+ mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch added to -mm tree

+ mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch added to -mm tree

[akpm]

The patch titled
     Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration
has been added to the -mm tree.  Its filename is
     mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.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: Barry Song <song.bao.hua@hisilicon.com>
Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration

Right now, all new ZIP drivers are using crypto_acomp APIs rather than
legacy crypto_comp APIs.  But zswap.c is still using the old APIs.  That
means zswap won't be able to use any new zip drivers in kernel.

This patch moves to use cryto_acomp APIs to fix the problem.  On the other
hand, tradiontal compressors like lz4,lzo etc have been wrapped into acomp
via scomp backend.  So platforms without async compressors can fallback to
use acomp via scomp backend.

Link: http://lkml.kernel.org/r/20200620235033.8420-1-song.bao.hua@hisilicon.com
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Cc: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David S. Miller <davem@davemloft.net>
Cc: Mahipal Challa <mahipalreddy2006@gmail.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Zhou Wang <wangzhou1@hisilicon.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |  153 ++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 110 insertions(+), 43 deletions(-)

--- a/mm/zswap.c~mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration
+++ a/mm/zswap.c
@@ -24,8 +24,10 @@
 #include <linux/rbtree.h>
 #include <linux/swap.h>
 #include <linux/crypto.h>
+#include <linux/scatterlist.h>
 #include <linux/mempool.h>
 #include <linux/zpool.h>
+#include <crypto/acompress.h>
 
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
@@ -127,9 +129,17 @@ module_param_named(same_filled_pages_ena
 * data structures
 **********************************/
 
+struct crypto_acomp_ctx {
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+	struct crypto_wait wait;
+	u8 *dstmem;
+	struct mutex mutex;
+};
+
 struct zswap_pool {
 	struct zpool *zpool;
-	struct crypto_comp * __percpu *tfm;
+	struct crypto_acomp_ctx * __percpu *acomp_ctx;
 	struct kref kref;
 	struct list_head list;
 	struct work_struct release_work;
@@ -415,30 +425,60 @@ static int zswap_dstmem_dead(unsigned in
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+	struct crypto_acomp_ctx *acomp_ctx;
 
-	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+	if (WARN_ON(*per_cpu_ptr(pool->acomp_ctx, cpu)))
 		return 0;
 
-	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-	if (IS_ERR_OR_NULL(tfm)) {
-		pr_err("could not alloc crypto comp %s : %ld\n",
-		       pool->tfm_name, PTR_ERR(tfm));
+	acomp_ctx = kzalloc(sizeof(*acomp_ctx), GFP_KERNEL);
+	if (IS_ERR_OR_NULL(acomp_ctx)) {
+		pr_err("Could not initialize acomp_ctx\n");
+		return -ENOMEM;
+	}
+	acomp = crypto_alloc_acomp(pool->tfm_name, 0, 0);
+	if (IS_ERR_OR_NULL(acomp)) {
+		pr_err("could not alloc crypto acomp %s : %ld\n",
+				pool->tfm_name, PTR_ERR(acomp));
+		return -ENOMEM;
+	}
+	acomp_ctx->acomp = acomp;
+
+	req = acomp_request_alloc(acomp_ctx->acomp);
+	if (IS_ERR_OR_NULL(req)) {
+		pr_err("could not alloc crypto acomp %s : %ld\n",
+		       pool->tfm_name, PTR_ERR(acomp));
 		return -ENOMEM;
 	}
-	*per_cpu_ptr(pool->tfm, cpu) = tfm;
+	acomp_ctx->req = req;
+
+	mutex_init(&acomp_ctx->mutex);
+	crypto_init_wait(&acomp_ctx->wait);
+	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   crypto_req_done, &acomp_ctx->wait);
+
+	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
+	*per_cpu_ptr(pool->acomp_ctx, cpu) = acomp_ctx;
+
 	return 0;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	acomp_ctx = *per_cpu_ptr(pool->acomp_ctx, cpu);
+	if (!IS_ERR_OR_NULL(acomp_ctx)) {
+		if (!IS_ERR_OR_NULL(acomp_ctx->req))
+			acomp_request_free(acomp_ctx->req);
+		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
+			crypto_free_acomp(acomp_ctx->acomp);
+		kfree(acomp_ctx);
+	}
+	*per_cpu_ptr(pool->acomp_ctx, cpu) = NULL;
 
-	tfm = *per_cpu_ptr(pool->tfm, cpu);
-	if (!IS_ERR_OR_NULL(tfm))
-		crypto_free_comp(tfm);
-	*per_cpu_ptr(pool->tfm, cpu) = NULL;
 	return 0;
 }
 
@@ -561,8 +601,9 @@ static struct zswap_pool *zswap_pool_cre
 	pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
 
 	strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
-	pool->tfm = alloc_percpu(struct crypto_comp *);
-	if (!pool->tfm) {
+
+	pool->acomp_ctx = alloc_percpu(struct crypto_acomp_ctx *);
+	if (!pool->acomp_ctx) {
 		pr_err("percpu alloc failed\n");
 		goto error;
 	}
@@ -585,7 +626,7 @@ static struct zswap_pool *zswap_pool_cre
 	return pool;
 
 error:
-	free_percpu(pool->tfm);
+	free_percpu(pool->acomp_ctx);
 	if (pool->zpool)
 		zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -596,14 +637,14 @@ static __init struct zswap_pool *__zswap
 {
 	bool has_comp, has_zpool;
 
-	has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+	has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	if (!has_comp && strcmp(zswap_compressor,
 				CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) {
 		pr_err("compressor %s not available, using default %s\n",
 		       zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT);
 		param_free_charp(&zswap_compressor);
 		zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
-		has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+		has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	}
 	if (!has_comp) {
 		pr_err("default compressor %s not available\n",
@@ -639,7 +680,7 @@ static void zswap_pool_destroy(struct zs
 	zswap_pool_debug("destroying", pool);
 
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
-	free_percpu(pool->tfm);
+	free_percpu(pool->acomp_ctx);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
 }
@@ -723,7 +764,7 @@ static int __zswap_param_set(const char
 		}
 		type = s;
 	} else if (!compressor) {
-		if (!crypto_has_comp(s, 0, 0)) {
+		if (!crypto_has_acomp(s, 0, 0)) {
 			pr_err("compressor %s not available\n", s);
 			return -ENOENT;
 		}
@@ -774,7 +815,7 @@ static int __zswap_param_set(const char
 		 * failed, maybe both compressor and zpool params were bad.
 		 * Allow changing this param, so pool creation will succeed
 		 * when the other param is changed. We already verified this
-		 * param is ok in the zpool_has_pool() or crypto_has_comp()
+		 * param is ok in the zpool_has_pool() or crypto_has_acomp()
 		 * checks above.
 		 */
 		ret = param_set_charp(s, kp);
@@ -876,7 +917,9 @@ static int zswap_writeback_entry(struct
 	pgoff_t offset;
 	struct zswap_entry *entry;
 	struct page *page;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+
 	u8 *src, *dst;
 	unsigned int dlen;
 	int ret;
@@ -916,14 +959,21 @@ static int zswap_writeback_entry(struct
 
 	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
 		/* decompress */
+		acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+
 		dlen = PAGE_SIZE;
 		src = (u8 *)zhdr + sizeof(struct zswap_header);
-		dst = kmap_atomic(page);
-		tfm = *get_cpu_ptr(entry->pool->tfm);
-		ret = crypto_comp_decompress(tfm, src, entry->length,
-					     dst, &dlen);
-		put_cpu_ptr(entry->pool->tfm);
-		kunmap_atomic(dst);
+		dst = kmap(page);
+
+		mutex_lock(&acomp_ctx->mutex);
+		sg_init_one(&input, src, entry->length);
+		sg_init_one(&output, dst, dlen);
+		acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+		ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+		dlen = acomp_ctx->req->dlen;
+		mutex_unlock(&acomp_ctx->mutex);
+
+		kunmap(page);
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -1004,7 +1054,8 @@ static int zswap_frontswap_store(unsigne
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry, *dupentry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	int ret;
 	unsigned int hlen, dlen = PAGE_SIZE;
 	unsigned long handle, value;
@@ -1074,12 +1125,20 @@ static int zswap_frontswap_store(unsigne
 	}
 
 	/* compress */
-	dst = get_cpu_var(zswap_dstmem);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	src = kmap_atomic(page);
-	ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
-	kunmap_atomic(src);
-	put_cpu_ptr(entry->pool->tfm);
+	acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+
+	mutex_lock(&acomp_ctx->mutex);
+
+	src = kmap(page);
+	dst = acomp_ctx->dstmem;
+	sg_init_one(&input, src, PAGE_SIZE);
+	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	sg_init_one(&output, dst, PAGE_SIZE * 2);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
+	ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
+	dlen = acomp_ctx->req->dlen;
+	kunmap(page);
+
 	if (ret) {
 		ret = -EINVAL;
 		goto put_dstmem;
@@ -1103,7 +1162,7 @@ static int zswap_frontswap_store(unsigne
 	memcpy(buf, &zhdr, hlen);
 	memcpy(buf + hlen, dst, dlen);
 	zpool_unmap_handle(entry->pool->zpool, handle);
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->offset = offset;
@@ -1131,7 +1190,7 @@ insert_entry:
 	return 0;
 
 put_dstmem:
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(&acomp_ctx->mutex);
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1148,7 +1207,8 @@ static int zswap_frontswap_load(unsigned
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src, *dst;
 	unsigned int dlen;
 	int ret;
@@ -1175,11 +1235,18 @@ static int zswap_frontswap_load(unsigned
 	src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
 	if (zpool_evictable(entry->pool->zpool))
 		src += sizeof(struct zswap_header);
-	dst = kmap_atomic(page);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
-	put_cpu_ptr(entry->pool->tfm);
-	kunmap_atomic(dst);
+	dst = kmap(page);
+
+	acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(&acomp_ctx->mutex);
+	sg_init_one(&input, src, entry->length);
+	sg_init_one(&output, dst, dlen);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+	dlen = acomp_ctx->req->dlen;
+	mutex_unlock(&acomp_ctx->mutex);
+
+	kunmap(page);
 	zpool_unmap_handle(entry->pool->zpool, entry->handle);
 	BUG_ON(ret);
 
_

Patches currently in -mm which might be from song.bao.hua@hisilicon.com are

mm-cma-fix-the-name-of-cma-areas.patch
mm-hugetlb-fix-the-name-of-hugetlb-cma.patch
mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch

incoming

[Andrew Morton]

5 patches, based on cdd3bb54332f82295ed90cd0c09c78cd0c0ee822.

Subsystems affected by this patch series:

  mm/hugetlb
  samples
  mm/cma
  mm/vmalloc
  mm/pagealloc

Subsystem: mm/hugetlb

    Mike Kravetz <mike.kravetz@oracle.com>:
      mm/hugetlb.c: fix pages per hugetlb calculation

Subsystem: samples

    Kees Cook <keescook@chromium.org>:
      samples/vfs: avoid warning in statx override

Subsystem: mm/cma

    Barry Song <song.bao.hua@hisilicon.com>:
      mm/cma.c: use exact_nid true to fix possible per-numa cma leak

Subsystem: mm/vmalloc

    Christoph Hellwig <hch@lst.de>:
      vmalloc: fix the owner argument for the new __vmalloc_node_range callers

Subsystem: mm/pagealloc

    Joel Savitz <jsavitz@redhat.com>:
      mm/page_alloc: fix documentation error

 arch/arm64/kernel/probes/kprobes.c |    2 +-
 arch/x86/hyperv/hv_init.c          |    3 ++-
 kernel/module.c                    |    2 +-
 mm/cma.c                           |    4 ++--
 mm/hugetlb.c                       |    2 +-
 mm/page_alloc.c                    |    2 +-
 samples/vfs/test-statx.c           |    2 ++
 7 files changed, 10 insertions(+), 7 deletions(-)

+ mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch added to -mm tree

[Andrew Morton]

The patch titled
     Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration
has been added to the -mm tree.  Its filename is
     mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch

This patch should soon appear at
    http://ozlabs.org/~akpm/mmots/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch
and later at
    http://ozlabs.org/~akpm/mmotm/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.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: Barry Song <song.bao.hua@hisilicon.com>
Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration

Right now, all new ZIP drivers are using crypto_acomp APIs rather than
legacy crypto_comp APIs.  But zswap.c is still using the old APIs.  That
means zswap won't be able to use any new zip drivers in kernel.

This patch moves to use cryto_acomp APIs to fix the problem.  On the other
hand, tradiontal compressors like lz4,lzo etc have been wrapped into acomp
via scomp backend.  So platforms without async compressors can fallback to
use acomp via scomp backend.

It is probably the first real user to use acomp but perhaps not a good
example to demonstrate how multiple acomp requests can be executed in
parallel in one acomp instance.  frontswap is doing page load and store
page by page.  It doesn't have a queuing or buffering mechinism to permit
multiple pages to do frontswap simultaneously in one thread.  However this
patch creates multiple acomp instances, so multiple threads running on
multiple different cpus can actually do (de)compression parallelly,
leveraging the power of multiple ZIP hardware queues.  This is also
consistent with frontswap's page management model.

On the other hand, the current zswap implementation has some per-cpu
global resource like zswap_dstmem.  So we create acomp instances in number
of CPUs just like before, zswap created comp instances in number of CPUs.

Link: http://lkml.kernel.org/r/20200707125210.33256-1-song.bao.hua@hisilicon.com
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Cc: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David S. Miller <davem@davemloft.net>
Cc: Mahipal Challa <mahipalreddy2006@gmail.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Cc: Zhou Wang <wangzhou1@hisilicon.com>
Cc: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |  177 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 134 insertions(+), 43 deletions(-)

--- a/mm/zswap.c~mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration
+++ a/mm/zswap.c
@@ -24,8 +24,10 @@
 #include <linux/rbtree.h>
 #include <linux/swap.h>
 #include <linux/crypto.h>
+#include <linux/scatterlist.h>
 #include <linux/mempool.h>
 #include <linux/zpool.h>
+#include <crypto/acompress.h>
 
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
@@ -127,9 +129,17 @@ module_param_named(same_filled_pages_ena
 * data structures
 **********************************/
 
+struct crypto_acomp_ctx {
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+	struct crypto_wait wait;
+	u8 *dstmem;
+	struct mutex mutex;
+};
+
 struct zswap_pool {
 	struct zpool *zpool;
-	struct crypto_comp * __percpu *tfm;
+	struct crypto_acomp_ctx * __percpu *acomp_ctx;
 	struct kref kref;
 	struct list_head list;
 	struct work_struct release_work;
@@ -415,30 +425,73 @@ static int zswap_dstmem_dead(unsigned in
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+	struct crypto_acomp_ctx *acomp_ctx;
+	int ret;
 
-	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+	if (WARN_ON(*per_cpu_ptr(pool->acomp_ctx, cpu)))
 		return 0;
 
-	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-	if (IS_ERR_OR_NULL(tfm)) {
-		pr_err("could not alloc crypto comp %s : %ld\n",
-		       pool->tfm_name, PTR_ERR(tfm));
+	acomp_ctx = kzalloc(sizeof(*acomp_ctx), GFP_KERNEL);
+	if (!acomp_ctx)
 		return -ENOMEM;
+
+	acomp = crypto_alloc_acomp(pool->tfm_name, 0, 0);
+	if (IS_ERR(acomp)) {
+		pr_err("could not alloc crypto acomp %s : %ld\n",
+				pool->tfm_name, PTR_ERR(acomp));
+		ret = PTR_ERR(acomp);
+		goto free_ctx;
+	}
+	acomp_ctx->acomp = acomp;
+
+	req = acomp_request_alloc(acomp_ctx->acomp);
+	if (!req) {
+		pr_err("could not alloc crypto acomp_request %s\n",
+		       pool->tfm_name);
+		ret = -ENOMEM;
+		goto free_acomp;
 	}
-	*per_cpu_ptr(pool->tfm, cpu) = tfm;
+	acomp_ctx->req = req;
+
+	mutex_init(&acomp_ctx->mutex);
+	crypto_init_wait(&acomp_ctx->wait);
+	/*
+	 * if the backend of acomp is async zip, crypto_req_done() will wakeup
+	 * crypto_wait_req(); if the backend of acomp is scomp, the callback
+	 * won't be called, crypto_wait_req() will return without blocking.
+	 */
+	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   crypto_req_done, &acomp_ctx->wait);
+
+	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
+	*per_cpu_ptr(pool->acomp_ctx, cpu) = acomp_ctx;
+
 	return 0;
+
+free_acomp:
+	crypto_free_acomp(acomp_ctx->acomp);
+free_ctx:
+	kfree(acomp_ctx);
+	return ret;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	acomp_ctx = *per_cpu_ptr(pool->acomp_ctx, cpu);
+	if (!IS_ERR_OR_NULL(acomp_ctx)) {
+		if (!IS_ERR_OR_NULL(acomp_ctx->req))
+			acomp_request_free(acomp_ctx->req);
+		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
+			crypto_free_acomp(acomp_ctx->acomp);
+		kfree(acomp_ctx);
+	}
+	*per_cpu_ptr(pool->acomp_ctx, cpu) = NULL;
 
-	tfm = *per_cpu_ptr(pool->tfm, cpu);
-	if (!IS_ERR_OR_NULL(tfm))
-		crypto_free_comp(tfm);
-	*per_cpu_ptr(pool->tfm, cpu) = NULL;
 	return 0;
 }
 
@@ -561,8 +614,9 @@ static struct zswap_pool *zswap_pool_cre
 	pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
 
 	strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
-	pool->tfm = alloc_percpu(struct crypto_comp *);
-	if (!pool->tfm) {
+
+	pool->acomp_ctx = alloc_percpu(struct crypto_acomp_ctx *);
+	if (!pool->acomp_ctx) {
 		pr_err("percpu alloc failed\n");
 		goto error;
 	}
@@ -585,7 +639,7 @@ static struct zswap_pool *zswap_pool_cre
 	return pool;
 
 error:
-	free_percpu(pool->tfm);
+	free_percpu(pool->acomp_ctx);
 	if (pool->zpool)
 		zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -596,14 +650,14 @@ static __init struct zswap_pool *__zswap
 {
 	bool has_comp, has_zpool;
 
-	has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+	has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	if (!has_comp && strcmp(zswap_compressor,
 				CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) {
 		pr_err("compressor %s not available, using default %s\n",
 		       zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT);
 		param_free_charp(&zswap_compressor);
 		zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
-		has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+		has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	}
 	if (!has_comp) {
 		pr_err("default compressor %s not available\n",
@@ -639,7 +693,7 @@ static void zswap_pool_destroy(struct zs
 	zswap_pool_debug("destroying", pool);
 
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
-	free_percpu(pool->tfm);
+	free_percpu(pool->acomp_ctx);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
 }
@@ -723,7 +777,7 @@ static int __zswap_param_set(const char
 		}
 		type = s;
 	} else if (!compressor) {
-		if (!crypto_has_comp(s, 0, 0)) {
+		if (!crypto_has_acomp(s, 0, 0)) {
 			pr_err("compressor %s not available\n", s);
 			return -ENOENT;
 		}
@@ -774,7 +828,7 @@ static int __zswap_param_set(const char
 		 * failed, maybe both compressor and zpool params were bad.
 		 * Allow changing this param, so pool creation will succeed
 		 * when the other param is changed. We already verified this
-		 * param is ok in the zpool_has_pool() or crypto_has_comp()
+		 * param is ok in the zpool_has_pool() or crypto_has_acomp()
 		 * checks above.
 		 */
 		ret = param_set_charp(s, kp);
@@ -876,7 +930,9 @@ static int zswap_writeback_entry(struct
 	pgoff_t offset;
 	struct zswap_entry *entry;
 	struct page *page;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+
 	u8 *src, *dst;
 	unsigned int dlen;
 	int ret;
@@ -916,14 +972,21 @@ static int zswap_writeback_entry(struct
 
 	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
 		/* decompress */
+		acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+
 		dlen = PAGE_SIZE;
 		src = (u8 *)zhdr + sizeof(struct zswap_header);
-		dst = kmap_atomic(page);
-		tfm = *get_cpu_ptr(entry->pool->tfm);
-		ret = crypto_comp_decompress(tfm, src, entry->length,
-					     dst, &dlen);
-		put_cpu_ptr(entry->pool->tfm);
-		kunmap_atomic(dst);
+		dst = kmap(page);
+
+		mutex_lock(&acomp_ctx->mutex);
+		sg_init_one(&input, src, entry->length);
+		sg_init_one(&output, dst, dlen);
+		acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+		ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+		dlen = acomp_ctx->req->dlen;
+		mutex_unlock(&acomp_ctx->mutex);
+
+		kunmap(page);
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -1004,7 +1067,8 @@ static int zswap_frontswap_store(unsigne
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry, *dupentry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	int ret;
 	unsigned int hlen, dlen = PAGE_SIZE;
 	unsigned long handle, value;
@@ -1074,12 +1138,32 @@ static int zswap_frontswap_store(unsigne
 	}
 
 	/* compress */
-	dst = get_cpu_var(zswap_dstmem);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	src = kmap_atomic(page);
-	ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
-	kunmap_atomic(src);
-	put_cpu_ptr(entry->pool->tfm);
+	acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+
+	mutex_lock(&acomp_ctx->mutex);
+
+	src = kmap(page);
+	dst = acomp_ctx->dstmem;
+	sg_init_one(&input, src, PAGE_SIZE);
+	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	sg_init_one(&output, dst, PAGE_SIZE * 2);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
+	/*
+	 * it maybe looks a little bit silly that we send an asynchronous request,
+	 * then wait for its completion synchronously. This makes the process look
+	 * synchronous in fact.
+	 * Theoretically, acomp supports users send multiple acomp requests in one
+	 * acomp instance, then get those requests done simultaneously. but in this
+	 * case, frontswap actually does store and load page by page, there is no
+	 * existing method to send the second page before the first page is done
+	 * in one thread doing frontswap.
+	 * but in different threads running on different cpu, we have different
+	 * acomp instance, so multiple threads can do (de)compression in parallel.
+	 */
+	ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
+	dlen = acomp_ctx->req->dlen;
+	kunmap(page);
+
 	if (ret) {
 		ret = -EINVAL;
 		goto put_dstmem;
@@ -1103,7 +1187,7 @@ static int zswap_frontswap_store(unsigne
 	memcpy(buf, &zhdr, hlen);
 	memcpy(buf + hlen, dst, dlen);
 	zpool_unmap_handle(entry->pool->zpool, handle);
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(&acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->offset = offset;
@@ -1131,7 +1215,7 @@ insert_entry:
 	return 0;
 
 put_dstmem:
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(&acomp_ctx->mutex);
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1148,7 +1232,8 @@ static int zswap_frontswap_load(unsigned
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src, *dst;
 	unsigned int dlen;
 	int ret;
@@ -1175,11 +1260,17 @@ static int zswap_frontswap_load(unsigned
 	src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
 	if (zpool_evictable(entry->pool->zpool))
 		src += sizeof(struct zswap_header);
-	dst = kmap_atomic(page);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
-	put_cpu_ptr(entry->pool->tfm);
-	kunmap_atomic(dst);
+	dst = kmap(page);
+
+	acomp_ctx = *this_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(&acomp_ctx->mutex);
+	sg_init_one(&input, src, entry->length);
+	sg_init_one(&output, dst, dlen);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+	mutex_unlock(&acomp_ctx->mutex);
+
+	kunmap(page);
 	zpool_unmap_handle(entry->pool->zpool, entry->handle);
 	BUG_ON(ret);
 
_

Patches currently in -mm which might be from song.bao.hua@hisilicon.com are

mm-cma-fix-the-name-of-cma-areas.patch
mm-hugetlb-fix-the-name-of-hugetlb-cma.patch
mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch

+ mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch added to -mm tree

[akpm]

The patch titled
     Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration
has been added to the -mm tree.  Its filename is
     mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch

This patch should soon appear at
    https://ozlabs.org/~akpm/mmots/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch
and later at
    https://ozlabs.org/~akpm/mmotm/broken-out/mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.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: Barry Song <song.bao.hua@hisilicon.com>
Subject: mm/zswap: move to use crypto_acomp API for hardware acceleration

Right now, all new ZIP drivers are adapted to crypto_acomp APIs rather
than legacy crypto_comp APIs.  Tradiontal ZIP drivers like lz4,lzo etc
have been also wrapped into acomp via scomp backend.  But zswap.c is still
using the old APIs.  That means zswap won't be able to work on any new ZIP
drivers in kernel.

This patch moves to use cryto_acomp APIs to fix the disconnected bridge
between new ZIP drivers and zswap.  It is probably the first real user to
use acomp but perhaps not a good example to demonstrate how multiple acomp
requests can be executed in parallel in one acomp instance.  frontswap is
doing page load and store page by page synchronously.  swap_writepage()
depends on the completion of frontswap_store() to decide if it should call
__swap_writepage() to swap to disk.

However this patch creates multiple acomp instances, so multiple threads
running on multiple different cpus can actually do (de)compression
parallelly, leveraging the power of multiple ZIP hardware queues.  This is
also consistent with frontswap's page management model.

The old zswap code uses atomic context and avoids the race conditions
while shared resources like zswap_dstmem are accessed.  Here since acomp
can sleep, per-cpu mutex is used to replace preemption-disable.

While it is possible to make mm/page_io.c and mm/frontswap.c support async
(de)compression in some way, the entire design requires careful thinking
and performance evaluation.  For the first step, the base with fixed
connection between ZIP drivers and zswap should be built.

Link: https://lkml.kernel.org/r/20201107065332.26992-1-song.bao.hua@hisilicon.com
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Acked-by: Vitaly Wool <vitalywool@gmail.com>
Cc: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David S. Miller <davem@davemloft.net>
Cc: Mahipal Challa <mahipalreddy2006@gmail.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Zhou Wang <wangzhou1@hisilicon.com>
Cc: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/zswap.c |  185 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 138 insertions(+), 47 deletions(-)

--- a/mm/zswap.c~mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration
+++ a/mm/zswap.c
@@ -24,8 +24,10 @@
 #include <linux/rbtree.h>
 #include <linux/swap.h>
 #include <linux/crypto.h>
+#include <linux/scatterlist.h>
 #include <linux/mempool.h>
 #include <linux/zpool.h>
+#include <crypto/acompress.h>
 
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
@@ -127,9 +129,17 @@ module_param_named(same_filled_pages_ena
 * data structures
 **********************************/
 
+struct crypto_acomp_ctx {
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+	struct crypto_wait wait;
+	u8 *dstmem;
+	struct mutex *mutex;
+};
+
 struct zswap_pool {
 	struct zpool *zpool;
-	struct crypto_comp * __percpu *tfm;
+	struct crypto_acomp_ctx __percpu *acomp_ctx;
 	struct kref kref;
 	struct list_head list;
 	struct work_struct release_work;
@@ -388,23 +398,43 @@ static struct zswap_entry *zswap_entry_f
 * per-cpu code
 **********************************/
 static DEFINE_PER_CPU(u8 *, zswap_dstmem);
+/*
+ * If users dynamically change the zpool type and compressor at runtime, i.e.
+ * zswap is running, zswap can have more than one zpool on one cpu, but they
+ * are sharing dtsmem. So we need this mutex to be per-cpu.
+ */
+static DEFINE_PER_CPU(struct mutex *, zswap_mutex);
 
 static int zswap_dstmem_prepare(unsigned int cpu)
 {
+	struct mutex *mutex;
 	u8 *dst;
 
 	dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
 	if (!dst)
 		return -ENOMEM;
 
+	mutex = kmalloc_node(sizeof(*mutex), GFP_KERNEL, cpu_to_node(cpu));
+	if (!mutex) {
+		kfree(dst);
+		return -ENOMEM;
+	}
+
+	mutex_init(mutex);
 	per_cpu(zswap_dstmem, cpu) = dst;
+	per_cpu(zswap_mutex, cpu) = mutex;
 	return 0;
 }
 
 static int zswap_dstmem_dead(unsigned int cpu)
 {
+	struct mutex *mutex;
 	u8 *dst;
 
+	mutex = per_cpu(zswap_mutex, cpu);
+	kfree(mutex);
+	per_cpu(zswap_mutex, cpu) = NULL;
+
 	dst = per_cpu(zswap_dstmem, cpu);
 	kfree(dst);
 	per_cpu(zswap_dstmem, cpu) = NULL;
@@ -415,30 +445,54 @@ static int zswap_dstmem_dead(unsigned in
 static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
-
-	if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
-		return 0;
-
-	tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
-	if (IS_ERR(tfm)) {
-		pr_err("could not alloc crypto comp %s : %ld\n",
-		       pool->tfm_name, PTR_ERR(tfm));
+	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
+	struct crypto_acomp *acomp;
+	struct acomp_req *req;
+
+	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
+	if (IS_ERR(acomp)) {
+		pr_err("could not alloc crypto acomp %s : %ld\n",
+				pool->tfm_name, PTR_ERR(acomp));
+		return PTR_ERR(acomp);
+	}
+	acomp_ctx->acomp = acomp;
+
+	req = acomp_request_alloc(acomp_ctx->acomp);
+	if (!req) {
+		pr_err("could not alloc crypto acomp_request %s\n",
+		       pool->tfm_name);
+		crypto_free_acomp(acomp_ctx->acomp);
 		return -ENOMEM;
 	}
-	*per_cpu_ptr(pool->tfm, cpu) = tfm;
+	acomp_ctx->req = req;
+
+	crypto_init_wait(&acomp_ctx->wait);
+	/*
+	 * if the backend of acomp is async zip, crypto_req_done() will wakeup
+	 * crypto_wait_req(); if the backend of acomp is scomp, the callback
+	 * won't be called, crypto_wait_req() will return without blocking.
+	 */
+	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				   crypto_req_done, &acomp_ctx->wait);
+
+	acomp_ctx->mutex = per_cpu(zswap_mutex, cpu);
+	acomp_ctx->dstmem = per_cpu(zswap_dstmem, cpu);
+
 	return 0;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
-	struct crypto_comp *tfm;
+	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
+
+	if (!IS_ERR_OR_NULL(acomp_ctx)) {
+		if (!IS_ERR_OR_NULL(acomp_ctx->req))
+			acomp_request_free(acomp_ctx->req);
+		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
+			crypto_free_acomp(acomp_ctx->acomp);
+	}
 
-	tfm = *per_cpu_ptr(pool->tfm, cpu);
-	if (!IS_ERR_OR_NULL(tfm))
-		crypto_free_comp(tfm);
-	*per_cpu_ptr(pool->tfm, cpu) = NULL;
 	return 0;
 }
 
@@ -561,8 +615,9 @@ static struct zswap_pool *zswap_pool_cre
 	pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
 
 	strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
-	pool->tfm = alloc_percpu(struct crypto_comp *);
-	if (!pool->tfm) {
+
+	pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx);
+	if (!pool->acomp_ctx) {
 		pr_err("percpu alloc failed\n");
 		goto error;
 	}
@@ -585,7 +640,8 @@ static struct zswap_pool *zswap_pool_cre
 	return pool;
 
 error:
-	free_percpu(pool->tfm);
+	if (pool->acomp_ctx)
+		free_percpu(pool->acomp_ctx);
 	if (pool->zpool)
 		zpool_destroy_pool(pool->zpool);
 	kfree(pool);
@@ -596,14 +652,14 @@ static __init struct zswap_pool *__zswap
 {
 	bool has_comp, has_zpool;
 
-	has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+	has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	if (!has_comp && strcmp(zswap_compressor,
 				CONFIG_ZSWAP_COMPRESSOR_DEFAULT)) {
 		pr_err("compressor %s not available, using default %s\n",
 		       zswap_compressor, CONFIG_ZSWAP_COMPRESSOR_DEFAULT);
 		param_free_charp(&zswap_compressor);
 		zswap_compressor = CONFIG_ZSWAP_COMPRESSOR_DEFAULT;
-		has_comp = crypto_has_comp(zswap_compressor, 0, 0);
+		has_comp = crypto_has_acomp(zswap_compressor, 0, 0);
 	}
 	if (!has_comp) {
 		pr_err("default compressor %s not available\n",
@@ -639,7 +695,7 @@ static void zswap_pool_destroy(struct zs
 	zswap_pool_debug("destroying", pool);
 
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
-	free_percpu(pool->tfm);
+	free_percpu(pool->acomp_ctx);
 	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
 }
@@ -723,7 +779,7 @@ static int __zswap_param_set(const char
 		}
 		type = s;
 	} else if (!compressor) {
-		if (!crypto_has_comp(s, 0, 0)) {
+		if (!crypto_has_acomp(s, 0, 0)) {
 			pr_err("compressor %s not available\n", s);
 			return -ENOENT;
 		}
@@ -774,7 +830,7 @@ static int __zswap_param_set(const char
 		 * failed, maybe both compressor and zpool params were bad.
 		 * Allow changing this param, so pool creation will succeed
 		 * when the other param is changed. We already verified this
-		 * param is ok in the zpool_has_pool() or crypto_has_comp()
+		 * param is ok in the zpool_has_pool() or crypto_has_acomp()
 		 * checks above.
 		 */
 		ret = param_set_charp(s, kp);
@@ -876,8 +932,10 @@ static int zswap_writeback_entry(struct
 	pgoff_t offset;
 	struct zswap_entry *entry;
 	struct page *page;
-	struct crypto_comp *tfm;
-	u8 *src, *dst;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	u8 *src;
 	unsigned int dlen;
 	int ret;
 	struct writeback_control wbc = {
@@ -916,14 +974,20 @@ static int zswap_writeback_entry(struct
 
 	case ZSWAP_SWAPCACHE_NEW: /* page is locked */
 		/* decompress */
+		acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+
 		dlen = PAGE_SIZE;
 		src = (u8 *)zhdr + sizeof(struct zswap_header);
-		dst = kmap_atomic(page);
-		tfm = *get_cpu_ptr(entry->pool->tfm);
-		ret = crypto_comp_decompress(tfm, src, entry->length,
-					     dst, &dlen);
-		put_cpu_ptr(entry->pool->tfm);
-		kunmap_atomic(dst);
+
+		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);
+		acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+		ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+		dlen = acomp_ctx->req->dlen;
+		mutex_unlock(acomp_ctx->mutex);
+
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -1004,7 +1068,8 @@ static int zswap_frontswap_store(unsigne
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry, *dupentry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	int ret;
 	unsigned int hlen, dlen = PAGE_SIZE;
 	unsigned long handle, value;
@@ -1074,12 +1139,32 @@ static int zswap_frontswap_store(unsigne
 	}
 
 	/* compress */
-	dst = get_cpu_var(zswap_dstmem);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	src = kmap_atomic(page);
-	ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
-	kunmap_atomic(src);
-	put_cpu_ptr(entry->pool->tfm);
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+
+	mutex_lock(acomp_ctx->mutex);
+
+	dst = acomp_ctx->dstmem;
+	sg_init_table(&input, 1);
+	sg_set_page(&input, page, PAGE_SIZE, 0);
+
+	/* zswap_dstmem is of size (PAGE_SIZE * 2). Reflect same in sg_list */
+	sg_init_one(&output, dst, PAGE_SIZE * 2);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
+	/*
+	 * it maybe looks a little bit silly that we send an asynchronous request,
+	 * then wait for its completion synchronously. This makes the process look
+	 * synchronous in fact.
+	 * Theoretically, acomp supports users send multiple acomp requests in one
+	 * acomp instance, then get those requests done simultaneously. but in this
+	 * case, frontswap actually does store and load page by page, there is no
+	 * existing method to send the second page before the first page is done
+	 * in one thread doing frontswap.
+	 * but in different threads running on different cpu, we have different
+	 * acomp instance, so multiple threads can do (de)compression in parallel.
+	 */
+	ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
+	dlen = acomp_ctx->req->dlen;
+
 	if (ret) {
 		ret = -EINVAL;
 		goto put_dstmem;
@@ -1103,7 +1188,7 @@ static int zswap_frontswap_store(unsigne
 	memcpy(buf, &zhdr, hlen);
 	memcpy(buf + hlen, dst, dlen);
 	zpool_unmap_handle(entry->pool->zpool, handle);
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(acomp_ctx->mutex);
 
 	/* populate entry */
 	entry->offset = offset;
@@ -1131,7 +1216,7 @@ insert_entry:
 	return 0;
 
 put_dstmem:
-	put_cpu_var(zswap_dstmem);
+	mutex_unlock(acomp_ctx->mutex);
 	zswap_pool_put(entry->pool);
 freepage:
 	zswap_entry_cache_free(entry);
@@ -1148,7 +1233,8 @@ static int zswap_frontswap_load(unsigned
 {
 	struct zswap_tree *tree = zswap_trees[type];
 	struct zswap_entry *entry;
-	struct crypto_comp *tfm;
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src, *dst;
 	unsigned int dlen;
 	int ret;
@@ -1175,11 +1261,16 @@ static int zswap_frontswap_load(unsigned
 	src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
 	if (zpool_evictable(entry->pool->zpool))
 		src += sizeof(struct zswap_header);
-	dst = kmap_atomic(page);
-	tfm = *get_cpu_ptr(entry->pool->tfm);
-	ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
-	put_cpu_ptr(entry->pool->tfm);
-	kunmap_atomic(dst);
+
+	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);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen);
+	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
+	mutex_unlock(acomp_ctx->mutex);
+
 	zpool_unmap_handle(entry->pool->zpool, entry->handle);
 	BUG_ON(ret);
 
_

Patches currently in -mm which might be from song.bao.hua@hisilicon.com are

mm-gup_benchmark-mark-gup_benchmark_init-as-__init-function.patch
mm-gup_benchmark-gup_benchmark-depends-on-debug_fs.patch
mm-zswap-move-to-use-crypto_acomp-api-for-hardware-acceleration.patch