diff options
Diffstat (limited to 'fs')
57 files changed, 918 insertions, 752 deletions
diff --git a/fs/affs/file.c b/fs/affs/file.c index 0548c53f41d5..22fc7c802d69 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to) pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino, page->index, to); BUG_ON(to > PAGE_CACHE_SIZE); - kmap(page); - data = page_address(page); bsize = AFFS_SB(sb)->s_data_blksize; tmp = page->index << PAGE_CACHE_SHIFT; bidx = tmp / bsize; @@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to) return PTR_ERR(bh); tmp = min(bsize - boff, to - pos); BUG_ON(pos + tmp > to || tmp > bsize); + data = kmap_atomic(page); memcpy(data + pos, AFFS_DATA(bh) + boff, tmp); + kunmap_atomic(data); affs_brelse(bh); bidx++; pos += tmp; boff = 0; } flush_dcache_page(page); - kunmap(page); return 0; } diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c index c6d7d3dbd52a..75dd739ac3e6 100644 --- a/fs/autofs4/root.c +++ b/fs/autofs4/root.c @@ -537,8 +537,6 @@ static struct dentry *autofs4_lookup(struct inode *dir, struct dentry *dentry, u ino->dentry = dentry; autofs4_add_active(dentry); - - d_instantiate(dentry, NULL); } return NULL; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 7b9cd49622b1..39b3a174a425 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1730,43 +1730,25 @@ static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return __dax_fault(vma, vmf, blkdev_get_block, NULL); } -static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) -{ - return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); -} - -static void blkdev_vm_open(struct vm_area_struct *vma) +static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma, + struct vm_fault *vmf) { - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count++; - inode_unlock(bd_inode); + return dax_pfn_mkwrite(vma, vmf); } -static void blkdev_vm_close(struct vm_area_struct *vma) +static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags) { - struct inode *bd_inode = bdev_file_inode(vma->vm_file); - struct block_device *bdev = I_BDEV(bd_inode); - - inode_lock(bd_inode); - bdev->bd_map_count--; - inode_unlock(bd_inode); + return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); } static const struct vm_operations_struct blkdev_dax_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = blkdev_dax_fault, .pmd_fault = blkdev_dax_pmd_fault, - .pfn_mkwrite = blkdev_dax_fault, + .pfn_mkwrite = blkdev_dax_pfn_mkwrite, }; static const struct vm_operations_struct blkdev_default_vm_ops = { - .open = blkdev_vm_open, - .close = blkdev_vm_close, .fault = filemap_fault, .map_pages = filemap_map_pages, }; @@ -1774,18 +1756,14 @@ static const struct vm_operations_struct blkdev_default_vm_ops = { static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *bd_inode = bdev_file_inode(file); - struct block_device *bdev = I_BDEV(bd_inode); file_accessed(file); - inode_lock(bd_inode); - bdev->bd_map_count++; if (IS_DAX(bd_inode)) { vma->vm_ops = &blkdev_dax_vm_ops; vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; } else { vma->vm_ops = &blkdev_default_vm_ops; } - inode_unlock(bd_inode); return 0; } diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index 88d9af3d4581..5fb60ea7eee2 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq, list_add_tail(&work->ordered_list, &wq->ordered_list); spin_unlock_irqrestore(&wq->list_lock, flags); } - queue_work(wq->normal_wq, &work->normal_work); trace_btrfs_work_queued(work); + queue_work(wq->normal_wq, &work->normal_work); } void btrfs_queue_work(struct btrfs_workqueue *wq, diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b90cd3776f8e..f6dac40f87ff 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1406,7 +1406,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { - btrfs_tree_read_unlock_blocking(eb); + if (!path->skip_locking) + btrfs_tree_read_unlock_blocking(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, @@ -1426,9 +1427,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { - atomic_inc(&eb->refs); - btrfs_tree_read_lock(eb); - btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + if (!path->skip_locking) + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + path->nodes[0] = NULL; + path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index c473c42d7d6c..3346cd8f9910 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -637,11 +637,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, faili = nr_pages - 1; cb->nr_pages = nr_pages; - /* In the parent-locked case, we only locked the range we are - * interested in. In all other cases, we can opportunistically - * cache decompressed data that goes beyond the requested range. */ - if (!(bio_flags & EXTENT_BIO_PARENT_LOCKED)) - add_ra_bio_pages(inode, em_start + em_len, cb); + add_ra_bio_pages(inode, em_start + em_len, cb); /* include any pages we added in add_ra-bio_pages */ uncompressed_len = bio->bi_vcnt * PAGE_CACHE_SIZE; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0be47e4b8136..b57daa895cea 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1689,7 +1689,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list, * */ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list) + struct list_head *ins_list, bool *emitted) { struct btrfs_dir_item *di; struct btrfs_delayed_item *curr, *next; @@ -1733,6 +1733,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, if (over) return 1; + *emitted = true; } return 0; } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index f70119f25421..0167853c84ae 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list, int btrfs_should_delete_dir_index(struct list_head *del_list, u64 index); int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, - struct list_head *ins_list); + struct list_head *ins_list, bool *emitted); /* for init */ int __init btrfs_delayed_inode_init(void); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dd08e29f5117..4545e2e2ad45 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -182,6 +182,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, + { .id = BTRFS_FREE_SPACE_TREE_OBJECTID, .name_stem = "free-space" }, { .id = 0, .name_stem = "tree" }, }; @@ -1787,7 +1788,6 @@ static int cleaner_kthread(void *arg) int again; struct btrfs_trans_handle *trans; - set_freezable(); do { again = 0; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 2e7c97a3f344..392592dc7010 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2897,12 +2897,11 @@ static int __do_readpage(struct extent_io_tree *tree, struct block_device *bdev; int ret; int nr = 0; - int parent_locked = *bio_flags & EXTENT_BIO_PARENT_LOCKED; size_t pg_offset = 0; size_t iosize; size_t disk_io_size; size_t blocksize = inode->i_sb->s_blocksize; - unsigned long this_bio_flag = *bio_flags & EXTENT_BIO_PARENT_LOCKED; + unsigned long this_bio_flag = 0; set_page_extent_mapped(page); @@ -2942,18 +2941,16 @@ static int __do_readpage(struct extent_io_tree *tree, kunmap_atomic(userpage); set_extent_uptodate(tree, cur, cur + iosize - 1, &cached, GFP_NOFS); - if (!parent_locked) - unlock_extent_cached(tree, cur, - cur + iosize - 1, - &cached, GFP_NOFS); + unlock_extent_cached(tree, cur, + cur + iosize - 1, + &cached, GFP_NOFS); break; } em = __get_extent_map(inode, page, pg_offset, cur, end - cur + 1, get_extent, em_cached); if (IS_ERR_OR_NULL(em)) { SetPageError(page); - if (!parent_locked) - unlock_extent(tree, cur, end); + unlock_extent(tree, cur, end); break; } extent_offset = cur - em->start; @@ -3038,12 +3035,9 @@ static int __do_readpage(struct extent_io_tree *tree, set_extent_uptodate(tree, cur, cur + iosize - 1, &cached, GFP_NOFS); - if (parent_locked) - free_extent_state(cached); - else - unlock_extent_cached(tree, cur, - cur + iosize - 1, - &cached, GFP_NOFS); + unlock_extent_cached(tree, cur, + cur + iosize - 1, + &cached, GFP_NOFS); cur = cur + iosize; pg_offset += iosize; continue; @@ -3052,8 +3046,7 @@ static int __do_readpage(struct extent_io_tree *tree, if (test_range_bit(tree, cur, cur_end, EXTENT_UPTODATE, 1, NULL)) { check_page_uptodate(tree, page); - if (!parent_locked) - unlock_extent(tree, cur, cur + iosize - 1); + unlock_extent(tree, cur, cur + iosize - 1); cur = cur + iosize; pg_offset += iosize; continue; @@ -3063,8 +3056,7 @@ static int __do_readpage(struct extent_io_tree *tree, */ if (block_start == EXTENT_MAP_INLINE) { SetPageError(page); - if (!parent_locked) - unlock_extent(tree, cur, cur + iosize - 1); + unlock_extent(tree, cur, cur + iosize - 1); cur = cur + iosize; pg_offset += iosize; continue; @@ -3083,8 +3075,7 @@ static int __do_readpage(struct extent_io_tree *tree, *bio_flags = this_bio_flag; } else { SetPageError(page); - if (!parent_locked) - unlock_extent(tree, cur, cur + iosize - 1); + unlock_extent(tree, cur, cur + iosize - 1); } cur = cur + iosize; pg_offset += iosize; @@ -3213,20 +3204,6 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page, return ret; } -int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, - get_extent_t *get_extent, int mirror_num) -{ - struct bio *bio = NULL; - unsigned long bio_flags = EXTENT_BIO_PARENT_LOCKED; - int ret; - - ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num, - &bio_flags, READ, NULL); - if (bio) - ret = submit_one_bio(READ, bio, mirror_num, bio_flags); - return ret; -} - static noinline void update_nr_written(struct page *page, struct writeback_control *wbc, unsigned long nr_written) diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 0377413bd4b9..880d5292e972 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -29,7 +29,6 @@ */ #define EXTENT_BIO_COMPRESSED 1 #define EXTENT_BIO_TREE_LOG 2 -#define EXTENT_BIO_PARENT_LOCKED 4 #define EXTENT_BIO_FLAG_SHIFT 16 /* these are bit numbers for test/set bit */ @@ -210,8 +209,6 @@ static inline int lock_extent(struct extent_io_tree *tree, u64 start, u64 end) int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end); int extent_read_full_page(struct extent_io_tree *tree, struct page *page, get_extent_t *get_extent, int mirror_num); -int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page, - get_extent_t *get_extent, int mirror_num); int __init extent_io_init(void); void extent_io_exit(void); diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c index 393e36bd5845..53dbeaf6ce94 100644 --- a/fs/btrfs/free-space-tree.c +++ b/fs/btrfs/free-space-tree.c @@ -153,6 +153,20 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize) static unsigned long *alloc_bitmap(u32 bitmap_size) { + void *mem; + + /* + * The allocation size varies, observed numbers were < 4K up to 16K. + * Using vmalloc unconditionally would be too heavy, we'll try + * contiguous allocations first. + */ + if (bitmap_size <= PAGE_SIZE) + return kzalloc(bitmap_size, GFP_NOFS); + + mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN); + if (mem) + return mem; + return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); } @@ -289,7 +303,7 @@ int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; @@ -438,7 +452,7 @@ int convert_free_space_to_extents(struct btrfs_trans_handle *trans, ret = 0; out: - vfree(bitmap); + kvfree(bitmap); if (ret) btrfs_abort_transaction(trans, root, ret); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e28f3d4691af..151b7c71b868 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5717,6 +5717,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) char *name_ptr; int name_len; int is_curr = 0; /* ctx->pos points to the current index? */ + bool emitted; /* FIXME, use a real flag for deciding about the key type */ if (root->fs_info->tree_root == root) @@ -5745,6 +5746,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx) if (ret < 0) goto err; + emitted = false; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; @@ -5824,6 +5826,7 @@ skip: if (over) goto nopos; + emitted = true; di_len = btrfs_dir_name_len(leaf, di) + btrfs_dir_data_len(leaf, di) + sizeof(*di); di_cur += di_len; @@ -5836,11 +5839,20 @@ next: if (key_type == BTRFS_DIR_INDEX_KEY) { if (is_curr) ctx->pos++; - ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list); + ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted); if (ret) goto nopos; } + /* + * If we haven't emitted any dir entry, we must not touch ctx->pos as + * it was was set to the termination value in previous call. We assume + * that "." and ".." were emitted if we reach this point and set the + * termination value as well for an empty directory. + */ + if (ctx->pos > 2 && !emitted) + goto nopos; + /* Reached end of directory/root. Bump pos past the last item. */ ctx->pos++; @@ -7116,21 +7128,41 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, if (ret) return ERR_PTR(ret); - em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, - ins.offset, ins.offset, ins.offset, 0); - if (IS_ERR(em)) { - btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - return em; - } - + /* + * Create the ordered extent before the extent map. This is to avoid + * races with the fast fsync path that would lead to it logging file + * extent items that point to disk extents that were not yet written to. + * The fast fsync path collects ordered extents into a local list and + * then collects all the new extent maps, so we must create the ordered + * extent first and make sure the fast fsync path collects any new + * ordered extents after collecting new extent maps as well. + * The fsync path simply can not rely on inode_dio_wait() because it + * causes deadlock with AIO. + */ ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid, ins.offset, ins.offset, 0); if (ret) { btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); - free_extent_map(em); return ERR_PTR(ret); } + em = create_pinned_em(inode, start, ins.offset, start, ins.objectid, + ins.offset, ins.offset, ins.offset, 0); + if (IS_ERR(em)) { + struct btrfs_ordered_extent *oe; + + btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); + oe = btrfs_lookup_ordered_extent(inode, start); + ASSERT(oe); + if (WARN_ON(!oe)) + return em; + set_bit(BTRFS_ORDERED_IOERR, &oe->flags); + set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags); + btrfs_remove_ordered_extent(inode, oe); + /* Once for our lookup and once for the ordered extents tree. */ + btrfs_put_ordered_extent(oe); + btrfs_put_ordered_extent(oe); + } return em; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 952172ca7e45..48aee9846329 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2794,24 +2794,29 @@ out: static struct page *extent_same_get_page(struct inode *inode, pgoff_t index) { struct page *page; - struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; page = grab_cache_page(inode->i_mapping, index); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); if (!PageUptodate(page)) { - if (extent_read_full_page_nolock(tree, page, btrfs_get_extent, - 0)) - return NULL; + int ret; + + ret = btrfs_readpage(NULL, page); + if (ret) + return ERR_PTR(ret); lock_page(page); if (!PageUptodate(page)) { unlock_page(page); page_cache_release(page); - return NULL; + return ERR_PTR(-EIO); + } + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + return ERR_PTR(-EAGAIN); } } - unlock_page(page); return page; } @@ -2823,17 +2828,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages, pgoff_t index = off >> PAGE_CACHE_SHIFT; for (i = 0; i < num_pages; i++) { +again: pages[i] = extent_same_get_page(inode, index + i); - if (!pages[i]) - return -ENOMEM; + if (IS_ERR(pages[i])) { + int err = PTR_ERR(pages[i]); + + if (err == -EAGAIN) + goto again; + pages[i] = NULL; + return err; + } } return 0; } -static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) +static int lock_extent_range(struct inode *inode, u64 off, u64 len, + bool retry_range_locking) { - /* do any pending delalloc/csum calc on src, one way or - another, and lock file content */ + /* + * Do any pending delalloc/csum calculations on inode, one way or + * another, and lock file content. + * The locking order is: + * + * 1) pages + * 2) range in the inode's io tree + */ while (1) { struct btrfs_ordered_extent *ordered; lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); @@ -2851,8 +2870,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len) unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1); if (ordered) btrfs_put_ordered_extent(ordered); + if (!retry_range_locking) + return -EAGAIN; btrfs_wait_ordered_range(inode, off, len); } + return 0; } static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2) @@ -2877,15 +2899,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1, unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1); } -static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1, - struct inode *inode2, u64 loff2, u64 len) +static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1, + struct inode *inode2, u64 loff2, u64 len, + bool retry_range_locking) { + int ret; + if (inode1 < inode2) { swap(inode1, inode2); swap(loff1, loff2); } - lock_extent_range(inode1, loff1, len); - lock_extent_range(inode2, loff2, len); + ret = lock_extent_range(inode1, loff1, len, retry_range_locking); + if (ret) + return ret; + ret = lock_extent_range(inode2, loff2, len, retry_range_locking); + if (ret) + unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, + loff1 + len - 1); + return ret; } struct cmp_pages { @@ -2901,11 +2932,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp) for (i = 0; i < cmp->num_pages; i++) { pg = cmp->src_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } pg = cmp->dst_pages[i]; - if (pg) + if (pg) { + unlock_page(pg); page_cache_release(pg); + } } kfree(cmp->src_pages); kfree(cmp->dst_pages); @@ -2966,6 +3001,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst, src_page = cmp->src_pages[i]; dst_page = cmp->dst_pages[i]; + ASSERT(PageLocked(src_page)); + ASSERT(PageLocked(dst_page)); addr = kmap_atomic(src_page); dst_addr = kmap_atomic(dst_page); @@ -3078,14 +3115,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen, goto out_unlock; } +again: ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp); if (ret) goto out_unlock; if (same_inode) - lock_extent_range(src, same_lock_start, same_lock_len); + ret = lock_extent_range(src, same_lock_start, same_lock_len, + false); else - btrfs_double_extent_lock(src, loff, dst, dst_loff, len); + ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len, + false); + /* + * If one of the inodes has dirty pages in the respective range or + * ordered extents, we need to flush dellaloc and wait for all ordered + * extents in the range. We must unlock the pages and the ranges in the + * io trees to avoid deadlocks when flushing delalloc (requires locking + * pages) and when waiting for ordered extents to complete (they require + * range locking). + */ + if (ret == -EAGAIN) { + /* + * Ranges in the io trees already unlocked. Now unlock all + * pages before waiting for all IO to complete. + */ + btrfs_cmp_data_free(&cmp); + if (same_inode) { + btrfs_wait_ordered_range(src, same_lock_start, + same_lock_len); + } else { + btrfs_wait_ordered_range(src, loff, len); + btrfs_wait_ordered_range(dst, dst_loff, len); + } + goto again; + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + btrfs_cmp_data_free(&cmp); + return ret; + } /* pass original length for comparison so we stay within i_size */ ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp); @@ -3795,9 +3864,15 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, u64 lock_start = min_t(u64, off, destoff); u64 lock_len = max_t(u64, off, destoff) + len - lock_start; - lock_extent_range(src, lock_start, lock_len); + ret = lock_extent_range(src, lock_start, lock_len, true); } else { - btrfs_double_extent_lock(src, off, inode, destoff, len); + ret = btrfs_double_extent_lock(src, off, inode, destoff, len, + true); + } + ASSERT(ret == 0); + if (WARN_ON(ret)) { + /* ranges in the io trees already unlocked */ + goto out_unlock; } ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index fd1c4d982463..2bd0011450df 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -575,7 +575,8 @@ static int is_cowonly_root(u64 root_objectid) root_objectid == BTRFS_TREE_LOG_OBJECTID || root_objectid == BTRFS_CSUM_TREE_OBJECTID || root_objectid == BTRFS_UUID_TREE_OBJECTID || - root_objectid == BTRFS_QUOTA_TREE_OBJECTID) + root_objectid == BTRFS_QUOTA_TREE_OBJECTID || + root_objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) return 1; return 0; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index e0ac85949067..539e7b5e3f86 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -202,6 +202,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(extended_iref, EXTENDED_IREF); BTRFS_FEAT_ATTR_INCOMPAT(raid56, RAID56); BTRFS_FEAT_ATTR_INCOMPAT(skinny_metadata, SKINNY_METADATA); BTRFS_FEAT_ATTR_INCOMPAT(no_holes, NO_HOLES); +BTRFS_FEAT_ATTR_COMPAT_RO(free_space_tree, FREE_SPACE_TREE); static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(mixed_backref), @@ -213,6 +214,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = { BTRFS_FEAT_ATTR_PTR(raid56), BTRFS_FEAT_ATTR_PTR(skinny_metadata), BTRFS_FEAT_ATTR_PTR(no_holes), + BTRFS_FEAT_ATTR_PTR(free_space_tree), NULL }; @@ -780,6 +782,39 @@ failure: return error; } + +/* + * Change per-fs features in /sys/fs/btrfs/UUID/features to match current + * values in superblock. Call after any changes to incompat/compat_ro flags + */ +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set) +{ + struct btrfs_fs_devices *fs_devs; + struct kobject *fsid_kobj; + u64 features; + int ret; + + if (!fs_info) + return; + + features = get_features(fs_info, set); + ASSERT(bit & supported_feature_masks[set]); + + fs_devs = fs_info->fs_devices; + fsid_kobj = &fs_devs->fsid_kobj; + + if (!fsid_kobj->state_initialized) + return; + + /* + * FIXME: this is too heavy to update just one value, ideally we'd like + * to use sysfs_update_group but some refactoring is needed first. + */ + sysfs_remove_group(fsid_kobj, &btrfs_feature_attr_group); + ret = sysfs_create_group(fsid_kobj, &btrfs_feature_attr_group); +} + static int btrfs_init_debugfs(void) { #ifdef CONFIG_DEBUG_FS diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h index 9c09522125a6..d7da1a4c2f6c 100644 --- a/fs/btrfs/sysfs.h +++ b/fs/btrfs/sysfs.h @@ -56,7 +56,7 @@ static struct btrfs_feature_attr btrfs_attr_##_name = { \ #define BTRFS_FEAT_ATTR_COMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_COMPAT, BTRFS_FEATURE_COMPAT, feature) #define BTRFS_FEAT_ATTR_COMPAT_RO(name, feature) \ - BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT, feature) + BTRFS_FEAT_ATTR(name, FEAT_COMPAT_RO, BTRFS_FEATURE_COMPAT_RO, feature) #define BTRFS_FEAT_ATTR_INCOMPAT(name, feature) \ BTRFS_FEAT_ATTR(name, FEAT_INCOMPAT, BTRFS_FEATURE_INCOMPAT, feature) @@ -90,4 +90,7 @@ int btrfs_sysfs_add_fsid(struct btrfs_fs_devices *fs_devs, struct kobject *parent); int btrfs_sysfs_add_device(struct btrfs_fs_devices *fs_devs); void btrfs_sysfs_remove_fsid(struct btrfs_fs_devices *fs_devs); +void btrfs_sysfs_feature_update(struct btrfs_fs_info *fs_info, + u64 bit, enum btrfs_feature_set set); + #endif /* _BTRFS_SYSFS_H_ */ diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c index b1d920b30070..0e1e61a7ec23 100644 --- a/fs/btrfs/tests/btrfs-tests.c +++ b/fs/btrfs/tests/btrfs-tests.c @@ -82,18 +82,18 @@ void btrfs_destroy_test_fs(void) struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(void) { struct btrfs_fs_info *fs_info = kzalloc(sizeof(struct btrfs_fs_info), - GFP_NOFS); + GFP_KERNEL); if (!fs_info) return fs_info; fs_info->fs_devices = kzalloc(sizeof(struct btrfs_fs_devices), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->fs_devices) { kfree(fs_info); return NULL; } fs_info->super_copy = kzalloc(sizeof(struct btrfs_super_block), - GFP_NOFS); + GFP_KERNEL); if (!fs_info->super_copy) { kfree(fs_info->fs_devices); kfree(fs_info); @@ -180,11 +180,11 @@ btrfs_alloc_dummy_block_group(unsigned long length) { struct btrfs_block_group_cache *cache; - cache = kzalloc(sizeof(*cache), GFP_NOFS); + cache = kzalloc(sizeof(*cache), GFP_KERNEL); if (!cache) return NULL; cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl), - GFP_NOFS); + GFP_KERNEL); if (!cache->free_space_ctl) { kfree(cache); return NULL; diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c index e29fa297e053..669b58201e36 100644 --- a/fs/btrfs/tests/extent-io-tests.c +++ b/fs/btrfs/tests/extent-io-tests.c @@ -94,7 +94,7 @@ static int test_find_delalloc(void) * test. */ for (index = 0; index < (total_dirty >> PAGE_CACHE_SHIFT); index++) { - page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); + page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL); if (!page) { test_msg("Failed to allocate test page\n"); ret = -ENOMEM; @@ -113,7 +113,7 @@ static int test_find_delalloc(void) * |--- delalloc ---| * |--- search ---| */ - set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 0, 4095, NULL, GFP_KERNEL); start = 0; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -144,7 +144,7 @@ static int test_find_delalloc(void) test_msg("Couldn't find the locked page\n"); goto out_bits; } - set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, 4096, max_bytes - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -199,7 +199,7 @@ static int test_find_delalloc(void) * * We are re-using our test_start from above since it works out well. */ - set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_NOFS); + set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL, GFP_KERNEL); start = test_start; end = 0; found = find_lock_delalloc_range(inode, &tmp, locked_page, &start, @@ -262,7 +262,7 @@ static int test_find_delalloc(void) } ret = 0; out_bits: - clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_NOFS); + clear_extent_bits(&tmp, 0, total_dirty - 1, (unsigned)-1, GFP_KERNEL); out: if (locked_page) page_cache_release(locked_page); @@ -360,7 +360,7 @@ static int test_eb_bitmaps(void) test_msg("Running extent buffer bitmap tests\n"); - bitmap = kmalloc(len, GFP_NOFS); + bitmap = kmalloc(len, GFP_KERNEL); if (!bitmap) { test_msg("Couldn't allocate test bitmap\n"); return -ENOMEM; diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c index 5de55fdd28bc..e2d3da02deee 100644 --- a/fs/btrfs/tests/inode-tests.c +++ b/fs/btrfs/tests/inode-tests.c @@ -974,7 +974,7 @@ static int test_extent_accounting(void) (BTRFS_MAX_EXTENT_SIZE >> 1) + 4095, EXTENT_DELALLOC | EXTENT_DIRTY | EXTENT_UPTODATE | EXTENT_DO_ACCOUNTING, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1045,7 +1045,7 @@ static int test_extent_accounting(void) BTRFS_MAX_EXTENT_SIZE+8191, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1079,7 +1079,7 @@ static int test_extent_accounting(void) ret = clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); if (ret) { test_msg("clear_extent_bit returned %d\n", ret); goto out; @@ -1096,7 +1096,7 @@ out: clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, (u64)-1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_UPTODATE, 0, 0, - NULL, GFP_NOFS); + NULL, GFP_KERNEL); iput(inode); btrfs_free_dummy_root(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 323e12cc9d2f..978c3a810893 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4127,7 +4127,9 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_path *path, struct list_head *logged_list, - struct btrfs_log_ctx *ctx) + struct btrfs_log_ctx *ctx, + const u64 start, + const u64 end) { struct extent_map *em, *n; struct list_head extents; @@ -4166,7 +4168,13 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, } list_sort(NULL, &extents, extent_cmp); - + /* + * Collect any new ordered extents within the range. This is to + * prevent logging file extent items without waiting for the disk + * location they point to being written. We do this only to deal + * with races against concurrent lockless direct IO writes. + */ + btrfs_get_logged_extents(inode, logged_list, start, end); process: while (!list_empty(&extents)) { em = list_entry(extents.next, struct extent_map, list); @@ -4701,7 +4709,7 @@ log_extents: goto out_unlock; } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, - &logged_list, ctx); + &logged_list, ctx, start, end); if (ret) { err = ret; goto out_unlock; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 86a9c383955e..eb9028e8cfc5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -698,8 +698,8 @@ static void ceph_aio_retry_work(struct work_struct *work) req = ceph_osdc_alloc_request(orig_req->r_osdc, snapc, 2, false, GFP_NOFS); - if (IS_ERR(req)) { - ret = PTR_ERR(req); + if (!req) { + ret = -ENOMEM; req = orig_req; goto out; } @@ -716,7 +716,6 @@ static void ceph_aio_retry_work(struct work_struct *work) ceph_osdc_build_request(req, req->r_ops[0].extent.offset, snapc, CEPH_NOSNAP, &aio_req->mtime); - ceph_put_snap_context(snapc); ceph_osdc_put_request(orig_req); req->r_callback = ceph_aio_complete_req; @@ -731,6 +730,7 @@ out: ceph_aio_complete_req(req, NULL); } + ceph_put_snap_context(snapc); kfree(aio_work); } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fb4ba2e4e2a5..be2d87f33177 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -975,13 +975,8 @@ out_unlock: /* * splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. - * - * we will only rehash the resulting dentry if @prehash is - * true; @prehash will be set to false (for the benefit of - * the caller) if we fail. */ -static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, - bool *prehash) +static struct dentry *splice_dentry(struct dentry *dn, struct inode *in) { struct dentry *realdn; @@ -994,8 +989,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, if (IS_ERR(realdn)) { pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n", PTR_ERR(realdn), dn, in, ceph_vinop(in)); - if (prehash) - *prehash = false; /* don't rehash on error */ dn = realdn; /* note realdn contains the error */ goto out; } else if (realdn) { @@ -1011,8 +1004,6 @@ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, dout("dn %p attached to %p ino %llx.%llx\n", dn, d_inode(dn), ceph_vinop(d_inode(dn))); } - if ((!prehash || *prehash) && d_unhashed(dn)) - d_rehash(dn); out: return dn; } @@ -1245,10 +1236,8 @@ retry_lookup: dout("d_delete %p\n", dn); d_delete(dn); } else { - dout("d_instantiate %p NULL\n", dn); - d_instantiate(dn, NULL); if (have_lease && d_unhashed(dn)) - d_rehash(dn); + d_add(dn, NULL); update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); @@ -1260,7 +1249,7 @@ retry_lookup: if (d_really_is_negative(dn)) { ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in, &have_lease); + dn = splice_dentry(dn, in); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1290,7 +1279,7 @@ retry_lookup: dout(" linking snapped dir %p to dn %p\n", in, dn); ceph_dir_clear_ordered(dir); ihold(in); - dn = splice_dentry(dn, in, NULL); + dn = splice_dentry(dn, in); if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; @@ -1501,7 +1490,7 @@ retry_lookup: } if (d_really_is_negative(dn)) { - struct dentry *realdn = splice_dentry(dn, in, NULL); + struct dentry *realdn = splice_dentry(dn, in); if (IS_ERR(realdn)) { err = PTR_ERR(realdn); d_drop(dn); diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c48ca13673e3..09b1db2cac31 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -642,9 +642,7 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb) while (*s && *s != sep) s++; - inode_lock(dir); - child = lookup_one_len(p, dentry, s - p); - inode_unlock(dir); + child = lookup_one_len_unlocked(p, dentry, s - p); dput(dentry); dentry = child; } while (!IS_ERR(dentry)); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index a5b8eb69a8f4..6402eaf8ab95 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1261,6 +1261,9 @@ COMPATIBLE_IOCTL(HCIUNBLOCKADDR) COMPATIBLE_IOCTL(HCIINQUIRY) COMPATIBLE_IOCTL(HCIUARTSETPROTO) COMPATIBLE_IOCTL(HCIUARTGETPROTO) +COMPATIBLE_IOCTL(HCIUARTGETDEVICE) +COMPATIBLE_IOCTL(HCIUARTSETFLAGS) +COMPATIBLE_IOCTL(HCIUARTGETFLAGS) COMPATIBLE_IOCTL(RFCOMMCREATEDEV) COMPATIBLE_IOCTL(RFCOMMRELEASEDEV) COMPATIBLE_IOCTL(RFCOMMGETDEVLIST) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index f419519ec41f..214ec14149d9 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -432,14 +432,9 @@ static int configfs_attach_attr(struct configfs_dirent * sd, struct dentry * den (sd->s_type & CONFIGFS_ITEM_BIN_ATTR) ? configfs_init_bin_file : configfs_init_file); - if (error) { + if (error) configfs_put(sd); - return error; - } - - d_rehash(dentry); - - return 0; + return error; } static struct dentry * configfs_lookup(struct inode *dir, diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index cee087d8f7e0..45811ea3fd87 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -199,9 +199,17 @@ int configfs_create(struct dentry * dentry, umode_t mode, void (*init)(struct in configfs_set_inode_lock_class(sd, inode); init(inode); - d_instantiate(dentry, inode); - if (S_ISDIR(mode) || S_ISLNK(mode)) + if (S_ISDIR(mode) || S_ISLNK(mode)) { + /* + * ->symlink(), ->mkdir(), configfs_register_subsystem() or + * create_default_group() - already hashed. + */ + d_instantiate(dentry, inode); dget(dentry); /* pin link and directory dentries in core */ + } else { + /* ->lookup() */ + d_add(dentry, inode); + } return error; } @@ -58,6 +58,26 @@ static void dax_unmap_atomic(struct block_device *bdev, blk_queue_exit(bdev->bd_queue); } +struct page *read_dax_sector(struct block_device *bdev, sector_t n) +{ + struct page *page = alloc_pages(GFP_KERNEL, 0); + struct blk_dax_ctl dax = { + .size = PAGE_SIZE, + .sector = n & ~((((int) PAGE_SIZE) / 512) - 1), + }; + long rc; + + if (!page) + return ERR_PTR(-ENOMEM); + + rc = dax_map_atomic(bdev, &dax); + if (rc < 0) + return ERR_PTR(rc); + memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE); + dax_unmap_atomic(bdev, &dax); + return page; +} + /* * dax_clear_blocks() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS @@ -338,7 +358,8 @@ static int dax_radix_entry(struct address_space *mapping, pgoff_t index, void *entry; WARN_ON_ONCE(pmd_entry && !dirty); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + if (dirty) + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); spin_lock_irq(&mapping->tree_lock); diff --git a/fs/dcache.c b/fs/dcache.c index 92d5140de851..32ceae3e6112 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -269,9 +269,6 @@ static inline int dname_external(const struct dentry *dentry) return dentry->d_name.name != dentry->d_iname; } -/* - * Make sure other CPUs see the inode attached before the type is set. - */ static inline void __d_set_inode_and_type(struct dentry *dentry, struct inode *inode, unsigned type_flags) @@ -279,28 +276,18 @@ static inline void __d_set_inode_and_type(struct dentry *dentry, unsigned flags; dentry->d_inode = inode; - smp_wmb(); flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); flags |= type_flags; WRITE_ONCE(dentry->d_flags, flags); } -/* - * Ideally, we want to make sure that other CPUs see the flags cleared before - * the inode is detached, but this is really a violation of RCU principles - * since the ordering suggests we should always set inode before flags. - * - * We should instead replace or discard the entire dentry - but that sucks - * performancewise on mass deletion/rename. - */ static inline void __d_clear_type_and_inode(struct dentry *dentry) { unsigned flags = READ_ONCE(dentry->d_flags); flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); - smp_wmb(); dentry->d_inode = NULL; } @@ -370,9 +357,11 @@ static void dentry_unlink_inode(struct dentry * dentry) __releases(dentry->d_inode->i_lock) { struct inode *inode = dentry->d_inode; + + raw_write_seqcount_begin(&dentry->d_seq); __d_clear_type_and_inode(dentry); hlist_del_init(&dentry->d_u.d_alias); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); spin_unlock(&dentry->d_lock); spin_unlock(&inode->i_lock); if (!inode->i_nlink) @@ -1756,12 +1745,12 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) unsigned add_flags = d_flags_for_inode(inode); spin_lock(&dentry->d_lock); - if (inode) - hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); - dentry_rcuwalk_invalidate(dentry); + raw_write_seqcount_end(&dentry->d_seq); + __fsnotify_d_instantiate(dentry); spin_unlock(&dentry->d_lock); - fsnotify_d_instantiate(dentry, inode); } /** @@ -1782,91 +1771,16 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) void d_instantiate(struct dentry *entry, struct inode * inode) { BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); - if (inode) + if (inode) { spin_lock(&inode->i_lock); - __d_instantiate(entry, inode); - if (inode) + __d_instantiate(entry, inode); spin_unlock(&inode->i_lock); + } security_d_instantiate(entry, inode); } EXPORT_SYMBOL(d_instantiate); /** - * d_instantiate_unique - instantiate a non-aliased dentry - * @entry: dentry to instantiate - * @inode: inode to attach to this dentry - * - * Fill in inode information in the entry. On success, it returns NULL. - * If an unhashed alias of "entry" already exists, then we return the - * aliased dentry instead and drop one reference to inode. - * - * Note that in order to avoid conflicts with rename() etc, the caller - * had better be holding the parent directory semaphore. - * - * This also assumes that the inode count has been incremented - * (or otherwise set) by the caller to indicate that it is now - * in use by the dcache. - */ -static struct dentry *__d_instantiate_unique(struct dentry *entry, - struct inode *inode) -{ - struct dentry *alias; - int len = entry->d_name.len; - const char *name = entry->d_name.name; - unsigned int hash = entry->d_name.hash; - - if (!inode) { - __d_instantiate(entry, NULL); - return NULL; - } - - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - /* - * Don't need alias->d_lock here, because aliases with - * d_parent == entry->d_parent are not subject to name or - * parent changes, because the parent inode i_mutex is held. - */ - if (alias->d_name.hash != hash) - continue; - if (alias->d_parent != entry->d_parent) - continue; - if (alias->d_name.len != len) - continue; - if (dentry_cmp(alias, name, len)) - continue; - __dget(alias); - return alias; - } - - __d_instantiate(entry, inode); - return NULL; -} - -struct dentry *d_instantiate_unique(struct dentry *entry, struct inode *inode) -{ - struct dentry *result; - - BUG_ON(!hlist_unhashed(&entry->d_u.d_alias)); - - if (inode) - spin_lock(&inode->i_lock); - result = __d_instantiate_unique(entry, inode); - if (inode) - spin_unlock(&inode->i_lock); - - if (!result) { - security_d_instantiate(entry, inode); - return NULL; - } - - BUG_ON(!d_unhashed(result)); - iput(inode); - return result; -} - -EXPORT_SYMBOL(d_instantiate_unique); - -/** * d_instantiate_no_diralias - instantiate a non-aliased dentry * @entry: dentry to complete * @inode: inode to attach to this dentry @@ -2446,6 +2360,86 @@ void d_rehash(struct dentry * entry) } EXPORT_SYMBOL(d_rehash); + +/* inode->i_lock held if inode is non-NULL */ + +static inline void __d_add(struct dentry *dentry, struct inode *inode) +{ + if (inode) { + __d_instantiate(dentry, inode); + spin_unlock(&inode->i_lock); + } + security_d_instantiate(dentry, inode); + d_rehash(dentry); +} + +/** + * d_add - add dentry to hash queues + * @entry: dentry to add + * @inode: The inode to attach to this dentry + * + * This adds the entry to the hash queues and initializes @inode. + * The entry was actually filled in earlier during d_alloc(). + */ + +void d_add(struct dentry *entry, struct inode *inode) +{ + if (inode) + spin_lock(&inode->i_lock); + __d_add(entry, inode); +} +EXPORT_SYMBOL(d_add); + +/** + * d_exact_alias - find and hash an exact unhashed alias + * @entry: dentry to add + * @inode: The inode to go with this dentry + * + * If an unhashed dentry with the same name/parent and desired + * inode already exists, hash and return it. Otherwise, return + * NULL. + * + * Parent directory should be locked. + */ +struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode) +{ + struct dentry *alias; + int len = entry->d_name.len; + const char *name = entry->d_name.name; + unsigned int hash = entry->d_name.hash; + + spin_lock(&inode->i_lock); + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + /* + * Don't need alias->d_lock here, because aliases with + * d_parent == entry->d_parent are not subject to name or + * parent changes, because the parent inode i_mutex is held. + */ + if (alias->d_name.hash != hash) + continue; + if (alias->d_parent != entry->d_parent) + continue; + if (alias->d_name.len != len) + continue; + if (dentry_cmp(alias, name, len)) + continue; + spin_lock(&alias->d_lock); + if (!d_unhashed(alias)) { + spin_unlock(&alias->d_lock); + alias = NULL; + } else { + __dget_dlock(alias); + _d_rehash(alias); + spin_unlock(&alias->d_lock); + } + spin_unlock(&inode->i_lock); + return alias; + } + spin_unlock(&inode->i_lock); + return NULL; +} +EXPORT_SYMBOL(d_exact_alias); + /** * dentry_update_name_case - update case insensitive dentry with a new name * @dentry: dentry to be updated @@ -2782,10 +2776,9 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) BUG_ON(!d_unhashed(dentry)); - if (!inode) { - __d_instantiate(dentry, NULL); + if (!inode) goto out; - } + spin_lock(&inode->i_lock); if (S_ISDIR(inode->i_mode)) { struct dentry *new = __d_find_any_alias(inode); @@ -2819,12 +2812,8 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry) return new; } } - /* already taking inode->i_lock, so d_add() by hand */ - __d_instantiate(dentry, inode); - spin_unlock(&inode->i_lock); out: - security_d_instantiate(dentry, inode); - d_rehash(dentry); + __d_add(dentry, inode); return NULL; } EXPORT_SYMBOL(d_splice_alias); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 1f107fd51328..655f21f99160 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -575,6 +575,26 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx) mutex_unlock(&allocated_ptys_lock); } +/* + * pty code needs to hold extra references in case of last /dev/tty close + */ + +void devpts_add_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + atomic_inc(&sb->s_active); + ihold(ptmx_inode); +} + +void devpts_del_ref(struct inode *ptmx_inode) +{ + struct super_block *sb = pts_sb_from_inode(ptmx_inode); + + iput(ptmx_inode); + deactivate_super(sb); +} + /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master diff --git a/fs/direct-io.c b/fs/direct-io.c index 1b2f7ffc8b84..85463171053b 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -445,7 +445,8 @@ static struct bio *dio_await_one(struct dio *dio) __set_current_state(TASK_UNINTERRUPTIBLE); dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); - if (!blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) + if (!(dio->iocb->ki_flags & IOCB_HIPRI) || + !blk_poll(bdev_get_queue(dio->bio_bdev), dio->bio_cookie)) io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c index 80d6901493cf..87dbdd4881ab 100644 --- a/fs/ecryptfs/crypto.c +++ b/fs/ecryptfs/crypto.c @@ -1499,16 +1499,14 @@ out: */ static int ecryptfs_encrypt_filename(struct ecryptfs_filename *filename, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat) { int rc = 0; filename->encrypted_filename = NULL; filename->encrypted_filename_size = 0; - if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) { + if (mount_crypt_stat && (mount_crypt_stat->flags + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { size_t packet_size; size_t remaining_bytes; @@ -1944,7 +1942,6 @@ out: int ecryptfs_encrypt_and_encode_filename( char **encoded_name, size_t *encoded_name_size, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, const char *name, size_t name_size) { @@ -1953,9 +1950,8 @@ int ecryptfs_encrypt_and_encode_filename( (*encoded_name) = NULL; (*encoded_name_size) = 0; - if ((crypt_stat && (crypt_stat->flags & ECRYPTFS_ENCRYPT_FILENAMES)) - || (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES))) { + if (mount_crypt_stat && (mount_crypt_stat->flags + & ECRYPTFS_GLOBAL_ENCRYPT_FILENAMES)) { struct ecryptfs_filename *filename; filename = kzalloc(sizeof(*filename), GFP_KERNEL); @@ -1968,8 +1964,7 @@ int ecryptfs_encrypt_and_encode_filename( } filename->filename = (char *)name; filename->filename_size = name_size; - rc = ecryptfs_encrypt_filename(filename, crypt_stat, - mount_crypt_stat); + rc = ecryptfs_encrypt_filename(filename, mount_crypt_stat); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt " "filename; rc = [%d]\n", __func__, rc); @@ -1980,11 +1975,9 @@ int ecryptfs_encrypt_and_encode_filename( NULL, &encoded_name_no_prefix_size, filename->encrypted_filename, filename->encrypted_filename_size); - if ((crypt_stat && (crypt_stat->flags - & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat + if (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) (*encoded_name_size) = (ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE + encoded_name_no_prefix_size); @@ -2002,11 +1995,9 @@ int ecryptfs_encrypt_and_encode_filename( kfree(filename); goto out; } - if ((crypt_stat && (crypt_stat->flags - & ECRYPTFS_ENCFN_USE_MOUNT_FNEK)) - || (mount_crypt_stat + if (mount_crypt_stat && (mount_crypt_stat->flags - & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK))) { + & ECRYPTFS_GLOBAL_ENCFN_USE_MOUNT_FNEK)) { memcpy((*encoded_name), ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX, ECRYPTFS_FNEK_ENCRYPTED_FILENAME_PREFIX_SIZE); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 7b39260c7bba..67e16128c572 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -569,7 +569,6 @@ int ecryptfs_fill_zeros(struct file *file, loff_t new_length); int ecryptfs_encrypt_and_encode_filename( char **encoded_name, size_t *encoded_name_size, - struct ecryptfs_crypt_stat *crypt_stat, struct ecryptfs_mount_crypt_stat *mount_crypt_stat, const char *name, size_t name_size); struct dentry *ecryptfs_lower_dentry(struct dentry *this_dentry); diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 4e685ac1024d..26651636cd1d 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -397,11 +397,9 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, int rc = 0; lower_dir_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry->d_parent); - inode_lock(d_inode(lower_dir_dentry)); - lower_dentry = lookup_one_len(ecryptfs_dentry->d_name.name, + lower_dentry = lookup_one_len_unlocked(ecryptfs_dentry->d_name.name, lower_dir_dentry, ecryptfs_dentry->d_name.len); - inode_unlock(d_inode(lower_dir_dentry)); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " @@ -419,18 +417,16 @@ static struct dentry *ecryptfs_lookup(struct inode *ecryptfs_dir_inode, dput(lower_dentry); rc = ecryptfs_encrypt_and_encode_filename( &encrypted_and_encoded_name, &encrypted_and_encoded_name_size, - NULL, mount_crypt_stat, ecryptfs_dentry->d_name.name, + mount_crypt_stat, ecryptfs_dentry->d_name.name, ecryptfs_dentry->d_name.len); if (rc) { printk(KERN_ERR "%s: Error attempting to encrypt and encode " "filename; rc = [%d]\n", __func__, rc); goto out; } - inode_lock(d_inode(lower_dir_dentry)); - lower_dentry = lookup_one_len(encrypted_and_encoded_name, + lower_dentry = lookup_one_len_unlocked(encrypted_and_encoded_name, lower_dir_dentry, encrypted_and_encoded_name_size); - inode_unlock(d_inode(lower_dir_dentry)); if (IS_ERR(lower_dentry)) { rc = PTR_ERR(lower_dentry); ecryptfs_printk(KERN_DEBUG, "%s: lookup_one_len() returned " @@ -502,7 +498,6 @@ static int ecryptfs_symlink(struct inode *dir, struct dentry *dentry, dir->i_sb)->mount_crypt_stat; rc = ecryptfs_encrypt_and_encode_filename(&encoded_symname, &encoded_symlen, - NULL, mount_crypt_stat, symname, strlen(symname)); if (rc) diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ae1dbcf47e97..cde60741cad2 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -94,6 +94,11 @@ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) +#define EPOLLINOUT_BITS (POLLIN | POLLOUT) + +#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \ + EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) + /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 @@ -1068,7 +1073,22 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k * wait list. */ if (waitqueue_active(&ep->wq)) { - ewake = 1; + if ((epi->event.events & EPOLLEXCLUSIVE) && + !((unsigned long)key & POLLFREE)) { + switch ((unsigned long)key & EPOLLINOUT_BITS) { + case POLLIN: + if (epi->event.events & POLLIN) + ewake = 1; + break; + case POLLOUT: + if (epi->event.events & POLLOUT) + ewake = 1; + break; + case 0: + ewake = 1; + break; + } + } wake_up_locked(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) @@ -1875,9 +1895,13 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, we do not currently supported nested exclusive wakeups. */ - if ((epds.events & EPOLLEXCLUSIVE) && (op == EPOLL_CTL_MOD || - (op == EPOLL_CTL_ADD && is_file_epoll(tf.file)))) - goto error_tgt_fput; + if (epds.events & EPOLLEXCLUSIVE) { + if (op == EPOLL_CTL_MOD) + goto error_tgt_fput; + if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) || + (epds.events & ~EPOLLEXCLUSIVE_OK_BITS))) + goto error_tgt_fput; + } /* * At this point it is safe to assume that the "private_data" contains @@ -1950,8 +1974,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, break; case EPOLL_CTL_MOD: if (epi) { - epds.events |= POLLERR | POLLHUP; - error = ep_modify(ep, epi, &epds); + if (!(epi->event.events & EPOLLEXCLUSIVE)) { + epds.events |= POLLERR | POLLHUP; + error = ep_modify(ep, epi, &epds); + } } else error = -ENOENT; break; diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 506765afa1a3..bb8d67e2740a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -401,33 +400,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index d211b8e18566..30c4c9ebb693 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -843,9 +843,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, pr_notice("%s(): Link succeeded, unlink failed (err %d). You now have a hard link\n", __func__, ret); - /* Might as well let the VFS know */ - d_instantiate(new_dentry, d_inode(old_dentry)); - ihold(d_inode(old_dentry)); + /* + * We can't keep the target in dcache after that. + * For one thing, we can't afford dentry aliases for directories. + * For another, if there was a victim, we _can't_ set new inode + * for that sucker and we have to trigger mount eviction - the + * caller won't do it on its own since we are returning an error. + */ + d_invalidate(new_dentry); new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); return ret; } diff --git a/fs/namei.c b/fs/namei.c index f624d132e01e..794f81dce766 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1220,8 +1220,8 @@ static int follow_managed(struct path *path, struct nameidata *nd) if (need_mntput && path->mnt == mnt) mntput(path->mnt); - if (ret == -EISDIR) - ret = 0; + if (ret == -EISDIR || !ret) + ret = 1; if (need_mntput) nd->flags |= LOOKUP_JUMPED; if (unlikely(ret < 0)) @@ -1444,40 +1444,26 @@ static int follow_dotdot(struct nameidata *nd) * This looks up the name in dcache, possibly revalidates the old dentry and * allocates a new one if not found or not valid. In the need_lookup argument * returns whether i_op->lookup is necessary. - * - * dir->d_inode->i_mutex must be held */ -static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir, - unsigned int flags, bool *need_lookup) +static struct dentry *lookup_dcache(const struct qstr *name, + struct dentry *dir, + unsigned int flags) { struct dentry *dentry; int error; - *need_lookup = false; dentry = d_lookup(dir, name); if (dentry) { if (dentry->d_flags & DCACHE_OP_REVALIDATE) { error = d_revalidate(dentry, flags); if (unlikely(error <= 0)) { - if (error < 0) { - dput(dentry); - return ERR_PTR(error); - } else { + if (!error) d_invalidate(dentry); - dput(dentry); - dentry = NULL; - } + dput(dentry); + return ERR_PTR(error); } } } - - if (!dentry) { - dentry = d_alloc(dir, name); - if (unlikely(!dentry)) - return ERR_PTR(-ENOMEM); - - *need_lookup = true; - } return dentry; } @@ -1506,45 +1492,44 @@ static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry, return dentry; } -static struct dentry *__lookup_hash(struct qstr *name, +static struct dentry *__lookup_hash(const struct qstr *name, struct dentry *base, unsigned int flags) { - bool need_lookup; - struct dentry *dentry; + struct dentry *dentry = lookup_dcache(name, base, flags); - dentry = lookup_dcache(name, base, flags, &need_lookup); - if (!need_lookup) + if (dentry) return dentry; + dentry = d_alloc(base, name); + if (unlikely(!dentry)) + return ERR_PTR(-ENOMEM); + return lookup_real(base->d_inode, dentry, flags); } -/* - * It's more convoluted than I'd like it to be, but... it's still fairly - * small and for now I'd prefer to have fast path as straight as possible. - * It _is_ time-critical. - */ static int lookup_fast(struct nameidata *nd, struct path *path, struct inode **inode, unsigned *seqp) { struct vfsmount *mnt = nd->path.mnt; struct dentry *dentry, *parent = nd->path.dentry; - int need_reval = 1; int status = 1; int err; /* * Rename seqlock is not required here because in the off chance - * of a false negative due to a concurrent rename, we're going to - * do the non-racy lookup, below. + * of a false negative due to a concurrent rename, the caller is + * going to fall back to non-racy lookup. */ if (nd->flags & LOOKUP_RCU) { unsigned seq; bool negative; dentry = __d_lookup_rcu(parent, &nd->last, &seq); - if (!dentry) - goto unlazy; + if (unlikely(!dentry)) { + if (unlazy_walk(nd, NULL, 0)) + return -ECHILD; + return 0; + } /* * This sequence count validates that the inode matches @@ -1552,7 +1537,7 @@ static int lookup_fast(struct nameidata *nd, */ *inode = d_backing_inode(dentry); negative = d_is_negative(dentry); - if (read_seqcount_retry(&dentry->d_seq, seq)) + if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) return -ECHILD; /* @@ -1562,81 +1547,89 @@ static int lookup_fast(struct nameidata *nd, * The memory barrier in read_seqcount_begin of child is * enough, we can use __read_seqcount_retry here. */ - if (__read_seqcount_retry(&parent->d_seq, nd->seq)) + if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq))) return -ECHILD; *seqp = seq; - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) { + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) status = d_revalidate(dentry, nd->flags); - if (unlikely(status <= 0)) { - if (status != -ECHILD) - need_reval = 0; - goto unlazy; - } + if (unlikely(status <= 0)) { + if (unlazy_walk(nd, dentry, seq)) + return -ECHILD; + if (status == -ECHILD) + status = d_revalidate(dentry, nd->flags); + } else { + /* + * Note: do negative dentry check after revalidation in + * case that drops it. + */ + if (unlikely(negative)) + return -ENOENT; + path->mnt = mnt; + path->dentry = dentry; + if (likely(__follow_mount_rcu(nd, path, inode, seqp))) + return 1; + if (unlazy_walk(nd, dentry, seq)) + return -ECHILD; } - /* - * Note: do negative dentry check after revalidation in - * case that drops it. - */ - if (negative) - return -ENOENT; - path->mnt = mnt; - path->dentry = dentry; - if (likely(__follow_mount_rcu(nd, path, inode, seqp))) - return 0; -unlazy: - if (unlazy_walk(nd, dentry, seq)) - return -ECHILD; } else { dentry = __d_lookup(parent, &nd->last); + if (unlikely(!dentry)) + return 0; + if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) + status = d_revalidate(dentry, nd->flags); } - - if (unlikely(!dentry)) - goto need_lookup; - - if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval) - status = d_revalidate(dentry, nd->flags); if (unlikely(status <= 0)) { - if (status < 0) { - dput(dentry); - return status; - } - d_invalidate(dentry); + if (!status) + d_invalidate(dentry); dput(dentry); - goto need_lookup; + return status; } - if (unlikely(d_is_negative(dentry))) { dput(dentry); return -ENOENT; } + path->mnt = mnt; path->dentry = dentry; err = follow_managed(path, nd); - if (likely(!err)) + if (likely(err > 0)) *inode = d_backing_inode(path->dentry); return err; - -need_lookup: - return 1; } /* Fast lookup failed, do it the slow way */ -static int lookup_slow(struct nameidata *nd, struct path *path) +static struct dentry *lookup_slow(const struct qstr *name, + struct dentry *dir, + unsigned int flags) { - struct dentry *dentry, *parent; - - parent = nd->path.dentry; - BUG_ON(nd->inode != parent->d_inode); - - inode_lock(parent->d_inode); - dentry = __lookup_hash(&nd->last, parent, nd->flags); - inode_unlock(parent->d_inode); - if (IS_ERR(dentry)) - return PTR_ERR(dentry); - path->mnt = nd->path.mnt; - path->dentry = dentry; - return follow_managed(path, nd); + struct dentry *dentry; + inode_lock(dir->d_inode); + dentry = d_lookup(dir, name); + if (unlikely(dentry)) { + if ((dentry->d_flags & DCACHE_OP_REVALIDATE) && + !(flags & LOOKUP_NO_REVAL)) { + int error = d_revalidate(dentry, flags); + if (unlikely(error <= 0)) { + if (!error) + d_invalidate(dentry); + dput(dentry); + dentry = ERR_PTR(error); + } + } + if (dentry) { + inode_unlock(dir->d_inode); + return dentry; + } + } + dentry = d_alloc(dir, name); + if (unlikely(!dentry)) { + inode_unlock(dir->d_inode); + return ERR_PTR(-ENOMEM); + } + dentry = lookup_real(dir->d_inode, dentry, flags); + inode_unlock(dir->d_inode); + return dentry; } static inline int may_lookup(struct nameidata *nd) @@ -1712,6 +1705,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } @@ -1735,19 +1733,24 @@ static int walk_component(struct nameidata *nd, int flags) return err; } err = lookup_fast(nd, &path, &inode, &seq); - if (unlikely(err)) { + if (unlikely(err <= 0)) { if (err < 0) return err; - - err = lookup_slow(nd, &path); - if (err < 0) + path.dentry = lookup_slow(&nd->last, nd->path.dentry, + nd->flags); + if (IS_ERR(path.dentry)) + return PTR_ERR(path.dentry); + if (unlikely(d_is_negative(path.dentry))) { + dput(path.dentry); + return -ENOENT; + } + path.mnt = nd->path.mnt; + err = follow_managed(&path, nd); + if (unlikely(err < 0)) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ - err = -ENOENT; - if (d_is_negative(path.dentry)) - goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -1759,10 +1762,6 @@ static int walk_component(struct nameidata *nd, int flags) nd->inode = inode; nd->seq = seq; return 0; - -out_path_put: - path_to_nameidata(&path, nd); - return err; } /* @@ -2368,21 +2367,9 @@ struct dentry *lookup_one_len_unlocked(const char *name, if (err) return ERR_PTR(err); - /* - * __d_lookup() is used to try to get a quick answer and avoid the - * mutex. A false-negative does no harm. - */ - ret = __d_lookup(base, &this); - if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) { - dput(ret); - ret = NULL; - } - if (ret) - return ret; - - inode_lock(base->d_inode); - ret = __lookup_hash(&this, base, 0); - inode_unlock(base->d_inode); + ret = lookup_dcache(&this, base, 0); + if (!ret) + ret = lookup_slow(&this, base, 0); return ret; } EXPORT_SYMBOL(lookup_one_len_unlocked); @@ -2460,31 +2447,21 @@ mountpoint_last(struct nameidata *nd, struct path *path) if (error) return error; dentry = dget(nd->path.dentry); - goto done; - } - - inode_lock(dir->d_inode); - dentry = d_lookup(dir, &nd->last); - if (!dentry) { - /* - * No cached dentry. Mounted dentries are pinned in the cache, - * so that means that this dentry is probably a symlink or the - * path doesn't actually point to a mounted dentry. - */ - dentry = d_alloc(dir, &nd->last); + } else { + dentry = d_lookup(dir, &nd->last); if (!dentry) { - inode_unlock(dir->d_inode); - return -ENOMEM; - } - dentry = lookup_real(dir->d_inode, dentry, nd->flags); - if (IS_ERR(dentry)) { - inode_unlock(dir->d_inode); - return PTR_ERR(dentry); + /* + * No cached dentry. Mounted dentries are pinned in the + * cache, so that means that this dentry is probably + * a symlink or the path doesn't actually point + * to a mounted dentry. + */ + dentry = lookup_slow(&nd->last, dir, + nd->flags | LOOKUP_NO_REVAL); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); } } - inode_unlock(dir->d_inode); - -done: if (d_is_negative(dentry)) { dput(dentry); return -ENOENT; @@ -3013,16 +2990,22 @@ static int lookup_open(struct nameidata *nd, struct path *path, struct inode *dir_inode = dir->d_inode; struct dentry *dentry; int error; - bool need_lookup; + bool need_lookup = false; *opened &= ~FILE_CREATED; - dentry = lookup_dcache(&nd->last, dir, nd->flags, &need_lookup); + dentry = lookup_dcache(&nd->last, dir, nd->flags); if (IS_ERR(dentry)) return PTR_ERR(dentry); - /* Cached positive dentry: will open in f_op->open */ - if (!need_lookup && dentry->d_inode) + if (!dentry) { + dentry = d_alloc(dir, &nd->last); + if (unlikely(!dentry)) + return -ENOMEM; + need_lookup = true; + } else if (dentry->d_inode) { + /* Cached positive dentry: will open in f_op->open */ goto out_no_open; + } if ((nd->flags & LOOKUP_OPEN) && dir_inode->i_op->atomic_open) { return atomic_open(nd, dentry, path, file, op, got_write, @@ -3106,13 +3089,14 @@ static int do_last(struct nameidata *nd, nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; /* we _can_ be in RCU mode here */ error = lookup_fast(nd, &path, &inode, &seq); - if (likely(!error)) + if (likely(error > 0)) goto finish_lookup; if (error < 0) return error; BUG_ON(nd->inode != dir->d_inode); + BUG_ON(nd->flags & LOOKUP_RCU); } else { /* create side of things */ /* @@ -3167,12 +3151,6 @@ retry_lookup: } /* - * create/update audit record if it already exists. - */ - if (d_is_positive(path.dentry)) - audit_inode(nd->name, path.dentry, 0); - - /* * If atomic_open() acquired write access it is dropped now due to * possible mount and symlink following (this might be optimized away if * necessary...) @@ -3182,6 +3160,16 @@ retry_lookup: got_write = false; } + if (unlikely(d_is_negative(path.dentry))) { + path_to_nameidata(&path, nd); + return -ENOENT; + } + + /* + * create/update audit record if it already exists. + */ + audit_inode(nd->name, path.dentry, 0); + if (unlikely((open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT))) { path_to_nameidata(&path, nd); return -EEXIST; @@ -3191,13 +3179,8 @@ retry_lookup: if (unlikely(error < 0)) return error; - BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ - if (unlikely(d_is_negative(path.dentry))) { - path_to_nameidata(&path, nd); - return -ENOENT; - } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); @@ -3206,11 +3189,6 @@ finish_lookup: if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3229,6 +3207,10 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; @@ -3273,6 +3255,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); @@ -3699,31 +3685,6 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) return sys_mkdirat(AT_FDCWD, pathname, mode); } -/* - * The dentry_unhash() helper will try to drop the dentry early: we - * should have a usage count of 1 if we're the only user of this - * dentry, and if that is true (possibly after pruning the dcache), - * then we drop the dentry now. - * - * A low-level filesystem can, if it choses, legally - * do a - * - * if (!d_unhashed(dentry)) - * return -EBUSY; - * - * if it cannot handle the case of removing a directory - * that is still in use by something else.. - */ -void dentry_unhash(struct dentry *dentry) -{ - shrink_dcache_parent(dentry); - spin_lock(&dentry->d_lock); - if (dentry->d_lockref.count == 1) - __d_drop(dentry); - spin_unlock(&dentry->d_lock); -} -EXPORT_SYMBOL(dentry_unhash); - int vfs_rmdir(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 1); diff --git a/fs/ncpfs/dir.c b/fs/ncpfs/dir.c index 26c2de2de13f..b7f8eaeea5d8 100644 --- a/fs/ncpfs/dir.c +++ b/fs/ncpfs/dir.c @@ -633,7 +633,7 @@ ncp_fill_cache(struct file *file, struct dir_context *ctx, d_rehash(newdent); } else { spin_lock(&dentry->d_lock); - NCP_FINFO(inode)->flags &= ~NCPI_DIR_CACHE; + NCP_FINFO(dir)->flags &= ~NCPI_DIR_CACHE; spin_unlock(&dentry->d_lock); } } else { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 9cce67043f92..4bfa7d8bcade 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1360,19 +1360,15 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry); nfs_inc_stats(dir, NFSIOS_VFSLOOKUP); - res = ERR_PTR(-ENAMETOOLONG); - if (dentry->d_name.len > NFS_SERVER(dir)->namelen) - goto out; + if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen)) + return ERR_PTR(-ENAMETOOLONG); /* * If we're doing an exclusive create, optimize away the lookup * but don't hash the dentry. */ - if (nfs_is_exclusive_create(dir, flags)) { - d_instantiate(dentry, NULL); - res = NULL; - goto out; - } + if (nfs_is_exclusive_create(dir, flags)) + return NULL; res = ERR_PTR(-ENOMEM); fhandle = nfs_alloc_fhandle(); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 5bcd92d50e82..0cb1abd535e3 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1215,7 +1215,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task, hdr->pgio_mirror_idx + 1, &hdr->pgio_mirror_idx)) goto out_eagain; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &hdr->lseg->pls_layout->plh_flags); pnfs_read_resend_pnfs(hdr); return task->tk_status; diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 29898a9550fa..eb370460ce20 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -412,7 +412,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx, OP_ILLEGAL, GFP_NOIO); if (!fail_return) { if (ff_layout_has_available_ds(lseg)) - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lseg->pls_layout->plh_flags); else pnfs_error_mark_layout_for_return(ino, lseg); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4bfc33ad0563..400a70b3be7b 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2461,14 +2461,15 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = opendata->dentry; if (d_really_is_negative(dentry)) { - /* FIXME: Is this d_drop() ever needed? */ + struct dentry *alias; d_drop(dentry); - dentry = d_add_unique(dentry, igrab(state->inode)); - if (dentry == NULL) { - dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + alias = d_exact_alias(dentry, state->inode); + if (!alias) + alias = d_splice_alias(igrab(state->inode), dentry); + /* d_splice_alias() can't fail here - it's a non-directory */ + if (alias) { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry = alias; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index a3592cc34a20..482b6e94bb37 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -52,9 +52,7 @@ static DEFINE_SPINLOCK(pnfs_spinlock); */ static LIST_HEAD(pnfs_modules_tbl); -static int -pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, - enum pnfs_iomode iomode, bool sync); +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo); /* Return the registered pnfs layout driver module matching given id */ static struct pnfs_layoutdriver_type * @@ -243,6 +241,8 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) { struct inode *inode = lo->plh_inode; + pnfs_layoutreturn_before_put_layout_hdr(lo); + if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) { if (!list_empty(&lo->plh_segs)) WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n"); @@ -345,58 +345,6 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo, rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq); } -/* Return true if layoutreturn is needed */ -static bool -pnfs_layout_need_return(struct pnfs_layout_hdr *lo, - struct pnfs_layout_segment *lseg) -{ - struct pnfs_layout_segment *s; - - if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - return false; - - list_for_each_entry(s, &lo->plh_segs, pls_list) - if (s != lseg && test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) - return false; - - return true; -} - -static bool -pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) -{ - if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) - return false; - lo->plh_return_iomode = 0; - pnfs_get_layout_hdr(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - return true; -} - -static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, - struct pnfs_layout_hdr *lo, struct inode *inode) -{ - lo = lseg->pls_layout; - inode = lo->plh_inode; - - spin_lock(&inode->i_lock); - if (pnfs_layout_need_return(lo, lseg)) { - nfs4_stateid stateid; - enum pnfs_iomode iomode; - bool send; - - nfs4_stateid_copy(&stateid, &lo->plh_stateid); - iomode = lo->plh_return_iomode; - send = pnfs_prepare_layoutreturn(lo); - spin_unlock(&inode->i_lock); - if (send) { - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, &stateid, iomode, false); - } - } else - spin_unlock(&inode->i_lock); -} - void pnfs_put_lseg(struct pnfs_layout_segment *lseg) { @@ -410,15 +358,8 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) atomic_read(&lseg->pls_refcount), test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); - /* Handle the case where refcount != 1 */ - if (atomic_add_unless(&lseg->pls_refcount, -1, 1)) - return; - lo = lseg->pls_layout; inode = lo->plh_inode; - /* Do we need a layoutreturn? */ - if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) - pnfs_layoutreturn_before_put_lseg(lseg, lo, inode); if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) { if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) { @@ -937,6 +878,17 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } +static bool +pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo) +{ + if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + return false; + lo->plh_return_iomode = 0; + pnfs_get_layout_hdr(lo); + clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); + return true; +} + static int pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid, enum pnfs_iomode iomode, bool sync) @@ -971,6 +923,48 @@ out: return status; } +/* Return true if layoutreturn is needed */ +static bool +pnfs_layout_need_return(struct pnfs_layout_hdr *lo) +{ + struct pnfs_layout_segment *s; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return false; + + /* Defer layoutreturn until all lsegs are done */ + list_for_each_entry(s, &lo->plh_segs, pls_list) { + if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags)) + return false; + } + + return true; +} + +static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo) +{ + struct inode *inode= lo->plh_inode; + + if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) + return; + spin_lock(&inode->i_lock); + if (pnfs_layout_need_return(lo)) { + nfs4_stateid stateid; + enum pnfs_iomode iomode; + bool send; + + nfs4_stateid_copy(&stateid, &lo->plh_stateid); + iomode = lo->plh_return_iomode; + send = pnfs_prepare_layoutreturn(lo); + spin_unlock(&inode->i_lock); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, &stateid, iomode, false); + } + } else + spin_unlock(&inode->i_lock); +} + /* * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr * when the layout segment list is empty. @@ -1091,7 +1085,7 @@ bool pnfs_roc(struct inode *ino) nfs4_stateid_copy(&stateid, &lo->plh_stateid); /* always send layoutreturn if being marked so */ - if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) layoutreturn = pnfs_prepare_layoutreturn(lo); @@ -1772,7 +1766,7 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, pnfs_set_plh_return_iomode(lo, return_range->iomode); if (!mark_lseg_invalid(lseg, tmp_list)) remaining++; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } return remaining; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 9f4e2a47f4aa..1ac1db5f6dad 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -94,8 +94,8 @@ enum { NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ NFS_LAYOUT_BULK_RECALL, /* bulk recall affecting layout */ - NFS_LAYOUT_RETURN, /* Return this layout ASAP */ - NFS_LAYOUT_RETURN_BEFORE_CLOSE, /* Return this layout before close */ + NFS_LAYOUT_RETURN, /* layoutreturn in progress */ + NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ }; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 5d2a57e4c03a..d40010e4f1a9 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -870,7 +870,7 @@ __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen, oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset); + host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0); set_fs(oldfs); return nfsd_finish_read(file, count, host_err); } @@ -957,7 +957,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, /* Write the data. */ oldfs = get_fs(); set_fs(KERNEL_DS); - host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos); + host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, 0); set_fs(oldfs); if (host_err < 0) goto out_nfserr; diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index a3cc6d2fc896..a76b9ea7722e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -1254,15 +1254,15 @@ static const struct file_operations o2hb_debug_fops = { void o2hb_exit(void) { - kfree(o2hb_db_livenodes); - kfree(o2hb_db_liveregions); - kfree(o2hb_db_quorumregions); - kfree(o2hb_db_failedregions); debugfs_remove(o2hb_debug_failedregions); debugfs_remove(o2hb_debug_quorumregions); debugfs_remove(o2hb_debug_liveregions); debugfs_remove(o2hb_debug_livenodes); debugfs_remove(o2hb_debug_dir); + kfree(o2hb_db_livenodes); + kfree(o2hb_db_liveregions); + kfree(o2hb_db_quorumregions); + kfree(o2hb_db_failedregions); } static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir, @@ -1438,13 +1438,15 @@ static void o2hb_region_release(struct config_item *item) kfree(reg->hr_slots); - kfree(reg->hr_db_regnum); - kfree(reg->hr_db_livenodes); debugfs_remove(reg->hr_debug_livenodes); debugfs_remove(reg->hr_debug_regnum); debugfs_remove(reg->hr_debug_elapsed_time); debugfs_remove(reg->hr_debug_pinned); debugfs_remove(reg->hr_debug_dir); + kfree(reg->hr_db_livenodes); + kfree(reg->hr_db_regnum); + kfree(reg->hr_debug_elapsed_time); + kfree(reg->hr_debug_pinned); spin_lock(&o2hb_live_lock); list_del(®->hr_all_item); diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c index c5bdf02c213b..b94a425f0175 100644 --- a/fs/ocfs2/dlm/dlmrecovery.c +++ b/fs/ocfs2/dlm/dlmrecovery.c @@ -2367,6 +2367,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node) break; } } + dlm_lockres_clear_refmap_bit(dlm, res, + dead_node); spin_unlock(&res->spinlock); continue; } diff --git a/fs/pnode.c b/fs/pnode.c index 6367e1e435c6..c524fdddc7fb 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,7 +217,7 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; @@ -223,7 +228,7 @@ static int propagate_one(struct mount *m) last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } - if (n->mnt_group_id != last_dest->mnt_group_id) { + if (!peers(n, last_dest)) { last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 85d16c67c33e..fa95ab2d3674 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file, sizeof(struct proc_maps_private)); } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +/* + * Indicate if the VMA is a stack for the given task; for + * /proc/PID/maps that is the stack of the main task. + */ +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= vma->vm_mm->start_stack && + vma->vm_end >= vma->vm_mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } static void @@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) name = arch_vma_name(vma); if (!name) { - pid_t tid; - if (!mm) { name = "[vdso]"; goto done; @@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) goto done; } - tid = pid_of_stack(priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) { - name = "[stack]"; - } else { - /* Thread stack in /proc/PID/maps */ - seq_pad(m, ' '); - seq_printf(m, "[stack:%d]", tid); - } - } + if (is_stack(priv, vma, is_pid)) + name = "[stack]"; } done: @@ -1552,18 +1543,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { + pte_t huge_pte = huge_ptep_get(pte); struct numa_maps *md; struct page *page; - if (!pte_present(*pte)) + if (!pte_present(huge_pte)) return 0; - page = pte_page(*pte); + page = pte_page(huge_pte); if (!page) return 0; md = walk->private; - gather_stats(page, md, pte_dirty(*pte), 1); + gather_stats(page, md, pte_dirty(huge_pte), 1); return 0; } @@ -1617,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) seq_file_path(m, file, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_puts(m, " heap"); - } else { - pid_t tid = pid_of_stack(proc_priv, vma, is_pid); - if (tid != 0) { - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_puts(m, " stack"); - else - seq_printf(m, " stack:%d", tid); - } + } else if (is_stack(proc_priv, vma, is_pid)) { + seq_puts(m, " stack"); } if (is_vm_hugetlb_page(vma)) diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c index e0d64c92e4f6..faacb0c0d857 100644 --- a/fs/proc/task_nommu.c +++ b/fs/proc/task_nommu.c @@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm, return size; } -static pid_t pid_of_stack(struct proc_maps_private *priv, - struct vm_area_struct *vma, bool is_pid) +static int is_stack(struct proc_maps_private *priv, + struct vm_area_struct *vma, int is_pid) { - struct inode *inode = priv->inode; - struct task_struct *task; - pid_t ret = 0; - - rcu_read_lock(); - task = pid_task(proc_pid(inode), PIDTYPE_PID); - if (task) { - task = task_of_stack(task, vma, is_pid); + struct mm_struct *mm = vma->vm_mm; + int stack = 0; + + if (is_pid) { + stack = vma->vm_start <= mm->start_stack && + vma->vm_end >= mm->start_stack; + } else { + struct inode *inode = priv->inode; + struct task_struct *task; + + rcu_read_lock(); + task = pid_task(proc_pid(inode), PIDTYPE_PID); if (task) - ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info); + stack = vma_is_stack_for_task(vma, task); + rcu_read_unlock(); } - rcu_read_unlock(); - - return ret; + return stack; } /* @@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma, if (file) { seq_pad(m, ' '); seq_file_path(m, file, ""); - } else if (mm) { - pid_t tid = pid_of_stack(priv, vma, is_pid); - - if (tid != 0) { - seq_pad(m, ' '); - /* - * Thread stack in /proc/PID/task/TID/maps or - * the main process stack. - */ - if (!is_pid || (vma->vm_start <= mm->start_stack && - vma->vm_end >= mm->start_stack)) - seq_printf(m, "[stack]"); - else - seq_printf(m, "[stack:%d]", tid); - } + } else if (mm && is_stack(priv, vma, is_pid)) { + seq_pad(m, ' '); + seq_printf(m, "[stack]"); } seq_putc(m, '\n'); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 3c3b81bb6dfe..04ca0cc6d065 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2430,9 +2430,7 @@ int dquot_quota_on_mount(struct super_block *sb, char *qf_name, struct dentry *dentry; int error; - inode_lock(d_inode(sb->s_root)); - dentry = lookup_one_len(qf_name, sb->s_root, strlen(qf_name)); - inode_unlock(d_inode(sb->s_root)); + dentry = lookup_one_len_unlocked(qf_name, sb->s_root, strlen(qf_name)); if (IS_ERR(dentry)) return PTR_ERR(dentry); diff --git a/fs/read_write.c b/fs/read_write.c index 324ec271cc4e..cf377cf9dfe3 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -17,6 +17,7 @@ #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> +#include <linux/fs.h> #include "internal.h" #include <asm/uaccess.h> @@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, - ~0ULL, 0); + OFFSET_MAX, 0); default: return -EINVAL; } @@ -692,12 +693,17 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, iter_fn_t fn) + loff_t *ppos, iter_fn_t fn, int flags) { struct kiocb kiocb; ssize_t ret; + if (flags & ~RWF_HIPRI) + return -EOPNOTSUPP; + init_sync_kiocb(&kiocb, filp); + if (flags & RWF_HIPRI) + kiocb.ki_flags |= IOCB_HIPRI; kiocb.ki_pos = *ppos; ret = fn(&kiocb, iter); @@ -708,10 +714,13 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, io_fn_t fn) + loff_t *ppos, io_fn_t fn, int flags) { ssize_t ret = 0; + if (flags & ~RWF_HIPRI) + return -EOPNOTSUPP; + while (iov_iter_count(iter)) { struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; @@ -812,7 +821,8 @@ out: static ssize_t do_readv_writev(int type, struct file *file, const struct iovec __user * uvector, - unsigned long nr_segs, loff_t *pos) + unsigned long nr_segs, loff_t *pos, + int flags) { size_t tot_len; struct iovec iovstack[UIO_FASTIOV]; @@ -844,9 +854,9 @@ static ssize_t do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); else - ret = do_loop_readv_writev(file, &iter, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn, flags); if (type != READ) file_end_write(file); @@ -863,40 +873,40 @@ out: } ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; - return do_readv_writev(READ, file, vec, vlen, pos); + return do_readv_writev(READ, file, vec, vlen, pos, flags); } EXPORT_SYMBOL(vfs_readv); ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; - return do_readv_writev(WRITE, file, vec, vlen, pos); + return do_readv_writev(WRITE, file, vec, vlen, pos, flags); } EXPORT_SYMBOL(vfs_writev); -SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen) +static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos = file_pos_read(f.file); - ret = vfs_readv(f.file, vec, vlen, &pos); + ret = vfs_readv(f.file, vec, vlen, &pos, flags); if (ret >= 0) file_pos_write(f.file, pos); fdput_pos(f); @@ -908,15 +918,15 @@ SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, return ret; } -SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen) +static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos = file_pos_read(f.file); - ret = vfs_writev(f.file, vec, vlen, &pos); + ret = vfs_writev(f.file, vec, vlen, &pos, flags); if (ret >= 0) file_pos_write(f.file, pos); fdput_pos(f); @@ -934,10 +944,9 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } -SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, loff_t pos, int flags) { - loff_t pos = pos_from_hilo(pos_h, pos_l); struct fd f; ssize_t ret = -EBADF; @@ -948,7 +957,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) - ret = vfs_readv(f.file, vec, vlen, &pos); + ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } @@ -958,10 +967,9 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, return ret; } -SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, - unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, + unsigned long vlen, loff_t pos, int flags) { - loff_t pos = pos_from_hilo(pos_h, pos_l); struct fd f; ssize_t ret = -EBADF; @@ -972,7 +980,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) - ret = vfs_writev(f.file, vec, vlen, &pos); + ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } @@ -982,11 +990,64 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, return ret; } +SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) +{ + return do_readv(fd, vec, vlen, 0); +} + +SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen) +{ + return do_writev(fd, vec, vlen, 0); +} + +SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + return do_preadv(fd, vec, vlen, pos, 0); +} + +SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, + int, flags) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + if (pos == -1) + return do_readv(fd, vec, vlen, flags); + + return do_preadv(fd, vec, vlen, pos, flags); +} + +SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + return do_pwritev(fd, vec, vlen, pos, 0); +} + +SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, + unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, + int, flags) +{ + loff_t pos = pos_from_hilo(pos_h, pos_l); + + if (pos == -1) + return do_writev(fd, vec, vlen, flags); + + return do_pwritev(fd, vec, vlen, pos, flags); +} + #ifdef CONFIG_COMPAT static ssize_t compat_do_readv_writev(int type, struct file *file, const struct compat_iovec __user *uvector, - unsigned long nr_segs, loff_t *pos) + unsigned long nr_segs, loff_t *pos, + int flags) { compat_ssize_t tot_len; struct iovec iovstack[UIO_FASTIOV]; @@ -1018,9 +1079,9 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, } if (iter_fn) - ret = do_iter_readv_writev(file, &iter, pos, iter_fn); + ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags); else - ret = do_loop_readv_writev(file, &iter, pos, fn); + ret = do_loop_readv_writev(file, &iter, pos, fn, flags); if (type != READ) file_end_write(file); @@ -1038,7 +1099,7 @@ out: static size_t compat_readv(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { ssize_t ret = -EBADF; @@ -1049,7 +1110,7 @@ static size_t compat_readv(struct file *file, if (!(file->f_mode & FMODE_CAN_READ)) goto out; - ret = compat_do_readv_writev(READ, file, vec, vlen, pos); + ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags); out: if (ret > 0) @@ -1058,9 +1119,9 @@ out: return ret; } -COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, - const struct compat_iovec __user *,vec, - compat_ulong_t, vlen) +static size_t do_compat_readv(compat_ulong_t fd, + const struct compat_iovec __user *vec, + compat_ulong_t vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1069,16 +1130,24 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, if (!f.file) return -EBADF; pos = f.file->f_pos; - ret = compat_readv(f.file, vec, vlen, &pos); + ret = compat_readv(f.file, vec, vlen, &pos, flags); if (ret >= 0) f.file->f_pos = pos; fdput_pos(f); return ret; + } -static long __compat_sys_preadv64(unsigned long fd, +COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen) +{ + return do_compat_readv(fd, vec, vlen, 0); +} + +static long do_compat_preadv64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos) + unsigned long vlen, loff_t pos, int flags) { struct fd f; ssize_t ret; @@ -1090,7 +1159,7 @@ static long __compat_sys_preadv64(unsigned long fd, return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) - ret = compat_readv(f.file, vec, vlen, &pos); + ret = compat_readv(f.file, vec, vlen, &pos, flags); fdput(f); return ret; } @@ -1100,7 +1169,7 @@ COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { - return __compat_sys_preadv64(fd, vec, vlen, pos); + return do_compat_preadv64(fd, vec, vlen, pos, 0); } #endif @@ -1110,12 +1179,25 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return __compat_sys_preadv64(fd, vec, vlen, pos); + return do_compat_preadv64(fd, vec, vlen, pos, 0); +} + +COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, + int, flags) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + + if (pos == -1) + return do_compat_readv(fd, vec, vlen, flags); + + return do_compat_preadv64(fd, vec, vlen, pos, flags); } static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos) + unsigned long vlen, loff_t *pos, int flags) { ssize_t ret = -EBADF; @@ -1126,7 +1208,7 @@ static size_t compat_writev(struct file *file, if (!(file->f_mode & FMODE_CAN_WRITE)) goto out; - ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos); + ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0); out: if (ret > 0) @@ -1135,9 +1217,9 @@ out: return ret; } -COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, - const struct compat_iovec __user *, vec, - compat_ulong_t, vlen) +static size_t do_compat_writev(compat_ulong_t fd, + const struct compat_iovec __user* vec, + compat_ulong_t vlen, int flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1146,16 +1228,23 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, if (!f.file) return -EBADF; pos = f.file->f_pos; - ret = compat_writev(f.file, vec, vlen, &pos); + ret = compat_writev(f.file, vec, vlen, &pos, flags); if (ret >= 0) f.file->f_pos = pos; fdput_pos(f); return ret; } -static long __compat_sys_pwritev64(unsigned long fd, +COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, + const struct compat_iovec __user *, vec, + compat_ulong_t, vlen) +{ + return do_compat_writev(fd, vec, vlen, 0); +} + +static long do_compat_pwritev64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos) + unsigned long vlen, loff_t pos, int flags) { struct fd f; ssize_t ret; @@ -1167,7 +1256,7 @@ static long __compat_sys_pwritev64(unsigned long fd, return -EBADF; ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) - ret = compat_writev(f.file, vec, vlen, &pos); + ret = compat_writev(f.file, vec, vlen, &pos, flags); fdput(f); return ret; } @@ -1177,7 +1266,7 @@ COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct compat_iovec __user *,vec, unsigned long, vlen, loff_t, pos) { - return __compat_sys_pwritev64(fd, vec, vlen, pos); + return do_compat_pwritev64(fd, vec, vlen, pos, 0); } #endif @@ -1187,8 +1276,21 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, { loff_t pos = ((loff_t)pos_high << 32) | pos_low; - return __compat_sys_pwritev64(fd, vec, vlen, pos); + return do_compat_pwritev64(fd, vec, vlen, pos, 0); } + +COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, + const struct compat_iovec __user *,vec, + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + + if (pos == -1) + return do_compat_writev(fd, vec, vlen, flags); + + return do_compat_pwritev64(fd, vec, vlen, pos, flags); +} + #endif static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, @@ -1532,10 +1634,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND) || - !file_in->f_op->clone_file_range) + (file_out->f_flags & O_APPEND)) return -EBADF; + if (!file_in->f_op->clone_file_range) + return -EOPNOTSUPP; + ret = clone_verify_area(file_in, pos_in, len, false); if (ret) return ret; diff --git a/fs/splice.c b/fs/splice.c index 19e0b103d253..9947b5c69664 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -580,7 +580,7 @@ static ssize_t kernel_readv(struct file *file, const struct iovec *vec, old_fs = get_fs(); set_fs(get_ds()); /* The cast to a user pointer is valid due to the set_fs() */ - res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos); + res = vfs_readv(file, (const struct iovec __user *)vec, vlen, &pos, 0); set_fs(old_fs); return res; diff --git a/fs/timerfd.c b/fs/timerfd.c index b94fa6c3c6eb..053818dd6c18 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -153,7 +153,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) if (isalarm(ctx)) remaining = alarm_expires_remaining(&ctx->t.alarm); else - remaining = hrtimer_expires_remaining(&ctx->t.tmr); + remaining = hrtimer_expires_remaining_adjusted(&ctx->t.tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } diff --git a/fs/xattr.c b/fs/xattr.c index 07d0e47f6a7f..4861322e28e8 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; - int err; + int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl) { @@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) - return err; + break; } spin_unlock(&xattrs->lock); - return size - remaining_size; + return err ? err : size - remaining_size; } /* diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index da37beb76f6e..594f7e63b432 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -4491,7 +4491,7 @@ xlog_recover_process( * know precisely what failed. */ if (pass == XLOG_RECOVER_CRCPASS) { - if (rhead->h_crc && crc != le32_to_cpu(rhead->h_crc)) + if (rhead->h_crc && crc != rhead->h_crc) return -EFSBADCRC; return 0; } @@ -4502,7 +4502,7 @@ xlog_recover_process( * zero CRC check prevents warnings from being emitted when upgrading * the kernel from one that does not add CRCs by default. */ - if (crc != le32_to_cpu(rhead->h_crc)) { + if (crc != rhead->h_crc) { if (rhead->h_crc || xfs_sb_version_hascrc(&log->l_mp->m_sb)) { xfs_alert(log->l_mp, "log record CRC mismatch: found 0x%x, expected 0x%x.", |