Received-SPF: pass (google.com: domain of linux-kernel+bounces-3245-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Precedence: bulk
MIME-Version: 1.0
References: <20231213-zswap-dstmem-v2-0-daa5d9ae41a7@bytedance.com> <20231213-zswap-dstmem-v2-2-daa5d9ae41a7@bytedance.com>
In-Reply-To: <20231213-zswap-dstmem-v2-2-daa5d9ae41a7@bytedance.com>
From: Yosry Ahmed <yosryahmed@google.com>
Date: Mon, 18 Dec 2023 01:24:20 -0800
Message-ID: <CAJD7tka3r=gPUDYYpFShUVzyynE0RyKd9Gsk-S8jcexr255_UQ@mail.gmail.com>
Subject: Re: [PATCH v2 2/6] mm/zswap: reuse dstmem when decompress
To: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Seth Jennings <sjenning@redhat.com>, Dan Streetman <ddstreet@ieee.org>, 
	Chris Li <chriscli@google.com>, Nhat Pham <nphamcs@gmail.com>, 
	Vitaly Wool <vitaly.wool@konsulko.com>, Andrew Morton <akpm@linux-foundation.org>, 
	Johannes Weiner <hannes@cmpxchg.org>, linux-kernel@vger.kernel.org, linux-mm@kvack.org, 
	Chris Li <chrisl@kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Mon, Dec 18, 2023 at 12:22=E2=80=AFAM Chengming Zhou
<zhouchengming@bytedance.com> wrote:
>
> 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.
>
> Reviewed-by: Nhat Pham <nphamcs@gmail.com>
> Acked-by: Chris Li <chrisl@kernel.org>
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>

Reviewed-by: Yosry Ahmed <yosryahmed@google.com>

> ---
>  mm/zswap.c | 44 ++++++++++++--------------------------------
>  1 file changed, 12 insertions(+), 32 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 976f278aa507..6b872744e962 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1417,19 +1417,13 @@ static int zswap_writeback_entry(struct zswap_ent=
ry *entry,
>         struct crypto_acomp_ctx *acomp_ctx;
>         struct zpool *pool =3D zswap_find_zpool(entry);
>         bool page_was_allocated;
> -       u8 *src, *tmp =3D NULL;
> +       u8 *src;
>         unsigned int dlen;
>         int ret;
>         struct writeback_control wbc =3D {
>                 .sync_mode =3D WB_SYNC_NONE,
>         };
>
> -       if (!zpool_can_sleep_mapped(pool)) {
> -               tmp =3D kmalloc(PAGE_SIZE, GFP_KERNEL);
> -               if (!tmp)
> -                       return -ENOMEM;
> -       }
> -
>         /* try to allocate swap cache page */
>         mpol =3D get_task_policy(current);
>         page =3D __read_swap_cache_async(swpentry, GFP_KERNEL, mpol,
> @@ -1465,15 +1459,15 @@ static int zswap_writeback_entry(struct zswap_ent=
ry *entry,
>         /* decompress */
>         acomp_ctx =3D raw_cpu_ptr(entry->pool->acomp_ctx);
>         dlen =3D PAGE_SIZE;
> +       mutex_lock(acomp_ctx->mutex);
>
>         src =3D zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
>         if (!zpool_can_sleep_mapped(pool)) {
> -               memcpy(tmp, src, entry->length);
> -               src =3D tmp;
> +               memcpy(acomp_ctx->dstmem, src, entry->length);
> +               src =3D 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 zswap_entry=
 *entry,
>         dlen =3D 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);
> @@ -1508,9 +1500,6 @@ static int zswap_writeback_entry(struct zswap_entry=
 *entry,
>         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
> @@ -1771,7 +1760,7 @@ 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;
> @@ -1796,26 +1785,19 @@ bool zswap_load(struct folio *folio)
>         }
>
>         zpool =3D zswap_find_zpool(entry);
> -       if (!zpool_can_sleep_mapped(zpool)) {
> -               tmp =3D kmalloc(entry->length, GFP_KERNEL);
> -               if (!tmp) {
> -                       ret =3D false;
> -                       goto freeentry;
> -               }
> -       }
>
>         /* decompress */
>         dlen =3D PAGE_SIZE;
> -       src =3D zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
> +       acomp_ctx =3D raw_cpu_ptr(entry->pool->acomp_ctx);
> +       mutex_lock(acomp_ctx->mutex);
>
> +       src =3D zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
>         if (!zpool_can_sleep_mapped(zpool)) {
> -               memcpy(tmp, src, entry->length);
> -               src =3D tmp;
> +               memcpy(acomp_ctx->dstmem, src, entry->length);
> +               src =3D acomp_ctx->dstmem;
>                 zpool_unmap_handle(zpool, entry->handle);
>         }
>
> -       acomp_ctx =3D 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);
> @@ -1826,15 +1808,13 @@ bool zswap_load(struct folio *folio)
>
>         if (zpool_can_sleep_mapped(zpool))
>                 zpool_unmap_handle(zpool, entry->handle);
> -       else
> -               kfree(tmp);
>
>         ret =3D 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);
>
> --
> b4 0.10.1