diff options
Diffstat (limited to 'fs')
63 files changed, 723 insertions, 357 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 643c70d2b2e6..4f8f75d9e839 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2563,7 +2563,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes); static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info, unsigned num_items) { - return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items; + return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items; } /* @@ -2573,7 +2573,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info, static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info, unsigned num_items) { - return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items; + return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items; } int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 60a750678a82..c24d615e3d7f 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -468,7 +468,7 @@ int verify_dir_item(struct btrfs_fs_info *fs_info, if (btrfs_dir_name_len(leaf, dir_item) > namelen) { btrfs_crit(fs_info, "invalid dir item name len: %u", - (unsigned)btrfs_dir_data_len(leaf, dir_item)); + (unsigned)btrfs_dir_name_len(leaf, dir_item)); return 1; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8685d67185d0..5f678dcb20e6 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3467,10 +3467,12 @@ static int write_dev_supers(struct btrfs_device *device, * we fua the first super. The others we allow * to go down lazy. */ - if (i == 0) - ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh); - else + if (i == 0) { + ret = btrfsic_submit_bh(REQ_OP_WRITE, + REQ_SYNC | REQ_FUA, bh); + } else { ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh); + } if (ret) errors++; } @@ -3535,7 +3537,7 @@ static int write_dev_flush(struct btrfs_device *device, int wait) bio->bi_end_io = btrfs_end_empty_barrier; bio->bi_bdev = device->bdev; - bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; init_completion(&device->flush_wait); bio->bi_private = &device->flush_wait; device->flush_bio = bio; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e390451c72e6..33d979e9ea2a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3993,6 +3993,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, info->space_info_kobj, "%s", alloc_name(found->flags)); if (ret) { + percpu_counter_destroy(&found->total_bytes_pinned); kfree(found); return ret; } @@ -4844,7 +4845,7 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info, spin_unlock(&delayed_rsv->lock); commit: - trans = btrfs_join_transaction(fs_info->fs_root); + trans = btrfs_join_transaction(fs_info->extent_root); if (IS_ERR(trans)) return -ENOSPC; @@ -4862,7 +4863,7 @@ static int flush_space(struct btrfs_fs_info *fs_info, struct btrfs_space_info *space_info, u64 num_bytes, u64 orig_bytes, int state) { - struct btrfs_root *root = fs_info->fs_root; + struct btrfs_root *root = fs_info->extent_root; struct btrfs_trans_handle *trans; int nr; int ret = 0; @@ -5062,7 +5063,7 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, int flush_state = FLUSH_DELAYED_ITEMS_NR; spin_lock(&space_info->lock); - to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root, + to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root, space_info); if (!to_reclaim) { spin_unlock(&space_info->lock); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d8da3edf2ac3..d3619e010005 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2458,7 +2458,7 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end) if (!uptodate) { ClearPageUptodate(page); SetPageError(page); - ret = ret < 0 ? ret : -EIO; + ret = err < 0 ? err : -EIO; mapping_set_error(page->mapping, ret); } } @@ -4377,6 +4377,123 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode, return NULL; } +/* + * To cache previous fiemap extent + * + * Will be used for merging fiemap extent + */ +struct fiemap_cache { + u64 offset; + u64 phys; + u64 len; + u32 flags; + bool cached; +}; + +/* + * Helper to submit fiemap extent. + * + * Will try to merge current fiemap extent specified by @offset, @phys, + * @len and @flags with cached one. + * And only when we fails to merge, cached one will be submitted as + * fiemap extent. + * + * Return value is the same as fiemap_fill_next_extent(). + */ +static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache, + u64 offset, u64 phys, u64 len, u32 flags) +{ + int ret = 0; + + if (!cache->cached) + goto assign; + + /* + * Sanity check, extent_fiemap() should have ensured that new + * fiemap extent won't overlap with cahced one. + * Not recoverable. + * + * NOTE: Physical address can overlap, due to compression + */ + if (cache->offset + cache->len > offset) { + WARN_ON(1); + return -EINVAL; + } + + /* + * Only merges fiemap extents if + * 1) Their logical addresses are continuous + * + * 2) Their physical addresses are continuous + * So truly compressed (physical size smaller than logical size) + * extents won't get merged with each other + * + * 3) Share same flags except FIEMAP_EXTENT_LAST + * So regular extent won't get merged with prealloc extent + */ + if (cache->offset + cache->len == offset && + cache->phys + cache->len == phys && + (cache->flags & ~FIEMAP_EXTENT_LAST) == + (flags & ~FIEMAP_EXTENT_LAST)) { + cache->len += len; + cache->flags |= flags; + goto try_submit_last; + } + + /* Not mergeable, need to submit cached one */ + ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, + cache->len, cache->flags); + cache->cached = false; + if (ret) + return ret; +assign: + cache->cached = true; + cache->offset = offset; + cache->phys = phys; + cache->len = len; + cache->flags = flags; +try_submit_last: + if (cache->flags & FIEMAP_EXTENT_LAST) { + ret = fiemap_fill_next_extent(fieinfo, cache->offset, + cache->phys, cache->len, cache->flags); + cache->cached = false; + } + return ret; +} + +/* + * Sanity check for fiemap cache + * + * All fiemap cache should be submitted by emit_fiemap_extent() + * Iteration should be terminated either by last fiemap extent or + * fieinfo->fi_extents_max. + * So no cached fiemap should exist. + */ +static int check_fiemap_cache(struct btrfs_fs_info *fs_info, + struct fiemap_extent_info *fieinfo, + struct fiemap_cache *cache) +{ + int ret; + + if (!cache->cached) + return 0; + + /* Small and recoverbale problem, only to info developer */ +#ifdef CONFIG_BTRFS_DEBUG + WARN_ON(1); +#endif + btrfs_warn(fs_info, + "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x", + cache->offset, cache->phys, cache->len, cache->flags); + ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys, + cache->len, cache->flags); + cache->cached = false; + if (ret > 0) + ret = 0; + return ret; +} + int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len, get_extent_t *get_extent) { @@ -4394,6 +4511,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, struct extent_state *cached_state = NULL; struct btrfs_path *path; struct btrfs_root *root = BTRFS_I(inode)->root; + struct fiemap_cache cache = { 0 }; int end = 0; u64 em_start = 0; u64 em_len = 0; @@ -4573,8 +4691,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags |= FIEMAP_EXTENT_LAST; end = 1; } - ret = fiemap_fill_next_extent(fieinfo, em_start, disko, - em_len, flags); + ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko, + em_len, flags); if (ret) { if (ret == 1) ret = 0; @@ -4582,6 +4700,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, } } out_free: + if (!ret) + ret = check_fiemap_cache(root->fs_info, fieinfo, &cache); free_extent_map(em); out: btrfs_free_path(path); diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c index a97fdc156a03..baacc1866861 100644 --- a/fs/btrfs/hash.c +++ b/fs/btrfs/hash.c @@ -38,6 +38,7 @@ u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length) { SHASH_DESC_ON_STACK(shash, tfm); u32 *ctx = (u32 *)shash_desc_ctx(shash); + u32 retval; int err; shash->tfm = tfm; @@ -47,5 +48,7 @@ u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length) err = crypto_shash_update(shash, address, length); BUG_ON(err); - return *ctx; + retval = *ctx; + barrier_data(ctx); + return retval; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 17cbe9306faf..ef3c98c527c1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2952,7 +2952,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) ret = test_range_bit(io_tree, ordered_extent->file_offset, ordered_extent->file_offset + ordered_extent->len - 1, - EXTENT_DEFRAG, 1, cached_state); + EXTENT_DEFRAG, 0, cached_state); if (ret) { u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item); if (0 && last_snapshot >= BTRFS_I(inode)->generation) @@ -7483,8 +7483,8 @@ bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end) int found = false; void **pagep = NULL; struct page *page = NULL; - int start_idx; - int end_idx; + unsigned long start_idx; + unsigned long end_idx; start_idx = start >> PAGE_SHIFT; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 3fdde0b283c9..29308a80d66f 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1671,8 +1671,12 @@ static long ceph_fallocate(struct file *file, int mode, } size = i_size_read(inode); - if (!(mode & FALLOC_FL_KEEP_SIZE)) + if (!(mode & FALLOC_FL_KEEP_SIZE)) { endoff = offset + length; + ret = inode_newsize_ok(inode, endoff); + if (ret) + goto unlock; + } if (fi->fmode & CEPH_FILE_MODE_LAZY) want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO; @@ -1155,6 +1155,17 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf, } /* + * It is possible, particularly with mixed reads & writes to private + * mappings, that we have raced with a PMD fault that overlaps with + * the PTE we need to set up. If so just return and the fault will be + * retried. + */ + if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) { + vmf_ret = VM_FAULT_NOPAGE; + goto unlock_entry; + } + + /* * Note that we don't bother to use iomap_apply here: DAX required * the file system block size to be equal the page size, which means * that we never have to deal with more than a single extent here. @@ -1398,6 +1409,18 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, goto fallback; /* + * It is possible, particularly with mixed reads & writes to private + * mappings, that we have raced with a PTE fault that overlaps with + * the PMD we need to set up. If so just return and the fault will be + * retried. + */ + if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) && + !pmd_devmap(*vmf->pmd)) { + result = 0; + goto unlock_entry; + } + + /* * Note that we don't use iomap_apply here. We aren't doing I/O, only * setting up a mapping, so really we're using iomap_begin() as a way * to look up our filesystem block. diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 26d77f9f8c12..2dcbd5698884 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -817,7 +817,7 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length, iomap->bdev = bdev; iomap->offset = (u64)first_block << blkbits; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; @@ -841,7 +841,7 @@ static int ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if (iomap->type == IOMAP_MAPPED && written < length && (flags & IOMAP_WRITE)) diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c index fd389935ecd1..3ec0e46de95f 100644 --- a/fs/ext4/acl.c +++ b/fs/ext4/acl.c @@ -4,6 +4,7 @@ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ +#include <linux/quotaops.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" @@ -232,6 +233,9 @@ ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type) handle_t *handle; int error, retries = 0; + error = dquot_initialize(inode); + if (error) + return error; retry: handle = ext4_journal_start(inode, EXT4_HT_XATTR, ext4_jbd2_credits_xattr(inode)); diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8e8046104f4d..32191548abed 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2523,7 +2523,6 @@ extern int ext4_search_dir(struct buffer_head *bh, int buf_size, struct inode *dir, struct ext4_filename *fname, - const struct qstr *d_name, unsigned int offset, struct ext4_dir_entry_2 **res_dir); extern int ext4_generic_delete_entry(handle_t *handle, @@ -3007,7 +3006,6 @@ extern int htree_inlinedir_to_tree(struct file *dir_file, int *has_inline_data); extern struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, - const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, int *has_inline_data); extern int ext4_delete_inline_entry(handle_t *handle, diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 2a97dff87b96..3e36508610b7 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3413,13 +3413,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; - struct ext4_extent zero_ex; + struct ext4_extent zero_ex1, zero_ex2; struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; int allocated = 0, max_zeroout = 0; int err = 0; - int split_flag = 0; + int split_flag = EXT4_EXT_DATA_VALID2; ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical" "block %llu, max_blocks %u\n", inode->i_ino, @@ -3436,7 +3436,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); - zero_ex.ee_len = 0; + zero_ex1.ee_len = 0; + zero_ex2.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); @@ -3576,62 +3577,52 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, if (ext4_encrypted_inode(inode)) max_zeroout = 0; - /* If extent is less than s_max_zeroout_kb, zeroout directly */ - if (max_zeroout && (ee_len <= max_zeroout)) { - err = ext4_ext_zeroout(inode, ex); - if (err) - goto out; - zero_ex.ee_block = ex->ee_block; - zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex)); - ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex)); - - err = ext4_ext_get_access(handle, inode, path + depth); - if (err) - goto out; - ext4_ext_mark_initialized(ex); - ext4_ext_try_to_merge(handle, inode, path, ex); - err = ext4_ext_dirty(handle, inode, path + path->p_depth); - goto out; - } - /* - * four cases: + * five cases: * 1. split the extent into three extents. - * 2. split the extent into two extents, zeroout the first half. - * 3. split the extent into two extents, zeroout the second half. + * 2. split the extent into two extents, zeroout the head of the first + * extent. + * 3. split the extent into two extents, zeroout the tail of the second + * extent. * 4. split the extent into two extents with out zeroout. + * 5. no splitting needed, just possibly zeroout the head and / or the + * tail of the extent. */ split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; - if (max_zeroout && (allocated > map->m_len)) { + if (max_zeroout && (allocated > split_map.m_len)) { if (allocated <= max_zeroout) { - /* case 3 */ - zero_ex.ee_block = - cpu_to_le32(map->m_lblk); - zero_ex.ee_len = cpu_to_le16(allocated); - ext4_ext_store_pblock(&zero_ex, - ext4_ext_pblock(ex) + map->m_lblk - ee_block); - err = ext4_ext_zeroout(inode, &zero_ex); + /* case 3 or 5 */ + zero_ex1.ee_block = + cpu_to_le32(split_map.m_lblk + + split_map.m_len); + zero_ex1.ee_len = + cpu_to_le16(allocated - split_map.m_len); + ext4_ext_store_pblock(&zero_ex1, + ext4_ext_pblock(ex) + split_map.m_lblk + + split_map.m_len - ee_block); + err = ext4_ext_zeroout(inode, &zero_ex1); if (err) goto out; - split_map.m_lblk = map->m_lblk; split_map.m_len = allocated; - } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) { - /* case 2 */ - if (map->m_lblk != ee_block) { - zero_ex.ee_block = ex->ee_block; - zero_ex.ee_len = cpu_to_le16(map->m_lblk - + } + if (split_map.m_lblk - ee_block + split_map.m_len < + max_zeroout) { + /* case 2 or 5 */ + if (split_map.m_lblk != ee_block) { + zero_ex2.ee_block = ex->ee_block; + zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk - ee_block); - ext4_ext_store_pblock(&zero_ex, + ext4_ext_store_pblock(&zero_ex2, ext4_ext_pblock(ex)); - err = ext4_ext_zeroout(inode, &zero_ex); + err = ext4_ext_zeroout(inode, &zero_ex2); if (err) goto out; } + split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; - split_map.m_len = map->m_lblk - ee_block + map->m_len; allocated = map->m_len; } } @@ -3642,8 +3633,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle, err = 0; out: /* If we have gotten a failure, don't zero out status tree */ - if (!err) - err = ext4_zeroout_es(inode, &zero_ex); + if (!err) { + err = ext4_zeroout_es(inode, &zero_ex1); + if (!err) + err = ext4_zeroout_es(inode, &zero_ex2); + } return err ? err : allocated; } @@ -4883,6 +4877,8 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(handle, inode, offset, len); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); if (file->f_flags & O_SYNC) ext4_handle_sync(handle); @@ -5569,6 +5565,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ext4_handle_sync(handle); inode->i_mtime = inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); @@ -5742,6 +5739,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); if (IS_SYNC(inode)) ext4_handle_sync(handle); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 831fd6beebf0..02ce7e7bbdf5 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -474,57 +474,37 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, endoff = (loff_t)end_blk << blkbits; index = startoff >> PAGE_SHIFT; - end = endoff >> PAGE_SHIFT; + end = (endoff - 1) >> PAGE_SHIFT; pagevec_init(&pvec, 0); do { int i, num; unsigned long nr_pages; - num = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, (pgoff_t)num); - if (nr_pages == 0) { - if (whence == SEEK_DATA) - break; - - BUG_ON(whence != SEEK_HOLE); - /* - * If this is the first time to go into the loop and - * offset is not beyond the end offset, it will be a - * hole at this offset - */ - if (lastoff == startoff || lastoff < endoff) - found = 1; - break; - } - - /* - * If this is the first time to go into the loop and - * offset is smaller than the first page offset, it will be a - * hole at this offset. - */ - if (lastoff == startoff && whence == SEEK_HOLE && - lastoff < page_offset(pvec.pages[0])) { - found = 1; + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; struct buffer_head *bh, *head; /* - * If the current offset is not beyond the end of given - * range, it will be a hole. + * If current offset is smaller than the page offset, + * there is a hole at this offset. */ - if (lastoff < endoff && whence == SEEK_HOLE && - page->index > end) { + if (whence == SEEK_HOLE && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { found = 1; *offset = lastoff; goto out; } + if (page->index > end) + goto out; + lock_page(page); if (unlikely(page->mapping != inode->i_mapping)) { @@ -564,20 +544,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode, unlock_page(page); } - /* - * The no. of pages is less than our desired, that would be a - * hole in there. - */ - if (nr_pages < num && whence == SEEK_HOLE) { - found = 1; - *offset = lastoff; + /* The no. of pages is less than our desired, we are done. */ + if (nr_pages < num) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + if (whence == SEEK_HOLE && lastoff < endoff) { + found = 1; + *offset = lastoff; + } out: pagevec_release(&pvec); return found; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index d5dea4c293ef..8d141c0c8ff9 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1627,7 +1627,6 @@ out: struct buffer_head *ext4_find_inline_entry(struct inode *dir, struct ext4_filename *fname, - const struct qstr *d_name, struct ext4_dir_entry_2 **res_dir, int *has_inline_data) { @@ -1649,7 +1648,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir, EXT4_INLINE_DOTDOT_SIZE; inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, - dir, fname, d_name, 0, res_dir); + dir, fname, 0, res_dir); if (ret == 1) goto out_find; if (ret < 0) @@ -1662,7 +1661,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir, inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE; ret = ext4_search_dir(iloc.bh, inline_start, inline_size, - dir, fname, d_name, 0, res_dir); + dir, fname, 0, res_dir); if (ret == 1) goto out_find; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5834c4d76be8..5cf82d03968c 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2124,15 +2124,29 @@ 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--; @@ -3412,7 +3426,7 @@ retry: bdev = inode->i_sb->s_bdev; iomap->bdev = bdev; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; iomap->offset = first_block << blkbits; @@ -3447,7 +3461,7 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, int blkbits = inode->i_blkbits; bool truncate = false; - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT)) return 0; @@ -3629,9 +3643,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter) get_block_func = ext4_dio_get_block_unwritten_async; dio_flags = DIO_LOCKING; } -#ifdef CONFIG_EXT4_FS_ENCRYPTION - BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); -#endif ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block_func, ext4_end_io_dio, NULL, dio_flags); @@ -3713,7 +3724,7 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) */ inode_lock_shared(inode); ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, - iocb->ki_pos + count); + iocb->ki_pos + count - 1); if (ret) goto out_unlock; ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, @@ -4207,6 +4218,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) inode->i_mtime = inode->i_ctime = current_time(inode); ext4_mark_inode_dirty(handle, inode); + if (ret >= 0) + ext4_update_inode_fsync_trans(handle, inode, 1); out_stop: ext4_journal_stop(handle); out_dio: @@ -5637,8 +5650,9 @@ static int ext4_expand_extra_isize(struct inode *inode, /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { - memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0, - new_extra_isize); + memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + + EXT4_I(inode)->i_extra_isize, 0, + new_extra_isize - EXT4_I(inode)->i_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5083bce20ac4..b7928cddd539 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3887,7 +3887,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb, err = ext4_mb_load_buddy(sb, group, &e4b); if (err) { - ext4_error(sb, "Error loading buddy information for %u", group); + ext4_warning(sb, "Error %d loading buddy information for %u", + err, group); put_bh(bitmap_bh); return 0; } @@ -4044,10 +4045,11 @@ repeat: BUG_ON(pa->pa_type != MB_INODE_PA); group = ext4_get_group_number(sb, pa->pa_pstart); - err = ext4_mb_load_buddy(sb, group, &e4b); + err = ext4_mb_load_buddy_gfp(sb, group, &e4b, + GFP_NOFS|__GFP_NOFAIL); if (err) { - ext4_error(sb, "Error loading buddy information for %u", - group); + ext4_error(sb, "Error %d loading buddy information for %u", + err, group); continue; } @@ -4303,11 +4305,14 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, spin_unlock(&lg->lg_prealloc_lock); list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) { + int err; group = ext4_get_group_number(sb, pa->pa_pstart); - if (ext4_mb_load_buddy(sb, group, &e4b)) { - ext4_error(sb, "Error loading buddy information for %u", - group); + err = ext4_mb_load_buddy_gfp(sb, group, &e4b, + GFP_NOFS|__GFP_NOFAIL); + if (err) { + ext4_error(sb, "Error %d loading buddy information for %u", + err, group); continue; } ext4_lock_group(sb, group); @@ -5127,8 +5132,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group, ret = ext4_mb_load_buddy(sb, group, &e4b); if (ret) { - ext4_error(sb, "Error in loading buddy " - "information for %u", group); + ext4_warning(sb, "Error %d loading buddy information for %u", + ret, group); return ret; } bitmap = e4b.bd_bitmap; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b81f7d46f344..404256caf9cf 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1155,12 +1155,11 @@ errout: static inline int search_dirblock(struct buffer_head *bh, struct inode *dir, struct ext4_filename *fname, - const struct qstr *d_name, unsigned int offset, struct ext4_dir_entry_2 **res_dir) { return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir, - fname, d_name, offset, res_dir); + fname, offset, res_dir); } /* @@ -1262,7 +1261,6 @@ static inline bool ext4_match(const struct ext4_filename *fname, */ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, struct inode *dir, struct ext4_filename *fname, - const struct qstr *d_name, unsigned int offset, struct ext4_dir_entry_2 **res_dir) { struct ext4_dir_entry_2 * de; @@ -1355,7 +1353,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir, if (ext4_has_inline_data(dir)) { int has_inline_data = 1; - ret = ext4_find_inline_entry(dir, &fname, d_name, res_dir, + ret = ext4_find_inline_entry(dir, &fname, res_dir, &has_inline_data); if (has_inline_data) { if (inlined) @@ -1447,7 +1445,7 @@ restart: goto next; } set_buffer_verified(bh); - i = search_dirblock(bh, dir, &fname, d_name, + i = search_dirblock(bh, dir, &fname, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (i == 1) { EXT4_I(dir)->i_dir_start_lookup = block; @@ -1488,7 +1486,6 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, { struct super_block * sb = dir->i_sb; struct dx_frame frames[2], *frame; - const struct qstr *d_name = fname->usr_fname; struct buffer_head *bh; ext4_lblk_t block; int retval; @@ -1505,7 +1502,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, if (IS_ERR(bh)) goto errout; - retval = search_dirblock(bh, dir, fname, d_name, + retval = search_dirblock(bh, dir, fname, block << EXT4_BLOCK_SIZE_BITS(sb), res_dir); if (retval == 1) @@ -1530,7 +1527,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, bh = NULL; errout: - dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name)); + dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name)); success: dx_release(frames); return bh; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0b177da9ea82..d37c81f327e7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -848,14 +848,9 @@ static inline void ext4_quota_off_umount(struct super_block *sb) { int type; - if (ext4_has_feature_quota(sb)) { - dquot_disable(sb, -1, - DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - } else { - /* Use our quota_off function to clear inode flags etc. */ - for (type = 0; type < EXT4_MAXQUOTAS; type++) - ext4_quota_off(sb, type); - } + /* Use our quota_off function to clear inode flags etc. */ + for (type = 0; type < EXT4_MAXQUOTAS; type++) + ext4_quota_off(sb, type); } #else static inline void ext4_quota_off_umount(struct super_block *sb) @@ -1179,6 +1174,9 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len, return res; } + res = dquot_initialize(inode); + if (res) + return res; retry: handle = ext4_journal_start(inode, EXT4_HT_MISC, ext4_jbd2_credits_xattr(inode)); @@ -5485,7 +5483,7 @@ static int ext4_quota_off(struct super_block *sb, int type) goto out; err = dquot_quota_off(sb, type); - if (err) + if (err || ext4_has_feature_quota(sb)) goto out_put; inode_lock(inode); @@ -5505,6 +5503,7 @@ static int ext4_quota_off(struct super_block *sb, int type) out_unlock: inode_unlock(inode); out_put: + lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL); iput(inode); return err; out: diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 8fb7ce14e6eb..5d3c2536641c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -888,6 +888,8 @@ inserted: else { u32 ref; + WARN_ON_ONCE(dquot_initialize_needed(inode)); + /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, @@ -954,6 +956,8 @@ inserted: /* We need to allocate a new block */ ext4_fsblk_t goal, block; + WARN_ON_ONCE(dquot_initialize_needed(inode)); + goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); @@ -1166,6 +1170,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, return -EINVAL; if (strlen(name) > 255) return -ERANGE; + ext4_write_lock_xattr(inode, &no_expand); error = ext4_reserve_inode_write(handle, inode, &is.iloc); @@ -1267,6 +1272,9 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name, int error, retries = 0; int credits = ext4_jbd2_credits_xattr(inode); + error = dquot_initialize(inode); + if (error) + return error; retry: handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 2185c7a040a1..fd2e651bad6d 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1078,6 +1078,7 @@ static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, { SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver); u32 *ctx = (u32 *)shash_desc_ctx(shash); + u32 retval; int err; shash->tfm = sbi->s_chksum_driver; @@ -1087,7 +1088,9 @@ static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address, err = crypto_shash_update(shash, address, length); BUG_ON(err); - return *ctx; + retval = *ctx; + barrier_data(ctx); + return retval; } static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 5a1b58f8fef4..65c88379a3a1 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -975,8 +975,15 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb) int err; char *suffix = ""; - if (sb->s_bdev) + if (sb->s_bdev) { suffix = "-fuseblk"; + /* + * sb->s_bdi points to blkdev's bdi however we want to redirect + * it to our private bdi... + */ + bdi_put(sb->s_bdi); + sb->s_bdi = &noop_backing_dev_info; + } err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev), MINOR(fc->dev), suffix); if (err) diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index f865b96374df..d2955daf17a4 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -659,7 +659,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags) struct gfs2_log_header *lh; unsigned int tail; u32 hash; - int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META; + int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC; struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO); enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state); lh = page_address(page); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 9ee4832b6f8b..2d30a6da7013 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -680,6 +680,12 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask) rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_); handle->h_buffer_credits = nblocks; + /* + * Restore the original nofs context because the journal restart + * is basically the same thing as journal stop and start. + * start_this_handle will start a new nofs context. + */ + memalloc_nofs_restore(handle->saved_alloc_context); ret = start_this_handle(journal, handle, gfp_mask); return ret; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index f5714ee01000..23542dc44a25 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -454,6 +454,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, goto out_err_free; /* fh */ + rc = -EIO; p = xdr_inline_decode(&stream, 4); if (!p) goto out_err_free; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index e9b4c3320e37..3e24392f2caa 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -398,7 +398,6 @@ extern struct file_system_type nfs4_referral_fs_type; bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t); struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); -void nfs_initialise_sb(struct super_block *); int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *, @@ -458,7 +457,6 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); /* super.c */ -void nfs_clone_super(struct super_block *, struct nfs_mount_info *); void nfs_umount_begin(struct super_block *); int nfs_statfs(struct dentry *, struct kstatfs *); int nfs_show_options(struct seq_file *, struct dentry *); diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 1a224a33a6c2..e5686be67be8 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -246,7 +246,7 @@ struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, devname = nfs_devname(dentry, page, PAGE_SIZE); if (IS_ERR(devname)) - mnt = (struct vfsmount *)devname; + mnt = ERR_CAST(devname); else mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 929d09a5310a..319a47db218d 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -177,7 +177,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, if (status) goto out; - if (!nfs_write_verifier_cmp(&res->write_res.verifier.verifier, + if (nfs_write_verifier_cmp(&res->write_res.verifier.verifier, &res->commit_res.verf->verifier)) { status = -EAGAIN; goto out; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 692a7a8bfc7a..66776f022111 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -582,7 +582,6 @@ int nfs40_walk_client_list(struct nfs_client *new, */ nfs4_schedule_path_down_recovery(pos); default: - spin_lock(&nn->nfs_client_lock); goto out; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index adc6ec28d4b5..c383d0913b54 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2094,12 +2094,26 @@ pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout); +/* + * Check for any intersection between the request and the pgio->pg_lseg, + * and if none, put this pgio->pg_lseg away. + */ +static void +pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) { + pnfs_put_lseg(pgio->pg_lseg); + pgio->pg_lseg = NULL; + } +} + void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) { u64 rd_size = req->wb_bytes; pnfs_generic_pg_check_layout(pgio); + pnfs_generic_pg_check_range(pgio, req); if (pgio->pg_lseg == NULL) { if (pgio->pg_dreq == NULL) rd_size = i_size_read(pgio->pg_inode) - req_offset(req); @@ -2131,6 +2145,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req, u64 wb_size) { pnfs_generic_pg_check_layout(pgio); + pnfs_generic_pg_check_range(pgio, req); if (pgio->pg_lseg == NULL) { pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode, req->wb_context, @@ -2191,16 +2206,10 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, seg_end = pnfs_end_offset(pgio->pg_lseg->pls_range.offset, pgio->pg_lseg->pls_range.length); req_start = req_offset(req); - WARN_ON_ONCE(req_start >= seg_end); + /* start of request is past the last byte of this segment */ - if (req_start >= seg_end) { - /* reference the new lseg */ - if (pgio->pg_ops->pg_cleanup) - pgio->pg_ops->pg_cleanup(pgio); - if (pgio->pg_ops->pg_init) - pgio->pg_ops->pg_init(pgio, req); + if (req_start >= seg_end) return 0; - } /* adjust 'size' iff there are fewer bytes left in the * segment than what nfs_generic_pg_test returned */ diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 2d05b756a8d6..99731e3e332f 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -593,6 +593,16 @@ pnfs_lseg_range_intersecting(const struct pnfs_layout_range *l1, return pnfs_is_range_intersecting(l1->offset, end1, l2->offset, end2); } +static inline bool +pnfs_lseg_request_intersecting(struct pnfs_layout_segment *lseg, struct nfs_page *req) +{ + u64 seg_last = pnfs_end_offset(lseg->pls_range.offset, lseg->pls_range.length); + u64 req_last = req_offset(req) + req->wb_bytes; + + return pnfs_is_range_intersecting(lseg->pls_range.offset, seg_last, + req_offset(req), req_last); +} + extern unsigned int layoutstats_timer; #ifdef NFS_DEBUG diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 2f3822a4a7d5..eceb4eabb064 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -2301,7 +2301,7 @@ EXPORT_SYMBOL_GPL(nfs_remount); /* * Initialise the common bits of the superblock */ -inline void nfs_initialise_sb(struct super_block *sb) +static void nfs_initialise_sb(struct super_block *sb) { struct nfs_server *server = NFS_SB(sb); @@ -2348,7 +2348,8 @@ EXPORT_SYMBOL_GPL(nfs_fill_super); /* * Finish setting up a cloned NFS2/3/4 superblock */ -void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) +static void nfs_clone_super(struct super_block *sb, + struct nfs_mount_info *mount_info) { const struct super_block *old_sb = mount_info->cloned->sb; struct nfs_server *server = NFS_SB(sb); diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 12feac6ee2fd..452334694a5d 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -334,11 +334,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, if (!p) return 0; p = xdr_decode_hyper(p, &args->offset); - args->count = ntohl(*p++); - - if (!xdr_argsize_check(rqstp, p)) - return 0; + args->count = ntohl(*p++); len = min(args->count, max_blocksize); /* set up the kvec */ @@ -352,7 +349,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, v++; } args->vlen = v; - return 1; + return xdr_argsize_check(rqstp, p); } int @@ -544,11 +541,9 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, p = decode_fh(p, &args->fh); if (!p) return 0; - if (!xdr_argsize_check(rqstp, p)) - return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); - return 1; + return xdr_argsize_check(rqstp, p); } int @@ -574,14 +569,10 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, args->verf = p; p += 2; args->dircount = ~0; args->count = ntohl(*p++); - - if (!xdr_argsize_check(rqstp, p)) - return 0; - args->count = min_t(u32, args->count, PAGE_SIZE); args->buffer = page_address(*(rqstp->rq_next_page++)); - return 1; + return xdr_argsize_check(rqstp, p); } int @@ -599,9 +590,6 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, args->dircount = ntohl(*p++); args->count = ntohl(*p++); - if (!xdr_argsize_check(rqstp, p)) - return 0; - len = args->count = min(args->count, max_blocksize); while (len > 0) { struct page *p = *(rqstp->rq_next_page++); @@ -609,7 +597,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p, args->buffer = page_address(p); len -= PAGE_SIZE; } - return 1; + + return xdr_argsize_check(rqstp, p); } int diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index c453a1998e00..dadb3bf305b2 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1769,6 +1769,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, opdesc->op_get_currentstateid(cstate, &op->u); op->status = opdesc->op_func(rqstp, cstate, &op->u); + /* Only from SEQUENCE */ + if (cstate->status == nfserr_replay_cache) { + dprintk("%s NFS4.1 replay from cache\n", __func__); + status = op->status; + goto out; + } if (!op->status) { if (opdesc->op_set_currentstateid) opdesc->op_set_currentstateid(cstate, &op->u); @@ -1779,14 +1785,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp, if (need_wrongsec_check(rqstp)) op->status = check_nfsd_access(current_fh->fh_export, rqstp); } - encode_op: - /* Only from SEQUENCE */ - if (cstate->status == nfserr_replay_cache) { - dprintk("%s NFS4.1 replay from cache\n", __func__); - status = op->status; - goto out; - } if (op->status == nfserr_replay_me) { op->replay = &cstate->replay_owner->so_replay; nfsd4_encode_replay(&resp->xdr, op); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 6a4947a3f4fa..de07ff625777 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -257,9 +257,6 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, len = args->count = ntohl(*p++); p++; /* totalcount - unused */ - if (!xdr_argsize_check(rqstp, p)) - return 0; - len = min_t(unsigned int, len, NFSSVC_MAXBLKSIZE_V2); /* set up somewhere to store response. @@ -275,7 +272,7 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p, v++; } args->vlen = v; - return 1; + return xdr_argsize_check(rqstp, p); } int @@ -365,11 +362,9 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli p = decode_fh(p, &args->fh); if (!p) return 0; - if (!xdr_argsize_check(rqstp, p)) - return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); - return 1; + return xdr_argsize_check(rqstp, p); } int @@ -407,11 +402,9 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p, args->cookie = ntohl(*p++); args->count = ntohl(*p++); args->count = min_t(u32, args->count, PAGE_SIZE); - if (!xdr_argsize_check(rqstp, p)) - return 0; args->buffer = page_address(*(rqstp->rq_next_page++)); - return 1; + return xdr_argsize_check(rqstp, p); } /* diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 358258364616..4690cd75d8d7 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -159,7 +159,7 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent, PTR_ERR(dent_inode)); kfree(name); /* Return the error code. */ - return (struct dentry *)dent_inode; + return ERR_CAST(dent_inode); } /* It is guaranteed that @name is no longer allocated at this point. */ if (MREF_ERR(mref) == -ENOENT) { diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 827fc9809bc2..9f88188060db 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -119,7 +119,7 @@ check_err: if (IS_ERR(inode)) { mlog_errno(PTR_ERR(inode)); - result = (void *)inode; + result = ERR_CAST(inode); goto bail; } diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig index 0daac5112f7a..c0c9683934b7 100644 --- a/fs/overlayfs/Kconfig +++ b/fs/overlayfs/Kconfig @@ -1,5 +1,6 @@ config OVERLAY_FS tristate "Overlay filesystem support" + select EXPORTFS help An overlay filesystem combines two filesystems - an 'upper' filesystem and a 'lower' filesystem. When a name exists in both filesystems, the diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 9008ab9fbd2e..7a44533f4bbf 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -300,7 +300,11 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower, return PTR_ERR(fh); } - err = ovl_do_setxattr(upper, OVL_XATTR_ORIGIN, fh, fh ? fh->len : 0, 0); + /* + * Do not fail when upper doesn't support xattrs. + */ + err = ovl_check_setxattr(dentry, upper, OVL_XATTR_ORIGIN, fh, + fh ? fh->len : 0, 0); kfree(fh); return err; @@ -342,13 +346,14 @@ static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir, if (tmpfile) temp = ovl_do_tmpfile(upperdir, stat->mode); else - temp = ovl_lookup_temp(workdir, dentry); - err = PTR_ERR(temp); - if (IS_ERR(temp)) - goto out1; - + temp = ovl_lookup_temp(workdir); err = 0; - if (!tmpfile) + if (IS_ERR(temp)) { + err = PTR_ERR(temp); + temp = NULL; + } + + if (!err && !tmpfile) err = ovl_create_real(wdir, temp, &cattr, NULL, true); if (new_creds) { @@ -454,6 +459,11 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, ovl_path_upper(parent, &parentpath); upperdir = parentpath.dentry; + /* Mark parent "impure" because it may now contain non-pure upper */ + err = ovl_set_impure(parent, upperdir); + if (err) + return err; + err = vfs_getattr(&parentpath, &pstat, STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT); if (err) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 723b98b90698..a63a71656e9b 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -41,7 +41,7 @@ void ovl_cleanup(struct inode *wdir, struct dentry *wdentry) } } -struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry) +struct dentry *ovl_lookup_temp(struct dentry *workdir) { struct dentry *temp; char name[20]; @@ -68,7 +68,7 @@ static struct dentry *ovl_whiteout(struct dentry *workdir, struct dentry *whiteout; struct inode *wdir = workdir->d_inode; - whiteout = ovl_lookup_temp(workdir, dentry); + whiteout = ovl_lookup_temp(workdir); if (IS_ERR(whiteout)) return whiteout; @@ -127,17 +127,28 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry, return err; } -static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry) +static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper, + int xerr) { int err; - err = ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0); + err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr); if (!err) ovl_dentry_set_opaque(dentry); return err; } +static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry) +{ + /* + * Fail with -EIO when trying to create opaque dir and upper doesn't + * support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to + * return a specific error for noxattr case. + */ + return ovl_set_opaque_xerr(dentry, upperdentry, -EIO); +} + /* Common operations required to be done after creation of file on upper */ static void ovl_instantiate(struct dentry *dentry, struct inode *inode, struct dentry *newdentry, bool hardlink) @@ -162,6 +173,11 @@ static bool ovl_type_merge(struct dentry *dentry) return OVL_TYPE_MERGE(ovl_path_type(dentry)); } +static bool ovl_type_origin(struct dentry *dentry) +{ + return OVL_TYPE_ORIGIN(ovl_path_type(dentry)); +} + static int ovl_create_upper(struct dentry *dentry, struct inode *inode, struct cattr *attr, struct dentry *hardlink) { @@ -250,7 +266,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry, if (upper->d_parent->d_inode != udir) goto out_unlock; - opaquedir = ovl_lookup_temp(workdir, dentry); + opaquedir = ovl_lookup_temp(workdir); err = PTR_ERR(opaquedir); if (IS_ERR(opaquedir)) goto out_unlock; @@ -382,7 +398,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode, if (err) goto out; - newdentry = ovl_lookup_temp(workdir, dentry); + newdentry = ovl_lookup_temp(workdir); err = PTR_ERR(newdentry); if (IS_ERR(newdentry)) goto out_unlock; @@ -846,18 +862,16 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir) if (IS_ERR(redirect)) return PTR_ERR(redirect); - err = ovl_do_setxattr(ovl_dentry_upper(dentry), OVL_XATTR_REDIRECT, - redirect, strlen(redirect), 0); + err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry), + OVL_XATTR_REDIRECT, + redirect, strlen(redirect), -EXDEV); if (!err) { spin_lock(&dentry->d_lock); ovl_dentry_set_redirect(dentry, redirect); spin_unlock(&dentry->d_lock); } else { kfree(redirect); - if (err == -EOPNOTSUPP) - ovl_clear_redirect_dir(dentry->d_sb); - else - pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err); + pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err); /* Fall back to userspace copy-up */ err = -EXDEV; } @@ -943,6 +957,25 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, old_upperdir = ovl_dentry_upper(old->d_parent); new_upperdir = ovl_dentry_upper(new->d_parent); + if (!samedir) { + /* + * When moving a merge dir or non-dir with copy up origin into + * a new parent, we are marking the new parent dir "impure". + * When ovl_iterate() iterates an "impure" upper dir, it will + * lookup the origin inodes of the entries to fill d_ino. + */ + if (ovl_type_origin(old)) { + err = ovl_set_impure(new->d_parent, new_upperdir); + if (err) + goto out_revert_creds; + } + if (!overwrite && ovl_type_origin(new)) { + err = ovl_set_impure(old->d_parent, old_upperdir); + if (err) + goto out_revert_creds; + } + } + trap = lock_rename(new_upperdir, old_upperdir); olddentry = lookup_one_len(old->d_name.name, old_upperdir, @@ -992,7 +1025,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, if (ovl_type_merge_or_lower(old)) err = ovl_set_redirect(old, samedir); else if (!old_opaque && ovl_type_merge(new->d_parent)) - err = ovl_set_opaque(old, olddentry); + err = ovl_set_opaque_xerr(old, olddentry, -EXDEV); if (err) goto out_dput; } @@ -1000,7 +1033,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old, if (ovl_type_merge_or_lower(new)) err = ovl_set_redirect(new, samedir); else if (!new_opaque && ovl_type_merge(old->d_parent)) - err = ovl_set_opaque(new, newdentry); + err = ovl_set_opaque_xerr(new, newdentry, -EXDEV); if (err) goto out_dput; } diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index ad9547f82da5..d613e2c41242 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -240,6 +240,16 @@ int ovl_xattr_get(struct dentry *dentry, const char *name, return res; } +static bool ovl_can_list(const char *s) +{ + /* List all non-trusted xatts */ + if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0) + return true; + + /* Never list trusted.overlay, list other trusted for superuser only */ + return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN); +} + ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) { struct dentry *realdentry = ovl_dentry_real(dentry); @@ -263,7 +273,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return -EIO; len -= slen; - if (ovl_is_private_xattr(s)) { + if (!ovl_can_list(s)) { res -= slen; memmove(s, s + slen, len); } else { diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index bad0f665a635..f3136c31e72a 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -169,17 +169,7 @@ invalid: static bool ovl_is_opaquedir(struct dentry *dentry) { - int res; - char val; - - if (!d_is_dir(dentry)) - return false; - - res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1); - if (res == 1 && val == 'y') - return true; - - return false; + return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE); } static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d, @@ -351,6 +341,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int ctr = 0; struct inode *inode = NULL; bool upperopaque = false; + bool upperimpure = false; char *upperredirect = NULL; struct dentry *this; unsigned int i; @@ -395,6 +386,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, poe = roe; } upperopaque = d.opaque; + if (upperdentry && d.is_dir) + upperimpure = ovl_is_impuredir(upperdentry); } if (!d.stop && poe->numlower) { @@ -463,6 +456,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, revert_creds(old_cred); oe->opaque = upperopaque; + oe->impure = upperimpure; oe->redirect = upperredirect; oe->__upperdentry = upperdentry; memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr); diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index caa36cb9c46d..0623cebeefff 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -24,6 +24,7 @@ enum ovl_path_type { #define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque" #define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect" #define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin" +#define OVL_XATTR_IMPURE OVL_XATTR_PREFIX "impure" /* * The tuple (fh,uuid) is a universal unique identifier for a copy up origin, @@ -203,10 +204,10 @@ struct dentry *ovl_dentry_real(struct dentry *dentry); struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry); void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache); bool ovl_dentry_is_opaque(struct dentry *dentry); +bool ovl_dentry_is_impure(struct dentry *dentry); bool ovl_dentry_is_whiteout(struct dentry *dentry); void ovl_dentry_set_opaque(struct dentry *dentry); bool ovl_redirect_dir(struct super_block *sb); -void ovl_clear_redirect_dir(struct super_block *sb); const char *ovl_dentry_get_redirect(struct dentry *dentry); void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect); void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry); @@ -219,6 +220,17 @@ bool ovl_is_whiteout(struct dentry *dentry); struct file *ovl_path_open(struct path *path, int flags); int ovl_copy_up_start(struct dentry *dentry); void ovl_copy_up_end(struct dentry *dentry); +bool ovl_check_dir_xattr(struct dentry *dentry, const char *name); +int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry, + const char *name, const void *value, size_t size, + int xerr); +int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry); + +static inline bool ovl_is_impuredir(struct dentry *dentry) +{ + return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE); +} + /* namei.c */ int ovl_path_next(int idx, struct dentry *dentry, struct path *path); @@ -263,7 +275,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to) /* dir.c */ extern const struct inode_operations ovl_dir_inode_operations; -struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry); +struct dentry *ovl_lookup_temp(struct dentry *workdir); struct cattr { dev_t rdev; umode_t mode; diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index b2023ddb8532..34bc4a9f5c61 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -28,6 +28,7 @@ struct ovl_fs { /* creds of process who forced instantiation of super block */ const struct cred *creator_cred; bool tmpfile; + bool noxattr; wait_queue_head_t copyup_wq; /* sb common to all layers */ struct super_block *same_sb; @@ -42,6 +43,7 @@ struct ovl_entry { u64 version; const char *redirect; bool opaque; + bool impure; bool copying; }; struct rcu_head rcu; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 9828b7de8999..4882ffb37bae 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -891,6 +891,19 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) dput(temp); else pr_warn("overlayfs: upper fs does not support tmpfile.\n"); + + /* + * Check if upper/work fs supports trusted.overlay.* + * xattr + */ + err = ovl_do_setxattr(ufs->workdir, OVL_XATTR_OPAQUE, + "0", 1, 0); + if (err) { + ufs->noxattr = true; + pr_warn("overlayfs: upper fs does not support xattr.\n"); + } else { + vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE); + } } } @@ -961,7 +974,10 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) path_put(&workpath); kfree(lowertmp); - oe->__upperdentry = upperpath.dentry; + if (upperpath.dentry) { + oe->__upperdentry = upperpath.dentry; + oe->impure = ovl_is_impuredir(upperpath.dentry); + } for (i = 0; i < numlower; i++) { oe->lowerstack[i].dentry = stack[i].dentry; oe->lowerstack[i].mnt = ufs->lower_mnt[i]; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index cfdea47313a1..809048913889 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -175,6 +175,13 @@ bool ovl_dentry_is_opaque(struct dentry *dentry) return oe->opaque; } +bool ovl_dentry_is_impure(struct dentry *dentry) +{ + struct ovl_entry *oe = dentry->d_fsdata; + + return oe->impure; +} + bool ovl_dentry_is_whiteout(struct dentry *dentry) { return !dentry->d_inode && ovl_dentry_is_opaque(dentry); @@ -191,14 +198,7 @@ bool ovl_redirect_dir(struct super_block *sb) { struct ovl_fs *ofs = sb->s_fs_info; - return ofs->config.redirect_dir; -} - -void ovl_clear_redirect_dir(struct super_block *sb) -{ - struct ovl_fs *ofs = sb->s_fs_info; - - ofs->config.redirect_dir = false; + return ofs->config.redirect_dir && !ofs->noxattr; } const char *ovl_dentry_get_redirect(struct dentry *dentry) @@ -303,3 +303,59 @@ void ovl_copy_up_end(struct dentry *dentry) wake_up_locked(&ofs->copyup_wq); spin_unlock(&ofs->copyup_wq.lock); } + +bool ovl_check_dir_xattr(struct dentry *dentry, const char *name) +{ + int res; + char val; + + if (!d_is_dir(dentry)) + return false; + + res = vfs_getxattr(dentry, name, &val, 1); + if (res == 1 && val == 'y') + return true; + + return false; +} + +int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry, + const char *name, const void *value, size_t size, + int xerr) +{ + int err; + struct ovl_fs *ofs = dentry->d_sb->s_fs_info; + + if (ofs->noxattr) + return xerr; + + err = ovl_do_setxattr(upperdentry, name, value, size, 0); + + if (err == -EOPNOTSUPP) { + pr_warn("overlayfs: cannot set %s xattr on upper\n", name); + ofs->noxattr = true; + return xerr; + } + + return err; +} + +int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry) +{ + int err; + struct ovl_entry *oe = dentry->d_fsdata; + + if (oe->impure) + return 0; + + /* + * Do not fail when upper doesn't support xattrs. + * Upper inodes won't have origin nor redirect xattr anyway. + */ + err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE, + "y", 1, 0); + if (!err) + oe->impure = true; + + return err; +} diff --git a/fs/proc/base.c b/fs/proc/base.c index 45f6bf68fff3..f1e1927ccd48 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -821,7 +821,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf, if (!mmget_not_zero(mm)) goto free; - flags = write ? FOLL_WRITE : 0; + flags = FOLL_FORCE | (write ? FOLL_WRITE : 0); while (count > 0) { int this_len = min_t(int, count, PAGE_SIZE); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ebf80c7739e1..48813aeaab80 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1512,6 +1512,22 @@ int dquot_initialize(struct inode *inode) } EXPORT_SYMBOL(dquot_initialize); +bool dquot_initialize_needed(struct inode *inode) +{ + struct dquot **dquots; + int i; + + if (!dquot_active(inode)) + return false; + + dquots = i_dquot(inode); + for (i = 0; i < MAXQUOTAS; i++) + if (!dquots[i] && sb_has_quota_active(inode->i_sb, i)) + return true; + return false; +} +EXPORT_SYMBOL(dquot_initialize_needed); + /* * Release all quotas referenced by inode. * diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c index da01f497180a..39bb1e838d8d 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -1112,7 +1112,7 @@ static int flush_commit_list(struct super_block *s, depth = reiserfs_write_unlock_nested(s); if (reiserfs_barrier_flush(s)) __sync_dirty_buffer(jl->j_commit_bh, - REQ_PREFLUSH | REQ_FUA); + REQ_SYNC | REQ_PREFLUSH | REQ_FUA); else sync_dirty_buffer(jl->j_commit_bh); reiserfs_write_lock_nested(s, depth); @@ -1271,7 +1271,7 @@ static int _update_journal_header_block(struct super_block *sb, if (reiserfs_barrier_flush(sb)) __sync_dirty_buffer(journal->j_header_bh, - REQ_PREFLUSH | REQ_FUA); + REQ_SYNC | REQ_PREFLUSH | REQ_FUA); else sync_dirty_buffer(journal->j_header_bh); diff --git a/fs/stat.c b/fs/stat.c index f494b182c7c7..c35610845ab1 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -672,6 +672,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes) inode->i_bytes -= 512; } } +EXPORT_SYMBOL(__inode_add_bytes); void inode_add_bytes(struct inode *inode, loff_t bytes) { diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index a0376a2c1c29..d642cc0a8271 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -82,7 +82,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count) ufs_error (sb, "ufs_free_fragments", "bit already cleared for fragment %u", i); } - + + inode_sub_bytes(inode, count << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, count); uspi->cs_total.cs_nffree += count; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count); @@ -184,6 +185,7 @@ do_more: ufs_error(sb, "ufs_free_blocks", "freeing free fragment"); } ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); + inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) ufs_clusteracct (sb, ucpi, blkno, 1); @@ -494,6 +496,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment, return 0; } +static bool try_add_frags(struct inode *inode, unsigned frags) +{ + unsigned size = frags * i_blocksize(inode); + spin_lock(&inode->i_lock); + __inode_add_bytes(inode, size); + if (unlikely((u32)inode->i_blocks != inode->i_blocks)) { + __inode_sub_bytes(inode, size); + spin_unlock(&inode->i_lock); + return false; + } + spin_unlock(&inode->i_lock); + return true; +} + static u64 ufs_add_fragments(struct inode *inode, u64 fragment, unsigned oldcount, unsigned newcount) { @@ -530,6 +546,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment, for (i = oldcount; i < newcount; i++) if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i)) return 0; + + if (!try_add_frags(inode, count)) + return 0; /* * Block can be extended */ @@ -647,6 +666,7 @@ cg_found: ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i); i = uspi->s_fpb - count; + inode_sub_bytes(inode, i << uspi->s_fshift); fs32_add(sb, &ucg->cg_cs.cs_nffree, i); uspi->cs_total.cs_nffree += i; fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i); @@ -657,6 +677,8 @@ cg_found: result = ufs_bitmap_search (sb, ucpi, goal, allocsize); if (result == INVBLOCK) return 0; + if (!try_add_frags(inode, count)) + return 0; for (i = 0; i < count; i++) ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i); @@ -716,6 +738,8 @@ norot: return INVBLOCK; ucpi->c_rotor = result; gotit: + if (!try_add_frags(inode, uspi->s_fpb)) + return 0; blkno = ufs_fragstoblks(result); ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno); if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD) diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 7e41aee7b69a..da553ffec85b 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to, p = ufs_get_direct_data_ptr(uspi, ufsi, block); tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p), - new_size, err, locked_page); + new_size - (lastfrag & uspi->s_fpbmask), err, + locked_page); return tmp != 0; } @@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index, goal += uspi->s_fpb; } tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment), - goal, uspi->s_fpb, err, locked_page); + goal, nfrags, err, locked_page); if (!tmp) { *err = -ENOSPC; @@ -402,7 +403,9 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff if (!create) { phys64 = ufs_frag_map(inode, offsets, depth); - goto out; + if (phys64) + map_bh(bh_result, sb, phys64 + frag); + return 0; } /* This code entered only while writing ....? */ @@ -841,8 +844,11 @@ void ufs_evict_inode(struct inode * inode) truncate_inode_pages_final(&inode->i_data); if (want_delete) { inode->i_size = 0; - if (inode->i_blocks) + if (inode->i_blocks && + (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) ufs_truncate_blocks(inode); + ufs_update_inode(inode, inode_needs_sync(inode)); } invalidate_inode_buffers(inode); @@ -1100,7 +1106,7 @@ out: return err; } -static void __ufs_truncate_blocks(struct inode *inode) +static void ufs_truncate_blocks(struct inode *inode) { struct ufs_inode_info *ufsi = UFS_I(inode); struct super_block *sb = inode->i_sb; @@ -1183,7 +1189,7 @@ static int ufs_truncate(struct inode *inode, loff_t size) truncate_setsize(inode, size); - __ufs_truncate_blocks(inode); + ufs_truncate_blocks(inode); inode->i_mtime = inode->i_ctime = current_time(inode); mark_inode_dirty(inode); out: @@ -1191,16 +1197,6 @@ out: return err; } -static void ufs_truncate_blocks(struct inode *inode) -{ - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode))) - return; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - return; - __ufs_truncate_blocks(inode); -} - int ufs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); diff --git a/fs/ufs/super.c b/fs/ufs/super.c index 131b2b77c818..878cc6264f1a 100644 --- a/fs/ufs/super.c +++ b/fs/ufs/super.c @@ -746,6 +746,23 @@ static void ufs_put_super(struct super_block *sb) return; } +static u64 ufs_max_bytes(struct super_block *sb) +{ + struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi; + int bits = uspi->s_apbshift; + u64 res; + + if (bits > 21) + res = ~0ULL; + else + res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) + + (1LL << (3*bits)); + + if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift)) + return MAX_LFS_FILESIZE; + return res << uspi->s_bshift; +} + static int ufs_fill_super(struct super_block *sb, void *data, int silent) { struct ufs_sb_info * sbi; @@ -812,9 +829,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent) uspi->s_dirblksize = UFS_SECTOR_SIZE; super_block_offset=UFS_SBLOCK; - /* Keep 2Gig file limit. Some UFS variants need to override - this but as I don't know which I'll let those in the know loosen - the rules */ + sb->s_maxbytes = MAX_LFS_FILESIZE; + switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) { case UFS_MOUNT_UFSTYPE_44BSD: UFSD("ufstype=44bsd\n"); @@ -1212,6 +1228,7 @@ magic_found: "fast symlink size (%u)\n", uspi->s_maxsymlinklen); uspi->s_maxsymlinklen = maxsymlen; } + sb->s_maxbytes = ufs_max_bytes(sb); sb->s_max_links = UFS_LINK_MAX; inode = ufs_iget(sb, UFS_ROOTINO); diff --git a/fs/ufs/util.h b/fs/ufs/util.h index b7fbf53dbc81..398019fb1448 100644 --- a/fs/ufs/util.h +++ b/fs/ufs/util.h @@ -473,15 +473,19 @@ static inline unsigned _ubh_find_last_zero_bit_( static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi, struct ufs_buffer_head * ubh, unsigned begin, unsigned block) { + u8 mask; switch (uspi->s_fpb) { case 8: return (*ubh_get_addr (ubh, begin + block) == 0xff); case 4: - return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2))); + mask = 0x0f << ((block & 0x01) << 2); + return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask; case 2: - return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1))); + mask = 0x03 << ((block & 0x03) << 1); + return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask; case 1: - return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07))); + mask = 0x01 << (block & 0x07); + return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask; } return 0; } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index f02eb7673392..a7048eafa8e6 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1280,7 +1280,6 @@ xfs_bmap_read_extents( xfs_bmbt_rec_t *frp; xfs_fsblock_t nextbno; xfs_extnum_t num_recs; - xfs_extnum_t start; num_recs = xfs_btree_get_numrecs(block); if (unlikely(i + num_recs > room)) { @@ -1303,7 +1302,6 @@ xfs_bmap_read_extents( * Copy records into the extent records. */ frp = XFS_BMBT_REC_ADDR(mp, block, 1); - start = i; for (j = 0; j < num_recs; j++, i++, frp++) { xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i); trp->l0 = be64_to_cpu(frp->l0); @@ -2065,8 +2063,10 @@ xfs_bmap_add_extent_delay_real( } temp = xfs_bmap_worst_indlen(bma->ip, temp); temp2 = xfs_bmap_worst_indlen(bma->ip, temp2); - diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); + diff = (int)(temp + temp2 - + (startblockval(PREV.br_startblock) - + (bma->cur ? + bma->cur->bc_private.b.allocated : 0))); if (diff > 0) { error = xfs_mod_fdblocks(bma->ip->i_mount, -((int64_t)diff), false); @@ -2123,7 +2123,6 @@ xfs_bmap_add_extent_delay_real( temp = da_new; if (bma->cur) temp += bma->cur->bc_private.b.allocated; - ASSERT(temp <= da_old); if (temp < da_old) xfs_mod_fdblocks(bma->ip->i_mount, (int64_t)(da_old - temp), false); diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5392674bf893..3a673ba201aa 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4395,7 +4395,7 @@ xfs_btree_visit_blocks( xfs_btree_readahead_ptr(cur, ptr, 1); /* save for the next iteration of the loop */ - lptr = *ptr; + xfs_btree_copy_ptrs(cur, &lptr, ptr, 1); } /* for each buffer in the level */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index b177ef33cd4c..82a38d86ebad 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1629,13 +1629,28 @@ xfs_refcount_recover_cow_leftovers( if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START) return -EOPNOTSUPP; - error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); + INIT_LIST_HEAD(&debris); + + /* + * In this first part, we use an empty transaction to gather up + * all the leftover CoW extents so that we can subsequently + * delete them. The empty transaction is used to avoid + * a buffer lock deadlock if there happens to be a loop in the + * refcountbt because we're allowed to re-grab a buffer that is + * already attached to our transaction. When we're done + * recording the CoW debris we cancel the (empty) transaction + * and everything goes away cleanly. + */ + error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; - cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL); + + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); /* Find all the leftover CoW staging extents. */ - INIT_LIST_HEAD(&debris); memset(&low, 0, sizeof(low)); memset(&high, 0, sizeof(high)); low.rc.rc_startblock = XFS_REFC_COW_START; @@ -1645,10 +1660,11 @@ xfs_refcount_recover_cow_leftovers( if (error) goto out_cursor; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); - xfs_buf_relse(agbp); + xfs_trans_brelse(tp, agbp); + xfs_trans_cancel(tp); /* Now iterate the list to free the leftovers */ - list_for_each_entry(rr, &debris, rr_list) { + list_for_each_entry_safe(rr, n, &debris, rr_list) { /* Set up transaction. */ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp); if (error) @@ -1676,8 +1692,16 @@ xfs_refcount_recover_cow_leftovers( error = xfs_trans_commit(tp); if (error) goto out_free; + + list_del(&rr->rr_list); + kmem_free(rr); } + return error; +out_defer: + xfs_defer_cancel(&dfops); +out_trans: + xfs_trans_cancel(tp); out_free: /* Free the leftover list */ list_for_each_entry_safe(rr, n, &debris, rr_list) { @@ -1688,11 +1712,6 @@ out_free: out_cursor: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); - xfs_buf_relse(agbp); - goto out_free; - -out_defer: - xfs_defer_cancel(&dfops); - xfs_trans_cancel(tp); - goto out_free; + xfs_trans_brelse(tp, agbp); + goto out_trans; } diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 2b954308a1d6..9e3cc2146d5b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -582,9 +582,13 @@ xfs_getbmap( } break; default: + /* Local format data forks report no extents. */ + if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) { + bmv->bmv_entries = 0; + return 0; + } if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS && - ip->i_d.di_format != XFS_DINODE_FMT_BTREE && - ip->i_d.di_format != XFS_DINODE_FMT_LOCAL) + ip->i_d.di_format != XFS_DINODE_FMT_BTREE) return -EINVAL; if (xfs_get_extsz_hint(ip) || @@ -712,7 +716,7 @@ xfs_getbmap( * extents. */ if (map[i].br_startblock == DELAYSTARTBLOCK && - map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) + map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) ASSERT((iflags & BMV_IF_DELALLOC) != 0); if (map[i].br_startblock == HOLESTARTBLOCK && diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 62fa39276a24..07b77b73b024 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -97,12 +97,16 @@ static inline void xfs_buf_ioacct_inc( struct xfs_buf *bp) { - if (bp->b_flags & (XBF_NO_IOACCT|_XBF_IN_FLIGHT)) + if (bp->b_flags & XBF_NO_IOACCT) return; ASSERT(bp->b_flags & XBF_ASYNC); - bp->b_flags |= _XBF_IN_FLIGHT; - percpu_counter_inc(&bp->b_target->bt_io_count); + spin_lock(&bp->b_lock); + if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) { + bp->b_state |= XFS_BSTATE_IN_FLIGHT; + percpu_counter_inc(&bp->b_target->bt_io_count); + } + spin_unlock(&bp->b_lock); } /* @@ -110,14 +114,24 @@ xfs_buf_ioacct_inc( * freed and unaccount from the buftarg. */ static inline void -xfs_buf_ioacct_dec( +__xfs_buf_ioacct_dec( struct xfs_buf *bp) { - if (!(bp->b_flags & _XBF_IN_FLIGHT)) - return; + ASSERT(spin_is_locked(&bp->b_lock)); - bp->b_flags &= ~_XBF_IN_FLIGHT; - percpu_counter_dec(&bp->b_target->bt_io_count); + if (bp->b_state & XFS_BSTATE_IN_FLIGHT) { + bp->b_state &= ~XFS_BSTATE_IN_FLIGHT; + percpu_counter_dec(&bp->b_target->bt_io_count); + } +} + +static inline void +xfs_buf_ioacct_dec( + struct xfs_buf *bp) +{ + spin_lock(&bp->b_lock); + __xfs_buf_ioacct_dec(bp); + spin_unlock(&bp->b_lock); } /* @@ -149,9 +163,9 @@ xfs_buf_stale( * unaccounted (released to LRU) before that occurs. Drop in-flight * status now to preserve accounting consistency. */ - xfs_buf_ioacct_dec(bp); - spin_lock(&bp->b_lock); + __xfs_buf_ioacct_dec(bp); + atomic_set(&bp->b_lru_ref, 0); if (!(bp->b_state & XFS_BSTATE_DISPOSE) && (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru))) @@ -979,12 +993,12 @@ xfs_buf_rele( * ensures the decrement occurs only once per-buf. */ if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru)) - xfs_buf_ioacct_dec(bp); + __xfs_buf_ioacct_dec(bp); goto out_unlock; } /* the last reference has been dropped ... */ - xfs_buf_ioacct_dec(bp); + __xfs_buf_ioacct_dec(bp); if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { /* * If the buffer is added to the LRU take a new reference to the diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8d1d44f87ce9..1508121f29f2 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -63,7 +63,6 @@ typedef enum { #define _XBF_KMEM (1 << 21)/* backed by heap memory */ #define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */ #define _XBF_COMPOUND (1 << 23)/* compound buffer */ -#define _XBF_IN_FLIGHT (1 << 25) /* I/O in flight, for accounting purposes */ typedef unsigned int xfs_buf_flags_t; @@ -84,14 +83,14 @@ typedef unsigned int xfs_buf_flags_t; { _XBF_PAGES, "PAGES" }, \ { _XBF_KMEM, "KMEM" }, \ { _XBF_DELWRI_Q, "DELWRI_Q" }, \ - { _XBF_COMPOUND, "COMPOUND" }, \ - { _XBF_IN_FLIGHT, "IN_FLIGHT" } + { _XBF_COMPOUND, "COMPOUND" } /* * Internal state flags. */ #define XFS_BSTATE_DISPOSE (1 << 0) /* buffer being discarded */ +#define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */ /* * The xfs_buftarg contains 2 notions of "sector size" - diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 35703a801372..5fb5a0958a14 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1043,49 +1043,17 @@ xfs_find_get_desired_pgoff( index = startoff >> PAGE_SHIFT; endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); - end = endoff >> PAGE_SHIFT; + end = (endoff - 1) >> PAGE_SHIFT; do { int want; unsigned nr_pages; unsigned int i; - want = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + 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; - } - break; - } - - /* - * At lease we found one page. If this is the first time we - * step into the loop, and if the first page index offset is - * greater than the given search offset, a hole was found. - */ - if (type == HOLE_OFF && lastoff == startoff && - lastoff < page_offset(pvec.pages[0])) { - found = true; + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1098,18 +1066,18 @@ xfs_find_get_desired_pgoff( * file mapping. However, page->index will not change * because we have a reference on the page. * - * Searching done if the page index is out of range. - * If the current offset is not reaches the end of - * the specified search range, there should be a hole - * between them. + * If current page offset is beyond where we've ended, + * we've found a hole. */ - if (page->index > end) { - if (type == HOLE_OFF && lastoff < endoff) { - *offset = lastoff; - found = true; - } + if (type == HOLE_OFF && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { + found = true; + *offset = lastoff; goto out; } + /* Searching done if the page index is out of range. */ + if (page->index > end) + goto out; lock_page(page); /* @@ -1151,21 +1119,20 @@ 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_fsmap.c b/fs/xfs/xfs_fsmap.c index 3683819887a5..814ed729881d 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -828,6 +828,7 @@ xfs_getfsmap( struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; struct xfs_getfsmap_info info = { NULL }; + bool use_rmap; int i; int error = 0; @@ -837,12 +838,14 @@ xfs_getfsmap( !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1])) return -EINVAL; + use_rmap = capable(CAP_SYS_ADMIN) && + xfs_sb_version_hasrmapbt(&mp->m_sb); head->fmh_entries = 0; /* Set up our device handlers. */ memset(handlers, 0, sizeof(handlers)); handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev); - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) + if (use_rmap) handlers[0].fn = xfs_getfsmap_datadev_rmapbt; else handlers[0].fn = xfs_getfsmap_datadev_bnobt; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index a63f61c256bd..94e5bdf7304c 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1068,7 +1068,7 @@ xfs_file_iomap_begin( /* optionally associate a dax device with the iomap bdev */ bdev = iomap->bdev; if (blk_queue_dax(bdev->bd_queue)) - iomap->dax_dev = dax_get_by_host(bdev->bd_disk->disk_name); + iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name); else iomap->dax_dev = NULL; @@ -1149,7 +1149,7 @@ xfs_file_iomap_end( unsigned flags, struct iomap *iomap) { - put_dax(iomap->dax_dev); + fs_put_dax(iomap->dax_dev); if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC) return xfs_file_iomap_end_delalloc(XFS_I(inode), offset, length, written, iomap); |