From: Huang Ying <ying.huang@xxxxxxxxx> Subject: block, THP: make block_device_operations.rw_page support THP The .rw_page in struct block_device_operations is used by the swap subsystem to read/write the page contents from/into the corresponding swap slot in the swap device. To support the THP (Transparent Huge Page) swap optimization, the .rw_page is enhanced to support to read/write THP if possible. Link: http://lkml.kernel.org/r/20170724051840.2309-6-ying.huang@xxxxxxxxx Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx> Reviewed-by: Ross Zwisler <ross.zwisler@xxxxxxxxx> [for brd.c, zram_drv.c, pmem.c] Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Minchan Kim <minchan@xxxxxxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Vishal L Verma <vishal.l.verma@xxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: "Kirill A . Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Shaohua Li <shli@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- drivers/block/brd.c | 6 ++++- drivers/block/zram/zram_drv.c | 2 + drivers/nvdimm/btt.c | 4 ++- drivers/nvdimm/pmem.c | 37 ++++++++++++++++++++++++-------- 4 files changed, 38 insertions(+), 11 deletions(-) diff -puN drivers/block/brd.c~block-thp-make-block_device_operationsrw_page-support-thp drivers/block/brd.c --- a/drivers/block/brd.c~block-thp-make-block_device_operationsrw_page-support-thp +++ a/drivers/block/brd.c @@ -326,7 +326,11 @@ static int brd_rw_page(struct block_devi struct page *page, bool is_write) { struct brd_device *brd = bdev->bd_disk->private_data; - int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); + int err; + + if (PageTransHuge(page)) + return -ENOTSUPP; + err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); page_endio(page, is_write, err); return err; } diff -puN drivers/block/zram/zram_drv.c~block-thp-make-block_device_operationsrw_page-support-thp drivers/block/zram/zram_drv.c --- a/drivers/block/zram/zram_drv.c~block-thp-make-block_device_operationsrw_page-support-thp +++ a/drivers/block/zram/zram_drv.c @@ -1285,6 +1285,8 @@ static int zram_rw_page(struct block_dev struct zram *zram; struct bio_vec bv; + if (PageTransHuge(page)) + return -ENOTSUPP; zram = bdev->bd_disk->private_data; if (!valid_io_request(zram, sector, PAGE_SIZE)) { diff -puN drivers/nvdimm/btt.c~block-thp-make-block_device_operationsrw_page-support-thp drivers/nvdimm/btt.c --- a/drivers/nvdimm/btt.c~block-thp-make-block_device_operationsrw_page-support-thp +++ a/drivers/nvdimm/btt.c @@ -1241,8 +1241,10 @@ static int btt_rw_page(struct block_devi { struct btt *btt = bdev->bd_disk->private_data; int rc; + unsigned int len; - rc = btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector); + len = hpage_nr_pages(page) * PAGE_SIZE; + rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector); if (rc == 0) page_endio(page, is_write, 0); diff -puN drivers/nvdimm/pmem.c~block-thp-make-block_device_operationsrw_page-support-thp drivers/nvdimm/pmem.c --- a/drivers/nvdimm/pmem.c~block-thp-make-block_device_operationsrw_page-support-thp +++ a/drivers/nvdimm/pmem.c @@ -80,22 +80,40 @@ static blk_status_t pmem_clear_poison(st static void write_pmem(void *pmem_addr, struct page *page, unsigned int off, unsigned int len) { - void *mem = kmap_atomic(page); + unsigned int chunk; + void *mem; - memcpy_flushcache(pmem_addr, mem + off, len); - kunmap_atomic(mem); + while (len) { + mem = kmap_atomic(page); + chunk = min_t(unsigned int, len, PAGE_SIZE); + memcpy_flushcache(pmem_addr, mem + off, chunk); + kunmap_atomic(mem); + len -= chunk; + off = 0; + page++; + pmem_addr += PAGE_SIZE; + } } static blk_status_t read_pmem(struct page *page, unsigned int off, void *pmem_addr, unsigned int len) { + unsigned int chunk; int rc; - void *mem = kmap_atomic(page); + void *mem; - rc = memcpy_mcsafe(mem + off, pmem_addr, len); - kunmap_atomic(mem); - if (rc) - return BLK_STS_IOERR; + while (len) { + mem = kmap_atomic(page); + chunk = min_t(unsigned int, len, PAGE_SIZE); + rc = memcpy_mcsafe(mem + off, pmem_addr, chunk); + kunmap_atomic(mem); + if (rc) + return BLK_STS_IOERR; + len -= chunk; + off = 0; + page++; + pmem_addr += PAGE_SIZE; + } return BLK_STS_OK; } @@ -188,7 +206,8 @@ static int pmem_rw_page(struct block_dev struct pmem_device *pmem = bdev->bd_queue->queuedata; blk_status_t rc; - rc = pmem_do_bvec(pmem, page, PAGE_SIZE, 0, is_write, sector); + rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE, + 0, is_write, sector); /* * The ->rw_page interface is subtle and tricky. The core _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
