diff options
Diffstat (limited to 'tools')
| -rw-r--r-- | tools/include/uapi/linux/if_xdp.h | 61 | ||||
| -rw-r--r-- | tools/include/uapi/linux/netdev.h | 16 | ||||
| -rw-r--r-- | tools/net/ynl/generated/netdev-user.c | 19 | ||||
| -rw-r--r-- | tools/net/ynl/generated/netdev-user.h | 3 | ||||
| -rw-r--r-- | tools/net/ynl/samples/netdev.c | 10 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/network_helpers.h | 43 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/prog_tests/xdp_metadata.c | 33 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/xdp_hw_metadata.c | 235 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/xsk.c | 3 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/xsk.h | 1 |
10 files changed, 385 insertions, 39 deletions
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index 73a47da885dc..638c606dfa74 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -26,14 +26,20 @@ */ #define XDP_USE_NEED_WAKEUP (1 << 3) /* By setting this option, userspace application indicates that it can - * handle multiple descriptors per packet thus enabling xsk core to split + * handle multiple descriptors per packet thus enabling AF_XDP to split * multi-buffer XDP frames into multiple Rx descriptors. Without this set - * such frames will be dropped by xsk. + * such frames will be dropped. */ -#define XDP_USE_SG (1 << 4) +#define XDP_USE_SG (1 << 4) /* Flags for xsk_umem_config flags */ -#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) +#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0) + +/* Force checksum calculation in software. Can be used for testing or + * working around potential HW issues. This option causes performance + * degradation and only works in XDP_COPY mode. + */ +#define XDP_UMEM_TX_SW_CSUM (1 << 1) struct sockaddr_xdp { __u16 sxdp_family; @@ -76,6 +82,7 @@ struct xdp_umem_reg { __u32 chunk_size; __u32 headroom; __u32 flags; + __u32 tx_metadata_len; }; struct xdp_statistics { @@ -105,6 +112,41 @@ struct xdp_options { #define XSK_UNALIGNED_BUF_ADDR_MASK \ ((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1) +/* Request transmit timestamp. Upon completion, put it into tx_timestamp + * field of union xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_TIMESTAMP (1 << 0) + +/* Request transmit checksum offload. Checksum start position and offset + * are communicated via csum_start and csum_offset fields of union + * xsk_tx_metadata. + */ +#define XDP_TXMD_FLAGS_CHECKSUM (1 << 1) + +/* AF_XDP offloads request. 'request' union member is consumed by the driver + * when the packet is being transmitted. 'completion' union member is + * filled by the driver when the transmit completion arrives. + */ +struct xsk_tx_metadata { + __u64 flags; + + union { + struct { + /* XDP_TXMD_FLAGS_CHECKSUM */ + + /* Offset from desc->addr where checksumming should start. */ + __u16 csum_start; + /* Offset from csum_start where checksum should be stored. */ + __u16 csum_offset; + } request; + + struct { + /* XDP_TXMD_FLAGS_TIMESTAMP */ + __u64 tx_timestamp; + } completion; + }; +}; + /* Rx/Tx descriptor */ struct xdp_desc { __u64 addr; @@ -112,9 +154,16 @@ struct xdp_desc { __u32 options; }; -/* Flag indicating packet constitutes of multiple buffers*/ +/* UMEM descriptor is __u64 */ + +/* Flag indicating that the packet continues with the buffer pointed out by the + * next frame in the ring. The end of the packet is signalled by setting this + * bit to zero. For single buffer packets, every descriptor has 'options' set + * to 0 and this maintains backward compatibility. + */ #define XDP_PKT_CONTD (1 << 0) -/* UMEM descriptor is __u64 */ +/* TX packet carries valid metadata. */ +#define XDP_TX_METADATA (1 << 1) #endif /* _LINUX_IF_XDP_H */ diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 2943a151d4f1..48d5477a668c 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -53,12 +53,28 @@ enum netdev_xdp_rx_metadata { NETDEV_XDP_RX_METADATA_MASK = 3, }; +/** + * enum netdev_xsk_flags + * @NETDEV_XSK_FLAGS_TX_TIMESTAMP: HW timestamping egress packets is supported + * by the driver. + * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the + * driver. + */ +enum netdev_xsk_flags { + NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1, + NETDEV_XSK_FLAGS_TX_CHECKSUM = 2, + + /* private: */ + NETDEV_XSK_FLAGS_MASK = 3, +}; + enum { NETDEV_A_DEV_IFINDEX = 1, NETDEV_A_DEV_PAD, NETDEV_A_DEV_XDP_FEATURES, NETDEV_A_DEV_XDP_ZC_MAX_SEGS, NETDEV_A_DEV_XDP_RX_METADATA_FEATURES, + NETDEV_A_DEV_XSK_FEATURES, __NETDEV_A_DEV_MAX, NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1) diff --git a/tools/net/ynl/generated/netdev-user.c b/tools/net/ynl/generated/netdev-user.c index b5ffe8cd1144..6283d87dad37 100644 --- a/tools/net/ynl/generated/netdev-user.c +++ b/tools/net/ynl/generated/netdev-user.c @@ -58,6 +58,19 @@ const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value) return netdev_xdp_rx_metadata_strmap[value]; } +static const char * const netdev_xsk_flags_strmap[] = { + [0] = "tx-timestamp", + [1] = "tx-checksum", +}; + +const char *netdev_xsk_flags_str(enum netdev_xsk_flags value) +{ + value = ffs(value) - 1; + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(netdev_xsk_flags_strmap)) + return NULL; + return netdev_xsk_flags_strmap[value]; +} + /* Policies */ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_IFINDEX] = { .name = "ifindex", .type = YNL_PT_U32, }, @@ -65,6 +78,7 @@ struct ynl_policy_attr netdev_dev_policy[NETDEV_A_DEV_MAX + 1] = { [NETDEV_A_DEV_XDP_FEATURES] = { .name = "xdp-features", .type = YNL_PT_U64, }, [NETDEV_A_DEV_XDP_ZC_MAX_SEGS] = { .name = "xdp-zc-max-segs", .type = YNL_PT_U32, }, [NETDEV_A_DEV_XDP_RX_METADATA_FEATURES] = { .name = "xdp-rx-metadata-features", .type = YNL_PT_U64, }, + [NETDEV_A_DEV_XSK_FEATURES] = { .name = "xsk-features", .type = YNL_PT_U64, }, }; struct ynl_policy_nest netdev_dev_nest = { @@ -116,6 +130,11 @@ int netdev_dev_get_rsp_parse(const struct nlmsghdr *nlh, void *data) return MNL_CB_ERROR; dst->_present.xdp_rx_metadata_features = 1; dst->xdp_rx_metadata_features = mnl_attr_get_u64(attr); + } else if (type == NETDEV_A_DEV_XSK_FEATURES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.xsk_features = 1; + dst->xsk_features = mnl_attr_get_u64(attr); } } diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index 4fafac879df3..39af1908444b 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -19,6 +19,7 @@ extern const struct ynl_family ynl_netdev_family; const char *netdev_op_str(int op); const char *netdev_xdp_act_str(enum netdev_xdp_act value); const char *netdev_xdp_rx_metadata_str(enum netdev_xdp_rx_metadata value); +const char *netdev_xsk_flags_str(enum netdev_xsk_flags value); /* Common nested types */ /* ============== NETDEV_CMD_DEV_GET ============== */ @@ -50,12 +51,14 @@ struct netdev_dev_get_rsp { __u32 xdp_features:1; __u32 xdp_zc_max_segs:1; __u32 xdp_rx_metadata_features:1; + __u32 xsk_features:1; } _present; __u32 ifindex; __u64 xdp_features; __u32 xdp_zc_max_segs; __u64 xdp_rx_metadata_features; + __u64 xsk_features; }; void netdev_dev_get_rsp_free(struct netdev_dev_get_rsp *rsp); diff --git a/tools/net/ynl/samples/netdev.c b/tools/net/ynl/samples/netdev.c index b828225daad0..591b90e21890 100644 --- a/tools/net/ynl/samples/netdev.c +++ b/tools/net/ynl/samples/netdev.c @@ -33,17 +33,23 @@ static void netdev_print_device(struct netdev_dev_get_rsp *d, unsigned int op) return; printf("xdp-features (%llx):", d->xdp_features); - for (int i = 0; d->xdp_features > 1U << i; i++) { + for (int i = 0; d->xdp_features >= 1U << i; i++) { if (d->xdp_features & (1U << i)) printf(" %s", netdev_xdp_act_str(1 << i)); } printf(" xdp-rx-metadata-features (%llx):", d->xdp_rx_metadata_features); - for (int i = 0; d->xdp_rx_metadata_features > 1U << i; i++) { + for (int i = 0; d->xdp_rx_metadata_features >= 1U << i; i++) { if (d->xdp_rx_metadata_features & (1U << i)) printf(" %s", netdev_xdp_rx_metadata_str(1 << i)); } + printf(" xsk-features (%llx):", d->xsk_features); + for (int i = 0; d->xsk_features >= 1U << i; i++) { + if (d->xsk_features & (1U << i)) + printf(" %s", netdev_xsk_flags_str(1 << i)); + } + printf(" xdp-zc-max-segs=%u", d->xdp_zc_max_segs); name = netdev_op_str(op); diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 34f1200a781b..94b9be24e39b 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -71,4 +71,47 @@ struct nstoken; */ struct nstoken *open_netns(const char *name); void close_netns(struct nstoken *token); + +static __u16 csum_fold(__u32 csum) +{ + csum = (csum & 0xffff) + (csum >> 16); + csum = (csum & 0xffff) + (csum >> 16); + + return (__u16)~csum; +} + +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum csum) +{ + __u64 s = csum; + + s += (__u32)saddr; + s += (__u32)daddr; + s += htons(proto + len); + s = (s & 0xffffffff) + (s >> 32); + s = (s & 0xffffffff) + (s >> 32); + + return csum_fold((__u32)s); +} + +static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, + __wsum csum) +{ + __u64 s = csum; + int i; + + for (i = 0; i < 4; i++) + s += (__u32)saddr->s6_addr32[i]; + for (i = 0; i < 4; i++) + s += (__u32)daddr->s6_addr32[i]; + s += htons(proto + len); + s = (s & 0xffffffff) + (s >> 32); + s = (s & 0xffffffff) + (s >> 32); + + return csum_fold((__u32)s); +} + #endif diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 4439ba9392f8..33cdf88efa6b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -56,7 +56,8 @@ static int open_xsk(int ifindex, struct xsk *xsk) .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 = XDP_UMEM_UNALIGNED_CHUNK_FLAG | XDP_UMEM_TX_SW_CSUM, + .tx_metadata_len = sizeof(struct xsk_tx_metadata), }; __u32 idx; u64 addr; @@ -138,6 +139,7 @@ static void ip_csum(struct iphdr *iph) static int generate_packet(struct xsk *xsk, __u16 dst_port) { + struct xsk_tx_metadata *meta; struct xdp_desc *tx_desc; struct udphdr *udph; struct ethhdr *eth; @@ -151,10 +153,14 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) return -1; tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx); - tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE; + tx_desc->addr = idx % (UMEM_NUM / 2) * UMEM_FRAME_SIZE + sizeof(struct xsk_tx_metadata); printf("%p: tx_desc[%u]->addr=%llx\n", xsk, idx, tx_desc->addr); 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 = data; iph = (void *)(eth + 1); udph = (void *)(iph + 1); @@ -178,11 +184,17 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) udph->source = htons(AF_XDP_SOURCE_PORT); udph->dest = htons(dst_port); udph->len = htons(sizeof(*udph) + UDP_PAYLOAD_BYTES); - udph->check = 0; + udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + ntohs(udph->len), IPPROTO_UDP, 0); memset(udph + 1, 0xAA, UDP_PAYLOAD_BYTES); + meta->flags |= XDP_TXMD_FLAGS_CHECKSUM; + meta->request.csum_start = sizeof(*eth) + sizeof(*iph); + meta->request.csum_offset = offsetof(struct udphdr, check); + tx_desc->len = sizeof(*eth) + sizeof(*iph) + sizeof(*udph) + UDP_PAYLOAD_BYTES; + tx_desc->options |= XDP_TX_METADATA; xsk_ring_prod__submit(&xsk->tx, 1); ret = sendto(xsk_socket__fd(xsk->socket), NULL, 0, MSG_DONTWAIT, NULL, 0); @@ -194,13 +206,21 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) static void complete_tx(struct xsk *xsk) { - __u32 idx; + struct xsk_tx_metadata *meta; __u64 addr; + void *data; + __u32 idx; if (ASSERT_EQ(xsk_ring_cons__peek(&xsk->comp, 1, &idx), 1, "xsk_ring_cons__peek")) { addr = *xsk_ring_cons__comp_addr(&xsk->comp, idx); printf("%p: complete tx idx=%u addr=%llx\n", xsk, idx, addr); + + data = xsk_umem__get_data(xsk->umem_area, addr); + meta = data - sizeof(struct xsk_tx_metadata); + + ASSERT_NEQ(meta->completion.tx_timestamp, 0, "tx_timestamp"); + xsk_ring_cons__release(&xsk->comp, 1); } } @@ -221,6 +241,7 @@ static int verify_xsk_metadata(struct xsk *xsk) const struct xdp_desc *rx_desc; struct pollfd fds = {}; struct xdp_meta *meta; + struct udphdr *udph; struct ethhdr *eth; struct iphdr *iph; __u64 comp_addr; @@ -257,6 +278,7 @@ static int verify_xsk_metadata(struct xsk *xsk) ASSERT_EQ(eth->h_proto, htons(ETH_P_IP), "eth->h_proto"); iph = (void *)(eth + 1); ASSERT_EQ((int)iph->version, 4, "iph->version"); + udph = (void *)(iph + 1); /* custom metadata */ @@ -270,6 +292,9 @@ static int verify_xsk_metadata(struct xsk *xsk) ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); + /* checksum offload */ + ASSERT_EQ(udph->check, htons(0x721c), "csum"); + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); 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); diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c index e574711eeb84..25d568abf0f2 100644 --- a/tools/testing/selftests/bpf/xsk.c +++ b/tools/testing/selftests/bpf/xsk.c @@ -115,6 +115,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM; cfg->flags = XSK_UMEM__DEFAULT_FLAGS; + cfg->tx_metadata_len = 0; return; } @@ -123,6 +124,7 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg, cfg->frame_size = usr_cfg->frame_size; cfg->frame_headroom = usr_cfg->frame_headroom; cfg->flags = usr_cfg->flags; + cfg->tx_metadata_len = usr_cfg->tx_metadata_len; } static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg, @@ -252,6 +254,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, mr.chunk_size = umem->config.frame_size; mr.headroom = umem->config.frame_headroom; mr.flags = umem->config.flags; + mr.tx_metadata_len = umem->config.tx_metadata_len; err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)); if (err) { diff --git a/tools/testing/selftests/bpf/xsk.h b/tools/testing/selftests/bpf/xsk.h index 771570bc3731..93c2cc413cfc 100644 --- a/tools/testing/selftests/bpf/xsk.h +++ b/tools/testing/selftests/bpf/xsk.h @@ -200,6 +200,7 @@ struct xsk_umem_config { __u32 frame_size; __u32 frame_headroom; __u32 flags; + __u32 tx_metadata_len; }; int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags); |