diff options
Diffstat (limited to 'fs')
156 files changed, 2269 insertions, 979 deletions
@@ -1085,7 +1085,8 @@ static void aio_complete(struct kiocb *kiocb, long res, long res2) * Tell lockdep we inherited freeze protection from submission * thread. */ - __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); + if (S_ISREG(file_inode(file)->i_mode)) + __sb_writers_acquired(file_inode(file)->i_sb, SB_FREEZE_WRITE); file_end_write(file); } @@ -1492,7 +1493,8 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored, * by telling it the lock got released so that it doesn't * complain about held lock when we return to userspace. */ - __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); + if (S_ISREG(file_inode(file)->i_mode)) + __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } kfree(iovec); return ret; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 2472af2..1fdf4e5 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -911,17 +911,60 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE; vaddr = elf_ppnt->p_vaddr; + /* + * If we are loading ET_EXEC or we have already performed + * the ET_DYN load_addr calculations, proceed normally. + */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { elf_flags |= MAP_FIXED; } else if (loc->elf_ex.e_type == ET_DYN) { - /* Try and get dynamic programs out of the way of the - * default mmap base, as well as whatever program they - * might try to exec. This is because the brk will - * follow the loader, and is not movable. */ - load_bias = ELF_ET_DYN_BASE - vaddr; - if (current->flags & PF_RANDOMIZE) - load_bias += arch_mmap_rnd(); - load_bias = ELF_PAGESTART(load_bias); + /* + * This logic is run once for the first LOAD Program + * Header for ET_DYN binaries to calculate the + * randomization (load_bias) for all the LOAD + * Program Headers, and to calculate the entire + * size of the ELF mapping (total_size). (Note that + * load_addr_set is set to true later once the + * initial mapping is performed.) + * + * There are effectively two types of ET_DYN + * binaries: programs (i.e. PIE: ET_DYN with INTERP) + * and loaders (ET_DYN without INTERP, since they + * _are_ the ELF interpreter). The loaders must + * be loaded away from programs since the program + * may otherwise collide with the loader (especially + * for ET_EXEC which does not have a randomized + * position). For example to handle invocations of + * "./ld.so someprog" to test out a new version of + * the loader, the subsequent program that the + * loader loads must avoid the loader itself, so + * they cannot share the same load range. Sufficient + * room for the brk must be allocated with the + * loader as well, since brk must be available with + * the loader. + * + * Therefore, programs are loaded offset from + * ELF_ET_DYN_BASE and loaders are loaded into the + * independently randomized mmap region (0 load_bias + * without MAP_FIXED). + */ + if (elf_interpreter) { + load_bias = ELF_ET_DYN_BASE; + if (current->flags & PF_RANDOMIZE) + load_bias += arch_mmap_rnd(); + elf_flags |= MAP_FIXED; + } else + load_bias = 0; + + /* + * Since load_bias is used for all subsequent loading + * calculations, we must lower it by the first vaddr + * so that the remaining calculations based on the + * ELF vaddrs will be correctly offset. The result + * is then page aligned. + */ + load_bias = ELF_PAGESTART(load_bias - vaddr); + total_size = total_mapping_size(elf_phdata, loc->elf_ex.e_phnum); if (!total_size) { @@ -2296,6 +2339,7 @@ static int elf_core_dump(struct coredump_params *cprm) goto end_coredump; } } + dump_truncate(cprm); if (!elf_core_write_extra_data(cprm)) goto end_coredump; diff --git a/fs/block_dev.c b/fs/block_dev.c index 07e46b7..cb936c9 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -450,10 +450,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index 247b8df..8d8370d 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -78,12 +78,6 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (ret) - return ret; - } - ret = 0; break; case ACL_TYPE_DEFAULT: if (!S_ISDIR(inode->i_mode)) @@ -119,6 +113,13 @@ out: int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + int ret; + + if (type == ACL_TYPE_ACCESS && acl) { + ret = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (ret) + return ret; + } return __btrfs_set_acl(NULL, inode, acl, type); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e46e7fb..705bb5f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4759,10 +4759,6 @@ skip_async: else flush = BTRFS_RESERVE_NO_FLUSH; spin_lock(&space_info->lock); - if (can_overcommit(root, space_info, orig, flush)) { - spin_unlock(&space_info->lock); - break; - } if (list_empty(&space_info->tickets) && list_empty(&space_info->priority_tickets)) { spin_unlock(&space_info->lock); @@ -7401,7 +7397,8 @@ btrfs_lock_cluster(struct btrfs_block_group_cache *block_group, spin_unlock(&cluster->refill_lock); - down_read(&used_bg->data_rwsem); + /* We should only have one-level nested. */ + down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING); spin_lock(&cluster->refill_lock); if (used_bg == cluster->block_group) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index bddbae7..f089d7d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4480,8 +4480,19 @@ search_again: if (found_type > min_type) { del_item = 1; } else { - if (item_end < new_size) + if (item_end < new_size) { + /* + * With NO_HOLES mode, for the following mapping + * + * [0-4k][hole][8k-12k] + * + * if truncating isize down to 6k, it ends up + * isize being 8k. + */ + if (btrfs_fs_incompat(root->fs_info, NO_HOLES)) + last_size = new_size; break; + } if (found_key.offset >= new_size) del_item = 1; else @@ -7235,7 +7246,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, struct extent_map *em = NULL; int ret; - down_read(&BTRFS_I(inode)->dio_sem); if (type != BTRFS_ORDERED_NOCOW) { em = create_pinned_em(inode, start, len, orig_start, block_start, block_len, orig_block_len, @@ -7254,7 +7264,6 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode, em = ERR_PTR(ret); } out: - up_read(&BTRFS_I(inode)->dio_sem); return em; } @@ -7639,11 +7648,18 @@ static void adjust_dio_outstanding_extents(struct inode *inode, * within our reservation, otherwise we need to adjust our inode * counter appropriately. */ - if (dio_data->outstanding_extents) { + if (dio_data->outstanding_extents >= num_extents) { dio_data->outstanding_extents -= num_extents; } else { + /* + * If dio write length has been split due to no large enough + * contiguous space, we need to compensate our inode counter + * appropriately. + */ + u64 num_needed = num_extents - dio_data->outstanding_extents; + spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents += num_extents; + BTRFS_I(inode)->outstanding_extents += num_needed; spin_unlock(&BTRFS_I(inode)->lock); } } @@ -8034,8 +8050,10 @@ next_block_or_try_again: start += sectorsize; - if (nr_sectors--) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block_or_try_again; } } @@ -8141,8 +8159,10 @@ next: ASSERT(nr_sectors); - if (--nr_sectors) { + nr_sectors--; + if (nr_sectors) { pgoff += sectorsize; + ASSERT(pgoff < PAGE_SIZE); goto next_block; } } @@ -8707,6 +8727,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) dio_data.unsubmitted_oe_range_start = (u64)offset; dio_data.unsubmitted_oe_range_end = (u64)offset; current->journal_info = &dio_data; + down_read(&BTRFS_I(inode)->dio_sem); } else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags)) { inode_dio_end(inode); @@ -8719,6 +8740,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) iter, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, flags); if (iov_iter_rw(iter) == WRITE) { + up_read(&BTRFS_I(inode)->dio_sem); current->journal_info = NULL; if (ret < 0 && ret != -EIOCBQUEUED) { if (dio_data.reserve) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1782804..0fe346c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3052,7 +3052,7 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff, out: if (ret) btrfs_cmp_data_free(cmp); - return 0; + return ret; } static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, @@ -4082,6 +4082,10 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) ret = PTR_ERR(new_root); goto out; } + if (!is_fstree(new_root->objectid)) { + ret = -ENOENT; + goto out; + } path = btrfs_alloc_path(); if (!path) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 2cf5e14..04c61bc 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2367,11 +2367,11 @@ void free_reloc_roots(struct list_head *list) while (!list_empty(list)) { reloc_root = list_entry(list->next, struct btrfs_root, root_list); + __del_reloc_root(reloc_root); free_extent_buffer(reloc_root->node); free_extent_buffer(reloc_root->commit_root); reloc_root->node = NULL; reloc_root->commit_root = NULL; - __del_reloc_root(reloc_root); } } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 71261b4..77f9efc 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1680,6 +1680,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen) { int ret; + if (ino == BTRFS_FIRST_FREE_OBJECTID) + return 1; + ret = get_cur_inode_state(sctx, ino, gen); if (ret < 0) goto out; @@ -1865,7 +1868,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, * not deleted and then re-created, if it was then we have no overwrite * and we can just unlink this entry. */ - if (sctx->parent_root) { + if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) { ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL, NULL, NULL, NULL); if (ret < 0 && ret != -ENOENT) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 74ed5aa..f6e1119 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1834,6 +1834,8 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) goto restore; } + btrfs_qgroup_rescan_resume(fs_info); + if (!fs_info->uuid_root) { btrfs_info(fs_info, "creating UUID tree"); ret = btrfs_create_uuid_tree(fs_info); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index b890045..309313b 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -37,6 +37,7 @@ */ #define LOG_INODE_ALL 0 #define LOG_INODE_EXISTS 1 +#define LOG_OTHER_INODE 2 /* * directory trouble cases @@ -4623,7 +4624,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, if (S_ISDIR(inode->i_mode) || (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags) && - inode_only == LOG_INODE_EXISTS)) + inode_only >= LOG_INODE_EXISTS)) max_key.type = BTRFS_XATTR_ITEM_KEY; else max_key.type = (u8)-1; @@ -4647,7 +4648,13 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, return ret; } - mutex_lock(&BTRFS_I(inode)->log_mutex); + if (inode_only == LOG_OTHER_INODE) { + inode_only = LOG_INODE_EXISTS; + mutex_lock_nested(&BTRFS_I(inode)->log_mutex, + SINGLE_DEPTH_NESTING); + } else { + mutex_lock(&BTRFS_I(inode)->log_mutex); + } /* * a brute force approach to making sure we get the most uptodate @@ -4799,7 +4806,7 @@ again: * unpin it. */ err = btrfs_log_inode(trans, root, other_inode, - LOG_INODE_EXISTS, + LOG_OTHER_INODE, 0, LLONG_MAX, ctx); iput(other_inode); if (err) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 71a60cc..06a77e4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6226,7 +6226,7 @@ int btrfs_map_bio(struct btrfs_root *root, struct bio *bio, for (dev_nr = 0; dev_nr < total_devs; dev_nr++) { dev = bbio->stripes[dev_nr].dev; if (!dev || !dev->bdev || - (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) { + (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) { bbio_error(bbio, first_bio, logical); continue; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 900ffaf..7b79a54 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -188,7 +188,7 @@ static int ceph_releasepage(struct page *page, gfp_t g) /* * read a single page, without unlocking it. */ -static int readpage_nounlock(struct file *filp, struct page *page) +static int ceph_do_readpage(struct file *filp, struct page *page) { struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); @@ -218,7 +218,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) err = ceph_readpage_from_fscache(inode, page); if (err == 0) - goto out; + return -EINPROGRESS; dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); @@ -248,8 +248,11 @@ out: static int ceph_readpage(struct file *filp, struct page *page) { - int r = readpage_nounlock(filp, page); - unlock_page(page); + int r = ceph_do_readpage(filp, page); + if (r != -EINPROGRESS) + unlock_page(page); + else + r = 0; return r; } @@ -1235,7 +1238,7 @@ retry_locked: goto retry_locked; r = writepage_nounlock(page, NULL); if (r < 0) - goto fail_nosnap; + goto fail_unlock; goto retry_locked; } @@ -1263,11 +1266,14 @@ retry_locked: } /* we need to read it. */ - r = readpage_nounlock(file, page); - if (r < 0) - goto fail_nosnap; + r = ceph_do_readpage(file, page); + if (r < 0) { + if (r == -EINPROGRESS) + return -EAGAIN; + goto fail_unlock; + } goto retry_locked; -fail_nosnap: +fail_unlock: unlock_page(page); return r; } diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index 5bc5d37..a2d7997 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -240,13 +240,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp) } } -static void ceph_vfs_readpage_complete(struct page *page, void *data, int error) -{ - if (!error) - SetPageUptodate(page); -} - -static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error) +static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error) { if (!error) SetPageUptodate(page); @@ -274,7 +268,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page) return -ENOBUFS; ret = fscache_read_or_alloc_page(ci->fscache, page, - ceph_vfs_readpage_complete, NULL, + ceph_readpage_from_fscache_complete, NULL, GFP_KERNEL); switch (ret) { @@ -303,7 +297,7 @@ int ceph_readpages_from_fscache(struct inode *inode, return -ENOBUFS; ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages, - ceph_vfs_readpage_complete_unlock, + ceph_readpage_from_fscache_complete, NULL, mapping_gfp_mask(mapping)); switch (ret) { diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 03951f9..3e1c136 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1900,6 +1900,7 @@ static int try_flush_caps(struct inode *inode, u64 *ptid) retry: spin_lock(&ci->i_ceph_lock); if (ci->i_ceph_flags & CEPH_I_NOFLUSH) { + spin_unlock(&ci->i_ceph_lock); dout("try_flush_caps skipping %p I_NOFLUSH set\n", inode); goto out; } @@ -1917,8 +1918,10 @@ retry: mutex_lock(&session->s_mutex); goto retry; } - if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) + if (cap->session->s_state < CEPH_MDS_SESSION_OPEN) { + spin_unlock(&ci->i_ceph_lock); goto out; + } flushing = __mark_caps_flushing(inode, session, true, &flush_tid, &oldest_flush_tid); diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 1afa111..cec2569 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -292,6 +292,11 @@ out: if (ret < 0) err = ret; dput(last); + /* last_name no longer match cache index */ + if (fi->readdir_cache_idx >= 0) { + fi->readdir_cache_idx = -1; + fi->dir_release_count = 0; + } } return err; } @@ -315,7 +320,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx) struct ceph_mds_client *mdsc = fsc->mdsc; int i; int err; - u32 ftype; + unsigned frag = -1; struct ceph_mds_reply_info_parsed *rinfo; dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos); @@ -362,7 +367,6 @@ more: /* do we have the correct frag content buffered? */ if (need_send_readdir(fi, ctx->pos)) { struct ceph_mds_request *req; - unsigned frag; int op = ceph_snap(inode) == CEPH_SNAPDIR ? CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR; @@ -373,8 +377,11 @@ more: } if (is_hash_order(ctx->pos)) { - frag = ceph_choose_frag(ci, fpos_hash(ctx->pos), - NULL, NULL); + /* fragtree isn't always accurate. choose frag + * based on previous reply when possible. */ + if (frag == (unsigned)-1) + frag = ceph_choose_frag(ci, fpos_hash(ctx->pos), + NULL, NULL); } else { frag = fpos_frag(ctx->pos); } @@ -497,6 +504,7 @@ more: struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i; struct ceph_vino vino; ino_t ino; + u32 ftype; BUG_ON(rde->offset < ctx->pos); @@ -519,15 +527,17 @@ more: ctx->pos++; } + ceph_mdsc_put_request(fi->last_readdir); + fi->last_readdir = NULL; + if (fi->next_offset > 2) { - ceph_mdsc_put_request(fi->last_readdir); - fi->last_readdir = NULL; + frag = fi->frag; goto more; } /* more frags? */ if (!ceph_frag_is_rightmost(fi->frag)) { - unsigned frag = ceph_frag_next(fi->frag); + frag = ceph_frag_next(fi->frag); if (is_hash_order(ctx->pos)) { loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag), fi->next_offset, true); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 953275b..4a6df2c 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -1323,8 +1323,8 @@ retry_lookup: ceph_dir_clear_ordered(dir); dout("d_delete %p\n", dn); d_delete(dn); - } else { - if (have_lease && d_unhashed(dn)) + } else if (have_lease) { + if (d_unhashed(dn)) d_add(dn, NULL); update_dentry_lease(dn, rinfo->dlease, session, diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 7d752d5..4c9c72f 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -25,7 +25,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg) l.stripe_count = ci->i_layout.stripe_count; l.object_size = ci->i_layout.object_size; l.data_pool = ci->i_layout.pool_id; - l.preferred_osd = (s32)-1; + l.preferred_osd = -1; if (copy_to_user(arg, &l, sizeof(l))) return -EFAULT; } @@ -97,7 +97,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg) nl.data_pool = ci->i_layout.pool_id; /* this is obsolete, and always -1 */ - nl.preferred_osd = le64_to_cpu(-1); + nl.preferred_osd = -1; err = __validate_layout(mdsc, &nl); if (err) diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index e3e1a80..c0f52c4 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -1782,13 +1782,18 @@ static int build_dentry_path(struct dentry *dentry, int *pfreepath) { char *path; + struct inode *dir; - if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) { - *pino = ceph_ino(d_inode(dentry->d_parent)); + rcu_read_lock(); + dir = d_inode_rcu(dentry->d_parent); + if (dir && ceph_snap(dir) == CEPH_NOSNAP) { + *pino = ceph_ino(dir); + rcu_read_unlock(); *ppath = dentry->d_name.name; *ppathlen = dentry->d_name.len; return 0; } + rcu_read_unlock(); path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1); if (IS_ERR(path)) return PTR_ERR(path); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c0c2530..87658f6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1360,7 +1360,7 @@ exit_cifs(void) exit_cifs_idmap(); #endif #ifdef CONFIG_CIFS_UPCALL - unregister_key_type(&cifs_spnego_key_type); + exit_cifs_spnego(); #endif cifs_destroy_request_bufs(); cifs_destroy_mids(); diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 48ef401..7b496a4 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -365,6 +365,8 @@ struct smb_version_operations { unsigned int (*calc_smb_size)(void *); /* check for STATUS_PENDING and process it in a positive case */ bool (*is_status_pending)(char *, struct TCP_Server_Info *, int); + /* check for STATUS_NETWORK_SESSION_EXPIRED */ + bool (*is_session_expired)(char *); /* send oplock break response */ int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *, struct cifsInodeInfo *); diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 1f91c9d..cc420d6 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1457,6 +1457,13 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid) return length; server->total_read += length; + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server); + wake_up(&server->response_q); + return -1; + } + if (server->ops->is_status_pending && server->ops->is_status_pending(buf, server, 0)) { discard_remaining_data(server); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 1a54569..580b3a4 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -796,6 +796,13 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid) cifs_dump_mem("Bad SMB: ", buf, min_t(unsigned int, server->total_read, 48)); + if (server->ops->is_session_expired && + server->ops->is_session_expired(buf)) { + cifs_reconnect(server); + wake_up(&server->response_q); + return -1; + } + if (server->ops->is_status_pending && server->ops->is_status_pending(buf, server, length)) return -1; @@ -4071,6 +4078,14 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, cifs_dbg(FYI, "Security Mode: 0x%x Capabilities: 0x%x TimeAdjust: %d\n", server->sec_mode, server->capabilities, server->timeAdj); + if (ses->auth_key.response) { + cifs_dbg(VFS, "Free previous auth_key.response = %p\n", + ses->auth_key.response); + kfree(ses->auth_key.response); + ses->auth_key.response = NULL; + ses->auth_key.len = 0; + } + if (server->ops->sess_setup) rc = server->ops->sess_setup(xid, ses, nls_info); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 789ff1d..d9cbda2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -183,15 +183,21 @@ cifs_bp_rename_retry: } /* + * Don't allow path components longer than the server max. * Don't allow the separator character in a path component. * The VFS will not allow "/", but "\" is allowed by posix. */ static int -check_name(struct dentry *direntry) +check_name(struct dentry *direntry, struct cifs_tcon *tcon) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); int i; + if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength && + direntry->d_name.len > + le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength))) + return -ENAMETOOLONG; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { for (i = 0; i < direntry->d_name.len; i++) { if (direntry->d_name.name[i] == '\\') { @@ -489,10 +495,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, return finish_no_open(file, res); } - rc = check_name(direntry); - if (rc) - return rc; - xid = get_xid(); cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n", @@ -505,6 +507,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, } tcon = tlink_tcon(tlink); + + rc = check_name(direntry, tcon); + if (rc) + goto out; + server = tcon->ses->server; if (server->ops->new_lease_key) @@ -765,7 +772,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } pTcon = tlink_tcon(tlink); - rc = check_name(direntry); + rc = check_name(direntry, pTcon); if (rc) goto lookup_out; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 3925758..cf192f9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -224,6 +224,13 @@ cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, if (backup_cred(cifs_sb)) create_options |= CREATE_OPEN_BACKUP_INTENT; + /* O_SYNC also has bit for O_DSYNC so following check picks up either */ + if (f_flags & O_SYNC) + create_options |= CREATE_WRITE_THROUGH; + + if (f_flags & O_DIRECT) + create_options |= CREATE_NO_BUFFER; + oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = desired_access; diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b696824..812e488 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1018,6 +1018,18 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length) return true; } +static bool +smb2_is_session_expired(char *buf) +{ + struct smb2_hdr *hdr = (struct smb2_hdr *)buf; + + if (hdr->Status != STATUS_NETWORK_SESSION_EXPIRED) + return false; + + cifs_dbg(FYI, "Session expired\n"); + return true; +} + static int smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid, struct cifsInodeInfo *cinode) @@ -1609,6 +1621,7 @@ struct smb_version_operations smb20_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -1690,6 +1703,7 @@ struct smb_version_operations smb21_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -1773,6 +1787,7 @@ struct smb_version_operations smb30_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, @@ -1862,6 +1877,7 @@ struct smb_version_operations smb311_operations = { .close_dir = smb2_close_dir, .calc_smb_size = smb2_calc_size, .is_status_pending = smb2_is_status_pending, + .is_session_expired = smb2_is_session_expired, .oplock_response = smb2_oplock_response, .queryfs = smb2_queryfs, .mand_lock = smb2_mand_lock, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 7c1c6c3..69b610ad 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -366,7 +366,7 @@ assemble_neg_contexts(struct smb2_negotiate_req *req) build_encrypt_ctxt((struct smb2_encryption_neg_context *)pneg_ctxt); req->NegotiateContextOffset = cpu_to_le32(OFFSET_OF_NEG_CONTEXT); req->NegotiateContextCount = cpu_to_le16(2); - inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + 2 + inc_rfc1001_len(req, 4 + sizeof(struct smb2_preauth_neg_context) + sizeof(struct smb2_encryption_neg_context)); /* calculate hash */ } #else @@ -531,15 +531,22 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) /* * validation ioctl must be signed, so no point sending this if we - * can not sign it. We could eventually change this to selectively + * can not sign it (ie are not known user). Even if signing is not + * required (enabled but not negotiated), in those cases we selectively * sign just this, the first and only signed request on a connection. - * This is good enough for now since a user who wants better security - * would also enable signing on the mount. Having validation of - * negotiate info for signed connections helps reduce attack vectors + * Having validation of negotiate info helps reduce attack vectors. */ - if (tcon->ses->server->sign == false) + if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) return 0; /* validation requires signing */ + if (tcon->ses->user_name == NULL) { + cifs_dbg(FYI, "Can't validate negotiate: null user mount\n"); + return 0; /* validation requires signing */ + } + + if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL) + cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n"); + vneg_inbuf.Capabilities = cpu_to_le32(tcon->ses->server->vals->req_capabilities); memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid, @@ -1010,6 +1017,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses, while (sess_data->func) sess_data->func(sess_data); + if ((ses->session_flags & SMB2_SESSION_FLAG_IS_GUEST) && (ses->sign)) + cifs_dbg(VFS, "signing requested but authenticated as guest\n"); rc = sess_data->result; out: kfree(sess_data); @@ -2930,8 +2939,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf, kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) * le32_to_cpu(pfs_inf->SectorsPerAllocationUnit); kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits); - kst->f_bfree = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits); - kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); + kst->f_bfree = kst->f_bavail = + le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); return; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index dc0d141..1e1449a 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* BB FIXME - analyze following length BB */ -#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ +/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ +#define MAX_SMB2_HDR_SIZE 0x00b0 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) diff --git a/fs/coredump.c b/fs/coredump.c index eb9c92c..4407e27 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -833,3 +833,21 @@ int dump_align(struct coredump_params *cprm, int align) return mod ? dump_skip(cprm, align - mod) : 1; } EXPORT_SYMBOL(dump_align); + +/* + * Ensures that file size is big enough to contain the current file + * postion. This prevents gdb from complaining about a truncated file + * if the last "write" to the file was dump_skip. + */ +void dump_truncate(struct coredump_params *cprm) +{ + struct file *file = cprm->file; + loff_t offset; + + if (file->f_op->llseek && file->f_op->llseek != no_llseek) { + offset = file->f_op->llseek(file, 0, SEEK_CUR); + if (i_size_read(file->f_mapping->host) < offset) + do_truncate(file->f_path.dentry, offset, 0, file); + } +} +EXPORT_SYMBOL(dump_truncate); diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index bb46063..a755fa1 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -108,6 +108,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info, goto out; } ukp = user_key_payload(keyring_key); + if (!ukp) { + /* key was revoked before we acquired its semaphore */ + res = -EKEYREVOKED; + goto out; + } if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; goto out; diff --git a/fs/dcache.c b/fs/dcache.c index 4485a48..67957f5 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -277,6 +277,33 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } +void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (unlikely(dname_external(dentry))) { + struct external_name *p = external_name(dentry); + atomic_inc(&p->u.count); + spin_unlock(&dentry->d_lock); + name->name = p->name; + } else { + memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN); + spin_unlock(&dentry->d_lock); + name->name = name->inline_name; + } +} +EXPORT_SYMBOL(take_dentry_name_snapshot); + +void release_dentry_name_snapshot(struct name_snapshot *name) +{ + if (unlikely(name->name != name->inline_name)) { + struct external_name *p; + p = container_of(name->name, struct external_name, name[0]); + if (unlikely(atomic_dec_and_test(&p->u.count))) + kfree_rcu(p, u.head); + } +} +EXPORT_SYMBOL(release_dentry_name_snapshot); + static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -1133,11 +1160,12 @@ void shrink_dcache_sb(struct super_block *sb) LIST_HEAD(dispose); freed = list_lru_walk(&sb->s_dentry_lru, - dentry_lru_isolate_shrink, &dispose, UINT_MAX); + dentry_lru_isolate_shrink, &dispose, 1024); this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); - } while (freed > 0); + cond_resched(); + } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 1e30f74..3d7de9f 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -730,7 +730,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, { int error; struct dentry *dentry = NULL, *trap; - const char *old_name; + struct name_snapshot old_name; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ @@ -745,19 +745,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); - fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name, + fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name, d_is_dir(old_dentry), NULL, old_dentry); - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; diff --git a/fs/direct-io.c b/fs/direct-io.c index c60756e..c6220a2 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -835,7 +835,8 @@ out: */ if (sdio->boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); - dio_bio_submit(dio, sdio); + if (sdio->bio) + dio_bio_submit(dio, sdio); put_page(sdio->cur_page); sdio->cur_page = NULL; } diff --git a/fs/dlm/user.c b/fs/dlm/user.c index 58c2f4a..9ac6591 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -355,6 +355,10 @@ static int dlm_device_register(struct dlm_ls *ls, char *name) error = misc_register(&ls->ls_device); if (error) { kfree(ls->ls_device.name); + /* this has to be set to NULL + * to avoid a double-free in dlm_device_deregister + */ + ls->ls_device.name = NULL; } fail: return error; diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 599a292..a896e46 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -84,11 +84,16 @@ struct ecryptfs_page_crypt_context { static inline struct ecryptfs_auth_tok * ecryptfs_get_encrypted_key_payload_data(struct key *key) { - if (key->type == &key_type_encrypted) - return (struct ecryptfs_auth_tok *) - (&((struct encrypted_key_payload *)key->payload.data[0])->payload_data); - else + struct encrypted_key_payload *payload; + + if (key->type != &key_type_encrypted) return NULL; + + payload = key->payload.data[0]; + if (!payload) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)payload->payload_data; } static inline struct key *ecryptfs_get_encrypted_key(char *sig) @@ -114,12 +119,17 @@ static inline struct ecryptfs_auth_tok * ecryptfs_get_key_payload_data(struct key *key) { struct ecryptfs_auth_tok *auth_tok; + const struct user_key_payload *ukp; auth_tok = ecryptfs_get_encrypted_key_payload_data(key); - if (!auth_tok) - return (struct ecryptfs_auth_tok *)user_key_payload(key)->data; - else + if (auth_tok) return auth_tok; + + ukp = user_key_payload(key); + if (!ukp) + return ERR_PTR(-EKEYREVOKED); + + return (struct ecryptfs_auth_tok *)ukp->data; } #define ECRYPTFS_MAX_KEYSET_SIZE 1024 diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c index 3cf1546..fa218cd 100644 --- a/fs/ecryptfs/keystore.c +++ b/fs/ecryptfs/keystore.c @@ -459,7 +459,8 @@ out: * @auth_tok_key: key containing the authentication token * @auth_tok: authentication token * - * Returns zero on valid auth tok; -EINVAL otherwise + * Returns zero on valid auth tok; -EINVAL if the payload is invalid; or + * -EKEYREVOKED if the key was revoked before we acquired its semaphore. */ static int ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, @@ -468,6 +469,12 @@ ecryptfs_verify_auth_tok_from_key(struct key *auth_tok_key, int rc = 0; (*auth_tok) = ecryptfs_get_key_payload_data(auth_tok_key); + if (IS_ERR(*auth_tok)) { + rc = PTR_ERR(*auth_tok); + *auth_tok = NULL; + goto out; + } + if (ecryptfs_verify_version((*auth_tok)->version)) { printk(KERN_ERR "Data structure version mismatch. Userspace " "tools must match eCryptfs kernel module with major " diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 10db912..3cbc304 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -523,8 +523,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq) wait_queue_head_t *whead; rcu_read_lock(); - /* If it is cleared by POLLFREE, it should be rcu-safe */ - whead = rcu_dereference(pwq->whead); + /* + * If it is cleared by POLLFREE, it should be rcu-safe. + * If we read NULL we need a barrier paired with + * smp_store_release() in ep_poll_callback(), otherwise + * we rely on whead->lock. + */ + whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); @@ -1009,17 +1014,6 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k struct eventpoll *ep = epi->ep; int ewake = 0; - if ((unsigned long)key & POLLFREE) { - ep_pwq_from_wait(wait)->whead = NULL; - /* - * whead = NULL above can race with ep_remove_wait_queue() - * which can do another remove_wait_queue() after us, so we - * can't use __remove_wait_queue(). whead->lock is held by - * the caller. - */ - list_del_init(&wait->task_list); - } - spin_lock_irqsave(&ep->lock, flags); /* @@ -1101,10 +1095,26 @@ out_unlock: if (pwake) ep_poll_safewake(&ep->poll_wait); - if (epi->event.events & EPOLLEXCLUSIVE) - return ewake; + if (!(epi->event.events & EPOLLEXCLUSIVE)) + ewake = 1; + + if ((unsigned long)key & POLLFREE) { + /* + * If we race with ep_remove_wait_queue() it can miss + * ->whead = NULL and do another remove_wait_queue() after + * us, so we can't use __remove_wait_queue(). + */ + list_del_init(&wait->task_list); + /* + * ->whead != NULL protects us from the race with ep_free() + * or ep_remove(), ep_remove_wait_queue() takes whead->lock + * held by the caller. Once we nullify it, nothing protects + * ep/epi or even wait. + */ + smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); + } - return 1; + return ewake; } /* @@ -215,8 +215,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, if (write) { unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start; - unsigned long ptr_size; - struct rlimit *rlim; + unsigned long ptr_size, limit; /* * Since the stack will hold pointers to the strings, we @@ -245,14 +244,16 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, return page; /* - * Limit to 1/4-th the stack size for the argv+env strings. + * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM + * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ - rlim = current->signal->rlim; - if (size > READ_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) + limit = _STK_LIM / 4 * 3; + limit = min(limit, rlimit(RLIMIT_STACK) / 4); + if (size > limit) goto fail; } diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c index 79dafa7..069c0dc 100644 --- a/fs/ext2/acl.c +++ b/fs/ext2/acl.c @@ -175,11 +175,8 @@ ext2_get_acl(struct inode *inode, int type) return acl; } -/* - * inode->i_mutex: down - */ -int -ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +static int +__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) { int name_index; void *value = NULL; @@ -189,13 +186,6 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch(type) { case ACL_TYPE_ACCESS: name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - inode->i_ctime = current_time(inode); - mark_inode_dirty(inode); - } break; case ACL_TYPE_DEFAULT: @@ -222,6 +212,24 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) } /* + * inode->i_mutex: down + */ +int +ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int error; + + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (error) + return error; + inode->i_ctime = current_time(inode); + mark_inode_dirty(inode); + } + return __ext2_set_acl(inode, acl, type); +} + +/* * Initialize the ACLs of a new inode. Called from ext2_new_inode. * * dir->i_mutex: down @@ -238,12 +246,12 @@ ext2_init_acl(struct inode *inode, struct inode *dir) return error; if (default_acl) { - error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } return error; diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index dfa5199..dfd01ca 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -192,13 +192,6 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - inode->i_ctime = ext4_current_time(inode); - ext4_mark_inode_dirty(handle, inode); - } break; case ACL_TYPE_DEFAULT: @@ -231,6 +224,8 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) { handle_t *handle; int error, retries = 0; + umode_t mode = inode->i_mode; + int update_mode = 0; retry: handle = ext4_journal_start(inode, EXT4_HT_XATTR, @@ -238,7 +233,20 @@ retry: if (IS_ERR(handle)) return PTR_ERR(handle); + if ((type == ACL_TYPE_ACCESS) && acl) { + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) + goto out_stop; + update_mode = 1; + } + error = __ext4_set_acl(handle, inode, type, acl); + if (!error && update_mode) { + inode->i_mode = mode; + inode->i_ctime = ext4_current_time(inode); + ext4_mark_inode_dirty(handle, inode); + } +out_stop: ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 9e77c08..510e664 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -469,6 +469,8 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, lastoff = page_offset(page); bh = head = page_buffers(page); do { + if (lastoff + bh->b_size <= startoff) + goto next; if (buffer_uptodate(bh) || buffer_unwritten(bh)) { if (whence == SEEK_DATA) @@ -483,6 +485,7 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); goto out; } +next: lastoff += bh->b_size; bh = bh->b_this_page; } while (bh != head); @@ -524,7 +527,7 @@ static loff_t ext4_seek_data(struct file *file, loff_t offset, loff_t maxsize) inode_lock(inode); isize = i_size_read(inode); - if (offset >= isize) { + if (offset < 0 || offset >= isize) { inode_unlock(inode); return -ENXIO; } @@ -587,7 +590,7 @@ static loff_t ext4_seek_hole(struct file *file, loff_t offset, loff_t maxsize) inode_lock(inode); isize = i_size_read(inode); - if (offset >= isize) { + if (offset < 0 || offset >= isize) { inode_unlock(inode); return -ENXIO; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 1b29efc..ec28e8e 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2107,15 +2107,29 @@ static int ext4_writepage(struct page *page, static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page) { int len; - loff_t size = i_size_read(mpd->inode); + loff_t size; int err; BUG_ON(page->index != mpd->first_page); + clear_page_dirty_for_io(page); + /* + * We have to be very careful here! Nothing protects writeback path + * against i_size changes and the page can be writeably mapped into + * page tables. So an application can be growing i_size and writing + * data through mmap while writeback runs. clear_page_dirty_for_io() + * write-protects our page in page tables and the page cannot get + * written to again until we release page lock. So only after + * clear_page_dirty_for_io() we are safe to sample i_size for + * ext4_bio_write_page() to zero-out tail of the written page. We rely + * on the barrier provided by TestClearPageDirty in + * clear_page_dirty_for_io() to make sure i_size is really sampled only + * after page tables are updated. + */ + size = i_size_read(mpd->inode); if (page->index == size >> PAGE_SHIFT) len = size & ~PAGE_MASK; else len = PAGE_SIZE; - clear_page_dirty_for_io(page); err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false); if (!err) mpd->wbc->nr_to_write--; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 846b57f..64056c6 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2136,8 +2136,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) * We search using buddy data only if the order of the request * is greater than equal to the sbi_s_mb_order2_reqs * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req + * We also support searching for power-of-two requests only for + * requests upto maximum buddy size we have constructed. */ - if (i >= sbi->s_mb_order2_reqs) { + if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) { /* * This should tell if fe_len is exactly power of 2 */ @@ -2207,7 +2209,7 @@ repeat: } ac->ac_groups_scanned++; - if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2) + if (cr == 0) ext4_mb_simple_scan_group(ac, &e4b); else if (cr == 1 && sbi->s_stripe && !(ac->ac_g_ex.fe_len % sbi->s_stripe)) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 423a21c..00b8a5a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3527,6 +3527,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, EXT4_I(old_dentry->d_inode)->i_projid))) return -EXDEV; + if ((ext4_encrypted_inode(old_dir) && + !fscrypt_has_encryption_key(old_dir)) || + (ext4_encrypted_inode(new_dir) && + !fscrypt_has_encryption_key(new_dir))) + return -ENOKEY; + retval = dquot_initialize(old.dir); if (retval) return retval; @@ -3726,6 +3732,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, u8 new_file_type; int retval; + if ((ext4_encrypted_inode(old_dir) && + !fscrypt_has_encryption_key(old_dir)) || + (ext4_encrypted_inode(new_dir) && + !fscrypt_has_encryption_key(new_dir))) + return -ENOKEY; + if ((ext4_encrypted_inode(old_dir) || ext4_encrypted_inode(new_dir)) && (old_dir != new_dir) && diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index cf68100..95bf466 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1926,7 +1926,8 @@ retry: n_desc_blocks = o_desc_blocks + le16_to_cpu(es->s_reserved_gdt_blocks); n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb); - n_blocks_count = n_group * EXT4_BLOCKS_PER_GROUP(sb); + n_blocks_count = (ext4_fsblk_t)n_group * + EXT4_BLOCKS_PER_GROUP(sb); n_group--; /* set to last group number */ } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5fa9ba1..1f58179 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2334,6 +2334,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, unsigned int s_flags = sb->s_flags; int nr_orphans = 0, nr_truncates = 0; #ifdef CONFIG_QUOTA + int quota_update = 0; int i; #endif if (!es->s_last_orphan) { @@ -2372,14 +2373,32 @@ static void ext4_orphan_cleanup(struct super_block *sb, #ifdef CONFIG_QUOTA /* Needed for iput() to work correctly and not trash data */ sb->s_flags |= MS_ACTIVE; - /* Turn on quotas so that they are updated correctly */ + + /* + * Turn on quotas which were not enabled for read-only mounts if + * filesystem has quota feature, so that they are updated correctly. + */ + if (ext4_has_feature_quota(sb) && (s_flags & MS_RDONLY)) { + int ret = ext4_enable_quotas(sb); + + if (!ret) + quota_update = 1; + else + ext4_msg(sb, KERN_ERR, + "Cannot turn on quotas: error %d", ret); + } + + /* Turn on journaled quotas used for old sytle */ for (i = 0; i < EXT4_MAXQUOTAS; i++) { if (EXT4_SB(sb)->s_qf_names[i]) { int ret = ext4_quota_on_mount(sb, i); - if (ret < 0) + + if (!ret) + quota_update = 1; + else ext4_msg(sb, KERN_ERR, "Cannot turn on journaled " - "quota: error %d", ret); + "quota: type %d: error %d", i, ret); } } #endif @@ -2438,10 +2457,12 @@ static void ext4_orphan_cleanup(struct super_block *sb, ext4_msg(sb, KERN_INFO, "%d truncate%s cleaned up", PLURAL(nr_truncates)); #ifdef CONFIG_QUOTA - /* Turn quotas off */ - for (i = 0; i < EXT4_MAXQUOTAS; i++) { - if (sb_dqopt(sb)->files[i]) - dquot_quota_off(sb, i); + /* Turn off quotas if they were enabled for orphan cleanup */ + if (quota_update) { + for (i = 0; i < EXT4_MAXQUOTAS; i++) { + if (sb_dqopt(sb)->files[i]) + dquot_quota_off(sb, i); + } } #endif sb->s_flags = s_flags; /* Restore MS_RDONLY status */ @@ -2607,9 +2628,9 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi) if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group) ret = sbi->s_stripe; - else if (stripe_width <= sbi->s_blocks_per_group) + else if (stripe_width && stripe_width <= sbi->s_blocks_per_group) ret = stripe_width; - else if (stride <= sbi->s_blocks_per_group) + else if (stride && stride <= sbi->s_blocks_per_group) ret = stride; else ret = 0; @@ -5365,6 +5386,9 @@ static int ext4_enable_quotas(struct super_block *sb) DQUOT_USAGE_ENABLED | (quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0)); if (err) { + for (type--; type >= 0; type--) + dquot_quota_off(sb, type); + ext4_warning(sb, "Failed to enable quota tracking " "(type=%d, err=%d). Please run " diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 42145be..5dc655e 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a, int ret; ret = kstrtoull(skip_spaces(buf), 0, &val); - if (!ret || val >= clusters) + if (ret || val >= clusters) return -EINVAL; atomic64_set(&sbi->s_resv_clusters, val); diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index 6fe23af..55aa29c 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -211,7 +211,7 @@ static int __f2fs_set_acl(struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; - if (acl) { + if (acl && !ipage) { error = posix_acl_update_mode(inode, &inode->i_mode, &acl); if (error) return error; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 14db4b7..99432b5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1619,7 +1619,12 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping, goto fail; } repeat: - page = grab_cache_page_write_begin(mapping, index, flags); + /* + * Do not use grab_cache_page_write_begin() to avoid deadlock due to + * wait_for_stable_page. Will wait that below with our IO control. + */ + page = pagecache_get_page(mapping, index, + FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS); if (!page) { err = -ENOMEM; goto fail; diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index 489fa0d..08d7dc9 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -663,6 +663,12 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, bool is_old_inline = f2fs_has_inline_dentry(old_dir); int err = -ENOENT; + if ((f2fs_encrypted_inode(old_dir) && + !fscrypt_has_encryption_key(old_dir)) || + (f2fs_encrypted_inode(new_dir) && + !fscrypt_has_encryption_key(new_dir))) + return -ENOKEY; + if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) && !fscrypt_has_permitted_context(new_dir, old_inode)) { err = -EPERM; @@ -843,6 +849,12 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry, int old_nlink = 0, new_nlink = 0; int err = -ENOENT; + if ((f2fs_encrypted_inode(old_dir) && + !fscrypt_has_encryption_key(old_dir)) || + (f2fs_encrypted_inode(new_dir) && + !fscrypt_has_encryption_key(new_dir))) + return -ENOKEY; + if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) && (old_dir != new_dir) && (!fscrypt_has_permitted_context(new_dir, old_inode) || diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 2fc84a9..98c1a63 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -316,7 +316,7 @@ static int check_index_in_prev_nodes(struct f2fs_sb_info *sbi, return 0; /* Get the previous summary */ - for (i = CURSEG_WARM_DATA; i <= CURSEG_COLD_DATA; i++) { + for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) { struct curseg_info *curseg = CURSEG_I(sbi, i); if (curseg->segno == segno) { sum = curseg->sum_blk->entries[blkoff]; @@ -626,8 +626,6 @@ out: } clear_sbi_flag(sbi, SBI_POR_DOING); - if (err) - set_ckpt_flags(sbi, CP_ERROR_FLAG); mutex_unlock(&sbi->cp_mutex); /* let's drop all the directory inodes for clean checkpoint */ diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a7943f8..e10f616 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -1263,7 +1263,7 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type) struct curseg_info *curseg = CURSEG_I(sbi, type); const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops; - if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0, 0)) + if (IS_NODESEG(type)) return v_ops->get_victim(sbi, &(curseg)->next_segno, BG_GC, type, SSR); @@ -1805,6 +1805,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type) static int restore_curseg_summaries(struct f2fs_sb_info *sbi) { + struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal; + struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal; int type = CURSEG_HOT_DATA; int err; @@ -1831,6 +1833,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi) return err; } + /* sanity check for summary blocks */ + if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES || + sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES) + return -EINVAL; + return 0; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 7e0c002..eb20b87 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1424,6 +1424,8 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) unsigned int total, fsmeta; struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi); struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); + unsigned int main_segs, blocks_per_seg; + int i; total = le32_to_cpu(raw_super->segment_count); fsmeta = le32_to_cpu(raw_super->segment_count_ckpt); @@ -1435,6 +1437,20 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi) if (unlikely(fsmeta >= total)) return 1; + main_segs = le32_to_cpu(raw_super->segment_count_main); + blocks_per_seg = sbi->blocks_per_seg; + + for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg) + return 1; + } + for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) { + if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs || + le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg) + return 1; + } + if (unlikely(f2fs_cp_error(sbi))) { f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck"); return 1; @@ -741,16 +741,10 @@ static int __init fcntl_init(void) * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ - BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( - O_RDONLY | O_WRONLY | O_RDWR | - O_CREAT | O_EXCL | O_NOCTTY | - O_TRUNC | O_APPEND | /* O_NONBLOCK | */ - __O_SYNC | O_DSYNC | FASYNC | - O_DIRECT | O_LARGEFILE | O_DIRECTORY | - O_NOFOLLOW | O_NOATIME | O_CLOEXEC | - __FMODE_EXEC | O_PATH | __O_TMPFILE | - __FMODE_NONOTIFY - )); + BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != + HWEIGHT32( + (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | + __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL); diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c index 5d5ddaa..37e0c31d 100644 --- a/fs/fscache/object-list.c +++ b/fs/fscache/object-list.c @@ -330,6 +330,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data) rcu_read_lock(); confkey = user_key_payload(key); + if (!confkey) { + /* key was revoked */ + rcu_read_unlock(); + key_put(key); + goto no_config; + } + buf = confkey->data; for (len = confkey->datalen - 1; len >= 0; len--) { diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 642c57b..4bbad74 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1312,7 +1312,8 @@ static int parse_dirplusfile(char *buf, size_t nbytes, struct file *file, */ over = !dir_emit(ctx, dirent->name, dirent->namelen, dirent->ino, dirent->type); - ctx->pos = dirent->off; + if (!over) + ctx->pos = dirent->off; } buf += reclen; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5ec5870..996aa23 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -46,7 +46,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc) { struct fuse_file *ff; - ff = kmalloc(sizeof(struct fuse_file), GFP_KERNEL); + ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL); if (unlikely(!ff)) return NULL; diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 6528724..7a8b1d7 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -80,9 +80,9 @@ static struct rhashtable_params ht_parms = { static struct rhashtable gl_hash_table; -void gfs2_glock_free(struct gfs2_glock *gl) +static void gfs2_glock_dealloc(struct rcu_head *rcu) { - struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu); if (gl->gl_ops->go_flags & GLOF_ASPACE) { kmem_cache_free(gfs2_glock_aspace_cachep, gl); @@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl) kfree(gl->gl_lksb.sb_lvbptr); kmem_cache_free(gfs2_glock_cachep, gl); } +} + +void gfs2_glock_free(struct gfs2_glock *gl) +{ + struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; + + call_rcu(&gl->gl_rcu, gfs2_glock_dealloc); if (atomic_dec_and_test(&sdp->sd_glock_disposal)) wake_up(&sdp->sd_glock_wait); } @@ -1813,29 +1820,27 @@ void gfs2_glock_exit(void) static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi) { - do { - gi->gl = rhashtable_walk_next(&gi->hti); + while ((gi->gl = rhashtable_walk_next(&gi->hti))) { if (IS_ERR(gi->gl)) { if (PTR_ERR(gi->gl) == -EAGAIN) continue; gi->gl = NULL; + return; } - /* Skip entries for other sb and dead entries */ - } while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) || - __lockref_is_dead(&gi->gl->gl_lockref))); + /* Skip entries for other sb and dead entries */ + if (gi->sdp == gi->gl->gl_name.ln_sbd && + !__lockref_is_dead(&gi->gl->gl_lockref)) + return; + } } static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) { struct gfs2_glock_iter *gi = seq->private; loff_t n = *pos; - int ret; - - if (gi->last_pos <= *pos) - n = (*pos - gi->last_pos); - ret = rhashtable_walk_start(&gi->hti); - if (ret) + rhashtable_walk_enter(&gl_hash_table, &gi->hti); + if (rhashtable_walk_start(&gi->hti) != 0) return NULL; do { @@ -1843,6 +1848,7 @@ static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos) } while (gi->gl && n--); gi->last_pos = *pos; + return gi->gl; } @@ -1854,6 +1860,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr, (*pos)++; gi->last_pos = *pos; gfs2_glock_iter_next(gi); + return gi->gl; } @@ -1863,6 +1870,7 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr) gi->gl = NULL; rhashtable_walk_stop(&gi->hti); + rhashtable_walk_exit(&gi->hti); } static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr) @@ -1925,12 +1933,10 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); } return ret; } @@ -1941,7 +1947,6 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file) struct gfs2_glock_iter *gi = seq->private; gi->gl = NULL; - rhashtable_walk_exit(&gi->hti); return seq_release_private(inode, file); } @@ -1953,12 +1958,10 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file) struct seq_file *seq = file->private_data; struct gfs2_glock_iter *gi = seq->private; gi->sdp = inode->i_private; - gi->last_pos = 0; seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN); if (seq->buf) seq->size = GFS2_SEQ_GOODSIZE; gi->gl = NULL; - ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL); } return ret; } diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h index 51519c2..a04bf95 100644 --- a/fs/gfs2/incore.h +++ b/fs/gfs2/incore.h @@ -370,6 +370,7 @@ struct gfs2_glock { loff_t end; } gl_vm; }; + struct rcu_head gl_rcu; struct rhash_head gl_node; }; diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c index 9b92058..6bb5d7c 100644 --- a/fs/hfsplus/posix_acl.c +++ b/fs/hfsplus/posix_acl.c @@ -51,8 +51,8 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type) return acl; } -int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, - int type) +static int __hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, + int type) { int err; char *xattr_name; @@ -64,12 +64,6 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, switch (type) { case ACL_TYPE_ACCESS: xattr_name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - err = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (err) - return err; - } - err = 0; break; case ACL_TYPE_DEFAULT: @@ -105,6 +99,18 @@ end_set_acl: return err; } +int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int err; + + if (type == ACL_TYPE_ACCESS && acl) { + err = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (err) + return err; + } + return __hfsplus_set_posix_acl(inode, acl, type); +} + int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) { int err = 0; @@ -122,15 +128,15 @@ int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir) return err; if (default_acl) { - err = hfsplus_set_posix_acl(inode, default_acl, - ACL_TYPE_DEFAULT); + err = __hfsplus_set_posix_acl(inode, default_acl, + ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!err) - err = hfsplus_set_posix_acl(inode, acl, - ACL_TYPE_ACCESS); + err = __hfsplus_set_posix_acl(inode, acl, + ACL_TYPE_ACCESS); posix_acl_release(acl); } return err; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 704fa0b..2c2f182 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -695,14 +695,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb, inode = new_inode(sb); if (inode) { - struct hugetlbfs_inode_info *info; inode->i_ino = get_next_ino(); inode->i_mode = S_IFDIR | config->mode; inode->i_uid = config->uid; inode->i_gid = config->gid; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); - info = HUGETLBFS_I(inode); - mpol_shared_policy_init(&info->policy, NULL); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ @@ -733,7 +730,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, inode = new_inode(sb); if (inode) { - struct hugetlbfs_inode_info *info; inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, @@ -741,15 +737,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, inode->i_mapping->a_ops = &hugetlbfs_aops; inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); inode->i_mapping->private_data = resv_map; - info = HUGETLBFS_I(inode); - /* - * The policy is initialized here even if we are creating a - * private inode because initialization simply creates an - * an empty rb tree and calls rwlock_init(), later when we - * call mpol_free_shared_policy() it will just return because - * the rb tree will still be empty. - */ - mpol_shared_policy_init(&info->policy, NULL); switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); @@ -937,6 +924,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) hugetlbfs_inc_free_inodes(sbinfo); return NULL; } + + /* + * Any time after allocation, hugetlbfs_destroy_inode can be called + * for the inode. mpol_free_shared_policy is unconditionally called + * as part of hugetlbfs_destroy_inode. So, initialize policy here + * in case of a quick call to destroy. + * + * Note that the policy is initialized even if we are creating a + * private inode. This simplifies hugetlbfs_destroy_inode. + */ + mpol_shared_policy_init(&p->policy, NULL); + return &p->vfs_inode; } @@ -637,6 +637,7 @@ again: dispose_list(&dispose); } +EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock diff --git a/fs/internal.h b/fs/internal.h index f4da334..8b7143b 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -136,7 +136,6 @@ extern bool atime_needs_update_rcu(const struct path *, struct inode *); extern void inode_io_list_del(struct inode *inode); extern long get_nr_dirty_inodes(void); -extern void evict_inodes(struct super_block *); extern int invalidate_inodes(struct super_block *, bool); /* @@ -281,7 +281,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, unsigned long bytes; /* Bytes to write to page */ offset = (pos & (PAGE_SIZE - 1)); - bytes = min_t(unsigned long, PAGE_SIZE - offset, length); + bytes = min_t(loff_t, PAGE_SIZE - offset, length); rpage = __iomap_read_page(inode, pos); if (IS_ERR(rpage)) @@ -376,7 +376,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, unsigned offset, bytes; offset = pos & (PAGE_SIZE - 1); /* Within page */ - bytes = min_t(unsigned, PAGE_SIZE - offset, count); + bytes = min_t(loff_t, PAGE_SIZE - offset, count); if (IS_DAX(inode)) status = iomap_dax_zero(pos, offset, bytes, iomap); diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c index 7bc186f..1be45c8 100644 --- a/fs/jfs/acl.c +++ b/fs/jfs/acl.c @@ -77,13 +77,6 @@ static int __jfs_set_acl(tid_t tid, struct inode *inode, int type, switch (type) { case ACL_TYPE_ACCESS: ea_name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (rc) - return rc; - inode->i_ctime = current_time(inode); - mark_inode_dirty(inode); - } break; case ACL_TYPE_DEFAULT: ea_name = XATTR_NAME_POSIX_ACL_DEFAULT; @@ -118,9 +111,17 @@ int jfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) tid = txBegin(inode->i_sb, 0); mutex_lock(&JFS_IP(inode)->commit_mutex); + if (type == ACL_TYPE_ACCESS && acl) { + rc = posix_acl_update_mode(inode, &inode->i_mode, &acl); + if (rc) + goto end_tx; + inode->i_ctime = current_time(inode); + mark_inode_dirty(inode); + } rc = __jfs_set_acl(tid, inode, type, acl); if (!rc) rc = txCommit(tid, 1, &inode, 0); +end_tx: txEnd(tid); mutex_unlock(&JFS_IP(inode)->commit_mutex); return rc; @@ -58,6 +58,7 @@ struct mount { struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct hlist_head mnt_fsnotify_marks; __u32 mnt_fsnotify_mask; @@ -466,6 +466,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -604,10 +614,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); @@ -2971,10 +2971,16 @@ static inline int open_to_namei_flags(int flag) static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode) { + struct user_namespace *s_user_ns; int error = security_path_mknod(dir, dentry, mode, 0); if (error) return error; + s_user_ns = dir->dentry->d_sb->s_user_ns; + if (!kuid_has_mapping(s_user_ns, current_fsuid()) || + !kgid_has_mapping(s_user_ns, current_fsgid())) + return -EOVERFLOW; + error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC); if (error) return error; @@ -4336,11 +4342,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, { int error; bool is_dir = d_is_dir(old_dentry); - const unsigned char *old_name; struct inode *source = old_dentry->d_inode; struct inode *target = new_dentry->d_inode; bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; + struct name_snapshot old_name; /* * Check source == target. @@ -4391,7 +4397,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (error) return error; - old_name = fsnotify_oldname_init(old_dentry->d_name.name); + take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); if (!is_dir || (flags & RENAME_EXCHANGE)) lock_two_nondirectories(source, target); @@ -4446,14 +4452,14 @@ out: inode_unlock(target); dput(new_dentry); if (!error) { - fsnotify_move(old_dir, new_dir, old_name, is_dir, + fsnotify_move(old_dir, new_dir, old_name.name, is_dir, !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry); if (flags & RENAME_EXCHANGE) { fsnotify_move(new_dir, old_dir, old_dentry->d_name.name, new_is_dir, NULL, new_dentry); } } - fsnotify_oldname_free(old_name); + release_dentry_name_snapshot(&old_name); return error; } diff --git a/fs/namespace.c b/fs/namespace.c index 5e35057..d7360f9 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -237,6 +237,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_slave_list); INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); + INIT_LIST_HEAD(&mnt->mnt_umounting); #ifdef CONFIG_FSNOTIFY INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks); #endif diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index f31fd0d..b1daeaf 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -121,6 +121,7 @@ config PNFS_FILE_LAYOUT config PNFS_BLOCK tristate depends on NFS_V4_1 && BLK_DEV_DM + depends on 64BIT || LBDAF default NFS_V4 config PNFS_OBJLAYOUT diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 484bebc..af84a92 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -75,7 +75,10 @@ nfs4_callback_svc(void *vrqstp) set_freezable(); - while (!kthread_should_stop()) { + while (!kthread_freezable_should_stop(NULL)) { + + if (signal_pending(current)) + flush_signals(current); /* * Listen for a request on the socket */ @@ -84,6 +87,8 @@ nfs4_callback_svc(void *vrqstp) continue; svc_process(rqstp); } + svc_exit_thread(rqstp); + module_put_and_exit(0); return 0; } @@ -102,9 +107,10 @@ nfs41_callback_svc(void *vrqstp) set_freezable(); - while (!kthread_should_stop()) { - if (try_to_freeze()) - continue; + while (!kthread_freezable_should_stop(NULL)) { + + if (signal_pending(current)) + flush_signals(current); prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE); spin_lock_bh(&serv->sv_cb_lock); @@ -120,11 +126,13 @@ nfs41_callback_svc(void *vrqstp) error); } else { spin_unlock_bh(&serv->sv_cb_lock); - schedule(); + if (!kthread_should_stop()) + schedule(); finish_wait(&serv->sv_cb_waitq, &wq); } - flush_signals(current); } + svc_exit_thread(rqstp); + module_put_and_exit(0); return 0; } @@ -220,23 +228,23 @@ err_bind: static struct svc_serv_ops nfs40_cb_sv_ops = { .svo_function = nfs4_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads, + .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; #if defined(CONFIG_NFS_V4_1) static struct svc_serv_ops nfs41_cb_sv_ops = { .svo_function = nfs41_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads, + .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = &nfs41_cb_sv_ops, }; #else -struct svc_serv_ops *nfs4_cb_sv_ops[] = { +static struct svc_serv_ops *nfs4_cb_sv_ops[] = { [0] = &nfs40_cb_sv_ops, [1] = NULL, }; @@ -279,7 +287,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n", cb_info->users); - serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops); + serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops); if (!serv) { printk(KERN_ERR "nfs_callback_create_svc: create service failed\n"); return ERR_PTR(-ENOMEM); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 53e02b8..d04ec381 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1167,11 +1167,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) /* Force a full look up iff the parent directory has changed */ if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) { - - if (nfs_lookup_verify_inode(inode, flags)) { + error = nfs_lookup_verify_inode(inode, flags); + if (error) { if (flags & LOOKUP_RCU) return -ECHILD; - goto out_zap_parent; + if (error == -ESTALE) + goto out_zap_parent; + goto out_error; } goto out_valid; } @@ -1195,8 +1197,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) trace_nfs_lookup_revalidate_enter(dir, dentry, flags); error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label); trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error); - if (error) + if (error == -ESTALE || error == -ENOENT) goto out_bad; + if (error) + goto out_error; if (nfs_compare_fh(NFS_FH(inode), fhandle)) goto out_bad; if ((error = nfs_refresh_inode(inode, fattr)) != 0) diff --git a/fs/nfs/file.c b/fs/nfs/file.c index a1de8ef..1eec947 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -636,11 +636,11 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) if (result <= 0) goto out; - result = generic_write_sync(iocb, result); - if (result < 0) - goto out; written = result; iocb->ki_pos += written; + result = generic_write_sync(iocb, written); + if (result < 0) + goto out; /* Return error values */ if (nfs_need_check_write(file, inode)) { @@ -757,7 +757,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) */ nfs_sync_mapping(filp->f_mapping); if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) - nfs_zap_mapping(inode, filp->f_mapping); + nfs_zap_caches(inode); out: return status; } diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index f7a3f6b..9009989 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -30,6 +30,7 @@ void nfs4_ff_layout_free_deviceid(struct nfs4_ff_layout_ds *mirror_ds) { nfs4_print_deviceid(&mirror_ds->id_node.deviceid); nfs4_pnfs_ds_put(mirror_ds->ds); + kfree(mirror_ds->ds_versions); kfree_rcu(mirror_ds, id_node.rcu); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index bf4ec5e..76ae256 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1278,9 +1278,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat return 0; /* Has the inode gone and changed behind our back? */ if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) - return -EIO; + return -ESTALE; if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) - return -EIO; + return -ESTALE; if (!nfs_file_has_buffered_writers(nfsi)) { /* Verify a few of the more important attributes */ diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 80bcc0b..52ea41b 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -248,7 +248,6 @@ int nfs_iocounter_wait(struct nfs_lock_context *l_ctx); extern const struct nfs_pageio_ops nfs_pgio_rw_ops; struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *); void nfs_pgio_header_free(struct nfs_pgio_header *); -void nfs_pgio_data_destroy(struct nfs_pgio_header *); int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *); int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index fc9b049..a53b8e0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2343,8 +2343,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred, if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0) return 0; - /* even though OPEN succeeded, access is denied. Close the file */ - nfs4_close_state(state, fmode); return -EACCES; } @@ -6421,7 +6419,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request) set_current_state(TASK_INTERRUPTIBLE); spin_unlock_irqrestore(&q->lock, flags); - freezable_schedule_timeout_interruptible(NFS4_LOCK_MAXTIMEOUT); + freezable_schedule_timeout(NFS4_LOCK_MAXTIMEOUT); } finish_wait(q, &wait); @@ -7412,7 +7410,7 @@ static void nfs4_exchange_id_done(struct rpc_task *task, void *data) cdata->res.server_scope = NULL; } /* Save the EXCHANGE_ID verifier session trunk tests */ - memcpy(clp->cl_confirm.data, cdata->args.verifier->data, + memcpy(clp->cl_confirm.data, cdata->args.verifier.data, sizeof(clp->cl_confirm.data)); } out: @@ -7449,7 +7447,6 @@ static const struct rpc_call_ops nfs4_exchange_id_call_ops = { static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, u32 sp4_how, struct rpc_xprt *xprt) { - nfs4_verifier verifier; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID], .rpc_cred = cred, @@ -7472,8 +7469,7 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, if (!calldata) goto out; - if (!xprt) - nfs4_init_boot_verifier(clp, &verifier); + nfs4_init_boot_verifier(clp, &calldata->args.verifier); status = nfs4_init_uniform_client_string(clp); if (status) @@ -7518,9 +7514,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred, task_setup_data.rpc_xprt = xprt; task_setup_data.flags = RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC; - calldata->args.verifier = &clp->cl_confirm; - } else { - calldata->args.verifier = &verifier; + memcpy(calldata->args.verifier.data, clp->cl_confirm.data, + sizeof(calldata->args.verifier.data)); } calldata->args.client = clp; #ifdef CONFIG_NFS_V4_1_MIGRATION @@ -8431,6 +8426,7 @@ static void nfs4_layoutget_release(void *calldata) size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_sequence_free_slot(&lgp->res.seq_res); nfs4_free_pages(lgp->args.layout.pages, max_pages); pnfs_put_layout_hdr(NFS_I(inode)->layout); put_nfs_open_context(lgp->args.ctx); @@ -8505,7 +8501,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags) /* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */ if (status == 0 && lgp->res.layoutp->len) lseg = pnfs_layout_process(lgp); - nfs4_sequence_free_slot(&lgp->res.seq_res); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); if (status) diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index c9c4d985..5e2724a 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1761,7 +1761,7 @@ static void encode_exchange_id(struct xdr_stream *xdr, int len = 0; encode_op_hdr(xdr, OP_EXCHANGE_ID, decode_exchange_id_maxsz, hdr); - encode_nfs4_verifier(xdr, args->verifier); + encode_nfs4_verifier(xdr, &args->verifier); encode_string(xdr, strlen(args->client->cl_owner_id), args->client->cl_owner_id); diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 142a74f..3d17fc8 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -497,16 +497,6 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *ops) } EXPORT_SYMBOL_GPL(nfs_pgio_header_alloc); -/* - * nfs_pgio_header_free - Free a read or write header - * @hdr: The header to free - */ -void nfs_pgio_header_free(struct nfs_pgio_header *hdr) -{ - hdr->rw_ops->rw_free_header(hdr); -} -EXPORT_SYMBOL_GPL(nfs_pgio_header_free); - /** * nfs_pgio_data_destroy - make @hdr suitable for reuse * @@ -515,14 +505,24 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free); * * @hdr: A header that has had nfs_generic_pgio called */ -void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr) +static void nfs_pgio_data_destroy(struct nfs_pgio_header *hdr) { if (hdr->args.context) put_nfs_open_context(hdr->args.context); if (hdr->page_array.pagevec != hdr->page_array.page_array) kfree(hdr->page_array.pagevec); } -EXPORT_SYMBOL_GPL(nfs_pgio_data_destroy); + +/* + * nfs_pgio_header_free - Free a read or write header + * @hdr: The header to free + */ +void nfs_pgio_header_free(struct nfs_pgio_header *hdr) +{ + nfs_pgio_data_destroy(hdr); + hdr->rw_ops->rw_free_header(hdr); +} +EXPORT_SYMBOL_GPL(nfs_pgio_header_free); /** * nfs_pgio_rpcsetup - Set up arguments for a pageio call @@ -636,7 +636,6 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); static void nfs_pgio_error(struct nfs_pgio_header *hdr) { set_bit(NFS_IOHDR_REDO, &hdr->flags); - nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); } @@ -647,7 +646,6 @@ static void nfs_pgio_error(struct nfs_pgio_header *hdr) static void nfs_pgio_release(void *calldata) { struct nfs_pgio_header *hdr = calldata; - nfs_pgio_data_destroy(hdr); hdr->completion_ops->completion(hdr); } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 415d7e6..b7a07ba 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2145,7 +2145,6 @@ pnfs_write_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_write_mds(desc); mirror->pg_recoalesce = 1; } - nfs_pgio_data_destroy(hdr); hdr->release(hdr); } @@ -2257,7 +2256,6 @@ pnfs_read_through_mds(struct nfs_pageio_descriptor *desc, nfs_pageio_reset_read_mds(desc); mirror->pg_recoalesce = 1; } - nfs_pgio_data_destroy(hdr); hdr->release(hdr); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 211dc2a..3069cd4 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -753,6 +753,14 @@ int set_callback_cred(void) return 0; } +void cleanup_callback_cred(void) +{ + if (callback_cred) { + put_rpccred(callback_cred); + callback_cred = NULL; + } +} + static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses) { if (clp->cl_minorversion == 0) { diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index a0dee8a..d35eb07 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7012,23 +7012,24 @@ nfs4_state_start(void) ret = set_callback_cred(); if (ret) - return -ENOMEM; + return ret; + laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); if (laundry_wq == NULL) { ret = -ENOMEM; - goto out_recovery; + goto out_cleanup_cred; } ret = nfsd4_create_callback_queue(); if (ret) goto out_free_laundry; set_max_delegations(); - return 0; out_free_laundry: destroy_workqueue(laundry_wq); -out_recovery: +out_cleanup_cred: + cleanup_callback_cred(); return ret; } @@ -7086,6 +7087,7 @@ nfs4_state_shutdown(void) { destroy_workqueue(laundry_wq); nfsd4_destroy_callback_queue(); + cleanup_callback_cred(); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 4e7a56a..2c4f7a2 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -129,7 +129,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp) argp->p = page_address(argp->pagelist[0]); argp->pagelist++; if (argp->pagelen < PAGE_SIZE) { - argp->end = argp->p + (argp->pagelen>>2); + argp->end = argp->p + XDR_QUADLEN(argp->pagelen); argp->pagelen = 0; } else { argp->end = argp->p + (PAGE_SIZE>>2); @@ -1246,9 +1246,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) argp->pagelen -= pages * PAGE_SIZE; len -= pages * PAGE_SIZE; - argp->p = (__be32 *)page_address(argp->pagelist[0]); - argp->pagelist++; - argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); + next_decode_page(argp); } argp->p += XDR_QUADLEN(len); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 4516e8b..005c911 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -615,6 +615,7 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir, extern __be32 nfs4_check_open_reclaim(clientid_t *clid, struct nfsd4_compound_state *cstate, struct nfsd_net *nn); extern int set_callback_cred(void); +extern void cleanup_callback_cred(void); extern void nfsd4_probe_callback(struct nfs4_client *clp); extern void nfsd4_probe_callback_sync(struct nfs4_client *clp); extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index db39de2..a64adc2 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -104,16 +104,20 @@ int __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask) if (unlikely(!fsnotify_inode_watches_children(p_inode))) __fsnotify_update_child_dentry_flags(p_inode); else if (p_inode->i_fsnotify_mask & mask) { + struct name_snapshot name; + /* we are notifying a parent so come up with the new mask which * specifies these are events which came from a child. */ mask |= FS_EVENT_ON_CHILD; + take_dentry_name_snapshot(&name, dentry); if (path) ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH, - dentry->d_name.name, 0); + name.name, 0); else ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE, - dentry->d_name.name, 0); + name.name, 0); + release_dentry_name_snapshot(&name); } dput(parent); diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index f72712f..06089be 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -7310,13 +7310,24 @@ out: static int ocfs2_trim_extent(struct super_block *sb, struct ocfs2_group_desc *gd, - u32 start, u32 count) + u64 group, u32 start, u32 count) { u64 discard, bcount; + struct ocfs2_super *osb = OCFS2_SB(sb); bcount = ocfs2_clusters_to_blocks(sb, count); - discard = le64_to_cpu(gd->bg_blkno) + - ocfs2_clusters_to_blocks(sb, start); + discard = ocfs2_clusters_to_blocks(sb, start); + + /* + * For the first cluster group, the gd->bg_blkno is not at the start + * of the group, but at an offset from the start. If we add it while + * calculating discard for first group, we will wrongly start fstrim a + * few blocks after the desried start block and the range can cross + * over into the next cluster group. So, add it only if this is not + * the first cluster group. + */ + if (group != osb->first_cluster_group_blkno) + discard += le64_to_cpu(gd->bg_blkno); trace_ocfs2_trim_extent(sb, (unsigned long long)discard, bcount); @@ -7324,7 +7335,7 @@ static int ocfs2_trim_extent(struct super_block *sb, } static int ocfs2_trim_group(struct super_block *sb, - struct ocfs2_group_desc *gd, + struct ocfs2_group_desc *gd, u64 group, u32 start, u32 max, u32 minbits) { int ret = 0, count = 0, next; @@ -7343,7 +7354,7 @@ static int ocfs2_trim_group(struct super_block *sb, next = ocfs2_find_next_bit(bitmap, max, start); if ((next - start) >= minbits) { - ret = ocfs2_trim_extent(sb, gd, + ret = ocfs2_trim_extent(sb, gd, group, start, next - start); if (ret < 0) { mlog_errno(ret); @@ -7441,7 +7452,8 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range) } gd = (struct ocfs2_group_desc *)gd_bh->b_data; - cnt = ocfs2_trim_group(sb, gd, first_bit, last_bit, minlen); + cnt = ocfs2_trim_group(sb, gd, group, + first_bit, last_bit, minlen); brelse(gd_bh); gd_bh = NULL; if (cnt < 0) { diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 636abcb..5e8709a 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -2242,13 +2242,13 @@ unlock: spin_unlock(&o2hb_live_lock); } -static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item, char *page) { return sprintf(page, "%u\n", o2hb_dead_threshold); } -static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item, +static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item, const char *page, size_t count) { unsigned long tmp; @@ -2297,11 +2297,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item, } -CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold); +CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold); CONFIGFS_ATTR(o2hb_heartbeat_group_, mode); static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = { - &o2hb_heartbeat_group_attr_threshold, + &o2hb_heartbeat_group_attr_dead_threshold, &o2hb_heartbeat_group_attr_mode, NULL, }; diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 77d1632..8dce409 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -532,6 +532,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res) init_waitqueue_head(&res->l_event); INIT_LIST_HEAD(&res->l_blocked_list); INIT_LIST_HEAD(&res->l_mask_waiters); + INIT_LIST_HEAD(&res->l_holders); } void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res, @@ -749,6 +750,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res) res->l_flags = 0UL; } +/* + * Keep a list of processes who have interest in a lockres. + * Note: this is now only uesed for check recursive cluster locking. + */ +static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + INIT_LIST_HEAD(&oh->oh_list); + oh->oh_owner_pid = get_pid(task_pid(current)); + + spin_lock(&lockres->l_lock); + list_add_tail(&oh->oh_list, &lockres->l_holders); + spin_unlock(&lockres->l_lock); +} + +static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres, + struct ocfs2_lock_holder *oh) +{ + spin_lock(&lockres->l_lock); + list_del(&oh->oh_list); + spin_unlock(&lockres->l_lock); + + put_pid(oh->oh_owner_pid); +} + +static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres) +{ + struct ocfs2_lock_holder *oh; + struct pid *pid; + + /* look in the list of holders for one with the current task as owner */ + spin_lock(&lockres->l_lock); + pid = task_pid(current); + list_for_each_entry(oh, &lockres->l_holders, oh_list) { + if (oh->oh_owner_pid == pid) { + spin_unlock(&lockres->l_lock); + return 1; + } + } + spin_unlock(&lockres->l_lock); + + return 0; +} + static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres, int level) { @@ -2333,8 +2378,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, goto getbh; } - if (ocfs2_mount_local(osb)) - goto local; + if ((arg_flags & OCFS2_META_LOCK_GETBH) || + ocfs2_mount_local(osb)) + goto update; if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); @@ -2363,7 +2409,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode, if (!(arg_flags & OCFS2_META_LOCK_RECOVERY)) ocfs2_wait_for_recovery(osb); -local: +update: /* * We only see this flag if we're being called from * ocfs2_read_locked_inode(). It means we're locking an inode @@ -2497,6 +2543,59 @@ void ocfs2_inode_unlock(struct inode *inode, ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level); } +/* + * This _tracker variantes are introduced to deal with the recursive cluster + * locking issue. The idea is to keep track of a lock holder on the stack of + * the current process. If there's a lock holder on the stack, we know the + * task context is already protected by cluster locking. Currently, they're + * used in some VFS entry routines. + * + * return < 0 on error, return == 0 if there's no lock holder on the stack + * before this call, return == 1 if this call would be a recursive locking. + */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh) +{ + int status; + int arg_flags = 0, has_locked; + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + has_locked = ocfs2_is_locked_by_me(lockres); + /* Just get buffer head if the cluster lock has been taken */ + if (has_locked) + arg_flags = OCFS2_META_LOCK_GETBH; + + if (likely(!has_locked || ret_bh)) { + status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags); + if (status < 0) { + if (status != -ENOENT) + mlog_errno(status); + return status; + } + } + if (!has_locked) + ocfs2_add_holder(lockres, oh); + + return has_locked; +} + +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock) +{ + struct ocfs2_lock_res *lockres; + + lockres = &OCFS2_I(inode)->ip_inode_lockres; + if (!had_lock) { + ocfs2_remove_holder(lockres, oh); + ocfs2_inode_unlock(inode, ex); + } +} + int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno) { struct ocfs2_lock_res *lockres; diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h index d293a22..a7fc18b 100644 --- a/fs/ocfs2/dlmglue.h +++ b/fs/ocfs2/dlmglue.h @@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb { __be32 lvb_os_seqno; }; +struct ocfs2_lock_holder { + struct list_head oh_list; + struct pid *oh_owner_pid; +}; + /* ocfs2_inode_lock_full() 'arg_flags' flags */ /* don't wait on recovery. */ #define OCFS2_META_LOCK_RECOVERY (0x01) @@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb { #define OCFS2_META_LOCK_NOQUEUE (0x02) /* don't block waiting for the downconvert thread, instead return -EAGAIN */ #define OCFS2_LOCK_NONBLOCK (0x04) +/* just get back disk inode bh if we've got cluster lock. */ +#define OCFS2_META_LOCK_GETBH (0x08) /* Locking subclasses of inode cluster lock */ enum { @@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug); /* To set the locking protocol on module initialization */ void ocfs2_set_locking_protocol(void); + +/* The _tracker pair is used to avoid cluster recursive locking */ +int ocfs2_inode_lock_tracker(struct inode *inode, + struct buffer_head **ret_bh, + int ex, + struct ocfs2_lock_holder *oh); +void ocfs2_inode_unlock_tracker(struct inode *inode, + int ex, + struct ocfs2_lock_holder *oh, + int had_lock); + #endif /* DLMGLUE_H */ diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index e63af7d..594575e 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -172,6 +172,7 @@ struct ocfs2_lock_res { struct list_head l_blocked_list; struct list_head l_mask_waiters; + struct list_head l_holders; unsigned long l_flags; char l_name[OCFS2_LOCK_ID_MAX_LEN]; @@ -902,6 +902,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o int lookup_flags = 0; int acc_mode = ACC_MODE(flags); + /* + * Clear out all open flags we don't know about so that we don't report + * them in fcntl(F_GETFD) or similar interfaces. + */ + flags &= VALID_OPEN_FLAGS; + if (flags & (O_CREAT | __O_TMPFILE)) op->mode = (mode & S_IALLUGO) | S_IFREG; else diff --git a/fs/orangefs/acl.c b/fs/orangefs/acl.c index 7a37544..9409aac 100644 --- a/fs/orangefs/acl.c +++ b/fs/orangefs/acl.c @@ -61,9 +61,9 @@ struct posix_acl *orangefs_get_acl(struct inode *inode, int type) return acl; } -int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +static int __orangefs_set_acl(struct inode *inode, struct posix_acl *acl, + int type) { - struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); int error = 0; void *value = NULL; size_t size = 0; @@ -72,22 +72,6 @@ int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - umode_t mode; - - error = posix_acl_update_mode(inode, &mode, &acl); - if (error) { - gossip_err("%s: posix_acl_update_mode err: %d\n", - __func__, - error); - return error; - } - - if (inode->i_mode != mode) - SetModeFlag(orangefs_inode); - inode->i_mode = mode; - mark_inode_dirty_sync(inode); - } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; @@ -132,6 +116,29 @@ out: return error; } +int orangefs_set_acl(struct inode *inode, struct posix_acl *acl, int type) +{ + int error; + + if (type == ACL_TYPE_ACCESS && acl) { + umode_t mode; + + error = posix_acl_update_mode(inode, &mode, &acl); + if (error) { + gossip_err("%s: posix_acl_update_mode err: %d\n", + __func__, + error); + return error; + } + + if (inode->i_mode != mode) + SetModeFlag(ORANGEFS_I(inode)); + inode->i_mode = mode; + mark_inode_dirty_sync(inode); + } + return __orangefs_set_acl(inode, acl, type); +} + int orangefs_init_acl(struct inode *inode, struct inode *dir) { struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode); @@ -146,13 +153,14 @@ int orangefs_init_acl(struct inode *inode, struct inode *dir) return error; if (default_acl) { - error = orangefs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __orangefs_set_acl(inode, default_acl, + ACL_TYPE_DEFAULT); posix_acl_release(default_acl); } if (acl) { if (!error) - error = orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __orangefs_set_acl(inode, acl, ACL_TYPE_ACCESS); posix_acl_release(acl); } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 0e10085..e7c8ac4 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1146,6 +1146,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) unsigned int stacklen = 0; unsigned int i; bool remote = false; + struct cred *cred; int err; err = -ENOMEM; @@ -1309,10 +1310,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) else sb->s_d_op = &ovl_dentry_operations; - ufs->creator_cred = prepare_creds(); - if (!ufs->creator_cred) + err = -ENOMEM; + ufs->creator_cred = cred = prepare_creds(); + if (!cred) goto out_put_lower_mnt; + /* Never override disk quota limits or use reserved space */ + cap_lower(cred->cap_effective, CAP_SYS_RESOURCE); + err = -ENOMEM; oe = ovl_alloc_entry(numlower); if (!oe) @@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p) return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave); } +static inline struct mount *last_slave(struct mount *p) +{ + return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave); +} + static inline struct mount *next_slave(struct mount *p) { return list_entry(p->mnt_slave.next, struct mount, mnt_slave); @@ -164,6 +169,19 @@ static struct mount *propagation_next(struct mount *m, } } +static struct mount *skip_propagation_subtree(struct mount *m, + struct mount *origin) +{ + /* + * Advance m such that propagation_next will not return + * the slaves of m. + */ + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) + m = last_slave(m); + + return m; +} + static struct mount *next_group(struct mount *m, struct mount *origin) { while (1) { @@ -415,65 +433,104 @@ void propagate_mount_unlock(struct mount *mnt) } } -/* - * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted. - */ -static void mark_umount_candidates(struct mount *mnt) +static void umount_one(struct mount *mnt, struct list_head *to_umount) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; - - BUG_ON(parent == mnt); - - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - if (!child || (child->mnt.mnt_flags & MNT_UMOUNT)) - continue; - if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) { - SET_MNT_MARK(child); - } - } + CLEAR_MNT_MARK(mnt); + mnt->mnt.mnt_flags |= MNT_UMOUNT; + list_del_init(&mnt->mnt_child); + list_del_init(&mnt->mnt_umounting); + list_move_tail(&mnt->mnt_list, to_umount); } /* * NOTE: unmounting 'mnt' naturally propagates to all other mounts its * parent propagates to. */ -static void __propagate_umount(struct mount *mnt) +static bool __propagate_umount(struct mount *mnt, + struct list_head *to_umount, + struct list_head *to_restore) { - struct mount *parent = mnt->mnt_parent; - struct mount *m; + bool progress = false; + struct mount *child; - BUG_ON(parent == mnt); + /* + * The state of the parent won't change if this mount is + * already unmounted or marked as without children. + */ + if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED)) + goto out; - for (m = propagation_next(parent, parent); m; - m = propagation_next(m, parent)) { - struct mount *topper; - struct mount *child = __lookup_mnt(&m->mnt, - mnt->mnt_mountpoint); - /* - * umount the child only if the child has no children - * and the child is marked safe to unmount. - */ - if (!child || !IS_MNT_MARKED(child)) + /* Verify topper is the only grandchild that has not been + * speculatively unmounted. + */ + list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { + if (child->mnt_mountpoint == mnt->mnt.mnt_root) continue; - CLEAR_MNT_MARK(child); + if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child)) + continue; + /* Found a mounted child */ + goto children; + } - /* If there is exactly one mount covering all of child - * replace child with that mount. - */ - topper = find_topper(child); - if (topper) - mnt_change_mountpoint(child->mnt_parent, child->mnt_mp, - topper); + /* Mark mounts that can be unmounted if not locked */ + SET_MNT_MARK(mnt); + progress = true; + + /* If a mount is without children and not locked umount it. */ + if (!IS_MNT_LOCKED(mnt)) { + umount_one(mnt, to_umount); + } else { +children: + list_move_tail(&mnt->mnt_umounting, to_restore); + } +out: + return progress; +} + +static void umount_list(struct list_head *to_umount, + struct list_head *to_restore) +{ + struct mount *mnt, *child, *tmp; + list_for_each_entry(mnt, to_umount, mnt_list) { + list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) { + /* topper? */ + if (child->mnt_mountpoint == mnt->mnt.mnt_root) + list_move_tail(&child->mnt_umounting, to_restore); + else + umount_one(child, to_umount); + } + } +} - if (list_empty(&child->mnt_mounts)) { - list_del_init(&child->mnt_child); - child->mnt.mnt_flags |= MNT_UMOUNT; - list_move_tail(&child->mnt_list, &mnt->mnt_list); +static void restore_mounts(struct list_head *to_restore) +{ + /* Restore mounts to a clean working state */ + while (!list_empty(to_restore)) { + struct mount *mnt, *parent; + struct mountpoint *mp; + + mnt = list_first_entry(to_restore, struct mount, mnt_umounting); + CLEAR_MNT_MARK(mnt); + list_del_init(&mnt->mnt_umounting); + + /* Should this mount be reparented? */ + mp = mnt->mnt_mp; + parent = mnt->mnt_parent; + while (parent->mnt.mnt_flags & MNT_UMOUNT) { + mp = parent->mnt_mp; + parent = parent->mnt_parent; } + if (parent != mnt->mnt_parent) + mnt_change_mountpoint(parent, mp, mnt); + } +} + +static void cleanup_umount_visitations(struct list_head *visited) +{ + while (!list_empty(visited)) { + struct mount *mnt = + list_first_entry(visited, struct mount, mnt_umounting); + list_del_init(&mnt->mnt_umounting); } } @@ -487,11 +544,68 @@ static void __propagate_umount(struct mount *mnt) int propagate_umount(struct list_head *list) { struct mount *mnt; + LIST_HEAD(to_restore); + LIST_HEAD(to_umount); + LIST_HEAD(visited); + + /* Find candidates for unmounting */ + list_for_each_entry_reverse(mnt, list, mnt_list) { + struct mount *parent = mnt->mnt_parent; + struct mount *m; + + /* + * If this mount has already been visited it is known that it's + * entire peer group and all of their slaves in the propagation + * tree for the mountpoint has already been visited and there is + * no need to visit them again. + */ + if (!list_empty(&mnt->mnt_umounting)) + continue; + + list_add_tail(&mnt->mnt_umounting, &visited); + for (m = propagation_next(parent, parent); m; + m = propagation_next(m, parent)) { + struct mount *child = __lookup_mnt(&m->mnt, + mnt->mnt_mountpoint); + if (!child) + continue; + + if (!list_empty(&child->mnt_umounting)) { + /* + * If the child has already been visited it is + * know that it's entire peer group and all of + * their slaves in the propgation tree for the + * mountpoint has already been visited and there + * is no need to visit this subtree again. + */ + m = skip_propagation_subtree(m, parent); + continue; + } else if (child->mnt.mnt_flags & MNT_UMOUNT) { + /* + * We have come accross an partially unmounted + * mount in list that has not been visited yet. + * Remember it has been visited and continue + * about our merry way. + */ + list_add_tail(&child->mnt_umounting, &visited); + continue; + } + + /* Check the child and parents while progress is made */ + while (__propagate_umount(child, + &to_umount, &to_restore)) { + /* Is the parent a umount candidate? */ + child = child->mnt_parent; + if (list_empty(&child->mnt_umounting)) + break; + } + } + } - list_for_each_entry_reverse(mnt, list, mnt_list) - mark_umount_candidates(mnt); + umount_list(&to_umount, &to_restore); + restore_mounts(&to_restore); + cleanup_umount_visitations(&visited); + list_splice_tail(&to_umount, list); - list_for_each_entry(mnt, list, mnt_list) - __propagate_umount(mnt); return 0; } diff --git a/fs/proc/array.c b/fs/proc/array.c index 81818ad..c932ec4 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -60,6 +60,7 @@ #include <linux/tty.h> #include <linux/string.h> #include <linux/mman.h> +#include <linux/sched.h> #include <linux/proc_fs.h> #include <linux/ioport.h> #include <linux/uaccess.h> @@ -416,7 +417,15 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * esp and eip are intentionally zeroed out. There is no * non-racy way to read them without freezing the task. * Programs that need reliable values can use ptrace(2). + * + * The only exception is if the task is core dumping because + * a program is not able to use ptrace(2) in that case. It is + * safe because the task has stopped executing permanently. */ + if (permitted && (task->flags & PF_DUMPCORE)) { + eip = KSTK_EIP(task); + esp = KSTK_ESP(task); + } } get_task_comm(tcomm, task); diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index 6ad831b..8b09271 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -434,7 +434,7 @@ static int ramoops_init_przs(struct device *dev, struct ramoops_context *cxt, for (i = 0; i < cxt->max_dump_cnt; i++) { cxt->przs[i] = persistent_ram_new(*paddr, cxt->record_size, 0, &cxt->ecc_info, - cxt->memtype); + cxt->memtype, 0); if (IS_ERR(cxt->przs[i])) { err = PTR_ERR(cxt->przs[i]); dev_err(dev, "failed to request mem region (0x%zx@0x%llx): %d\n", @@ -471,7 +471,8 @@ static int ramoops_init_prz(struct device *dev, struct ramoops_context *cxt, return -ENOMEM; } - *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, cxt->memtype); + *prz = persistent_ram_new(*paddr, sz, sig, &cxt->ecc_info, + cxt->memtype, 0); if (IS_ERR(*prz)) { int err = PTR_ERR(*prz); diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 3975dee..e11672a 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -48,16 +48,15 @@ static inline size_t buffer_start(struct persistent_ram_zone *prz) return atomic_read(&prz->buffer->start); } -static DEFINE_RAW_SPINLOCK(buffer_lock); - /* increase and wrap the start pointer, returning the old value */ static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) { int old; int new; - unsigned long flags; + unsigned long flags = 0; - raw_spin_lock_irqsave(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_lock_irqsave(&prz->buffer_lock, flags); old = atomic_read(&prz->buffer->start); new = old + a; @@ -65,7 +64,8 @@ static size_t buffer_start_add(struct persistent_ram_zone *prz, size_t a) new -= prz->buffer_size; atomic_set(&prz->buffer->start, new); - raw_spin_unlock_irqrestore(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_unlock_irqrestore(&prz->buffer_lock, flags); return old; } @@ -75,9 +75,10 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a) { size_t old; size_t new; - unsigned long flags; + unsigned long flags = 0; - raw_spin_lock_irqsave(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_lock_irqsave(&prz->buffer_lock, flags); old = atomic_read(&prz->buffer->size); if (old == prz->buffer_size) @@ -89,7 +90,8 @@ static void buffer_size_add(struct persistent_ram_zone *prz, size_t a) atomic_set(&prz->buffer->size, new); exit: - raw_spin_unlock_irqrestore(&buffer_lock, flags); + if (!(prz->flags & PRZ_FLAG_NO_LOCK)) + raw_spin_unlock_irqrestore(&prz->buffer_lock, flags); } static void notrace persistent_ram_encode_rs8(struct persistent_ram_zone *prz, @@ -491,6 +493,7 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig, prz->buffer->sig); } + /* Rewind missing or invalid memory area. */ prz->buffer->sig = sig; persistent_ram_zap(prz); @@ -517,7 +520,7 @@ void persistent_ram_free(struct persistent_ram_zone *prz) struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, u32 sig, struct persistent_ram_ecc_info *ecc_info, - unsigned int memtype) + unsigned int memtype, u32 flags) { struct persistent_ram_zone *prz; int ret = -ENOMEM; @@ -528,6 +531,10 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size, goto err; } + /* Initialize general buffer state. */ + raw_spin_lock_init(&prz->buffer_lock); + prz->flags = flags; + ret = persistent_ram_buffer_map(start, size, prz, memtype); if (ret) goto err; diff --git a/fs/read_write.c b/fs/read_write.c index e479e24..ba28059 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -114,7 +114,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: @@ -122,7 +122,7 @@ generic_file_llseek_size(struct file *file, loff_t offset, int whence, * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ - if (offset >= eof) + if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; @@ -1518,6 +1518,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, if (flags != 0) return -EINVAL; + if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) + return -EISDIR; + if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) + return -EINVAL; + ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c index 3d2256a..d92a1dc 100644 --- a/fs/reiserfs/xattr_acl.c +++ b/fs/reiserfs/xattr_acl.c @@ -37,7 +37,14 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) error = journal_begin(&th, inode->i_sb, jcreate_blocks); reiserfs_write_unlock(inode->i_sb); if (error == 0) { + if (type == ACL_TYPE_ACCESS && acl) { + error = posix_acl_update_mode(inode, &inode->i_mode, + &acl); + if (error) + goto unlock; + } error = __reiserfs_set_acl(&th, inode, type, acl); +unlock: reiserfs_write_lock(inode->i_sb); error2 = journal_end(&th); reiserfs_write_unlock(inode->i_sb); @@ -241,11 +248,6 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode, switch (type) { case ACL_TYPE_ACCESS: name = XATTR_NAME_POSIX_ACL_ACCESS; - if (acl) { - error = posix_acl_update_mode(inode, &inode->i_mode, &acl); - if (error) - return error; - } break; case ACL_TYPE_DEFAULT: name = XATTR_NAME_POSIX_ACL_DEFAULT; diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c index 91bc76dc..7d764e3 100644 --- a/fs/ubifs/journal.c +++ b/fs/ubifs/journal.c @@ -576,7 +576,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir, /* Make sure to also account for extended attributes */ len += host_ui->data_len; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -952,7 +952,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir, if (twoparents) len += plen; - dent1 = kmalloc(len, GFP_NOFS); + dent1 = kzalloc(len, GFP_NOFS); if (!dent1) return -ENOMEM; @@ -1102,7 +1102,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir, len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8); if (move) len += plen; - dent = kmalloc(len, GFP_NOFS); + dent = kzalloc(len, GFP_NOFS); if (!dent) return -ENOMEM; @@ -1466,7 +1466,7 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host, hlen = host_ui->data_len + UBIFS_INO_NODE_SZ; len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8); - xent = kmalloc(len, GFP_NOFS); + xent = kzalloc(len, GFP_NOFS); if (!xent) return -ENOMEM; @@ -1573,7 +1573,7 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode, aligned_len1 = ALIGN(len1, 8); aligned_len = aligned_len1 + ALIGN(len2, 8); - ino = kmalloc(aligned_len, GFP_NOFS); + ino = kzalloc(aligned_len, GFP_NOFS); if (!ino) return -ENOMEM; diff --git a/fs/udf/inode.c b/fs/udf/inode.c index 129b18a..0359435 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1243,8 +1243,8 @@ int udf_setsize(struct inode *inode, loff_t newsize) return err; } set_size: - truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); + truncate_setsize(inode, newsize); } else { if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { down_write(&iinfo->i_data_sem); @@ -1261,9 +1261,9 @@ set_size: udf_get_block); if (err) return err; + truncate_setsize(inode, newsize); down_write(&iinfo->i_data_sem); udf_clear_extent_cache(inode); - truncate_setsize(inode, newsize); udf_truncate_extents(inode); up_write(&iinfo->i_data_sem); } @@ -249,7 +249,7 @@ xattr_getsecurity(struct inode *inode, const char *name, void *value, } memcpy(value, buffer, len); out: - security_release_secctx(buffer, len); + kfree(buffer); out_noalloc: return len; } diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 339c696..bb2beae 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -24,24 +24,6 @@ #include "kmem.h" #include "xfs_message.h" -/* - * Greedy allocation. May fail and may return vmalloced memory. - */ -void * -kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize) -{ - void *ptr; - size_t kmsize = maxsize; - - while (!(ptr = vzalloc(kmsize))) { - if ((kmsize >>= 1) <= minsize) - kmsize = minsize; - } - if (ptr) - *size = kmsize; - return ptr; -} - void * kmem_alloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h index 689f746..f0fc84f 100644 --- a/fs/xfs/kmem.h +++ b/fs/xfs/kmem.h @@ -69,8 +69,6 @@ static inline void kmem_free(const void *ptr) } -extern void *kmem_zalloc_greedy(size_t *, size_t, size_t); - static inline void * kmem_zalloc(size_t size, xfs_km_flags_t flags) { diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c index 33db69b..eed8f58 100644 --- a/fs/xfs/libxfs/xfs_ag_resv.c +++ b/fs/xfs/libxfs/xfs_ag_resv.c @@ -157,7 +157,8 @@ __xfs_ag_resv_free( trace_xfs_ag_resv_free(pag, type, 0); resv = xfs_perag_resv(pag, type); - pag->pag_mount->m_ag_max_usable += resv->ar_asked; + if (pag->pag_agno == 0) + pag->pag_mount->m_ag_max_usable += resv->ar_asked; /* * AGFL blocks are always considered "free", so whatever * was reserved at mount time must be given back at umount. @@ -217,7 +218,14 @@ __xfs_ag_resv_init( return error; } - mp->m_ag_max_usable -= ask; + /* + * Reduce the maximum per-AG allocation length by however much we're + * trying to reserve for an AG. Since this is a filesystem-wide + * counter, we only make the adjustment for AG 0. This assumes that + * there aren't any AGs hungrier for per-AG reservation than AG 0. + */ + if (pag->pag_agno == 0) + mp->m_ag_max_usable -= ask; resv = xfs_perag_resv(pag, type); resv->ar_asked = ask; diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 9f06a21..c3702cd 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1579,6 +1579,10 @@ xfs_alloc_ag_vextent_small( bp = xfs_btree_get_bufs(args->mp, args->tp, args->agno, fbno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto error0; + } xfs_trans_binval(args->tp, bp); } args->len = 1; @@ -2136,6 +2140,10 @@ xfs_alloc_fix_freelist( if (error) goto out_agbp_relse; bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0); + if (!bp) { + error = -EFSCORRUPTED; + goto out_agbp_relse; + } xfs_trans_binval(tp, bp); } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 2852521..c6c15e5 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -351,7 +351,7 @@ xfs_attr3_leaf_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 2a8cbd1..7eb9970 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -579,7 +579,7 @@ xfs_bmap_validate_ret( #else #define xfs_bmap_check_leaf_extents(cur, ip, whichfork) do { } while (0) -#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) +#define xfs_bmap_validate_ret(bno,len,flags,mval,onmap,nmap) do { } while (0) #endif /* DEBUG */ /* @@ -4057,6 +4057,17 @@ xfs_trim_extent( } } +/* trim extent to within eof */ +void +xfs_trim_extent_eof( + struct xfs_bmbt_irec *irec, + struct xfs_inode *ip) + +{ + xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount, + i_size_read(VFS_I(ip)))); +} + /* * Trim the returned map to the required bounds */ @@ -5555,6 +5566,8 @@ __xfs_bunmapi( int whichfork; /* data or attribute fork */ xfs_fsblock_t sum; xfs_filblks_t len = *rlen; /* length to unmap in file */ + xfs_fileoff_t max_len; + xfs_agnumber_t prev_agno = NULLAGNUMBER, agno; trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_); @@ -5576,6 +5589,16 @@ __xfs_bunmapi( ASSERT(len > 0); ASSERT(nexts >= 0); + /* + * Guesstimate how many blocks we can unmap without running the risk of + * blowing out the transaction with a mix of EFIs and reflink + * adjustments. + */ + if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); + else + max_len = len; + if (!(ifp->if_flags & XFS_IFEXTENTS) && (error = xfs_iread_extents(tp, ip, whichfork))) return error; @@ -5621,7 +5644,7 @@ __xfs_bunmapi( extno = 0; while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 && - (nexts == 0 || extno < nexts)) { + (nexts == 0 || extno < nexts) && max_len > 0) { /* * Is the found extent after a hole in which bno lives? * Just back up to the previous extent, if so. @@ -5647,6 +5670,17 @@ __xfs_bunmapi( ASSERT(ep != NULL); del = got; wasdel = isnullstartblock(del.br_startblock); + + /* + * Make sure we don't touch multiple AGF headers out of order + * in a single transaction, as that could cause AB-BA deadlocks. + */ + if (!wasdel) { + agno = XFS_FSB_TO_AGNO(mp, del.br_startblock); + if (prev_agno != NULLAGNUMBER && prev_agno > agno) + break; + prev_agno = agno; + } if (got.br_startoff < start) { del.br_startoff = start; del.br_blockcount -= start - got.br_startoff; @@ -5655,6 +5689,15 @@ __xfs_bunmapi( } if (del.br_startoff + del.br_blockcount > bno + 1) del.br_blockcount = bno + 1 - del.br_startoff; + + /* How much can we safely unmap? */ + if (max_len < del.br_blockcount) { + del.br_startoff += del.br_blockcount - max_len; + if (!wasdel) + del.br_startblock += del.br_blockcount - max_len; + del.br_blockcount = max_len; + } + sum = del.br_startblock + del.br_blockcount; if (isrt && (mod = do_mod(sum, mp->m_sb.sb_rextsize))) { @@ -5835,6 +5878,7 @@ __xfs_bunmapi( if (!isrt && wasdel) xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false); + max_len -= del.br_blockcount; bno = del.br_startoff - 1; nodelete: /* @@ -6604,25 +6648,33 @@ xfs_bmap_finish_one( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { struct xfs_bmbt_irec bmap; int nimaps = 1; xfs_fsblock_t firstfsb; int flags = XFS_BMAPI_REMAP; - int done; int error = 0; bmap.br_startblock = startblock; bmap.br_startoff = startoff; - bmap.br_blockcount = blockcount; + bmap.br_blockcount = *blockcount; bmap.br_state = state; + /* + * firstfsb is tied to the transaction lifetime and is used to + * ensure correct AG locking order and schedule work item + * continuations. XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us + * to only making one bmap call per transaction, so it should + * be safe to have it as a local variable here. + */ + firstfsb = NULLFSBLOCK; + trace_xfs_bmap_deferred(tp->t_mountp, XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock), - ip->i_ino, whichfork, startoff, blockcount, state); + ip->i_ino, whichfork, startoff, *blockcount, state); if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) return -EFSCORRUPTED; @@ -6641,12 +6693,11 @@ xfs_bmap_finish_one( bmap.br_blockcount, flags, &firstfsb, bmap.br_blockcount, &bmap, &nimaps, dfops); + *blockcount = 0; break; case XFS_BMAP_UNMAP: - error = xfs_bunmapi(tp, ip, bmap.br_startoff, - bmap.br_blockcount, flags, 1, &firstfsb, - dfops, &done); - ASSERT(done); + error = __xfs_bunmapi(tp, ip, startoff, blockcount, + XFS_BMAPI_REMAP, 1, &firstfsb, dfops); break; default: ASSERT(0); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e7d40b3..f1446d1 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -196,6 +196,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt, void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno, xfs_filblks_t len); +void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *); int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd); void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork); void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops, @@ -265,7 +266,7 @@ struct xfs_bmap_intent { int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, enum xfs_bmap_intent_type type, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); int xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, struct xfs_inode *ip, struct xfs_bmbt_irec *imap); int xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops, diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 5c39186..9968a74 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -888,6 +888,7 @@ xfs_bmbt_change_owner( cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork); if (!cur) return -ENOMEM; + cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER; error = xfs_btree_change_owner(cur, new_owner, buffer_list); xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 91c6891..4ad1e21 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -714,7 +714,8 @@ xfs_btree_firstrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -743,7 +744,8 @@ xfs_btree_lastrec( * Get the block pointer for this level. */ block = xfs_btree_get_block(cur, level, &bp); - xfs_btree_check_block(cur, block, level, bp); + if (xfs_btree_check_block(cur, block, level, bp)) + return 0; /* * It's empty, there is no such record. */ @@ -1772,6 +1774,7 @@ xfs_btree_lookup_get_block( /* Check the inode owner since the verifiers don't. */ if (xfs_sb_version_hascrc(&cur->bc_mp->m_sb) && + !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_INVALID_OWNER) && (cur->bc_flags & XFS_BTREE_LONG_PTRS) && be64_to_cpu((*blkp)->bb_u.l.bb_owner) != cur->bc_private.b.ip->i_ino) @@ -4432,10 +4435,15 @@ xfs_btree_block_change_owner( /* modify the owner */ block = xfs_btree_get_block(cur, level, &bp); - if (cur->bc_flags & XFS_BTREE_LONG_PTRS) + if (cur->bc_flags & XFS_BTREE_LONG_PTRS) { + if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner)) + return 0; block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner); - else + } else { + if (block->bb_u.s.bb_owner == cpu_to_be32(bbcoi->new_owner)) + return 0; block->bb_u.s.bb_owner = cpu_to_be32(bbcoi->new_owner); + } /* * If the block is a root block hosted in an inode, we might not have a @@ -4444,16 +4452,19 @@ xfs_btree_block_change_owner( * block is formatted into the on-disk inode fork. We still change it, * though, so everything is consistent in memory. */ - if (bp) { - if (cur->bc_tp) { - xfs_trans_ordered_buf(cur->bc_tp, bp); + if (!bp) { + ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); + ASSERT(level == cur->bc_nlevels - 1); + return 0; + } + + if (cur->bc_tp) { + if (!xfs_trans_ordered_buf(cur->bc_tp, bp)) { xfs_btree_log_block(cur, bp, XFS_BB_OWNER); - } else { - xfs_buf_delwri_queue(bp, bbcoi->buffer_list); + return -EAGAIN; } } else { - ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE); - ASSERT(level == cur->bc_nlevels - 1); + xfs_buf_delwri_queue(bp, bbcoi->buffer_list); } return 0; diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h index 3b0fc1a..33c7be2 100644 --- a/fs/xfs/libxfs/xfs_btree.h +++ b/fs/xfs/libxfs/xfs_btree.h @@ -268,7 +268,8 @@ typedef struct xfs_btree_cur short forksize; /* fork's inode space */ char whichfork; /* data or attr fork */ char flags; /* flags */ -#define XFS_BTCUR_BPRV_WASDEL 1 /* was delayed */ +#define XFS_BTCUR_BPRV_WASDEL (1<<0) /* was delayed */ +#define XFS_BTCUR_BPRV_INVALID_OWNER (1<<1) /* for ext swap */ } b; } bc_private; /* per-btree type data */ } xfs_btree_cur_t; diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c index 1bdf288..b305dbf 100644 --- a/fs/xfs/libxfs/xfs_da_btree.c +++ b/fs/xfs/libxfs/xfs_da_btree.c @@ -263,7 +263,7 @@ xfs_da3_node_read( err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp, which_fork, &xfs_da3_node_buf_ops); - if (!err && tp) { + if (!err && tp && *bpp) { struct xfs_da_blkinfo *info = (*bpp)->b_addr; int type; diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c index aa17cb7..43c902f 100644 --- a/fs/xfs/libxfs/xfs_dir2_block.c +++ b/fs/xfs/libxfs/xfs_dir2_block.c @@ -139,7 +139,7 @@ xfs_dir3_block_read( err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp, XFS_DATA_FORK, &xfs_dir3_block_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index b887fb2..f2e342e 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -268,7 +268,7 @@ xfs_dir3_leaf_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF); return err; } @@ -285,7 +285,7 @@ xfs_dir3_leafn_read( err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp, XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops); - if (!err && tp) + if (!err && tp && *bpp) xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF); return err; } diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index a2818f6..42fef07 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -368,8 +368,6 @@ xfs_ialloc_inode_init( * transaction and pin the log appropriately. */ xfs_trans_ordered_buf(tp, fbuf); - xfs_trans_log_buf(tp, fbuf, 0, - BBTOB(fbuf->b_length) - 1); } } else { fbuf->b_flags |= XBF_DONE; @@ -1123,6 +1121,7 @@ xfs_dialloc_ag_inobt( int error; int offset; int i, j; + int searchdistance = 10; pag = xfs_perag_get(mp, agno); @@ -1149,7 +1148,6 @@ xfs_dialloc_ag_inobt( if (pagno == agno) { int doneleft; /* done, to the left */ int doneright; /* done, to the right */ - int searchdistance = 10; error = xfs_inobt_lookup(cur, pagino, XFS_LOOKUP_LE, &i); if (error) @@ -1210,21 +1208,9 @@ xfs_dialloc_ag_inobt( /* * Loop until we find an inode chunk with a free inode. */ - while (!doneleft || !doneright) { + while (--searchdistance > 0 && (!doneleft || !doneright)) { int useleft; /* using left inode chunk this time */ - if (!--searchdistance) { - /* - * Not in range - save last search - * location and allocate a new inode - */ - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - pag->pagl_leftrec = trec.ir_startino; - pag->pagl_rightrec = rec.ir_startino; - pag->pagl_pagino = pagino; - goto newino; - } - /* figure out the closer block if both are valid. */ if (!doneleft && !doneright) { useleft = pagino - @@ -1236,13 +1222,13 @@ xfs_dialloc_ag_inobt( /* free inodes to the left? */ if (useleft && trec.ir_freecount) { - rec = trec; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); cur = tcur; pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; + rec = trec; goto alloc_inode; } @@ -1268,26 +1254,37 @@ xfs_dialloc_ag_inobt( goto error1; } - /* - * We've reached the end of the btree. because - * we are only searching a small chunk of the - * btree each search, there is obviously free - * inodes closer to the parent inode than we - * are now. restart the search again. - */ - pag->pagl_pagino = NULLAGINO; - pag->pagl_leftrec = NULLAGINO; - pag->pagl_rightrec = NULLAGINO; - xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); - xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); - goto restart_pagno; + if (searchdistance <= 0) { + /* + * Not in range - save last search + * location and allocate a new inode + */ + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + pag->pagl_leftrec = trec.ir_startino; + pag->pagl_rightrec = rec.ir_startino; + pag->pagl_pagino = pagino; + + } else { + /* + * We've reached the end of the btree. because + * we are only searching a small chunk of the + * btree each search, there is obviously free + * inodes closer to the parent inode than we + * are now. restart the search again. + */ + pag->pagl_pagino = NULLAGINO; + pag->pagl_leftrec = NULLAGINO; + pag->pagl_rightrec = NULLAGINO; + xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR); + xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); + goto restart_pagno; + } } /* * In a different AG from the parent. * See if the most recently allocated block has any free. */ -newino: if (agi->agi_newino != cpu_to_be32(NULLAGINO)) { error = xfs_inobt_lookup(cur, be32_to_cpu(agi->agi_newino), XFS_LOOKUP_EQ, &i); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 8a37efe..4e30448 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -1539,14 +1539,11 @@ xfs_iext_realloc_indirect( xfs_ifork_t *ifp, /* inode fork pointer */ int new_size) /* new indirection array size */ { - int nlists; /* number of irec's (ex lists) */ - int size; /* current indirection array size */ - ASSERT(ifp->if_flags & XFS_IFEXTIREC); - nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - size = nlists * sizeof(xfs_ext_irec_t); ASSERT(ifp->if_real_bytes); - ASSERT((new_size >= 0) && (new_size != size)); + ASSERT((new_size >= 0) && + (new_size != ((ifp->if_real_bytes / XFS_IEXT_BUFSZ) * + sizeof(xfs_ext_irec_t)))); if (new_size == 0) { xfs_iext_destroy(ifp); } else { diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index 083cdd6..ce6958b 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -270,6 +270,7 @@ typedef struct xfs_inode_log_format { __uint32_t ilf_fields; /* flags for fields logged */ __uint16_t ilf_asize; /* size of attr d/ext/root */ __uint16_t ilf_dsize; /* size of data/ext/root */ + __uint32_t ilf_pad; /* pad for 64 bit boundary */ __uint64_t ilf_ino; /* inode number */ union { __uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -280,29 +281,17 @@ typedef struct xfs_inode_log_format { __int32_t ilf_boffset; /* off of inode in buffer */ } xfs_inode_log_format_t; -typedef struct xfs_inode_log_format_32 { - __uint16_t ilf_type; /* inode log item type */ - __uint16_t ilf_size; /* size of this item */ - __uint32_t ilf_fields; /* flags for fields logged */ - __uint16_t ilf_asize; /* size of attr d/ext/root */ - __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint64_t ilf_ino; /* inode number */ - union { - __uint32_t ilfu_rdev; /* rdev value for dev inode*/ - uuid_t ilfu_uuid; /* mount point value */ - } ilf_u; - __int64_t ilf_blkno; /* blkno of inode buffer */ - __int32_t ilf_len; /* len of inode buffer */ - __int32_t ilf_boffset; /* off of inode in buffer */ -} __attribute__((packed)) xfs_inode_log_format_32_t; - -typedef struct xfs_inode_log_format_64 { +/* + * Old 32 bit systems will log in this format without the 64 bit + * alignment padding. Recovery will detect this and convert it to the + * correct format. + */ +struct xfs_inode_log_format_32 { __uint16_t ilf_type; /* inode log item type */ __uint16_t ilf_size; /* size of this item */ __uint32_t ilf_fields; /* flags for fields logged */ __uint16_t ilf_asize; /* size of attr d/ext/root */ __uint16_t ilf_dsize; /* size of data/ext/root */ - __uint32_t ilf_pad; /* pad for 64 bit boundary */ __uint64_t ilf_ino; /* inode number */ union { __uint32_t ilfu_rdev; /* rdev value for dev inode*/ @@ -311,7 +300,7 @@ typedef struct xfs_inode_log_format_64 { __int64_t ilf_blkno; /* blkno of inode buffer */ __int32_t ilf_len; /* len of inode buffer */ __int32_t ilf_boffset; /* off of inode in buffer */ -} xfs_inode_log_format_64_t; +} __attribute__((packed)); /* diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 82a38d8..d71cb63 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -784,14 +784,6 @@ xfs_refcount_merge_extents( } /* - * While we're adjusting the refcounts records of an extent, we have - * to keep an eye on the number of extents we're dirtying -- run too - * many in a single transaction and we'll exceed the transaction's - * reservation and crash the fs. Each record adds 12 bytes to the - * log (plus any key updates) so we'll conservatively assume 24 bytes - * per record. We must also leave space for btree splits on both ends - * of the range and space for the CUD and a new CUI. - * * XXX: This is a pretty hand-wavy estimate. The penalty for guessing * true incorrectly is a shutdown FS; the penalty for guessing false * incorrectly is more transaction rolls than might be necessary. @@ -822,7 +814,7 @@ xfs_refcount_still_have_space( else if (overhead > cur->bc_tp->t_log_res) return false; return cur->bc_tp->t_log_res - overhead > - cur->bc_private.a.priv.refc.nr_ops * 32; + cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD; } /* @@ -1648,6 +1640,10 @@ xfs_refcount_recover_cow_leftovers( error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); if (error) goto out_trans; + if (!agbp) { + error = -ENOMEM; + goto out_trans; + } cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); /* Find all the leftover CoW staging extents. */ diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index 098dc66..eafb9d1 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp, extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, xfs_agnumber_t agno); +/* + * While we're adjusting the refcounts records of an extent, we have + * to keep an eye on the number of extents we're dirtying -- run too + * many in a single transaction and we'll exceed the transaction's + * reservation and crash the fs. Each record adds 12 bytes to the + * log (plus any key updates) so we'll conservatively assume 32 bytes + * per record. We must also leave space for btree splits on both ends + * of the range and space for the CUD and a new CUI. + */ +#define XFS_REFCOUNT_ITEM_OVERHEAD 32 + +static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res) +{ + return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD; +} + #endif /* __XFS_REFCOUNT_H__ */ diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index b468e04..3354140 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -170,8 +170,8 @@ xfs_get_acl(struct inode *inode, int type) return acl; } -STATIC int -__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl) +int +__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { struct xfs_inode *ip = XFS_I(inode); unsigned char *ea_name; @@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode) int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) { + umode_t mode; + bool set_mode = false; int error = 0; if (!acl) @@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type) return error; if (type == ACL_TYPE_ACCESS) { - umode_t mode; - error = posix_acl_update_mode(inode, &mode, &acl); if (error) return error; - error = xfs_set_mode(inode, mode); - if (error) - return error; + set_mode = true; } set_acl: - return __xfs_set_acl(inode, type, acl); + error = __xfs_set_acl(inode, acl, type); + if (error) + return error; + + /* + * We set the mode after successfully updating the ACL xattr because the + * xattr update can fail at ENOSPC and we don't want to change the mode + * if the ACL update hasn't been applied. + */ + if (set_mode) + error = xfs_set_mode(inode, mode); + + return error; } diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h index 286fa89..0432731 100644 --- a/fs/xfs/xfs_acl.h +++ b/fs/xfs/xfs_acl.h @@ -24,6 +24,7 @@ struct posix_acl; #ifdef CONFIG_XFS_POSIX_ACL extern struct posix_acl *xfs_get_acl(struct inode *inode, int type); extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type); #else static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type) { diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 5789814..d31cd1e 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -90,11 +90,11 @@ xfs_find_bdev_for_inode( * associated buffer_heads, paying attention to the start and end offsets that * we need to process on the page. * - * Landmine Warning: bh->b_end_io() will call end_page_writeback() on the last - * buffer in the IO. Once it does this, it is unsafe to access the bufferhead or - * the page at all, as we may be racing with memory reclaim and it can free both - * the bufferhead chain and the page as it will see the page as clean and - * unused. + * Note that we open code the action in end_buffer_async_write here so that we + * only have to iterate over the buffers attached to the page once. This is not + * only more efficient, but also ensures that we only calls end_page_writeback + * at the end of the iteration, and thus avoids the pitfall of having the page + * and buffers potentially freed after every call to end_buffer_async_write. */ static void xfs_finish_page_writeback( @@ -102,29 +102,45 @@ xfs_finish_page_writeback( struct bio_vec *bvec, int error) { - unsigned int end = bvec->bv_offset + bvec->bv_len - 1; - struct buffer_head *head, *bh, *next; + struct buffer_head *head = page_buffers(bvec->bv_page), *bh = head; + bool busy = false; unsigned int off = 0; - unsigned int bsize; + unsigned long flags; ASSERT(bvec->bv_offset < PAGE_SIZE); ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0); - ASSERT(end < PAGE_SIZE); + ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE); ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); - bh = head = page_buffers(bvec->bv_page); - - bsize = bh->b_size; + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &head->b_state); do { - if (off > end) - break; - next = bh->b_this_page; - if (off < bvec->bv_offset) - goto next_bh; - bh->b_end_io(bh, !error); -next_bh: - off += bsize; - } while ((bh = next) != head); + if (off >= bvec->bv_offset && + off < bvec->bv_offset + bvec->bv_len) { + ASSERT(buffer_async_write(bh)); + ASSERT(bh->b_end_io == NULL); + + if (error) { + mapping_set_error(bvec->bv_page->mapping, -EIO); + set_buffer_write_io_error(bh); + clear_buffer_uptodate(bh); + SetPageError(bvec->bv_page); + } else { + set_buffer_uptodate(bh); + } + clear_buffer_async_write(bh); + unlock_buffer(bh); + } else if (buffer_async_write(bh)) { + ASSERT(buffer_locked(bh)); + busy = true; + } + off += bh->b_size; + } while ((bh = bh->b_this_page) != head); + bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); + local_irq_restore(flags); + + if (!busy) + end_page_writeback(bvec->bv_page); } /* @@ -138,8 +154,10 @@ xfs_destroy_ioend( int error) { struct inode *inode = ioend->io_inode; - struct bio *last = ioend->io_bio; - struct bio *bio, *next; + struct bio *bio = &ioend->io_inline_bio; + struct bio *last = ioend->io_bio, *next; + u64 start = bio->bi_iter.bi_sector; + bool quiet = bio_flagged(bio, BIO_QUIET); for (bio = &ioend->io_inline_bio; bio; bio = next) { struct bio_vec *bvec; @@ -160,6 +178,11 @@ xfs_destroy_ioend( bio_put(bio); } + + if (unlikely(error && !quiet)) { + xfs_err_ratelimited(XFS_I(inode)->i_mount, + "writeback error on sector %llu", start); + } } /* @@ -312,7 +335,8 @@ xfs_end_io( error = xfs_reflink_end_cow(ip, offset, size); break; case XFS_IO_UNWRITTEN: - error = xfs_iomap_write_unwritten(ip, offset, size); + /* writeback should never update isize */ + error = xfs_iomap_write_unwritten(ip, offset, size, false); break; default: ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans); @@ -414,6 +438,19 @@ xfs_imap_valid( { offset >>= inode->i_blkbits; + /* + * We have to make sure the cached mapping is within EOF to protect + * against eofblocks trimming on file release leaving us with a stale + * mapping. Otherwise, a page for a subsequent file extending buffered + * write could get picked up by this writeback cycle and written to the + * wrong blocks. + * + * Note that what we really want here is a generic mapping invalidation + * mechanism to protect us from arbitrary extent modifying contexts, not + * just eofblocks. + */ + xfs_trim_extent_eof(imap, XFS_I(inode)); + return offset >= imap->br_startoff && offset < imap->br_startoff + imap->br_blockcount; } @@ -427,7 +464,8 @@ xfs_start_buffer_writeback( ASSERT(!buffer_delay(bh)); ASSERT(!buffer_unwritten(bh)); - mark_buffer_async_write(bh); + bh->b_end_io = NULL; + set_buffer_async_write(bh); set_buffer_uptodate(bh); clear_buffer_dirty(bh); } @@ -701,6 +739,14 @@ xfs_vm_invalidatepage( { trace_xfs_invalidatepage(page->mapping->host, page, offset, length); + + /* + * If we are invalidating the entire page, clear the dirty state from it + * so that we can check for attempts to release dirty cached pages in + * xfs_vm_releasepage(). + */ + if (offset == 0 && length >= PAGE_SIZE) + cancel_dirty_page(page); block_invalidatepage(page, offset, length); } @@ -1156,25 +1202,27 @@ xfs_vm_releasepage( * mm accommodates an old ext3 case where clean pages might not have had * the dirty bit cleared. Thus, it can send actual dirty pages to * ->releasepage() via shrink_active_list(). Conversely, - * block_invalidatepage() can send pages that are still marked dirty - * but otherwise have invalidated buffers. + * block_invalidatepage() can send pages that are still marked dirty but + * otherwise have invalidated buffers. * * We want to release the latter to avoid unnecessary buildup of the - * LRU, skip the former and warn if we've left any lingering - * delalloc/unwritten buffers on clean pages. Skip pages with delalloc - * or unwritten buffers and warn if the page is not dirty. Otherwise - * try to release the buffers. + * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages + * that are entirely invalidated and need to be released. Hence the + * only time we should get dirty pages here is through + * shrink_active_list() and so we can simply skip those now. + * + * warn if we've left any lingering delalloc/unwritten buffers on clean + * or invalidated pages we are about to release. */ + if (PageDirty(page)) + return 0; + xfs_count_page_state(page, &delalloc, &unwritten); - if (delalloc) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(delalloc)) return 0; - } - if (unwritten) { - WARN_ON_ONCE(!PageDirty(page)); + if (WARN_ON_ONCE(unwritten)) return 0; - } return try_to_free_buffers(page); } @@ -1508,6 +1556,21 @@ xfs_end_io_direct_write( return 0; } + if (flags & XFS_DIO_FLAG_COW) + error = xfs_reflink_end_cow(ip, offset, size); + + /* + * Unwritten conversion updates the in-core isize after extent + * conversion but before updating the on-disk size. Updating isize any + * earlier allows a racing dio read to find unwritten extents before + * they are converted. + */ + if (flags & XFS_DIO_FLAG_UNWRITTEN) { + trace_xfs_end_io_direct_write_unwritten(ip, offset, size); + + return xfs_iomap_write_unwritten(ip, offset, size, true); + } + /* * We need to update the in-core inode size here so that we don't end up * with the on-disk inode size being outside the in-core inode size. We @@ -1524,13 +1587,6 @@ xfs_end_io_direct_write( i_size_write(inode, offset + size); spin_unlock(&ip->i_flags_lock); - if (flags & XFS_DIO_FLAG_COW) - error = xfs_reflink_end_cow(ip, offset, size); - if (flags & XFS_DIO_FLAG_UNWRITTEN) { - trace_xfs_end_io_direct_write_unwritten(ip, offset, size); - - error = xfs_iomap_write_unwritten(ip, offset, size); - } if (flags & XFS_DIO_FLAG_APPEND) { trace_xfs_end_io_direct_write_append(ip, offset, size); @@ -1566,9 +1622,12 @@ xfs_vm_bmap( * The swap code (ab-)uses ->bmap to get a block mapping and then * bypasseѕ the file system for actual I/O. We really can't allow * that on reflinks inodes, so we have to skip out here. And yes, - * 0 is the magic code for a bmap error.. + * 0 is the magic code for a bmap error. + * + * Since we don't pass back blockdev info, we can't return bmap + * information for rt files either. */ - if (xfs_is_reflink_inode(ip)) { + if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip)) { xfs_iunlock(ip, XFS_IOLOCK_SHARED); return 0; } diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c index be0b79d..c664300 100644 --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -302,6 +302,8 @@ xfs_attr3_node_inactive( &bp, XFS_ATTR_FORK); if (error) return error; + node = bp->b_addr; + btree = dp->d_ops->node_tree_p(node); child_fsb = be32_to_cpu(btree[i + 1].before); xfs_trans_brelse(*trans, bp); } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index c4b90e7..5a54dcd 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -395,6 +395,7 @@ xfs_bui_recover( struct xfs_map_extent *bmap; xfs_fsblock_t startblock_fsb; xfs_fsblock_t inode_fsb; + xfs_filblks_t count; bool op_ok; struct xfs_bud_log_item *budp; enum xfs_bmap_intent_type type; @@ -403,6 +404,7 @@ xfs_bui_recover( struct xfs_trans *tp; struct xfs_inode *ip = NULL; struct xfs_defer_ops dfops; + struct xfs_bmbt_irec irec; xfs_fsblock_t firstfsb; ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags)); @@ -480,13 +482,24 @@ xfs_bui_recover( } xfs_trans_ijoin(tp, ip, 0); + count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type, ip, whichfork, bmap->me_startoff, - bmap->me_startblock, bmap->me_len, - state); + bmap->me_startblock, &count, state); if (error) goto err_dfops; + if (count > 0) { + ASSERT(type == XFS_BMAP_UNMAP); + irec.br_startblock = bmap->me_startblock; + irec.br_blockcount = count; + irec.br_startoff = bmap->me_startoff; + irec.br_state = state; + error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec); + if (error) + goto err_dfops; + } + /* Finish transaction, free inodes. */ error = xfs_defer_finish(&tp, &dfops, NULL); if (error) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 87b495e..cb62871 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -84,6 +84,7 @@ xfs_zero_extent( GFP_NOFS, true); } +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( struct xfs_bmalloca *ap) /* bmap alloc argument struct */ @@ -195,6 +196,7 @@ xfs_bmap_rtalloc( } return 0; } +#endif /* CONFIG_XFS_RT */ /* * Check if the endoff is outside the last extent. If so the caller will grow @@ -1445,7 +1447,19 @@ xfs_shift_file_space( return error; /* - * The extent shiting code works on extent granularity. So, if + * Clean out anything hanging around in the cow fork now that + * we've flushed all the dirty data out to disk to avoid having + * CoW extents at the wrong offsets. + */ + if (xfs_is_reflink_inode(ip)) { + error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF, + true); + if (error) + return error; + } + + /* + * The extent shifting code works on extent granularity. So, if * stop_fsb is not the starting block of extent, we need to split * the extent at stop_fsb. */ @@ -1825,29 +1839,18 @@ xfs_swap_extent_forks( } /* - * Before we've swapped the forks, lets set the owners of the forks - * appropriately. We have to do this as we are demand paging the btree - * buffers, and so the validation done on read will expect the owner - * field to be correctly set. Once we change the owners, we can swap the - * inode forks. + * Btree format (v3) inodes have the inode number stamped in the bmbt + * block headers. We can't start changing the bmbt blocks until the + * inode owner change is logged so recovery does the right thing in the + * event of a crash. Set the owner change log flags now and leave the + * bmbt scan as the last step. */ if (ip->i_d.di_version == 3 && - ip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + ip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*target_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, - tip->i_ino, NULL); - if (error) - return error; - } - if (tip->i_d.di_version == 3 && - tip->i_d.di_format == XFS_DINODE_FMT_BTREE) { + tip->i_d.di_format == XFS_DINODE_FMT_BTREE) (*src_log_flags) |= XFS_ILOG_DOWNER; - error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK, - ip->i_ino, NULL); - if (error) - return error; - } /* * Swap the data forks of the inodes @@ -1925,6 +1928,48 @@ xfs_swap_extent_forks( return 0; } +/* + * Fix up the owners of the bmbt blocks to refer to the current inode. The + * change owner scan attempts to order all modified buffers in the current + * transaction. In the event of ordered buffer failure, the offending buffer is + * physically logged as a fallback and the scan returns -EAGAIN. We must roll + * the transaction in this case to replenish the fallback log reservation and + * restart the scan. This process repeats until the scan completes. + */ +static int +xfs_swap_change_owner( + struct xfs_trans **tpp, + struct xfs_inode *ip, + struct xfs_inode *tmpip) +{ + int error; + struct xfs_trans *tp = *tpp; + + do { + error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino, + NULL); + /* success or fatal error */ + if (error != -EAGAIN) + break; + + error = xfs_trans_roll(tpp, NULL); + if (error) + break; + tp = *tpp; + + /* + * Redirty both inodes so they can relog and keep the log tail + * moving forward. + */ + xfs_trans_ijoin(tp, ip, 0); + xfs_trans_ijoin(tp, tmpip, 0); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE); + } while (true); + + return error; +} + int xfs_swap_extents( struct xfs_inode *ip, /* target inode */ @@ -1938,8 +1983,8 @@ xfs_swap_extents( int error = 0; int lock_flags; struct xfs_ifork *cowfp; - __uint64_t f; - int resblks; + uint64_t f; + int resblks = 0; /* * Lock the inodes against other IO, page faults and truncate to @@ -1987,11 +2032,8 @@ xfs_swap_extents( XFS_SWAP_RMAP_SPACE_RES(mp, XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK), XFS_DATA_FORK); - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, - 0, 0, &tp); - } else - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, - 0, 0, &tp); + } + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp); if (error) goto out_unlock; @@ -2066,17 +2108,54 @@ xfs_swap_extents( ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK; + } + + /* Swap the cow forks. */ + if (xfs_sb_version_hasreflink(&mp->m_sb)) { + xfs_extnum_t extnum; + + ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS); + ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS); + + extnum = ip->i_cnextents; + ip->i_cnextents = tip->i_cnextents; + tip->i_cnextents = extnum; + cowfp = ip->i_cowfp; ip->i_cowfp = tip->i_cowfp; tip->i_cowfp = cowfp; - xfs_inode_set_cowblocks_tag(ip); - xfs_inode_set_cowblocks_tag(tip); + + if (ip->i_cowfp && ip->i_cnextents) + xfs_inode_set_cowblocks_tag(ip); + else + xfs_inode_clear_cowblocks_tag(ip); + if (tip->i_cowfp && tip->i_cnextents) + xfs_inode_set_cowblocks_tag(tip); + else + xfs_inode_clear_cowblocks_tag(tip); } xfs_trans_log_inode(tp, ip, src_log_flags); xfs_trans_log_inode(tp, tip, target_log_flags); /* + * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems + * have inode number owner values in the bmbt blocks that still refer to + * the old inode. Scan each bmbt to fix up the owner values with the + * inode number of the current inode. + */ + if (src_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, ip, tip); + if (error) + goto out_trans_cancel; + } + if (target_log_flags & XFS_ILOG_DOWNER) { + error = xfs_swap_change_owner(&tp, tip, ip); + if (error) + goto out_trans_cancel; + } + + /* * If this is a synchronous mount, make sure that the * transaction goes to disk before returning to the user. */ diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index f100539..ce330f0 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -28,7 +28,20 @@ struct xfs_mount; struct xfs_trans; struct xfs_bmalloca; +#ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc(struct xfs_bmalloca *ap); +#else /* !CONFIG_XFS_RT */ +/* + * Attempts to allocate RT extents when RT is disable indicates corruption and + * should trigger a shutdown. + */ +static inline int +xfs_bmap_rtalloc(struct xfs_bmalloca *ap) +{ + return -EFSCORRUPTED; +} +#endif /* CONFIG_XFS_RT */ + int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff, int whichfork, int *eof); int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 1626927..eca7bae 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -116,7 +116,7 @@ static inline void __xfs_buf_ioacct_dec( struct xfs_buf *bp) { - ASSERT(spin_is_locked(&bp->b_lock)); + lockdep_assert_held(&bp->b_lock); if (bp->b_state & XFS_BSTATE_IN_FLIGHT) { bp->b_state &= ~XFS_BSTATE_IN_FLIGHT; @@ -2022,6 +2022,66 @@ xfs_buf_delwri_submit( return error; } +/* + * Push a single buffer on a delwri queue. + * + * The purpose of this function is to submit a single buffer of a delwri queue + * and return with the buffer still on the original queue. The waiting delwri + * buffer submission infrastructure guarantees transfer of the delwri queue + * buffer reference to a temporary wait list. We reuse this infrastructure to + * transfer the buffer back to the original queue. + * + * Note the buffer transitions from the queued state, to the submitted and wait + * listed state and back to the queued state during this call. The buffer + * locking and queue management logic between _delwri_pushbuf() and + * _delwri_queue() guarantee that the buffer cannot be queued to another list + * before returning. + */ +int +xfs_buf_delwri_pushbuf( + struct xfs_buf *bp, + struct list_head *buffer_list) +{ + LIST_HEAD (submit_list); + int error; + + ASSERT(bp->b_flags & _XBF_DELWRI_Q); + + trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_); + + /* + * Isolate the buffer to a new local list so we can submit it for I/O + * independently from the rest of the original list. + */ + xfs_buf_lock(bp); + list_move(&bp->b_list, &submit_list); + xfs_buf_unlock(bp); + + /* + * Delwri submission clears the DELWRI_Q buffer flag and returns with + * the buffer on the wait list with an associated reference. Rather than + * bounce the buffer from a local wait list back to the original list + * after I/O completion, reuse the original list as the wait list. + */ + xfs_buf_delwri_submit_buffers(&submit_list, buffer_list); + + /* + * The buffer is now under I/O and wait listed as during typical delwri + * submission. Lock the buffer to wait for I/O completion. Rather than + * remove the buffer from the wait list and release the reference, we + * want to return with the buffer queued to the original list. The + * buffer already sits on the original list with a wait list reference, + * however. If we let the queue inherit that wait list reference, all we + * need to do is reset the DELWRI_Q flag. + */ + xfs_buf_lock(bp); + error = bp->b_error; + bp->b_flags |= _XBF_DELWRI_Q; + xfs_buf_unlock(bp); + + return error; +} + int __init xfs_buf_init(void) { diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index ad514a8..f961b19 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -333,6 +333,7 @@ extern void xfs_buf_delwri_cancel(struct list_head *); extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *); extern int xfs_buf_delwri_submit(struct list_head *); extern int xfs_buf_delwri_submit_nowait(struct list_head *); +extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *); /* Buffer Daemon Setup Routines */ extern int xfs_buf_init(void); diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index 0306168..e0a0af0 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -29,6 +29,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_log.h" +#include "xfs_inode.h" kmem_zone_t *xfs_buf_item_zone; @@ -322,6 +323,8 @@ xfs_buf_item_format( ASSERT((bip->bli_flags & XFS_BLI_STALE) || (xfs_blft_from_flags(&bip->__bli_format) > XFS_BLFT_UNKNOWN_BUF && xfs_blft_from_flags(&bip->__bli_format) < XFS_BLFT_MAX_BUF)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED) || + (bip->bli_flags & XFS_BLI_STALE)); /* @@ -346,16 +349,6 @@ xfs_buf_item_format( bip->bli_flags &= ~XFS_BLI_INODE_BUF; } - if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) == - XFS_BLI_ORDERED) { - /* - * The buffer has been logged just to order it. It is not being - * included in the transaction commit, so don't format it. - */ - trace_xfs_buf_item_format_ordered(bip); - return; - } - for (i = 0; i < bip->bli_format_count; i++) { xfs_buf_item_format_segment(bip, lv, &vecp, offset, &bip->bli_formats[i]); @@ -574,26 +567,20 @@ xfs_buf_item_unlock( { struct xfs_buf_log_item *bip = BUF_ITEM(lip); struct xfs_buf *bp = bip->bli_buf; - bool clean; - bool aborted; - int flags; + bool aborted = !!(lip->li_flags & XFS_LI_ABORTED); + bool hold = !!(bip->bli_flags & XFS_BLI_HOLD); + bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY); +#if defined(DEBUG) || defined(XFS_WARN) + bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED); +#endif /* Clear the buffer's association with this transaction. */ bp->b_transp = NULL; /* - * If this is a transaction abort, don't return early. Instead, allow - * the brelse to happen. Normally it would be done for stale - * (cancelled) buffers at unpin time, but we'll never go through the - * pin/unpin cycle if we abort inside commit. - */ - aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false; - /* - * Before possibly freeing the buf item, copy the per-transaction state - * so we can reference it safely later after clearing it from the - * buffer log item. + * The per-transaction state has been copied above so clear it from the + * bli. */ - flags = bip->bli_flags; bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED); /* @@ -601,7 +588,7 @@ xfs_buf_item_unlock( * unlock the buffer and free the buf item when the buffer is unpinned * for the last time. */ - if (flags & XFS_BLI_STALE) { + if (bip->bli_flags & XFS_BLI_STALE) { trace_xfs_buf_item_unlock_stale(bip); ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL); if (!aborted) { @@ -619,40 +606,34 @@ xfs_buf_item_unlock( * regardless of whether it is dirty or not. A dirty abort implies a * shutdown, anyway. * - * Ordered buffers are dirty but may have no recorded changes, so ensure - * we only release clean items here. + * The bli dirty state should match whether the blf has logged segments + * except for ordered buffers, where only the bli should be dirty. */ - clean = (flags & XFS_BLI_DIRTY) ? false : true; - if (clean) { - int i; - for (i = 0; i < bip->bli_format_count; i++) { - if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, - bip->bli_formats[i].blf_map_size)) { - clean = false; - break; - } - } - } + ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) || + (ordered && dirty && !xfs_buf_item_dirty_format(bip))); /* * Clean buffers, by definition, cannot be in the AIL. However, aborted - * buffers may be dirty and hence in the AIL. Therefore if we are - * aborting a buffer and we've just taken the last refernce away, we - * have to check if it is in the AIL before freeing it. We need to free - * it in this case, because an aborted transaction has already shut the - * filesystem down and this is the last chance we will have to do so. + * buffers may be in the AIL regardless of dirty state. An aborted + * transaction that invalidates a buffer already in the AIL may have + * marked it stale and cleared the dirty state, for example. + * + * Therefore if we are aborting a buffer and we've just taken the last + * reference away, we have to check if it is in the AIL before freeing + * it. We need to free it in this case, because an aborted transaction + * has already shut the filesystem down and this is the last chance we + * will have to do so. */ if (atomic_dec_and_test(&bip->bli_refcount)) { - if (clean) - xfs_buf_item_relse(bp); - else if (aborted) { + if (aborted) { ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp)); xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR); xfs_buf_item_relse(bp); - } + } else if (!dirty) + xfs_buf_item_relse(bp); } - if (!(flags & XFS_BLI_HOLD)) + if (!hold) xfs_buf_relse(bp); } @@ -942,14 +923,22 @@ xfs_buf_item_log( /* - * Return 1 if the buffer has been logged or ordered in a transaction (at any - * point, not just the current transaction) and 0 if not. + * Return true if the buffer has any ranges logged/dirtied by a transaction, + * false otherwise. */ -uint -xfs_buf_item_dirty( - xfs_buf_log_item_t *bip) +bool +xfs_buf_item_dirty_format( + struct xfs_buf_log_item *bip) { - return (bip->bli_flags & XFS_BLI_DIRTY); + int i; + + for (i = 0; i < bip->bli_format_count; i++) { + if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map, + bip->bli_formats[i].blf_map_size)) + return true; + } + + return false; } STATIC void @@ -1051,6 +1040,31 @@ xfs_buf_do_callbacks( } } +/* + * Invoke the error state callback for each log item affected by the failed I/O. + * + * If a metadata buffer write fails with a non-permanent error, the buffer is + * eventually resubmitted and so the completion callbacks are not run. The error + * state may need to be propagated to the log items attached to the buffer, + * however, so the next AIL push of the item knows hot to handle it correctly. + */ +STATIC void +xfs_buf_do_callbacks_fail( + struct xfs_buf *bp) +{ + struct xfs_log_item *next; + struct xfs_log_item *lip = bp->b_fspriv; + struct xfs_ail *ailp = lip->li_ailp; + + spin_lock(&ailp->xa_lock); + for (; lip; lip = next) { + next = lip->li_bio_list; + if (lip->li_ops->iop_error) + lip->li_ops->iop_error(lip, bp); + } + spin_unlock(&ailp->xa_lock); +} + static bool xfs_buf_iodone_callback_error( struct xfs_buf *bp) @@ -1120,7 +1134,11 @@ xfs_buf_iodone_callback_error( if ((mp->m_flags & XFS_MOUNT_UNMOUNTING) && mp->m_fail_unmount) goto permanent_error; - /* still a transient error, higher layers will retry */ + /* + * Still a transient error, run IO completion failure callbacks and let + * the higher layers retry the buffer. + */ + xfs_buf_do_callbacks_fail(bp); xfs_buf_ioerror(bp, 0); xfs_buf_relse(bp); return true; @@ -1201,3 +1219,31 @@ xfs_buf_iodone( xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE); xfs_buf_item_free(BUF_ITEM(lip)); } + +/* + * Requeue a failed buffer for writeback + * + * Return true if the buffer has been re-queued properly, false otherwise + */ +bool +xfs_buf_resubmit_failed_buffers( + struct xfs_buf *bp, + struct xfs_log_item *lip, + struct list_head *buffer_list) +{ + struct xfs_log_item *next; + + /* + * Clear XFS_LI_FAILED flag from all items before resubmit + * + * XFS_LI_FAILED set/clear is protected by xa_lock, caller this + * function already have it acquired + */ + for (; lip; lip = next) { + next = lip->li_bio_list; + xfs_clear_li_failed(lip); + } + + /* Add this buffer back to the delayed write list */ + return xfs_buf_delwri_queue(bp, buffer_list); +} diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h index f7eba99..9690ce6 100644 --- a/fs/xfs/xfs_buf_item.h +++ b/fs/xfs/xfs_buf_item.h @@ -64,12 +64,15 @@ typedef struct xfs_buf_log_item { int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *); void xfs_buf_item_relse(struct xfs_buf *); void xfs_buf_item_log(xfs_buf_log_item_t *, uint, uint); -uint xfs_buf_item_dirty(xfs_buf_log_item_t *); +bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *); void xfs_buf_attach_iodone(struct xfs_buf *, void(*)(struct xfs_buf *, xfs_log_item_t *), xfs_log_item_t *); void xfs_buf_iodone_callbacks(struct xfs_buf *); void xfs_buf_iodone(struct xfs_buf *, struct xfs_log_item *); +bool xfs_buf_resubmit_failed_buffers(struct xfs_buf *, + struct xfs_log_item *, + struct list_head *); extern kmem_zone_t *xfs_buf_item_zone; diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index ed7ee4e..bcf7297 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -167,7 +167,7 @@ xfs_verifier_error( { struct xfs_mount *mp = bp->b_target->bt_mount; - xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx", + xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx", bp->b_error == -EFSBADCRC ? "CRC error" : "corruption", __return_address, bp->b_ops->name, bp->b_bn); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index df206cf..362c6b4 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -92,7 +92,7 @@ xfs_zero_range( xfs_off_t count, bool *did_zero) { - return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops); + return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops); } int @@ -729,6 +729,7 @@ write_retry: xfs_rw_iunlock(ip, iolock); eofb.eof_flags = XFS_EOF_FLAGS_SYNC; xfs_icache_free_eofblocks(ip->i_mount, &eofb); + xfs_icache_free_cowblocks(ip->i_mount, &eofb); goto write_retry; } @@ -1139,29 +1140,8 @@ xfs_find_get_desired_pgoff( want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); - /* - * No page mapped into given range. If we are searching holes - * and if this is the first time we got into the loop, it means - * that the given offset is landed in a hole, return it. - * - * If we have already stepped through some block buffers to find - * holes but they all contains data. In this case, the last - * offset is already updated and pointed to the end of the last - * mapped page, if it does not reach the endpoint to search, - * that means there should be a hole between them. - */ - if (nr_pages == 0) { - /* Data search found nothing */ - if (type == DATA_OFF) - break; - - ASSERT(type == HOLE_OFF); - if (lastoff == startoff || lastoff < endoff) { - found = true; - *offset = lastoff; - } + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1227,21 +1207,20 @@ xfs_find_get_desired_pgoff( /* * The number of returned pages less than our desired, search - * done. In this case, nothing was found for searching data, - * but we found a hole behind the last offset. + * done. */ - if (nr_pages < want) { - if (type == HOLE_OFF) { - *offset = lastoff; - found = true; - } + if (nr_pages < want) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + /* No page at lastoff and we are not done - we found a hole. */ + if (type == HOLE_OFF && lastoff < endoff) { + *offset = lastoff; + found = true; + } out: pagevec_release(&pvec); return found; diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 74304b6..86a4911 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -66,7 +66,6 @@ xfs_inode_alloc( XFS_STATS_INC(mp, vn_active); ASSERT(atomic_read(&ip->i_pincount) == 0); - ASSERT(!spin_is_locked(&ip->i_flags_lock)); ASSERT(!xfs_isiflocked(ip)); ASSERT(ip->i_ino == 0); @@ -192,7 +191,7 @@ xfs_perag_set_reclaim_tag( { struct xfs_mount *mp = pag->pag_mount; - ASSERT(spin_is_locked(&pag->pag_ici_lock)); + lockdep_assert_held(&pag->pag_ici_lock); if (pag->pag_ici_reclaimable++) return; @@ -214,7 +213,7 @@ xfs_perag_clear_reclaim_tag( { struct xfs_mount *mp = pag->pag_mount; - ASSERT(spin_is_locked(&pag->pag_ici_lock)); + lockdep_assert_held(&pag->pag_ici_lock); if (--pag->pag_ici_reclaimable) return; @@ -1079,11 +1078,11 @@ reclaim: * Because we use RCU freeing we need to ensure the inode always appears * to be reclaimed with an invalid inode number when in the free state. * We do this as early as possible under the ILOCK so that - * xfs_iflush_cluster() can be guaranteed to detect races with us here. - * By doing this, we guarantee that once xfs_iflush_cluster has locked - * XFS_ILOCK that it will see either a valid, flushable inode that will - * serialise correctly, or it will see a clean (and invalid) inode that - * it can skip. + * xfs_iflush_cluster() and xfs_ifree_cluster() can be guaranteed to + * detect races with us here. By doing this, we guarantee that once + * xfs_iflush_cluster() or xfs_ifree_cluster() has locked XFS_ILOCK that + * it will see either a valid inode that will serialise correctly, or it + * will see an invalid inode that it can skip. */ spin_lock(&ip->i_flags_lock); ip->i_flags = XFS_IRECLAIM; diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 7a0b4ee..fe9a9a1 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -881,7 +881,6 @@ xfs_ialloc( case S_IFREG: case S_IFDIR: if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) { - uint64_t di_flags2 = 0; uint di_flags = 0; if (S_ISDIR(mode)) { @@ -918,20 +917,23 @@ xfs_ialloc( di_flags |= XFS_DIFLAG_NODEFRAG; if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM) di_flags |= XFS_DIFLAG_FILESTREAM; - if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) - di_flags2 |= XFS_DIFLAG2_DAX; ip->i_d.di_flags |= di_flags; - ip->i_d.di_flags2 |= di_flags2; } if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) && pip->i_d.di_version == 3 && ip->i_d.di_version == 3) { + uint64_t di_flags2 = 0; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) { - ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; ip->i_d.di_cowextsize = pip->i_d.di_cowextsize; } + if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) + di_flags2 |= XFS_DIFLAG2_DAX; + + ip->i_d.di_flags2 |= di_flags2; } /* FALLTHROUGH */ case S_IFLNK: @@ -1630,10 +1632,12 @@ xfs_itruncate_extents( goto out; /* - * Clear the reflink flag if we truncated everything. + * Clear the reflink flag if there are no data fork blocks and + * there are no extents staged in the cow fork. */ - if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) { - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { + if (ip->i_d.di_nblocks == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; xfs_inode_clear_cowblocks_tag(ip); } @@ -2366,11 +2370,24 @@ retry: * already marked stale. If we can't lock it, back off * and retry. */ - if (ip != free_ip && - !xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { - rcu_read_unlock(); - delay(1); - goto retry; + if (ip != free_ip) { + if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) { + rcu_read_unlock(); + delay(1); + goto retry; + } + + /* + * Check the inode number again in case we're + * racing with freeing in xfs_reclaim_inode(). + * See the comments in that function for more + * information as to why the initial check is + * not sufficient. + */ + if (ip->i_ino != inum + i) { + xfs_iunlock(ip, XFS_ILOCK_EXCL); + continue; + } } rcu_read_unlock(); diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c index d90e781..d0a3c4b 100644 --- a/fs/xfs/xfs_inode_item.c +++ b/fs/xfs/xfs_inode_item.c @@ -27,6 +27,7 @@ #include "xfs_error.h" #include "xfs_trace.h" #include "xfs_trans_priv.h" +#include "xfs_buf_item.h" #include "xfs_log.h" @@ -363,6 +364,9 @@ xfs_inode_to_log_dinode( to->di_dmstate = from->di_dmstate; to->di_flags = from->di_flags; + /* log a dummy value to ensure log structure is fully initialised */ + to->di_next_unlinked = NULLAGINO; + if (from->di_version == 3) { to->di_changecount = inode->i_version; to->di_crtime.t_sec = from->di_crtime.t_sec; @@ -403,6 +407,11 @@ xfs_inode_item_format_core( * the second with the on-disk inode structure, and a possible third and/or * fourth with the inode data/extents/b-tree root and inode attributes * data/extents/b-tree root. + * + * Note: Always use the 64 bit inode log format structure so we don't + * leave an uninitialised hole in the format item on 64 bit systems. Log + * recovery on 32 bit systems handles this just fine, so there's no reason + * for not using an initialising the properly padded structure all the time. */ STATIC void xfs_inode_item_format( @@ -411,8 +420,8 @@ xfs_inode_item_format( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_inode_log_format *ilf; struct xfs_log_iovec *vecp = NULL; + struct xfs_inode_log_format *ilf; ASSERT(ip->i_d.di_version > 1); @@ -424,7 +433,17 @@ xfs_inode_item_format( ilf->ilf_boffset = ip->i_imap.im_boffset; ilf->ilf_fields = XFS_ILOG_CORE; ilf->ilf_size = 2; /* format + core */ - xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format)); + + /* + * make sure we don't leak uninitialised data into the log in the case + * when we don't log every field in the inode. + */ + ilf->ilf_dsize = 0; + ilf->ilf_asize = 0; + ilf->ilf_pad = 0; + memset(&ilf->ilf_u.ilfu_uuid, 0, sizeof(ilf->ilf_u.ilfu_uuid)); + + xlog_finish_iovec(lv, vecp, sizeof(*ilf)); xfs_inode_item_format_core(ip, lv, &vecp); xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp); @@ -475,6 +494,23 @@ xfs_inode_item_unpin( wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT); } +/* + * Callback used to mark a buffer with XFS_LI_FAILED when items in the buffer + * have been failed during writeback + * + * This informs the AIL that the inode is already flush locked on the next push, + * and acquires a hold on the buffer to ensure that it isn't reclaimed before + * dirty data makes it to disk. + */ +STATIC void +xfs_inode_item_error( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + ASSERT(xfs_isiflocked(INODE_ITEM(lip)->ili_inode)); + xfs_set_li_failed(lip, bp); +} + STATIC uint xfs_inode_item_push( struct xfs_log_item *lip, @@ -484,13 +520,28 @@ xfs_inode_item_push( { struct xfs_inode_log_item *iip = INODE_ITEM(lip); struct xfs_inode *ip = iip->ili_inode; - struct xfs_buf *bp = NULL; + struct xfs_buf *bp = lip->li_buf; uint rval = XFS_ITEM_SUCCESS; int error; if (xfs_ipincount(ip) > 0) return XFS_ITEM_PINNED; + /* + * The buffer containing this item failed to be written back + * previously. Resubmit the buffer for IO. + */ + if (lip->li_flags & XFS_LI_FAILED) { + if (!xfs_buf_trylock(bp)) + return XFS_ITEM_LOCKED; + + if (!xfs_buf_resubmit_failed_buffers(bp, lip, buffer_list)) + rval = XFS_ITEM_FLUSHING; + + xfs_buf_unlock(bp); + return rval; + } + if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) return XFS_ITEM_LOCKED; @@ -622,7 +673,8 @@ static const struct xfs_item_ops xfs_inode_item_ops = { .iop_unlock = xfs_inode_item_unlock, .iop_committed = xfs_inode_item_committed, .iop_push = xfs_inode_item_push, - .iop_committing = xfs_inode_item_committing + .iop_committing = xfs_inode_item_committing, + .iop_error = xfs_inode_item_error }; @@ -710,7 +762,8 @@ xfs_iflush_done( * the AIL lock. */ iip = INODE_ITEM(blip); - if (iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) || + (blip->li_flags & XFS_LI_FAILED)) need_ail++; blip = next; @@ -718,7 +771,8 @@ xfs_iflush_done( /* make sure we capture the state of the initial inode. */ iip = INODE_ITEM(lip); - if (iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) + if ((iip->ili_logged && lip->li_lsn == iip->ili_flush_lsn) || + lip->li_flags & XFS_LI_FAILED) need_ail++; /* @@ -731,22 +785,30 @@ xfs_iflush_done( * holding the lock before removing the inode from the AIL. */ if (need_ail) { - struct xfs_log_item *log_items[need_ail]; - int i = 0; + bool mlip_changed = false; + + /* this is an opencoded batch version of xfs_trans_ail_delete */ spin_lock(&ailp->xa_lock); for (blip = lip; blip; blip = blip->li_bio_list) { - iip = INODE_ITEM(blip); - if (iip->ili_logged && - blip->li_lsn == iip->ili_flush_lsn) { - log_items[i++] = blip; + if (INODE_ITEM(blip)->ili_logged && + blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) + mlip_changed |= xfs_ail_delete_one(ailp, blip); + else { + xfs_clear_li_failed(blip); } - ASSERT(i <= need_ail); } - /* xfs_trans_ail_delete_bulk() drops the AIL lock. */ - xfs_trans_ail_delete_bulk(ailp, log_items, i, - SHUTDOWN_CORRUPT_INCORE); - } + if (mlip_changed) { + if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) + xlog_assign_tail_lsn_locked(ailp->xa_mount); + if (list_empty(&ailp->xa_ail)) + wake_up_all(&ailp->xa_empty); + } + spin_unlock(&ailp->xa_lock); + + if (mlip_changed) + xfs_log_space_wake(ailp->xa_mount); + } /* * clean up and unlock the flush lock now we are done. We can clear the @@ -811,48 +873,30 @@ xfs_istale_done( } /* - * convert an xfs_inode_log_format struct from either 32 or 64 bit versions - * (which can have different field alignments) to the native version + * convert an xfs_inode_log_format struct from the old 32 bit version + * (which can have different field alignments) to the native 64 bit version */ int xfs_inode_item_format_convert( - xfs_log_iovec_t *buf, - xfs_inode_log_format_t *in_f) + struct xfs_log_iovec *buf, + struct xfs_inode_log_format *in_f) { - if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) { - xfs_inode_log_format_32_t *in_f32 = buf->i_addr; - - in_f->ilf_type = in_f32->ilf_type; - in_f->ilf_size = in_f32->ilf_size; - in_f->ilf_fields = in_f32->ilf_fields; - in_f->ilf_asize = in_f32->ilf_asize; - in_f->ilf_dsize = in_f32->ilf_dsize; - in_f->ilf_ino = in_f32->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f32->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f32->ilf_blkno; - in_f->ilf_len = in_f32->ilf_len; - in_f->ilf_boffset = in_f32->ilf_boffset; - return 0; - } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){ - xfs_inode_log_format_64_t *in_f64 = buf->i_addr; - - in_f->ilf_type = in_f64->ilf_type; - in_f->ilf_size = in_f64->ilf_size; - in_f->ilf_fields = in_f64->ilf_fields; - in_f->ilf_asize = in_f64->ilf_asize; - in_f->ilf_dsize = in_f64->ilf_dsize; - in_f->ilf_ino = in_f64->ilf_ino; - /* copy biggest field of ilf_u */ - memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, - in_f64->ilf_u.ilfu_uuid.__u_bits, - sizeof(uuid_t)); - in_f->ilf_blkno = in_f64->ilf_blkno; - in_f->ilf_len = in_f64->ilf_len; - in_f->ilf_boffset = in_f64->ilf_boffset; - return 0; - } - return -EFSCORRUPTED; + struct xfs_inode_log_format_32 *in_f32 = buf->i_addr; + + if (buf->i_len != sizeof(*in_f32)) + return -EFSCORRUPTED; + + in_f->ilf_type = in_f32->ilf_type; + in_f->ilf_size = in_f32->ilf_size; + in_f->ilf_fields = in_f32->ilf_fields; + in_f->ilf_asize = in_f32->ilf_asize; + in_f->ilf_dsize = in_f32->ilf_dsize; + in_f->ilf_ino = in_f32->ilf_ino; + /* copy biggest field of ilf_u */ + memcpy(in_f->ilf_u.ilfu_uuid.__u_bits, + in_f32->ilf_u.ilfu_uuid.__u_bits, sizeof(uuid_t)); + in_f->ilf_blkno = in_f32->ilf_blkno; + in_f->ilf_len = in_f32->ilf_len; + in_f->ilf_boffset = in_f32->ilf_boffset; + return 0; } diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 73cfc71..6c95812 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -928,16 +928,15 @@ xfs_ioc_fsgetxattr( return 0; } -STATIC void -xfs_set_diflags( +STATIC uint16_t +xfs_flags2diflags( struct xfs_inode *ip, unsigned int xflags) { - unsigned int di_flags; - uint64_t di_flags2; - /* can't set PREALLOC this way, just preserve it */ - di_flags = (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + uint16_t di_flags = + (ip->i_d.di_flags & XFS_DIFLAG_PREALLOC); + if (xflags & FS_XFLAG_IMMUTABLE) di_flags |= XFS_DIFLAG_IMMUTABLE; if (xflags & FS_XFLAG_APPEND) @@ -967,19 +966,24 @@ xfs_set_diflags( if (xflags & FS_XFLAG_EXTSIZE) di_flags |= XFS_DIFLAG_EXTSIZE; } - ip->i_d.di_flags = di_flags; - /* diflags2 only valid for v3 inodes. */ - if (ip->i_d.di_version < 3) - return; + return di_flags; +} + +STATIC uint64_t +xfs_flags2diflags2( + struct xfs_inode *ip, + unsigned int xflags) +{ + uint64_t di_flags2 = + (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); - di_flags2 = (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK); if (xflags & FS_XFLAG_DAX) di_flags2 |= XFS_DIFLAG2_DAX; if (xflags & FS_XFLAG_COWEXTSIZE) di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; - ip->i_d.di_flags2 = di_flags2; + return di_flags2; } STATIC void @@ -1005,11 +1009,12 @@ xfs_diflags_to_linux( inode->i_flags |= S_NOATIME; else inode->i_flags &= ~S_NOATIME; +#if 0 /* disabled until the flag switching races are sorted out */ if (xflags & FS_XFLAG_DAX) inode->i_flags |= S_DAX; else inode->i_flags &= ~S_DAX; - +#endif } static int @@ -1019,6 +1024,7 @@ xfs_ioctl_setattr_xflags( struct fsxattr *fa) { struct xfs_mount *mp = ip->i_mount; + uint64_t di_flags2; /* Can't change realtime flag if any extents are allocated. */ if ((ip->i_d.di_nextents || ip->i_delayed_blks) && @@ -1049,7 +1055,14 @@ xfs_ioctl_setattr_xflags( !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; - xfs_set_diflags(ip, fa->fsx_xflags); + /* diflags2 only valid for v3 inodes. */ + di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); + if (di_flags2 && ip->i_d.di_version < 3) + return -EINVAL; + + ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags); + ip->i_d.di_flags2 = di_flags2; + xfs_diflags_to_linux(ip); xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG); xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); @@ -1072,6 +1085,7 @@ xfs_ioctl_setattr_dax_invalidate( int *join_flags) { struct inode *inode = VFS_I(ip); + struct super_block *sb = inode->i_sb; int error; *join_flags = 0; @@ -1084,7 +1098,7 @@ xfs_ioctl_setattr_dax_invalidate( if (fa->fsx_xflags & FS_XFLAG_DAX) { if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; - if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE) + if (bdev_dax_supported(sb, sb->s_blocksize) < 0) return -EINVAL; } diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 65740d1..f286f63 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -836,7 +836,8 @@ int xfs_iomap_write_unwritten( xfs_inode_t *ip, xfs_off_t offset, - xfs_off_t count) + xfs_off_t count, + bool update_isize) { xfs_mount_t *mp = ip->i_mount; xfs_fileoff_t offset_fsb; @@ -847,6 +848,7 @@ xfs_iomap_write_unwritten( xfs_trans_t *tp; xfs_bmbt_irec_t imap; struct xfs_defer_ops dfops; + struct inode *inode = VFS_I(ip); xfs_fsize_t i_size; uint resblks; int error; @@ -906,7 +908,8 @@ xfs_iomap_write_unwritten( i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb); if (i_size > offset + count) i_size = offset + count; - + if (update_isize && i_size > i_size_read(inode)) + i_size_write(inode, i_size); i_size = xfs_new_eof(ip, i_size); if (i_size) { ip->i_d.di_size = i_size; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 6d45cf0..d71703a 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t, struct xfs_bmbt_irec *, int); int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t, struct xfs_bmbt_irec *); -int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t); +int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index f5e0f60..5b81f7f 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -190,12 +190,12 @@ xfs_generic_create( #ifdef CONFIG_XFS_POSIX_ACL if (default_acl) { - error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); + error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT); if (error) goto out_cleanup_inode; } if (acl) { - error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); + error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS); if (error) goto out_cleanup_inode; } @@ -802,7 +802,7 @@ xfs_vn_setattr_nonsize( * Caution: The caller of this function is responsible for calling * setattr_prepare() or otherwise verifying the change is fine. */ -int +STATIC int xfs_setattr_size( struct xfs_inode *ip, struct iattr *iattr) diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c index d8a77db..26d67ce 100644 --- a/fs/xfs/xfs_itable.c +++ b/fs/xfs/xfs_itable.c @@ -361,7 +361,6 @@ xfs_bulkstat( xfs_agino_t agino; /* inode # in allocation group */ xfs_agnumber_t agno; /* allocation group number */ xfs_btree_cur_t *cur; /* btree cursor for ialloc btree */ - size_t irbsize; /* size of irec buffer in bytes */ xfs_inobt_rec_incore_t *irbuf; /* start of irec buffer */ int nirbuf; /* size of irbuf */ int ubcount; /* size of user's buffer */ @@ -388,11 +387,10 @@ xfs_bulkstat( *ubcountp = 0; *done = 0; - irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4); + irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP); if (!irbuf) return -ENOMEM; - - nirbuf = irbsize / sizeof(*irbuf); + nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf); /* * Loop over the allocation groups, starting from the last diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index 1455b2520..3ebed16 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -363,7 +363,14 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y) #endif /* DEBUG */ #ifdef CONFIG_XFS_RT -#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) + +/* + * make sure we ignore the inode flag if the filesystem doesn't have a + * configured realtime device. + */ +#define XFS_IS_REALTIME_INODE(ip) \ + (((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) && \ + (ip)->i_mount->m_rtdev_targp) #else #define XFS_IS_REALTIME_INODE(ip) (0) #endif diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index b57ab34..33c9a3a 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -743,15 +743,45 @@ xfs_log_mount_finish( struct xfs_mount *mp) { int error = 0; + bool readonly = (mp->m_flags & XFS_MOUNT_RDONLY); if (mp->m_flags & XFS_MOUNT_NORECOVERY) { ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } else if (readonly) { + /* Allow unlinked processing to proceed */ + mp->m_flags &= ~XFS_MOUNT_RDONLY; } + /* + * During the second phase of log recovery, we need iget and + * iput to behave like they do for an active filesystem. + * xfs_fs_drop_inode needs to be able to prevent the deletion + * of inodes before we're done replaying log items on those + * inodes. Turn it off immediately after recovery finishes + * so that we don't leak the quota inodes if subsequent mount + * activities fail. + * + * We let all inodes involved in redo item processing end up on + * the LRU instead of being evicted immediately so that if we do + * something to an unlinked inode, the irele won't cause + * premature truncation and freeing of the inode, which results + * in log recovery failure. We have to evict the unreferenced + * lru inodes after clearing MS_ACTIVE because we don't + * otherwise clean up the lru if there's a subsequent failure in + * xfs_mountfs, which leads to us leaking the inodes if nothing + * else (e.g. quotacheck) references the inodes before the + * mount failure occurs. + */ + mp->m_super->s_flags |= MS_ACTIVE; error = xlog_recover_finish(mp->m_log); if (!error) xfs_log_work_queue(mp); + mp->m_super->s_flags &= ~MS_ACTIVE; + evict_inodes(mp->m_super); + + if (readonly) + mp->m_flags |= XFS_MOUNT_RDONLY; return error; } @@ -801,11 +831,14 @@ xfs_log_unmount_write(xfs_mount_t *mp) int error; /* - * Don't write out unmount record on read-only mounts. + * Don't write out unmount record on norecovery mounts or ro devices. * Or, if we are doing a forced umount (typically because of IO errors). */ - if (mp->m_flags & XFS_MOUNT_RDONLY) + if (mp->m_flags & XFS_MOUNT_NORECOVERY || + xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) { + ASSERT(mp->m_flags & XFS_MOUNT_RDONLY); return 0; + } error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL); ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log))); @@ -3304,8 +3337,6 @@ maybe_sleep: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - if (log_flushed) - *log_flushed = 1; } else { no_sleep: @@ -3409,8 +3440,6 @@ try_again: xlog_wait(&iclog->ic_prev->ic_write_wait, &log->l_icloglock); - if (log_flushed) - *log_flushed = 1; already_slept = 1; goto try_again; } @@ -3444,9 +3473,6 @@ try_again: */ if (iclog->ic_state & XLOG_STATE_IOERROR) return -EIO; - - if (log_flushed) - *log_flushed = 1; } else { /* just return */ spin_unlock(&log->l_icloglock); } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 9b3d7c7..0590926 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1029,61 +1029,106 @@ out_error: } /* - * Check the log tail for torn writes. This is required when torn writes are - * detected at the head and the head had to be walked back to a previous record. - * The tail of the previous record must now be verified to ensure the torn - * writes didn't corrupt the previous tail. + * Calculate distance from head to tail (i.e., unused space in the log). + */ +static inline int +xlog_tail_distance( + struct xlog *log, + xfs_daddr_t head_blk, + xfs_daddr_t tail_blk) +{ + if (head_blk < tail_blk) + return tail_blk - head_blk; + + return tail_blk + (log->l_logBBsize - head_blk); +} + +/* + * Verify the log tail. This is particularly important when torn or incomplete + * writes have been detected near the front of the log and the head has been + * walked back accordingly. * - * Return an error if CRC verification fails as recovery cannot proceed. + * We also have to handle the case where the tail was pinned and the head + * blocked behind the tail right before a crash. If the tail had been pushed + * immediately prior to the crash and the subsequent checkpoint was only + * partially written, it's possible it overwrote the last referenced tail in the + * log with garbage. This is not a coherency problem because the tail must have + * been pushed before it can be overwritten, but appears as log corruption to + * recovery because we have no way to know the tail was updated if the + * subsequent checkpoint didn't write successfully. + * + * Therefore, CRC check the log from tail to head. If a failure occurs and the + * offending record is within max iclog bufs from the head, walk the tail + * forward and retry until a valid tail is found or corruption is detected out + * of the range of a possible overwrite. */ STATIC int xlog_verify_tail( struct xlog *log, xfs_daddr_t head_blk, - xfs_daddr_t tail_blk) + xfs_daddr_t *tail_blk, + int hsize) { struct xlog_rec_header *thead; struct xfs_buf *bp; xfs_daddr_t first_bad; - int count; int error = 0; bool wrapped; - xfs_daddr_t tmp_head; + xfs_daddr_t tmp_tail; + xfs_daddr_t orig_tail = *tail_blk; bp = xlog_get_bp(log, 1); if (!bp) return -ENOMEM; /* - * Seek XLOG_MAX_ICLOGS + 1 records past the current tail record to get - * a temporary head block that points after the last possible - * concurrently written record of the tail. + * Make sure the tail points to a record (returns positive count on + * success). */ - count = xlog_seek_logrec_hdr(log, head_blk, tail_blk, - XLOG_MAX_ICLOGS + 1, bp, &tmp_head, &thead, - &wrapped); - if (count < 0) { - error = count; + error = xlog_seek_logrec_hdr(log, head_blk, *tail_blk, 1, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) goto out; - } - - /* - * If the call above didn't find XLOG_MAX_ICLOGS + 1 records, we ran - * into the actual log head. tmp_head points to the start of the record - * so update it to the actual head block. - */ - if (count < XLOG_MAX_ICLOGS + 1) - tmp_head = head_blk; + if (*tail_blk != tmp_tail) + *tail_blk = tmp_tail; /* - * We now have a tail and temporary head block that covers at least - * XLOG_MAX_ICLOGS records from the tail. We need to verify that these - * records were completely written. Run a CRC verification pass from - * tail to head and return the result. + * Run a CRC check from the tail to the head. We can't just check + * MAX_ICLOGS records past the tail because the tail may point to stale + * blocks cleared during the search for the head/tail. These blocks are + * overwritten with zero-length records and thus record count is not a + * reliable indicator of the iclog state before a crash. */ - error = xlog_do_recovery_pass(log, tmp_head, tail_blk, + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, XLOG_RECOVER_CRCPASS, &first_bad); + while ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { + int tail_distance; + + /* + * Is corruption within range of the head? If so, retry from + * the next record. Otherwise return an error. + */ + tail_distance = xlog_tail_distance(log, head_blk, first_bad); + if (tail_distance > BTOBB(XLOG_MAX_ICLOGS * hsize)) + break; + + /* skip to the next record; returns positive count on success */ + error = xlog_seek_logrec_hdr(log, head_blk, first_bad, 2, bp, + &tmp_tail, &thead, &wrapped); + if (error < 0) + goto out; + + *tail_blk = tmp_tail; + first_bad = 0; + error = xlog_do_recovery_pass(log, head_blk, *tail_blk, + XLOG_RECOVER_CRCPASS, &first_bad); + } + if (!error && *tail_blk != orig_tail) + xfs_warn(log->l_mp, + "Tail block (0x%llx) overwrite detected. Updated to 0x%llx", + orig_tail, *tail_blk); out: xlog_put_bp(bp); return error; @@ -1143,7 +1188,7 @@ xlog_verify_head( */ error = xlog_do_recovery_pass(log, *head_blk, tmp_rhead_blk, XLOG_RECOVER_CRCPASS, &first_bad); - if (error == -EFSBADCRC) { + if ((error == -EFSBADCRC || error == -EFSCORRUPTED) && first_bad) { /* * We've hit a potential torn write. Reset the error and warn * about it. @@ -1183,31 +1228,12 @@ xlog_verify_head( ASSERT(0); return 0; } - - /* - * Now verify the tail based on the updated head. This is - * required because the torn writes trimmed from the head could - * have been written over the tail of a previous record. Return - * any errors since recovery cannot proceed if the tail is - * corrupt. - * - * XXX: This leaves a gap in truly robust protection from torn - * writes in the log. If the head is behind the tail, the tail - * pushes forward to create some space and then a crash occurs - * causing the writes into the previous record's tail region to - * tear, log recovery isn't able to recover. - * - * How likely is this to occur? If possible, can we do something - * more intelligent here? Is it safe to push the tail forward if - * we can determine that the tail is within the range of the - * torn write (e.g., the kernel can only overwrite the tail if - * it has actually been pushed forward)? Alternatively, could we - * somehow prevent this condition at runtime? - */ - error = xlog_verify_tail(log, *head_blk, *tail_blk); } + if (error) + return error; - return error; + return xlog_verify_tail(log, *head_blk, tail_blk, + be32_to_cpu((*rhead)->h_size)); } /* @@ -4152,7 +4178,7 @@ xlog_recover_commit_trans( #define XLOG_RECOVER_COMMIT_QUEUE_MAX 100 - hlist_del(&trans->r_list); + hlist_del_init(&trans->r_list); error = xlog_recover_reorder_trans(log, trans, pass); if (error) @@ -4354,6 +4380,8 @@ xlog_recover_free_trans( xlog_recover_item_t *item, *n; int i; + hlist_del_init(&trans->r_list); + list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) { /* Free the regions in the item. */ list_del(&item->ri_list); @@ -4799,12 +4827,16 @@ xlog_recover_process_intents( int error = 0; struct xfs_ail_cursor cur; struct xfs_ail *ailp; +#if defined(DEBUG) || defined(XFS_WARN) xfs_lsn_t last_lsn; +#endif ailp = log->l_ailp; spin_lock(&ailp->xa_lock); lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); +#if defined(DEBUG) || defined(XFS_WARN) last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block); +#endif while (lip != NULL) { /* * We're done when we see something other than an intent. @@ -5214,7 +5246,7 @@ xlog_do_recovery_pass( xfs_daddr_t *first_bad) /* out: first bad log rec */ { xlog_rec_header_t *rhead; - xfs_daddr_t blk_no; + xfs_daddr_t blk_no, rblk_no; xfs_daddr_t rhead_blk; char *offset; xfs_buf_t *hbp, *dbp; @@ -5222,11 +5254,15 @@ xlog_do_recovery_pass( int error2 = 0; int bblks, split_bblks; int hblks, split_hblks, wrapped_hblks; + int i; struct hlist_head rhash[XLOG_RHASH_SIZE]; LIST_HEAD (buffer_list); ASSERT(head_blk != tail_blk); - rhead_blk = 0; + blk_no = rhead_blk = tail_blk; + + for (i = 0; i < XLOG_RHASH_SIZE; i++) + INIT_HLIST_HEAD(&rhash[i]); /* * Read the header of the tail block and get the iclog buffer size from @@ -5301,7 +5337,6 @@ xlog_do_recovery_pass( } memset(rhash, 0, sizeof(rhash)); - blk_no = rhead_blk = tail_blk; if (tail_blk > head_blk) { /* * Perform recovery around the end of the physical log. @@ -5363,9 +5398,19 @@ xlog_do_recovery_pass( bblks = (int)BTOBB(be32_to_cpu(rhead->h_len)); blk_no += hblks; - /* Read in data for log record */ - if (blk_no + bblks <= log->l_logBBsize) { - error = xlog_bread(log, blk_no, bblks, dbp, + /* + * Read the log record data in multiple reads if it + * wraps around the end of the log. Note that if the + * header already wrapped, blk_no could point past the + * end of the log. The record data is contiguous in + * that case. + */ + if (blk_no + bblks <= log->l_logBBsize || + blk_no >= log->l_logBBsize) { + /* mod blk_no in case the header wrapped and + * pushed it beyond the end of the log */ + rblk_no = do_mod(blk_no, log->l_logBBsize); + error = xlog_bread(log, rblk_no, bblks, dbp, &offset); if (error) goto bread_err2; @@ -5464,6 +5509,19 @@ xlog_do_recovery_pass( if (error && first_bad) *first_bad = rhead_blk; + /* + * Transactions are freed at commit time but transactions without commit + * records on disk are never committed. Free any that may be left in the + * hash table. + */ + for (i = 0; i < XLOG_RHASH_SIZE; i++) { + struct hlist_node *tmp; + struct xlog_recover *trans; + + hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list) + xlog_recover_free_trans(trans); + } + return error ? error : error2; } @@ -5542,6 +5600,8 @@ xlog_do_recover( xfs_buf_t *bp; xfs_sb_t *sbp; + trace_xfs_log_recover(log, head_blk, tail_blk); + /* * First replay the images in the log. */ diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 13796f2..d4ce8d2 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -925,15 +925,6 @@ xfs_mountfs( } /* - * During the second phase of log recovery, we need iget and - * iput to behave like they do for an active filesystem. - * xfs_fs_drop_inode needs to be able to prevent the deletion - * of inodes before we're done replaying log items on those - * inodes. - */ - mp->m_super->s_flags |= MS_ACTIVE; - - /* * Finish recovering the file system. This part needed to be delayed * until after the root and real-time bitmap inodes were consistently * read in. @@ -1008,12 +999,13 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: - mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + /* Clean out dquots that might be in memory after quotacheck. */ + xfs_qm_unmount(mp); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 0c381d7..0492436 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28); XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52); - XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56); + XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20); XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); } diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 93a7aaf..cecd375 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -279,7 +279,7 @@ xfs_fs_commit_blocks( (end - 1) >> PAGE_SHIFT); WARN_ON_ONCE(error); - error = xfs_iomap_write_unwritten(ip, start, length); + error = xfs_iomap_write_unwritten(ip, start, length, false); if (error) goto out_drop_iolock; } diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index 8b9a9f1..1fdd3fa 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -111,6 +111,9 @@ restart: skipped = 0; break; } + /* we're done if id overflows back to zero */ + if (!next_index) + break; } if (skipped) { @@ -1247,6 +1250,7 @@ xfs_qm_flush_one( struct xfs_dquot *dqp, void *data) { + struct xfs_mount *mp = dqp->q_mount; struct list_head *buffer_list = data; struct xfs_buf *bp = NULL; int error = 0; @@ -1257,7 +1261,32 @@ xfs_qm_flush_one( if (!XFS_DQ_IS_DIRTY(dqp)) goto out_unlock; - xfs_dqflock(dqp); + /* + * The only way the dquot is already flush locked by the time quotacheck + * gets here is if reclaim flushed it before the dqadjust walk dirtied + * it for the final time. Quotacheck collects all dquot bufs in the + * local delwri queue before dquots are dirtied, so reclaim can't have + * possibly queued it for I/O. The only way out is to push the buffer to + * cycle the flush lock. + */ + if (!xfs_dqflock_nowait(dqp)) { + /* buf is pinned in-core by delwri list */ + DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno, + mp->m_quotainfo->qi_dqchunklen); + bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL); + if (!bp) { + error = -EINVAL; + goto out_unlock; + } + xfs_buf_unlock(bp); + + xfs_buf_delwri_pushbuf(bp, buffer_list); + xfs_buf_rele(bp); + + error = -EAGAIN; + goto out_unlock; + } + error = xfs_qm_dqflush(dqp, &bp); if (error) goto out_unlock; diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 29a75ec..17d3c96 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -169,6 +169,8 @@ xfs_reflink_find_shared( error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); if (error) return error; + if (!agbp) + return -ENOMEM; cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL); @@ -333,7 +335,7 @@ xfs_reflink_convert_cow_extent( struct xfs_defer_ops *dfops) { struct xfs_bmbt_irec irec = *imap; - xfs_fsblock_t first_block; + xfs_fsblock_t first_block = NULLFSBLOCK; int nimaps = 1; if (imap->br_state == XFS_EXT_NORM) @@ -765,7 +767,13 @@ xfs_reflink_end_cow( /* If there is a hole at end_fsb - 1 go to the previous extent */ if (eof || got.br_startoff > end_fsb) { - ASSERT(idx > 0); + /* + * In case of racing, overlapping AIO writes no COW extents + * might be left by the time I/O completes for the loser of + * the race. In that case we are done. + */ + if (idx <= 0) + goto out_cancel; xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got); } @@ -839,6 +847,7 @@ next_extent: out_defer: xfs_defer_cancel(&dfops); +out_cancel: xfs_trans_cancel(tp); xfs_iunlock(ip, XFS_ILOCK_EXCL); out: diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 882fb85..67d589e 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1214,7 +1214,7 @@ xfs_test_remount_options( tmp_mp->m_super = sb; error = xfs_parseargs(tmp_mp, options); xfs_free_fsname(tmp_mp); - kfree(tmp_mp); + kmem_free(tmp_mp); return error; } diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 828f383..bdf69e1 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -366,6 +366,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); +DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_bdstrat_shut); DEFINE_BUF_EVENT(xfs_buf_item_relse); @@ -519,7 +520,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format); -DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); @@ -1990,6 +1990,24 @@ DEFINE_EVENT(xfs_swap_extent_class, name, \ DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); +TRACE_EVENT(xfs_log_recover, + TP_PROTO(struct xlog *log, xfs_daddr_t headblk, xfs_daddr_t tailblk), + TP_ARGS(log, headblk, tailblk), + TP_STRUCT__entry( + __field(dev_t, dev) + __field(xfs_daddr_t, headblk) + __field(xfs_daddr_t, tailblk) + ), + TP_fast_assign( + __entry->dev = log->l_mp->m_super->s_dev; + __entry->headblk = headblk; + __entry->tailblk = tailblk; + ), + TP_printk("dev %d:%d headblk 0x%llx tailblk 0x%llx", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->headblk, + __entry->tailblk) +) + TRACE_EVENT(xfs_log_recover_record, TP_PROTO(struct xlog *log, struct xlog_rec_header *rhead, int pass), TP_ARGS(log, rhead, pass), diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h index 98024cb..5669cf0 100644 --- a/fs/xfs/xfs_trans.h +++ b/fs/xfs/xfs_trans.h @@ -50,6 +50,7 @@ typedef struct xfs_log_item { struct xfs_ail *li_ailp; /* ptr to AIL */ uint li_type; /* item type */ uint li_flags; /* misc flags */ + struct xfs_buf *li_buf; /* real buffer pointer */ struct xfs_log_item *li_bio_list; /* buffer item list */ void (*li_cb)(struct xfs_buf *, struct xfs_log_item *); @@ -65,11 +66,13 @@ typedef struct xfs_log_item { } xfs_log_item_t; #define XFS_LI_IN_AIL 0x1 -#define XFS_LI_ABORTED 0x2 +#define XFS_LI_ABORTED 0x2 +#define XFS_LI_FAILED 0x4 #define XFS_LI_FLAGS \ { XFS_LI_IN_AIL, "IN_AIL" }, \ - { XFS_LI_ABORTED, "ABORTED" } + { XFS_LI_ABORTED, "ABORTED" }, \ + { XFS_LI_FAILED, "FAILED" } struct xfs_item_ops { void (*iop_size)(xfs_log_item_t *, int *, int *); @@ -80,6 +83,7 @@ struct xfs_item_ops { void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); + void (*iop_error)(xfs_log_item_t *, xfs_buf_t *); }; void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, @@ -213,12 +217,14 @@ void xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *); void xfs_trans_binval(xfs_trans_t *, struct xfs_buf *); void xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *); -void xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); +bool xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint); void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int); void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint); -void xfs_trans_log_buf(xfs_trans_t *, struct xfs_buf *, uint, uint); +void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint, + uint); +void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); void xfs_extent_free_init_defer_op(void); @@ -277,6 +283,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp, struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops, enum xfs_bmap_intent_type type, struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, xfs_exntst_t state); + xfs_filblks_t *blockcount, xfs_exntst_t state); #endif /* __XFS_TRANS_H__ */ diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index d6c9c3e..70f5ab0 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -684,8 +684,24 @@ xfs_trans_ail_update_bulk( } } -/* - * xfs_trans_ail_delete_bulk - remove multiple log items from the AIL +bool +xfs_ail_delete_one( + struct xfs_ail *ailp, + struct xfs_log_item *lip) +{ + struct xfs_log_item *mlip = xfs_ail_min(ailp); + + trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); + xfs_ail_delete(ailp, lip); + xfs_clear_li_failed(lip); + lip->li_flags &= ~XFS_LI_IN_AIL; + lip->li_lsn = 0; + + return mlip == lip; +} + +/** + * Remove a log items from the AIL * * @xfs_trans_ail_delete_bulk takes an array of log items that all need to * removed from the AIL. The caller is already holding the AIL lock, and done @@ -706,52 +722,36 @@ xfs_trans_ail_update_bulk( * before returning. */ void -xfs_trans_ail_delete_bulk( +xfs_trans_ail_delete( struct xfs_ail *ailp, - struct xfs_log_item **log_items, - int nr_items, + struct xfs_log_item *lip, int shutdown_type) __releases(ailp->xa_lock) { - xfs_log_item_t *mlip; - int mlip_changed = 0; - int i; - - mlip = xfs_ail_min(ailp); + struct xfs_mount *mp = ailp->xa_mount; + bool mlip_changed; - for (i = 0; i < nr_items; i++) { - struct xfs_log_item *lip = log_items[i]; - if (!(lip->li_flags & XFS_LI_IN_AIL)) { - struct xfs_mount *mp = ailp->xa_mount; - - spin_unlock(&ailp->xa_lock); - if (!XFS_FORCED_SHUTDOWN(mp)) { - xfs_alert_tag(mp, XFS_PTAG_AILDELETE, - "%s: attempting to delete a log item that is not in the AIL", - __func__); - xfs_force_shutdown(mp, shutdown_type); - } - return; + if (!(lip->li_flags & XFS_LI_IN_AIL)) { + spin_unlock(&ailp->xa_lock); + if (!XFS_FORCED_SHUTDOWN(mp)) { + xfs_alert_tag(mp, XFS_PTAG_AILDELETE, + "%s: attempting to delete a log item that is not in the AIL", + __func__); + xfs_force_shutdown(mp, shutdown_type); } - - trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn); - xfs_ail_delete(ailp, lip); - lip->li_flags &= ~XFS_LI_IN_AIL; - lip->li_lsn = 0; - if (mlip == lip) - mlip_changed = 1; + return; } + mlip_changed = xfs_ail_delete_one(ailp, lip); if (mlip_changed) { - if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount)) - xlog_assign_tail_lsn_locked(ailp->xa_mount); + if (!XFS_FORCED_SHUTDOWN(mp)) + xlog_assign_tail_lsn_locked(mp); if (list_empty(&ailp->xa_ail)) wake_up_all(&ailp->xa_empty); - spin_unlock(&ailp->xa_lock); + } + spin_unlock(&ailp->xa_lock); + if (mlip_changed) xfs_log_space_wake(ailp->xa_mount); - } else { - spin_unlock(&ailp->xa_lock); - } } int diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c index 6408e7d..14543d9 100644 --- a/fs/xfs/xfs_trans_bmap.c +++ b/fs/xfs/xfs_trans_bmap.c @@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update( int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, - xfs_filblks_t blockcount, + xfs_filblks_t *blockcount, xfs_exntst_t state) { int error; @@ -196,16 +196,23 @@ xfs_bmap_update_finish_item( void **state) { struct xfs_bmap_intent *bmap; + xfs_filblks_t count; int error; bmap = container_of(item, struct xfs_bmap_intent, bi_list); + count = bmap->bi_bmap.br_blockcount; error = xfs_trans_log_finish_bmap_update(tp, done_item, dop, bmap->bi_type, bmap->bi_owner, bmap->bi_whichfork, bmap->bi_bmap.br_startoff, bmap->bi_bmap.br_startblock, - bmap->bi_bmap.br_blockcount, + &count, bmap->bi_bmap.br_state); + if (!error && count > 0) { + ASSERT(bmap->bi_type == XFS_BMAP_UNMAP); + bmap->bi_bmap.br_blockcount = count; + return -EAGAIN; + } kmem_free(bmap); return error; } diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c index 8ee29ca..3ba7a96 100644 --- a/fs/xfs/xfs_trans_buf.c +++ b/fs/xfs/xfs_trans_buf.c @@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t *tp, xfs_buf_t *bp) { xfs_buf_log_item_t *bip; + int freed; /* * Default to a normal brelse() call if the tp is NULL. @@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t *tp, /* * Drop our reference to the buf log item. */ - atomic_dec(&bip->bli_refcount); + freed = atomic_dec_and_test(&bip->bli_refcount); /* - * If the buf item is not tracking data in the log, then - * we must free it before releasing the buffer back to the - * free pool. Before releasing the buffer to the free pool, - * clear the transaction pointer in b_fsprivate2 to dissolve - * its relation to this transaction. + * If the buf item is not tracking data in the log, then we must free it + * before releasing the buffer back to the free pool. + * + * If the fs has shutdown and we dropped the last reference, it may fall + * on us to release a (possibly dirty) bli if it never made it to the + * AIL (e.g., the aborted unpin already happened and didn't release it + * due to our reference). Since we're already shutdown and need xa_lock, + * just force remove from the AIL and release the bli here. */ - if (!xfs_buf_item_dirty(bip)) { + if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) { + xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR); + xfs_buf_item_relse(bp); + } else if (!(bip->bli_flags & XFS_BLI_DIRTY)) { /*** ASSERT(bp->b_pincount == 0); ***/ @@ -486,25 +493,17 @@ xfs_trans_bhold_release(xfs_trans_t *tp, } /* - * This is called to mark bytes first through last inclusive of the given - * buffer as needing to be logged when the transaction is committed. - * The buffer must already be associated with the given transaction. - * - * First and last are numbers relative to the beginning of this buffer, - * so the first byte in the buffer is numbered 0 regardless of the - * value of b_blkno. + * Mark a buffer dirty in the transaction. */ void -xfs_trans_log_buf(xfs_trans_t *tp, - xfs_buf_t *bp, - uint first, - uint last) +xfs_trans_dirty_buf( + struct xfs_trans *tp, + struct xfs_buf *bp) { - xfs_buf_log_item_t *bip = bp->b_fspriv; + struct xfs_buf_log_item *bip = bp->b_fspriv; ASSERT(bp->b_transp == tp); ASSERT(bip != NULL); - ASSERT(first <= last && last < BBTOB(bp->b_length)); ASSERT(bp->b_iodone == NULL || bp->b_iodone == xfs_buf_iodone_callbacks); @@ -524,8 +523,6 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_iodone = xfs_buf_iodone_callbacks; bip->bli_item.li_cb = xfs_buf_iodone; - trace_xfs_trans_log_buf(bip); - /* * If we invalidated the buffer within this transaction, then * cancel the invalidation now that we're dirtying the buffer @@ -538,17 +535,37 @@ xfs_trans_log_buf(xfs_trans_t *tp, bp->b_flags &= ~XBF_STALE; bip->__bli_format.blf_flags &= ~XFS_BLF_CANCEL; } + bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; tp->t_flags |= XFS_TRANS_DIRTY; bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY; +} - /* - * If we have an ordered buffer we are not logging any dirty range but - * it still needs to be marked dirty and that it has been logged. - */ - bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED; - if (!(bip->bli_flags & XFS_BLI_ORDERED)) - xfs_buf_item_log(bip, first, last); +/* + * This is called to mark bytes first through last inclusive of the given + * buffer as needing to be logged when the transaction is committed. + * The buffer must already be associated with the given transaction. + * + * First and last are numbers relative to the beginning of this buffer, + * so the first byte in the buffer is numbered 0 regardless of the + * value of b_blkno. + */ +void +xfs_trans_log_buf( + struct xfs_trans *tp, + struct xfs_buf *bp, + uint first, + uint last) +{ + struct xfs_buf_log_item *bip = bp->b_fspriv; + + ASSERT(first <= last && last < BBTOB(bp->b_length)); + ASSERT(!(bip->bli_flags & XFS_BLI_ORDERED)); + + xfs_trans_dirty_buf(tp, bp); + + trace_xfs_trans_log_buf(bip); + xfs_buf_item_log(bip, first, last); } @@ -701,14 +718,13 @@ xfs_trans_inode_alloc_buf( } /* - * Mark the buffer as ordered for this transaction. This means - * that the contents of the buffer are not recorded in the transaction - * but it is tracked in the AIL as though it was. This allows us - * to record logical changes in transactions rather than the physical - * changes we make to the buffer without changing writeback ordering - * constraints of metadata buffers. + * Mark the buffer as ordered for this transaction. This means that the contents + * of the buffer are not recorded in the transaction but it is tracked in the + * AIL as though it was. This allows us to record logical changes in + * transactions rather than the physical changes we make to the buffer without + * changing writeback ordering constraints of metadata buffers. */ -void +bool xfs_trans_ordered_buf( struct xfs_trans *tp, struct xfs_buf *bp) @@ -719,8 +735,18 @@ xfs_trans_ordered_buf( ASSERT(bip != NULL); ASSERT(atomic_read(&bip->bli_refcount) > 0); + if (xfs_buf_item_dirty_format(bip)) + return false; + bip->bli_flags |= XFS_BLI_ORDERED; trace_xfs_buf_item_ordered(bip); + + /* + * We don't log a dirty range of an ordered buffer but it still needs + * to be marked dirty and that it has been logged. + */ + xfs_trans_dirty_buf(tp, bp); + return true; } /* diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h index 49931b7..b317a36 100644 --- a/fs/xfs/xfs_trans_priv.h +++ b/fs/xfs/xfs_trans_priv.h @@ -106,18 +106,9 @@ xfs_trans_ail_update( xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn); } -void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp, - struct xfs_log_item **log_items, int nr_items, - int shutdown_type) - __releases(ailp->xa_lock); -static inline void -xfs_trans_ail_delete( - struct xfs_ail *ailp, - xfs_log_item_t *lip, - int shutdown_type) __releases(ailp->xa_lock) -{ - xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type); -} +bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip); +void xfs_trans_ail_delete(struct xfs_ail *ailp, struct xfs_log_item *lip, + int shutdown_type) __releases(ailp->xa_lock); static inline void xfs_trans_ail_remove( @@ -173,4 +164,35 @@ xfs_trans_ail_copy_lsn( *dst = *src; } #endif + +static inline void +xfs_clear_li_failed( + struct xfs_log_item *lip) +{ + struct xfs_buf *bp = lip->li_buf; + + ASSERT(lip->li_flags & XFS_LI_IN_AIL); + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (lip->li_flags & XFS_LI_FAILED) { + lip->li_flags &= ~XFS_LI_FAILED; + lip->li_buf = NULL; + xfs_buf_rele(bp); + } +} + +static inline void +xfs_set_li_failed( + struct xfs_log_item *lip, + struct xfs_buf *bp) +{ + lockdep_assert_held(&lip->li_ailp->xa_lock); + + if (!(lip->li_flags & XFS_LI_FAILED)) { + xfs_buf_hold(bp); + lip->li_flags |= XFS_LI_FAILED; + lip->li_buf = bp; + } +} + #endif /* __XFS_TRANS_PRIV_H__ */ |