From: Nithin Dabilpuram <ndabilpuram@marvell.com>
To: Nithin Dabilpuram <ndabilpuram@marvell.com>,
Kiran Kumar K <kirankumark@marvell.com>,
Sunil Kumar Kori <skori@marvell.com>,
Satha Rao <skoteshwar@marvell.com>
Cc: <jerinj@marvell.com>, <dev@dpdk.org>,
Kommula Shiva Shankar <kshankar@marvell.com>
Subject: [PATCH 18/31] common/cnxk: enable CQ stashing
Date: Fri, 11 Aug 2023 14:27:52 +0530 [thread overview]
Message-ID: <20230811085805.441256-18-ndabilpuram@marvell.com> (raw)
In-Reply-To: <20230811085805.441256-1-ndabilpuram@marvell.com>
From: Kommula Shiva Shankar <kshankar@marvell.com>
This patch enables CQ stashing for better CQE
processing performance
Signed-off-by: Kommula Shiva Shankar <kshankar@marvell.com>
---
drivers/common/cnxk/roc_features.h | 6 ++++++
drivers/common/cnxk/roc_nix.h | 1 +
drivers/common/cnxk/roc_nix_queue.c | 7 +++++++
3 files changed, 14 insertions(+)
diff --git a/drivers/common/cnxk/roc_features.h b/drivers/common/cnxk/roc_features.h
index 815f800e7a..a461ca46c5 100644
--- a/drivers/common/cnxk/roc_features.h
+++ b/drivers/common/cnxk/roc_features.h
@@ -46,6 +46,12 @@ roc_feature_nix_has_reass(void)
return roc_model_is_cn10ka();
}
+static inline bool
+roc_feature_nix_has_cqe_stash(void)
+{
+ return roc_model_is_cn10ka_b0();
+}
+
static inline bool
roc_feature_nix_has_rxchan_multi_bpid(void)
{
diff --git a/drivers/common/cnxk/roc_nix.h b/drivers/common/cnxk/roc_nix.h
index bb55fbe971..5892de6b24 100644
--- a/drivers/common/cnxk/roc_nix.h
+++ b/drivers/common/cnxk/roc_nix.h
@@ -368,6 +368,7 @@ struct roc_nix_cq {
/* Input parameters */
uint16_t qid;
uint32_t nb_desc;
+ uint8_t stash_thresh;
/* End of Input parameters */
uint16_t drop_thresh;
struct roc_nix *roc_nix;
diff --git a/drivers/common/cnxk/roc_nix_queue.c b/drivers/common/cnxk/roc_nix_queue.c
index 5e689d08be..f96d5c3a96 100644
--- a/drivers/common/cnxk/roc_nix_queue.c
+++ b/drivers/common/cnxk/roc_nix_queue.c
@@ -908,6 +908,13 @@ roc_nix_cq_init(struct roc_nix *roc_nix, struct roc_nix_cq *cq)
}
cq_ctx->bp = cq->drop_thresh;
+ if (roc_feature_nix_has_cqe_stash()) {
+ if (cq_ctx->caching) {
+ cq_ctx->stashing = 1;
+ cq_ctx->stash_thresh = cq->stash_thresh;
+ }
+ }
+
rc = mbox_process(mbox);
mbox_put(mbox);
if (rc)
--
2.25.1
next prev parent reply other threads:[~2023-08-11 9:00 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-11 8:57 [PATCH 01/31] common/cnxk: add aura ref count mechanism Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 02/31] common/cnxk: optimize time while configuring fc on VF Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 03/31] common/cnxk: use only user sqb slack when provided Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 04/31] common/cnxk: add workaround for CPT ctx fetch issue Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 05/31] common/cnxk: support rate limit on PFC TM tree Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 06/31] common/cnxk: fixes CGX promisc toggling Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 07/31] common/cnxk: fix xstats for different packet sizes Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 08/31] common/cnxk: disable BP on SDP link while closing SQ Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 09/31] common/cnxk: fix leak in error path Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 10/31] common/cnxk: fix different size bit operations Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 11/31] " Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 12/31] common/cnxk: remove unnecessory ROC API calls Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 13/31] common/cnxk: sync MAC addr set mailbox structure Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 14/31] common/cnxk: add API to get Rx chan count from NIX Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 15/31] common/cnxk: fix BP threshold calculation Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 16/31] common/cnxk: allow same TC on multiple RQs Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 17/31] common/cnxk: expose different params for bp config Nithin Dabilpuram
2023-08-11 8:57 ` Nithin Dabilpuram [this message]
2023-08-11 8:57 ` [PATCH 19/31] common/cnxk: fix incorrect aura ID Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 20/31] net/cnxk: fix CQ allocation Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 21/31] net/cnxk: fix issue with GCC 4.8 Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 22/31] net/cnxk: add mapping of DMAC address indexes Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 23/31] net/cnxk: support rate limit in PFC TM tree Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 24/31] net/cnxk: move MAC address set from init to configure Nithin Dabilpuram
2023-08-11 8:57 ` [PATCH 25/31] net/cnxk: update different size bit operations Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 26/31] net/cnxk: fix uninitialized variable Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 27/31] net/cnxk: fix usage of mbuf rearm data Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 28/31] net/cnxk: fix uninitialized variable Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 29/31] net/cnxk: check returned value for null Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 30/31] net/cnxk: add flag check for extension header when used Nithin Dabilpuram
2023-08-11 8:58 ` [PATCH 31/31] net/cnxk: fixes for IPv6 header in reassembly Nithin Dabilpuram
2023-08-14 12:07 ` Jerin Jacob
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=20230811085805.441256-18-ndabilpuram@marvell.com \
--to=ndabilpuram@marvell.com \
--cc=dev@dpdk.org \
--cc=jerinj@marvell.com \
--cc=kirankumark@marvell.com \
--cc=kshankar@marvell.com \
--cc=skori@marvell.com \
--cc=skoteshwar@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).