linux-crypto.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	hannes@cmpxchg.org, yosry.ahmed@linux.dev, 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, 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, kristen.c.accardi@intel.com,
	vinicius.gomes@intel.com
Cc: wajdi.k.feghali@intel.com, vinodh.gopal@intel.com,
	kanchana.p.sridhar@intel.com
Subject: [PATCH v10 16/25] crypto: iaa - Submit the two largest source buffers first in decompress batching.
Date: Thu,  3 Jul 2025 21:23:14 -0700	[thread overview]
Message-ID: <20250704042323.10318-17-kanchana.p.sridhar@intel.com> (raw)
In-Reply-To: <20250704042323.10318-1-kanchana.p.sridhar@intel.com>

This patch finds the two largest source buffers in a given decompression
batch, and submits them first to the IAA decompress engines.

This improves decompress batching latency because the hardware has a
head start on decompressing the highest latency source buffers in the
batch. Workload performance is also significantly improved as a result
of this optimization.

Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
 drivers/crypto/intel/iaa/iaa_crypto_main.c | 60 +++++++++++++++++++++-
 1 file changed, 58 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 09d786e85ab66..4ed56a69112a9 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -2375,6 +2375,35 @@ static int iaa_comp_acompress_batch(
 	return err;
 }
 
+/*
+ * Find the two largest source buffers in @slens for a decompress batch,
+ * and pass their indices back in @idx_max and @idx_next_max.
+ *
+ * Returns true if there is no second largest source buffer, only a max buffer.
+ */
+static __always_inline bool decomp_batch_get_max_slens_idx(
+	unsigned int slens[],
+	int nr_pages,
+	int *idx_max,
+	int *idx_next_max)
+{
+	int i, max_i = 0, next_max_i = 0;
+
+	for (i = 0; i < nr_pages; ++i) {
+		if (slens[i] >= slens[max_i]) {
+			next_max_i = max_i;
+			max_i = i;
+		} else if ((next_max_i == max_i) || (slens[i] > slens[next_max_i])) {
+			next_max_i = i;
+		}
+	}
+
+	*idx_max = max_i;
+	*idx_next_max = next_max_i;
+
+	return (next_max_i == max_i);
+}
+
 /**
  * This API provides IAA decompress batching functionality for use by swap
  * modules.
@@ -2407,18 +2436,36 @@ static int iaa_comp_adecompress_batch(
 {
 	struct scatterlist inputs[IAA_CRYPTO_MAX_BATCH_SIZE];
 	struct scatterlist outputs[IAA_CRYPTO_MAX_BATCH_SIZE];
+	bool max_processed = false, next_max_processed = false;
 	bool decompressions_done = false;
-	int i, err = 0;
+	int i, max_i, next_max_i, err = 0;
 
 	BUG_ON(nr_reqs > IAA_CRYPTO_MAX_BATCH_SIZE);
 
 	iaa_set_req_poll(reqs, nr_reqs, true);
 
+	/*
+	 * Get the indices of the two largest decomp buffers in the batch.
+	 * Submit them first. This improves latency of the batch.
+	 */
+	next_max_processed = decomp_batch_get_max_slens_idx(slens, nr_reqs,
+							    &max_i, &next_max_i);
+
+	i = max_i;
+
 	/*
 	 * Prepare and submit the batch of iaa_reqs to IAA. IAA will process
 	 * these decompress jobs in parallel.
 	 */
-	for (i = 0; i < nr_reqs; ++i) {
+	for (; i < nr_reqs; ++i) {
+		if ((i == max_i) && max_processed)
+			continue;
+		if ((i == next_max_i) && max_processed && next_max_processed)
+			continue;
+
+		if (max_processed && !next_max_processed)
+			i = next_max_i;
+
 		reqs[i]->src = &inputs[i];
 		reqs[i]->dst = &outputs[i];
 		sg_init_one(reqs[i]->src, srcs[i], slens[i]);
@@ -2437,6 +2484,15 @@ static int iaa_comp_adecompress_batch(
 			errors[i] = -EAGAIN;
 		else if (errors[i])
 			err = -EINVAL;
+
+		if (i == max_i) {
+			max_processed = true;
+			i = -1;
+		}
+		if (i == next_max_i) {
+			next_max_processed = true;
+			i = -1;
+		}
 	}
 
 	/*
-- 
2.27.0


  parent reply	other threads:[~2025-07-04  4:23 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-07-04  4:22 [PATCH v10 00/25] zswap compression batching with optimized iaa_crypto driver Kanchana P Sridhar
2025-07-04  4:22 ` [PATCH v10 01/25] crypto: iaa - Reorganize the iaa_crypto driver code Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 02/25] crypto: iaa - New architecture for IAA device WQ comp/decomp usage & core mapping Kanchana P Sridhar
2025-07-05  6:00   ` kernel test robot
2025-07-04  4:23 ` [PATCH v10 03/25] crypto: iaa - Simplify, consistency of function parameters, minor stats bug fix Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 04/25] crypto: iaa - Descriptor allocation timeouts with mitigations Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 05/25] crypto: iaa - iaa_wq uses percpu_refs for get/put reference counting Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 06/25] crypto: iaa - Simplify the code flow in iaa_compress() and iaa_decompress() Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 07/25] crypto: iaa - Refactor hardware descriptor setup into separate procedures Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 08/25] crypto: iaa - Simplified, efficient job submissions for non-irq mode Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 09/25] crypto: iaa - Deprecate exporting add/remove IAA compression modes Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 10/25] crypto: iaa - Rearchitect the iaa_crypto driver to be usable by zswap and zram Kanchana P Sridhar
2025-07-04 15:56   ` kernel test robot
2025-07-05 14:49   ` kernel test robot
2025-07-04  4:23 ` [PATCH v10 11/25] crypto: iaa - Enablers for submitting descriptors then polling for completion Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 12/25] crypto: acomp - Add "void *kernel_data" in "struct acomp_req" for kernel users Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 13/25] crypto: iaa - IAA Batching for parallel compressions/decompressions Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 14/25] crypto: iaa - Enable async mode and make it the default Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 15/25] crypto: iaa - Disable iaa_verify_compress by default Kanchana P Sridhar
2025-07-04  4:23 ` Kanchana P Sridhar [this message]
2025-07-04  4:23 ` [PATCH v10 17/25] crypto: iaa - Add deflate-iaa-dynamic compression mode Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 18/25] crypto: acomp - Add crypto_acomp_batch_size() to get an algorithm's batch-size Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 19/25] crypto: iaa - IAA acomp_algs register the get_batch_size() interface Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 20/25] mm: zswap: Move the CPU hotplug procedures under "pool functions" Kanchana P Sridhar
2025-07-04 18:39   ` Nhat Pham
2025-07-04 21:35     ` Sridhar, Kanchana P
2025-07-04  4:23 ` [PATCH v10 21/25] mm: zswap: Per-CPU acomp_ctx resources exist from pool creation to deletion Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 22/25] mm: zswap: Consistently use IS_ERR_OR_NULL() to check acomp_ctx resources Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 23/25] mm: zswap: Allocate pool batching resources if the compressor supports batching Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 24/25] mm: zswap: zswap_store() will process a large folio in batches Kanchana P Sridhar
2025-07-04  4:23 ` [PATCH v10 25/25] mm: zswap: Batched zswap_compress() with compress batching of large folios Kanchana P Sridhar
2025-07-04 18:37 ` [PATCH v10 00/25] zswap compression batching with optimized iaa_crypto driver Nhat Pham
2025-07-04 21:39   ` Sridhar, Kanchana P

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=20250704042323.10318-17-kanchana.p.sridhar@intel.com \
    --to=kanchana.p.sridhar@intel.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=ardb@kernel.org \
    --cc=chengming.zhou@linux.dev \
    --cc=clabbe@baylibre.com \
    --cc=davem@davemloft.net \
    --cc=ebiggers@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=herbert@gondor.apana.org.au \
    --cc=kristen.c.accardi@intel.com \
    --cc=linux-crypto@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nphamcs@gmail.com \
    --cc=ryan.roberts@arm.com \
    --cc=senozhatsky@chromium.org \
    --cc=surenb@google.com \
    --cc=usamaarif642@gmail.com \
    --cc=vinicius.gomes@intel.com \
    --cc=vinodh.gopal@intel.com \
    --cc=wajdi.k.feghali@intel.com \
    --cc=ying.huang@linux.alibaba.com \
    --cc=yosry.ahmed@linux.dev \
    /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;
as well as URLs for NNTP newsgroup(s).