Commit 0553640d authored by Vladimir Shulman's avatar Vladimir Shulman Committed by Kalle Valo

wil6210: allow to handle Rx on 2 cores

Allow network stack part of Rx processing to run on separate core,
relaxing CPU utilization on the core used for Rx NAPI.

If RXHASH feature is enabled, the driver sets rxhash of each skb to 1
to enable RPS. The core for processing the rx skb is determined by RPS
mechanism according to rx_cpus bit mask which is configured at user level.
For processing skbs on different core from the core which processes
the interrupts, it is recommended not to enable core 0 in rx_cpus bit mask.
Signed-off-by: default avatarVladimir Shulman <QCA_shulmanv@QCA.qualcomm.com>
Signed-off-by: default avatarVladimir Kondratiev <qca_vkondrat@qca.qualcomm.com>
Signed-off-by: default avatarKalle Valo <kvalo@qca.qualcomm.com>
parent b9eeb512
......@@ -174,7 +174,8 @@ void *wil_if_alloc(struct device *dev)
ndev->ieee80211_ptr = wdev;
ndev->hw_features = NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
NETIF_F_SG | NETIF_F_GRO |
NETIF_F_TSO | NETIF_F_TSO6;
NETIF_F_TSO | NETIF_F_TSO6 |
NETIF_F_RXHASH;
ndev->features |= ndev->hw_features;
SET_NETDEV_DEV(ndev, wiphy_dev(wdev->wiphy));
......
......@@ -541,6 +541,14 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
[GRO_DROP] = "GRO_DROP",
};
if (ndev->features & NETIF_F_RXHASH)
/* fake L4 to ensure it won't be re-calculated later
* set hash to any non-zero value to activate rps
* mechanism, core will be chosen according
* to user-level rps configuration.
*/
skb_set_hash(skb, 1, PKT_HASH_TYPE_L4);
skb_orphan(skb);
if (wdev->iftype == NL80211_IFTYPE_AP && !wil->ap_isolate) {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment