linux-kernel - Re: [PATCH v2 2/2] mm: zswap: disable migration while using per-CPU acomp

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <857acdc4-c4b7-44ea-a67d-2df83ca245ed@linux.dev>
Date: Wed, 8 Jan 2025 13:00:24 +0800
From: Chengming Zhou <chengming.zhou@...ux.dev>
To: Nhat Pham <nphamcs@...il.com>, Yosry Ahmed <yosryahmed@...gle.com>
Cc: Johannes Weiner <hannes@...xchg.org>,
 Andrew Morton <akpm@...ux-foundation.org>, Vitaly Wool
 <vitalywool@...il.com>, Barry Song <baohua@...nel.org>,
 Sam Sun <samsun1006219@...il.com>, "linux-mm@...ck.org"
 <linux-mm@...ck.org>,
 "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
 "stable@...r.kernel.org" <stable@...r.kernel.org>,
 "Sridhar, Kanchana P" <kanchana.p.sridhar@...el.com>
Subject: Re: [PATCH v2 2/2] mm: zswap: disable migration while using per-CPU
 acomp_ctx

On 2025/1/8 12:46, Nhat Pham wrote:
> On Wed, Jan 8, 2025 at 9:34 AM Yosry Ahmed <yosryahmed@...gle.com> wrote:
>>
>>
>> Actually, using the mutex to protect against CPU hotunplug is not too
>> complicated. The following diff is one way to do it (lightly tested).
>> Johannes, Nhat, any preferences between this patch (disabling
>> migration) and the following diff?
> 
> I mean if this works, this over migration diasbling any day? :)
> 
>>
>> diff --git a/mm/zswap.c b/mm/zswap.c
>> index f6316b66fb236..4d6817c679a54 100644
>> --- a/mm/zswap.c
>> +++ b/mm/zswap.c
>> @@ -869,17 +869,40 @@ 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_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
>>
>> +       mutex_lock(&acomp_ctx->mutex);
>>          if (!IS_ERR_OR_NULL(acomp_ctx)) {
>>                  if (!IS_ERR_OR_NULL(acomp_ctx->req))
>>                          acomp_request_free(acomp_ctx->req);
>> +               acomp_ctx->req = NULL;
>>                  if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
>>                          crypto_free_acomp(acomp_ctx->acomp);
>>                  kfree(acomp_ctx->buffer);
>>          }
>> +       mutex_unlock(&acomp_ctx->mutex);
>>
>>          return 0;
>>   }
>>
>> +static struct crypto_acomp_ctx *acomp_ctx_get_cpu_locked(
>> +               struct crypto_acomp_ctx __percpu *acomp_ctx)
>> +{
>> +       struct crypto_acomp_ctx *ctx;
>> +
>> +       for (;;) {
>> +               ctx = raw_cpu_ptr(acomp_ctx);
>> +               mutex_lock(&ctx->mutex);
> 
> I'm a bit confused. IIUC, ctx is per-cpu right? What's protecting this
> cpu-local data (including the mutex) from being invalidated under us
> while we're sleeping and waiting for the mutex?

Yeah, it's not safe, we can only use this_cpu_ptr(), which will disable
preempt (so cpu offline can't kick in), and get refcount of ctx. Since
we can't mutex_lock in the preempt disabled section.

Thanks.

> 
> If it is somehow protected, then yeah this seems quite elegant :)
> 
>> +               if (likely(ctx->req))
>> +                       return ctx;
>> +               /* Raced with zswap_cpu_comp_dead() on CPU hotunplug */
>> +               mutex_unlock(&ctx->mutex);
>> +       }
>> +}
>> +
>> +static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *ctx)
>> +{
>> +       mutex_unlock(&ctx->mutex);
>> +}
>> +
>>   static bool zswap_compress(struct page *page, struct zswap_entry *entry,
>>                             struct zswap_pool *pool)
>>   {
>> @@ -893,10 +916,7 @@ static bool zswap_compress(struct page *page,
>> struct zswap_entry *entry,
>>          gfp_t gfp;
>>          u8 *dst;
>>
>> -       acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
>> -
>> -       mutex_lock(&acomp_ctx->mutex);
>> -
>> +       acomp_ctx = acomp_ctx_get_cpu_locked(pool->acomp_ctx);
>>          dst = acomp_ctx->buffer;
>>          sg_init_table(&input, 1);
>>          sg_set_page(&input, page, PAGE_SIZE, 0);
>> @@ -949,7 +969,7 @@ static bool zswap_compress(struct page *page,
>> struct zswap_entry *entry,
>>          else if (alloc_ret)
>>                  zswap_reject_alloc_fail++;
>>
>> -       mutex_unlock(&acomp_ctx->mutex);
>> +       acomp_ctx_put_unlock(acomp_ctx);
>>          return comp_ret == 0 && alloc_ret == 0;
>>   }
>>
>> @@ -960,9 +980,7 @@ static void zswap_decompress(struct zswap_entry
>> *entry, struct folio *folio)
>>          struct crypto_acomp_ctx *acomp_ctx;
>>          u8 *src;
>>
>> -       acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
>> -       mutex_lock(&acomp_ctx->mutex);
>> -
>> +       acomp_ctx = acomp_ctx_get_cpu_locked(entry->pool->acomp_ctx);
>>          src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
>>          /*