From: Huang Ying <ying.huang@xxxxxxxxx> 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. 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: linux-nvdimm@xxxxxxxxxxxx --- drivers/block/brd.c | 6 +++++- drivers/block/zram/zram_drv.c | 2 ++ drivers/nvdimm/btt.c | 4 +++- drivers/nvdimm/pmem.c | 41 ++++++++++++++++++++++++++++++----------- 4 files changed, 40 insertions(+), 13 deletions(-) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 57b574f2f66a..4240d2a9dcf9 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -324,7 +324,11 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, 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 --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d3e3af22a088..9f4973f6ba56 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -927,6 +927,8 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, 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 --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 31b2d14e210d..6ec2250b5276 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1248,8 +1248,10 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { struct btt *btt = bdev->bd_disk->private_data; + unsigned int len; - btt_do_bvec(btt, NULL, page, PAGE_SIZE, 0, is_write, sector); + len = hpage_nr_pages(page) * PAGE_SIZE; + btt_do_bvec(btt, NULL, page, len, 0, is_write, sector); page_endio(page, is_write, 0); return 0; } diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7bd383aeea14..72e3fbaefee9 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -78,22 +78,40 @@ static blk_status_t pmem_clear_poison(struct pmem_device *pmem, static void write_pmem(void *pmem_addr, struct page *page, unsigned int off, unsigned int len) { - void *mem = kmap_atomic(page); - - memcpy_to_pmem(pmem_addr, mem + off, len); - kunmap_atomic(mem); + unsigned int chunk; + void *mem; + + while (len) { + mem = kmap_atomic(page); + chunk = min_t(unsigned int, len, PAGE_SIZE); + memcpy_to_pmem(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); - - rc = memcpy_mcsafe(mem + off, pmem_addr, len); - kunmap_atomic(mem); - if (rc) - return BLK_STS_IOERR; + void *mem; + + 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; } @@ -186,7 +204,8 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, 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 -- 2.11.0 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx"> email@xxxxxxxxx </a>