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

Daniel Borkmann says:

====================
pull-request: bpf-next 2024-05-28

We've added 23 non-merge commits during the last 11 day(s) which contain
a total of 45 files changed, 696 insertions(+), 277 deletions(-).

The main changes are:

1) Rename skb's mono_delivery_time to tstamp_type for extensibility
   and add SKB_CLOCK_TAI type support to bpf_skb_set_tstamp(),
   from Abhishek Chauhan.

2) Add netfilter CT zone ID and direction to bpf_ct_opts so that arbitrary
   CT zones can be used from XDP/tc BPF netfilter CT helper functions,
   from Brad Cowie.

3) Several tweaks to the instruction-set.rst IETF doc to address
   the Last Call review comments, from Dave Thaler.

4) Small batch of riscv64 BPF JIT optimizations in order to emit more
   compressed instructions to the JITed image for better icache efficiency,
   from Xiao Wang.

5) Sort bpftool C dump output from BTF, aiming to simplify vmlinux.h
   diffing and forcing more natural type definitions ordering,
   from Mykyta Yatsenko.

6) Use DEV_STATS_INC() macro in BPF redirect helpers to silence
   a syzbot/KCSAN race report for the tx_errors counter,
   from Jiang Yunshui.

7) Un-constify bpf_func_info in bpftool to fix compilation with LLVM 17+
   which started treating const structs as constants and thus breaking
   full BTF program name resolution, from Ivan Babrou.

8) Fix up BPF program numbers in test_sockmap selftest in order to reduce
   some of the test-internal array sizes, from Geliang Tang.

9) Small cleanup in Makefile.btf script to use test-ge check for v1.25-only
   pahole, from Alan Maguire.

10) Fix bpftool's make dependencies for vmlinux.h in order to avoid needless
    rebuilds in some corner cases, from Artem Savkov.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (23 commits)
  bpf, net: Use DEV_STAT_INC()
  bpf, docs: Fix instruction.rst indentation
  bpf, docs: Clarify call local offset
  bpf, docs: Add table captions
  bpf, docs: clarify sign extension of 64-bit use of 32-bit imm
  bpf, docs: Use RFC 2119 language for ISA requirements
  bpf, docs: Move sentence about returning R0 to abi.rst
  bpf: constify member bpf_sysctl_kern:: Table
  riscv, bpf: Try RVC for reg move within BPF_CMPXCHG JIT
  riscv, bpf: Use STACK_ALIGN macro for size rounding up
  riscv, bpf: Optimize zextw insn with Zba extension
  selftests/bpf: Handle forwarding of UDP CLOCK_TAI packets
  net: Add additional bit to support clockid_t timestamp type
  net: Rename mono_delivery_time to tstamp_type for scalabilty
  selftests/bpf: Update tests for new ct zone opts for nf_conntrack kfuncs
  net: netfilter: Make ct zone opts configurable for bpf ct helpers
  selftests/bpf: Fix prog numbers in test_sockmap
  bpf: Remove unused variable "prev_state"
  bpftool: Un-const bpf_func_info to fix it for llvm 17 and newer
  bpf: Fix order of args in call to bpf_map_kvcalloc
  ...
====================

Link: https://lore.kernel.org/r/20240528105924.30905-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 22 insertions, 13 deletions

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 27d8725445e3..e7a19df3125e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -859,7 +859,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 	struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
 				inet6_sk(skb->sk) : NULL;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	struct ip6_frag_state state;
 	unsigned int mtu, hlen, nexthdr_offset;
 	ktime_t tstamp = skb->tstamp;
@@ -955,7 +955,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, skb);
 			if (!err)
 				IP6_INC_STATS(net, ip6_dst_idev(&rt->dst),
@@ -1016,7 +1016,7 @@ slow_path:
 		/*
 		 *	Put this fragment into the sending queue.
 		 */
-		skb_set_delivery_time(frag, tstamp, mono_delivery_time);
+		skb_set_delivery_time(frag, tstamp, tstamp_type);
 		err = output(net, sk, frag);
 		if (err)
 			goto fail;
@@ -1924,7 +1924,10 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = cork->base.mark;
-	skb->tstamp = cork->base.transmit_time;
+	if (sk_is_tcp(sk))
+		skb_set_delivery_time(skb, cork->base.transmit_time, SKB_CLOCK_MONOTONIC);
+	else
+		skb_set_delivery_type_by_clockid(skb, cork->base.transmit_time, sk->sk_clockid);
 
 	ip6_cork_steal_dst(skb, cork);
 	IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 53d255838e6a..e0c2347b4dc6 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -126,7 +126,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				  struct sk_buff *))
 {
 	int frag_max_size = BR_INPUT_SKB_CB(skb)->frag_max_size;
-	bool mono_delivery_time = skb->mono_delivery_time;
+	u8 tstamp_type = skb->tstamp_type;
 	ktime_t tstamp = skb->tstamp;
 	struct ip6_frag_state state;
 	u8 *prevhdr, nexthdr = 0;
@@ -192,7 +192,7 @@ int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 			if (iter.frag)
 				ip6_fraglist_prepare(skb, &iter);
 
-			skb_set_delivery_time(skb, tstamp, mono_delivery_time);
+			skb_set_delivery_time(skb, tstamp, tstamp_type);
 			err = output(net, sk, data, skb);
 			if (err || !iter.frag)
 				break;
@@ -225,7 +225,7 @@ slow_path:
 			goto blackhole;
 		}
 
-		skb_set_delivery_time(skb2, tstamp, mono_delivery_time);
+		skb_set_delivery_time(skb2, tstamp, tstamp_type);
 		err = output(net, sk, data, skb2);
 		if (err)
 			goto blackhole;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e1b50c6a44d..6f0844c9315d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -263,7 +263,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->iif = dev->ifindex;
 
 	fq->q.stamp = skb->tstamp;
-	fq->q.mono_delivery_time = skb->mono_delivery_time;
+	fq->q.tstamp_type = skb->tstamp_type;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
 	if (payload_len > fq->q.max_size)
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 2eedf255600b..f838366e8256 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -621,7 +621,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
-	skb->tstamp = sockc->transmit_time;
+	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, sk->sk_clockid);
 
 	skb_put(skb, length);
 	skb_reset_network_header(skb);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 327caca64257..a48be617a8ab 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -198,7 +198,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		fq->iif = dev->ifindex;
 
 	fq->q.stamp = skb->tstamp;
-	fq->q.mono_delivery_time = skb->mono_delivery_time;
+	fq->q.tstamp_type = skb->tstamp_type;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
 	add_frag_mem_limit(fq->q.fqdir, skb->truesize);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 4c3605485b68..750aa681779c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -975,7 +975,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 			mark = inet_twsk(sk)->tw_mark;
 		else
 			mark = READ_ONCE(sk->sk_mark);
-		skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
+		skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC);
 	}
 	if (txhash) {
 		/* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */
@@ -2387,8 +2387,14 @@ static struct inet_protosw tcpv6_protosw = {
 
 static int __net_init tcpv6_net_init(struct net *net)
 {
-	return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
-				    SOCK_RAW, IPPROTO_TCP, net);
+	int res;
+
+	res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
+				   SOCK_RAW, IPPROTO_TCP, net);
+	if (!res)
+		net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC;
+
+	return res;
 }
 
 static void __net_exit tcpv6_net_exit(struct net *net)