[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <167604167956.1726972.7266620647404438534.stgit@firesoul>
Date: Fri, 10 Feb 2023 16:07:59 +0100
From: Jesper Dangaard Brouer <brouer@...hat.com>
To: bpf@...r.kernel.org
Cc: Jesper Dangaard Brouer <brouer@...hat.com>, netdev@...r.kernel.org,
Stanislav Fomichev <sdf@...gle.com>, martin.lau@...nel.org,
ast@...nel.org, daniel@...earbox.net, alexandr.lobakin@...el.com,
yoong.siang.song@...el.com, anthony.l.nguyen@...el.com,
intel-wired-lan@...ts.osuosl.org, xdp-hints@...-project.net
Subject: [PATCH bpf-next V1] 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 were 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 result 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.
Fixes: 2121c2712f82 ("igc: Add multiple receive queues control supporting")
Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
drivers/net/ethernet/intel/igc/igc.h | 52 +++++++++++++++++++++++++++++
drivers/net/ethernet/intel/igc/igc_main.c | 35 +++++++++++++++++---
2 files changed, 83 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index df3e26c0cf01..a112eeb59525 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -311,6 +311,58 @@ extern char igc_driver_name[];
#define IGC_MRQC_RSS_FIELD_IPV4_UDP 0x00400000
#define IGC_MRQC_RSS_FIELD_IPV6_UDP 0x00800000
+/* RX-desc Write-Back format RSS Type's */
+enum igc_rss_type_num {
+ IGC_RSS_TYPE_NO_HASH = 0,
+ IGC_RSS_TYPE_HASH_TCP_IPV4 = 1,
+ IGC_RSS_TYPE_HASH_IPV4 = 2,
+ IGC_RSS_TYPE_HASH_TCP_IPV6 = 3,
+ IGC_RSS_TYPE_HASH_IPV6_EX = 4,
+ IGC_RSS_TYPE_HASH_IPV6 = 5,
+ IGC_RSS_TYPE_HASH_TCP_IPV6_EX = 6,
+ IGC_RSS_TYPE_HASH_UDP_IPV4 = 7,
+ IGC_RSS_TYPE_HASH_UDP_IPV6 = 8,
+ IGC_RSS_TYPE_HASH_UDP_IPV6_EX = 9,
+ IGC_RSS_TYPE_MAX = 10,
+};
+#define IGC_RSS_TYPE_MAX_TABLE 16
+#define IGC_RSS_TYPE_MASK 0xF
+
+/* igc_rss_type - Rx descriptor RSS type field */
+static inline u8 igc_rss_type(union igc_adv_rx_desc *rx_desc)
+{
+ /* RSS Type 4-bit number: 0-9 (above 9 is reserved) */
+ return rx_desc->wb.lower.lo_dword.hs_rss.pkt_info & IGC_RSS_TYPE_MASK;
+}
+
+/* Packet header type identified by hardware (when BIT(11) is zero).
+ * Even when UDP ports are not part of RSS hash HW still parse and mark UDP bits
+ */
+enum igc_pkt_type_bits {
+ IGC_PKT_TYPE_HDR_IPV4 = BIT(0),
+ IGC_PKT_TYPE_HDR_IPV4_WITH_OPT= BIT(1), /* IPv4 Hdr includes IP options */
+ IGC_PKT_TYPE_HDR_IPV6 = BIT(2),
+ IGC_PKT_TYPE_HDR_IPV6_WITH_EXT= BIT(3), /* IPv6 Hdr includes extensions */
+ IGC_PKT_TYPE_HDR_L4_TCP = BIT(4),
+ IGC_PKT_TYPE_HDR_L4_UDP = BIT(5),
+ IGC_PKT_TYPE_HDR_L4_SCTP= BIT(6),
+ IGC_PKT_TYPE_HDR_NFS = BIT(7),
+ /* Above only valid when BIT(11) is zero */
+ IGC_PKT_TYPE_L2 = BIT(11),
+ IGC_PKT_TYPE_VLAN = BIT(12),
+ IGC_PKT_TYPE_MASK = 0x1FFF, /* 13-bits */
+};
+
+/* igc_pkt_type - Rx descriptor Packet type field */
+static inline u16 igc_pkt_type(union igc_adv_rx_desc *rx_desc)
+{
+ u32 data = le32_to_cpu(rx_desc->wb.lower.lo_dword.data);
+ /* Packet type is 13-bits - as bits (16:4) in lower.lo_dword*/
+ u16 pkt_type = (data >> 4) & IGC_PKT_TYPE_MASK;
+
+ return pkt_type;
+}
+
/* Interrupt defines */
#define IGC_START_ITR 648 /* ~6000 ints/sec */
#define IGC_4K_ITR 980
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 8b572cd2c350..42a072509d2a 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1677,14 +1677,40 @@ 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 */
+struct igc_rss_type {
+ u8 hash_type; /* can contain enum pkt_hash_types */
+} igc_rss_type_table[IGC_RSS_TYPE_MAX_TABLE] = {
+ [IGC_RSS_TYPE_NO_HASH].hash_type = PKT_HASH_TYPE_L2,
+ [IGC_RSS_TYPE_HASH_TCP_IPV4].hash_type = PKT_HASH_TYPE_L4,
+ [IGC_RSS_TYPE_HASH_IPV4].hash_type = PKT_HASH_TYPE_L3,
+ [IGC_RSS_TYPE_HASH_TCP_IPV6].hash_type = PKT_HASH_TYPE_L4,
+ [IGC_RSS_TYPE_HASH_IPV6_EX].hash_type = PKT_HASH_TYPE_L3,
+ [IGC_RSS_TYPE_HASH_IPV6].hash_type = PKT_HASH_TYPE_L3,
+ [IGC_RSS_TYPE_HASH_TCP_IPV6_EX].hash_type = PKT_HASH_TYPE_L4,
+ [IGC_RSS_TYPE_HASH_UDP_IPV4].hash_type = PKT_HASH_TYPE_L4,
+ [IGC_RSS_TYPE_HASH_UDP_IPV6].hash_type = PKT_HASH_TYPE_L4,
+ [IGC_RSS_TYPE_HASH_UDP_IPV6_EX].hash_type = PKT_HASH_TYPE_L4,
+ [10].hash_type = PKT_HASH_TYPE_L2, /* RSS Type above 9 "Reserved" by HW */
+ [11].hash_type = PKT_HASH_TYPE_L2,
+ [12].hash_type = PKT_HASH_TYPE_L2,
+ [13].hash_type = PKT_HASH_TYPE_L2,
+ [14].hash_type = PKT_HASH_TYPE_L2,
+ [15].hash_type = PKT_HASH_TYPE_L2,
+};
+
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);
+ u8 rss_type = igc_rss_type(rx_desc);
+ enum pkt_hash_types hash_type;
+
+ hash_type = igc_rss_type_table[rss_type].hash_type;
+ skb_set_hash(skb, rss_hash, hash_type);
+ }
}
static void igc_rx_vlan(struct igc_ring *rx_ring,
@@ -6501,6 +6527,7 @@ 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;
Powered by blists - more mailing lists