[v6,2/2] mm/zswap: remove the memcpy if acomp is not sleepable

Message ID 20240222081135.173040-3-21cnbao@gmail.com
State New
Headers
Series zswap: remove the memcpy if acomp is not sleepable |

Commit Message

Barry Song Feb. 22, 2024, 8:11 a.m. UTC
  From: Barry Song <v-songbaohua@oppo.com>

Most compressors are actually CPU-based and won't sleep during
compression and decompression. We should remove the redundant
memcpy for them.
This patch checks if the algorithm is sleepable by testing the
CRYPTO_ALG_ASYNC algorithm flag.
Generally speaking, async and sleepable are semantically similar
but not equal. But for compress drivers, they are basically equal
at least due to the below facts.
Firstly, scompress drivers - crypto/deflate.c, lz4.c, zstd.c,
lzo.c etc have no sleep. Secondly, zRAM has been using these
scompress drivers for years in atomic contexts, and never
worried those drivers going to sleep.
One exception is that an async driver can sometimes still return
synchronously per Herbert's clarification. In this case, we are
still having a redundant memcpy. But we can't know if one
particular acomp request will sleep or not unless crypto can
expose more details for each specific request from offload
drivers.

Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Tested-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 mm/zswap.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)
  

Comments

Chris Li Feb. 24, 2024, 4:53 p.m. UTC | #1
Acked-by: Chris Li <chrisl@kernel.org>

Chris

On Thu, Feb 22, 2024 at 12:12 AM Barry Song <21cnbao@gmail.com> wrote:
>
> From: Barry Song <v-songbaohua@oppo.com>
>
> Most compressors are actually CPU-based and won't sleep during
> compression and decompression. We should remove the redundant
> memcpy for them.
> This patch checks if the algorithm is sleepable by testing the
> CRYPTO_ALG_ASYNC algorithm flag.
> Generally speaking, async and sleepable are semantically similar
> but not equal. But for compress drivers, they are basically equal
> at least due to the below facts.
> Firstly, scompress drivers - crypto/deflate.c, lz4.c, zstd.c,
> lzo.c etc have no sleep. Secondly, zRAM has been using these
> scompress drivers for years in atomic contexts, and never
> worried those drivers going to sleep.
> One exception is that an async driver can sometimes still return
> synchronously per Herbert's clarification. In this case, we are
> still having a redundant memcpy. But we can't know if one
> particular acomp request will sleep or not unless crypto can
> expose more details for each specific request from offload
> drivers.
>
> Signed-off-by: Barry Song <v-songbaohua@oppo.com>
> Tested-by: Chengming Zhou <zhouchengming@bytedance.com>
> Reviewed-by: Nhat Pham <nphamcs@gmail.com>
> Acked-by: Yosry Ahmed <yosryahmed@google.com>
> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com>
> ---
>  mm/zswap.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 011e068eb355..de3c9e30bed7 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -162,6 +162,7 @@ struct crypto_acomp_ctx {
>         struct crypto_wait wait;
>         u8 *buffer;
>         struct mutex mutex;
> +       bool is_sleepable;
>  };
>
>  /*
> @@ -950,6 +951,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
>                 goto acomp_fail;
>         }
>         acomp_ctx->acomp = acomp;
> +       acomp_ctx->is_sleepable = acomp_is_async(acomp);
>
>         req = acomp_request_alloc(acomp_ctx->acomp);
>         if (!req) {
> @@ -1077,7 +1079,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
>         mutex_lock(&acomp_ctx->mutex);
>
>         src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
> -       if (!zpool_can_sleep_mapped(zpool)) {
> +       if (acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) {
>                 memcpy(acomp_ctx->buffer, src, entry->length);
>                 src = acomp_ctx->buffer;
>                 zpool_unmap_handle(zpool, entry->handle);
> @@ -1091,7 +1093,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
>         BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
>         mutex_unlock(&acomp_ctx->mutex);
>
> -       if (zpool_can_sleep_mapped(zpool))
> +       if (!acomp_ctx->is_sleepable || zpool_can_sleep_mapped(zpool))
>                 zpool_unmap_handle(zpool, entry->handle);
>  }
>
> --
> 2.34.1
>
  

Patch

diff --git a/mm/zswap.c b/mm/zswap.c
index 011e068eb355..de3c9e30bed7 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -162,6 +162,7 @@  struct crypto_acomp_ctx {
 	struct crypto_wait wait;
 	u8 *buffer;
 	struct mutex mutex;
+	bool is_sleepable;
 };
 
 /*
@@ -950,6 +951,7 @@  static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 		goto acomp_fail;
 	}
 	acomp_ctx->acomp = acomp;
+	acomp_ctx->is_sleepable = acomp_is_async(acomp);
 
 	req = acomp_request_alloc(acomp_ctx->acomp);
 	if (!req) {
@@ -1077,7 +1079,7 @@  static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	mutex_lock(&acomp_ctx->mutex);
 
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-	if (!zpool_can_sleep_mapped(zpool)) {
+	if (acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) {
 		memcpy(acomp_ctx->buffer, src, entry->length);
 		src = acomp_ctx->buffer;
 		zpool_unmap_handle(zpool, entry->handle);
@@ -1091,7 +1093,7 @@  static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
 	mutex_unlock(&acomp_ctx->mutex);
 
-	if (zpool_can_sleep_mapped(zpool))
+	if (!acomp_ctx->is_sleepable || zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
 }