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, 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,
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 v13 08/22] crypto: iaa - Simplified, efficient job submissions for non-irq mode.
Date: Tue, 4 Nov 2025 01:12:21 -0800 [thread overview]
Message-ID: <20251104091235.8793-9-kanchana.p.sridhar@intel.com> (raw)
In-Reply-To: <20251104091235.8793-1-kanchana.p.sridhar@intel.com>
This patch adds a new procedure, iaa_submit_desc_movdir64b(), that
directly calls movdir64b. The core iaa_crypto routines that submit
compress and decompress jobs now invoke iaa_submit_desc_movdir64b() in
non-irq driver modes, instead of idxd_submit_desc().
idxd_submit_desc() is called only in irq mode.
This improves latency for the most commonly used iaa_crypto usage
(i.e., async non-irq) in zswap by eliminating redundant computes
that would otherwise be incurred in idxd_submit_desc():
For a single-threaded madvise-based workload with the Silesia.tar
dataset, these are the before/after batch compression latencies for a
compress batch of 8 pages:
==================================
p50 (ns) p99 (ns)
==================================
before 5,568 6,056
after 5,472 5,848
Change -96 -208
==================================
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
drivers/crypto/intel/iaa/iaa_crypto_main.c | 30 ++++++++++++++--------
1 file changed, 20 insertions(+), 10 deletions(-)
diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
index 697e98785335..dfc67109e81e 100644
--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
+++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
@@ -1788,6 +1788,24 @@ iaa_setup_decompress_hw_desc(struct idxd_desc *idxd_desc,
return desc;
}
+/*
+ * Call this for non-irq, non-enqcmds job submissions.
+ */
+static __always_inline void iaa_submit_desc_movdir64b(struct idxd_wq *wq,
+ struct idxd_desc *desc)
+{
+ void __iomem *portal = idxd_wq_portal_addr(wq);
+
+ /*
+ * The wmb() flushes writes to coherent DMA data before
+ * possibly triggering a DMA read. The wmb() is necessary
+ * even on UP because the recipient is a device.
+ */
+ wmb();
+
+ iosubmit_cmds512(portal, desc->hw, 1);
+}
+
static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
struct idxd_wq *wq,
dma_addr_t src_addr, unsigned int slen,
@@ -1826,11 +1844,7 @@ static int iaa_compress(struct crypto_tfm *tfm, struct acomp_req *req,
ctx->mode, iaa_device->compression_modes[ctx->mode]);
if (likely(!ctx->use_irq)) {
- ret = idxd_submit_desc(wq, idxd_desc);
- if (ret) {
- dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
- goto out;
- }
+ iaa_submit_desc_movdir64b(wq, idxd_desc);
/* Update stats */
update_total_comp_calls();
@@ -1918,11 +1932,7 @@ static int iaa_decompress(struct crypto_tfm *tfm, struct acomp_req *req,
desc = iaa_setup_decompress_hw_desc(idxd_desc, src_addr, slen, dst_addr, *dlen);
if (likely(!ctx->use_irq)) {
- ret = idxd_submit_desc(wq, idxd_desc);
- if (ret) {
- dev_dbg(dev, "submit_desc failed ret=%d\n", ret);
- goto fallback_software_decomp;
- }
+ iaa_submit_desc_movdir64b(wq, idxd_desc);
/* Update stats */
update_total_decomp_calls();
--
2.27.0
next prev parent reply other threads:[~2025-11-04 9:12 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-04 9:12 [PATCH v13 00/22] zswap compression batching with optimized iaa_crypto driver Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 01/22] crypto: iaa - Reorganize the iaa_crypto driver code Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 02/22] crypto: iaa - New architecture for IAA device WQ comp/decomp usage & core mapping Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 03/22] crypto: iaa - Simplify, consistency of function parameters, minor stats bug fix Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 04/22] crypto: iaa - Descriptor allocation timeouts with mitigations Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 05/22] crypto: iaa - iaa_wq uses percpu_refs for get/put reference counting Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 06/22] crypto: iaa - Simplify the code flow in iaa_compress() and iaa_decompress() Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 07/22] crypto: iaa - Refactor hardware descriptor setup into separate procedures Kanchana P Sridhar
2025-11-04 9:12 ` Kanchana P Sridhar [this message]
2025-11-04 9:12 ` [PATCH v13 09/22] crypto: iaa - Deprecate exporting add/remove IAA compression modes Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 10/22] crypto: iaa - Expect a single scatterlist for a [de]compress request's src/dst Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 11/22] crypto: iaa - Rearchitect iaa_crypto to have clean interfaces with crypto_acomp Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 12/22] crypto: acomp - Define a unit_size in struct acomp_req to enable batching Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 13/22] crypto: iaa - IAA Batching for parallel compressions/decompressions Kanchana P Sridhar
2025-11-14 9:59 ` Herbert Xu
2025-11-16 18:53 ` Sridhar, Kanchana P
2025-11-17 3:12 ` Herbert Xu
2025-11-17 5:47 ` Sridhar, Kanchana P
2025-11-04 9:12 ` [PATCH v13 14/22] crypto: iaa - Enable async mode and make it the default Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 15/22] crypto: iaa - Disable iaa_verify_compress by default Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 16/22] crypto: iaa - Submit the two largest source buffers first in decompress batching Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 17/22] crypto: iaa - Add deflate-iaa-dynamic compression mode Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 18/22] crypto: acomp - Add crypto_acomp_batch_size() to get an algorithm's batch-size Kanchana P Sridhar
2025-11-04 9:12 ` [PATCH v13 19/22] mm: zswap: Per-CPU acomp_ctx resources exist from pool creation to deletion Kanchana P Sridhar
2025-11-13 20:24 ` Yosry Ahmed
2025-12-12 0:55 ` Sridhar, Kanchana P
2025-12-12 1:06 ` Yosry Ahmed
2025-12-12 1:58 ` Sridhar, Kanchana P
2025-12-12 2:47 ` Yosry Ahmed
2025-12-12 4:32 ` Sridhar, Kanchana P
2025-12-12 18:17 ` Sridhar, Kanchana P
2025-12-12 18:43 ` Yosry Ahmed
2025-12-12 20:53 ` Sridhar, Kanchana P
2025-12-12 22:25 ` Yosry Ahmed
2025-12-13 19:53 ` Sridhar, Kanchana P
2025-11-04 9:12 ` [PATCH v13 20/22] mm: zswap: Consistently use IS_ERR_OR_NULL() to check acomp_ctx resources Kanchana P Sridhar
2025-11-13 20:25 ` Yosry Ahmed
2025-12-12 1:07 ` Sridhar, Kanchana P
2025-11-04 9:12 ` [PATCH v13 21/22] mm: zswap: zswap_store() will process a large folio in batches Kanchana P Sridhar
2025-11-06 17:45 ` Nhat Pham
2025-11-07 2:28 ` Sridhar, Kanchana P
2025-11-13 20:52 ` Yosry Ahmed
2025-11-13 20:51 ` Yosry Ahmed
2025-12-12 1:43 ` Sridhar, Kanchana P
2025-12-12 4:40 ` Yosry Ahmed
2025-12-12 18:03 ` Sridhar, Kanchana P
2025-11-04 9:12 ` [PATCH v13 22/22] mm: zswap: Batched zswap_compress() with compress batching of large folios Kanchana P Sridhar
2025-11-13 21:34 ` Yosry Ahmed
2025-11-13 23:55 ` Sridhar, Kanchana P
2025-11-14 0:46 ` Yosry Ahmed
2025-12-19 2:29 ` Sridhar, Kanchana P
2025-12-19 15:26 ` Yosry Ahmed
2025-12-19 19:03 ` Sridhar, Kanchana P
2025-11-14 5:52 ` Yosry Ahmed
2025-11-14 6:43 ` Sridhar, Kanchana P
2025-11-14 15:37 ` Yosry Ahmed
2025-11-14 19:23 ` Sridhar, Kanchana P
2025-11-14 19:44 ` Yosry Ahmed
2025-11-14 19:59 ` Sridhar, Kanchana P
2025-11-14 20:49 ` Yosry Ahmed
2025-11-26 5:46 ` Herbert Xu
2025-11-26 6:34 ` Yosry Ahmed
2025-11-26 20:05 ` Sridhar, Kanchana P
2025-12-08 3:23 ` Herbert Xu
2025-12-08 4:17 ` Sridhar, Kanchana P
2025-12-08 4:24 ` Herbert Xu
2025-12-08 4:33 ` Sridhar, Kanchana P
2025-12-09 1:15 ` Yosry Ahmed
2025-12-09 2:32 ` Herbert Xu
2025-12-09 16:55 ` Yosry Ahmed
2025-12-09 17:21 ` Sridhar, Kanchana P
2025-12-09 17:31 ` Yosry Ahmed
2025-12-09 19:38 ` Sridhar, Kanchana P
2025-12-10 16:01 ` Yosry Ahmed
2025-12-10 18:47 ` Sridhar, Kanchana P
2025-12-10 4:28 ` Herbert Xu
2025-12-10 5:36 ` Sridhar, Kanchana P
2025-12-10 15:53 ` Yosry Ahmed
2025-11-13 18:14 ` [PATCH v13 00/22] zswap compression batching with optimized iaa_crypto driver 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=20251104091235.8793-9-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=kasong@tencent.com \
--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=sj@kernel.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
all inboxes | Powered by JetHome®