From: Yosry Ahmed <yosryahmed@google.com>
To: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Nhat Pham <nphamcs@gmail.com>, Chris Li <chriscli@google.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Seth Jennings <sjenning@redhat.com>,
Dan Streetman <ddstreet@ieee.org>,
Vitaly Wool <vitaly.wool@konsulko.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [PATCH 1/5] mm/zswap: reuse dstmem when decompress
Date: Wed, 13 Dec 2023 15:24:17 -0800 [thread overview]
Message-ID: <CAJD7tkbicqevYuJbTUZBQUo2n_k-HKTixG5TbXGtdbtFJgFmfg@mail.gmail.com> (raw)
In-Reply-To: <20231213-zswap-dstmem-v1-1-896763369d04@bytedance.com>
On Tue, Dec 12, 2023 at 8:18 PM 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 mutex.
>
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
> Reviewed-by: Nhat Pham <nphamcs@gmail.com>
> ---
> mm/zswap.c | 29 +++++++++--------------------
> 1 file changed, 9 insertions(+), 20 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 7ee54a3d8281..edb8b45ed5a1 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -1772,9 +1772,9 @@ 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));
> @@ -1796,27 +1796,18 @@ 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;
I don't like that we are now using acomp_ctx->dstmem and
acomp_ctx->mutex now for purposes other than what the naming suggests.
How about removing these two fields from acomp_ctx, and directly using
zswap_dstmem and zswap_mutex in both the load and store paths, rename
them, and add proper comments above their definitions that they are
for generic percpu buffering on the load and store paths?
next prev parent reply other threads:[~2023-12-13 23:24 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-12-13 4:17 [PATCH 0/5] mm/zswap: dstmem reuse optimizations and cleanups Chengming Zhou
2023-12-13 4:17 ` [PATCH 1/5] mm/zswap: reuse dstmem when decompress Chengming Zhou
2023-12-13 23:24 ` Yosry Ahmed [this message]
2023-12-14 13:29 ` Chengming Zhou
2023-12-14 13:32 ` Yosry Ahmed
2023-12-14 14:42 ` Chengming Zhou
2023-12-14 18:24 ` Yosry Ahmed
2023-12-18 8:06 ` Chengming Zhou
2023-12-14 17:59 ` Chris Li
2023-12-14 18:26 ` Yosry Ahmed
2023-12-14 22:02 ` Chris Li
2023-12-14 20:33 ` Nhat Pham
2023-12-13 4:17 ` [PATCH 2/5] mm/zswap: change dstmem size to one page Chengming Zhou
2023-12-13 23:34 ` Yosry Ahmed
2023-12-14 0:18 ` Nhat Pham
2023-12-14 13:33 ` Chengming Zhou
2023-12-14 13:37 ` Yosry Ahmed
2023-12-14 13:57 ` Chengming Zhou
2023-12-14 15:03 ` Chengming Zhou
2023-12-14 18:34 ` Yosry Ahmed
2023-12-14 18:30 ` Yosry Ahmed
2023-12-14 20:29 ` Nhat Pham
2023-12-13 4:18 ` [PATCH 3/5] mm/zswap: refactor out __zswap_load() Chengming Zhou
2023-12-13 23:37 ` Yosry Ahmed
2023-12-14 0:52 ` Yosry Ahmed
2023-12-14 14:45 ` Chengming Zhou
2023-12-18 8:15 ` Chengming Zhou
2023-12-18 9:38 ` Yosry Ahmed
2023-12-13 4:18 ` [PATCH 4/5] mm/zswap: cleanup zswap_load() Chengming Zhou
2023-12-14 0:56 ` Yosry Ahmed
2023-12-13 4:18 ` [PATCH 5/5] mm/zswap: cleanup zswap_reclaim_entry() Chengming Zhou
2023-12-13 23:27 ` Nhat Pham
2023-12-14 1:02 ` Yosry Ahmed
2023-12-14 22:23 ` Andrew Morton
2023-12-14 22:41 ` Yosry Ahmed
2023-12-18 14:03 ` Johannes Weiner
2023-12-18 14:39 ` Yosry Ahmed
2023-12-18 14:58 ` Johannes Weiner
2023-12-18 20:52 ` Yosry Ahmed
2023-12-19 12:16 ` Chengming Zhou
2023-12-20 4:30 ` Johannes Weiner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAJD7tkbicqevYuJbTUZBQUo2n_k-HKTixG5TbXGtdbtFJgFmfg@mail.gmail.com \
--to=yosryahmed@google.com \
--cc=akpm@linux-foundation.org \
--cc=chriscli@google.com \
--cc=ddstreet@ieee.org \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nphamcs@gmail.com \
--cc=sjenning@redhat.com \
--cc=vitaly.wool@konsulko.com \
--cc=zhouchengming@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox