patch 'common/cnxk: fix max number of SQB buffers in clean up' has been queued to stable release 24.11.4
Kevin Traynor
ktraynor at redhat.com
Fri Nov 21 12:20:59 CET 2025
Hi,
FYI, your patch has been queued to stable release 24.11.4
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 11/26/25. So please
shout if anyone has objections.
Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.
Queued patches are on a temporary branch at:
https://github.com/kevintraynor/dpdk-stable
This queued commit can be viewed at:
https://github.com/kevintraynor/dpdk-stable/commit/103bd8849273e26acf455f818895adf35fbc1e32
Thanks.
Kevin
---
>From 103bd8849273e26acf455f818895adf35fbc1e32 Mon Sep 17 00:00:00 2001
From: Sunil Kumar Kori <skori at marvell.com>
Date: Thu, 13 Nov 2025 10:07:57 +0530
Subject: [PATCH] common/cnxk: fix max number of SQB buffers in clean up
[ upstream commit f3c15bb6062475a62451c62ca2c5c9a5e12706c8 ]
By default, SQB pool is created with max (512 buffers) +
extra threshold buffers and aura limit is set to 512 + thr.
But while clean up, aura limit is reset to MAX (512 buffers)
only before destroying the pool.
Hence while destroying the pool, only 512 buffers are cleaned
from aura and extra threshold buffers are left as it is.
At later stage if same SQB pool is created then H/W
throws error for extra threshold buffers that it is already
in pool.
Fixes: 780f90e951a5 ("common/cnxk: restore NIX SQB pool limit before destroy")
Signed-off-by: Sunil Kumar Kori <skori at marvell.com>
---
drivers/common/cnxk/roc_nix_queue.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/common/cnxk/roc_nix_queue.c b/drivers/common/cnxk/roc_nix_queue.c
index 39bd051c94..ccb685240c 100644
--- a/drivers/common/cnxk/roc_nix_queue.c
+++ b/drivers/common/cnxk/roc_nix_queue.c
@@ -2032,5 +2032,5 @@ roc_nix_sq_fini(struct roc_nix_sq *sq)
* for aura drain to succeed.
*/
- roc_npa_aura_limit_modify(sq->aura_handle, NIX_MAX_SQB);
+ roc_npa_aura_limit_modify(sq->aura_handle, sq->aura_sqb_bufs);
rc |= roc_npa_pool_destroy(sq->aura_handle);
plt_free(sq->fc);
--
2.51.0
---
Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- - 2025-11-21 11:05:11.903598220 +0000
+++ 0075-common-cnxk-fix-max-number-of-SQB-buffers-in-clean-u.patch 2025-11-21 11:05:09.555201562 +0000
@@ -1 +1 @@
-From f3c15bb6062475a62451c62ca2c5c9a5e12706c8 Mon Sep 17 00:00:00 2001
+From 103bd8849273e26acf455f818895adf35fbc1e32 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit f3c15bb6062475a62451c62ca2c5c9a5e12706c8 ]
+
@@ -20 +21,0 @@
-Cc: stable at dpdk.org
@@ -28 +29 @@
-index e59cd77538..1de6e51c5e 100644
+index 39bd051c94..ccb685240c 100644
@@ -31 +32 @@
-@@ -2058,5 +2058,5 @@ roc_nix_sq_fini(struct roc_nix_sq *sq)
+@@ -2032,5 +2032,5 @@ roc_nix_sq_fini(struct roc_nix_sq *sq)
More information about the stable
mailing list