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>

2 files changed, 35 insertions, 29 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index e1bb6d7856d9..85fe8138f3e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2160,7 +2160,7 @@ EXPORT_SYMBOL(net_disable_timestamp);
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp = 0;
-	skb->mono_delivery_time = 0;
+	skb->tstamp_type = SKB_CLOCK_REALTIME;
 	if (static_branch_unlikely(&netstamp_needed_key))
 		skb->tstamp = ktime_get_real();
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index 2510464692af..7c46ecba3b01 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2274,12 +2274,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
 
 	err = bpf_out_neigh_v6(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
 	goto out_xmit;
 out_drop:
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 out_xmit:
 	return ret;
@@ -2380,12 +2380,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
 
 	err = bpf_out_neigh_v4(net, skb, dev, nh);
 	if (unlikely(net_xmit_eval(err)))
-		dev->stats.tx_errors++;
+		DEV_STATS_INC(dev, tx_errors);
 	else
 		ret = NET_XMIT_SUCCESS;
 	goto out_xmit;
 out_drop:
-	dev->stats.tx_errors++;
+	DEV_STATS_INC(dev, tx_errors);
 	kfree_skb(skb);
 out_xmit:
 	return ret;
@@ -7726,17 +7726,21 @@ BPF_CALL_3(bpf_skb_set_tstamp, struct sk_buff *, skb,
 		return -EOPNOTSUPP;
 
 	switch (tstamp_type) {
-	case BPF_SKB_TSTAMP_DELIVERY_MONO:
+	case BPF_SKB_CLOCK_REALTIME:
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
+		break;
+	case BPF_SKB_CLOCK_MONOTONIC:
 		if (!tstamp)
 			return -EINVAL;
 		skb->tstamp = tstamp;
-		skb->mono_delivery_time = 1;
+		skb->tstamp_type = SKB_CLOCK_MONOTONIC;
 		break;
-	case BPF_SKB_TSTAMP_UNSPEC:
-		if (tstamp)
+	case BPF_SKB_CLOCK_TAI:
+		if (!tstamp)
 			return -EINVAL;
-		skb->tstamp = 0;
-		skb->mono_delivery_time = 0;
+		skb->tstamp = tstamp;
+		skb->tstamp_type = SKB_CLOCK_TAI;
 		break;
 	default:
 		return -EINVAL;
@@ -9387,16 +9391,17 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si,
 {
 	__u8 value_reg = si->dst_reg;
 	__u8 skb_reg = si->src_reg;
-	/* AX is needed because src_reg and dst_reg could be the same */
-	__u8 tmp_reg = BPF_REG_AX;
-
-	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
-			      SKB_BF_MONO_TC_OFFSET);
-	*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg,
-				SKB_MONO_DELIVERY_TIME_MASK, 2);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_UNSPEC);
-	*insn++ = BPF_JMP_A(1);
-	*insn++ = BPF_MOV32_IMM(value_reg, BPF_SKB_TSTAMP_DELIVERY_MONO);
+	BUILD_BUG_ON(__SKB_CLOCK_MAX != (int)BPF_SKB_CLOCK_TAI);
+	BUILD_BUG_ON(SKB_CLOCK_REALTIME != (int)BPF_SKB_CLOCK_REALTIME);
+	BUILD_BUG_ON(SKB_CLOCK_MONOTONIC != (int)BPF_SKB_CLOCK_MONOTONIC);
+	BUILD_BUG_ON(SKB_CLOCK_TAI != (int)BPF_SKB_CLOCK_TAI);
+	*insn++ = BPF_LDX_MEM(BPF_B, value_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, value_reg, SKB_TSTAMP_TYPE_MASK);
+#ifdef __BIG_ENDIAN_BITFIELD
+	*insn++ = BPF_ALU32_IMM(BPF_RSH, value_reg, SKB_TSTAMP_TYPE_RSHIFT);
+#else
+	BUILD_BUG_ON(!(SKB_TSTAMP_TYPE_MASK & 0x1));
+#endif
 
 	return insn;
 }
@@ -9439,11 +9444,12 @@ static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_prog *prog,
 		__u8 tmp_reg = BPF_REG_AX;
 
 		*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, SKB_BF_MONO_TC_OFFSET);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK);
-		*insn++ = BPF_JMP32_IMM(BPF_JNE, tmp_reg,
-					TC_AT_INGRESS_MASK | SKB_MONO_DELIVERY_TIME_MASK, 2);
-		/* skb->tc_at_ingress && skb->mono_delivery_time,
+		/* check if ingress mask bits is set */
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
+		*insn++ = BPF_JMP_A(4);
+		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, SKB_TSTAMP_TYPE_MASK, 1);
+		*insn++ = BPF_JMP_A(2);
+		/* skb->tc_at_ingress && skb->tstamp_type,
 		 * read 0 as the (rcv) timestamp.
 		 */
 		*insn++ = BPF_MOV64_IMM(value_reg, 0);
@@ -9468,7 +9474,7 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 	 * the bpf prog is aware the tstamp could have delivery time.
 	 * Thus, write skb->tstamp as is if tstamp_type_access is true.
 	 * Otherwise, writing at ingress will have to clear the
-	 * mono_delivery_time bit also.
+	 * skb->tstamp_type bit also.
 	 */
 	if (!prog->tstamp_type_access) {
 		__u8 tmp_reg = BPF_REG_AX;
@@ -9478,8 +9484,8 @@ static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_prog *prog,
 		*insn++ = BPF_JMP32_IMM(BPF_JSET, tmp_reg, TC_AT_INGRESS_MASK, 1);
 		/* goto <store> */
 		*insn++ = BPF_JMP_A(2);
-		/* <clear>: mono_delivery_time */
-		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_MONO_DELIVERY_TIME_MASK);
+		/* <clear>: skb->tstamp_type */
+		*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, ~SKB_TSTAMP_TYPE_MASK);
 		*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg, SKB_BF_MONO_TC_OFFSET);
 	}
 #endif