From 74d46992e0d9dee7f1f376de0d56d31614c8a17a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 23 Aug 2017 19:10:32 +0200 Subject: block: replace bi_bdev with a gendisk pointer and partitions index This way we don't need a block_device structure to submit I/O. The block_device has different life time rules from the gendisk and request_queue and is usually only available when the block device node is open. Other callers need to explicitly create one (e.g. the lightnvm passthrough code, or the new nvme multipathing code). For the actual I/O path all that we need is the gendisk, which exists once per block device. But given that the block layer also does partition remapping we additionally need a partition index, which is used for said remapping in generic_make_request. Note that all the block drivers generally want request_queue or sometimes the gendisk, so this removes a layer of indirection all over the stack. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- mm/page_io.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'mm/page_io.c') diff --git a/mm/page_io.c b/mm/page_io.c index b6c4ac388209..9cf1bc751d79 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -31,7 +31,10 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, bio = bio_alloc(gfp_flags, 1); if (bio) { - bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev); + struct block_device *bdev; + + bio->bi_iter.bi_sector = map_swap_page(page, &bdev); + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_end_io = end_io; @@ -57,8 +60,7 @@ void end_swap_bio_write(struct bio *bio) */ set_page_dirty(page); pr_alert("Write-error on swap-device (%u:%u:%llu)\n", - imajor(bio->bi_bdev->bd_inode), - iminor(bio->bi_bdev->bd_inode), + MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), (unsigned long long)bio->bi_iter.bi_sector); ClearPageReclaim(page); } @@ -123,8 +125,7 @@ static void end_swap_bio_read(struct bio *bio) SetPageError(page); ClearPageUptodate(page); pr_alert("Read-error on swap-device (%u:%u:%llu)\n", - imajor(bio->bi_bdev->bd_inode), - iminor(bio->bi_bdev->bd_inode), + MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)), (unsigned long long)bio->bi_iter.bi_sector); goto out; } @@ -338,7 +339,7 @@ int swap_readpage(struct page *page, bool do_poll) int ret = 0; struct swap_info_struct *sis = page_swap_info(page); blk_qc_t qc; - struct block_device *bdev; + struct gendisk *disk; VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -377,7 +378,7 @@ int swap_readpage(struct page *page, bool do_poll) ret = -ENOMEM; goto out; } - bdev = bio->bi_bdev; + disk = bio->bi_disk; bio->bi_private = current; bio_set_op_attrs(bio, REQ_OP_READ, 0); count_vm_event(PSWPIN); @@ -388,7 +389,7 @@ int swap_readpage(struct page *page, bool do_poll) if (!READ_ONCE(bio->bi_private)) break; - if (!blk_mq_poll(bdev_get_queue(bdev), qc)) + if (!blk_mq_poll(disk->queue, qc)) break; } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 225311a46411c37e20e73d99f4382f141e12f6f9 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:22:30 -0700 Subject: mm: test code to write THP to swap device as a whole To support delay splitting THP (Transparent Huge Page) after swapped out, we need to enhance swap writing code to support to write a THP as a whole. This will improve swap write IO performance. As Ming Lei pointed out, this should be based on multipage bvec support, which hasn't been merged yet. So this patch is only for testing the functionality of the other patches in the series. And will be reimplemented after multipage bvec support is merged. Link: http://lkml.kernel.org/r/20170724051840.2309-7-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: "Kirill A . Shutemov" Cc: Andrea Arcangeli Cc: Dan Williams Cc: Hugh Dickins Cc: Jens Axboe Cc: Johannes Weiner Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Shaohua Li Cc: Vishal L Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bio.h | 8 ++++++++ include/linux/page-flags.h | 4 ++-- include/linux/vm_event_item.h | 1 + mm/page_io.c | 21 ++++++++++++++++----- mm/vmstat.c | 1 + 5 files changed, 28 insertions(+), 7 deletions(-) (limited to 'mm/page_io.c') diff --git a/include/linux/bio.h b/include/linux/bio.h index 7b1cf4ba0902..1f0720de8990 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -38,7 +38,15 @@ #define BIO_BUG_ON #endif +#ifdef CONFIG_THP_SWAP +#if HPAGE_PMD_NR > 256 +#define BIO_MAX_PAGES HPAGE_PMD_NR +#else #define BIO_MAX_PAGES 256 +#endif +#else +#define BIO_MAX_PAGES 256 +#endif #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d33e3280c8ad..ba2d470d2d0a 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY) * Only test-and-set exist for PG_writeback. The unconditional operators are * risky: they bypass page accounting. */ -TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND) - TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND) +TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL) + TESTSCFLAG(Writeback, writeback, PF_NO_TAIL) PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 37e8d31a4632..c75024e80eed 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -85,6 +85,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #endif THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, + THP_SWPOUT, #endif #ifdef CONFIG_MEMORY_BALLOON BALLOON_INFLATE, diff --git a/mm/page_io.c b/mm/page_io.c index 5f61b54ee1f3..20139b90125a 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -28,16 +28,18 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, struct page *page, bio_end_io_t end_io) { + int i, nr = hpage_nr_pages(page); struct bio *bio; - bio = bio_alloc(gfp_flags, 1); + bio = bio_alloc(gfp_flags, nr); if (bio) { bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev); bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_end_io = end_io; - bio_add_page(bio, page, PAGE_SIZE, 0); - BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE); + for (i = 0; i < nr; i++) + bio_add_page(bio, page + i, PAGE_SIZE, 0); + VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr); } return bio; } @@ -262,6 +264,15 @@ static sector_t swap_page_sector(struct page *page) return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9); } +static inline void count_swpout_vm_event(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (unlikely(PageTransHuge(page))) + count_vm_event(THP_SWPOUT); +#endif + count_vm_events(PSWPOUT, hpage_nr_pages(page)); +} + int __swap_writepage(struct page *page, struct writeback_control *wbc, bio_end_io_t end_write_func) { @@ -313,7 +324,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc); if (!ret) { - count_vm_event(PSWPOUT); + count_swpout_vm_event(page); return 0; } @@ -326,7 +337,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); - count_vm_event(PSWPOUT); + count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); submit_bio(bio); diff --git a/mm/vmstat.c b/mm/vmstat.c index 9a4441bbeef2..bccf426453cd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1071,6 +1071,7 @@ const char * const vmstat_text[] = { #endif "thp_zero_page_alloc", "thp_zero_page_alloc_failed", + "thp_swpout", #endif #ifdef CONFIG_MEMORY_BALLOON "balloon_inflate", -- cgit v1.2.3