+ mm-zswap-reuse-dstmem-when-decompress.patch added to mm-unstable branch

+ mm-zswap-reuse-dstmem-when-decompress.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/zswap: reuse dstmem when decompress
has been added to the -mm mm-unstable branch.  Its filename is
     mm-zswap-reuse-dstmem-when-decompress.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-zswap-reuse-dstmem-when-decompress.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Chengming Zhou <zhouchengming@bytedance.com>
Subject: mm/zswap: reuse dstmem when decompress
Date: Wed, 13 Dec 2023 04:17:58 +0000

Patch series "mm/zswap: dstmem reuse optimizations and cleanups".

The problem this series tries to optimize is that zswap_load() and
zswap_writeback_entry() have to malloc a temporary memory to support
!zpool_can_sleep_mapped().  We can avoid it by reusing the percpu
crypto_acomp_ctx->dstmem, which is also used by zswap_store() and
protected by the same percpu crypto_acomp_ctx->mutex.


This patch (of 5):

In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first
copy the entry->handle memory to a temporary memory, which is allocated
using kmalloc.

Obviously we can reuse the per-compressor dstmem to avoid allocating every
time, since it's percpu-compressor and protected in mutex.

Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v1-0-896763369d04@bytedance.com
Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v1-1-896763369d04@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Chris Li <chriscli@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |   29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

--- a/mm/zswap.c~mm-zswap-reuse-dstmem-when-decompress
+++ a/mm/zswap.c
@@ -1767,9 +1767,9 @@ bool zswap_load(struct folio *folio)
 	struct zswap_entry *entry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
+	unsigned int dlen = PAGE_SIZE;
+	u8 *src, *dst;
 	struct zpool *zpool;
-	unsigned int dlen;
 	bool ret;
 
 	VM_WARN_ON_ONCE(!folio_test_locked(folio));
@@ -1791,27 +1791,18 @@ bool zswap_load(struct folio *folio)
 		goto stats;
 	}
 
-	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
-
 	/* decompress */
-	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(acomp_ctx->mutex);
 
+	zpool = zswap_find_zpool(entry);
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(zpool, entry->handle);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1822,15 +1813,13 @@ bool zswap_load(struct folio *folio)
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
 
 	ret = true;
 stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
 	if (ret && zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
_

Patches currently in -mm which might be from zhouchengming@bytedance.com are

mm-zswap-reuse-dstmem-when-decompress.patch
mm-zswap-change-dstmem-size-to-one-page.patch
mm-zswap-refactor-out-__zswap_load.patch
mm-zswap-cleanup-zswap_load.patch
mm-zswap-cleanup-zswap_reclaim_entry.patch

+ mm-zswap-reuse-dstmem-when-decompress.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/zswap: reuse dstmem when decompress
has been added to the -mm mm-unstable branch.  Its filename is
     mm-zswap-reuse-dstmem-when-decompress.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-zswap-reuse-dstmem-when-decompress.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Chengming Zhou <zhouchengming@bytedance.com>
Subject: mm/zswap: reuse dstmem when decompress
Date: Mon, 18 Dec 2023 11:50:32 +0000

In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first
copy the entry->handle memory to a temporary memory, which is allocated
using kmalloc.

Obviously we can reuse the per-compressor dstmem to avoid allocating every
time, since it's percpu-compressor and protected in percpu mutex.

Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v3-2-4eac09b94ece@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Chris Li <chrisl@kernel.org>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |   44 ++++++++++++--------------------------------
 1 file changed, 12 insertions(+), 32 deletions(-)

--- a/mm/zswap.c~mm-zswap-reuse-dstmem-when-decompress
+++ a/mm/zswap.c
@@ -1417,19 +1417,13 @@ static int zswap_writeback_entry(struct
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct zpool *pool = zswap_find_zpool(entry);
 	bool page_was_allocated;
-	u8 *src, *tmp = NULL;
+	u8 *src;
 	unsigned int dlen;
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	if (!zpool_can_sleep_mapped(pool)) {
-		tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!tmp)
-			return -ENOMEM;
-	}
-
 	/* try to allocate swap cache page */
 	mpol = get_task_policy(current);
 	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
@@ -1465,15 +1459,15 @@ static int zswap_writeback_entry(struct
 	/* decompress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 	dlen = PAGE_SIZE;
+	mutex_lock(acomp_ctx->mutex);
 
 	src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(pool, entry->handle);
 	}
 
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1482,9 +1476,7 @@ static int zswap_writeback_entry(struct
 	dlen = acomp_ctx->req->dlen;
 	mutex_unlock(acomp_ctx->mutex);
 
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-	else
+	if (zpool_can_sleep_mapped(pool))
 		zpool_unmap_handle(pool, entry->handle);
 
 	BUG_ON(ret);
@@ -1503,9 +1495,6 @@ static int zswap_writeback_entry(struct
 	return ret;
 
 fail:
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-
 	/*
 	 * If we get here because the page is already in swapcache, a
 	 * load may be happening concurrently. It is safe and okay to
@@ -1766,7 +1755,7 @@ bool zswap_load(struct folio *folio)
 	struct zswap_entry *entry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
+	u8 *src, *dst;
 	struct zpool *zpool;
 	unsigned int dlen;
 	bool ret;
@@ -1791,26 +1780,19 @@ bool zswap_load(struct folio *folio)
 	}
 
 	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
 
 	/* decompress */
 	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(acomp_ctx->mutex);
 
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(zpool, entry->handle);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1821,15 +1803,13 @@ bool zswap_load(struct folio *folio)
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
 
 	ret = true;
 stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
 	if (ret && zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
_

Patches currently in -mm which might be from zhouchengming@bytedance.com are

mm-zswap-change-dstmem-size-to-one-page.patch
mm-zswap-reuse-dstmem-when-decompress.patch
mm-zswap-refactor-out-__zswap_load.patch
mm-zswap-cleanup-zswap_load.patch
mm-zswap-cleanup-zswap_writeback_entry.patch
mm-zswap-directly-use-percpu-mutex-and-buffer-in-load-store.patch

+ mm-zswap-reuse-dstmem-when-decompress.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/zswap: reuse dstmem when decompress
has been added to the -mm mm-unstable branch.  Its filename is
     mm-zswap-reuse-dstmem-when-decompress.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-zswap-reuse-dstmem-when-decompress.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Chengming Zhou <zhouchengming@bytedance.com>
Subject: mm/zswap: reuse dstmem when decompress
Date: Tue, 26 Dec 2023 15:54:09 +0000

In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first
copy the entry->handle memory to a temporary memory, which is allocated
using kmalloc.

Obviously we can reuse the per-compressor dstmem to avoid allocating every
time, since it's percpu-compressor and protected in percpu mutex.

Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v4-2-f228b059dd89@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Chris Li <chrisl@kernel.org> (Google)
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |   44 ++++++++++++--------------------------------
 1 file changed, 12 insertions(+), 32 deletions(-)

--- a/mm/zswap.c~mm-zswap-reuse-dstmem-when-decompress
+++ a/mm/zswap.c
@@ -1417,19 +1417,13 @@ static int zswap_writeback_entry(struct
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct zpool *pool = zswap_find_zpool(entry);
 	bool page_was_allocated;
-	u8 *src, *tmp = NULL;
+	u8 *src;
 	unsigned int dlen;
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	if (!zpool_can_sleep_mapped(pool)) {
-		tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!tmp)
-			return -ENOMEM;
-	}
-
 	/* try to allocate swap cache page */
 	mpol = get_task_policy(current);
 	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
@@ -1465,15 +1459,15 @@ static int zswap_writeback_entry(struct
 	/* decompress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 	dlen = PAGE_SIZE;
+	mutex_lock(acomp_ctx->mutex);
 
 	src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(pool, entry->handle);
 	}
 
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1482,9 +1476,7 @@ static int zswap_writeback_entry(struct
 	dlen = acomp_ctx->req->dlen;
 	mutex_unlock(acomp_ctx->mutex);
 
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-	else
+	if (zpool_can_sleep_mapped(pool))
 		zpool_unmap_handle(pool, entry->handle);
 
 	BUG_ON(ret);
@@ -1503,9 +1495,6 @@ static int zswap_writeback_entry(struct
 	return ret;
 
 fail:
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-
 	/*
 	 * If we get here because the page is already in swapcache, a
 	 * load may be happening concurrently. It is safe and okay to
@@ -1766,7 +1755,7 @@ bool zswap_load(struct folio *folio)
 	struct zswap_entry *entry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
+	u8 *src, *dst;
 	struct zpool *zpool;
 	unsigned int dlen;
 	bool ret;
@@ -1791,26 +1780,19 @@ bool zswap_load(struct folio *folio)
 	}
 
 	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
 
 	/* decompress */
 	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(acomp_ctx->mutex);
 
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(zpool, entry->handle);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1821,15 +1803,13 @@ bool zswap_load(struct folio *folio)
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
 
 	ret = true;
 stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
 	if (ret && zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
_

Patches currently in -mm which might be from zhouchengming@bytedance.com are

mm-zswap-change-dstmem-size-to-one-page.patch
mm-zswap-reuse-dstmem-when-decompress.patch
mm-zswap-refactor-out-__zswap_load.patch
mm-zswap-cleanup-zswap_load.patch
mm-zswap-cleanup-zswap_writeback_entry.patch
mm-zswap-change-per-cpu-mutex-and-buffer-to-per-acomp_ctx.patch

+ mm-zswap-reuse-dstmem-when-decompress.patch added to mm-unstable branch

[Andrew Morton]

The patch titled
     Subject: mm/zswap: reuse dstmem when decompress
has been added to the -mm mm-unstable branch.  Its filename is
     mm-zswap-reuse-dstmem-when-decompress.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-zswap-reuse-dstmem-when-decompress.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

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 via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Chengming Zhou <zhouchengming@bytedance.com>
Subject: mm/zswap: reuse dstmem when decompress
Date: Thu, 28 Dec 2023 09:45:42 +0000

Patch series "mm/zswap: dstmem reuse optimizations and cleanups", v5.

The problem this series tries to optimize is that zswap_load() and
zswap_writeback_entry() have to malloc a temporary memory to support
!zpool_can_sleep_mapped().  We can avoid it by reusing the percpu
crypto_acomp_ctx->dstmem, which is also used by zswap_store() and
protected by the same percpu crypto_acomp_ctx->mutex.


This patch (of 5):

In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first
copy the entry->handle memory to a temporary memory, which is allocated
using kmalloc.

Obviously we can reuse the per-compressor dstmem to avoid allocating every
time, since it's percpu-compressor and protected in percpu mutex.

Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v5-0-9382162bbf05@bytedance.com
Link: https://lkml.kernel.org/r/20231213-zswap-dstmem-v5-1-9382162bbf05@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Chris Li <chrisl@kernel.org> (Google)
Cc: Barry Song <21cnbao@gmail.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |   44 ++++++++++++--------------------------------
 1 file changed, 12 insertions(+), 32 deletions(-)

--- a/mm/zswap.c~mm-zswap-reuse-dstmem-when-decompress
+++ a/mm/zswap.c
@@ -1417,19 +1417,13 @@ static int zswap_writeback_entry(struct
 	struct crypto_acomp_ctx *acomp_ctx;
 	struct zpool *pool = zswap_find_zpool(entry);
 	bool page_was_allocated;
-	u8 *src, *tmp = NULL;
+	u8 *src;
 	unsigned int dlen;
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
 
-	if (!zpool_can_sleep_mapped(pool)) {
-		tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
-		if (!tmp)
-			return -ENOMEM;
-	}
-
 	/* try to allocate swap cache page */
 	mpol = get_task_policy(current);
 	page = __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
@@ -1465,15 +1459,15 @@ static int zswap_writeback_entry(struct
 	/* decompress */
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 	dlen = PAGE_SIZE;
+	mutex_lock(acomp_ctx->mutex);
 
 	src = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(pool, entry->handle);
 	}
 
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1482,9 +1476,7 @@ static int zswap_writeback_entry(struct
 	dlen = acomp_ctx->req->dlen;
 	mutex_unlock(acomp_ctx->mutex);
 
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-	else
+	if (zpool_can_sleep_mapped(pool))
 		zpool_unmap_handle(pool, entry->handle);
 
 	BUG_ON(ret);
@@ -1503,9 +1495,6 @@ static int zswap_writeback_entry(struct
 	return ret;
 
 fail:
-	if (!zpool_can_sleep_mapped(pool))
-		kfree(tmp);
-
 	/*
 	 * If we get here because the page is already in swapcache, a
 	 * load may be happening concurrently. It is safe and okay to
@@ -1767,7 +1756,7 @@ bool zswap_load(struct folio *folio)
 	struct zswap_entry *entry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst, *tmp;
+	u8 *src, *dst;
 	struct zpool *zpool;
 	unsigned int dlen;
 	bool ret;
@@ -1792,26 +1781,19 @@ bool zswap_load(struct folio *folio)
 	}
 
 	zpool = zswap_find_zpool(entry);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		tmp = kmalloc(entry->length, GFP_KERNEL);
-		if (!tmp) {
-			ret = false;
-			goto freeentry;
-		}
-	}
 
 	/* decompress */
 	dlen = PAGE_SIZE;
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(acomp_ctx->mutex);
 
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
+		memcpy(acomp_ctx->dstmem, src, entry->length);
+		src = acomp_ctx->dstmem;
 		zpool_unmap_handle(zpool, entry->handle);
 	}
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(acomp_ctx->mutex);
 	sg_init_one(&input, src, entry->length);
 	sg_init_table(&output, 1);
 	sg_set_page(&output, page, PAGE_SIZE, 0);
@@ -1822,15 +1804,13 @@ bool zswap_load(struct folio *folio)
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
-	else
-		kfree(tmp);
 
 	ret = true;
 stats:
 	count_vm_event(ZSWPIN);
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
-freeentry:
+
 	spin_lock(&tree->lock);
 	if (ret && zswap_exclusive_loads_enabled) {
 		zswap_invalidate_entry(tree, entry);
_

Patches currently in -mm which might be from zhouchengming@bytedance.com are

mm-zswap-reuse-dstmem-when-decompress.patch
mm-zswap-refactor-out-__zswap_load.patch
mm-zswap-cleanup-zswap_load.patch
mm-zswap-cleanup-zswap_writeback_entry.patch
mm-zswap-change-per-cpu-mutex-and-buffer-to-per-acomp_ctx.patch