XDP-hints kfuncs for Intel driver igc

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"
 
@@ -311,6 +312,33 @@ 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
@@ -471,6 +499,13 @@ 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;

drivers/net/ethernet/intel/igc/igc_main.c

@@ -1677,14 +1677,36 @@ 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 */
+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,
@@ -2201,6 +2223,8 @@ 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;
@@ -2485,8 +2509,8 @@ 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;
 
@@ -2515,18 +2539,20 @@ 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)) {
@@ -2548,9 +2574,9 @@ 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 */
@@ -2651,6 +2677,15 @@ 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;
@@ -2669,6 +2704,7 @@ 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;
@@ -2686,9 +2722,13 @@ 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;
 
@@ -6443,6 +6483,36 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	return value;
 }
 
+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 int igc_xdp_rx_hash(const struct xdp_md *_ctx, u32 *hash)
+{
+	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);
+
+	return 0;
+}
+
+const struct xdp_metadata_ops igc_xdp_metadata_ops = {
+	.xmo_rx_timestamp		= igc_xdp_rx_timestamp,
+	.xmo_rx_hash			= igc_xdp_rx_hash,
+};
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -6516,6 +6586,7 @@ 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;
 
@@ -6543,6 +6614,7 @@ 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;

tools/testing/selftests/bpf/progs/xdp_hw_metadata.c

@@ -69,15 +69,21 @@ int rx(struct xdp_md *ctx)
 		return XDP_PASS;
 	}
 
-	if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp))
-		bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp);
-	else
+	if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) {
+		meta->xdp_timestamp = bpf_ktime_get_tai_ns();
+		bpf_printk("populated rx_timestamp with  %llu", meta->rx_timestamp);
+		bpf_printk("populated xdp_timestamp with %llu", meta->xdp_timestamp);
+	} else {
 		meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */
+	}
 
-	if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash))
-		bpf_printk("populated rx_hash with %u", meta->rx_hash);
-	else
+	ret = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash);
+	if (ret >= 0) {
+		bpf_printk("populated rx_hash with 0x%08X", meta->rx_hash);
+	} else {
+		bpf_printk("rx_hash not-avail errno:%d", ret);
 		meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */
+	}
 
 	return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS);
 }

tools/testing/selftests/bpf/xdp_hw_metadata.c

@@ -3,6 +3,9 @@
 /* Reference program for verifying XDP metadata on real HW. Functional test
  * only, doesn't test the performance.
  *
+ * BPF-prog bpf_printk info output can be access via
+ * /sys/kernel/debug/tracing/trace_pipe
+ *
  * RX:
  * - UDP 9091 packets are diverted into AF_XDP
  * - Metadata verified:
@@ -27,6 +30,7 @@
 #include <sys/mman.h>
 #include <net/if.h>
 #include <poll.h>
+#include <time.h>
 
 #include "xdp_metadata.h"
 
@@ -134,14 +138,47 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	}
 }
 
-static void verify_xdp_metadata(void *data)
+#define NANOSEC_PER_SEC 1000000000 /* 10^9 */
+static __u64 gettime(clockid_t clock_id)
+{
+	struct timespec t;
+	int res;
+
+	/* See man clock_gettime(2) for type of clock_id's */
+	res = clock_gettime(clock_id, &t);
+
+	if (res < 0)
+		error(res, errno, "Error with clock_gettime()");
+
+	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
+}
+
+static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
 
 	meta = data - sizeof(*meta);
 
-	printf("rx_timestamp: %llu\n", meta->rx_timestamp);
-	printf("rx_hash: %u\n", meta->rx_hash);
+	printf("rx_hash: 0x%08X\n", meta->rx_hash);
+	printf("rx_timestamp:  %llu (sec:%0.4f)\n", meta->rx_timestamp,
+	       (double)meta->rx_timestamp / NANOSEC_PER_SEC);
+	if (meta->rx_timestamp) {
+		__u64 usr_clock = gettime(clock_id);
+		__u64 xdp_clock = meta->xdp_timestamp;
+		__s64 delta_X = xdp_clock - meta->rx_timestamp;
+		__s64 delta_X2U = usr_clock - xdp_clock;
+
+		printf("XDP RX-time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
+		       xdp_clock, (double)xdp_clock / NANOSEC_PER_SEC,
+		       (double)delta_X / NANOSEC_PER_SEC,
+		       (double)delta_X / 1000);
+
+		printf("AF_XDP time:   %llu (sec:%0.4f) delta sec:%0.4f (%0.3f usec)\n",
+		       usr_clock, (double)usr_clock / NANOSEC_PER_SEC,
+		       (double)delta_X2U / NANOSEC_PER_SEC,
+		       (double)delta_X2U / 1000);
+	}
+
 }
 
 static void verify_skb_metadata(int fd)
@@ -189,7 +226,7 @@ static void verify_skb_metadata(int fd)
 	printf("skb hwtstamp is not found!\n");
 }
 
-static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd)
+static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
 {
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds[rxq + 1];
@@ -237,7 +274,8 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd)
 			addr = xsk_umem__add_offset_to_addr(rx_desc->addr);
 			printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n",
 			       xsk, idx, rx_desc->addr, addr, comp_addr);
-			verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr));
+			verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
+					    clock_id);
 			xsk_ring_cons__release(&xsk->rx, 1);
 			refill_rx(xsk, comp_addr);
 		}
@@ -364,6 +402,7 @@ static void timestamping_enable(int fd, int val)
 
 int main(int argc, char *argv[])
 {
+	clockid_t clock_id = CLOCK_TAI;
 	int server_fd = -1;
 	int ret;
 	int i;
@@ -437,7 +476,7 @@ int main(int argc, char *argv[])
 		error(1, -ret, "bpf_xdp_attach");
 
 	signal(SIGINT, handle_signal);
-	ret = verify_metadata(rx_xsk, rxq, server_fd);
+	ret = verify_metadata(rx_xsk, rxq, server_fd, clock_id);
 	close(server_fd);
 	cleanup();
 	if (ret)

tools/testing/selftests/bpf/xdp_metadata.h

@@ -11,5 +11,6 @@
 
 struct xdp_meta {
 	__u64 rx_timestamp;
+	__u64 xdp_timestamp;
 	__u32 rx_hash;
 };