Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753130AbdGXFTm (ORCPT ); Mon, 24 Jul 2017 01:19:42 -0400 Received: from mga04.intel.com ([192.55.52.120]:64840 "EHLO mga04.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752790AbdGXFS5 (ORCPT ); Mon, 24 Jul 2017 01:18:57 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.40,405,1496127600"; d="scan'208";a="290458711" From: "Huang, Ying" To: Andrew Morton Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Huang Ying , Johannes Weiner , Minchan Kim , Dan Williams , Vishal L Verma , Jens Axboe , linux-nvdimm@lists.01.org Subject: [PATCH -mm -v3 05/12] block, THP: Make block_device_operations.rw_page support THP Date: Mon, 24 Jul 2017 13:18:33 +0800 Message-Id: <20170724051840.2309-6-ying.huang@intel.com> X-Mailer: git-send-email 2.13.2 In-Reply-To: <20170724051840.2309-1-ying.huang@intel.com> References: <20170724051840.2309-1-ying.huang@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4281 Lines: 136 From: Huang Ying 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" Reviewed-by: Ross Zwisler [for brd.c, zram_drv.c, pmem.c] Cc: Johannes Weiner Cc: Minchan Kim Cc: Dan Williams Cc: Vishal L Verma Cc: Jens Axboe Cc: linux-nvdimm@lists.01.org --- 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 104b71c0490d..5d9ed0616413 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -326,7 +326,11 @@ 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 856d5dc02451..e2a305b41cd4 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 14323faf8bd9..60491641a8d6 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1241,8 +1241,10 @@ static int btt_rw_page(struct block_device *bdev, sector_t sector, { 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 --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f7099adaabc0..e9aa453da50c 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -80,22 +80,40 @@ 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_flushcache(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_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); - - 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; } @@ -188,7 +206,8 @@ 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 -- 2.13.2