Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2023-11-30

We've added 30 non-merge commits during the last 7 day(s) which contain
a total of 58 files changed, 1598 insertions(+), 154 deletions(-).

The main changes are:

1) Add initial TX metadata implementation for AF_XDP with support in mlx5
   and stmmac drivers. Two types of offloads are supported right now, that
   is, TX timestamp and TX checksum offload, from Stanislav Fomichev with
   stmmac implementation from Song Yoong Siang.

2) Change BPF verifier logic to validate global subprograms lazily instead
   of unconditionally before the main program, so they can be guarded using
   BPF CO-RE techniques, from Andrii Nakryiko.

3) Add BPF link_info support for uprobe multi link along with bpftool
   integration for the latter, from Jiri Olsa.

4) Use pkg-config in BPF selftests to determine ld flags which is
   in particular needed for linking statically, from Akihiko Odaki.

5) Fix a few BPF selftest failures to adapt to the upcoming LLVM18,
   from Yonghong Song.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (30 commits)
  bpf/tests: Remove duplicate JSGT tests
  selftests/bpf: Add TX side to xdp_hw_metadata
  selftests/bpf: Convert xdp_hw_metadata to XDP_USE_NEED_WAKEUP
  selftests/bpf: Add TX side to xdp_metadata
  selftests/bpf: Add csum helpers
  selftests/xsk: Support tx_metadata_len
  xsk: Add option to calculate TX checksum in SW
  xsk: Validate xsk_tx_metadata flags
  xsk: Document tx_metadata_len layout
  net: stmmac: Add Tx HWTS support to XDP ZC
  net/mlx5e: Implement AF_XDP TX timestamp and checksum offload
  tools: ynl: Print xsk-features from the sample
  xsk: Add TX timestamp and TX checksum offload support
  xsk: Support tx_metadata_len
  selftests/bpf: Use pkg-config for libelf
  selftests/bpf: Override PKG_CONFIG for static builds
  selftests/bpf: Choose pkg-config for the target
  bpftool: Add support to display uprobe_multi links
  selftests/bpf: Add link_info test for uprobe_multi link
  selftests/bpf: Use bpf_link__destroy in fill_link_info tests
  ...
====================

Conflicts:

Documentation/netlink/specs/netdev.yaml:
  839ff60df3ab ("net: page_pool: add nlspec for basic access to page pools")
  48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
https://lore.kernel.org/all/20231201094705.1ee3cab8@canb.auug.org.au/

While at it also regen, tree is dirty after:
  48eb03dd2630 ("xsk: Add TX timestamp and TX checksum offload support")
looks like code wasn't re-rendered after "render-max" was removed.

Link: https://lore.kernel.org/r/20231130145708.32573-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 208 insertions, 27 deletions

diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index c3ba40d0b9de..3291625ba4fb 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -10,7 +10,9 @@
  *   - rx_hash
  *
  * TX:
- * - TBD
+ * - UDP 9091 packets trigger TX reply
+ * - TX HW timestamp is requested and reported back upon completion
+ * - TX checksum is requested
  */
 
 #include <test_progs.h>
@@ -24,15 +26,18 @@
 #include <linux/net_tstamp.h>
 #include <linux/udp.h>
 #include <linux/sockios.h>
+#include <linux/if_xdp.h>
 #include <sys/mman.h>
 #include <net/if.h>
 #include <ctype.h>
 #include <poll.h>
 #include <time.h>
+#include <unistd.h>
+#include <libgen.h>
 
 #include "xdp_metadata.h"
 
-#define UMEM_NUM 16
+#define UMEM_NUM 256
 #define UMEM_FRAME_SIZE XSK_UMEM__DEFAULT_FRAME_SIZE
 #define UMEM_SIZE (UMEM_FRAME_SIZE * UMEM_NUM)
 #define XDP_FLAGS (XDP_FLAGS_DRV_MODE | XDP_FLAGS_REPLACE)
@@ -48,11 +53,14 @@ struct xsk {
 };
 
 struct xdp_hw_metadata *bpf_obj;
-__u16 bind_flags = XDP_COPY;
+__u16 bind_flags = XDP_USE_NEED_WAKEUP | XDP_ZEROCOPY;
 struct xsk *rx_xsk;
 const char *ifname;
 int ifindex;
 int rxq;
+bool skip_tx;
+__u64 last_hw_rx_timestamp;
+__u64 last_xdp_rx_timestamp;
 
 void test__fail(void) { /* for network_helpers.c */ }
 
@@ -68,7 +76,8 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.flags = XDP_UMEM_UNALIGNED_CHUNK_FLAG,
+		.flags = XSK_UMEM__DEFAULT_FLAGS,
+		.tx_metadata_len = sizeof(struct xsk_tx_metadata),
 	};
 	__u32 idx;
 	u64 addr;
@@ -110,7 +119,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id)
 	for (i = 0; i < UMEM_NUM / 2; i++) {
 		addr = (UMEM_NUM / 2 + i) * UMEM_FRAME_SIZE;
 		printf("%p: rx_desc[%d] -> %lx\n", xsk, i, addr);
-		*xsk_ring_prod__fill_addr(&xsk->fill, i) = addr;
+		*xsk_ring_prod__fill_addr(&xsk->fill, idx + i) = addr;
 	}
 	xsk_ring_prod__submit(&xsk->fill, ret);
 
@@ -131,12 +140,22 @@ static void refill_rx(struct xsk *xsk, __u64 addr)
 	__u32 idx;
 
 	if (xsk_ring_prod__reserve(&xsk->fill, 1, &idx) == 1) {
-		printf("%p: complete idx=%u addr=%llx\n", xsk, idx, addr);
+		printf("%p: complete rx idx=%u addr=%llx\n", xsk, idx, addr);
 		*xsk_ring_prod__fill_addr(&xsk->fill, idx) = addr;
 		xsk_ring_prod__submit(&xsk->fill, 1);
 	}
 }
 
+static int kick_tx(struct xsk *xsk)
+{
+	return sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0);
+}
+
+static int kick_rx(struct xsk *xsk)
+{
+	return recvfrom(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, NULL);
+}
+
 #define NANOSEC_PER_SEC 1000000000 /* 10^9 */
 static __u64 gettime(clockid_t clock_id)
 {
@@ -152,6 +171,17 @@ static __u64 gettime(clockid_t clock_id)
 	return (__u64) t.tv_sec * NANOSEC_PER_SEC + t.tv_nsec;
 }
 
+static void print_tstamp_delta(const char *name, const char *refname,
+			       __u64 tstamp, __u64 reference)
+{
+	__s64 delta = (__s64)reference - (__s64)tstamp;
+
+	printf("%s:   %llu (sec:%0.4f) delta to %s sec:%0.4f (%0.3f usec)\n",
+	       name, tstamp, (double)tstamp / NANOSEC_PER_SEC, refname,
+	       (double)delta / NANOSEC_PER_SEC,
+	       (double)delta / 1000);
+}
+
 static void verify_xdp_metadata(void *data, clockid_t clock_id)
 {
 	struct xdp_meta *meta;
@@ -164,25 +194,20 @@ static void verify_xdp_metadata(void *data, clockid_t clock_id)
 		printf("rx_hash: 0x%X with RSS type:0x%X\n",
 		       meta->rx_hash, meta->rx_hash_type);
 
-	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);
+		__u64 ref_tstamp = gettime(clock_id);
+
+		/* store received timestamps to calculate a delta at tx */
+		last_hw_rx_timestamp = meta->rx_timestamp;
+		last_xdp_rx_timestamp = meta->xdp_timestamp;
+
+		print_tstamp_delta("HW RX-time", "User RX-time",
+				   meta->rx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User RX-time",
+				   meta->xdp_timestamp, ref_tstamp);
+	} else {
+		printf("No rx_timestamp\n");
 	}
-
 }
 
 static void verify_skb_metadata(int fd)
@@ -230,6 +255,129 @@ static void verify_skb_metadata(int fd)
 	printf("skb hwtstamp is not found!\n");
 }
 
+static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	__u64 addr;
+	void *data;
+	__u32 idx;
+
+	if (!xsk_ring_cons__peek(&xsk->comp, 1, &idx))
+		return false;
+
+	addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx);
+	data = xsk_umem__get_data(xsk->umem_area, addr);
+	meta = data - sizeof(struct xsk_tx_metadata);
+
+	printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr);
+
+	if (meta->completion.tx_timestamp) {
+		__u64 ref_tstamp = gettime(clock_id);
+
+		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
+				   meta->completion.tx_timestamp, ref_tstamp);
+		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
+				   last_xdp_rx_timestamp, ref_tstamp);
+		print_tstamp_delta("HW RX-time", "HW TX-complete-time",
+				   last_hw_rx_timestamp, meta->completion.tx_timestamp);
+	} else {
+		printf("No tx_timestamp\n");
+	}
+
+	xsk_ring_cons__release(&xsk->comp, 1);
+
+	return true;
+}
+
+#define swap(a, b, len) do { \
+	for (int i = 0; i < len; i++) { \
+		__u8 tmp = ((__u8 *)a)[i]; \
+		((__u8 *)a)[i] = ((__u8 *)b)[i]; \
+		((__u8 *)b)[i] = tmp; \
+	} \
+} while (0)
+
+static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
+{
+	struct xsk_tx_metadata *meta;
+	struct ipv6hdr *ip6h = NULL;
+	struct iphdr *iph = NULL;
+	struct xdp_desc *tx_desc;
+	struct udphdr *udph;
+	struct ethhdr *eth;
+	__sum16 want_csum;
+	void *data;
+	__u32 idx;
+	int ret;
+	int len;
+
+	ret = xsk_ring_prod__reserve(&xsk->tx, 1, &idx);
+	if (ret != 1) {
+		printf("%p: failed to reserve tx slot\n", xsk);
+		return;
+	}
+
+	tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx);
+	tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata);
+	data = xsk_umem__get_data(xsk->umem_area, tx_desc->addr);
+
+	meta = data - sizeof(struct xsk_tx_metadata);
+	memset(meta, 0, sizeof(*meta));
+	meta->flags = XDP_TXMD_FLAGS_TIMESTAMP;
+
+	eth = rx_packet;
+
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		iph = (void *)(eth + 1);
+		udph = (void *)(iph + 1);
+	} else if (eth->h_proto == htons(ETH_P_IPV6)) {
+		ip6h = (void *)(eth + 1);
+		udph = (void *)(ip6h + 1);
+	} else {
+		printf("%p: failed to detect IP version for ping pong %04x\n", xsk, eth->h_proto);
+		xsk_ring_prod__cancel(&xsk->tx, 1);
+		return;
+	}
+
+	len = ETH_HLEN;
+	if (ip6h)
+		len += sizeof(*ip6h) + ntohs(ip6h->payload_len);
+	if (iph)
+		len += ntohs(iph->tot_len);
+
+	swap(eth->h_dest, eth->h_source, ETH_ALEN);
+	if (iph)
+		swap(&iph->saddr, &iph->daddr, 4);
+	else
+		swap(&ip6h->saddr, &ip6h->daddr, 16);
+	swap(&udph->source, &udph->dest, 2);
+
+	want_csum = udph->check;
+	if (ip6h)
+		udph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					       ntohs(udph->len), IPPROTO_UDP, 0);
+	else
+		udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
+						 ntohs(udph->len), IPPROTO_UDP, 0);
+
+	meta->flags |= XDP_TXMD_FLAGS_CHECKSUM;
+	if (iph)
+		meta->request.csum_start = sizeof(*eth) + sizeof(*iph);
+	else
+		meta->request.csum_start = sizeof(*eth) + sizeof(*ip6h);
+	meta->request.csum_offset = offsetof(struct udphdr, check);
+
+	printf("%p: ping-pong with csum=%04x (want %04x) csum_start=%d csum_offset=%d\n",
+	       xsk, ntohs(udph->check), ntohs(want_csum),
+	       meta->request.csum_start, meta->request.csum_offset);
+
+	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
+	tx_desc->options |= XDP_TX_METADATA;
+	tx_desc->len = len;
+
+	xsk_ring_prod__submit(&xsk->tx, 1);
+}
+
 static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t clock_id)
 {
 	const struct xdp_desc *rx_desc;
@@ -252,6 +400,13 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 
 	while (true) {
 		errno = 0;
+
+		for (i = 0; i < rxq; i++) {
+			ret = kick_rx(&rx_xsk[i]);
+			if (ret)
+				printf("kick_rx ret=%d\n", ret);
+		}
+
 		ret = poll(fds, rxq + 1, 1000);
 		printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n",
 		       ret, errno, bpf_obj->bss->pkts_skip,
@@ -288,6 +443,22 @@ peek:
 				verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr),
 						    clock_id);
 				first_seg = false;
+
+				if (!skip_tx) {
+					/* mirror first chunk back */
+					ping_pong(xsk, xsk_umem__get_data(xsk->umem_area, addr),
+						  clock_id);
+
+					ret = kick_tx(xsk);
+					if (ret)
+						printf("kick_tx ret=%d\n", ret);
+
+					for (int j = 0; j < 500; j++) {
+						if (complete_tx(xsk, clock_id))
+							break;
+						usleep(10*1000);
+					}
+				}
 			}
 
 			xsk_ring_cons__release(&xsk->rx, 1);
@@ -420,8 +591,10 @@ static void print_usage(void)
 {
 	const char *usage =
 		"Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n"
-		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -c    Run in copy mode (zerocopy is default)\n"
 		"  -h    Display this help and exit\n\n"
+		"  -m    Enable multi-buffer XDP for larger MTU\n"
+		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
 		"Generate test packets on the other machine with:\n"
 		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
 
@@ -432,14 +605,22 @@ static void read_args(int argc, char *argv[])
 {
 	int opt;
 
-	while ((opt = getopt(argc, argv, "mh")) != -1) {
+	while ((opt = getopt(argc, argv, "chmr")) != -1) {
 		switch (opt) {
-		case 'm':
-			bind_flags |= XDP_USE_SG;
+		case 'c':
+			bind_flags &= ~XDP_USE_NEED_WAKEUP;
+			bind_flags &= ~XDP_ZEROCOPY;
+			bind_flags |= XDP_COPY;
 			break;
 		case 'h':
 			print_usage();
 			exit(0);
+		case 'm':
+			bind_flags |= XDP_USE_SG;
+			break;
+		case 'r':
+			skip_tx = true;
+			break;
 		case '?':
 			if (isprint(optopt))
 				fprintf(stderr, "Unknown option: -%c\n", optopt);