> -----Original Message-----
> From: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
> Sent: Friday, November 8, 2024 12:23 PM
> To: Sridhar, Kanchana P <kanchana.p.sridhar@xxxxxxxxx>
> Cc: linux-kernel@xxxxxxxxxxxxxxx; linux-mm@xxxxxxxxx;
> hannes@xxxxxxxxxxx; nphamcs@xxxxxxxxx; chengming.zhou@xxxxxxxxx;
> usamaarif642@xxxxxxxxx; ryan.roberts@xxxxxxx; Huang, Ying
> <ying.huang@xxxxxxxxx>; 21cnbao@xxxxxxxxx; akpm@xxxxxxxxxxxxxxxxxxxx;
> linux-crypto@xxxxxxxxxxxxxxx; herbert@xxxxxxxxxxxxxxxxxxx;
> davem@xxxxxxxxxxxxx; clabbe@xxxxxxxxxxxx; ardb@xxxxxxxxxx;
> ebiggers@xxxxxxxxxx; surenb@xxxxxxxxxx; Accardi, Kristen C
> <kristen.c.accardi@xxxxxxxxx>; zanussi@xxxxxxxxxx; Feghali, Wajdi K
> <wajdi.k.feghali@xxxxxxxxx>; Gopal, Vinodh <vinodh.gopal@xxxxxxxxx>
> Subject: Re: [PATCH v3 10/13] mm: zswap: Add a per-cpu "acomp_batch_ctx"
> to struct zswap_pool.
>
> On Wed, Nov 6, 2024 at 11:21 AM Kanchana P Sridhar
> <kanchana.p.sridhar@xxxxxxxxx> wrote:
> >
> > This patch adds a separate per-cpu batching acomp context
> "acomp_batch_ctx"
> > to the zswap_pool. The per-cpu acomp_batch_ctx pointer is allocated at
> pool
> > creation time, but no per-cpu resources are allocated for it.
> >
> > The idea is to not incur the memory footprint cost of multiple acomp_reqs
> > and buffers in the existing "acomp_ctx" for cases where compress batching
> > is not possible; for instance, with software compressor algorithms, on
> > systems without IAA, on systems with IAA that want to run the existing
> > non-batching implementation of zswap_store() of large folios.
> >
> > By creating a separate acomp_batch_ctx, we have the ability to allocate
> > additional memory per-cpu only if the zswap compressor supports batching,
> > and if the user wants to enable the use of compress batching in
> > zswap_store() to improve swapout performance of large folios.
> >
> > Suggested-by: Yosry Ahmed <yosryahmed@xxxxxxxxxx>
>
> This isn't needed if the sysctl is removed and we just allocate the
> number of buffers during pool initialization, right? Same for the next
> patch.
That's correct.
Thanks,
Kanchana
>
>
> > Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@xxxxxxxxx>
> > ---
> > mm/zswap.c | 22 +++++++++++++++++++++-
> > 1 file changed, 21 insertions(+), 1 deletion(-)
> >
> > diff --git a/mm/zswap.c b/mm/zswap.c
> > index 02e031122fdf..80a928cf0f7e 100644
> > --- a/mm/zswap.c
> > +++ b/mm/zswap.c
> > @@ -160,6 +160,7 @@ struct crypto_acomp_ctx {
> > struct zswap_pool {
> > struct zpool *zpool;
> > struct crypto_acomp_ctx __percpu *acomp_ctx;
> > + struct crypto_acomp_ctx __percpu *acomp_batch_ctx;
> > struct percpu_ref ref;
> > struct list_head list;
> > struct work_struct release_work;
> > @@ -287,10 +288,14 @@ static struct zswap_pool
> *zswap_pool_create(char *type, char *compressor)
> >
> > pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx);
> > if (!pool->acomp_ctx) {
> > - pr_err("percpu alloc failed\n");
> > + pr_err("percpu acomp_ctx alloc failed\n");
> > goto error;
> > }
> >
> > + pool->acomp_batch_ctx = alloc_percpu(*pool->acomp_batch_ctx);
> > + if (!pool->acomp_batch_ctx)
> > + pr_err("percpu acomp_batch_ctx alloc failed\n");
> > +
> > ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> > &pool->node);
> > if (ret)
> > @@ -312,6 +317,8 @@ static struct zswap_pool *zswap_pool_create(char
> *type, char *compressor)
> > ref_fail:
> > cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> &pool->node);
> > error:
> > + if (pool->acomp_batch_ctx)
> > + free_percpu(pool->acomp_batch_ctx);
> > if (pool->acomp_ctx)
> > free_percpu(pool->acomp_ctx);
> > if (pool->zpool)
> > @@ -368,6 +375,8 @@ static void zswap_pool_destroy(struct zswap_pool
> *pool)
> >
> > cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> &pool->node);
> > free_percpu(pool->acomp_ctx);
> > + if (pool->acomp_batch_ctx)
> > + free_percpu(pool->acomp_batch_ctx);
> >
> > zpool_destroy_pool(pool->zpool);
> > kfree(pool);
> > @@ -930,6 +939,11 @@ 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_acomp_ctx *acomp_ctx;
> >
> > + if (pool->acomp_batch_ctx) {
> > + acomp_ctx = per_cpu_ptr(pool->acomp_batch_ctx, cpu);
> > + acomp_ctx->nr_reqs = 0;
> > + }
> > +
> > acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
> > return zswap_create_acomp_ctx(cpu, acomp_ctx, pool->tfm_name, 1);
> > }
> > @@ -939,6 +953,12 @@ 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;
> >
> > + if (pool->acomp_batch_ctx) {
> > + acomp_ctx = per_cpu_ptr(pool->acomp_batch_ctx, cpu);
> > + if (!IS_ERR_OR_NULL(acomp_ctx) && (acomp_ctx->nr_reqs > 0))
> > + zswap_delete_acomp_ctx(acomp_ctx);
> > + }
> > +
> > acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
> > zswap_delete_acomp_ctx(acomp_ctx);
> >
> > --
> > 2.27.0
> >
