The patch titled
Subject: mm: handle THP in swap_*page_fs()
has been added to the -mm tree. Its filename is
mm-handle-thp-in-swap_page_fs.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-handle-thp-in-swap_page_fs.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-handle-thp-in-swap_page_fs.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: NeilBrown <neilb@xxxxxxx>
Subject: mm: handle THP in swap_*page_fs()
Pages passed to swap_readpage()/swap_writepage() are not necessarily all
the same size - there may be transparent-huge-pages involves.
The BIO paths of swap_*page() handle this correctly, but the SWP_FS_OPS
path does not.
So we need to use thp_size() to find the size, not just assume PAGE_SIZE,
and we need to track the total length of the request, not just assume it
is "page * PAGE_SIZE".
Link: https://lkml.kernel.org/r/165119301488.15698.9457662928942765453.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@xxxxxxx>
Reported-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Geert Uytterhoeven <geert+renesas@xxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_io.c | 23 +++++++++++++----------
1 file changed, 13 insertions(+), 10 deletions(-)
--- a/mm/page_io.c~mm-handle-thp-in-swap_page_fs
+++ a/mm/page_io.c
@@ -239,6 +239,7 @@ struct swap_iocb {
struct kiocb iocb;
struct bio_vec bvec[SWAP_CLUSTER_MAX];
int pages;
+ int len;
};
static mempool_t *sio_pool;
@@ -261,7 +262,7 @@ static void sio_write_complete(struct ki
struct page *page = sio->bvec[0].bv_page;
int p;
- if (ret != PAGE_SIZE * sio->pages) {
+ if (ret != sio->len) {
/*
* In the case of swap-over-nfs, this can be a
* temporary failure if the system has limited
@@ -301,7 +302,7 @@ static int swap_writepage_fs(struct page
sio = *wbc->swap_plug;
if (sio) {
if (sio->iocb.ki_filp != swap_file ||
- sio->iocb.ki_pos + sio->pages * PAGE_SIZE != pos) {
+ sio->iocb.ki_pos + sio->len != pos) {
swap_write_unplug(sio);
sio = NULL;
}
@@ -312,10 +313,12 @@ static int swap_writepage_fs(struct page
sio->iocb.ki_complete = sio_write_complete;
sio->iocb.ki_pos = pos;
sio->pages = 0;
+ sio->len = 0;
}
sio->bvec[sio->pages].bv_page = page;
- sio->bvec[sio->pages].bv_len = PAGE_SIZE;
+ sio->bvec[sio->pages].bv_len = thp_size(page);
sio->bvec[sio->pages].bv_offset = 0;
+ sio->len += thp_size(page);
sio->pages += 1;
if (sio->pages == ARRAY_SIZE(sio->bvec) || !wbc->swap_plug) {
swap_write_unplug(sio);
@@ -371,8 +374,7 @@ void swap_write_unplug(struct swap_iocb
struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
int ret;
- iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages,
- PAGE_SIZE * sio->pages);
+ iov_iter_bvec(&from, WRITE, sio->bvec, sio->pages, sio->len);
ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
if (ret != -EIOCBQUEUED)
sio_write_complete(&sio->iocb, ret);
@@ -383,7 +385,7 @@ static void sio_read_complete(struct kio
struct swap_iocb *sio = container_of(iocb, struct swap_iocb, iocb);
int p;
- if (ret == PAGE_SIZE * sio->pages) {
+ if (ret == sio->len) {
for (p = 0; p < sio->pages; p++) {
struct page *page = sio->bvec[p].bv_page;
@@ -415,7 +417,7 @@ static void swap_readpage_fs(struct page
sio = *plug;
if (sio) {
if (sio->iocb.ki_filp != sis->swap_file ||
- sio->iocb.ki_pos + sio->pages * PAGE_SIZE != pos) {
+ sio->iocb.ki_pos + sio->len != pos) {
swap_read_unplug(sio);
sio = NULL;
}
@@ -426,10 +428,12 @@ static void swap_readpage_fs(struct page
sio->iocb.ki_pos = pos;
sio->iocb.ki_complete = sio_read_complete;
sio->pages = 0;
+ sio->len = 0;
}
sio->bvec[sio->pages].bv_page = page;
- sio->bvec[sio->pages].bv_len = PAGE_SIZE;
+ sio->bvec[sio->pages].bv_len = thp_size(page);
sio->bvec[sio->pages].bv_offset = 0;
+ sio->len += thp_size(page);
sio->pages += 1;
if (sio->pages == ARRAY_SIZE(sio->bvec) || !plug) {
swap_read_unplug(sio);
@@ -521,8 +525,7 @@ void __swap_read_unplug(struct swap_iocb
struct address_space *mapping = sio->iocb.ki_filp->f_mapping;
int ret;
- iov_iter_bvec(&from, READ, sio->bvec, sio->pages,
- PAGE_SIZE * sio->pages);
+ iov_iter_bvec(&from, READ, sio->bvec, sio->pages, sio->len);
ret = mapping->a_ops->swap_rw(&sio->iocb, &from);
if (ret != -EIOCBQUEUED)
sio_read_complete(&sio->iocb, ret);
_
Patches currently in -mm which might be from neilb@xxxxxxx are
mm-create-new-mm-swaph-header-file.patch
mm-drop-swap_dirty_folio.patch
mm-move-responsibility-for-setting-swp_fs_ops-to-swap_activate.patch
mm-reclaim-mustnt-enter-fs-for-swp_fs_ops-swap-space.patch
mm-introduce-swap_rw-and-use-it-for-reads-from-swp_fs_ops-swap-space.patch
nfs-rename-nfs_direct_io-and-use-as-swap_rw.patch
mm-perform-async-writes-to-swp_fs_ops-swap-space-using-swap_rw.patch
doc-update-documentation-for-swap_activate-and-swap_rw.patch
mm-submit-multipage-reads-for-swp_fs_ops-swap-space.patch
mm-submit-multipage-write-for-swp_fs_ops-swap-space.patch
mm-handle-thp-in-swap_page_fs.patch
vfs-add-fmode_can_odirect-file-flag.patch
mm-discard-__gfp_atomic.patch
