net: qed: fix excessive QM ILT lines consumption
authorAlexander Lobakin <alobakin@marvell.com>
Tue, 23 Jun 2020 13:51:33 +0000 (16:51 +0300)
committerSasha Levin <sashal@kernel.org>
Tue, 30 Jun 2020 19:38:42 +0000 (15:38 -0400)
[ Upstream commit d434d02f7e7c24c721365fd594ed781acb18e0da ]

This is likely a copy'n'paste mistake. The amount of ILT lines to
reserve for a single VF was being multiplied by the total VFs count.
This led to a huge redundancy in reservation and potential lines
drainouts.

Fixes: 1408cc1fa48c ("qed: Introduce VFs")
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
drivers/net/ethernet/qlogic/qed/qed_cxt.c

index f1956c4d02a0164ed41963db0c6237ec822ad707..d026da36e47e679dbe2cf5d09a74dd33e99b229d 100644 (file)
@@ -339,7 +339,7 @@ static void qed_cxt_qm_iids(struct qed_hwfn *p_hwfn,
                vf_tids += segs[NUM_TASK_PF_SEGMENTS].count;
        }
 
-       iids->vf_cids += vf_cids * p_mngr->vf_count;
+       iids->vf_cids = vf_cids;
        iids->tids += vf_tids * p_mngr->vf_count;
 
        DP_VERBOSE(p_hwfn, QED_MSG_ILT,