DPDK patches and discussions
 help / color / mirror / Atom feed
From: Radu Nicolau <radu.nicolau@intel.com>
To: dev@dpdk.org
Cc: Radu Nicolau <radu.nicolau@intel.com>,
	stable@dpdk.org, Kai Ji <kai.ji@intel.com>
Subject: [PATCH 2/2] crypto/qat: align the the vector address
Date: Tue,  2 Dec 2025 10:46:06 +0000	[thread overview]
Message-ID: <20251202104606.849348-1-radu.nicolau@intel.com> (raw)

Align the vector address rather than computed source address to
make sure the alignement is properly propagated.

Fixes: 253174309ff7 ("crypto/qat: fix source buffer alignment")
Cc: stable@dpdk.org

Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
---
 drivers/crypto/qat/dev/qat_crypto_pmd_gens.h | 33 +++++++++-----------
 1 file changed, 15 insertions(+), 18 deletions(-)

diff --git a/drivers/crypto/qat/dev/qat_crypto_pmd_gens.h b/drivers/crypto/qat/dev/qat_crypto_pmd_gens.h
index 67dc889b50..3883a06aaf 100644
--- a/drivers/crypto/qat/dev/qat_crypto_pmd_gens.h
+++ b/drivers/crypto/qat/dev/qat_crypto_pmd_gens.h
@@ -443,6 +443,21 @@ qat_sym_build_req_set_data(struct icp_qat_fw_la_bulk_req *req,
 			n_dst > QAT_SYM_SGL_MAX_NUMBER))
 		return -1;
 
+	/* For crypto API only: try to align the in-place buffers*/
+	if (op != NULL && likely(n_dst == 0) && likely(!is_sgl)) {
+		rte_iova_t offset = src_vec[0].iova & RTE_CACHE_LINE_MASK;
+		if (offset) {
+			rte_iova_t buff_addr = rte_mbuf_iova_get(op->sym->m_src);
+			/* make sure src_data_start is still within the buffer */
+			if (src_data_start - offset >= buff_addr) {
+				src_vec[0].iova -= offset;
+				src_vec[0].len += offset;
+				ofs->ofs.auth.head += offset;
+				ofs->ofs.cipher.head += offset;
+			}
+		}
+	}
+
 	if (likely(!is_sgl)) {
 		src_data_start = src_vec[0].iova;
 		tl_src = total_len_src =
@@ -503,24 +518,6 @@ qat_sym_build_req_set_data(struct icp_qat_fw_la_bulk_req *req,
 			dst_data_start = src_data_start;
 	}
 
-	/* For crypto API only try to align the in-place buffers*/
-	if (op != NULL && likely(n_dst == 0)) {
-		uint16_t offset = src_data_start & RTE_CACHE_LINE_MASK;
-		if (offset) {
-			rte_iova_t buff_addr = rte_mbuf_iova_get(op->sym->m_src);
-			/* make sure src_data_start is still within the buffer */
-			if (src_data_start - offset >= buff_addr) {
-				src_data_start -= offset;
-				dst_data_start = src_data_start;
-				ofs->ofs.auth.head += offset;
-				ofs->ofs.cipher.head += offset;
-				tl_src += offset;
-				total_len_src = tl_src;
-				total_len_dst = tl_src;
-			}
-		}
-	}
-
 	req->comn_mid.src_data_addr = src_data_start;
 	req->comn_mid.dest_data_addr = dst_data_start;
 	req->comn_mid.src_length = total_len_src;
-- 
2.50.1


                 reply	other threads:[~2025-12-02 10:46 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=20251202104606.849348-1-radu.nicolau@intel.com \
    --to=radu.nicolau@intel.com \
    --cc=dev@dpdk.org \
    --cc=kai.ji@intel.com \
    --cc=stable@dpdk.org \
    /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).