diff options
Diffstat (limited to 'fs')
85 files changed, 802 insertions, 609 deletions
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index ce7dec88f4b8..541fbfaed276 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -343,7 +343,7 @@ static int btrfsic_process_written_superblock( struct btrfsic_state *state, struct btrfsic_block *const block, struct btrfs_super_block *const super_hdr); -static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status); +static void btrfsic_bio_end_io(struct bio *bp); static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate); static int btrfsic_is_block_ref_by_superblock(const struct btrfsic_state *state, const struct btrfsic_block *block, @@ -2207,7 +2207,7 @@ continue_loop: goto again; } -static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) +static void btrfsic_bio_end_io(struct bio *bp) { struct btrfsic_block *block = (struct btrfsic_block *)bp->bi_private; int iodone_w_error; @@ -2215,7 +2215,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) /* mutex is not held! This is not save if IO is not yet completed * on umount */ iodone_w_error = 0; - if (bio_error_status) + if (bp->bi_error) iodone_w_error = 1; BUG_ON(NULL == block); @@ -2230,7 +2230,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) BTRFSIC_PRINT_MASK_END_IO_BIO_BH)) printk(KERN_INFO "bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n", - bio_error_status, + bp->bi_error, btrfsic_get_block_type(dev_state->state, block), block->logical_bytenr, dev_state->name, block->dev_bytenr, block->mirror_num); @@ -2252,7 +2252,7 @@ static void btrfsic_bio_end_io(struct bio *bp, int bio_error_status) block = next_block; } while (NULL != block); - bp->bi_end_io(bp, bio_error_status); + bp->bi_end_io(bp); } static void btrfsic_bh_end_io(struct buffer_head *bh, int uptodate) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index ce62324c78e7..57ee8ca29b06 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -97,10 +97,7 @@ static inline int compressed_bio_size(struct btrfs_root *root, static struct bio *compressed_bio_alloc(struct block_device *bdev, u64 first_byte, gfp_t gfp_flags) { - int nr_vecs; - - nr_vecs = bio_get_nr_vecs(bdev); - return btrfs_bio_alloc(bdev, first_byte >> 9, nr_vecs, gfp_flags); + return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags); } static int check_compressed_csum(struct inode *inode, @@ -152,7 +149,7 @@ fail: * The compressed pages are freed here, and it must be run * in process context */ -static void end_compressed_bio_read(struct bio *bio, int err) +static void end_compressed_bio_read(struct bio *bio) { struct compressed_bio *cb = bio->bi_private; struct inode *inode; @@ -160,7 +157,7 @@ static void end_compressed_bio_read(struct bio *bio, int err) unsigned long index; int ret; - if (err) + if (bio->bi_error) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -210,7 +207,7 @@ csum_failed: bio_for_each_segment_all(bvec, cb->orig_bio, i) SetPageChecked(bvec->bv_page); - bio_endio(cb->orig_bio, 0); + bio_endio(cb->orig_bio); } /* finally free the cb struct */ @@ -266,7 +263,7 @@ static noinline void end_compressed_writeback(struct inode *inode, * This also calls the writeback end hooks for the file pages so that * metadata and checksums can be updated in the file. */ -static void end_compressed_bio_write(struct bio *bio, int err) +static void end_compressed_bio_write(struct bio *bio) { struct extent_io_tree *tree; struct compressed_bio *cb = bio->bi_private; @@ -274,7 +271,7 @@ static void end_compressed_bio_write(struct bio *bio, int err) struct page *page; unsigned long index; - if (err) + if (bio->bi_error) cb->errors = 1; /* if there are more bios still pending for this compressed @@ -293,7 +290,7 @@ static void end_compressed_bio_write(struct bio *bio, int err) cb->start, cb->start + cb->len - 1, NULL, - err ? 0 : 1); + bio->bi_error ? 0 : 1); cb->compressed_pages[0]->mapping = NULL; end_compressed_writeback(inode, cb); @@ -697,8 +694,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); - if (ret) - bio_endio(comp_bio, ret); + if (ret) { + bio->bi_error = ret; + bio_endio(comp_bio); + } bio_put(comp_bio); @@ -724,8 +723,10 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio, } ret = btrfs_map_bio(root, READ, comp_bio, mirror_num, 0); - if (ret) - bio_endio(comp_bio, ret); + if (ret) { + bio->bi_error = ret; + bio_endio(comp_bio); + } bio_put(comp_bio); return 0; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 862fbc206755..564a7de17d99 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -378,7 +378,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device); if (ret) - btrfs_error(root->fs_info, ret, "kobj add dev failed"); + btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret); printk_in_rcu(KERN_INFO "BTRFS: dev_replace from %s (devid %llu) to %s started\n", diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a9aadb2ad525..5e307bd0471a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -703,7 +703,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror) return -EIO; /* we fixed nothing */ } -static void end_workqueue_bio(struct bio *bio, int err) +static void end_workqueue_bio(struct bio *bio) { struct btrfs_end_io_wq *end_io_wq = bio->bi_private; struct btrfs_fs_info *fs_info; @@ -711,7 +711,7 @@ static void end_workqueue_bio(struct bio *bio, int err) btrfs_work_func_t func; fs_info = end_io_wq->info; - end_io_wq->error = err; + end_io_wq->error = bio->bi_error; if (bio->bi_rw & REQ_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { @@ -808,7 +808,8 @@ static void run_one_async_done(struct btrfs_work *work) /* If an error occured we just want to clean up the bio and move on */ if (async->error) { - bio_endio(async->bio, async->error); + async->bio->bi_error = async->error; + bio_endio(async->bio); return; } @@ -908,8 +909,10 @@ static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio, * submission context. Just jump into btrfs_map_bio */ ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1); - if (ret) - bio_endio(bio, ret); + if (ret) { + bio->bi_error = ret; + bio_endio(bio); + } return ret; } @@ -960,10 +963,13 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, __btree_submit_bio_done); } - if (ret) { + if (ret) + goto out_w_error; + return 0; + out_w_error: - bio_endio(bio, ret); - } + bio->bi_error = ret; + bio_endio(bio); return ret; } @@ -1735,16 +1741,15 @@ static void end_workqueue_fn(struct btrfs_work *work) { struct bio *bio; struct btrfs_end_io_wq *end_io_wq; - int error; end_io_wq = container_of(work, struct btrfs_end_io_wq, work); bio = end_io_wq->bio; - error = end_io_wq->error; + bio->bi_error = end_io_wq->error; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); - bio_endio(bio, error); + bio_endio(bio); } static int cleaner_kthread(void *arg) @@ -2842,6 +2847,7 @@ int open_ctree(struct super_block *sb, !extent_buffer_uptodate(chunk_root->node)) { printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n", sb->s_id); + chunk_root->node = NULL; goto fail_tree_roots; } btrfs_set_root_node(&chunk_root->root_item, chunk_root->node); @@ -2879,7 +2885,7 @@ retry_root_backup: !extent_buffer_uptodate(tree_root->node)) { printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n", sb->s_id); - + tree_root->node = NULL; goto recovery_tree_root; } @@ -3323,10 +3329,8 @@ static int write_dev_supers(struct btrfs_device *device, * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done */ -static void btrfs_end_empty_barrier(struct bio *bio, int err) +static void btrfs_end_empty_barrier(struct bio *bio) { - if (err) - clear_bit(BIO_UPTODATE, &bio->bi_flags); if (bio->bi_private) complete(bio->bi_private); bio_put(bio); @@ -3354,8 +3358,8 @@ static int write_dev_flush(struct btrfs_device *device, int wait) wait_for_completion(&device->flush_wait); - if (!bio_flagged(bio, BIO_UPTODATE)) { - ret = -EIO; + if (bio->bi_error) { + ret = bio->bi_error; btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); } diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 171312d51799..07204bf601ed 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4227,6 +4227,24 @@ out: space_info->chunk_alloc = 0; spin_unlock(&space_info->lock); mutex_unlock(&fs_info->chunk_mutex); + /* + * When we allocate a new chunk we reserve space in the chunk block + * reserve to make sure we can COW nodes/leafs in the chunk tree or + * add new nodes/leafs to it if we end up needing to do it when + * inserting the chunk item and updating device items as part of the + * second phase of chunk allocation, performed by + * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a + * large number of new block groups to create in our transaction + * handle's new_bgs list to avoid exhausting the chunk block reserve + * in extreme cases - like having a single transaction create many new + * block groups when starting to write out the free space caches of all + * the block groups that were made dirty during the lifetime of the + * transaction. + */ + if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) { + btrfs_create_pending_block_groups(trans, trans->root); + btrfs_trans_release_chunk_metadata(trans); + } return ret; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 02d05817cbdf..68b12bbc709f 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2486,7 +2486,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end) * Scheduling is not allowed, so the extent state tree is expected * to have one and only one object corresponding to this IO. */ -static void end_bio_extent_writepage(struct bio *bio, int err) +static void end_bio_extent_writepage(struct bio *bio) { struct bio_vec *bvec; u64 start; @@ -2516,7 +2516,7 @@ static void end_bio_extent_writepage(struct bio *bio, int err) start = page_offset(page); end = start + bvec->bv_offset + bvec->bv_len - 1; - if (end_extent_writepage(page, err, start, end)) + if (end_extent_writepage(page, bio->bi_error, start, end)) continue; end_page_writeback(page); @@ -2548,10 +2548,10 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len, * Scheduling is not allowed, so the extent state tree is expected * to have one and only one object corresponding to this IO. */ -static void end_bio_extent_readpage(struct bio *bio, int err) +static void end_bio_extent_readpage(struct bio *bio) { struct bio_vec *bvec; - int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); + int uptodate = !bio->bi_error; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); struct extent_io_tree *tree; u64 offset = 0; @@ -2564,16 +2564,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err) int ret; int i; - if (err) - uptodate = 0; - bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; struct inode *inode = page->mapping->host; pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, " - "mirror=%u\n", (u64)bio->bi_iter.bi_sector, err, - io_bio->mirror_num); + "mirror=%u\n", (u64)bio->bi_iter.bi_sector, + bio->bi_error, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; /* We always issue full-page reads, but if some block @@ -2614,8 +2611,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) if (tree->ops && tree->ops->readpage_io_failed_hook) { ret = tree->ops->readpage_io_failed_hook(page, mirror); - if (!ret && !err && - test_bit(BIO_UPTODATE, &bio->bi_flags)) + if (!ret && !bio->bi_error) uptodate = 1; } else { /* @@ -2631,10 +2627,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err) ret = bio_readpage_error(bio, offset, page, start, end, mirror); if (ret == 0) { - uptodate = - test_bit(BIO_UPTODATE, &bio->bi_flags); - if (err) - uptodate = 0; + uptodate = !bio->bi_error; offset += len; continue; } @@ -2684,7 +2677,7 @@ readpage_ok: endio_readpage_release_extent(tree, extent_start, extent_len, uptodate); if (io_bio->end_io) - io_bio->end_io(io_bio, err); + io_bio->end_io(io_bio, bio->bi_error); bio_put(bio); } @@ -2802,9 +2795,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, { int ret = 0; struct bio *bio; - int nr; int contig = 0; - int this_compressed = bio_flags & EXTENT_BIO_COMPRESSED; int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED; size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE); @@ -2829,12 +2820,9 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, return 0; } } - if (this_compressed) - nr = BIO_MAX_PAGES; - else - nr = bio_get_nr_vecs(bdev); - bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH); + bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES, + GFP_NOFS | __GFP_HIGH); if (!bio) return -ENOMEM; @@ -3696,7 +3684,7 @@ static void set_btree_ioerr(struct page *page) } } -static void end_bio_extent_buffer_writepage(struct bio *bio, int err) +static void end_bio_extent_buffer_writepage(struct bio *bio) { struct bio_vec *bvec; struct extent_buffer *eb; @@ -3709,7 +3697,8 @@ static void end_bio_extent_buffer_writepage(struct bio *bio, int err) BUG_ON(!eb); done = atomic_dec_and_test(&eb->io_pages); - if (err || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { + if (bio->bi_error || + test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) { ClearPageUptodate(page); set_btree_ioerr(page); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e33dff356460..f924d9a62700 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1845,8 +1845,10 @@ static int __btrfs_submit_bio_done(struct inode *inode, int rw, struct bio *bio, int ret; ret = btrfs_map_bio(root, rw, bio, mirror_num, 1); - if (ret) - bio_endio(bio, ret); + if (ret) { + bio->bi_error = ret; + bio_endio(bio); + } return ret; } @@ -1906,8 +1908,10 @@ mapit: ret = btrfs_map_bio(root, rw, bio, mirror_num, 0); out: - if (ret < 0) - bio_endio(bio, ret); + if (ret < 0) { + bio->bi_error = ret; + bio_endio(bio); + } return ret; } @@ -7688,13 +7692,13 @@ struct btrfs_retry_complete { int uptodate; }; -static void btrfs_retry_endio_nocsum(struct bio *bio, int err) +static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct bio_vec *bvec; int i; - if (err) + if (bio->bi_error) goto end; done->uptodate = 1; @@ -7743,7 +7747,7 @@ try_again: return 0; } -static void btrfs_retry_endio(struct bio *bio, int err) +static void btrfs_retry_endio(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); @@ -7752,7 +7756,7 @@ static void btrfs_retry_endio(struct bio *bio, int err) int ret; int i; - if (err) + if (bio->bi_error) goto end; uptodate = 1; @@ -7835,12 +7839,13 @@ static int btrfs_subio_endio_read(struct inode *inode, } } -static void btrfs_endio_direct_read(struct bio *bio, int err) +static void btrfs_endio_direct_read(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; struct inode *inode = dip->inode; struct bio *dio_bio; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); + int err = bio->bi_error; if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) err = btrfs_subio_endio_read(inode, io_bio, err); @@ -7851,17 +7856,14 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) kfree(dip); - /* If we had a csum failure make sure to clear the uptodate flag */ - if (err) - clear_bit(BIO_UPTODATE, &dio_bio->bi_flags); - dio_end_io(dio_bio, err); + dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) io_bio->end_io(io_bio, err); bio_put(bio); } -static void btrfs_endio_direct_write(struct bio *bio, int err) +static void btrfs_endio_direct_write(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; struct inode *inode = dip->inode; @@ -7875,7 +7877,8 @@ static void btrfs_endio_direct_write(struct bio *bio, int err) again: ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, &ordered_offset, - ordered_bytes, !err); + ordered_bytes, + !bio->bi_error); if (!ret) goto out_test; @@ -7898,10 +7901,7 @@ out_test: kfree(dip); - /* If we had an error make sure to clear the uptodate flag */ - if (err) - clear_bit(BIO_UPTODATE, &dio_bio->bi_flags); - dio_end_io(dio_bio, err); + dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } @@ -7916,9 +7916,10 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode, int rw, return 0; } -static void btrfs_end_dio_bio(struct bio *bio, int err) +static void btrfs_end_dio_bio(struct bio *bio) { struct btrfs_dio_private *dip = bio->bi_private; + int err = bio->bi_error; if (err) btrfs_warn(BTRFS_I(dip->inode)->root->fs_info, @@ -7947,8 +7948,8 @@ static void btrfs_end_dio_bio(struct bio *bio, int err) if (dip->errors) { bio_io_error(dip->orig_bio); } else { - set_bit(BIO_UPTODATE, &dip->dio_bio->bi_flags); - bio_endio(dip->orig_bio, 0); + dip->dio_bio->bi_error = 0; + bio_endio(dip->orig_bio); } out: bio_put(bio); @@ -7957,8 +7958,7 @@ out: static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, u64 first_sector, gfp_t gfp_flags) { - int nr_vecs = bio_get_nr_vecs(bdev); - return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags); + return btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags); } static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root, @@ -8219,7 +8219,8 @@ free_ordered: * callbacks - they require an allocated dip and a clone of dio_bio. */ if (io_bio && dip) { - bio_endio(io_bio, ret); + io_bio->bi_error = -EIO; + bio_endio(io_bio); /* * The end io callbacks free our dip, do the final put on io_bio * and all the cleanup and final put for dio_bio (through @@ -8246,7 +8247,7 @@ free_ordered: unlock_extent(&BTRFS_I(inode)->io_tree, file_offset, file_offset + dio_bio->bi_iter.bi_size - 1); } - clear_bit(BIO_UPTODATE, &dio_bio->bi_flags); + dio_bio->bi_error = -EIO; /* * Releases and cleans up our dio_bio, no need to bio_put() * nor bio_endio()/bio_io_error() against dio_bio. diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index e9ace099162c..d904ee1c5349 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -376,7 +376,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info) qgroup = find_qgroup_rb(fs_info, found_key.offset); if ((qgroup && found_key.type == BTRFS_QGROUP_INFO_KEY) || (!qgroup && found_key.type == BTRFS_QGROUP_LIMIT_KEY)) { - btrfs_err(fs_info, "inconsitent qgroup config"); + btrfs_err(fs_info, "inconsistent qgroup config"); flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT; } if (!qgroup) { @@ -1651,6 +1651,11 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info, /* Exclusive -> exclusive, nothing changed */ } } + + /* For exclusive extent, free its reserved bytes too */ + if (nr_old_roots == 0 && nr_new_roots == 1 && + cur_new_count == nr_new_roots) + qg->reserved -= num_bytes; if (dirty) qgroup_dirty(fs_info, qg); } diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index fa72068bd256..0a02e24900aa 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -851,7 +851,7 @@ static void free_raid_bio(struct btrfs_raid_bio *rbio) * this frees the rbio and runs through all the bios in the * bio_list and calls end_io on them */ -static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate) +static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err) { struct bio *cur = bio_list_get(&rbio->bio_list); struct bio *next; @@ -864,9 +864,8 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate) while (cur) { next = cur->bi_next; cur->bi_next = NULL; - if (uptodate) - set_bit(BIO_UPTODATE, &cur->bi_flags); - bio_endio(cur, err); + cur->bi_error = err; + bio_endio(cur); cur = next; } } @@ -875,9 +874,10 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err, int uptodate) * end io function used by finish_rmw. When we finally * get here, we've written a full stripe */ -static void raid_write_end_io(struct bio *bio, int err) +static void raid_write_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; + int err = bio->bi_error; if (err) fail_bio_stripe(rbio, bio); @@ -893,7 +893,7 @@ static void raid_write_end_io(struct bio *bio, int err) if (atomic_read(&rbio->error) > rbio->bbio->max_errors) err = -EIO; - rbio_orig_end_io(rbio, err, 0); + rbio_orig_end_io(rbio, err); return; } @@ -1071,7 +1071,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, * devices or if they are not contiguous */ if (last_end == disk_start && stripe->dev->bdev && - test_bit(BIO_UPTODATE, &last->bi_flags) && + !last->bi_error && last->bi_bdev == stripe->dev->bdev) { ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0); if (ret == PAGE_CACHE_SIZE) @@ -1087,7 +1087,6 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio, bio->bi_iter.bi_size = 0; bio->bi_bdev = stripe->dev->bdev; bio->bi_iter.bi_sector = disk_start >> 9; - set_bit(BIO_UPTODATE, &bio->bi_flags); bio_add_page(bio, page, PAGE_CACHE_SIZE, 0); bio_list_add(bio_list, bio); @@ -1312,13 +1311,12 @@ write_data: bio->bi_private = rbio; bio->bi_end_io = raid_write_end_io; - BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); submit_bio(WRITE, bio); } return; cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); } /* @@ -1441,11 +1439,11 @@ static void set_bio_pages_uptodate(struct bio *bio) * This will usually kick off finish_rmw once all the bios are read in, but it * may trigger parity reconstruction if we had any errors along the way */ -static void raid_rmw_end_io(struct bio *bio, int err) +static void raid_rmw_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (err) + if (bio->bi_error) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -1455,7 +1453,6 @@ static void raid_rmw_end_io(struct bio *bio, int err) if (!atomic_dec_and_test(&rbio->stripes_pending)) return; - err = 0; if (atomic_read(&rbio->error) > rbio->bbio->max_errors) goto cleanup; @@ -1469,7 +1466,7 @@ static void raid_rmw_end_io(struct bio *bio, int err) cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); } static void async_rmw_stripe(struct btrfs_raid_bio *rbio) @@ -1572,14 +1569,13 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); - BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); submit_bio(READ, bio); } /* the actual write will happen once the reads are done */ return 0; cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); return -EIO; finish: @@ -1964,7 +1960,7 @@ cleanup_io: else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); - rbio_orig_end_io(rbio, err, err == 0); + rbio_orig_end_io(rbio, err); } else if (err == 0) { rbio->faila = -1; rbio->failb = -1; @@ -1976,7 +1972,7 @@ cleanup_io: else BUG(); } else { - rbio_orig_end_io(rbio, err, 0); + rbio_orig_end_io(rbio, err); } } @@ -1984,7 +1980,7 @@ cleanup_io: * This is called only for stripes we've read from disk to * reconstruct the parity. */ -static void raid_recover_end_io(struct bio *bio, int err) +static void raid_recover_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; @@ -1992,7 +1988,7 @@ static void raid_recover_end_io(struct bio *bio, int err) * we only read stripe pages off the disk, set them * up to date if there were no errors */ - if (err) + if (bio->bi_error) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -2002,7 +1998,7 @@ static void raid_recover_end_io(struct bio *bio, int err) return; if (atomic_read(&rbio->error) > rbio->bbio->max_errors) - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); else __raid_recover_end_io(rbio); } @@ -2094,7 +2090,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio) btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); - BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); submit_bio(READ, bio); } out: @@ -2102,7 +2097,7 @@ out: cleanup: if (rbio->operation == BTRFS_RBIO_READ_REBUILD) - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); return -EIO; } @@ -2277,11 +2272,12 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) * end io function used by finish_rmw. When we finally * get here, we've written a full stripe */ -static void raid_write_parity_end_io(struct bio *bio, int err) +static void raid_write_parity_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; + int err = bio->bi_error; - if (err) + if (bio->bi_error) fail_bio_stripe(rbio, bio); bio_put(bio); @@ -2294,7 +2290,7 @@ static void raid_write_parity_end_io(struct bio *bio, int err) if (atomic_read(&rbio->error)) err = -EIO; - rbio_orig_end_io(rbio, err, 0); + rbio_orig_end_io(rbio, err); } static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio, @@ -2437,7 +2433,7 @@ submit_write: nr_data = bio_list_size(&bio_list); if (!nr_data) { /* Every parity is right */ - rbio_orig_end_io(rbio, 0, 0); + rbio_orig_end_io(rbio, 0); return; } @@ -2450,13 +2446,12 @@ submit_write: bio->bi_private = rbio; bio->bi_end_io = raid_write_parity_end_io; - BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); submit_bio(WRITE, bio); } return; cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); } static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe) @@ -2524,7 +2519,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio) return; cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); } /* @@ -2535,11 +2530,11 @@ cleanup: * This will usually kick off finish_rmw once all the bios are read in, but it * may trigger parity reconstruction if we had any errors along the way */ -static void raid56_parity_scrub_end_io(struct bio *bio, int err) +static void raid56_parity_scrub_end_io(struct bio *bio) { struct btrfs_raid_bio *rbio = bio->bi_private; - if (err) + if (bio->bi_error) fail_bio_stripe(rbio, bio); else set_bio_pages_uptodate(bio); @@ -2632,14 +2627,13 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56); - BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags)); submit_bio(READ, bio); } /* the actual write will happen once the reads are done */ return; cleanup: - rbio_orig_end_io(rbio, -EIO, 0); + rbio_orig_end_io(rbio, -EIO); return; finish: diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 94db0fa5225a..9c146d8307b5 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -278,7 +278,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len, u64 physical, struct btrfs_device *dev, u64 flags, u64 gen, int mirror_num, u8 *csum, int force, u64 physical_for_dev_replace); -static void scrub_bio_end_io(struct bio *bio, int err); +static void scrub_bio_end_io(struct bio *bio); static void scrub_bio_end_io_worker(struct btrfs_work *work); static void scrub_block_complete(struct scrub_block *sblock); static void scrub_remap_extent(struct btrfs_fs_info *fs_info, @@ -295,7 +295,7 @@ static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx); static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx, struct scrub_page *spage); static void scrub_wr_submit(struct scrub_ctx *sctx); -static void scrub_wr_bio_end_io(struct bio *bio, int err); +static void scrub_wr_bio_end_io(struct bio *bio); static void scrub_wr_bio_end_io_worker(struct btrfs_work *work); static int write_page_nocow(struct scrub_ctx *sctx, u64 physical_for_dev_replace, struct page *page); @@ -454,27 +454,14 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace) struct scrub_ctx *sctx; int i; struct btrfs_fs_info *fs_info = dev->dev_root->fs_info; - int pages_per_rd_bio; int ret; - /* - * the setting of pages_per_rd_bio is correct for scrub but might - * be wrong for the dev_replace code where we might read from - * different devices in the initial huge bios. However, that - * code is able to correctly handle the case when adding a page - * to a bio fails. - */ - if (dev->bdev) - pages_per_rd_bio = min_t(int, SCRUB_PAGES_PER_RD_BIO, - bio_get_nr_vecs(dev->bdev)); - else - pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO; sctx = kzalloc(sizeof(*sctx), GFP_NOFS); if (!sctx) goto nomem; atomic_set(&sctx->refs, 1); sctx->is_dev_replace = is_dev_replace; - sctx->pages_per_rd_bio = pages_per_rd_bio; + sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO; sctx->curr = -1; sctx->dev_root = dev->dev_root; for (i = 0; i < SCRUB_BIOS_PER_SCTX; ++i) { @@ -1429,11 +1416,11 @@ struct scrub_bio_ret { int error; }; -static void scrub_bio_wait_endio(struct bio *bio, int error) +static void scrub_bio_wait_endio(struct bio *bio) { struct scrub_bio_ret *ret = bio->bi_private; - ret->error = error; + ret->error = bio->bi_error; complete(&ret->event); } @@ -1790,12 +1777,12 @@ static void scrub_wr_submit(struct scrub_ctx *sctx) btrfsic_submit_bio(WRITE, sbio->bio); } -static void scrub_wr_bio_end_io(struct bio *bio, int err) +static void scrub_wr_bio_end_io(struct bio *bio) { struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->dev_root->fs_info; - sbio->err = err; + sbio->err = bio->bi_error; sbio->bio = bio; btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper, @@ -2098,7 +2085,7 @@ static void scrub_submit(struct scrub_ctx *sctx) */ printk_ratelimited(KERN_WARNING "BTRFS: scrub_submit(bio bdev == NULL) is unexpected!\n"); - bio_endio(sbio->bio, -EIO); + bio_io_error(sbio->bio); } else { btrfsic_submit_bio(READ, sbio->bio); } @@ -2260,12 +2247,12 @@ leave_nomem: return 0; } -static void scrub_bio_end_io(struct bio *bio, int err) +static void scrub_bio_end_io(struct bio *bio) { struct scrub_bio *sbio = bio->bi_private; struct btrfs_fs_info *fs_info = sbio->dev->dev_root->fs_info; - sbio->err = err; + sbio->err = bio->bi_error; sbio->bio = bio; btrfs_queue_work(fs_info->scrub_workers, &sbio->work); @@ -2672,11 +2659,11 @@ static void scrub_parity_bio_endio_worker(struct btrfs_work *work) scrub_pending_bio_dec(sctx); } -static void scrub_parity_bio_endio(struct bio *bio, int error) +static void scrub_parity_bio_endio(struct bio *bio) { struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private; - if (error) + if (bio->bi_error) bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap, sparity->nsectors); @@ -3896,8 +3883,7 @@ static int scrub_setup_wr_ctx(struct scrub_ctx *sctx, return 0; WARN_ON(!dev->bdev); - wr_ctx->pages_per_wr_bio = min_t(int, SCRUB_PAGES_PER_WR_BIO, - bio_get_nr_vecs(dev->bdev)); + wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO; wr_ctx->tgtdev = dev; atomic_set(&wr_ctx->flush_all_writes, 0); return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cd7ef34d2dce..6bad63379a4c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2163,8 +2163,7 @@ static int btrfs_interface_init(void) static void btrfs_interface_exit(void) { - if (misc_deregister(&btrfs_misc) < 0) - printk(KERN_INFO "BTRFS: misc_deregister failed for control device\n"); + misc_deregister(&btrfs_misc); } static void btrfs_print_info(void) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 51e0f0d0053e..f5021fcb154e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2152,7 +2152,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); - if (current != root->fs_info->transaction_kthread) + if (current != root->fs_info->transaction_kthread && + current != root->fs_info->cleaner_kthread) btrfs_run_delayed_iputs(root); return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fbe7c104531c..762476f5f08d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5741,23 +5741,23 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } -static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio, int err) +static inline void btrfs_end_bbio(struct btrfs_bio *bbio, struct bio *bio) { bio->bi_private = bbio->private; bio->bi_end_io = bbio->end_io; - bio_endio(bio, err); + bio_endio(bio); btrfs_put_bbio(bbio); } -static void btrfs_end_bio(struct bio *bio, int err) +static void btrfs_end_bio(struct bio *bio) { struct btrfs_bio *bbio = bio->bi_private; int is_orig_bio = 0; - if (err) { + if (bio->bi_error) { atomic_inc(&bbio->error); - if (err == -EIO || err == -EREMOTEIO) { + if (bio->bi_error == -EIO || bio->bi_error == -EREMOTEIO) { unsigned int stripe_index = btrfs_io_bio(bio)->stripe_index; struct btrfs_device *dev; @@ -5795,17 +5795,16 @@ static void btrfs_end_bio(struct bio *bio, int err) * beyond the tolerance of the btrfs bio */ if (atomic_read(&bbio->error) > bbio->max_errors) { - err = -EIO; + bio->bi_error = -EIO; } else { /* * this bio is actually up to date, we didn't * go over the max number of errors */ - set_bit(BIO_UPTODATE, &bio->bi_flags); - err = 0; + bio->bi_error = 0; } - btrfs_end_bbio(bbio, bio, err); + btrfs_end_bbio(bbio, bio); } else if (!is_orig_bio) { bio_put(bio); } @@ -5826,7 +5825,7 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root, struct btrfs_pending_bios *pending_bios; if (device->missing || !device->bdev) { - bio_endio(bio, -EIO); + bio_io_error(bio); return; } @@ -5871,34 +5870,6 @@ static noinline void btrfs_schedule_bio(struct btrfs_root *root, &device->work); } -static int bio_size_ok(struct block_device *bdev, struct bio *bio, - sector_t sector) -{ - struct bio_vec *prev; - struct request_queue *q = bdev_get_queue(bdev); - unsigned int max_sectors = queue_max_sectors(q); - struct bvec_merge_data bvm = { - .bi_bdev = bdev, - .bi_sector = sector, - .bi_rw = bio->bi_rw, - }; - - if (WARN_ON(bio->bi_vcnt == 0)) - return 1; - - prev = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (bio_sectors(bio) > max_sectors) - return 0; - - if (!q->merge_bvec_fn) - return 1; - - bvm.bi_size = bio->bi_iter.bi_size - prev->bv_len; - if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) - return 0; - return 1; -} - static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio, struct bio *bio, u64 physical, int dev_nr, int rw, int async) @@ -5932,38 +5903,6 @@ static void submit_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio, btrfsic_submit_bio(rw, bio); } -static int breakup_stripe_bio(struct btrfs_root *root, struct btrfs_bio *bbio, - struct bio *first_bio, struct btrfs_device *dev, - int dev_nr, int rw, int async) -{ - struct bio_vec *bvec = first_bio->bi_io_vec; - struct bio *bio; - int nr_vecs = bio_get_nr_vecs(dev->bdev); - u64 physical = bbio->stripes[dev_nr].physical; - -again: - bio = btrfs_bio_alloc(dev->bdev, physical >> 9, nr_vecs, GFP_NOFS); - if (!bio) - return -ENOMEM; - - while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) { - if (bio_add_page(bio, bvec->bv_page, bvec->bv_len, - bvec->bv_offset) < bvec->bv_len) { - u64 len = bio->bi_iter.bi_size; - - atomic_inc(&bbio->stripes_pending); - submit_stripe_bio(root, bbio, bio, physical, dev_nr, - rw, async); - physical += len; - goto again; - } - bvec++; - } - - submit_stripe_bio(root, bbio, bio, physical, dev_nr, rw, async); - return 0; -} - static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) { atomic_inc(&bbio->error); @@ -5973,8 +5912,8 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) btrfs_io_bio(bio)->mirror_num = bbio->mirror_num; bio->bi_iter.bi_sector = logical >> 9; - - btrfs_end_bbio(bbio, bio, -EIO); + bio->bi_error = -EIO; + btrfs_end_bbio(bbio, bio); } } @@ -6036,18 +5975,6 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, continue; } - /* - * Check and see if we're ok with this bio based on it's size - * and offset with the given device. - */ - if (!bio_size_ok(dev->bdev, first_bio, - bbio->stripes[dev_nr].physical >> 9)) { - ret = breakup_stripe_bio(root, bbio, first_bio, dev, - dev_nr, rw, async_submit); - BUG_ON(ret); - continue; - } - if (dev_nr < total_devs - 1) { bio = btrfs_bio_clone(first_bio, GFP_NOFS); BUG_ON(!bio); /* -ENOMEM */ diff --git a/fs/buffer.c b/fs/buffer.c index 1cf7a53a0277..82283abb2795 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2957,14 +2957,14 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, } EXPORT_SYMBOL(generic_block_bmap); -static void end_bio_bh_io_sync(struct bio *bio, int err) +static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; - if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags))) + if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); - bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags)); + bh->b_end_io(bh, !bio->bi_error); bio_put(bio); } @@ -3046,12 +3046,9 @@ static int submit_bh_wbc(int rw, struct buffer_head *bh, bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_bdev = bh->b_bdev; - bio->bi_io_vec[0].bv_page = bh->b_page; - bio->bi_io_vec[0].bv_len = bh->b_size; - bio->bi_io_vec[0].bv_offset = bh_offset(bh); - bio->bi_vcnt = 1; - bio->bi_iter.bi_size = bh->b_size; + bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh)); + BUG_ON(bio->bi_iter.bi_size != bh->b_size); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index dc10c9dd36c1..ddd5e9471290 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1506,7 +1506,6 @@ static int __mark_caps_flushing(struct inode *inode, swap(cf, ci->i_prealloc_cap_flush); cf->caps = flushing; - cf->kick = false; spin_lock(&mdsc->cap_dirty_lock); list_del_init(&ci->i_dirty_item); @@ -2123,8 +2122,7 @@ static void kick_flushing_capsnaps(struct ceph_mds_client *mdsc, static int __kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session, - struct ceph_inode_info *ci, - bool kick_all) + struct ceph_inode_info *ci) { struct inode *inode = &ci->vfs_inode; struct ceph_cap *cap; @@ -2150,9 +2148,7 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc, for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) { cf = rb_entry(n, struct ceph_cap_flush, i_node); - if (cf->tid < first_tid) - continue; - if (kick_all || cf->kick) + if (cf->tid >= first_tid) break; } if (!n) { @@ -2161,7 +2157,6 @@ static int __kick_flushing_caps(struct ceph_mds_client *mdsc, } cf = rb_entry(n, struct ceph_cap_flush, i_node); - cf->kick = false; first_tid = cf->tid + 1; @@ -2181,8 +2176,6 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, { struct ceph_inode_info *ci; struct ceph_cap *cap; - struct ceph_cap_flush *cf; - struct rb_node *n; dout("early_kick_flushing_caps mds%d\n", session->s_mds); list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) { @@ -2205,16 +2198,11 @@ void ceph_early_kick_flushing_caps(struct ceph_mds_client *mdsc, if ((cap->issued & ci->i_flushing_caps) != ci->i_flushing_caps) { spin_unlock(&ci->i_ceph_lock); - if (!__kick_flushing_caps(mdsc, session, ci, true)) + if (!__kick_flushing_caps(mdsc, session, ci)) continue; spin_lock(&ci->i_ceph_lock); } - for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) { - cf = rb_entry(n, struct ceph_cap_flush, i_node); - cf->kick = true; - } - spin_unlock(&ci->i_ceph_lock); } } @@ -2228,7 +2216,7 @@ void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, dout("kick_flushing_caps mds%d\n", session->s_mds); list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) { - int delayed = __kick_flushing_caps(mdsc, session, ci, false); + int delayed = __kick_flushing_caps(mdsc, session, ci); if (delayed) { spin_lock(&ci->i_ceph_lock); __cap_delay_requeue(mdsc, ci); @@ -2261,7 +2249,7 @@ static void kick_flushing_inode_caps(struct ceph_mds_client *mdsc, spin_unlock(&ci->i_ceph_lock); - delayed = __kick_flushing_caps(mdsc, session, ci, true); + delayed = __kick_flushing_caps(mdsc, session, ci); if (delayed) { spin_lock(&ci->i_ceph_lock); __cap_delay_requeue(mdsc, ci); diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c index 4347039ecc18..6706bde9ad1b 100644 --- a/fs/ceph/locks.c +++ b/fs/ceph/locks.c @@ -287,7 +287,7 @@ int ceph_encode_locks_to_buffer(struct inode *inode, return 0; spin_lock(&ctx->flc_lock); - list_for_each_entry(lock, &ctx->flc_flock, fl_list) { + list_for_each_entry(lock, &ctx->flc_posix, fl_list) { ++seen_fcntl; if (seen_fcntl > num_fcntl_locks) { err = -ENOSPC; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 860cc016e70d..2f2460d23a06 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -189,7 +189,6 @@ static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap) struct ceph_cap_flush { u64 tid; int caps; - bool kick; struct rb_node g_node; // global union { struct rb_node i_node; // inode diff --git a/fs/char_dev.c b/fs/char_dev.c index ea06a3d0364c..24b142569ca9 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -274,7 +274,7 @@ out2: } /** - * unregister_chrdev_region() - return a range of device numbers + * unregister_chrdev_region() - unregister a range of device numbers * @from: the first in the range of numbers to unregister * @count: the number of device numbers to unregister * @@ -319,6 +319,12 @@ static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh, * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @get_block: The filesystem method used to translate file offsets to blocks + * @complete_unwritten: The filesystem method used to convert unwritten blocks + * to written so the data written to them is exposed. This is required for + * required by write faults for filesystems that will return unwritten + * extent mappings from @get_block, but it is optional for reads as + * dax_insert_mapping() will always zero unwritten blocks. If the fs does + * not support unwritten extents, the it should pass NULL. * * When a page fault occurs, filesystems may call this helper in their * fault handler for DAX files. __dax_fault() assumes the caller has done all @@ -437,8 +443,12 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, * as for normal BH based IO completions. */ error = dax_insert_mapping(inode, &bh, vma, vmf); - if (buffer_unwritten(&bh)) - complete_unwritten(&bh, !error); + if (buffer_unwritten(&bh)) { + if (complete_unwritten) + complete_unwritten(&bh, !error); + else + WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE)); + } out: if (error == -ENOMEM) diff --git a/fs/dcache.c b/fs/dcache.c index 5c8ea15e73a5..9b5fe503f6cb 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -3442,22 +3442,15 @@ void __init vfs_caches_init_early(void) inode_init_early(); } -void __init vfs_caches_init(unsigned long mempages) +void __init vfs_caches_init(void) { - unsigned long reserve; - - /* Base hash sizes on available memory, with a reserve equal to - 150% of current kernel size */ - - reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1); - mempages -= reserve; - names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); dcache_init(); inode_init(); - files_init(mempages); + files_init(); + files_maxfiles_init(); mnt_init(); bdev_cache_init(); chrdev_init(); diff --git a/fs/direct-io.c b/fs/direct-io.c index 745d2342651a..11256291642e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -285,7 +285,7 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio); /* * Asynchronous IO callback. */ -static void dio_bio_end_aio(struct bio *bio, int error) +static void dio_bio_end_aio(struct bio *bio) { struct dio *dio = bio->bi_private; unsigned long remaining; @@ -318,7 +318,7 @@ static void dio_bio_end_aio(struct bio *bio, int error) * During I/O bi_private points at the dio. After I/O, bi_private is used to * implement a singly-linked list of completed BIOs, at dio->bio_list. */ -static void dio_bio_end_io(struct bio *bio, int error) +static void dio_bio_end_io(struct bio *bio) { struct dio *dio = bio->bi_private; unsigned long flags; @@ -345,9 +345,9 @@ void dio_end_io(struct bio *bio, int error) struct dio *dio = bio->bi_private; if (dio->is_async) - dio_bio_end_aio(bio, error); + dio_bio_end_aio(bio); else - dio_bio_end_io(bio, error); + dio_bio_end_io(bio); } EXPORT_SYMBOL_GPL(dio_end_io); @@ -457,15 +457,16 @@ static struct bio *dio_await_one(struct dio *dio) */ static int dio_bio_complete(struct dio *dio, struct bio *bio) { - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec; unsigned i; + int err; - if (!uptodate) + if (bio->bi_error) dio->io_error = -EIO; if (dio->is_async && dio->rw == READ) { bio_check_pages_dirty(bio); /* transfers ownership */ + err = bio->bi_error; } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; @@ -474,9 +475,10 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) set_page_dirty_lock(page); page_cache_release(page); } + err = bio->bi_error; bio_put(bio); } - return uptodate ? 0 : -EIO; + return err; } /* @@ -653,7 +655,7 @@ static inline int dio_new_bio(struct dio *dio, struct dio_submit *sdio, if (ret) goto out; sector = start_sector << (sdio->blkbits - 9); - nr_pages = min(sdio->pages_in_io, bio_get_nr_vecs(map_bh->b_bdev)); + nr_pages = min(sdio->pages_in_io, BIO_MAX_PAGES); BUG_ON(nr_pages <= 0); dio_bio_alloc(dio, sdio, map_bh->b_bdev, sector, nr_pages); sdio->boundary = 0; diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c index e0ab3a93eeff..5532f097f6da 100644 --- a/fs/dlm/plock.c +++ b/fs/dlm/plock.c @@ -509,7 +509,6 @@ int dlm_plock_init(void) void dlm_plock_exit(void) { - if (misc_deregister(&plock_dev_misc) < 0) - log_print("dlm_plock_exit: misc_deregister failed"); + misc_deregister(&plock_dev_misc); } diff --git a/fs/dlm/user.c b/fs/dlm/user.c index fb85f32e9eca..75ecc0d3bc85 100644 --- a/fs/dlm/user.c +++ b/fs/dlm/user.c @@ -362,18 +362,15 @@ fail: int dlm_device_deregister(struct dlm_ls *ls) { - int error; - /* The device is not registered. This happens when the lockspace was never used from userspace, or when device_create_lockspace() calls dlm_release_lockspace() after the register fails. */ if (!ls->ls_device.name) return 0; - error = misc_deregister(&ls->ls_device); - if (!error) - kfree(ls->ls_device.name); - return error; + misc_deregister(&ls->ls_device); + kfree(ls->ls_device.name); + return 0; } static int device_user_purge(struct dlm_user_proc *proc, diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c index cf208522998e..caba848ac763 100644 --- a/fs/ecryptfs/mmap.c +++ b/fs/ecryptfs/mmap.c @@ -299,7 +299,7 @@ static int ecryptfs_write_begin(struct file *file, rc = ecryptfs_read_lower_page_segment( page, index, 0, PAGE_CACHE_SIZE, mapping->host); if (rc) { - printk(KERN_ERR "%s: Error attemping to read " + printk(KERN_ERR "%s: Error attempting to read " "lower page segment; rc = [%d]\n", __func__, rc); ClearPageUptodate(page); diff --git a/fs/exec.c b/fs/exec.c index 1977c2a553ac..b06623a9347f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -98,6 +98,12 @@ static inline void put_binfmt(struct linux_binfmt * fmt) module_put(fmt->module); } +bool path_noexec(const struct path *path) +{ + return (path->mnt->mnt_flags & MNT_NOEXEC) || + (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); +} + #ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to @@ -132,7 +138,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) goto exit; error = -EACCES; - if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) + if (path_noexec(&file->f_path)) goto exit; fsnotify_open(file); @@ -777,7 +783,7 @@ static struct file *do_open_execat(int fd, struct filename *name, int flags) if (!S_ISREG(file_inode(file)->i_mode)) goto exit; - if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) + if (path_noexec(&file->f_path)) goto exit; err = deny_write_access(file); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 5602450f03f6..8a9d63a0c071 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -61,7 +61,6 @@ static void buffer_io_error(struct buffer_head *bh) static void ext4_finish_bio(struct bio *bio) { int i; - int error = !test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec; bio_for_each_segment_all(bvec, bio, i) { @@ -88,7 +87,7 @@ static void ext4_finish_bio(struct bio *bio) } #endif - if (error) { + if (bio->bi_error) { SetPageError(page); set_bit(AS_EIO, &page->mapping->flags); } @@ -107,7 +106,7 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (error) + if (bio->bi_error) buffer_io_error(bh); } while ((bh = bh->b_this_page) != head); bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); @@ -310,27 +309,25 @@ ext4_io_end_t *ext4_get_io_end(ext4_io_end_t *io_end) } /* BIO completion function for page writeback */ -static void ext4_end_bio(struct bio *bio, int error) +static void ext4_end_bio(struct bio *bio) { ext4_io_end_t *io_end = bio->bi_private; sector_t bi_sector = bio->bi_iter.bi_sector; BUG_ON(!io_end); bio->bi_end_io = NULL; - if (test_bit(BIO_UPTODATE, &bio->bi_flags)) - error = 0; - if (error) { + if (bio->bi_error) { struct inode *inode = io_end->inode; ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu " "(offset %llu size %ld starting block %llu)", - error, inode->i_ino, + bio->bi_error, inode->i_ino, (unsigned long long) io_end->offset, (long) io_end->size, (unsigned long long) bi_sector >> (inode->i_blkbits - 9)); - mapping_set_error(inode->i_mapping, error); + mapping_set_error(inode->i_mapping, bio->bi_error); } if (io_end->flag & EXT4_IO_END_UNWRITTEN) { @@ -375,10 +372,9 @@ void ext4_io_submit_init(struct ext4_io_submit *io, static int io_submit_init_bio(struct ext4_io_submit *io, struct buffer_head *bh) { - int nvecs = bio_get_nr_vecs(bh->b_bdev); struct bio *bio; - bio = bio_alloc(GFP_NOIO, min(nvecs, BIO_MAX_PAGES)); + bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); if (!bio) return -ENOMEM; bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index ec3ef93a52db..e26803fb210d 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -98,7 +98,7 @@ static inline bool ext4_bio_encrypted(struct bio *bio) * status of that page is hard. See end_buffer_async_read() for the details. * There is no point in duplicating all that complexity. */ -static void mpage_end_io(struct bio *bio, int err) +static void mpage_end_io(struct bio *bio) { struct bio_vec *bv; int i; @@ -106,7 +106,7 @@ static void mpage_end_io(struct bio *bio, int err) if (ext4_bio_encrypted(bio)) { struct ext4_crypto_ctx *ctx = bio->bi_private; - if (err) { + if (bio->bi_error) { ext4_release_crypto_ctx(ctx); } else { INIT_WORK(&ctx->r.work, completion_pages); @@ -118,7 +118,7 @@ static void mpage_end_io(struct bio *bio, int err) bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - if (!err) { + if (!bio->bi_error) { SetPageUptodate(page); } else { ClearPageUptodate(page); @@ -284,7 +284,7 @@ int ext4_mpage_readpages(struct address_space *mapping, goto set_error_page; } bio = bio_alloc(GFP_KERNEL, - min_t(int, nr_pages, bio_get_nr_vecs(bdev))); + min_t(int, nr_pages, BIO_MAX_PAGES)); if (!bio) { if (ctx) ext4_release_crypto_ctx(ctx); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9bedfa8dd3a5..c414d49aa2de 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -29,13 +29,13 @@ static struct kmem_cache *extent_tree_slab; static struct kmem_cache *extent_node_slab; -static void f2fs_read_end_io(struct bio *bio, int err) +static void f2fs_read_end_io(struct bio *bio) { struct bio_vec *bvec; int i; if (f2fs_bio_encrypted(bio)) { - if (err) { + if (bio->bi_error) { f2fs_release_crypto_ctx(bio->bi_private); } else { f2fs_end_io_crypto_work(bio->bi_private, bio); @@ -46,7 +46,7 @@ static void f2fs_read_end_io(struct bio *bio, int err) bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; - if (!err) { + if (!bio->bi_error) { SetPageUptodate(page); } else { ClearPageUptodate(page); @@ -57,7 +57,7 @@ static void f2fs_read_end_io(struct bio *bio, int err) bio_put(bio); } -static void f2fs_write_end_io(struct bio *bio, int err) +static void f2fs_write_end_io(struct bio *bio) { struct f2fs_sb_info *sbi = bio->bi_private; struct bio_vec *bvec; @@ -68,7 +68,7 @@ static void f2fs_write_end_io(struct bio *bio, int err) f2fs_restore_and_release_control_page(&page); - if (unlikely(err)) { + if (unlikely(bio->bi_error)) { set_page_dirty(page); set_bit(AS_EIO, &page->mapping->flags); f2fs_stop_checkpoint(sbi); @@ -1552,7 +1552,7 @@ submit_and_realloc: } bio = bio_alloc(GFP_KERNEL, - min_t(int, nr_pages, bio_get_nr_vecs(bdev))); + min_t(int, nr_pages, BIO_MAX_PAGES)); if (!bio) { if (ctx) f2fs_release_crypto_ctx(ctx); @@ -2072,8 +2072,6 @@ static int f2fs_set_data_page_dirty(struct page *page) return 1; } - mark_inode_dirty(inode); - if (!PageDirty(page)) { __set_page_dirty_nobuffers(page); update_dirty_page(inode, page); diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index ada2a3dd701a..b0f38c3b37f4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1331,12 +1331,13 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp) if (ret) return ret; - if (f2fs_is_atomic_file(inode)) + if (f2fs_is_atomic_file(inode)) { + clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); commit_inmem_pages(inode, false); + } ret = f2fs_sync_file(filp, 0, LONG_MAX, 0); mnt_drop_write_file(filp); - clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); return ret; } @@ -1387,8 +1388,8 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp) f2fs_balance_fs(F2FS_I_SB(inode)); if (f2fs_is_atomic_file(inode)) { - commit_inmem_pages(inode, false); clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE); + commit_inmem_pages(inode, false); } if (f2fs_is_volatile_file(inode)) diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index e1e73617d13b..22fb5ef37966 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -556,27 +556,39 @@ static void move_encrypted_block(struct inode *inode, block_t bidx) if (!fio.encrypted_page) goto put_out; - f2fs_submit_page_bio(&fio); + err = f2fs_submit_page_bio(&fio); + if (err) + goto put_page_out; + + /* write page */ + lock_page(fio.encrypted_page); + + if (unlikely(!PageUptodate(fio.encrypted_page))) + goto put_page_out; + if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi))) + goto put_page_out; + + set_page_dirty(fio.encrypted_page); + f2fs_wait_on_page_writeback(fio.encrypted_page, META); + if (clear_page_dirty_for_io(fio.encrypted_page)) + dec_page_count(fio.sbi, F2FS_DIRTY_META); + + set_page_writeback(fio.encrypted_page); /* allocate block address */ f2fs_wait_on_page_writeback(dn.node_page, NODE); - allocate_data_block(fio.sbi, NULL, fio.blk_addr, &fio.blk_addr, &sum, CURSEG_COLD_DATA); - dn.data_blkaddr = fio.blk_addr; - - /* write page */ - lock_page(fio.encrypted_page); - set_page_writeback(fio.encrypted_page); fio.rw = WRITE_SYNC; f2fs_submit_page_mbio(&fio); + dn.data_blkaddr = fio.blk_addr; set_data_blkaddr(&dn); f2fs_update_extent_cache(&dn); set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE); if (page->index == 0) set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN); - +put_page_out: f2fs_put_page(fio.encrypted_page, 1); put_out: f2fs_put_dnode(&dn); @@ -605,8 +617,8 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type) .page = page, .encrypted_page = NULL, }; + set_page_dirty(page); f2fs_wait_on_page_writeback(page, DATA); - if (clear_page_dirty_for_io(page)) inode_dec_dirty_pages(inode); set_cold_data(page); diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 38e75fb1e488..a13ffcc32992 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -141,6 +141,8 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page) kunmap_atomic(dst_addr); SetPageUptodate(page); no_update: + set_page_dirty(page); + /* clear dirty state */ dirty = clear_page_dirty_for_io(page); diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 1eb343768781..61b97f9cb9f6 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -257,6 +257,7 @@ void commit_inmem_pages(struct inode *inode, bool abort) if (!abort) { lock_page(cur->page); if (cur->page->mapping == inode->i_mapping) { + set_page_dirty(cur->page); f2fs_wait_on_page_writeback(cur->page, DATA); if (clear_page_dirty_for_io(cur->page)) inode_dec_dirty_pages(inode); diff --git a/fs/file_table.c b/fs/file_table.c index 7f9d407c7595..ad17e05ebf95 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -25,6 +25,7 @@ #include <linux/hardirq.h> #include <linux/task_work.h> #include <linux/ima.h> +#include <linux/swap.h> #include <linux/atomic.h> @@ -308,19 +309,24 @@ void put_filp(struct file *file) } } -void __init files_init(unsigned long mempages) +void __init files_init(void) { - unsigned long n; - filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); + percpu_counter_init(&nr_files, 0, GFP_KERNEL); +} - /* - * One file with associated inode and dcache is very roughly 1K. - * Per default don't use more than 10% of our memory for files. - */ +/* + * One file with associated inode and dcache is very roughly 1K. Per default + * do not use more than 10% of our memory for files. + */ +void __init files_maxfiles_init(void) +{ + unsigned long n; + unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2; + + memreserve = min(memreserve, totalram_pages - 1); + n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10; - n = (mempages * (PAGE_SIZE / 1024)) / 10; files_stat.max_files = max_t(unsigned long, n, NR_FILE); - percpu_counter_init(&nr_files, 0, GFP_KERNEL); } diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c index 484b32d3234a..1cff72df0389 100644 --- a/fs/freevxfs/vxfs_lookup.c +++ b/fs/freevxfs/vxfs_lookup.c @@ -192,7 +192,7 @@ vxfs_inode_by_name(struct inode *dip, struct dentry *dp) * by @dp in @dip. * * Returns: - * A NULL-pointer on success, else an negative error code encoded + * A NULL-pointer on success, else a negative error code encoded * in the return pointer. */ static struct dentry * diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index f0520bcf2094..5fa588e933d5 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -702,6 +702,7 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page, else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } +EXPORT_SYMBOL_GPL(wbc_account_io); /** * inode_congested - test whether an inode is congested @@ -843,14 +844,15 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_iter iter; might_sleep(); - - if (!bdi_has_dirty_io(bdi)) - return; restart: rcu_read_lock(); bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) { - if (!wb_has_dirty_io(wb) || - (skip_if_busy && writeback_in_progress(wb))) + /* SYNC_ALL writes out I_DIRTY_TIME too */ + if (!wb_has_dirty_io(wb) && + (base_work->sync_mode == WB_SYNC_NONE || + list_empty(&wb->b_dirty_time))) + continue; + if (skip_if_busy && writeback_in_progress(wb)) continue; base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages); @@ -898,8 +900,7 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, { might_sleep(); - if (bdi_has_dirty_io(bdi) && - (!skip_if_busy || !writeback_in_progress(&bdi->wb))) { + if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; base_work->single_wait = 0; base_work->single_done = 0; @@ -2274,8 +2275,12 @@ void sync_inodes_sb(struct super_block *sb) }; struct backing_dev_info *bdi = sb->s_bdi; - /* Nothing to do? */ - if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) + /* + * Can't skip on !bdi_has_dirty() because we should wait for !dirty + * inodes under writeback and I_DIRTY_TIME inodes ignored by + * bdi_has_dirty() need to be written out too. + */ + if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 80cc1b35d460..ebb5e37455a0 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2246,7 +2246,15 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, err = -EINVAL; if (old) { - struct fuse_dev *fud = fuse_get_dev(old); + struct fuse_dev *fud = NULL; + + /* + * Check against file->f_op because CUSE + * uses the same ioctl handler. + */ + if (old->f_op == file->f_op && + old->f_cred->user_ns == file->f_cred->user_ns) + fud = fuse_get_dev(old); if (fud) { mutex_lock(&fuse_mutex); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 2c1ae861dc94..92324ac58290 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -202,22 +202,22 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, * */ -static void gfs2_end_log_write(struct bio *bio, int error) +static void gfs2_end_log_write(struct bio *bio) { struct gfs2_sbd *sdp = bio->bi_private; struct bio_vec *bvec; struct page *page; int i; - if (error) { - sdp->sd_log_error = error; - fs_err(sdp, "Error %d writing to log\n", error); + if (bio->bi_error) { + sdp->sd_log_error = bio->bi_error; + fs_err(sdp, "Error %d writing to log\n", bio->bi_error); } bio_for_each_segment_all(bvec, bio, i) { page = bvec->bv_page; if (page_has_buffers(page)) - gfs2_end_log_write_bh(sdp, bvec, error); + gfs2_end_log_write_bh(sdp, bvec, bio->bi_error); else mempool_free(page, gfs2_page_pool); } @@ -261,18 +261,11 @@ void gfs2_log_flush_bio(struct gfs2_sbd *sdp, int rw) static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno) { struct super_block *sb = sdp->sd_vfs; - unsigned nrvecs = bio_get_nr_vecs(sb->s_bdev); struct bio *bio; BUG_ON(sdp->sd_log_bio); - while (1) { - bio = bio_alloc(GFP_NOIO, nrvecs); - if (likely(bio)) - break; - nrvecs = max(nrvecs/2, 1U); - } - + bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); bio->bi_iter.bi_sector = blkno * (sb->s_blocksize >> 9); bio->bi_bdev = sb->s_bdev; bio->bi_end_io = gfs2_end_log_write; diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1e3a93f2f71d..02586e7eb964 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -171,14 +171,14 @@ static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent) return -EINVAL; } -static void end_bio_io_page(struct bio *bio, int error) +static void end_bio_io_page(struct bio *bio) { struct page *page = bio->bi_private; - if (!error) + if (!bio->bi_error) SetPageUptodate(page); else - pr_warn("error %d reading superblock\n", error); + pr_warn("error %d reading superblock\n", bio->bi_error); unlock_page(page); } diff --git a/fs/hpfs/buffer.c b/fs/hpfs/buffer.c index 8057fe4e6574..f626114449e4 100644 --- a/fs/hpfs/buffer.c +++ b/fs/hpfs/buffer.c @@ -10,6 +10,30 @@ #include <linux/blkdev.h> #include "hpfs_fn.h" +secno hpfs_search_hotfix_map(struct super_block *s, secno sec) +{ + unsigned i; + struct hpfs_sb_info *sbi = hpfs_sb(s); + for (i = 0; unlikely(i < sbi->n_hotfixes); i++) { + if (sbi->hotfix_from[i] == sec) { + return sbi->hotfix_to[i]; + } + } + return sec; +} + +unsigned hpfs_search_hotfix_map_for_range(struct super_block *s, secno sec, unsigned n) +{ + unsigned i; + struct hpfs_sb_info *sbi = hpfs_sb(s); + for (i = 0; unlikely(i < sbi->n_hotfixes); i++) { + if (sbi->hotfix_from[i] >= sec && sbi->hotfix_from[i] < sec + n) { + n = sbi->hotfix_from[i] - sec; + } + } + return n; +} + void hpfs_prefetch_sectors(struct super_block *s, unsigned secno, int n) { struct buffer_head *bh; @@ -18,6 +42,9 @@ void hpfs_prefetch_sectors(struct super_block *s, unsigned secno, int n) if (n <= 0 || unlikely(secno >= hpfs_sb(s)->sb_fs_size)) return; + if (unlikely(hpfs_search_hotfix_map_for_range(s, secno, n) != n)) + return; + bh = sb_find_get_block(s, secno); if (bh) { if (buffer_uptodate(bh)) { @@ -51,7 +78,7 @@ void *hpfs_map_sector(struct super_block *s, unsigned secno, struct buffer_head cond_resched(); - *bhp = bh = sb_bread(s, secno); + *bhp = bh = sb_bread(s, hpfs_search_hotfix_map(s, secno)); if (bh != NULL) return bh->b_data; else { @@ -71,7 +98,7 @@ void *hpfs_get_sector(struct super_block *s, unsigned secno, struct buffer_head cond_resched(); - if ((*bhp = bh = sb_getblk(s, secno)) != NULL) { + if ((*bhp = bh = sb_getblk(s, hpfs_search_hotfix_map(s, secno))) != NULL) { if (!buffer_uptodate(bh)) wait_on_buffer(bh); set_buffer_uptodate(bh); return bh->b_data; @@ -99,10 +126,10 @@ void *hpfs_map_4sectors(struct super_block *s, unsigned secno, struct quad_buffe hpfs_prefetch_sectors(s, secno, 4 + ahead); - if (!(qbh->bh[0] = sb_bread(s, secno + 0))) goto bail0; - if (!(qbh->bh[1] = sb_bread(s, secno + 1))) goto bail1; - if (!(qbh->bh[2] = sb_bread(s, secno + 2))) goto bail2; - if (!(qbh->bh[3] = sb_bread(s, secno + 3))) goto bail3; + if (!hpfs_map_sector(s, secno + 0, &qbh->bh[0], 0)) goto bail0; + if (!hpfs_map_sector(s, secno + 1, &qbh->bh[1], 0)) goto bail1; + if (!hpfs_map_sector(s, secno + 2, &qbh->bh[2], 0)) goto bail2; + if (!hpfs_map_sector(s, secno + 3, &qbh->bh[3], 0)) goto bail3; if (likely(qbh->bh[1]->b_data == qbh->bh[0]->b_data + 1 * 512) && likely(qbh->bh[2]->b_data == qbh->bh[0]->b_data + 2 * 512) && diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 7ca28d604bf7..d3bcdd975700 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -83,6 +83,11 @@ static int hpfs_get_block(struct inode *inode, sector_t iblock, struct buffer_he if (s) { if (bh_result->b_size >> 9 < n_secs) n_secs = bh_result->b_size >> 9; + n_secs = hpfs_search_hotfix_map_for_range(inode->i_sb, s, n_secs); + if (unlikely(!n_secs)) { + s = hpfs_search_hotfix_map(inode->i_sb, s); + n_secs = 1; + } map_bh(bh_result, inode->i_sb, s); bh_result->b_size = n_secs << 9; goto ret_0; @@ -101,7 +106,7 @@ static int hpfs_get_block(struct inode *inode, sector_t iblock, struct buffer_he inode->i_blocks++; hpfs_i(inode)->mmu_private += 512; set_buffer_new(bh_result); - map_bh(bh_result, inode->i_sb, s); + map_bh(bh_result, inode->i_sb, hpfs_search_hotfix_map(inode->i_sb, s)); ret_0: r = 0; ret_r: @@ -181,7 +186,7 @@ static int hpfs_write_end(struct file *file, struct address_space *mapping, static sector_t _hpfs_bmap(struct address_space *mapping, sector_t block) { - return generic_block_bmap(mapping,block,hpfs_get_block); + return generic_block_bmap(mapping, block, hpfs_get_block); } const struct address_space_operations hpfs_aops = { diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index c4867b5116dd..975654a63c13 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -88,6 +88,10 @@ struct hpfs_sb_info { unsigned sb_max_fwd_alloc; /* max forwad allocation */ int sb_timeshift; struct rcu_head rcu; + + unsigned n_hotfixes; + secno hotfix_from[256]; + secno hotfix_to[256]; }; /* Four 512-byte buffers and the 2k block obtained by concatenating them */ @@ -217,6 +221,8 @@ void hpfs_remove_fnode(struct super_block *, fnode_secno fno); /* buffer.c */ +secno hpfs_search_hotfix_map(struct super_block *s, secno sec); +unsigned hpfs_search_hotfix_map_for_range(struct super_block *s, secno sec, unsigned n); void hpfs_prefetch_sectors(struct super_block *, unsigned, int); void *hpfs_map_sector(struct super_block *, unsigned, struct buffer_head **, int); void *hpfs_get_sector(struct super_block *, unsigned, struct buffer_head **); @@ -285,6 +291,7 @@ __le32 *hpfs_map_bitmap(struct super_block *, unsigned, struct quad_buffer_head void hpfs_prefetch_bitmap(struct super_block *, unsigned); unsigned char *hpfs_load_code_page(struct super_block *, secno); __le32 *hpfs_load_bitmap_directory(struct super_block *, secno bmp); +void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock); struct fnode *hpfs_map_fnode(struct super_block *s, ino_t, struct buffer_head **); struct anode *hpfs_map_anode(struct super_block *s, anode_secno, struct buffer_head **); struct dnode *hpfs_map_dnode(struct super_block *s, dnode_secno, struct quad_buffer_head *); diff --git a/fs/hpfs/map.c b/fs/hpfs/map.c index 442770edcdc7..a69bbc1e87f8 100644 --- a/fs/hpfs/map.c +++ b/fs/hpfs/map.c @@ -130,6 +130,32 @@ __le32 *hpfs_load_bitmap_directory(struct super_block *s, secno bmp) return b; } +void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock) +{ + struct quad_buffer_head qbh; + u32 *directory; + u32 n_hotfixes, n_used_hotfixes; + unsigned i; + + n_hotfixes = le32_to_cpu(spareblock->n_spares); + n_used_hotfixes = le32_to_cpu(spareblock->n_spares_used); + + if (n_hotfixes > 256 || n_used_hotfixes > n_hotfixes) { + hpfs_error(s, "invalid number of hotfixes: %u, used: %u", n_hotfixes, n_used_hotfixes); + return; + } + if (!(directory = hpfs_map_4sectors(s, le32_to_cpu(spareblock->hotfix_map), &qbh, 0))) { + hpfs_error(s, "can't load hotfix map"); + return; + } + for (i = 0; i < n_used_hotfixes; i++) { + hpfs_sb(s)->hotfix_from[i] = le32_to_cpu(directory[i]); + hpfs_sb(s)->hotfix_to[i] = le32_to_cpu(directory[n_hotfixes + i]); + } + hpfs_sb(s)->n_hotfixes = n_used_hotfixes; + hpfs_brelse4(&qbh); +} + /* * Load fnode to memory */ diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index a0872f239f04..9e92c9c2d319 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -8,6 +8,17 @@ #include <linux/sched.h> #include "hpfs_fn.h" +static void hpfs_update_directory_times(struct inode *dir) +{ + time_t t = get_seconds(); + if (t == dir->i_mtime.tv_sec && + t == dir->i_ctime.tv_sec) + return; + dir->i_mtime.tv_sec = dir->i_ctime.tv_sec = t; + dir->i_mtime.tv_nsec = dir->i_ctime.tv_nsec = 0; + hpfs_write_inode_nolock(dir); +} + static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { const unsigned char *name = dentry->d_name.name; @@ -99,6 +110,7 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) result->i_mode = mode | S_IFDIR; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -187,6 +199,7 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, b result->i_mode = mode | S_IFREG; hpfs_write_inode_nolock(result); } + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -262,6 +275,7 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, de insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); brelse(bh); hpfs_unlock(dir->i_sb); @@ -340,6 +354,7 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy insert_inode_hash(result); hpfs_write_inode_nolock(result); + hpfs_update_directory_times(dir); d_instantiate(dentry, result); hpfs_unlock(dir->i_sb); return 0; @@ -423,6 +438,8 @@ again: out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -477,6 +494,8 @@ static int hpfs_rmdir(struct inode *dir, struct dentry *dentry) out1: hpfs_brelse4(&qbh); out: + if (!err) + hpfs_update_directory_times(dir); hpfs_unlock(dir->i_sb); return err; } @@ -595,7 +614,7 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, goto end1; } - end: +end: hpfs_i(i)->i_parent_dir = new_dir->i_ino; if (S_ISDIR(i->i_mode)) { inc_nlink(new_dir); @@ -610,6 +629,10 @@ static int hpfs_rename(struct inode *old_dir, struct dentry *old_dentry, brelse(bh); } end1: + if (!err) { + hpfs_update_directory_times(old_dir); + hpfs_update_directory_times(new_dir); + } hpfs_unlock(i->i_sb); return err; } diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 68a9bed05628..a561591896bd 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -628,6 +628,9 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) goto bail4; } + if (spareblock->n_spares_used) + hpfs_load_hotfix_map(s, spareblock); + /* Load bitmap directory */ if (!(sbi->sb_bmp_dir = hpfs_load_bitmap_directory(s, le32_to_cpu(superblock->bitmaps)))) goto bail4; @@ -647,18 +650,6 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) mark_buffer_dirty(bh2); } - if (spareblock->hotfixes_used || spareblock->n_spares_used) { - if (errs >= 2) { - pr_err("Hotfixes not supported here, try chkdsk\n"); - mark_dirty(s, 0); - goto bail4; - } - hpfs_error(s, "hotfixes not supported here, try chkdsk"); - if (errs == 0) - pr_err("Proceeding, but your filesystem will be probably corrupted by this driver...\n"); - else - pr_err("This driver may read bad files or crash when operating on disk with hotfixes.\n"); - } if (le32_to_cpu(spareblock->n_dnode_spares) != le32_to_cpu(spareblock->n_dnode_spares_free)) { if (errs >= 2) { pr_err("Spare dnodes used, try chkdsk\n"); diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 0cf74df68617..973c24ce59ad 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1010,6 +1010,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size, inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0); if (!inode) goto out_dentry; + if (creat_flags == HUGETLB_SHMFS_INODE) + inode->i_flags |= S_PRIVATE; file = ERR_PTR(-ENOMEM); if (hugetlb_reserve_pages(inode, 0, diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c index bc462dcd7a40..a69bdf2a1085 100644 --- a/fs/jfs/jfs_logmgr.c +++ b/fs/jfs/jfs_logmgr.c @@ -1999,19 +1999,16 @@ static int lbmRead(struct jfs_log * log, int pn, struct lbuf ** bpp) bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); bio->bi_bdev = log->bdev; - bio->bi_io_vec[0].bv_page = bp->l_page; - bio->bi_io_vec[0].bv_len = LOGPSIZE; - bio->bi_io_vec[0].bv_offset = bp->l_offset; - bio->bi_vcnt = 1; - bio->bi_iter.bi_size = LOGPSIZE; + bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; bio->bi_private = bp; /*check if journaling to disk has been disabled*/ if (log->no_integrity) { bio->bi_iter.bi_size = 0; - lbmIODone(bio, 0); + lbmIODone(bio); } else { submit_bio(READ_SYNC, bio); } @@ -2145,12 +2142,9 @@ static void lbmStartIO(struct lbuf * bp) bio = bio_alloc(GFP_NOFS, 1); bio->bi_iter.bi_sector = bp->l_blkno << (log->l2bsize - 9); bio->bi_bdev = log->bdev; - bio->bi_io_vec[0].bv_page = bp->l_page; - bio->bi_io_vec[0].bv_len = LOGPSIZE; - bio->bi_io_vec[0].bv_offset = bp->l_offset; - bio->bi_vcnt = 1; - bio->bi_iter.bi_size = LOGPSIZE; + bio_add_page(bio, bp->l_page, LOGPSIZE, bp->l_offset); + BUG_ON(bio->bi_iter.bi_size != LOGPSIZE); bio->bi_end_io = lbmIODone; bio->bi_private = bp; @@ -2158,7 +2152,7 @@ static void lbmStartIO(struct lbuf * bp) /* check if journaling to disk has been disabled */ if (log->no_integrity) { bio->bi_iter.bi_size = 0; - lbmIODone(bio, 0); + lbmIODone(bio); } else { submit_bio(WRITE_SYNC, bio); INCREMENT(lmStat.submitted); @@ -2196,7 +2190,7 @@ static int lbmIOWait(struct lbuf * bp, int flag) * * executed at INTIODONE level */ -static void lbmIODone(struct bio *bio, int error) +static void lbmIODone(struct bio *bio) { struct lbuf *bp = bio->bi_private; struct lbuf *nextbp, *tail; @@ -2212,7 +2206,7 @@ static void lbmIODone(struct bio *bio, int error) bp->l_flag |= lbmDONE; - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { + if (bio->bi_error) { bp->l_flag |= lbmERROR; jfs_err("lbmIODone: I/O error in JFS log"); diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 16a0922beb59..a3eb316b1ac3 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -276,11 +276,11 @@ static void last_read_complete(struct page *page) unlock_page(page); } -static void metapage_read_end_io(struct bio *bio, int err) +static void metapage_read_end_io(struct bio *bio) { struct page *page = bio->bi_private; - if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) { + if (bio->bi_error) { printk(KERN_ERR "metapage_read_end_io: I/O error\n"); SetPageError(page); } @@ -331,13 +331,13 @@ static void last_write_complete(struct page *page) end_page_writeback(page); } -static void metapage_write_end_io(struct bio *bio, int err) +static void metapage_write_end_io(struct bio *bio) { struct page *page = bio->bi_private; BUG_ON(!PagePrivate(page)); - if (! test_bit(BIO_UPTODATE, &bio->bi_flags)) { + if (bio->bi_error) { printk(KERN_ERR "metapage_write_end_io: I/O error\n"); SetPageError(page); } diff --git a/fs/libfs.c b/fs/libfs.c index 102edfd39000..c7cbfb092e94 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1185,7 +1185,7 @@ void make_empty_dir_inode(struct inode *inode) inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_rdev = 0; - inode->i_size = 2; + inode->i_size = 0; inode->i_blkbits = PAGE_SHIFT; inode->i_blocks = 0; diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index 76279e11982d..a7fdbd868474 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -53,16 +53,14 @@ static int bdev_readpage(void *_sb, struct page *page) static DECLARE_WAIT_QUEUE_HEAD(wq); -static void writeseg_end_io(struct bio *bio, int err) +static void writeseg_end_io(struct bio *bio) { - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec; int i; struct super_block *sb = bio->bi_private; struct logfs_super *super = logfs_super(sb); - BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */ - BUG_ON(err); + BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */ bio_for_each_segment_all(bvec, bio, i) { end_page_writeback(bvec->bv_page); @@ -83,7 +81,7 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index, unsigned int max_pages; int i; - max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + max_pages = min(nr_pages, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); @@ -153,14 +151,12 @@ static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len) } -static void erase_end_io(struct bio *bio, int err) +static void erase_end_io(struct bio *bio) { - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct super_block *sb = bio->bi_private; struct logfs_super *super = logfs_super(sb); - BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */ - BUG_ON(err); + BUG_ON(bio->bi_error); /* FIXME: Retry io or write elsewhere */ BUG_ON(bio->bi_vcnt == 0); bio_put(bio); if (atomic_dec_and_test(&super->s_pending_writes)) @@ -175,7 +171,7 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index, unsigned int max_pages; int i; - max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + max_pages = min(nr_pages, BIO_MAX_PAGES); bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); diff --git a/fs/mpage.c b/fs/mpage.c index ca0244b69de8..778a4ddef77a 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -42,14 +42,14 @@ * status of that page is hard. See end_buffer_async_read() for the details. * There is no point in duplicating all that complexity. */ -static void mpage_end_io(struct bio *bio, int err) +static void mpage_end_io(struct bio *bio) { struct bio_vec *bv; int i; bio_for_each_segment_all(bv, bio, i) { struct page *page = bv->bv_page; - page_endio(page, bio_data_dir(bio), err); + page_endio(page, bio_data_dir(bio), bio->bi_error); } bio_put(bio); @@ -277,7 +277,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - min_t(int, nr_pages, bio_get_nr_vecs(bdev)), + min_t(int, nr_pages, BIO_MAX_PAGES), GFP_KERNEL); if (bio == NULL) goto confused; @@ -602,7 +602,7 @@ alloc_new: } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - bio_get_nr_vecs(bdev), GFP_NOFS|__GFP_HIGH); + BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); if (bio == NULL) goto confused; diff --git a/fs/namei.c b/fs/namei.c index ae4e4c18b2ac..1c2105ed20c5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -879,7 +879,7 @@ static inline int may_follow_link(struct nameidata *nd) return 0; /* Allowed if parent directory not sticky and world-writable. */ - parent = nd->path.dentry->d_inode; + parent = nd->inode; if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH)) return 0; @@ -1954,8 +1954,13 @@ OK: continue; } } - if (unlikely(!d_can_lookup(nd->path.dentry))) + if (unlikely(!d_can_lookup(nd->path.dentry))) { + if (nd->flags & LOOKUP_RCU) { + if (unlazy_walk(nd, NULL, 0)) + return -ECHILD; + } return -ENOTDIR; + } } } diff --git a/fs/namespace.c b/fs/namespace.c index c7cb8a526c05..0570729c87fd 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1361,6 +1361,36 @@ enum umount_tree_flags { UMOUNT_PROPAGATE = 2, UMOUNT_CONNECTED = 4, }; + +static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how) +{ + /* Leaving mounts connected is only valid for lazy umounts */ + if (how & UMOUNT_SYNC) + return true; + + /* A mount without a parent has nothing to be connected to */ + if (!mnt_has_parent(mnt)) + return true; + + /* Because the reference counting rules change when mounts are + * unmounted and connected, umounted mounts may not be + * connected to mounted mounts. + */ + if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) + return true; + + /* Has it been requested that the mount remain connected? */ + if (how & UMOUNT_CONNECTED) + return false; + + /* Is the mount locked such that it needs to remain connected? */ + if (IS_MNT_LOCKED(mnt)) + return false; + + /* By default disconnect the mount */ + return true; +} + /* * mount_lock must be held * namespace_sem must be held for write @@ -1398,10 +1428,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) if (how & UMOUNT_SYNC) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; - disconnect = !(((how & UMOUNT_CONNECTED) && - mnt_has_parent(p) && - (p->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) || - IS_MNT_LOCKED_AND_LAZY(p)); + disconnect = disconnect_mount(p, how); pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, disconnect ? &unmounted : NULL); @@ -1538,11 +1565,8 @@ void __detach_mounts(struct dentry *dentry) while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { - struct mount *p, *tmp; - list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { - hlist_add_head(&p->mnt_umount.s_list, &unmounted); - umount_mnt(p); - } + hlist_add_head(&mnt->mnt_umount.s_list, &unmounted); + umount_mnt(mnt); } else umount_tree(mnt, UMOUNT_CONNECTED); } @@ -3194,6 +3218,8 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) down_read(&namespace_sem); list_for_each_entry(mnt, &ns->list, mnt_list) { struct mount *child; + int mnt_flags; + if (mnt->mnt.mnt_sb->s_type != type) continue; @@ -3203,17 +3229,30 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root) continue; + /* Read the mount flags and filter out flags that + * may safely be ignored. + */ + mnt_flags = mnt->mnt.mnt_flags; + if (mnt->mnt.mnt_sb->s_iflags & SB_I_NOEXEC) + mnt_flags &= ~(MNT_LOCK_NOSUID | MNT_LOCK_NOEXEC); + /* Verify the mount flags are equal to or more permissive * than the proposed new mount. */ - if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) && + if ((mnt_flags & MNT_LOCK_READONLY) && !(new_flags & MNT_READONLY)) continue; - if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) && + if ((mnt_flags & MNT_LOCK_NODEV) && !(new_flags & MNT_NODEV)) continue; - if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) && - ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) + if ((mnt_flags & MNT_LOCK_NOSUID) && + !(new_flags & MNT_NOSUID)) + continue; + if ((mnt_flags & MNT_LOCK_NOEXEC) && + !(new_flags & MNT_NOEXEC)) + continue; + if ((mnt_flags & MNT_LOCK_ATIME) && + ((mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK))) continue; /* This mount is not fully visible if there are any @@ -3223,16 +3262,18 @@ static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags) list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) { struct inode *inode = child->mnt_mountpoint->d_inode; /* Only worry about locked mounts */ - if (!(mnt->mnt.mnt_flags & MNT_LOCKED)) + if (!(mnt_flags & MNT_LOCKED)) continue; /* Is the directory permanetly empty? */ if (!is_empty_dir_inode(inode)) goto next; } /* Preserve the locked attributes */ - *new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \ - MNT_LOCK_NODEV | \ - MNT_LOCK_ATIME); + *new_mnt_flags |= mnt_flags & (MNT_LOCK_READONLY | \ + MNT_LOCK_NODEV | \ + MNT_LOCK_NOSUID | \ + MNT_LOCK_NOEXEC | \ + MNT_LOCK_ATIME); visible = true; goto found; next: ; diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index d2554fe140a3..9cd4eb3a1e22 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -116,7 +116,7 @@ bl_submit_bio(int rw, struct bio *bio) static struct bio * bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, - void (*end_io)(struct bio *, int err), struct parallel_io *par) + bio_end_io_t end_io, struct parallel_io *par) { struct bio *bio; @@ -139,8 +139,7 @@ bl_alloc_init_bio(int npg, struct block_device *bdev, sector_t disk_sector, static struct bio * do_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, struct page *page, struct pnfs_block_dev_map *map, - struct pnfs_block_extent *be, - void (*end_io)(struct bio *, int err), + struct pnfs_block_extent *be, bio_end_io_t end_io, struct parallel_io *par, unsigned int offset, int *len) { struct pnfs_block_dev *dev = @@ -183,11 +182,11 @@ retry: return bio; } -static void bl_end_io_read(struct bio *bio, int err) +static void bl_end_io_read(struct bio *bio) { struct parallel_io *par = bio->bi_private; - if (err) { + if (bio->bi_error) { struct nfs_pgio_header *header = par->data; if (!header->pnfs_error) @@ -316,13 +315,12 @@ out: return PNFS_ATTEMPTED; } -static void bl_end_io_write(struct bio *bio, int err) +static void bl_end_io_write(struct bio *bio) { struct parallel_io *par = bio->bi_private; - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct nfs_pgio_header *header = par->data; - if (!uptodate) { + if (bio->bi_error) { if (!header->pnfs_error) header->pnfs_error = -EIO; pnfs_set_lo_fail(header->lseg); diff --git a/fs/nfs/client.c b/fs/nfs/client.c index ecebb406cc1a..4a90c9bb3135 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -775,7 +775,7 @@ static int nfs_init_server(struct nfs_server *server, server->options = data->options; server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID| NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP| - NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR; + NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME; if (data->rsize) server->rsize = nfs_block_size(data->rsize, NULL); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index c12951b9551e..b3289d701eea 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -1852,7 +1852,7 @@ ff_layout_mirror_prepare_stats(struct nfs42_layoutstat_args *args, struct nfs42_layoutstat_devinfo *devinfo; int i; - for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) { + for (i = 0; i < FF_LAYOUT_MIRROR_COUNT(pls); i++) { if (*dev_count >= dev_limit) break; mirror = FF_LAYOUT_COMP(pls, i); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index b77b328a06d7..0adc7d245b3d 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -442,8 +442,9 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) inode->i_version = fattr->change_attr; - else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR)) - nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR); + else + nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR + | NFS_INO_REVAL_PAGECACHE); if (fattr->valid & NFS_ATTR_FATTR_SIZE) inode->i_size = nfs_size_to_loff_t(fattr->size); else @@ -1244,9 +1245,11 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (fattr->valid & NFS_ATTR_FATTR_SIZE) { cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); - if (cur_size != new_isize && nfsi->nrequests == 0) + if (cur_size != new_isize) invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; } + if (nfsi->nrequests != 0) + invalid &= ~NFS_INO_REVAL_PAGECACHE; /* Have any file permissions changed? */ if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) @@ -1684,13 +1687,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) invalid |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA | NFS_INO_INVALID_ACCESS - | NFS_INO_INVALID_ACL - | NFS_INO_REVAL_PAGECACHE; + | NFS_INO_INVALID_ACL; if (S_ISDIR(inode->i_mode)) nfs_force_lookup_revalidate(inode); inode->i_version = fattr->change_attr; } - } else if (server->caps & NFS_CAP_CHANGE_ATTR) + } else nfsi->cache_validity |= save_cache_validity; if (fattr->valid & NFS_ATTR_FATTR_MTIME) { @@ -1717,7 +1719,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if ((nfsi->nrequests == 0) || new_isize > cur_isize) { i_size_write(inode, new_isize); invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA; - invalid &= ~NFS_INO_REVAL_PAGECACHE; } dprintk("NFS: isize change on server for file %s/%ld " "(%Ld to %Ld)\n", diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7e3c4604bea8..9b372b845f6a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -296,6 +296,22 @@ extern struct rpc_procinfo nfs4_procedures[]; #ifdef CONFIG_NFS_V4_SECURITY_LABEL extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); +static inline struct nfs4_label * +nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) +{ + if (!dst || !src) + return NULL; + + if (src->len > NFS4_MAXLABELLEN) + return NULL; + + dst->lfs = src->lfs; + dst->pi = src->pi; + dst->len = src->len; + memcpy(dst->label, src->label, src->len); + + return dst; +} static inline void nfs4_label_free(struct nfs4_label *label) { if (label) { @@ -316,6 +332,11 @@ static inline void nfs4_label_free(void *label) {} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } +static inline struct nfs4_label * +nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) +{ + return NULL; +} #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ /* proc.c */ diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index f486b80f927a..d731bbf974aa 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -135,7 +135,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -171,6 +171,23 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes); } +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 = { }; + int err; + + do { + err = _nfs42_proc_llseek(filep, offset, whence); + if (err == -ENOTSUPP) + return -EOPNOTSUPP; + err = nfs4_handle_exception(server, err, &exception); + } while (exception.retry); + + return err; +} + + static void nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 8bee93469617..3acb1eb72930 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -467,7 +467,10 @@ static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp) static void renew_lease(const struct nfs_server *server, unsigned long timestamp) { - do_renew_lease(server->nfs_client, timestamp); + struct nfs_client *clp = server->nfs_client; + + if (!nfs4_has_session(clp)) + do_renew_lease(clp, timestamp); } struct nfs4_call_sync_data { @@ -616,8 +619,7 @@ int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) clp = session->clp; do_renew_lease(clp, res->sr_timestamp); /* Check sequence flags */ - if (res->sr_status_flags != 0) - nfs4_schedule_lease_recovery(clp); + nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); nfs41_update_target_slotid(slot->table, slot, res); break; case 1: @@ -910,6 +912,7 @@ struct nfs4_opendata { struct nfs_open_confirmres c_res; struct nfs4_string owner_name; struct nfs4_string group_name; + struct nfs4_label *a_label; struct nfs_fattr f_attr; struct nfs4_label *f_label; struct dentry *dir; @@ -1013,6 +1016,10 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, if (IS_ERR(p->f_label)) goto err_free_p; + p->a_label = nfs4_label_alloc(server, gfp_mask); + if (IS_ERR(p->a_label)) + goto err_free_f; + alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid; p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask); if (IS_ERR(p->o_arg.seqid)) @@ -1041,7 +1048,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, p->o_arg.server = server; p->o_arg.bitmask = nfs4_bitmask(server, label); p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0]; - p->o_arg.label = label; + p->o_arg.label = nfs4_label_copy(p->a_label, label); p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim); switch (p->o_arg.claim) { case NFS4_OPEN_CLAIM_NULL: @@ -1074,6 +1081,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, return p; err_free_label: + nfs4_label_free(p->a_label); +err_free_f: nfs4_label_free(p->f_label); err_free_p: kfree(p); @@ -1093,6 +1102,7 @@ static void nfs4_opendata_free(struct kref *kref) nfs4_put_open_state(p->state); nfs4_put_state_owner(p->owner); + nfs4_label_free(p->a_label); nfs4_label_free(p->f_label); dput(p->dir); @@ -1198,12 +1208,15 @@ static bool nfs_need_update_open_stateid(struct nfs4_state *state, static void nfs_resync_open_stateid_locked(struct nfs4_state *state) { + if (!(state->n_wronly || state->n_rdonly || state->n_rdwr)) + return; if (state->n_wronly) set_bit(NFS_O_WRONLY_STATE, &state->flags); if (state->n_rdonly) set_bit(NFS_O_RDONLY_STATE, &state->flags); if (state->n_rdwr) set_bit(NFS_O_RDWR_STATE, &state->flags); + set_bit(NFS_OPEN_STATE, &state->flags); } static void nfs_clear_open_stateid_locked(struct nfs4_state *state, @@ -7571,13 +7584,8 @@ static int nfs4_proc_sequence(struct nfs_client *clp, struct rpc_cred *cred) goto out; } ret = rpc_wait_for_completion_task(task); - if (!ret) { - struct nfs4_sequence_res *res = task->tk_msg.rpc_resp; - - if (task->tk_status == 0) - nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags); + if (!ret) ret = task->tk_status; - } rpc_put_task(task); out: dprintk("<-- %s status=%d\n", __func__, ret); @@ -7965,16 +7973,17 @@ static void nfs4_layoutreturn_release(void *calldata) { struct nfs4_layoutreturn *lrp = calldata; struct pnfs_layout_hdr *lo = lrp->args.layout; + LIST_HEAD(freeme); dprintk("--> %s\n", __func__); spin_lock(&lo->plh_inode->i_lock); if (lrp->res.lrs_present) pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); + pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range); pnfs_clear_layoutreturn_waitbit(lo); - clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags); - rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); + pnfs_free_lseg_list(&freeme); pnfs_put_layout_hdr(lrp->args.layout); nfs_iput_and_deactive(lrp->inode); kfree(calldata); @@ -8588,7 +8597,6 @@ static const struct nfs4_minor_version_ops nfs_v4_0_minor_ops = { .minor_version = 0, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK, .init_client = nfs40_init_client, .shutdown_client = nfs40_shutdown_client, @@ -8614,7 +8622,6 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { .minor_version = 1, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1, @@ -8637,7 +8644,6 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { .minor_version = 2, .init_caps = NFS_CAP_READDIRPLUS | NFS_CAP_ATOMIC_OPEN - | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 | NFS_CAP_ATOMIC_OPEN_V1 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 605840dc89cf..f2e2ad894461 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2191,25 +2191,35 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp) } } -static void nfs41_handle_state_revoked(struct nfs_client *clp) +static void nfs41_handle_all_state_revoked(struct nfs_client *clp) { nfs4_reset_all_state(clp); dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); } +static void nfs41_handle_some_state_revoked(struct nfs_client *clp) +{ + nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce); + nfs4_schedule_state_manager(clp); + + dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname); +} + static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp) { - /* This will need to handle layouts too */ - nfs_expire_all_delegations(clp); + /* FIXME: For now, we destroy all layouts. */ + pnfs_destroy_all_layouts(clp); + /* FIXME: For now, we test all delegations+open state+locks. */ + nfs41_handle_some_state_revoked(clp); dprintk("%s: Recallable state revoked on server %s!\n", __func__, clp->cl_hostname); } static void nfs41_handle_backchannel_fault(struct nfs_client *clp) { - nfs_expire_all_delegations(clp); - if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0) - nfs4_schedule_state_manager(clp); + set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); + nfs4_schedule_state_manager(clp); + dprintk("%s: server %s declared a backchannel fault\n", __func__, clp->cl_hostname); } @@ -2231,10 +2241,11 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) nfs41_handle_server_reboot(clp); - if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | - SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | + if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED)) + nfs41_handle_all_state_revoked(clp); + if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | SEQ4_STATUS_ADMIN_STATE_REVOKED)) - nfs41_handle_state_revoked(clp); + nfs41_handle_some_state_revoked(clp); if (flags & SEQ4_STATUS_LEASE_MOVED) nfs4_schedule_lease_moved_recovery(clp); if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1da68d3b1eda..4984bbe55ff1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -1100,8 +1100,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) mirror->pg_base = 0; mirror->pg_recoalesce = 0; - desc->pg_moreio = 0; - while (!list_empty(&head)) { struct nfs_page *req; @@ -1109,8 +1107,11 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) nfs_list_remove_request(req); if (__nfs_pageio_add_request(desc, req)) continue; - if (desc->pg_error < 0) + if (desc->pg_error < 0) { + list_splice_tail(&head, &mirror->pg_list); + mirror->pg_recoalesce = 1; return 0; + } break; } } while (mirror->pg_recoalesce); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 0ba9a02c9566..70bf706b1090 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -352,7 +352,7 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, { struct pnfs_layout_segment *s; - if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) + if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)) return false; list_for_each_entry(s, &lo->plh_segs, pls_list) @@ -362,6 +362,18 @@ pnfs_layout_need_return(struct pnfs_layout_hdr *lo, 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; + lo->plh_block_lgets++; + 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) { @@ -372,17 +384,16 @@ static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg, if (pnfs_layout_need_return(lo, lseg)) { nfs4_stateid stateid; enum pnfs_iomode iomode; + bool send; stateid = lo->plh_stateid; iomode = lo->plh_return_iomode; - /* decreased in pnfs_send_layoutreturn() */ - lo->plh_block_lgets++; - lo->plh_return_iomode = 0; + send = pnfs_prepare_layoutreturn(lo); spin_unlock(&inode->i_lock); - pnfs_get_layout_hdr(lo); - - /* Send an async layoutreturn so we dont deadlock */ - pnfs_send_layoutreturn(lo, stateid, iomode, false); + if (send) { + /* Send an async layoutreturn so we dont deadlock */ + pnfs_send_layoutreturn(lo, stateid, iomode, false); + } } else spin_unlock(&inode->i_lock); } @@ -411,6 +422,10 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg) 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)) { + spin_unlock(&inode->i_lock); + return; + } pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); spin_unlock(&inode->i_lock); @@ -451,6 +466,8 @@ pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg) test_bit(NFS_LSEG_VALID, &lseg->pls_flags)); if (atomic_dec_and_test(&lseg->pls_refcount)) { struct pnfs_layout_hdr *lo = lseg->pls_layout; + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) + return; pnfs_get_layout_hdr(lo); pnfs_layout_remove_lseg(lo, lseg); pnfs_free_lseg_async(lseg); @@ -924,6 +941,7 @@ void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo) clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags); smp_mb__after_atomic(); wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN); + rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq); } static int @@ -978,6 +996,7 @@ _pnfs_return_layout(struct inode *ino) LIST_HEAD(tmp_list); nfs4_stateid stateid; int status = 0, empty; + bool send; dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino); @@ -1007,17 +1026,18 @@ _pnfs_return_layout(struct inode *ino) /* Don't send a LAYOUTRETURN if list was initially empty */ if (empty) { spin_unlock(&ino->i_lock); - pnfs_put_layout_hdr(lo); dprintk("NFS: %s no layout segments to return\n", __func__); - goto out; + goto out_put_layout_hdr; } set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); - lo->plh_block_lgets++; + send = pnfs_prepare_layoutreturn(lo); spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); - - status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); + if (send) + status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true); +out_put_layout_hdr: + pnfs_put_layout_hdr(lo); out: dprintk("<-- %s status: %d\n", __func__, status); return status; @@ -1097,13 +1117,9 @@ bool pnfs_roc(struct inode *ino) out_noroc: if (lo) { stateid = lo->plh_stateid; - layoutreturn = - test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, - &lo->plh_flags); - if (layoutreturn) { - lo->plh_block_lgets++; - pnfs_get_layout_hdr(lo); - } + if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags)) + layoutreturn = pnfs_prepare_layoutreturn(lo); } spin_unlock(&ino->i_lock); if (layoutreturn) { @@ -1146,15 +1162,18 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) struct pnfs_layout_segment *lseg; nfs4_stateid stateid; u32 current_seqid; - bool found = false, layoutreturn = false; + bool layoutreturn = false; spin_lock(&ino->i_lock); - list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) - if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) { - rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); - found = true; - goto out; - } + list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) { + if (!test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) + continue; + if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) + continue; + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + spin_unlock(&ino->i_lock); + return true; + } lo = nfsi->layout; current_seqid = be32_to_cpu(lo->plh_stateid.seqid); @@ -1162,23 +1181,19 @@ bool pnfs_roc_drain(struct inode *ino, u32 *barrier, struct rpc_task *task) * a barrier, we choose the worst-case barrier. */ *barrier = current_seqid + atomic_read(&lo->plh_outstanding); -out: - if (!found) { - stateid = lo->plh_stateid; - layoutreturn = - test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, - &lo->plh_flags); - if (layoutreturn) { - lo->plh_block_lgets++; - pnfs_get_layout_hdr(lo); - } - } + stateid = lo->plh_stateid; + if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, + &lo->plh_flags)) + layoutreturn = pnfs_prepare_layoutreturn(lo); + if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) + rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); + spin_unlock(&ino->i_lock); if (layoutreturn) { - rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL); pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false); + return true; } - return found; + return false; } /* @@ -1695,7 +1710,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode, spin_lock(&inode->i_lock); /* set failure bit so that pnfs path will be retried later */ pnfs_layout_set_fail_bit(lo, iomode); - set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags); if (lo->plh_return_iomode == 0) lo->plh_return_iomode = range.iomode; else if (lo->plh_return_iomode != range.iomode) @@ -2207,13 +2221,12 @@ pnfs_layoutcommit_inode(struct inode *inode, bool sync) if (ld->prepare_layoutcommit) { status = ld->prepare_layoutcommit(&data->args); if (status) { + put_rpccred(data->cred); spin_lock(&inode->i_lock); set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags); if (end_pos > nfsi->layout->plh_lwb) nfsi->layout->plh_lwb = end_pos; - spin_unlock(&inode->i_lock); - put_rpccred(data->cred); - goto clear_layoutcommitting; + goto out_unlock; } } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 65869ca9c851..75a35a1afa79 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1379,24 +1379,27 @@ static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, { struct nfs_pgio_args *argp = &hdr->args; struct nfs_pgio_res *resp = &hdr->res; + u64 size = argp->offset + resp->count; if (!(fattr->valid & NFS_ATTR_FATTR_SIZE)) + fattr->size = size; + if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) { + fattr->valid &= ~NFS_ATTR_FATTR_SIZE; return; - if (argp->offset + resp->count != fattr->size) - return; - if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) + } + if (size != fattr->size) return; /* Set attribute barrier */ nfs_fattr_set_barrier(fattr); + /* ...and update size */ + fattr->valid |= NFS_ATTR_FATTR_SIZE; } void nfs_writeback_update_inode(struct nfs_pgio_header *hdr) { - struct nfs_fattr *fattr = hdr->res.fattr; + struct nfs_fattr *fattr = &hdr->fattr; struct inode *inode = hdr->inode; - if (fattr == NULL) - return; spin_lock(&inode->i_lock); nfs_writeback_check_extend(hdr, fattr); nfs_post_op_update_inode_force_wcc_locked(inode, fattr); diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 6904213a4363..ebf90e487c75 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -212,6 +212,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, BUG_ON(!ls->ls_file); if (nfsd4_layout_setlease(ls)) { + fput(ls->ls_file); put_nfs4_file(fp); kmem_cache_free(nfs4_layout_stateid_cache, ls); return NULL; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 61dfb33f0559..95202719a1fd 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4396,9 +4396,9 @@ laundromat_main(struct work_struct *laundry) queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } -static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp) +static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { - if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle)) + if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } @@ -4601,9 +4601,6 @@ nfs4_check_olstateid(struct svc_fh *fhp, struct nfs4_ol_stateid *ols, int flags) { __be32 status; - status = nfs4_check_fh(fhp, ols); - if (status) - return status; status = nfsd4_check_openowner_confirmed(ols); if (status) return status; @@ -4690,6 +4687,9 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, status = nfserr_bad_stateid; break; } + if (status) + goto out; + status = nfs4_check_fh(fhp, s); done: if (!status && filpp) @@ -4798,7 +4798,7 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status) return status; - return nfs4_check_fh(current_fh, stp); + return nfs4_check_fh(current_fh, &stp->st_stid); } /* diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 54633858733a..75e0563c09d1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2143,6 +2143,7 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp, #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \ FATTR4_WORD0_RDATTR_ERROR) #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID +#define WORD2_ABSENT_FS_ATTRS 0 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL static inline __be32 @@ -2171,7 +2172,7 @@ nfsd4_encode_security_label(struct xdr_stream *xdr, struct svc_rqst *rqstp, { return 0; } #endif -static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) +static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err) { /* As per referral draft: */ if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS || @@ -2184,6 +2185,7 @@ static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err) } *bmval0 &= WORD0_ABSENT_FS_ATTRS; *bmval1 &= WORD1_ABSENT_FS_ATTRS; + *bmval2 &= WORD2_ABSENT_FS_ATTRS; return 0; } @@ -2246,8 +2248,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion)); if (exp->ex_fslocs.migrated) { - BUG_ON(bmval[2]); - status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err); + status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err); if (status) goto out; } @@ -2286,8 +2287,8 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, } #ifdef CONFIG_NFSD_V4_SECURITY_LABEL - if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) || - bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) { + if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) || + bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) { err = security_inode_getsecctx(d_inode(dentry), &context, &contextlen); contextsupport = (err == 0); diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 42468e5ab3e7..f63620ce3892 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -338,12 +338,11 @@ void nilfs_add_checksums_on_logs(struct list_head *logs, u32 seed) /* * BIO operations */ -static void nilfs_end_bio_write(struct bio *bio, int err) +static void nilfs_end_bio_write(struct bio *bio) { - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct nilfs_segment_buffer *segbuf = bio->bi_private; - if (!uptodate) + if (bio->bi_error) atomic_inc(&segbuf->sb_err); bio_put(bio); @@ -415,7 +414,7 @@ static void nilfs_segbuf_prepare_write(struct nilfs_segment_buffer *segbuf, { wi->bio = NULL; wi->rest_blocks = segbuf->sb_sum.nblocks; - wi->max_pages = bio_get_nr_vecs(wi->nilfs->ns_bdev); + wi->max_pages = BIO_MAX_PAGES; wi->nr_vecs = min(wi->max_pages, wi->rest_blocks); wi->start = wi->end = 0; wi->blocknr = segbuf->sb_pseg_start; diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 92e48c70f0f0..39ddcaf0918f 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -412,16 +412,36 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group, unsigned int flags) { struct fsnotify_mark *lmark, *mark; + LIST_HEAD(to_free); + /* + * We have to be really careful here. Anytime we drop mark_mutex, e.g. + * fsnotify_clear_marks_by_inode() can come and free marks. Even in our + * to_free list so we have to use mark_mutex even when accessing that + * list. And freeing mark requires us to drop mark_mutex. So we can + * reliably free only the first mark in the list. That's why we first + * move marks to free to to_free list in one go and then free marks in + * to_free list one by one. + */ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if (mark->flags & flags) { - fsnotify_get_mark(mark); - fsnotify_destroy_mark_locked(mark, group); - fsnotify_put_mark(mark); - } + if (mark->flags & flags) + list_move(&mark->g_list, &to_free); } mutex_unlock(&group->mark_mutex); + + while (1) { + mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); + if (list_empty(&to_free)) { + mutex_unlock(&group->mark_mutex); + break; + } + mark = list_first_entry(&to_free, struct fsnotify_mark, g_list); + fsnotify_get_mark(mark); + fsnotify_destroy_mark_locked(mark, group); + mutex_unlock(&group->mark_mutex); + fsnotify_put_mark(mark); + } } /* diff --git a/fs/nsfs.c b/fs/nsfs.c index 99521e7c492b..e4905fbf3396 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -4,6 +4,7 @@ #include <linux/proc_ns.h> #include <linux/magic.h> #include <linux/ktime.h> +#include <linux/seq_file.h> static struct vfsmount *nsfs_mnt; @@ -136,9 +137,18 @@ out_invalid: return ERR_PTR(-EINVAL); } +static int nsfs_show_path(struct seq_file *seq, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + const struct proc_ns_operations *ns_ops = dentry->d_fsdata; + + return seq_printf(seq, "%s:[%lu]", ns_ops->name, inode->i_ino); +} + static const struct super_operations nsfs_ops = { .statfs = simple_statfs, .evict_inode = nsfs_evict, + .show_path = nsfs_show_path, }; static struct dentry *nsfs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 9e1e112074fb..c1128bcbeb5e 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -543,7 +543,7 @@ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) return -EROFS; } if (!ntfs_stamp_usnjrnl(vol)) { - ntfs_error(sb, "Failed to stamp transation log " + ntfs_error(sb, "Failed to stamp transaction log " "($UsnJrnl)%s", es); NVolSetErrors(vol); return -EROFS; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 1a35c6139656..0f5fd9db8194 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -685,7 +685,7 @@ static int ocfs2_direct_IO_zero_extend(struct ocfs2_super *osb, if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) { u64 s = i_size_read(inode); - sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) + + sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) + (do_div(s, osb->s_clustersize) >> 9); ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector, @@ -910,7 +910,7 @@ static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb, BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN)); ret = blkdev_issue_zeroout(osb->sb->s_bdev, - p_cpos << (osb->s_clustersize_bits - 9), + (u64)p_cpos << (osb->s_clustersize_bits - 9), zero_len_head >> 9, GFP_NOFS, false); if (ret < 0) mlog_errno(ret); diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 16eff45727ee..140de3c93d2e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -372,14 +372,13 @@ static void o2hb_wait_on_io(struct o2hb_region *reg, wait_for_completion(&wc->wc_io_complete); } -static void o2hb_bio_end_io(struct bio *bio, - int error) +static void o2hb_bio_end_io(struct bio *bio) { struct o2hb_bio_wait_ctxt *wc = bio->bi_private; - if (error) { - mlog(ML_ERROR, "IO Error %d\n", error); - wc->wc_error = error; + if (bio->bi_error) { + mlog(ML_ERROR, "IO Error %d\n", bio->bi_error); + wc->wc_error = bio->bi_error; } o2hb_bio_wait_dec(wc, 1); diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 8b23aa2f52dd..23157e40dd74 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -4025,9 +4025,13 @@ static void ocfs2_downconvert_thread_do_work(struct ocfs2_super *osb) osb->dc_work_sequence = osb->dc_wake_sequence; processed = osb->blocked_lock_count; - while (processed) { - BUG_ON(list_empty(&osb->blocked_lock_list)); - + /* + * blocked lock processing in this loop might call iput which can + * remove items off osb->blocked_lock_list. Downconvert up to + * 'processed' number of locks, but stop short if we had some + * removed in ocfs2_mark_lockres_freeing when downconverting. + */ + while (processed && !list_empty(&osb->blocked_lock_list)) { lockres = list_entry(osb->blocked_lock_list.next, struct ocfs2_lock_res, l_blocked_list); list_del_init(&lockres->l_blocked_list); diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index db64ce2d4667..540ab5b75dbb 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -168,7 +168,7 @@ /* Refcount tree support */ #define OCFS2_FEATURE_INCOMPAT_REFCOUNT_TREE 0x1000 -/* Discontigous block groups */ +/* Discontiguous block groups */ #define OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG 0x2000 /* @@ -939,7 +939,7 @@ struct ocfs2_group_desc /* * Block groups may be discontiguous when * OCFS2_FEATURE_INCOMPAT_DISCONTIG_BG is set. - * The extents of a discontigous block group are + * The extents of a discontiguous block group are * stored in bg_list. It is a flat list. * l_tree_depth must always be zero. A * discontiguous group is signified by a non-zero diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c index 2768eb1da2b8..ced70c8139f7 100644 --- a/fs/ocfs2/stack_user.c +++ b/fs/ocfs2/stack_user.c @@ -655,14 +655,7 @@ static int ocfs2_control_init(void) static void ocfs2_control_exit(void) { - int rc; - - rc = misc_deregister(&ocfs2_control_device); - if (rc) - printk(KERN_ERR - "ocfs2: Unable to deregister ocfs2_control device " - "(errno %d)\n", - -rc); + misc_deregister(&ocfs2_control_device); } static void fsdlm_lock_ast_wrapper(void *astarg) diff --git a/fs/open.c b/fs/open.c index e33dab287fa0..b6f1e96a7c0b 100644 --- a/fs/open.c +++ b/fs/open.c @@ -377,7 +377,7 @@ retry: * with the "noexec" flag. */ res = -EACCES; - if (path.mnt->mnt_flags & MNT_NOEXEC) + if (path_noexec(&path)) goto out_path_release; } diff --git a/fs/pnode.h b/fs/pnode.h index 7114ce6e6b9e..0fcdbe7ca648 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -20,8 +20,6 @@ #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED) #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED) #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED) -#define IS_MNT_LOCKED_AND_LAZY(m) \ - (((m)->mnt.mnt_flags & (MNT_LOCKED|MNT_SYNC_UMOUNT)) == MNT_LOCKED) #define CL_EXPIRE 0x01 #define CL_SLAVE 0x02 diff --git a/fs/proc/root.c b/fs/proc/root.c index 68feb0f70e63..361ab4ee42fc 100644 --- a/fs/proc/root.c +++ b/fs/proc/root.c @@ -134,6 +134,8 @@ static struct dentry *proc_mount(struct file_system_type *fs_type, } sb->s_flags |= MS_ACTIVE; + /* User space would break if executables appear on proc */ + sb->s_iflags |= SB_I_NOEXEC; } return dget(sb->s_root); diff --git a/fs/signalfd.c b/fs/signalfd.c index 7e412ad74836..270221fcef42 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -121,8 +121,9 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, * Other callers might not initialize the si_lsb field, * so check explicitly for the right codes here. */ - if (kinfo->si_code == BUS_MCEERR_AR || - kinfo->si_code == BUS_MCEERR_AO) + if (kinfo->si_signo == SIGBUS && + (kinfo->si_code == BUS_MCEERR_AR || + kinfo->si_code == BUS_MCEERR_AO)) err |= __put_user((short) kinfo->si_addr_lsb, &uinfo->ssi_addr_lsb); #endif diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 1c6ac6fcee9f..f3db82071cfb 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -40,6 +40,10 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type, SYSFS_MAGIC, &new_sb, ns); if (IS_ERR(root) || !new_sb) kobj_ns_drop(KOBJ_NS_TYPE_NET, ns); + else if (new_sb) + /* Userspace would break if executables appear on sysfs */ + root->d_sb->s_iflags |= SB_I_NOEXEC; + return root; } diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c index 20de88d1bf86..dd714037c322 100644 --- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -159,11 +159,10 @@ xfs_attr3_rmt_write_verify( struct xfs_buf *bp) { struct xfs_mount *mp = bp->b_target->bt_mount; - struct xfs_buf_log_item *bip = bp->b_fspriv; + int blksize = mp->m_attr_geo->blksize; char *ptr; int len; xfs_daddr_t bno; - int blksize = mp->m_attr_geo->blksize; /* no verification of non-crc buffers */ if (!xfs_sb_version_hascrc(&mp->m_sb)) @@ -175,16 +174,22 @@ xfs_attr3_rmt_write_verify( ASSERT(len >= blksize); while (len > 0) { + struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr; + if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) { xfs_buf_ioerror(bp, -EFSCORRUPTED); xfs_verifier_error(bp); return; } - if (bip) { - struct xfs_attr3_rmt_hdr *rmt; - rmt = (struct xfs_attr3_rmt_hdr *)ptr; - rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn); + /* + * Ensure we aren't writing bogus LSNs to disk. See + * xfs_attr3_rmt_hdr_set() for the explanation. + */ + if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) { + xfs_buf_ioerror(bp, -EFSCORRUPTED); + xfs_verifier_error(bp); + return; } xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF); @@ -221,6 +226,18 @@ xfs_attr3_rmt_hdr_set( rmt->rm_owner = cpu_to_be64(ino); rmt->rm_blkno = cpu_to_be64(bno); + /* + * Remote attribute blocks are written synchronously, so we don't + * have an LSN that we can stamp in them that makes any sense to log + * recovery. To ensure that log recovery handles overwrites of these + * blocks sanely (i.e. once they've been freed and reallocated as some + * other type of metadata) we need to ensure that the LSN has a value + * that tells log recovery to ignore the LSN and overwrite the buffer + * with whatever is in it's log. To do this, we use the magic + * NULLCOMMITLSN to indicate that the LSN is invalid. + */ + rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN); + return sizeof(struct xfs_attr3_rmt_hdr); } @@ -434,14 +451,21 @@ xfs_attr_rmtval_set( /* * Allocate a single extent, up to the size of the value. + * + * Note that we have to consider this a data allocation as we + * write the remote attribute without logging the contents. + * Hence we must ensure that we aren't using blocks that are on + * the busy list so that we don't overwrite blocks which have + * recently been freed but their transactions are not yet + * committed to disk. If we overwrite the contents of a busy + * extent and then crash then the block may not contain the + * correct metadata after log recovery occurs. */ xfs_bmap_init(args->flist, args->firstblock); nmap = 1; error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno, - blkcnt, - XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA, - args->firstblock, args->total, &map, &nmap, - args->flist); + blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock, + args->total, &map, &nmap, args->flist); if (!error) { error = xfs_bmap_finish(&args->trans, args->flist, &committed); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 3859f5e27a4d..c77499bcbd7a 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -351,12 +351,11 @@ xfs_imap_valid( */ STATIC void xfs_end_bio( - struct bio *bio, - int error) + struct bio *bio) { xfs_ioend_t *ioend = bio->bi_private; - ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error; + ioend->io_error = bio->bi_error; /* Toss bio and pass work off to an xfsdatad thread */ bio->bi_private = NULL; @@ -382,8 +381,7 @@ STATIC struct bio * xfs_alloc_ioend_bio( struct buffer_head *bh) { - int nvecs = bio_get_nr_vecs(bh->b_bdev); - struct bio *bio = bio_alloc(GFP_NOIO, nvecs); + struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); ASSERT(bio->bi_private == NULL); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index a4b7d92e946c..01bd6781974e 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1096,8 +1096,7 @@ xfs_bwrite( STATIC void xfs_buf_bio_end_io( - struct bio *bio, - int error) + struct bio *bio) { xfs_buf_t *bp = (xfs_buf_t *)bio->bi_private; @@ -1105,10 +1104,10 @@ xfs_buf_bio_end_io( * don't overwrite existing errors - otherwise we can lose errors on * buffers that require multiple bios to complete. */ - if (error) { + if (bio->bi_error) { spin_lock(&bp->b_lock); if (!bp->b_io_error) - bp->b_io_error = error; + bp->b_io_error = bio->bi_error; spin_unlock(&bp->b_lock); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f0e8249722d4..db4acc1c3e73 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1514,18 +1514,27 @@ xfs_filemap_fault( struct vm_area_struct *vma, struct vm_fault *vmf) { - struct xfs_inode *ip = XFS_I(file_inode(vma->vm_file)); + struct inode *inode = file_inode(vma->vm_file); int ret; - trace_xfs_filemap_fault(ip); + trace_xfs_filemap_fault(XFS_I(inode)); /* DAX can shortcut the normal fault path on write faults! */ - if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip))) + if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode)) return xfs_filemap_page_mkwrite(vma, vmf); - xfs_ilock(ip, XFS_MMAPLOCK_SHARED); - ret = filemap_fault(vma, vmf); - xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + if (IS_DAX(inode)) { + /* + * we do not want to trigger unwritten extent conversion on read + * faults - that is unnecessary overhead and would also require + * changes to xfs_get_blocks_direct() to map unwritten extent + * ioend for conversion on read-only mappings. + */ + ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL); + } else + ret = filemap_fault(vma, vmf); + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); return ret; } diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 01dd228ca05e..480ebba8464f 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -1886,9 +1886,14 @@ xlog_recover_get_buf_lsn( uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid; break; case XFS_ATTR3_RMT_MAGIC: - lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn); - uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid; - break; + /* + * Remote attr blocks are written synchronously, rather than + * being logged. That means they do not contain a valid LSN + * (i.e. transactionally ordered) in them, and hence any time we + * see a buffer to replay over the top of a remote attribute + * block we should simply do so. + */ + goto recover_immediately; case XFS_SB_MAGIC: lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn); uuid = &((struct xfs_dsb *)blk)->sb_uuid; |