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

Martin KaFai Lau says:

====================
pull-request: bpf-next 2023-08-03

We've added 54 non-merge commits during the last 10 day(s) which contain
a total of 84 files changed, 4026 insertions(+), 562 deletions(-).

The main changes are:

1) Add SO_REUSEPORT support for TC bpf_sk_assign from Lorenz Bauer,
   Daniel Borkmann

2) Support new insns from cpu v4 from Yonghong Song

3) Non-atomically allocate freelist during prefill from YiFei Zhu

4) Support defragmenting IPv(4|6) packets in BPF from Daniel Xu

5) Add tracepoint to xdp attaching failure from Leon Hwang

6) struct netdev_rx_queue and xdp.h reshuffling to reduce
   rebuild time from Jakub Kicinski

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (54 commits)
  net: invert the netdevice.h vs xdp.h dependency
  net: move struct netdev_rx_queue out of netdevice.h
  eth: add missing xdp.h includes in drivers
  selftests/bpf: Add testcase for xdp attaching failure tracepoint
  bpf, xdp: Add tracepoint to xdp attaching failure
  selftests/bpf: fix static assert compilation issue for test_cls_*.c
  bpf: fix bpf_probe_read_kernel prototype mismatch
  riscv, bpf: Adapt bpf trampoline to optimized riscv ftrace framework
  libbpf: fix typos in Makefile
  tracing: bpf: use struct trace_entry in struct syscall_tp_t
  bpf, devmap: Remove unused dtab field from bpf_dtab_netdev
  bpf, cpumap: Remove unused cmap field from bpf_cpu_map_entry
  netfilter: bpf: Only define get_proto_defrag_hook() if necessary
  bpf: Fix an array-index-out-of-bounds issue in disasm.c
  net: remove duplicate INDIRECT_CALLABLE_DECLARE of udp[6]_ehashfn
  docs/bpf: Fix malformed documentation
  bpf: selftests: Add defrag selftests
  bpf: selftests: Support custom type and proto for client sockets
  bpf: selftests: Support not connecting client socket
  netfilter: bpf: Support BPF_F_NETFILTER_IP_DEFRAG in netfilter link
  ...
====================

Link: https://lore.kernel.org/r/20230803174845.825419-1-martin.lau@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 142 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/progs/test_assign_reuse.c b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
new file mode 100644
index 000000000000..4f2e2321ea06
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_assign_reuse.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2023 Isovalent */
+#include <stdbool.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/pkt_cls.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+__u64 sk_cookie_seen;
+__u64 reuseport_executed;
+union {
+	struct tcphdr tcp;
+	struct udphdr udp;
+} headers;
+
+const volatile __u16 dest_port;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SOCKMAP);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} sk_map SEC(".maps");
+
+SEC("sk_reuseport")
+int reuse_accept(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+
+	if (ctx->ip_protocol == IPPROTO_TCP) {
+		if (ctx->data + sizeof(headers.tcp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.tcp, ctx->data, sizeof(headers.tcp)) != 0)
+			return SK_DROP;
+	} else if (ctx->ip_protocol == IPPROTO_UDP) {
+		if (ctx->data + sizeof(headers.udp) > ctx->data_end)
+			return SK_DROP;
+
+		if (__builtin_memcmp(&headers.udp, ctx->data, sizeof(headers.udp)) != 0)
+			return SK_DROP;
+	} else {
+		return SK_DROP;
+	}
+
+	sk_cookie_seen = bpf_get_socket_cookie(ctx->sk);
+	return SK_PASS;
+}
+
+SEC("sk_reuseport")
+int reuse_drop(struct sk_reuseport_md *ctx)
+{
+	reuseport_executed++;
+	sk_cookie_seen = 0;
+	return SK_DROP;
+}
+
+static int
+assign_sk(struct __sk_buff *skb)
+{
+	int zero = 0, ret = 0;
+	struct bpf_sock *sk;
+
+	sk = bpf_map_lookup_elem(&sk_map, &zero);
+	if (!sk)
+		return TC_ACT_SHOT;
+	ret = bpf_sk_assign(skb, sk, 0);
+	bpf_sk_release(sk);
+	return ret ? TC_ACT_SHOT : TC_ACT_OK;
+}
+
+static bool
+maybe_assign_tcp(struct __sk_buff *skb, struct tcphdr *th)
+{
+	if (th + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (!th->syn || th->ack || th->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.tcp, th, sizeof(headers.tcp));
+	return assign_sk(skb);
+}
+
+static bool
+maybe_assign_udp(struct __sk_buff *skb, struct udphdr *uh)
+{
+	if (uh + 1 > (void *)(long)(skb->data_end))
+		return TC_ACT_SHOT;
+
+	if (uh->dest != bpf_htons(dest_port))
+		return TC_ACT_OK;
+
+	__builtin_memcpy(&headers.udp, uh, sizeof(headers.udp));
+	return assign_sk(skb);
+}
+
+SEC("tc")
+int tc_main(struct __sk_buff *skb)
+{
+	void *data_end = (void *)(long)skb->data_end;
+	void *data = (void *)(long)skb->data;
+	struct ethhdr *eth;
+
+	eth = (struct ethhdr *)(data);
+	if (eth + 1 > data_end)
+		return TC_ACT_SHOT;
+
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (struct iphdr *)(data + sizeof(*eth));
+
+		if (iph + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (iph->protocol == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(iph + 1));
+		else if (iph->protocol == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(iph + 1));
+		else
+			return TC_ACT_SHOT;
+	} else {
+		struct ipv6hdr *ip6h = (struct ipv6hdr *)(data + sizeof(*eth));
+
+		if (ip6h + 1 > data_end)
+			return TC_ACT_SHOT;
+
+		if (ip6h->nexthdr == IPPROTO_TCP)
+			return maybe_assign_tcp(skb, (struct tcphdr *)(ip6h + 1));
+		else if (ip6h->nexthdr == IPPROTO_UDP)
+			return maybe_assign_udp(skb, (struct udphdr *)(ip6h + 1));
+		else
+			return TC_ACT_SHOT;
+	}
+}