diff options
Diffstat (limited to 'fs')
65 files changed, 931 insertions, 444 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/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..d96f5cf38a2d 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; } @@ -7954,6 +7986,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) @@ -8008,6 +8041,7 @@ static void btrfs_endio_direct_write(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } 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/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index 7dc886c9a78f..e956cba94338 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -175,7 +175,7 @@ char *cifs_compose_mount_options(const char *sb_mountdata, * string to the length of the original string to allow for worst case. */ md_len = strlen(sb_mountdata) + INET6_ADDRSTRLEN; - mountdata = kzalloc(md_len + 1, GFP_KERNEL); + mountdata = kzalloc(md_len + sizeof("ip=") + 1, GFP_KERNEL); if (mountdata == NULL) { rc = -ENOMEM; goto compose_mount_options_err; diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index afa09fce8151..e682b36a210f 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -714,7 +714,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp) ses->auth_key.response = kmalloc(baselen + tilen, GFP_KERNEL); if (!ses->auth_key.response) { - rc = ENOMEM; + rc = -ENOMEM; ses->auth_key.len = 0; goto setup_ntlmv2_rsp_ret; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 4fbd92d2e113..a763cd3d9e7c 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2999,8 +2999,7 @@ ip_rfc1001_connect(struct TCP_Server_Info *server) if (ses_init_buf) { ses_init_buf->trailer.session_req.called_len = 32; - if (server->server_RFC1001_name && - server->server_RFC1001_name[0] != 0) + if (server->server_RFC1001_name[0] != 0) rfc1002mangle(ses_init_buf->trailer. session_req.called_name, server->server_RFC1001_name, 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) @@ -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/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..d6a9012d42ad 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) dio->io_error = -EIO; if (dio->is_async && dio->rw == READ && dio->should_dirty) { - bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; + bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index c424e4813ec8..d48e0d261d78 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include <linux/efi.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/mount.h> #include "internal.h" @@ -103,9 +104,78 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + inode_lock(inode); + inode_set_flags(inode, i_flags, S_IMMUTABLE); + inode_unlock(inode); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 3381b9da9ee6..e2ab6d0497f2 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16addb7c..b4505188e799 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index b8a564f29107..dd029d13ea61 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -118,8 +118,9 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; char *name; - int len, i; + int len; int err = -ENOMEM; + bool is_removable = false; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -128,15 +129,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, memcpy(entry->var.VariableName, name16, name_size); memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - len = ucs2_strlen(entry->var.VariableName); + len = ucs2_utf8size(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); if (!name) goto fail; - for (i = 0; i < len; i++) - name[i] = entry->var.VariableName[i] & 0xFF; + ucs2_as_utf8(name, entry->var.VariableName, len); + + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; name[len] = '-'; @@ -144,7 +147,8 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -200,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; 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/ext4/balloc.c b/fs/ext4/balloc.c index ec0668a60678..fe1f50fe764f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init block bitmap for group " + "%u: %d", block_group, err); goto out; + } goto verify; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index c8021208a7eb..38f7562489bb 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -467,3 +467,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size) return size; return 0; } + +/* + * Validate dentries for encrypted directories to make sure we aren't + * potentially caching stale data after a key has been added or + * removed. + */ +static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct inode *dir = d_inode(dentry->d_parent); + struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info; + int dir_has_key, cached_with_key; + + if (!ext4_encrypted_inode(dir)) + return 0; + + if (ci && ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD)))) + ci = NULL; + + /* this should eventually be an flag in d_flags */ + cached_with_key = dentry->d_fsdata != NULL; + dir_has_key = (ci != NULL); + + /* + * If the dentry was cached without the key, and it is a + * negative dentry, it might be a valid name. We can't check + * if the key has since been made available due to locking + * reasons, so we fail the validation so ext4_lookup() can do + * this check. + * + * We also fail the validation if the dentry was created with + * the key present, but we no longer have the key, or vice versa. + */ + if ((!cached_with_key && d_is_negative(dentry)) || + (!cached_with_key && dir_has_key) || + (cached_with_key && !dir_has_key)) { +#if 0 /* Revalidation debug */ + char buf[80]; + char *cp = simple_dname(dentry, buf, sizeof(buf)); + + if (IS_ERR(cp)) + cp = (char *) "???"; + pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata, + cached_with_key, d_is_negative(dentry), + dir_has_key); +#endif + return 0; + } + return 1; +} + +const struct dentry_operations ext4_encrypted_d_ops = { + .d_revalidate = ext4_d_revalidate, +}; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 1d1bca74f844..33f5e2a50cf8 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) int dir_has_error = 0; struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + if (ext4_encrypted_inode(inode)) { + err = ext4_get_encryption_info(inode); + if (err && err != -ENOKEY) + return err; + } + if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) { @@ -157,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + bh = NULL; + goto errout; + } } if (!bh) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0662b285dc8a..157b458a69d4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2302,6 +2302,7 @@ struct page *ext4_encrypt(struct inode *inode, int ext4_decrypt(struct page *page); int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len); +extern const struct dentry_operations ext4_encrypted_d_ops; #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_init_crypto(void); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0ffabaf90aa5..3753ceb0b0dd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3928,7 +3928,7 @@ static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags, - unsigned int allocated, ext4_fsblk_t newblock) + unsigned int allocated) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; @@ -4347,7 +4347,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { allocated = convert_initialized_extent( handle, inode, map, &path, - flags, allocated, newblock); + flags, allocated); goto out2; } else if (!ext4_ext_is_unwritten(ex)) goto out; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 1126436dada1..474f1a4d2ca8 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -350,6 +350,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp) struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct vfsmount *mnt = filp->f_path.mnt; + struct inode *dir = filp->f_path.dentry->d_parent->d_inode; struct path path; char buf[64], *cp; int ret; @@ -393,6 +394,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp) if (ext4_encryption_info(inode) == NULL) return -ENOKEY; } + if (ext4_encrypted_inode(dir) && + !ext4_is_child_context_consistent_with_parent(dir, inode)) { + ext4_warning(inode->i_sb, + "Inconsistent encryption contexts: %lu/%lu\n", + (unsigned long) dir->i_ino, + (unsigned long) inode->i_ino); + return -EPERM; + } /* * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 3fcfd50a2e8a..acc0ad56bf2f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init inode bitmap for group " + "%u: %d", block_group, err); goto out; + } return bh; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 83bc8bfb3bea..9cc57c3b4661 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -686,6 +686,34 @@ out_sem: return retval; } +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) +{ + unsigned long old_state; + unsigned long new_state; + + flags &= EXT4_MAP_FLAGS; + + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_page) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; + return; + } + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + do { + old_state = READ_ONCE(bh->b_state); + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely( + cmpxchg(&bh->b_state, old_state, new_state) != old_state)); +} + /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 @@ -722,7 +750,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_io_end_t *io_end = ext4_inode_aio(inode); map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; @@ -1685,7 +1713,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked @@ -3253,29 +3281,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * case, we allocate an io_end structure to hook to the iocb. */ iocb->private = NULL; - ext4_inode_aio_set(inode, NULL); - if (!is_sync_kiocb(iocb)) { - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) { - ret = -ENOMEM; - goto retake_lock; - } - /* - * Grab reference for DIO. Will be dropped in ext4_end_io_dio() - */ - iocb->private = ext4_get_io_end(io_end); - /* - * we save the io structure for current async direct - * IO, so that later ext4_map_blocks() could flag the - * io structure whether there is a unwritten extents - * needs to be converted when IO is completed. - */ - ext4_inode_aio_set(inode, io_end); - } - if (overwrite) { get_block_func = ext4_get_block_overwrite; } else { + ext4_inode_aio_set(inode, NULL); + if (!is_sync_kiocb(iocb)) { + io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } + /* + * Grab reference for DIO. Will be dropped in + * ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); + /* + * we save the io structure for current async direct + * IO, so that later ext4_map_blocks() could flag the + * io structure whether there is a unwritten extents + * needs to be converted when IO is completed. + */ + ext4_inode_aio_set(inode, io_end); + } get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0f6c36922c24..a99b010e2194 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode, { struct ext4_inode_info *ei = EXT4_I(inode); handle_t *handle = NULL; - int err = EPERM, migrate = 0; + int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; unsigned int jflag; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 61eaf74dca37..4424b7bf8ac6 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2285,7 +2285,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " - " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]"); + " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index fb6f11709ae6..e032a0423e35 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -380,8 +381,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 06574dd77614..48e4b8907826 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct ext4_dir_entry_2 *de; struct buffer_head *bh; + if (ext4_encrypted_inode(dir)) { + int res = ext4_get_encryption_info(dir); + + /* + * This should be a properly defined flag for + * dentry->d_flags when we uplift this to the VFS. + * d_fsdata is set to (void *) 1 if if the dentry is + * created while the directory was encrypted and we + * don't have access to the key. + */ + dentry->d_fsdata = NULL; + if (ext4_encryption_info(dir)) + dentry->d_fsdata = (void *) 1; + d_set_d_op(dentry, &ext4_encrypted_d_ops); + if (res && res != -ENOKEY) + return ERR_PTR(res); + } + if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); @@ -1585,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi return ERR_PTR(-EFSCORRUPTED); } if (!IS_ERR(inode) && ext4_encrypted_inode(dir) && - (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) && + (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && !ext4_is_child_context_consistent_with_parent(dir, inode)) { + int nokey = ext4_encrypted_inode(inode) && + !ext4_encryption_info(inode); + iput(inode); + if (nokey) + return ERR_PTR(-ENOKEY); ext4_warning(inode->i_sb, "Inconsistent encryption contexts: %lu/%lu\n", (unsigned long) dir->i_ino, diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ad62d7acc315..34038e3598d5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6915c950e6e8..1f76d8950a57 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -317,6 +317,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -423,6 +424,7 @@ skip_switch: wb_put(new_wb); iput(inode); + deactivate_super(sb); kfree(isw); } @@ -469,11 +471,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); + if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) { - spin_unlock(&inode->i_lock); - goto out_free; - } + inode_to_wb(inode) == isw->new_wb) + goto out_unlock; + + if (!atomic_inc_not_zero(&inode->i_sb->s_active)) + goto out_unlock; + inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); @@ -489,6 +494,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; +out_unlock: + spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); diff --git a/fs/inode.c b/fs/inode.c index 9f62db3bcc3e..69b8b526c194 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_rdev = 0; inode->dirtied_when = 0; +#ifdef CONFIG_CGROUP_WRITEBACK + inode->i_wb_frn_winner = 0; + inode->i_wb_frn_avg_time = 0; + inode->i_wb_frn_history = 0; +#endif + if (security_inode_alloc(inode)) goto out; spin_lock_init(&inode->i_lock); diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index c59a59c37f3d..35ab51c04814 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, for (i = 0; i < nr_pages; i++) put_page(arg->layoutupdate_pages[i]); + vfree(arg->start_p); kfree(arg->layoutupdate_pages); } else { put_page(arg->layoutupdate_page); @@ -559,10 +560,15 @@ retry: if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { void *p = start_p, *end = p + arg->layoutupdate_len; + struct page *page = NULL; int i = 0; - for ( ; p < end; p += PAGE_SIZE) - arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + arg->start_p = start_p; + for ( ; p < end; p += PAGE_SIZE) { + page = vmalloc_to_page(p); + arg->layoutupdate_pages[i++] = page; + get_page(page); + } } dprintk("%s found %zu ranges\n", __func__, count); 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/nfs42proc.c b/fs/nfs/nfs42proc.c index bd25dc7077f7..dff83460e5a6 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -16,29 +16,8 @@ #define NFSDBG_FACILITY NFSDBG_PROC -static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, - fmode_t fmode) -{ - struct nfs_open_context *open; - struct nfs_lock_context *lock; - int ret; - - open = get_nfs_open_context(nfs_file_open_context(file)); - lock = nfs_get_lock_context(open); - if (IS_ERR(lock)) { - put_nfs_open_context(open); - return PTR_ERR(lock); - } - - ret = nfs4_set_rw_stateid(dst, open, lock, fmode); - - nfs_put_lock_context(lock); - put_nfs_open_context(open); - return ret; -} - static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, - loff_t offset, loff_t len) + struct nfs_lock_context *lock, loff_t offset, loff_t len) { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); @@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context, + lock, FMODE_WRITE); if (status) return status; @@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; int err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_fallocate(msg, filep, offset, len); - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, + struct nfs_lock_context *lock, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; - status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); + status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context, + lock, FMODE_READ); if (status) return status; @@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; loff_t err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_llseek(filep, offset, whence); + err = _nfs42_proc_llseek(filep, lock, offset, whence); if (err >= 0) break; - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, } static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, - struct file *dst_f, loff_t src_offset, - loff_t dst_offset, loff_t count) + struct file *dst_f, struct nfs_lock_context *src_lock, + struct nfs_lock_context *dst_lock, loff_t src_offset, + loff_t dst_offset, loff_t count) { struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); @@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context, + src_lock, FMODE_READ); if (status) return status; - status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context, + dst_lock, FMODE_WRITE); if (status) return status; @@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f, }; struct inode *inode = file_inode(src_f); struct nfs_server *server = NFS_SERVER(file_inode(src_f)); - struct nfs4_exception exception = { }; - int err; + struct nfs_lock_context *src_lock; + struct nfs_lock_context *dst_lock; + struct nfs4_exception src_exception = { }; + struct nfs4_exception dst_exception = { }; + int err, err2; if (!nfs_server_capable(inode, NFS_CAP_CLONE)) return -EOPNOTSUPP; + src_lock = nfs_get_lock_context(nfs_file_open_context(src_f)); + if (IS_ERR(src_lock)) + return PTR_ERR(src_lock); + + src_exception.inode = file_inode(src_f); + src_exception.state = src_lock->open_context->state; + + dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f)); + if (IS_ERR(dst_lock)) { + err = PTR_ERR(dst_lock); + goto out_put_src_lock; + } + + dst_exception.inode = file_inode(dst_f); + dst_exception.state = dst_lock->open_context->state; + do { - err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, - dst_offset, count); + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock, + src_offset, dst_offset, count); if (err == -ENOTSUPP || err == -EOPNOTSUPP) { NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + break; } - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); - return err; + err2 = nfs4_handle_exception(server, err, &src_exception); + err = nfs4_handle_exception(server, err, &dst_exception); + if (!err) + err = err2; + } while (src_exception.retry || dst_exception.retry); + nfs_put_lock_context(dst_lock); +out_put_src_lock: + nfs_put_lock_context(src_lock); + return err; } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4bfc33ad0563..14881594dd07 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } 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..2fa483e6dbe2 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"); @@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) } } +/* + * Mark a pnfs_layout_hdr and all associated layout segments as invalid + * + * In order to continue using the pnfs_layout_hdr, a full recovery + * is required. + * Note that caller must hold inode->i_lock. + */ +static int +pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, + struct list_head *lseg_list) +{ + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); +} + static int pnfs_iomode_to_fail_bit(u32 iomode) { @@ -345,58 +366,6 @@ 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 +379,8 @@ 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)) { @@ -613,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) spin_lock(&nfsi->vfs_inode.i_lock); lo = nfsi->layout; if (lo) { - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); pnfs_get_layout_hdr(lo); + pnfs_mark_layout_stateid_invalid(lo, &tmp_list); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); spin_unlock(&nfsi->vfs_inode.i_lock); @@ -676,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, { struct pnfs_layout_hdr *lo; struct inode *inode; - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; LIST_HEAD(lseg_list); int ret = 0; @@ -695,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, spin_lock(&inode->i_lock); list_del_init(&lo->plh_bulk_destroy); - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - if (is_bulk_recall) - set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); - if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range)) + if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) { + if (is_bulk_recall) + set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); ret = -EAGAIN; + } spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); /* Free all lsegs that are attached to commit buckets */ @@ -937,6 +893,17 @@ 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 +938,48 @@ 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 +1100,7 @@ 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); @@ -1744,8 +1753,19 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) if (lo->plh_return_iomode != 0) iomode = IOMODE_ANY; lo->plh_return_iomode = iomode; + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } +/** + * pnfs_mark_matching_lsegs_return - Free or return matching layout segments + * @lo: pointer to layout header + * @tmp_list: list header to be used with pnfs_free_lseg_list() + * @return_range: describe layout segment ranges to be returned + * + * This function is mainly intended for use by layoutrecall. It attempts + * to free the layout segment immediately, or else to mark it for return + * as soon as its reference count drops to zero. + */ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, @@ -1768,12 +1788,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); + if (mark_lseg_invalid(lseg, tmp_list)) + continue; + remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - if (!mark_lseg_invalid(lseg, tmp_list)) - remaining++; - set_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, - &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/notify/mark.c b/fs/notify/mark.c index cfcbf114676e..7115c5d7d373 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -91,7 +91,14 @@ #include <linux/fsnotify_backend.h> #include "fsnotify.h" +#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ + struct srcu_struct fsnotify_mark_srcu; +static DEFINE_SPINLOCK(destroy_lock); +static LIST_HEAD(destroy_list); + +static void fsnotify_mark_destroy(struct work_struct *work); +static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -165,19 +172,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark) atomic_dec(&group->num_marks); } -static void -fsnotify_mark_free_rcu(struct rcu_head *rcu) -{ - struct fsnotify_mark *mark; - - mark = container_of(rcu, struct fsnotify_mark, g_rcu); - fsnotify_put_mark(mark); -} - /* - * Free fsnotify mark. The freeing is actually happening from a call_srcu - * callback. Caller must have a reference to the mark or be protected by - * fsnotify_mark_srcu. + * Free fsnotify mark. The freeing is actually happening from a kthread which + * first waits for srcu period end. Caller must have a reference to the mark + * or be protected by fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { @@ -192,7 +190,11 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + queue_delayed_work(system_unbound_wq, &reaper_work, + FSNOTIFY_REAPER_DELAY); /* * Some groups like to know that marks are being freed. This is a @@ -388,7 +390,12 @@ err: spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + queue_delayed_work(system_unbound_wq, &reaper_work, + FSNOTIFY_REAPER_DELAY); + return ret; } @@ -491,3 +498,21 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } + +static void fsnotify_mark_destroy(struct work_struct *work) +{ + struct fsnotify_mark *mark, *next; + struct list_head private_destroy_list; + + spin_lock(&destroy_lock); + /* exchange the list head */ + list_replace_init(&destroy_list, &private_destroy_list); + spin_unlock(&destroy_lock); + + synchronize_srcu(&fsnotify_mark_srcu); + + list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { + list_del_init(&mark->g_list); + fsnotify_put_mark(mark); + } +} 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/read_write.c b/fs/read_write.c index 324ec271cc4e..0c8782aa3d71 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; } 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.", |