[dpdk-stable] patch 'net/qede: fix PF fastpath status block index' has been queued to stable release 16.11.1
Yuanhan Liu
yuanhan.liu at linux.intel.com
Mon Jan 23 08:47:28 CET 2017
Hi,
FYI, your patch has been queued to stable release 16.11.1
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable
yet. It will be pushed if I get no objections before 01/28/17.
So please shout if anyone has objections.
---
Note 16.11 is a LTS release. v16.11.1 is planned to be released
shortly (about 2-3 weeks) after v17.02.
---
Thanks.
--yliu
---
>From 0032f48fb417956ace999cdb65dd9fc19a870432 Mon Sep 17 00:00:00 2001
From: Harish Patil <harish.patil at qlogic.com>
Date: Fri, 6 Jan 2017 00:16:47 -0800
Subject: [PATCH] net/qede: fix PF fastpath status block index
[ upstream commit 9dd9cb4274e573d8bc927327f7a73f1a881746f6 ]
Allocate double the number of fastpath status block index
since the PF RX/TX queues are not sharing the status block.
This is an interim solution till other parts of the code
is modified to handle the same.
Fixes: f1e4b6c0acee ("net/qede: fix status block index for VF queues")
Signed-off-by: Harish Patil <harish.patil at qlogic.com>
---
drivers/net/qede/qede_rxtx.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
index 2e181c8..a34b665 100644
--- a/drivers/net/qede/qede_rxtx.c
+++ b/drivers/net/qede/qede_rxtx.c
@@ -435,13 +435,15 @@ int qede_alloc_fp_resc(struct qede_dev *qdev)
struct ecore_dev *edev = &qdev->edev;
struct qede_fastpath *fp;
uint32_t num_sbs;
- int rc, i;
+ uint16_t i;
+ uint16_t sb_idx;
+ int rc;
if (IS_VF(edev))
ecore_vf_get_num_sbs(ECORE_LEADING_HWFN(edev), &num_sbs);
else
- num_sbs = (ecore_cxt_get_proto_cid_count
- (ECORE_LEADING_HWFN(edev), PROTOCOLID_ETH, NULL)) / 2;
+ num_sbs = ecore_cxt_get_proto_cid_count
+ (ECORE_LEADING_HWFN(edev), PROTOCOLID_ETH, NULL);
if (num_sbs == 0) {
DP_ERR(edev, "No status blocks available\n");
@@ -459,7 +461,11 @@ int qede_alloc_fp_resc(struct qede_dev *qdev)
for (i = 0; i < QEDE_QUEUE_CNT(qdev); i++) {
fp = &qdev->fp_array[i];
- if (qede_alloc_mem_sb(qdev, fp->sb_info, i % num_sbs)) {
+ if (IS_VF(edev))
+ sb_idx = i % num_sbs;
+ else
+ sb_idx = i;
+ if (qede_alloc_mem_sb(qdev, fp->sb_info, sb_idx)) {
qede_free_fp_arrays(qdev);
return -ENOMEM;
}
--
1.9.0
More information about the stable
mailing list