From: Linus Torvalds Date: Wed, 5 Jul 2017 23:41:23 +0000 (-0700) Subject: Merge branch 'for-4.13-part1' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave... X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=8c27cb3566762613a23c080e3db7d0501af9a787;p=GitHub%2Fmoto-9609%2Fandroid_kernel_motorola_exynos9610.git Merge branch 'for-4.13-part1' of git://git./linux/kernel/git/kdave/linux Pull btrfs updates from David Sterba: "The core updates improve error handling (mostly related to bios), with the usual incremental work on the GFP_NOFS (mis)use removal, refactoring or cleanups. Except the two top patches, all have been in for-next for an extensive amount of time. User visible changes: - statx support - quota override tunable - improved compression thresholds - obsoleted mount option alloc_start Core updates: - bio-related updates: - faster bio cloning - no allocation failures - preallocated flush bios - more kvzalloc use, memalloc_nofs protections, GFP_NOFS updates - prep work for btree_inode removal - dir-item validation - qgoup fixes and updates - cleanups: - removed unused struct members, unused code, refactoring - argument refactoring (fs_info/root, caller -> callee sink) - SEARCH_TREE ioctl docs" * 'for-4.13-part1' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (115 commits) btrfs: Remove false alert when fiemap range is smaller than on-disk extent btrfs: Don't clear SGID when inheriting ACLs btrfs: fix integer overflow in calc_reclaim_items_nr btrfs: scrub: fix target device intialization while setting up scrub context btrfs: qgroup: Fix qgroup reserved space underflow by only freeing reserved ranges btrfs: qgroup: Introduce extent changeset for qgroup reserve functions btrfs: qgroup: Fix qgroup reserved space underflow caused by buffered write and quotas being enabled btrfs: qgroup: Return actually freed bytes for qgroup release or free data btrfs: qgroup: Cleanup btrfs_qgroup_prepare_account_extents function btrfs: qgroup: Add quick exit for non-fs extents Btrfs: rework delayed ref total_bytes_pinned accounting Btrfs: return old and new total ref mods when adding delayed refs Btrfs: always account pinned bytes when dropping a tree block ref Btrfs: update total_bytes_pinned when pinning down extents Btrfs: make BUG_ON() in add_pinned_bytes() an ASSERT() Btrfs: make add_pinned_bytes() take an s64 num_bytes instead of u64 btrfs: fix validation of XATTR_ITEM dir items btrfs: Verify dir_item in iterate_object_props btrfs: Check name_len before in btrfs_del_root_ref btrfs: Check name_len before reading btrfs_get_name ... --- 8c27cb3566762613a23c080e3db7d0501af9a787 diff --cc fs/btrfs/disk-io.c index 6036d15b47b8,b6758892874f..5abcbdc743fa --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@@ -87,9 -87,8 +87,8 @@@ struct btrfs_end_io_wq bio_end_io_t *end_io; void *private; struct btrfs_fs_info *info; - int error; + blk_status_t status; enum btrfs_wq_endio_type metadata; - struct list_head list; struct btrfs_work work; }; @@@ -868,10 -867,10 +867,10 @@@ unsigned long btrfs_async_submit_limit( static void run_one_async_start(struct btrfs_work *work) { struct async_submit_bio *async; - int ret; + blk_status_t ret; async = container_of(work, struct async_submit_bio, work); - ret = async->submit_bio_start(async->inode, async->bio, + ret = async->submit_bio_start(async->private_data, async->bio, async->mirror_num, async->bio_flags, async->bio_offset); if (ret) @@@ -916,19 -915,20 +915,20 @@@ static void run_one_async_free(struct b kfree(async); } - blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, - struct inode *inode, struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset, void *private_data, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done) ++blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, ++ int mirror_num, unsigned long bio_flags, ++ u64 bio_offset, void *private_data, ++ extent_submit_bio_hook_t *submit_bio_start, ++ extent_submit_bio_hook_t *submit_bio_done) { struct async_submit_bio *async; async = kmalloc(sizeof(*async), GFP_NOFS); if (!async) - return -ENOMEM; + return BLK_STS_RESOURCE; - async->inode = inode; + async->private_data = private_data; + async->fs_info = fs_info; async->bio = bio; async->mirror_num = mirror_num; async->submit_bio_start = submit_bio_start; @@@ -971,12 -971,12 +971,12 @@@ static blk_status_t btree_csum_one_bio( break; } - return ret; + return errno_to_blk_status(ret); } - static blk_status_t __btree_submit_bio_start(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) -static int __btree_submit_bio_start(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) ++static blk_status_t __btree_submit_bio_start(void *private_data, struct bio *bio, ++ int mirror_num, unsigned long bio_flags, ++ u64 bio_offset) { /* * when we're called for a write, we're already in the async @@@ -985,11 -985,12 +985,12 @@@ return btree_csum_one_bio(bio); } - static blk_status_t __btree_submit_bio_done(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) -static int __btree_submit_bio_done(void *private_data, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) ++static blk_status_t __btree_submit_bio_done(void *private_data, struct bio *bio, ++ int mirror_num, unsigned long bio_flags, ++ u64 bio_offset) { + struct inode *inode = private_data; - int ret; + blk_status_t ret; /* * when we're called for a write, we're already in the async @@@ -1014,13 -1015,14 +1015,14 @@@ static int check_async_write(unsigned l return 1; } - static blk_status_t btree_submit_bio_hook(struct inode *inode, struct bio *bio, -static int btree_submit_bio_hook(void *private_data, struct bio *bio, -- int mirror_num, unsigned long bio_flags, -- u64 bio_offset) ++static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio, ++ int mirror_num, unsigned long bio_flags, ++ u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); int async = check_async_write(bio_flags); - int ret; + blk_status_t ret; if (bio_op(bio) != REQ_OP_WRITE) { /* @@@ -3490,59 -3485,57 +3485,57 @@@ static void btrfs_end_empty_barrier(str } /* - * trigger flushes for one the devices. If you pass wait == 0, the flushes are - * sent down. With wait == 1, it waits for the previous flush. - * - * any device where the flush fails with eopnotsupp are flagged as not-barrier - * capable + * Submit a flush request to the device if it supports it. Error handling is + * done in the waiting counterpart. */ - static blk_status_t write_dev_flush(struct btrfs_device *device, int wait) + static void write_dev_flush(struct btrfs_device *device) { struct request_queue *q = bdev_get_queue(device->bdev); - struct bio *bio; - blk_status_t ret = 0; + struct bio *bio = device->flush_bio; if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) - return 0; + return; - if (wait) { - bio = device->flush_bio; - if (!bio) - return 0; + bio_reset(bio); + bio->bi_end_io = btrfs_end_empty_barrier; + bio->bi_bdev = device->bdev; + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; + init_completion(&device->flush_wait); + bio->bi_private = &device->flush_wait; - wait_for_completion(&device->flush_wait); + submit_bio(bio); + device->flush_bio_sent = 1; + } - if (bio->bi_status) { - ret = bio->bi_status; - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_FLUSH_ERRS); - } + /* + * If the flush bio has been submitted by write_dev_flush, wait for it. + */ -static int wait_dev_flush(struct btrfs_device *device) ++static blk_status_t wait_dev_flush(struct btrfs_device *device) + { + struct bio *bio = device->flush_bio; - /* drop the reference from the wait == 0 run */ - bio_put(bio); - device->flush_bio = NULL; + if (!device->flush_bio_sent) + return 0; - return ret; - } + device->flush_bio_sent = 0; + wait_for_completion_io(&device->flush_wait); - /* - * one reference for us, and we leave it for the - * caller - */ - device->flush_bio = NULL; - bio = btrfs_io_bio_alloc(GFP_NOFS, 0); - if (!bio) - return BLK_STS_RESOURCE; - return bio->bi_error; ++ return bio->bi_status; + } - bio->bi_end_io = btrfs_end_empty_barrier; - bio->bi_bdev = device->bdev; - bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; - init_completion(&device->flush_wait); - bio->bi_private = &device->flush_wait; - device->flush_bio = bio; + static int check_barrier_error(struct btrfs_fs_devices *fsdevs) + { + int dev_flush_error = 0; + struct btrfs_device *dev; - bio_get(bio); - btrfsic_submit_bio(bio); + list_for_each_entry_rcu(dev, &fsdevs->devices, dev_list) { + if (!dev->bdev || dev->last_flush_error) + dev_flush_error++; + } + + if (dev_flush_error > + fsdevs->fs_info->num_tolerated_disk_barrier_failures) + return -EIO; return 0; } @@@ -3555,9 -3548,8 +3548,8 @@@ static int barrier_all_devices(struct b { struct list_head *head; struct btrfs_device *dev; - int errors_send = 0; int errors_wait = 0; - int ret; + blk_status_t ret; /* send down all the barriers */ head = &info->fs_devices->devices; diff --cc fs/btrfs/disk-io.h index c581927555f3,4654d129aa76..0a634d3ffc16 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@@ -118,16 -118,16 +118,16 @@@ int btrfs_buffer_uptodate(struct extent int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid); u32 btrfs_csum_data(const char *data, u32 seed, size_t len); void btrfs_csum_final(u32 crc, u8 *result); -int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, +blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio, enum btrfs_wq_endio_type metadata); - blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, - struct inode *inode, struct bio *bio, int mirror_num, - unsigned long bio_flags, u64 bio_offset, - extent_submit_bio_hook_t *submit_bio_start, - extent_submit_bio_hook_t *submit_bio_done); -int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, ++blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset, void *private_data, + extent_submit_bio_hook_t *submit_bio_start, + extent_submit_bio_hook_t *submit_bio_done); unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info); int btrfs_write_tree_block(struct extent_buffer *buf); - int btrfs_wait_tree_block_writeback(struct extent_buffer *buf); + void btrfs_wait_tree_block_writeback(struct extent_buffer *buf); int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_add_log_tree(struct btrfs_trans_handle *trans, diff --cc fs/btrfs/extent_io.c index d1cd60140817,2e6f69908303..7a18b5762ac9 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@@ -2398,9 -2369,9 +2370,10 @@@ static int bio_readpage_error(struct bi struct io_failure_record *failrec; struct inode *inode = page->mapping->host; struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree; struct bio *bio; int read_mode = 0; + blk_status_t status; int ret; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); @@@ -2433,12 -2404,11 +2406,12 @@@ "Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d", read_mode, failrec->this_mirror, failrec->in_validation); - status = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror, - ret = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror, ++ status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror, failrec->bio_flags, 0); - if (ret) { + if (status) { - free_io_failure(BTRFS_I(inode), failrec); + free_io_failure(failure_tree, tree, failrec); bio_put(bio); + ret = blk_status_to_errno(status); } return ret; @@@ -2540,9 -2509,9 +2513,9 @@@ endio_readpage_release_extent(struct ex static void end_bio_extent_readpage(struct bio *bio) { struct bio_vec *bvec; - int uptodate = !bio->bi_error; + int uptodate = !bio->bi_status; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - struct extent_io_tree *tree; + struct extent_io_tree *tree, *failure_tree; u64 offset = 0; u64 start; u64 end; @@@ -2560,9 -2529,10 +2533,10 @@@ btrfs_debug(fs_info, "end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u", - (u64)bio->bi_iter.bi_sector, bio->bi_error, + (u64)bio->bi_iter.bi_sector, bio->bi_status, io_bio->mirror_num); tree = &BTRFS_I(inode)->io_tree; + failure_tree = &BTRFS_I(inode)->io_failure_tree; /* We always issue full-page reads, but if some block * in a page fails to read, blk_update_request() will diff --cc fs/btrfs/extent_io.h index 487ca0207cb6,aeafdb35d90b..3fb8513bf02e --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@@ -92,9 -92,9 +92,9 @@@ struct btrfs_inode struct btrfs_io_bio; struct io_failure_record; - typedef blk_status_t (extent_submit_bio_hook_t)(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset); -typedef int (extent_submit_bio_hook_t)(void *private_data, struct bio *bio, ++typedef blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset); struct extent_io_ops { /* * The following callbacks must be allways defined, the function diff --cc fs/btrfs/inode.c index 556c93060606,5d3c6ac960fd..8d050314591c --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@@ -1900,11 -1900,12 +1899,12 @@@ int btrfs_merge_bio_hook(struct page *p * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ - static blk_status_t __btrfs_submit_bio_start(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) -static int __btrfs_submit_bio_start(void *private_data, struct bio *bio, ++static blk_status_t __btrfs_submit_bio_start(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; - int ret = 0; + blk_status_t ret = 0; ret = btrfs_csum_one_bio(inode, bio, 0, 0); BUG_ON(ret); /* -ENOMEM */ @@@ -1919,12 -1920,13 +1919,13 @@@ * At IO completion time the cums attached on the ordered extent record * are inserted into the btree */ - static blk_status_t __btrfs_submit_bio_done(struct inode *inode, - struct bio *bio, int mirror_num, unsigned long bio_flags, - u64 bio_offset) -static int __btrfs_submit_bio_done(void *private_data, struct bio *bio, ++static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; + blk_status_t ret; ret = btrfs_map_bio(fs_info, bio, mirror_num, 1); if (ret) { @@@ -1938,10 -1940,11 +1939,11 @@@ * extent_io.c submission hook. This does the right thing for csum calculation * on write, or reading the csums from the tree before a read */ - static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio, - int mirror_num, unsigned long bio_flags, - u64 bio_offset) -static int btrfs_submit_bio_hook(void *private_data, struct bio *bio, ++static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio, + int mirror_num, unsigned long bio_flags, + u64 bio_offset) { + struct inode *inode = private_data; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA; @@@ -8033,10 -8046,12 +8045,12 @@@ struct btrfs_retry_complete static void btrfs_retry_endio_nocsum(struct bio *bio) { struct btrfs_retry_complete *done = bio->bi_private; + struct inode *inode = done->inode; struct bio_vec *bvec; + struct extent_io_tree *io_tree, *failure_tree; int i; - if (bio->bi_error) + if (bio->bi_status) goto end; ASSERT(bio->bi_vcnt == 1); @@@ -8140,11 -8171,12 +8170,12 @@@ end bio_put(bio); } -static int __btrfs_subio_endio_read(struct inode *inode, - struct btrfs_io_bio *io_bio, int err) +static blk_status_t __btrfs_subio_endio_read(struct inode *inode, + struct btrfs_io_bio *io_bio, blk_status_t err) { struct btrfs_fs_info *fs_info; - struct bio_vec *bvec; + struct bio_vec bvec; + struct bvec_iter iter; struct btrfs_retry_complete done; u64 start; u64 offset = 0; @@@ -8231,10 -8265,13 +8264,13 @@@ static void btrfs_endio_direct_read(str struct inode *inode = dip->inode; struct bio *dio_bio; struct btrfs_io_bio *io_bio = btrfs_io_bio(bio); - int err = bio->bi_error; + blk_status_t err = bio->bi_status; - if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) + if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) { err = btrfs_subio_endio_read(inode, io_bio, err); + if (!err) - bio->bi_error = 0; ++ bio->bi_status = 0; + } unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset, dip->logical_offset + dip->bytes - 1); @@@ -8307,11 -8344,12 +8343,12 @@@ static void btrfs_endio_direct_write(st bio_put(bio); } - static blk_status_t __btrfs_submit_bio_start_direct_io(struct inode *inode, -static int __btrfs_submit_bio_start_direct_io(void *private_data, ++static blk_status_t __btrfs_submit_bio_start_direct_io(void *private_data, struct bio *bio, int mirror_num, unsigned long bio_flags, u64 offset) { + struct inode *inode = private_data; - int ret; + blk_status_t ret; ret = btrfs_csum_one_bio(inode, bio, offset, 1); BUG_ON(ret); /* -ENOMEM */ return 0; @@@ -8357,17 -8395,7 +8394,7 @@@ out bio_put(bio); } - static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, - u64 first_sector, gfp_t gfp_flags) - { - struct bio *bio; - bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags); - if (bio) - bio_associate_current(bio); - return bio; - } - -static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode, +static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, struct btrfs_dio_private *dip, struct bio *bio, u64 file_offset) @@@ -8672,10 -8675,10 +8674,10 @@@ free_ordered * Releases and cleans up our dio_bio, no need to bio_put() * nor bio_endio()/bio_io_error() against dio_bio. */ - dio_end_io(dio_bio, ret); + dio_end_io(dio_bio); } - if (io_bio) - bio_put(io_bio); + if (bio) + bio_put(bio); kfree(dip); } @@@ -8754,11 -8758,9 +8757,12 @@@ static ssize_t btrfs_direct_IO(struct k dio_data.overwrite = 1; inode_unlock(inode); relock = true; + } else if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; } - ret = btrfs_delalloc_reserve_space(inode, offset, count); + ret = btrfs_delalloc_reserve_space(inode, &data_reserved, + offset, count); if (ret) goto out; dio_data.outstanding_extents = count_max_extents(count);