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@intel.comSigned-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@intel.com> [for brd.c, zram_drv.c, pmem.c]
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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;
 }

drivers/block/zram/zram_drv.c

@@ -1285,6 +1285,8 @@ 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)) {

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);
 

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);
+	unsigned int chunk;
+	void *mem;
 
-	memcpy_flushcache(pmem_addr, mem + off, len);
+	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);
+	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