igc: Enable and fix RX hash usage by netstack

When function igc_rx_hash() was introduced in v4.20 via commit 0507ef8a0372
("igc: Add transmit and receive fastpath and interrupt handlers"), the
hardware wasn't configured to provide RSS hash, thus it made sense to not
enable net_device NETIF_F_RXHASH feature bit.

The NIC hardware was configured to enable RSS hash info in v5.2 via commit
2121c2712f82 ("igc: Add multiple receive queues control supporting"), but
forgot to set the NETIF_F_RXHASH feature bit.

The original implementation of igc_rx_hash() didn't extract the associated
pkt_hash_type, but statically set PKT_HASH_TYPE_L3. The largest portions of
this patch are about extracting the RSS Type from the hardware and mapping
this to enum pkt_hash_types. This was based on Foxville i225 software user
manual rev-1.3.1 and tested on Intel Ethernet Controller I225-LM (rev 03).

For UDP it's worth noting that RSS (type) hashing have been disabled both for
IPv4 and IPv6 (see IGC_MRQC_RSS_FIELD_IPV4_UDP + IGC_MRQC_RSS_FIELD_IPV6_UDP)
because hardware RSS doesn't handle fragmented pkts well when enabled (can
cause out-of-order). This results in PKT_HASH_TYPE_L3 for UDP packets, and
hash value doesn't include UDP port numbers. Not being PKT_HASH_TYPE_L4, have
the effect that netstack will do a software based hash calc calling into
flow_dissect, but only when code calls skb_get_hash(), which doesn't
necessary happen for local delivery.

For QA verification testing I wrote a small bpftrace prog:
 [0] https://github.com/xdp-project/xdp-project/blob/master/areas/hints/monitor_skb_hash_on_dev.bt

Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Yoong Siang <yoong.siang.song@intel.com>
Link: https://lore.kernel.org/bpf/168182464270.616355.11391652654430626584.stgit@firesoul

1 files changed, 27 insertions, 4 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index ba49728be919..f6b03e0372e0 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1687,14 +1687,36 @@ static void igc_rx_checksum(struct igc_ring *ring,
 		   le32_to_cpu(rx_desc->wb.upper.status_error));
 }
 
+/* Mapping HW RSS Type to enum pkt_hash_types */
+static const enum pkt_hash_types igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= PKT_HASH_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV4]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_IPV6]	= PKT_HASH_TYPE_L3,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= PKT_HASH_TYPE_L4,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = PKT_HASH_TYPE_L4,
+	[10] = PKT_HASH_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = PKT_HASH_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = PKT_HASH_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = PKT_HASH_TYPE_NONE,
+	[14] = PKT_HASH_TYPE_NONE,
+	[15] = PKT_HASH_TYPE_NONE,
+};
+
 static inline void igc_rx_hash(struct igc_ring *ring,
 			       union igc_adv_rx_desc *rx_desc,
 			       struct sk_buff *skb)
 {
-	if (ring->netdev->features & NETIF_F_RXHASH)
-		skb_set_hash(skb,
-			     le32_to_cpu(rx_desc->wb.lower.hi_dword.rss),
-			     PKT_HASH_TYPE_L3);
+	if (ring->netdev->features & NETIF_F_RXHASH) {
+		u32 rss_hash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss);
+		u32 rss_type = igc_rss_type(rx_desc);
+
+		skb_set_hash(skb, rss_hash, igc_rss_type_table[rss_type]);
+	}
 }
 
 static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -6551,6 +6573,7 @@ static int igc_probe(struct pci_dev *pdev,
 	netdev->features |= NETIF_F_TSO;
 	netdev->features |= NETIF_F_TSO6;
 	netdev->features |= NETIF_F_TSO_ECN;
+	netdev->features |= NETIF_F_RXHASH;
 	netdev->features |= NETIF_F_RXCSUM;
 	netdev->features |= NETIF_F_HW_CSUM;
 	netdev->features |= NETIF_F_SCTP_CRC;