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.com Signed-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>
This commit is contained in:
parent
f0eea189e8
commit
98cc093cba
|
@ -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;
|
||||
}
|
||||
|
|
|
@ -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)) {
|
||||
|
|
|
@ -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);
|
||||
|
||||
|
|
|
@ -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);
|
||||
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_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
|
||||
|
|
Loading…
Reference in New Issue