Skip to contentSkip to conversation

bnxt_en: Fix the resource check condition for RSS contexts

PATCH Applied Michael Chan 3 participants 3 messages Jul 3, 2024 – Jul 4, 2024

Subsystems (3)
lore
Share & tools
lore

Michael Chan

author maintainer
#0 lore raw

PATCH 1/1 bnxt_en: Fix the resource check condition for RSS contexts

From: Pavan Chebbi <[email protected]>

While creating a new RSS context, bnxt_rfs_capable() currently makes a strict check to see if the required VNICs are already available. If the current VNICs are not what is required, either too many or not enough, it will call the firmware to reserve the exact number required.

There is a bug in the firmware when the driver tries to relinquish some reserved VNICs and RSS contexts. It will cause the default VNIC to lose its RSS configuration and cause receive packets to be placed incorrectly.

Workaround this problem by skipping the resource reduction. The driver will not reduce the VNIC and RSS context reservations when a context is deleted. The resources will be available for use when new contexts are created later.

Potentially, this workaround can cause us to run out of VNIC and RSS contexts if there are a lot of VF functions creating and deleting RSS contexts. In the future, we will conditionally disable this workaround when the firmware fix is available.

Fixes 438ba39b25fe ("bnxt_en: Improve RSS context reservation infrastructure")
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/net/ethernet/broadcom/bnxt/bnxt.c +5 -1
index a6d69a45fa01..53085058100c 100644
@@ -12669,7 +12669,11 @@ bool bnxt_rfs_capable(struct bnxt *bp, bool new_rss_ctx)
 	if (!BNXT_NEW_RM(bp))
 		return true;
 
-	if (hwr.vnic == bp->hw_resc.resv_vnics &&
+	/* Do not reduce VNIC and RSS ctx reservations.  There is a FW
+	 * issue that will mess up the default VNIC if we reduce the
+	 * reservations.
+	 */
+	if (hwr.vnic <= bp->hw_resc.resv_vnics &&
 	    hwr.rss_ctx <= bp->hw_resc.resv_rsscos_ctxs)
 		return true;
 
Signature · 1 line
2.30.1
reviewer Reviewed-by on v1 1/1
#1 lore raw
Quoted 23 lines · Michael Chan

From: Pavan Chebbi <[email protected]>

While creating a new RSS context, bnxt_rfs_capable() currently makes a strict check to see if the required VNICs are already available. If the current VNICs are not what is required, either too many or not enough, it will call the firmware to reserve the exact number required.

There is a bug in the firmware when the driver tries to relinquish some reserved VNICs and RSS contexts. It will cause the default VNIC to lose its RSS configuration and cause receive packets to be placed incorrectly.

Workaround this problem by skipping the resource reduction. The driver will not reduce the VNIC and RSS context reservations when a context is deleted. The resources will be available for use when new contexts are created later.

Potentially, this workaround can cause us to run out of VNIC and RSS contexts if there are a lot of VF functions creating and deleting RSS contexts. In the future, we will conditionally disable this workaround when the firmware fix is available.

Quoted 6 lines
Fixes 438ba39b25fe ("bnxt_en: Improve RSS context reservation infrastructure")
#2 lore raw
In reply to Michael Chan
This patch was applied to netdev/net.git (main) by Jakub Kicinski <[email protected]>:

Hello:

This patch was applied to netdev/net.git (main)
by Jakub Kicinski <[email protected]>:

Quoted 9 lines · On Wed, 3 Jul 2024 11:01:12 -0700 you wrote:

From: Pavan Chebbi <[email protected]>

While creating a new RSS context, bnxt_rfs_capable() currently makes a strict check to see if the required VNICs are already available. If the current VNICs are not what is required, either too many or not enough, it will call the firmware to reserve the exact number required.

[...]

Here is the summary with links:
- [net] bnxt_en: Fix the resource check condition for RSS contexts

    https://git.kernel.org/netdev/net/c/5d350dc3429b

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html