RE: [PATCH v6 15/16] mm: zswap: Compress batching with Intel IAA in zswap_store() of large folios.

[Sridhar, Kanchana P]

> -----Original Message-----
> From: Yosry Ahmed <yosry.ahmed@xxxxxxxxx>
> Sent: Thursday, February 6, 2025 11:11 AM
> 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; 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>;
> Feghali, Wajdi K <wajdi.k.feghali@xxxxxxxxx>; Gopal, Vinodh
> <vinodh.gopal@xxxxxxxxx>
> Subject: Re: [PATCH v6 15/16] mm: zswap: Compress batching with Intel IAA
> in zswap_store() of large folios.
> 
> On Wed, Feb 05, 2025 at 11:21:01PM -0800, Kanchana P Sridhar wrote:
> > zswap_compress_folio() is modified to detect if the pool's acomp_ctx has
> > more than one "nr_reqs", which will be the case if the cpu onlining code
> > has allocated multiple batching resources in the acomp_ctx. If so, it means
> > compress batching can be used with a batch-size of "acomp_ctx->nr_reqs".
> >
> > If compress batching can be used, zswap_compress_folio() will invoke the
> > newly added zswap_batch_compress() procedure to compress and store the
> > folio in batches of "acomp_ctx->nr_reqs" pages.
> >
> > With Intel IAA, the iaa_crypto driver will compress each batch of pages in
> > parallel in hardware.
> >
> > Hence, zswap_batch_compress() does the same computes for a batch, as
> > zswap_compress() does for a page; and returns true if the batch was
> > successfully compressed/stored, and false otherwise.
> >
> > If the pool does not support compress batching, or the folio has only one
> > page, zswap_compress_folio() calls zswap_compress() for each individual
> > page in the folio, as before.
> >
> > Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@xxxxxxxxx>
> > ---
> >  mm/zswap.c | 122
> +++++++++++++++++++++++++++++++++++++++++++++++++----
> >  1 file changed, 113 insertions(+), 9 deletions(-)
> >
> > diff --git a/mm/zswap.c b/mm/zswap.c
> > index 6563d12e907b..f1cba77eda62 100644
> > --- a/mm/zswap.c
> > +++ b/mm/zswap.c
> > @@ -985,10 +985,11 @@ static void acomp_ctx_put_unlock(struct
> crypto_acomp_ctx *acomp_ctx)
> >  	mutex_unlock(&acomp_ctx->mutex);
> >  }
> >
> > +/* The per-cpu @acomp_ctx mutex should be locked/unlocked in the
> caller. */
> 
> Please use lockdep assertions rather than comments for internal locking rules.

Sure. Thanks for the suggestion.

> 
> >  static bool zswap_compress(struct page *page, struct zswap_entry *entry,
> > -			   struct zswap_pool *pool)
> > +			   struct zswap_pool *pool,
> > +			   struct crypto_acomp_ctx *acomp_ctx)
> >  {
> > -	struct crypto_acomp_ctx *acomp_ctx;
> >  	struct scatterlist input, output;
> >  	int comp_ret = 0, alloc_ret = 0;
> >  	unsigned int dlen = PAGE_SIZE;
> > @@ -998,7 +999,6 @@ static bool zswap_compress(struct page *page,
> struct zswap_entry *entry,
> >  	gfp_t gfp;
> >  	u8 *dst;
> >
> > -	acomp_ctx = acomp_ctx_get_cpu_lock(pool);
> >  	dst = acomp_ctx->buffers[0];
> >  	sg_init_table(&input, 1);
> >  	sg_set_page(&input, page, PAGE_SIZE, 0);
> > @@ -1051,7 +1051,6 @@ static bool zswap_compress(struct page *page,
> struct zswap_entry *entry,
> >  	else if (alloc_ret)
> >  		zswap_reject_alloc_fail++;
> >
> > -	acomp_ctx_put_unlock(acomp_ctx);
> >  	return comp_ret == 0 && alloc_ret == 0;
> >  }
> >
> > @@ -1509,20 +1508,125 @@ static void shrink_worker(struct work_struct
> *w)
> >  * main API
> >  **********************************/
> >
> > +/* The per-cpu @acomp_ctx mutex should be locked/unlocked in the
> caller. */
> > +static bool zswap_batch_compress(struct folio *folio,
> > +				 long index,
> > +				 unsigned int batch_size,
> > +				 struct zswap_entry *entries[],
> > +				 struct zswap_pool *pool,
> > +				 struct crypto_acomp_ctx *acomp_ctx)
> > +{
> > +	int comp_errors[ZSWAP_MAX_BATCH_SIZE] = { 0 };
> > +	unsigned int dlens[ZSWAP_MAX_BATCH_SIZE];
> > +	struct page *pages[ZSWAP_MAX_BATCH_SIZE];
> > +	unsigned int i, nr_batch_pages;
> > +	bool ret = true;
> > +
> > +	nr_batch_pages = min((unsigned int)(folio_nr_pages(folio) - index),
> batch_size);
> > +
> > +	for (i = 0; i < nr_batch_pages; ++i) {
> > +		pages[i] = folio_page(folio, index + i);
> > +		dlens[i] = PAGE_SIZE;
> > +	}
> > +
> > +	/*
> > +	 * Batch compress @nr_batch_pages. If IAA is the compressor, the
> > +	 * hardware will compress @nr_batch_pages in parallel.
> > +	 */
> 
> Please do not specifically mention IAA in zswap.c, as batching could be
> supported in the future by other compressors.

Ok.

> 
> > +	ret = crypto_acomp_batch_compress(
> > +		acomp_ctx->reqs,
> > +		NULL,
> > +		pages,
> > +		acomp_ctx->buffers,
> > +		dlens,
> > +		comp_errors,
> > +		nr_batch_pages);
> 
> Does crypto_acomp_batch_compress() not require calling
> crypto_wait_req()?

It actually doesn't. If the crypto_wait parameter is NULL, the API requires
the driver to provide a way to process request completions asynchronously,
as described in patch 2 that adds the crypto batching API.

> 
> > +
> > +	if (ret) {
> > +		/*
> > +		 * All batch pages were successfully compressed.
> > +		 * Store the pages in zpool.
> > +		 */
> > +		struct zpool *zpool = pool->zpool;
> > +		gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN |
> __GFP_KSWAPD_RECLAIM;
> > +
> > +		if (zpool_malloc_support_movable(zpool))
> > +			gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
> > +
> > +		for (i = 0; i < nr_batch_pages; ++i) {
> > +			unsigned long handle;
> > +			char *buf;
> > +			int err;
> > +
> > +			err = zpool_malloc(zpool, dlens[i], gfp, &handle);
> > +
> > +			if (err) {
> > +				if (err == -ENOSPC)
> > +					zswap_reject_compress_poor++;
> > +				else
> > +					zswap_reject_alloc_fail++;
> > +
> > +				ret = false;
> > +				break;
> > +			}
> > +
> > +			buf = zpool_map_handle(zpool, handle,
> ZPOOL_MM_WO);
> > +			memcpy(buf, acomp_ctx->buffers[i], dlens[i]);
> > +			zpool_unmap_handle(zpool, handle);
> > +
> > +			entries[i]->handle = handle;
> > +			entries[i]->length = dlens[i];
> > +		}
> > +	} else {
> > +		/* Some batch pages had compression errors. */
> > +		for (i = 0; i < nr_batch_pages; ++i) {
> > +			if (comp_errors[i]) {
> > +				if (comp_errors[i] == -ENOSPC)
> > +					zswap_reject_compress_poor++;
> > +				else
> > +					zswap_reject_compress_fail++;
> > +			}
> > +		}
> > +	}
> 
> This function is awfully close to zswap_compress(). It's essentially a
> vectorized version and uses crypto_acomp_batch_compress() instead of
> crypto_acomp_compress().
> 
> My questions are:
> - Can we use crypto_acomp_batch_compress() for the non-batched case as
>   well to unify the code? Does it cause any regressions?
> 
> - If we have to use different compressions APIs, can we at least reuse
>   the rest of the code? We can abstract the compression call into a
>   helper that chooses the appropriate API based on the batch size. The
>   rest should be the same AFAICT.

All good ideas. Let me think about this some more, and gather some data.

Thanks,
Kanchana

> 
> > +
> > +	return ret;
> > +}
> > +
> >  static bool zswap_compress_folio(struct folio *folio,
> >  				 struct zswap_entry *entries[],
> >  				 struct zswap_pool *pool)
> >  {
> >  	long index, nr_pages = folio_nr_pages(folio);
> > +	struct crypto_acomp_ctx *acomp_ctx;
> > +	unsigned int batch_size;
> > +	bool ret = true;
> >
> > -	for (index = 0; index < nr_pages; ++index) {
> > -		struct page *page = folio_page(folio, index);
> > +	acomp_ctx = acomp_ctx_get_cpu_lock(pool);
> > +	batch_size = acomp_ctx->nr_reqs;
> > +
> > +	if ((batch_size > 1) && (nr_pages > 1)) {
> > +		for (index = 0; index < nr_pages; index += batch_size) {
> > +
> > +			if (!zswap_batch_compress(folio, index, batch_size,
> > +						  &entries[index], pool,
> acomp_ctx)) {
> > +				ret = false;
> > +				goto unlock_acomp_ctx;
> > +			}
> > +		}
> > +	} else {
> > +		for (index = 0; index < nr_pages; ++index) {
> > +			struct page *page = folio_page(folio, index);
> >
> > -		if (!zswap_compress(page, entries[index], pool))
> > -			return false;
> > +			if (!zswap_compress(page, entries[index], pool,
> acomp_ctx)) {
> > +				ret = false;
> > +				goto unlock_acomp_ctx;
> > +			}
> > +		}
> >  	}
> >
> > -	return true;
> > +unlock_acomp_ctx:
> > +	acomp_ctx_put_unlock(acomp_ctx);
> > +	return ret;
> >  }
> >
> >  /*
> > --
> > 2.27.0
> >