Netdev Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Michael Chan <michael.chan@broadcom.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, kuba@kernel.org, gospo@broadcom.com
Subject: [PATCH net 2/9] bnxt_en: reject ETS settings that will starve a TC
Date: Sun, 18 Jul 2021 15:36:26 -0400	[thread overview]
Message-ID: <1626636993-31926-3-git-send-email-michael.chan@broadcom.com> (raw)
In-Reply-To: <1626636993-31926-1-git-send-email-michael.chan@broadcom.com>

[-- Attachment #1: Type: text/plain, Size: 1742 bytes --]

From: Edwin Peer <edwin.peer@broadcom.com>

ETS proportions are presented to HWRM_QUEUE_COS2BW_CFG as minimum
bandwidth constraints. Thus, zero is a legal value for a given TC.
However, if all the other TCs sum up to 100%, then at least one
hardware queue will starve, resulting in guaranteed TX timeouts.
Reject such nonsensical configurations.

Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Edwin Peer <edwin.peer@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 8e90224c43a2..8a68df4d9e59 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -433,6 +433,7 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
 static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 {
 	int total_ets_bw = 0;
+	bool zero = false;
 	u8 max_tc = 0;
 	int i;
 
@@ -453,13 +454,20 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 			break;
 		case IEEE_8021QAZ_TSA_ETS:
 			total_ets_bw += ets->tc_tx_bw[i];
+			zero = zero || !ets->tc_tx_bw[i];
 			break;
 		default:
 			return -ENOTSUPP;
 		}
 	}
-	if (total_ets_bw > 100)
+	if (total_ets_bw > 100) {
+		netdev_warn(bp->dev, "rejecting ETS config exceeding available bandwidth\n");
 		return -EINVAL;
+	}
+	if (zero && total_ets_bw == 100) {
+		netdev_warn(bp->dev, "rejecting ETS config starving a TC\n");
+		return -EINVAL;
+	}
 
 	if (max_tc >= bp->max_tc)
 		*tc = bp->max_tc;
-- 
2.18.1


[-- Attachment #2: S/MIME Cryptographic Signature --]
[-- Type: application/pkcs7-signature, Size: 4209 bytes --]

  parent reply	other threads:[~2021-07-18 19:36 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-18 19:36 [PATCH net 0/9] bnxt_en: Bug fixes Michael Chan
2021-07-18 19:36 ` [PATCH net 1/9] bnxt_en: don't disable an already disabled PCI device Michael Chan
2021-07-18 19:36 ` Michael Chan [this message]
2021-07-18 19:36 ` [PATCH net 3/9] bnxt_en: Refresh RoCE capabilities in bnxt_ulp_probe() Michael Chan
2021-07-18 19:36 ` [PATCH net 4/9] bnxt_en: Add missing check for BNXT_STATE_ABORT_ERR in bnxt_fw_rset_task() Michael Chan
2021-07-18 19:36 ` [PATCH net 5/9] bnxt_en: fix error path of FW reset Michael Chan
2021-07-18 19:36 ` [PATCH net 6/9] bnxt_en: Validate vlan protocol ID on RX packets Michael Chan
2021-07-18 19:36 ` [PATCH net 7/9] bnxt_en: Check abort error state in bnxt_half_open_nic() Michael Chan
2021-07-18 19:36 ` [PATCH net 8/9] bnxt_en: Move bnxt_ptp_init() to bnxt_open() Michael Chan
2021-07-19 10:43   ` Jakub Kicinski
2021-07-19 17:07     ` Richard Cochran
2021-07-20  5:29       ` Michael Chan
2021-07-18 19:36 ` [PATCH net 9/9] bnxt_en: Fix PTP capability discovery Michael Chan
2021-07-19 16:00 ` [PATCH net 0/9] bnxt_en: Bug fixes patchwork-bot+netdevbpf

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=1626636993-31926-3-git-send-email-michael.chan@broadcom.com \
    --to=michael.chan@broadcom.com \
    --cc=davem@davemloft.net \
    --cc=gospo@broadcom.com \
    --cc=kuba@kernel.org \
    --cc=netdev@vger.kernel.org \
    --subject='Re: [PATCH net 2/9] bnxt_en: reject ETS settings that will starve a TC' \
    /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

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).