Re: [PATCH 2/3] mm/swap: account synchronous swap reads as memory stall

[Johannes Weiner <hannes@cmpxchg.org>]

On Fri, Oct 30, 2026 at 02:31:42AM +0800, Kairui Song via B4 Relay wrote:
> From: Josef Bacik <josef@toxicpanda.com>
> 
> Swap-ins from SWP_SYNCHRONOUS_IO devices such as zram are no longer
> counted in PSI memory pressure or in the swapin and thrashing delays of
> delay accounting.  Refaults of the workingset from zram, the main input
> to userspace OOM handlers like lmkd and systemd-oomd on zram systems,
> become invisible in /proc/pressure/memory.
> 
> swap_read_folio() opens the accounting window with
> psi_memstall_enter() and delayacct_swapin_start() and, per its comment,
> means to count the submission time.  For synchronous devices the
> submission is the entire read: swap_bdev_submit_read() does
> submit_bio_wait() and completes the folio.  Since reads are batched in
> a swap_iocb, swap_read_folio() only queues the folio with
> swap_add_folio(), and the bio is submitted later by swap_read_submit()
> in the caller, e.g. swapin_sync(), after the window has been closed.
> By then the folio is uptodate and unlocked, so the fault does not wait
> on the folio lock either and the read time is not counted anywhere.
> 
> Found by code inspection; not reproduced.
> 
> Fix by submitting synchronous reads from within swap_read_folio(), as
> was done before the batching, rather than from the caller.  This gives
> up batching of readahead for synchronous devices, which do their I/O
> inline anyway, in exchange for keeping the accounting simple and in one
> place.
> 
> Fixes: dda8fb68b590 ("mm/swap: also use struct swap_iocb for block I/O")
> Assisted-by: LLM
> Signed-off-by: Josef Bacik <josef@toxicpanda.com>
> Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
> Signed-off-by: Kairui Song <kasong@tencent.com>

Hm, this isn't a complete fix to the problem described. IO throttling
happens at submission time, so there can be significant delays on
async devices too that are no longer tracked since the culprit change.

How about keeping the accounting window open across the batch? Opens
on first read, closes on submission. A batch with at least one
workingset folio is "contaminated" and the whole sequence and
submission becomes a stall. Would need to pull the !can_merge flush
out of the batch-add function to get the accounting window right but
that seems reasonable.

Something like this:

diff --git a/include/linux/swap_ops.h b/include/linux/swap_ops.h
index 57ac6c703f68..6e45c9204482 100644
--- a/include/linux/swap_ops.h
+++ b/include/linux/swap_ops.h
@@ -17,6 +17,10 @@ struct swap_iocb {
 struct swap_io_ctx {
 	struct swap_iocb	*sio;
 	struct swap_info_struct	*sis;
+	bool			in_batch;
+	bool			workingset;
+	bool			in_thrashing;
+	unsigned long		in_memstall;
 };
 
 /*
diff --git a/mm/page_io.c b/mm/page_io.c
index c6824fcd483e..22e5ac1d298f 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -197,6 +197,19 @@ static void swap_zeromap_folio_clear(struct folio *folio)
 	swap_cluster_unlock(ci);
 }
 
+static bool swap_can_merge(struct swap_io_ctx *ctx, struct folio *folio,
+		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);
+
+	if (ctx->sis != sis)
+		return false;
+	return sis->ops->can_merge(folio, prev_folio, prev_folio_size, rw);
+}
+
 /*
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
@@ -218,6 +231,13 @@ int swap_writeout(struct swap_io_ctx *ctx, struct folio *folio)
 		goto out_unlock;
 	}
 
+	/*
+	 * Don't hold up a batch this folio can't join for the zero
+	 * check and possible compression. Submit it now.
+	 */
+	if (ctx->sio && !swap_can_merge(ctx, folio, WRITE))
+		swap_write_submit(ctx);
+
 	/*
 	 * Use the swap table zero mark to avoid doing IO for zero-filled
 	 * folios. The zero mark is protected by the cluster lock, which is
@@ -322,32 +342,15 @@ int sio_pool_init(void)
 	return 0;
 }
 
-static bool swap_can_merge(struct swap_io_ctx *ctx, struct folio *folio,
-		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);
-
-	if (ctx->sis != sis)
-		return false;
-	return sis->ops->can_merge(folio, prev_folio, prev_folio_size, rw);
-}
-
+/*
+ * Callers submit a pending batch that @folio can't join before adding
+ * it, see swap_writeout() and swap_read_folio().
+ */
 static void swap_add_folio(struct swap_io_ctx *ctx, struct folio *folio, int rw)
 {
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 	struct swap_iocb *sio = ctx->sio;
 
-	if (sio && !swap_can_merge(ctx, folio, rw)) {
-		if (rw == WRITE)
-			swap_write_submit(ctx);
-		else
-			swap_read_submit(ctx);
-		sio = ctx->sio;
-	}
-
 	if (!sio) {
 		ctx->sis = sis;
 		ctx->sio = sio = mempool_alloc(sio_pool, GFP_NOIO);
@@ -460,42 +463,45 @@ void swap_read_folio(struct swap_io_ctx *ctx, struct folio *folio)
 	struct swap_info_struct *sis = __swap_entry_to_info(folio->swap);
 	bool synchronous = sis->flags & SWP_SYNCHRONOUS_IO;
 	bool workingset = folio_test_workingset(folio);
-	unsigned long pflags;
-	bool in_thrashing;
 
 	VM_BUG_ON_FOLIO(!folio_test_swapcache(folio) && !synchronous, folio);
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
 
+	/*
+	 * Don't hold up a batch this folio can't join for its lookup
+	 * and possible decompression. Submit it now.
+	 */
+	if (ctx->sio && !swap_can_merge(ctx, folio, READ))
+		swap_read_submit(ctx);
+
 	/*
 	 * Count submission time as memory stall and delay. When the device
 	 * is congested, or the submitting cgroup IO-throttled, submission
-	 * can be a significant part of overall IO time.
+	 * can be a significant part of overall IO time. Reads are batched
+	 * and submitted later, so the windows close in swap_read_submit().
 	 */
-	if (workingset) {
-		delayacct_thrashing_start(&in_thrashing);
-		psi_memstall_enter(&pflags);
+	if (!ctx->in_batch) {
+		delayacct_swapin_start();
+		ctx->in_batch = true;
+	}
+	if (workingset && !ctx->workingset) {
+		delayacct_thrashing_start(&ctx->in_thrashing);
+		psi_memstall_enter(&ctx->in_memstall);
+		ctx->workingset = true;
 	}
-	delayacct_swapin_start();
 
 	if (swap_read_folio_zeromap(folio)) {
 		folio_unlock(folio);
-		goto finish;
+		return;
 	}
 
 	if (zswap_load(folio) != -ENOENT)
-		goto finish;
+		return;
 
 	/* We have to read from slower devices. Increase zswap protection. */
 	zswap_folio_swapin(folio);
 	swap_add_folio(ctx, folio, READ);
-
-finish:
-	if (workingset) {
-		delayacct_thrashing_end(&in_thrashing);
-		psi_memstall_leave(&pflags);
-	}
-	delayacct_swapin_end();
 }
 
 static void swap_write_end(struct swap_iocb *sio, bool failed)
@@ -709,9 +715,19 @@ void swap_write_submit(struct swap_io_ctx *ctx)
 void swap_read_submit(struct swap_io_ctx *ctx)
 {
 	if (!ctx->sio)
-		return;
+		goto out;
 	count_vm_events(NRSWPIN, 1);
 	ctx->sis->ops->submit_read(ctx);
 	ctx->sio = NULL;
 	ctx->sis = NULL;
+out:
+	if (ctx->workingset) {
+		delayacct_thrashing_end(&ctx->in_thrashing);
+		psi_memstall_leave(&ctx->in_memstall);
+		ctx->workingset = false;
+	}
+	if (ctx->in_batch) {
+		delayacct_swapin_end();
+		ctx->in_batch = false;
+	}
 }