From: Nhat Pham <nphamcs@gmail.com>
To: akpm@linux-foundation.org
Cc: chrisl@kernel.org, kasong@tencent.com, hannes@cmpxchg.org,
mhocko@kernel.org, roman.gushchin@linux.dev,
shakeel.butt@linux.dev, yosry@kernel.org, david@kernel.org,
muchun.song@linux.dev, shikemeng@huaweicloud.com,
baoquan.he@linux.dev, baohua@kernel.org, youngjun.park@lge.com,
chengming.zhou@linux.dev, ljs@kernel.org, liam@infradead.org,
vbabka@kernel.org, rppt@kernel.org, surenb@google.com,
qi.zheng@linux.dev, axelrasmussen@google.com, yuanchu@google.com,
weixugc@google.com, riel@surriel.com, gourry@gourry.net,
haowenchao22@gmail.com, corbet@lwn.net, hughd@google.com,
baolin.wang@linux.alibaba.com, tj@kernel.org, mkoutny@suse.com,
skhan@linuxfoundation.org, kunwu.chan@linux.dev,
kernel-team@meta.com, nphamcs@gmail.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
cgroups@vger.kernel.org
Subject: [PATCH v4 03/11] mm, swap: prepare the swap IO path for vswap
Date: Tue, 25 Aug 2026 08:32:29 -0700 [thread overview]
Message-ID: <20260825153238.2695446-4-nphamcs@gmail.com> (raw)
In-Reply-To: <20260825153238.2695446-1-nphamcs@gmail.com>
In preparation for adding a physical swap backend for vswap, make the
swap IO path able to submit IO for a swap entry other than folio->swap.
The swap IO path derives the target device and sector from folio->swap.
For a vswap folio backed by a physical slot that entry is virtual, so it
identifies neither the backing device nor the sector to submit IO
against.
Compute the sector from an explicit entry (swap_folio_sector becomes
swap_entry_sector), thread that entry through swap_add_folio,
__swap_writepage and ops->can_merge, and stash it in swap_iocb so the
submit and completion paths address the IO from it rather than from
folio->swap.
This lets the batching path serve both vswap entries (backed by a
physical slot) and physical entries mapped directly into PTEs.
All callers pass folio->swap for now, so there is no functional change.
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
include/linux/swap.h | 2 +-
include/linux/swap_ops.h | 9 ++++---
mm/page_io.c | 54 +++++++++++++++++++---------------------
mm/swap.h | 3 ++-
mm/swapfile.c | 6 ++---
mm/zswap.c | 2 +-
6 files changed, 38 insertions(+), 38 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 5339323486d5..f57f4aeeb822 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -388,7 +388,7 @@ extern int __swap_count(swp_entry_t entry);
extern bool swap_entry_swapped(struct swap_info_struct *si, swp_entry_t entry);
extern int swp_swapcount(swp_entry_t entry);
extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
-sector_t swap_folio_sector(struct folio *folio);
+sector_t swap_entry_sector(swp_entry_t entry);
/*
* If there is an existing swap slot reference (swap entry) and the caller
diff --git a/include/linux/swap_ops.h b/include/linux/swap_ops.h
index 57ac6c703f68..223c84548bde 100644
--- a/include/linux/swap_ops.h
+++ b/include/linux/swap_ops.h
@@ -12,6 +12,7 @@ struct swap_iocb {
struct bio_vec bvecs[SWAP_CLUSTER_MAX];
int nr_bvecs;
int len;
+ swp_entry_t entry; /* first slot in the batch; addresses the IO */
};
struct swap_io_ctx {
@@ -30,15 +31,15 @@ struct swap_io_ctx {
struct swap_ops {
unsigned int flags;
- bool (*can_merge)(struct folio *folio, struct folio *prev_folio,
- size_t prev_folio_size, int rw);
+ bool (*can_merge)(struct folio *folio, swp_entry_t phys,
+ struct swap_iocb *sio, int rw);
void (*submit_write)(struct swap_io_ctx *ctx);
void (*submit_read)(struct swap_io_ctx *ctx);
};
void swap_fs_prepare_rw(struct swap_io_ctx *ctx, int rw, struct iov_iter *iter);
-bool swap_fs_can_merge(struct folio *folio, struct folio *prev_folio,
- size_t prev_folio_size, int rw);
+bool swap_fs_can_merge(struct folio *folio, swp_entry_t phys,
+ struct swap_iocb *sio, int rw);
int swap_fs_activate(struct swap_info_struct *sis, const struct swap_ops *ops);
#endif /* _MM_SWAP_OPS_H */
diff --git a/mm/page_io.c b/mm/page_io.c
index 3bc69c2dbe4d..a3aaa61d6c79 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -265,7 +265,7 @@ int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
return AOP_WRITEPAGE_ACTIVATE;
}
- __swap_writepage(ctx, folio);
+ __swap_writepage(ctx, folio, folio->swap);
return 0;
out_unlock:
folio_unlock(folio);
@@ -334,24 +334,22 @@ int sio_pool_init(void)
}
static bool swap_can_merge(struct swap_io_ctx *ctx, struct folio *folio,
- int rw)
+ swp_entry_t phys, int rw)
{
- struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
- struct bio_vec *last_bv = &ctx->sio->bvecs[ctx->sio->nr_bvecs - 1];
- struct folio *prev_folio = bvec_folio(last_bv);
- size_t prev_folio_size = folio_size(prev_folio);
+ struct swap_info_struct *sis = __swap_entry_to_info(phys);
if (ctx->sis != sis)
return false;
- return sis->ops->can_merge(folio, prev_folio, prev_folio_size, rw);
+ return sis->ops->can_merge(folio, phys, ctx->sio, rw);
}
-static void swap_add_folio(struct swap_io_ctx *ctx, struct folio *folio, int rw)
+static void swap_add_folio(struct swap_io_ctx *ctx, struct folio *folio,
+ swp_entry_t phys, int rw)
{
- struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(phys);
struct swap_iocb *sio = ctx->sio;
- if (sio && !swap_can_merge(ctx, folio, rw)) {
+ if (sio && !swap_can_merge(ctx, folio, phys, rw)) {
if (rw == WRITE)
swap_write_submit(ctx);
else
@@ -364,6 +362,7 @@ static void swap_add_folio(struct swap_io_ctx *ctx, struct folio *folio, int rw)
ctx->sio = sio = mempool_alloc(sio_pool, GFP_NOIO);
sio->nr_bvecs = 0;
sio->len = 0;
+ sio->entry = phys;
}
bvec_set_folio(&sio->bvecs[sio->nr_bvecs], folio, folio_size(folio), 0);
sio->len += folio_size(folio);
@@ -384,7 +383,8 @@ static void swap_add_folio(struct swap_io_ctx *ctx, struct folio *folio, int rw)
}
}
-void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio,
+ swp_entry_t phys)
{
VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
@@ -400,7 +400,7 @@ void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio)
folio_start_writeback(folio);
folio_unlock(folio);
- swap_add_folio(ctx, folio, WRITE);
+ swap_add_folio(ctx, folio, phys, WRITE);
}
/*
@@ -504,7 +504,7 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
/* We have to read from slower devices. Increase zswap protection. */
zswap_folio_swapin(folio);
- swap_add_folio(ctx, folio, READ);
+ swap_add_folio(ctx, folio, folio->swap, READ);
finish:
if (workingset) {
@@ -536,8 +536,6 @@ static void swap_fs_write_complete(struct kiocb *iocb, long ret)
bool failed = ret != sio->len;
if (failed) {
- struct page *page = sio->bvecs[0].bv_page;
-
/*
* In the case of swap-over-nfs, this can be a temporary failure
* if the system has limited memory for allocating transmit
@@ -545,7 +543,7 @@ static void swap_fs_write_complete(struct kiocb *iocb, long ret)
* folio_rotate_reclaimable but rate-limit the messages.
*/
pr_err_ratelimited("Write error %ld on dio swapfile (%llu)\n",
- ret, swap_dev_pos(page_swap_entry(page)));
+ ret, swap_dev_pos(sio->entry));
}
swap_write_end(sio, failed);
@@ -617,7 +615,7 @@ static void swap_bdev_submit_write(struct swap_io_ctx *ctx)
bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
REQ_OP_WRITE | REQ_SWAP);
bio->bi_iter.bi_size = sio->len;
- bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+ bio->bi_iter.bi_sector = swap_entry_sector(sio->entry);
bio_associate_blkg_from_page(bio, bio_first_folio_all(bio));
if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
@@ -637,7 +635,7 @@ static void swap_bdev_submit_read(struct swap_io_ctx *ctx)
bio_init(bio, ctx->sis->bdev, sio->bvecs, ARRAY_SIZE(sio->bvecs),
REQ_OP_READ);
bio->bi_iter.bi_size = sio->len;
- bio->bi_iter.bi_sector = swap_folio_sector(bio_first_folio_all(bio));
+ bio->bi_iter.bi_sector = swap_entry_sector(sio->entry);
if (ctx->sis->flags & SWP_SYNCHRONOUS_IO) {
/*
@@ -655,13 +653,14 @@ static void swap_bdev_submit_read(struct swap_io_ctx *ctx)
}
}
-static bool swap_bdev_can_merge(struct folio *folio, struct folio *prev_folio,
- size_t prev_folio_size, int rw)
+static bool swap_bdev_can_merge(struct folio *folio, swp_entry_t phys,
+ struct swap_iocb *sio, int rw)
{
- if (swap_folio_sector(folio) !=
- swap_folio_sector(prev_folio) + (prev_folio_size >> SECTOR_SHIFT))
+ if (swap_entry_sector(phys) !=
+ swap_entry_sector(sio->entry) + (sio->len >> SECTOR_SHIFT))
return false;
- if (rw == WRITE && !folio_blkg_can_merge(folio, prev_folio))
+ if (rw == WRITE && !folio_blkg_can_merge(folio,
+ bvec_folio(&sio->bvecs[sio->nr_bvecs - 1])))
return false;
return true;
}
@@ -677,7 +676,7 @@ void swap_fs_prepare_rw(struct swap_io_ctx *ctx, int rw, struct iov_iter *iter)
struct swap_iocb *sio = ctx->sio;
init_sync_kiocb(&sio->iocb, ctx->sis->swap_file);
- sio->iocb.ki_pos = swap_dev_pos(bvec_folio(&sio->bvecs[0])->swap);
+ sio->iocb.ki_pos = swap_dev_pos(sio->entry);
if (rw == WRITE)
sio->iocb.ki_complete = swap_fs_write_complete;
else
@@ -688,11 +687,10 @@ void swap_fs_prepare_rw(struct swap_io_ctx *ctx, int rw, struct iov_iter *iter)
}
EXPORT_SYMBOL_GPL(swap_fs_prepare_rw);
-bool swap_fs_can_merge(struct folio *folio, struct folio *prev_folio,
- size_t prev_folio_size, int rw)
+bool swap_fs_can_merge(struct folio *folio, swp_entry_t phys,
+ struct swap_iocb *sio, int rw)
{
- return swap_dev_pos(folio->swap) ==
- swap_dev_pos(prev_folio->swap) + prev_folio_size;
+ return swap_dev_pos(phys) == swap_dev_pos(sio->entry) + sio->len;
}
EXPORT_SYMBOL_GPL(swap_fs_can_merge);
diff --git a/mm/swap.h b/mm/swap.h
index 1cc9f3f5105e..f2b64920ae5b 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -320,7 +320,8 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio);
void swap_read_submit(struct swap_io_ctx *ctx);
void swap_write_submit(struct swap_io_ctx *ctx);
int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio);
-void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio);
+void __swap_writepage(struct swap_io_ctx *ctx, struct folio *folio,
+ swp_entry_t phys);
/* linux/mm/swap_state.c */
extern struct address_space swap_space __read_mostly;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index e0b603a247c0..f5fd01307a67 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -343,14 +343,14 @@ offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset)
BUG();
}
-sector_t swap_folio_sector(struct folio *folio)
+sector_t swap_entry_sector(swp_entry_t entry)
{
- struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
+ struct swap_info_struct *sis = __swap_entry_to_info(entry);
struct swap_extent *se;
sector_t sector;
pgoff_t offset;
- offset = swp_offset(folio->swap);
+ offset = swp_offset(entry);
se = offset_to_swap_extent(sis, offset);
sector = se->start_block + (offset - se->start_page);
return sector << (PAGE_SHIFT - 9);
diff --git a/mm/zswap.c b/mm/zswap.c
index e5a9922b951a..54506935ceba 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1076,7 +1076,7 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
folio_set_reclaim(folio);
/* start writeback */
- __swap_writepage(&ctx, folio);
+ __swap_writepage(&ctx, folio, folio->swap);
swap_write_submit(&ctx);
out:
--
2.53.0-Meta
next prev parent reply other threads:[~2026-08-25 15:32 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-25 15:32 [PATCH v4 00/11] Virtual Swap Space (Swap Table Edition) Nhat Pham
2026-08-25 15:32 ` [PATCH v4 01/11] mm, swap: add virtual swap device infrastructure Nhat Pham
2026-08-25 15:32 ` [PATCH v4 02/11] mm, swap: support zswap and zero-filled swap pages as vswap backends Nhat Pham
2026-08-25 15:32 ` Nhat Pham [this message]
2026-08-25 15:32 ` [PATCH v4 04/11] mm, swap: support physical swap as a vswap backend Nhat Pham
2026-08-25 15:32 ` [PATCH v4 05/11] mm, swap: enable THP swapin for vswap entries Nhat Pham
2026-08-25 15:32 ` [PATCH v4 06/11] mm, swap: write back vswap zswap entries to physical swap Nhat Pham
2026-08-25 15:32 ` [PATCH v4 07/11] mm, swap: reclaim physical slots backing cache-only vswap entries Nhat Pham
2026-08-25 15:32 ` [PATCH v4 08/11] mm, swap: only charge physical swap entries Nhat Pham
2026-08-25 15:32 ` [PATCH v4 09/11] mm, swap: add debugfs counters for vswap Nhat Pham
2026-08-25 15:32 ` [PATCH v4 10/11] mm, swap: defer memcg_table allocation for physical swap clusters Nhat Pham
2026-08-25 15:32 ` [PATCH v4 11/11] mm, swap: widen swap_info_struct max/pages to unsigned long Nhat Pham
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260825153238.2695446-4-nphamcs@gmail.com \
--to=nphamcs@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=baoquan.he@linux.dev \
--cc=cgroups@vger.kernel.org \
--cc=chengming.zhou@linux.dev \
--cc=chrisl@kernel.org \
--cc=corbet@lwn.net \
--cc=david@kernel.org \
--cc=gourry@gourry.net \
--cc=hannes@cmpxchg.org \
--cc=haowenchao22@gmail.com \
--cc=hughd@google.com \
--cc=kasong@tencent.com \
--cc=kernel-team@meta.com \
--cc=kunwu.chan@linux.dev \
--cc=liam@infradead.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@kernel.org \
--cc=mkoutny@suse.com \
--cc=muchun.song@linux.dev \
--cc=qi.zheng@linux.dev \
--cc=riel@surriel.com \
--cc=roman.gushchin@linux.dev \
--cc=rppt@kernel.org \
--cc=shakeel.butt@linux.dev \
--cc=shikemeng@huaweicloud.com \
--cc=skhan@linuxfoundation.org \
--cc=surenb@google.com \
--cc=tj@kernel.org \
--cc=vbabka@kernel.org \
--cc=weixugc@google.com \
--cc=yosry@kernel.org \
--cc=youngjun.park@lge.com \
--cc=yuanchu@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox