From: Linus Torvalds Date: Thu, 30 Jan 2014 19:19:05 +0000 (-0800) Subject: Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block X-Git-Url: http://pileus.org/git/?p=~andy%2Flinux;a=commitdiff_plain;h=f568849edac8611d603e00bd6cbbcfea09395ae6 Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block Pull core block IO changes from Jens Axboe: "The major piece in here is the immutable bio_ve series from Kent, the rest is fairly minor. It was supposed to go in last round, but various issues pushed it to this release instead. The pull request contains: - Various smaller blk-mq fixes from different folks. Nothing major here, just minor fixes and cleanups. - Fix for a memory leak in the error path in the block ioctl code from Christian Engelmayer. - Header export fix from CaiZhiyong. - Finally the immutable biovec changes from Kent Overstreet. This enables some nice future work on making arbitrarily sized bios possible, and splitting more efficient. Related fixes to immutable bio_vecs: - dm-cache immutable fixup from Mike Snitzer. - btrfs immutable fixup from Muthu Kumar. - bio-integrity fix from Nic Bellinger, which is also going to stable" * 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits) xtensa: fixup simdisk driver to work with immutable bio_vecs block/blk-mq-cpu.c: use hotcpu_notifier() blk-mq: for_each_* macro correctness block: Fix memory leak in rw_copy_check_uvector() handling bio-integrity: Fix bio_integrity_verify segment start bug block: remove unrelated header files and export symbol blk-mq: uses page->list incorrectly blk-mq: use __smp_call_function_single directly btrfs: fix missing increment of bi_remaining Revert "block: Warn and free bio if bi_end_io is not set" block: Warn and free bio if bi_end_io is not set blk-mq: fix initializing request's start time block: blk-mq: don't export blk_mq_free_queue() block: blk-mq: make blk_sync_queue support mq block: blk-mq: support draining mq queue dm cache: increment bi_remaining when bi_end_io is restored block: fixup for generic bio chaining block: Really silence spurious compiler warnings block: Silence spurious compiler warnings block: Kill bio_pair_split() ... --- f568849edac8611d603e00bd6cbbcfea09395ae6 diff --cc drivers/md/dm-thin.c index 726228b33a0,357eb272dbd..faaf944597a --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@@ -1258,8 -1262,8 +1264,8 @@@ static void process_bio_read_only(struc r = dm_thin_find_block(tc->td, block, 1, &lookup_result); switch (r) { case 0: - if (lookup_result.shared && (rw == WRITE) && bio->bi_size) + if (lookup_result.shared && (rw == WRITE) && bio->bi_iter.bi_size) - bio_io_error(bio); + handle_unserviceable_bio(tc->pool, bio); else { inc_all_io_entry(tc->pool, bio); remap_and_issue(tc, bio, lookup_result.block); diff --cc drivers/md/raid10.c index 8d39d63281b,6d43d88657a..33fc408e5ea --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@@ -1319,8 -1256,8 +1256,8 @@@ read_again /* Could not read all from this device, so we will * need another r10_bio. */ - sectors_handled = (r10_bio->sectors + max_sectors + sectors_handled = (r10_bio->sector + max_sectors - - bio->bi_sector); + - bio->bi_iter.bi_sector); r10_bio->sectors = max_sectors; spin_lock_irq(&conf->device_lock); if (bio->bi_phys_segments == 0) diff --cc fs/f2fs/data.c index 0ae55872350,a2c8de8ba6c..2261ccdd0b5 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@@ -24,195 -24,6 +24,188 @@@ #include "segment.h" #include +static void f2fs_read_end_io(struct bio *bio, int err) +{ - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; ++ struct bio_vec *bvec; ++ int i; + - do { ++ bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + - if (--bvec >= bio->bi_io_vec) - prefetchw(&bvec->bv_page->flags); - - if (unlikely(!uptodate)) { ++ if (!err) { ++ SetPageUptodate(page); ++ } else { + ClearPageUptodate(page); + SetPageError(page); - } else { - SetPageUptodate(page); + } + unlock_page(page); - } while (bvec >= bio->bi_io_vec); - ++ } + bio_put(bio); +} + +static void f2fs_write_end_io(struct bio *bio, int err) +{ - const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); - struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; - struct f2fs_sb_info *sbi = F2FS_SB(bvec->bv_page->mapping->host->i_sb); ++ struct f2fs_sb_info *sbi = F2FS_SB(bio->bi_io_vec->bv_page->mapping->host->i_sb); ++ struct bio_vec *bvec; ++ int i; + - do { ++ bio_for_each_segment_all(bvec, bio, i) { + struct page *page = bvec->bv_page; + - if (--bvec >= bio->bi_io_vec) - prefetchw(&bvec->bv_page->flags); - - if (unlikely(!uptodate)) { ++ if (unlikely(err)) { + SetPageError(page); + set_bit(AS_EIO, &page->mapping->flags); + set_ckpt_flags(sbi->ckpt, CP_ERROR_FLAG); + sbi->sb->s_flags |= MS_RDONLY; + } + end_page_writeback(page); + dec_page_count(sbi, F2FS_WRITEBACK); - } while (bvec >= bio->bi_io_vec); ++ } + + if (bio->bi_private) + complete(bio->bi_private); + + if (!get_pages(sbi, F2FS_WRITEBACK) && + !list_empty(&sbi->cp_wait.task_list)) + wake_up(&sbi->cp_wait); + + bio_put(bio); +} + +/* + * Low-level block read/write IO operations. + */ +static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr, + int npages, bool is_read) +{ + struct bio *bio; + + /* No failure on bio allocation */ + bio = bio_alloc(GFP_NOIO, npages); + + bio->bi_bdev = sbi->sb->s_bdev; - bio->bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); ++ bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr); + bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io; + + return bio; +} + +static void __submit_merged_bio(struct f2fs_bio_info *io) +{ + struct f2fs_io_info *fio = &io->fio; + int rw; + + if (!io->bio) + return; + + rw = fio->rw; + + if (is_read_io(rw)) { + trace_f2fs_submit_read_bio(io->sbi->sb, rw, + fio->type, io->bio); + submit_bio(rw, io->bio); + } else { + trace_f2fs_submit_write_bio(io->sbi->sb, rw, + fio->type, io->bio); + /* + * META_FLUSH is only from the checkpoint procedure, and we + * should wait this metadata bio for FS consistency. + */ + if (fio->type == META_FLUSH) { + DECLARE_COMPLETION_ONSTACK(wait); + io->bio->bi_private = &wait; + submit_bio(rw, io->bio); + wait_for_completion(&wait); + } else { + submit_bio(rw, io->bio); + } + } + + io->bio = NULL; +} + +void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, + enum page_type type, int rw) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(type); + struct f2fs_bio_info *io; + + io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype]; + + mutex_lock(&io->io_mutex); + + /* change META to META_FLUSH in the checkpoint procedure */ + if (type >= META_FLUSH) { + io->fio.type = META_FLUSH; + io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO; + } + __submit_merged_bio(io); + mutex_unlock(&io->io_mutex); +} + +/* + * Fill the locked page with data located in the block address. + * Return unlocked page. + */ +int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, int rw) +{ + struct bio *bio; + + trace_f2fs_submit_page_bio(page, blk_addr, rw); + + /* Allocate a new bio */ + bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw)); + + if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { + bio_put(bio); + f2fs_put_page(page, 1); + return -EFAULT; + } + + submit_bio(rw, bio); + return 0; +} + +void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page, + block_t blk_addr, struct f2fs_io_info *fio) +{ + enum page_type btype = PAGE_TYPE_OF_BIO(fio->type); + struct f2fs_bio_info *io; + bool is_read = is_read_io(fio->rw); + + io = is_read ? &sbi->read_io : &sbi->write_io[btype]; + + verify_block_addr(sbi, blk_addr); + + mutex_lock(&io->io_mutex); + + if (!is_read) + inc_page_count(sbi, F2FS_WRITEBACK); + + if (io->bio && (io->last_block_in_bio != blk_addr - 1 || + io->fio.rw != fio->rw)) + __submit_merged_bio(io); +alloc_new: + if (io->bio == NULL) { + int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi)); + + io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read); + io->fio = *fio; + } + + if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) < + PAGE_CACHE_SIZE) { + __submit_merged_bio(io); + goto alloc_new; + } + + io->last_block_in_bio = blk_addr; + + mutex_unlock(&io->io_mutex); + trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr); +} + /* * Lock ordering for the change of data block address: * ->data_page diff --cc include/trace/events/f2fs.h index 3b9f28dfc84,bd3ee4fbe7a..67f38faac58 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@@ -627,16 -614,16 +627,16 @@@ DECLARE_EVENT_CLASS(f2fs__submit_bio TP_fast_assign( __entry->dev = sb->s_dev; - __entry->btype = btype; - __entry->sync = sync; + __entry->rw = rw; + __entry->type = type; - __entry->sector = bio->bi_sector; - __entry->size = bio->bi_size; + __entry->sector = bio->bi_iter.bi_sector; + __entry->size = bio->bi_iter.bi_size; ), - TP_printk("dev = (%d,%d), type = %s, io = %s, sector = %lld, size = %u", + TP_printk("dev = (%d,%d), %s%s, %s, sector = %lld, size = %u", show_dev(__entry), - show_block_type(__entry->btype), - __entry->sync ? "sync" : "no sync", + show_bio_type(__entry->rw), + show_block_type(__entry->type), (unsigned long long)__entry->sector, __entry->size) );