From: Tejasree Kondoj <ktejasree@marvell.com>
To: Akhil Goyal <gakhil@marvell.com>
Cc: Anoob Joseph <anoobj@marvell.com>,
Aakash Sasidharan <asasidharan@marvell.com>,
Gowrishankar Muthukrishnan <gmuthukrishn@marvell.com>,
Vidya Sagar Velumuri <vvelumuri@marvell.com>, <dev@dpdk.org>
Subject: [PATCH v3 2/8] crypto/cnxk: remove packet length checks in crypto offload
Date: Tue, 20 Jun 2023 15:51:00 +0530 [thread overview]
Message-ID: <20230620102106.3970544-3-ktejasree@marvell.com> (raw)
In-Reply-To: <20230620102106.3970544-1-ktejasree@marvell.com>
From: Anoob Joseph <anoobj@marvell.com>
When performing crypto offload, the packet length of the input/output
buffer does not matter. The length that matters is the
cipher/authentication range specified in crypto_op. Since application
can request for ciphering of a small portion of the buffer, the extra
comparison of buffer lengths may result in false failures during
enqueue of OOP operations.
Signed-off-by: Anoob Joseph <anoobj@marvell.com>
---
drivers/crypto/cnxk/cnxk_se.h | 54 +++--------------------------------
1 file changed, 4 insertions(+), 50 deletions(-)
diff --git a/drivers/crypto/cnxk/cnxk_se.h b/drivers/crypto/cnxk/cnxk_se.h
index a85e4c5170..87414eb131 100644
--- a/drivers/crypto/cnxk/cnxk_se.h
+++ b/drivers/crypto/cnxk/cnxk_se.h
@@ -2539,23 +2539,6 @@ fill_fc_params(struct rte_crypto_op *cop, struct cnxk_se_sess *sess,
}
if (unlikely(m_dst != NULL)) {
- uint32_t pkt_len;
-
- /* Try to make room as much as src has */
- pkt_len = rte_pktmbuf_pkt_len(m_dst);
-
- if (unlikely(pkt_len < rte_pktmbuf_pkt_len(m_src))) {
- pkt_len = rte_pktmbuf_pkt_len(m_src) - pkt_len;
- if (!rte_pktmbuf_append(m_dst, pkt_len)) {
- plt_dp_err("Not enough space in "
- "m_dst %p, need %u"
- " more",
- m_dst, pkt_len);
- ret = -EINVAL;
- goto err_exit;
- }
- }
-
if (prepare_iov_from_pkt(m_dst, fc_params.dst_iov, 0)) {
plt_dp_err("Prepare dst iov failed for "
"m_dst %p",
@@ -2650,32 +2633,18 @@ fill_pdcp_params(struct rte_crypto_op *cop, struct cnxk_se_sess *sess,
fc_params.dst_iov = fc_params.src_iov = (void *)src;
prepare_iov_from_pkt_inplace(m_src, &fc_params, &flags);
} else {
- uint32_t pkt_len;
-
/* Out of place processing */
+
fc_params.src_iov = (void *)src;
fc_params.dst_iov = (void *)dst;
/* Store SG I/O in the api for reuse */
- if (prepare_iov_from_pkt(m_src, fc_params.src_iov, 0)) {
+ if (unlikely(prepare_iov_from_pkt(m_src, fc_params.src_iov, 0))) {
plt_dp_err("Prepare src iov failed");
ret = -EINVAL;
goto err_exit;
}
- /* Try to make room as much as src has */
- pkt_len = rte_pktmbuf_pkt_len(m_dst);
-
- if (unlikely(pkt_len < rte_pktmbuf_pkt_len(m_src))) {
- pkt_len = rte_pktmbuf_pkt_len(m_src) - pkt_len;
- if (unlikely(rte_pktmbuf_append(m_dst, pkt_len) == NULL)) {
- plt_dp_err("Not enough space in m_dst %p, need %u more", m_dst,
- pkt_len);
- ret = -EINVAL;
- goto err_exit;
- }
- }
-
if (unlikely(prepare_iov_from_pkt(m_dst, fc_params.dst_iov, 0))) {
plt_dp_err("Prepare dst iov failed for m_dst %p", m_dst);
ret = -EINVAL;
@@ -2689,7 +2658,8 @@ fill_pdcp_params(struct rte_crypto_op *cop, struct cnxk_se_sess *sess,
mdata = alloc_op_meta(&fc_params.meta_buf, m_info->mlen, m_info->pool, infl_req);
if (mdata == NULL) {
plt_dp_err("Could not allocate meta buffer");
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto err_exit;
}
}
@@ -2798,22 +2768,6 @@ fill_pdcp_chain_params(struct rte_crypto_op *cop, struct cnxk_se_sess *sess,
}
if (unlikely(m_dst != NULL)) {
- uint32_t pkt_len;
-
- /* Try to make room as much as src has */
- pkt_len = rte_pktmbuf_pkt_len(m_dst);
-
- if (unlikely(pkt_len < rte_pktmbuf_pkt_len(m_src))) {
- pkt_len = rte_pktmbuf_pkt_len(m_src) - pkt_len;
- if (!rte_pktmbuf_append(m_dst, pkt_len)) {
- plt_dp_err("Not enough space in m_dst "
- "%p, need %u more",
- m_dst, pkt_len);
- ret = -EINVAL;
- goto err_exit;
- }
- }
-
if (unlikely(prepare_iov_from_pkt(m_dst, fc_params.dst_iov, 0))) {
plt_dp_err("Could not prepare m_dst iov %p", m_dst);
ret = -EINVAL;
--
2.25.1
next prev parent reply other threads:[~2023-06-20 10:21 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-06-20 10:20 [PATCH v3 0/8] fixes and improvements to CNXK crypto PMD Tejasree Kondoj
2023-06-20 10:20 ` [PATCH v3 1/8] crypto/cnxk: check for null pointer Tejasree Kondoj
2023-06-20 10:21 ` Tejasree Kondoj [this message]
2023-06-20 10:21 ` [PATCH v3 3/8] crypto/cnxk: use pt inst for null cipher with null auth Tejasree Kondoj
2023-06-20 10:21 ` [PATCH v3 4/8] crypto/cnxk: enable context cache for 103XX Tejasree Kondoj
2023-06-20 10:21 ` [PATCH v3 5/8] crypto/cnxk: add support for raw APIs Tejasree Kondoj
2023-06-23 14:25 ` Thomas Monjalon
2023-06-20 10:21 ` [PATCH v3 6/8] test/crypto: enable raw crypto tests for crypto_cn10k Tejasree Kondoj
2023-06-20 10:21 ` [PATCH v3 7/8] crypto/cnxk: add support for sm4 Tejasree Kondoj
2023-06-20 10:21 ` [PATCH v3 8/8] crypto/cnxk: fix order of ECFPM parameters Tejasree Kondoj
2023-06-20 10:26 ` [PATCH v3 0/8] fixes and improvements to CNXK crypto PMD Akhil Goyal
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=20230620102106.3970544-3-ktejasree@marvell.com \
--to=ktejasree@marvell.com \
--cc=anoobj@marvell.com \
--cc=asasidharan@marvell.com \
--cc=dev@dpdk.org \
--cc=gakhil@marvell.com \
--cc=gmuthukrishn@marvell.com \
--cc=vvelumuri@marvell.com \
/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).