RE: [PATCH v13 19/22] mm: zswap: Per-CPU acomp_ctx resources exist from pool creation to deletion.

["Sridhar, Kanchana P" <kanchana.p.sridhar@intel.com>]

> -----Original Message-----
> From: Yosry Ahmed <yosry.ahmed@linux.dev>
> Sent: Thursday, November 13, 2025 12:24 PM
> To: Sridhar, Kanchana P <kanchana.p.sridhar@intel.com>
> Cc: linux-kernel@vger.kernel.org; linux-mm@kvack.org;
> hannes@cmpxchg.org; nphamcs@gmail.com; chengming.zhou@linux.dev;
> usamaarif642@gmail.com; ryan.roberts@arm.com; 21cnbao@gmail.com;
> ying.huang@linux.alibaba.com; akpm@linux-foundation.org;
> senozhatsky@chromium.org; sj@kernel.org; kasong@tencent.com; linux-
> crypto@vger.kernel.org; herbert@gondor.apana.org.au;
> davem@davemloft.net; clabbe@baylibre.com; ardb@kernel.org;
> ebiggers@google.com; surenb@google.com; Accardi, Kristen C
> <kristen.c.accardi@intel.com>; Gomes, Vinicius <vinicius.gomes@intel.com>;
> Feghali, Wajdi K <wajdi.k.feghali@intel.com>; Gopal, Vinodh
> <vinodh.gopal@intel.com>
> Subject: Re: [PATCH v13 19/22] mm: zswap: Per-CPU acomp_ctx resources
> exist from pool creation to deletion.
> 
> On Tue, Nov 04, 2025 at 01:12:32AM -0800, Kanchana P Sridhar wrote:
>
[...]
> >  mm/zswap.c | 164 +++++++++++++++++++++--------------------------------
> >  1 file changed, 64 insertions(+), 100 deletions(-)
> >
> > diff --git a/mm/zswap.c b/mm/zswap.c
> > index 4897ed689b9f..87d50786f61f 100644
> > --- a/mm/zswap.c
> > +++ b/mm/zswap.c
> > @@ -242,6 +242,20 @@ static inline struct xarray
> *swap_zswap_tree(swp_entry_t swp)
> >  **********************************/
> >  static void __zswap_pool_empty(struct percpu_ref *ref);
> >
> > +static void acomp_ctx_dealloc(struct crypto_acomp_ctx *acomp_ctx)
> > +{
> > +	if (IS_ERR_OR_NULL(acomp_ctx))
> > +		return;
> > +
> > +	if (!IS_ERR_OR_NULL(acomp_ctx->req))
> > +		acomp_request_free(acomp_ctx->req);
> > +
> > +	if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
> > +		crypto_free_acomp(acomp_ctx->acomp);
> > +
> > +	kfree(acomp_ctx->buffer);
> > +}
> > +
> >  static struct zswap_pool *zswap_pool_create(char *compressor)
> >  {
> >  	struct zswap_pool *pool;
> > @@ -263,19 +277,26 @@ static struct zswap_pool
> *zswap_pool_create(char *compressor)
> >
> >  	strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
> >
> > -	pool->acomp_ctx = alloc_percpu(*pool->acomp_ctx);
> > +	/* Many things rely on the zero-initialization. */
> > +	pool->acomp_ctx = alloc_percpu_gfp(*pool->acomp_ctx,
> > +					   GFP_KERNEL | __GFP_ZERO);
> >  	if (!pool->acomp_ctx) {
> >  		pr_err("percpu alloc failed\n");
> >  		goto error;
> >  	}
> >
> > -	for_each_possible_cpu(cpu)
> > -		mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex);
> > -
> > +	/*
> > +	 * This is serialized against CPU hotplug operations. Hence, cores
> > +	 * cannot be offlined until this finishes.
> > +	 * In case of errors, we need to goto "ref_fail" instead of "error"
> > +	 * because there is no teardown callback registered anymore, for
> > +	 * cpuhp_state_add_instance() to de-allocate resources as it rolls
> back
> > +	 * state on cores before the CPU on which error was encountered.
> > +	 */
> 
> Do we need to manually call acomp_ctx_dealloc() on each CPU on failure
> because cpuhp_state_add_instance() relies on the hotunplug callback for
> cleanup, and we don't have any?

That's correct.

> 
> If that's the case:
> 
> 	/*
> 	 * cpuhp_state_add_instance() will not cleanup on failure since
> 	 * we don't register a hotunplug callback.
> 	 */
> 
> Describing what the code does is not helpful, and things like "anymore"
> do not make sense once the code is merged.

Ok.

> 
> >  	ret =
> cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> >  				       &pool->node);
> >  	if (ret)
> > -		goto error;
> > +		goto ref_fail;
> 
> IIUC we shouldn't call cpuhp_state_remove_instance() on failure, we
> probably should add a new label.

In this case we should because it is part of the pool creation failure
handling flow, at the end of which, the pool will be deleted.

> 
> >
> >  	/* being the current pool takes 1 ref; this func expects the
> >  	 * caller to always add the new pool as the current pool
> > @@ -292,6 +313,9 @@ static struct zswap_pool *zswap_pool_create(char
> *compressor)
> >
> >  ref_fail:
> >  	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> &pool->node);
> > +
> > +	for_each_possible_cpu(cpu)
> > +		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu));
> >  error:
> >  	if (pool->acomp_ctx)
> >  		free_percpu(pool->acomp_ctx);
> > @@ -322,9 +346,15 @@ static struct zswap_pool
> *__zswap_pool_create_fallback(void)
> >
> >  static void zswap_pool_destroy(struct zswap_pool *pool)
> >  {
> > +	int cpu;
> > +
> >  	zswap_pool_debug("destroying", pool);
> >
> >  	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
> &pool->node);
> > +
> > +	for_each_possible_cpu(cpu)
> > +		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu));
> > +
> >  	free_percpu(pool->acomp_ctx);
> >
> >  	zs_destroy_pool(pool->zs_pool);
> > @@ -736,39 +766,35 @@ 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 = per_cpu_ptr(pool-
> >acomp_ctx, cpu);
> > -	struct crypto_acomp *acomp = NULL;
> > -	struct acomp_req *req = NULL;
> > -	u8 *buffer = NULL;
> > -	int ret;
> > +	int ret = -ENOMEM;
> >
> > -	buffer = kmalloc_node(PAGE_SIZE, GFP_KERNEL, cpu_to_node(cpu));
> > -	if (!buffer) {
> > -		ret = -ENOMEM;
> > -		goto fail;
> > -	}
> > +	/*
> > +	 * To handle cases where the CPU goes through online-offline-online
> > +	 * transitions, we return if the acomp_ctx has already been initialized.
> > +	 */
> > +	if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
> > +		return 0;
> 
> Is it possible for acomp_ctx->acomp to be an ERR value here? If it is,
> then zswap initialization should have failed. Maybe WARN_ON_ONCE() for
> that case?

This is checking for a valid acomp_ctx->acomp using the same criteria
being uniformly used in acomp_ctx_dealloc(). This check is necessary to
handle the case where the CPU goes through online-offline-online state
transitions.

Thanks,
Kanchana

> 
> >
> > -	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0,
> cpu_to_node(cpu));
> > -	if (IS_ERR(acomp)) {
> > +	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE, GFP_KERNEL,
> cpu_to_node(cpu));
> > +	if (!acomp_ctx->buffer)
> > +		return ret;
> > +
> > +	acomp_ctx->acomp = crypto_alloc_acomp_node(pool->tfm_name, 0,
> 0, cpu_to_node(cpu));
> > +	if (IS_ERR(acomp_ctx->acomp)) {
> >  		pr_err("could not alloc crypto acomp %s : %ld\n",
> > -				pool->tfm_name, PTR_ERR(acomp));
> > -		ret = PTR_ERR(acomp);
> > +				pool->tfm_name, PTR_ERR(acomp_ctx-
> >acomp));
> > +		ret = PTR_ERR(acomp_ctx->acomp);
> >  		goto fail;
> >  	}
> > +	acomp_ctx->is_sleepable = acomp_is_async(acomp_ctx->acomp);
> >
> > -	req = acomp_request_alloc(acomp);
> > -	if (!req) {
> > +	acomp_ctx->req = acomp_request_alloc(acomp_ctx->acomp);
> > +	if (!acomp_ctx->req) {
> >  		pr_err("could not alloc crypto acomp_request %s\n",
> >  		       pool->tfm_name);
> > -		ret = -ENOMEM;
> >  		goto fail;
> >  	}
> >
> > -	/*
> > -	 * Only hold the mutex after completing allocations, otherwise we
> may
> > -	 * recurse into zswap through reclaim and attempt to hold the mutex
> > -	 * again resulting in a deadlock.
> > -	 */
> > -	mutex_lock(&acomp_ctx->mutex);
> >  	crypto_init_wait(&acomp_ctx->wait);
> >
> >  	/*
> [..]