i40e: Fix RSS size at init since default num queue calculation has changed

With changes to default number of queue pairs that the interface comes up with
from 1 per online CPU to 1 per lan_msix, we need to make sure we recalculate
rss_size. We will now recalculate rss_size based on number of queues enabled in
the VSI.

Without this fix if the max_lan_msix < num_online_cpu we will be coming up
with fewer queues but will be populating rss_size based on num_online_cpus.
This will result in packets getting silently dropped because RSS LUT has queues
that are not enabled.

Change-ID: Ifac8796ce1be1758bb0c34f38dbf4a3a76621e76
Signed-off-by: Anjali Singhai Jain <anjali.singhai@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
This commit is contained in:
Anjali Singhai Jain
2015-02-24 06:58:50 +00:00
committed by Jeff Kirsher
parent 5db4cb59cd
commit 66ddcffb1a
2 changed files with 5 additions and 1 deletions

View File

@@ -472,6 +472,7 @@ struct i40e_vsi {
u16 tx_itr_setting;
u16 rss_table_size;
u16 rss_size;
u16 max_frame;
u16 rx_hdr_len;