &udqp, &gdqp, &pdqp); if (error) return error; diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index ca310a125d1e..3498b97fb06d 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -168,6 +168,12 @@ xfs_bulkstat_one( }; int error; + if (breq->mnt_userns != &init_user_ns) { + xfs_warn_ratelimited(breq->mp, + "bulkstat not supported inside of idmapped mounts."); + return -EINVAL; + } + ASSERT(breq->icount == 1); bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat), diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 52370d0a3f43..1c97b155a8ee 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -635,6 +635,47 @@ xfs_check_summary_counts( } /* + * Flush and reclaim dirty inodes in preparation for unmount. Inodes and + * internal inode structures can be sitting in the CIL and AIL at this point, + * so we need to unpin them, write them back and/or reclaim them before unmount + * can proceed. + * + * An inode cluster that has been freed can have its buffer still pinned in + * memory because the transaction is still sitting in a iclog. The stale inodes + * on that buffer will be pinned to the buffer until the transaction hits the + * disk and the callbacks run. Pushing the AIL will skip the stale inodes and + * may never see the pinned buffer, so nothing will push out the iclog and + * unpin the buffer. + * + * Hence we need to force the log to unpin everything first. However, log + * forces don't wait for the discards they issue to complete, so we have to + * explicitly wait for them to complete here as well. + * + * Then we can tell the world we are unmounting so that error handling knows + * that the filesystem is going away and we should error out anything that we + * have been retrying in the background. This will prevent never-ending + * retries in AIL pushing from hanging the unmount. + * + * Finally, we can push the AIL to clean all the remaining dirty objects, then + * reclaim the remaining inodes that are still in memory at this point in time. + */ +static void +xfs_unmount_flush_inodes( + struct xfs_mount *mp) +{ + xfs_log_force(mp, XFS_LOG_SYNC); + xfs_extent_busy_wait_all(mp); + flush_workqueue(xfs_discard_wq); + + mp->m_flags |= XFS_MOUNT_UNMOUNTING; + + xfs_ail_push_all_sync(mp->m_ail); + cancel_delayed_work_sync(&mp->m_reclaim_work); + xfs_reclaim_inodes(mp); + xfs_health_unmount(mp); +} + +/* * This function does the following on an initial mount of a file system: * - reads the superblock from disk and init the mount struct * - if we're a 32-bit kernel, do a size check on the superblock @@ -1008,7 +1049,7 @@ xfs_mountfs( /* Clean out dquots that might be in memory after quotacheck. */ xfs_qm_unmount(mp); /* - * Cancel all delayed reclaim work and reclaim the inodes directly. + * Flush all inode reclamation work and flush the log. * We have to do this /after/ rtunmount and qm_unmount because those * two will have scheduled delayed reclaim for the rt/quota inodes. * @@ -1018,11 +1059,8 @@ xfs_mountfs( * qm_unmount_quotas and therefore rely on qm_unmount to release the * quota inodes. */ - cancel_delayed_work_sync(&mp->m_reclaim_work); - xfs_reclaim_inodes(mp); - xfs_health_unmount(mp); + xfs_unmount_flush_inodes(mp); out_log_dealloc: - mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); out_fail_wait: if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) @@ -1063,47 +1101,7 @@ xfs_unmountfs( xfs_rtunmount_inodes(mp); xfs_irele(mp->m_rootip); - /* - * We can potentially deadlock here if we have an inode cluster - * that has been freed has its buffer still pinned in memory because - * the transaction is still sitting in a iclog. The stale inodes - * on that buffer will be pinned to the buffer until the - * transaction hits the disk and the callbacks run. Pushing the AIL will - * skip the stale inodes and may never see the pinned buffer, so - * nothing will push out the iclog and unpin the buffer. Hence we - * need to force the log here to ensure all items are flushed into the - * AIL before we go any further. - */ - xfs_log_force(mp, XFS_LOG_SYNC); - - /* - * Wait for all busy extents to be freed, including completion of - * any discard operation. - */ - xfs_extent_busy_wait_all(mp); - flush_workqueue(xfs_discard_wq); - - /* - * We now need to tell the world we are unmounting. This will allow - * us to detect that the filesystem is going away and we should error - * out anything that we have been retrying in the background. This will - * prevent neverending retries in AIL pushing from hanging the unmount. - */ - mp->m_flags |= XFS_MOUNT_UNMOUNTING; - - /* - * Flush all pending changes from the AIL. - */ - xfs_ail_push_all_sync(mp->m_ail); - - /* - * Reclaim all inodes. At this point there should be no dirty inodes and - * none should be pinned or locked. Stop background inode reclaim here - * if it is still running. - */ - cancel_delayed_work_sync(&mp->m_reclaim_work); - xfs_reclaim_inodes(mp); - xfs_health_unmount(mp); + xfs_unmount_flush_inodes(mp); xfs_qm_unmount(mp); diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index 1379013d74b8..7f368b10ded1 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -182,7 +182,8 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid, + error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns), + fsgid_into_mnt(mnt_userns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 0fe76f376dee..049e36c69ed7 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -165,6 +165,21 @@ static int zonefs_writepages(struct address_space *mapping, return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops); } +static int zonefs_swap_activate(struct swap_info_struct *sis, + struct file *swap_file, sector_t *span) +{ + struct inode *inode = file_inode(swap_file); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + + if (zi->i_ztype != ZONEFS_ZTYPE_CNV) { + zonefs_err(inode->i_sb, + "swap file: not a conventional zone file\n"); + return -EINVAL; + } + + return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops); +} + static const struct address_space_operations zonefs_file_aops = { .readpage = zonefs_readpage, .readahead = zonefs_readahead, @@ -177,6 +192,7 @@ static const struct address_space_operations zonefs_file_aops = { .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_page = generic_error_remove_page, .direct_IO = noop_direct_IO, + .swap_activate = zonefs_swap_activate, }; static void zonefs_update_stats(struct inode *inode, loff_t new_isize) @@ -728,6 +744,68 @@ out_release: } /* + * Do not exceed the LFS limits nor the file zone size. If pos is under the + * limit it becomes a short access. If it exceeds the limit, return -EFBIG. + */ +static loff_t zonefs_write_check_limits(struct file *file, loff_t pos, + loff_t count) +{ + struct inode *inode = file_inode(file); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + loff_t limit = rlimit(RLIMIT_FSIZE); + loff_t max_size = zi->i_max_size; + + if (limit != RLIM_INFINITY) { + if (pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + count = min(count, limit - pos); + } + + if (!(file->f_flags & O_LARGEFILE)) + max_size = min_t(loff_t, MAX_NON_LFS, max_size); + + if (unlikely(pos >= max_size)) + return -EFBIG; + + return min(count, max_size - pos); +} + +static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); + struct zonefs_inode_info *zi = ZONEFS_I(inode); + loff_t count; + + if (IS_SWAPFILE(inode)) + return -ETXTBSY; + + if (!iov_iter_count(from)) + return 0; + + if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) + return -EINVAL; + + if (iocb->ki_flags & IOCB_APPEND) { + if (zi->i_ztype != ZONEFS_ZTYPE_SEQ) + return -EINVAL; + mutex_lock(&zi->i_truncate_mutex); + iocb->ki_pos = zi->i_wpoffset; + mutex_unlock(&zi->i_truncate_mutex); + } + + count = zonefs_write_check_limits(file, iocb->ki_pos, + iov_iter_count(from)); + if (count < 0) + return count; + + iov_iter_truncate(from, count); + return iov_iter_count(from); +} + +/* * Handle direct writes. For sequential zone files, this is the only possible * write path. For these files, check that the user is issuing writes * sequentially from the end of the file. This code assumes that the block layer @@ -744,8 +822,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) struct super_block *sb = inode->i_sb; bool sync = is_sync_kiocb(iocb); bool append = false; - size_t count; - ssize_t ret; + ssize_t ret, count; /* * For async direct IOs to sequential zone files, refuse IOCB_NOWAIT @@ -763,12 +840,11 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) inode_lock(inode); } - ret = generic_write_checks(iocb, from); - if (ret <= 0) + count = zonefs_write_checks(iocb, from); + if (count <= 0) { + ret = count; goto inode_unlock; - - iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos); - count = iov_iter_count(from); + } if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) { ret = -EINVAL; @@ -828,12 +904,10 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb, inode_lock(inode); } - ret = generic_write_checks(iocb, from); + ret = zonefs_write_checks(iocb, from); if (ret <= 0) goto inode_unlock; - iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos); - ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops); if (ret > 0) iocb->ki_pos += ret; @@ -966,9 +1040,7 @@ static int zonefs_open_zone(struct inode *inode) mutex_lock(&zi->i_truncate_mutex); - zi->i_wr_refcnt++; - if (zi->i_wr_refcnt == 1) { - + if (!zi->i_wr_refcnt) { if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) { atomic_dec(&sbi->s_open_zones); ret = -EBUSY; @@ -978,7 +1050,6 @@ static int zonefs_open_zone(struct inode *inode) if (i_size_read(inode) < zi->i_max_size) { ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN); if (ret) { - zi->i_wr_refcnt--; atomic_dec(&sbi->s_open_zones); goto unlock; } @@ -986,6 +1057,8 @@ static int zonefs_open_zone(struct inode *inode) } } + zi->i_wr_refcnt++; + unlock: mutex_unlock(&zi->i_truncate_mutex); |