2 files changed, 159 insertions, 13 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index a00738bf6b19..00a5ee487812 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -13,6 +13,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
+#include <linux/bitfield.h>
 
 #include "igc_hw.h"
 
@@ -314,6 +315,33 @@ 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		GENMASK(3,0) /* 4-bits (3:0) = mask 0x0F */
+
+/* igc_rss_type - Rx descriptor RSS type field */
+static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
+{
+	/* RSS Type 4-bits (3:0) number: 0-9 (above 9 is reserved)
+	 * Accessing the same bits via u16 (wb.lower.lo_dword.hs_rss.pkt_info)
+	 * is slightly slower than via u32 (wb.lower.lo_dword.data)
+	 */
+	return le32_get_bits(rx_desc->wb.lower.lo_dword.data, IGC_RSS_TYPE_MASK);
+}
+
 /* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
@@ -473,6 +501,13 @@ struct igc_rx_buffer {
 	};
 };
 
+/* context wrapper around xdp_buff to provide access to descriptor metadata */
+struct igc_xdp_buff {
+	struct xdp_buff xdp;
+	union igc_adv_rx_desc *rx_desc;
+	ktime_t rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */
+};
+
 struct igc_q_vector {
 	struct igc_adapter *adapter;    /* backlink */
 	void __iomem *itr_register;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index eb4f0e562f60..019ce91c45aa 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1701,14 +1701,36 @@ 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,
@@ -2225,6 +2247,8 @@ static bool igc_alloc_rx_buffers_zc(struct igc_ring *ring, u16 count)
 	if (!count)
 		return ok;
 
+	XSK_CHECK_PRIV_TYPE(struct igc_xdp_buff);
+
 	desc = IGC_RX_DESC(ring, i);
 	bi = &ring->rx_buffer_info[i];
 	i -= ring->count;
@@ -2398,6 +2422,8 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp)
 	nq = txring_txq(ring);
 
 	__netif_tx_lock(nq, cpu);
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
 	res = igc_xdp_init_tx_descriptor(ring, xdpf);
 	__netif_tx_unlock(nq);
 	return res;
@@ -2509,8 +2535,8 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		union igc_adv_rx_desc *rx_desc;
 		struct igc_rx_buffer *rx_buffer;
 		unsigned int size, truesize;
+		struct igc_xdp_buff ctx;
 		ktime_t timestamp = 0;
-		struct xdp_buff xdp;
 		int pkt_offset = 0;
 		void *pktbuf;
 
@@ -2539,18 +2565,20 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		if (igc_test_staterr(rx_desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							pktbuf);
+			ctx.rx_ts = timestamp;
 			pkt_offset = IGC_TS_HDR_LEN;
 			size -= IGC_TS_HDR_LEN;
 		}
 
 		if (!skb) {
-			xdp_init_buff(&xdp, truesize, &rx_ring->xdp_rxq);
-			xdp_prepare_buff(&xdp, pktbuf - igc_rx_offset(rx_ring),
+			xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq);
+			xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring),
 					 igc_rx_offset(rx_ring) + pkt_offset,
 					 size, true);
-			xdp_buff_clear_frags_flag(&xdp);
+			xdp_buff_clear_frags_flag(&ctx.xdp);
+			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &xdp);
+			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
 		if (IS_ERR(skb)) {
@@ -2572,9 +2600,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 		} else if (skb)
 			igc_add_rx_frag(rx_ring, rx_buffer, skb, size);
 		else if (ring_uses_build_skb(rx_ring))
-			skb = igc_build_skb(rx_ring, rx_buffer, &xdp);
+			skb = igc_build_skb(rx_ring, rx_buffer, &ctx.xdp);
 		else
-			skb = igc_construct_skb(rx_ring, rx_buffer, &xdp,
+			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx.xdp,
 						timestamp);
 
 		/* exit if we failed to retrieve a buffer */
@@ -2675,6 +2703,15 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
 	napi_gro_receive(&q_vector->napi, skb);
 }
 
+static struct igc_xdp_buff *xsk_buff_to_igc_ctx(struct xdp_buff *xdp)
+{
+	/* xdp_buff pointer used by ZC code path is alloc as xdp_buff_xsk. The
+	 * igc_xdp_buff shares its layout with xdp_buff_xsk and private
+	 * igc_xdp_buff fields fall into xdp_buff_xsk->cb
+	 */
+       return (struct igc_xdp_buff *)xdp;
+}
+
 static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 {
 	struct igc_adapter *adapter = q_vector->adapter;
@@ -2693,6 +2730,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 	while (likely(total_packets < budget)) {
 		union igc_adv_rx_desc *desc;
 		struct igc_rx_buffer *bi;
+		struct igc_xdp_buff *ctx;
 		ktime_t timestamp = 0;
 		unsigned int size;
 		int res;
@@ -2710,9 +2748,13 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget)
 
 		bi = &ring->rx_buffer_info[ntc];
 
+		ctx = xsk_buff_to_igc_ctx(bi->xdp);
+		ctx->rx_desc = desc;
+
 		if (igc_test_staterr(desc, IGC_RXDADV_STAT_TSIP)) {
 			timestamp = igc_ptp_rx_pktstamp(q_vector->adapter,
 							bi->xdp->data);
+			ctx->rx_ts = timestamp;
 
 			bi->xdp->data += IGC_TS_HDR_LEN;
 
@@ -2800,6 +2842,9 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
+
 	budget = igc_desc_unused(ring);
 
 	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
@@ -6079,9 +6124,18 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
 	size_t n;
 	int i;
 
-	adapter->qbv_enable = qopt->enable;
+	switch (qopt->cmd) {
+	case TAPRIO_CMD_REPLACE:
+		adapter->qbv_enable = true;
+		break;
+	case TAPRIO_CMD_DESTROY:
+		adapter->qbv_enable = false;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	if (!qopt->enable)
+	if (!adapter->qbv_enable)
 		return igc_tsn_clear_schedule(adapter);
 
 	if (qopt->base_time < 0)
@@ -6325,6 +6379,9 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 
 	__netif_tx_lock(nq, cpu);
 
+	/* Avoid transmit queue timeout since we share it with the slow path */
+	txq_trans_cond_update(nq);
+
 	drops = 0;
 	for (i = 0; i < num_frames; i++) {
 		int err;
@@ -6465,6 +6522,58 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	return value;
 }
 
+/* Mapping HW RSS Type to enum xdp_rss_hash_type */
+static enum xdp_rss_hash_type igc_xdp_rss_type[IGC_RSS_TYPE_MAX_TABLE] = {
+	[IGC_RSS_TYPE_NO_HASH]		= XDP_RSS_TYPE_L2,
+	[IGC_RSS_TYPE_HASH_TCP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_TCP,
+	[IGC_RSS_TYPE_HASH_IPV4]	= XDP_RSS_TYPE_L3_IPV4,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_TCP,
+	[IGC_RSS_TYPE_HASH_IPV6_EX]	= XDP_RSS_TYPE_L3_IPV6_EX,
+	[IGC_RSS_TYPE_HASH_IPV6]	= XDP_RSS_TYPE_L3_IPV6,
+	[IGC_RSS_TYPE_HASH_TCP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_TCP_EX,
+	[IGC_RSS_TYPE_HASH_UDP_IPV4]	= XDP_RSS_TYPE_L4_IPV4_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6]	= XDP_RSS_TYPE_L4_IPV6_UDP,
+	[IGC_RSS_TYPE_HASH_UDP_IPV6_EX] = XDP_RSS_TYPE_L4_IPV6_UDP_EX,
+	[10] = XDP_RSS_TYPE_NONE, /* RSS Type above 9 "Reserved" by HW  */
+	[11] = XDP_RSS_TYPE_NONE, /* keep array sized for SW bit-mask   */
+	[12] = XDP_RSS_TYPE_NONE, /* to handle future HW revisons       */
+	[13] = XDP_RSS_TYPE_NONE,
+	[14] = XDP_RSS_TYPE_NONE,
+	[15] = XDP_RSS_TYPE_NONE,
+};
+
+static int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash,
+			   enum xdp_rss_hash_type *rss_type)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (!(ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))
+		return -ENODATA;
+
+	*hash = le32_to_cpu(ctx->rx_desc->wb.lower.hi_dword.rss);
+	*rss_type = igc_xdp_rss_type[igc_rss_type(ctx->rx_desc)];
+
+	return 0;
+}
+
+static int igc_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp)
+{
+	const struct igc_xdp_buff *ctx = (void *)_ctx;
+
+	if (igc_test_staterr(ctx->rx_desc, IGC_RXDADV_STAT_TSIP)) {
+		*timestamp = ctx->rx_ts;
+
+		return 0;
+	}
+
+	return -ENODATA;
+}
+
+static const struct xdp_metadata_ops igc_xdp_metadata_ops = {
+	.xmo_rx_hash			= igc_xdp_rx_hash,
+	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
+};
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6538,6 +6647,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
+	netdev->xdp_metadata_ops = &igc_xdp_metadata_ops;
 	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
@@ -6565,6 +6675,7 @@ 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;