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>

1 files changed, 50 insertions, 18 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1c2902eaebd3..fe7d8dbef77e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -706,6 +706,13 @@ typedef unsigned int sk_buff_data_t;
 typedef unsigned char *sk_buff_data_t;
 #endif
 
+enum skb_tstamp_type {
+	SKB_CLOCK_REALTIME,
+	SKB_CLOCK_MONOTONIC,
+	SKB_CLOCK_TAI,
+	__SKB_CLOCK_MAX = SKB_CLOCK_TAI,
+};
+
 /**
  * DOC: Basic sk_buff geometry
  *
@@ -823,10 +830,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@slow_gro: state present at GRO time, slower prepare step required
- *	@mono_delivery_time: When set, skb->tstamp has the
- *		delivery_time in mono clock base (i.e. EDT).  Otherwise, the
- *		skb->tstamp has the (rcv) timestamp at ingress and
- *		delivery_time at egress.
+ *	@tstamp_type: When set, skb->tstamp has the
+ *		delivery_time clock base of skb->tstamp.
  *	@napi_id: id of the NAPI struct this skb came from
  *	@sender_cpu: (aka @napi_id) source CPU in XPS
  *	@alloc_cpu: CPU which did the skb allocation.
@@ -954,7 +959,7 @@ struct sk_buff {
 	/* private: */
 	__u8			__mono_tc_offset[0];
 	/* public: */
-	__u8			mono_delivery_time:1;	/* See SKB_MONO_DELIVERY_TIME_MASK */
+	__u8			tstamp_type:2;	/* See skb_tstamp_type */
 #ifdef CONFIG_NET_XGRESS
 	__u8			tc_at_ingress:1;	/* See TC_AT_INGRESS_MASK */
 	__u8			tc_skip_classify:1;
@@ -1084,15 +1089,16 @@ struct sk_buff {
 #endif
 #define PKT_TYPE_OFFSET		offsetof(struct sk_buff, __pkt_type_offset)
 
-/* if you move tc_at_ingress or mono_delivery_time
+/* if you move tc_at_ingress or tstamp_type
  * around, you also must adapt these constants.
  */
 #ifdef __BIG_ENDIAN_BITFIELD
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 7)
-#define TC_AT_INGRESS_MASK		(1 << 6)
+#define SKB_TSTAMP_TYPE_MASK		(3 << 6)
+#define SKB_TSTAMP_TYPE_RSHIFT		(6)
+#define TC_AT_INGRESS_MASK		(1 << 5)
 #else
-#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 0)
-#define TC_AT_INGRESS_MASK		(1 << 1)
+#define SKB_TSTAMP_TYPE_MASK		(3)
+#define TC_AT_INGRESS_MASK		(1 << 2)
 #endif
 #define SKB_BF_MONO_TC_OFFSET		offsetof(struct sk_buff, __mono_tc_offset)
 
@@ -4179,7 +4185,7 @@ static inline void skb_get_new_timestampns(const struct sk_buff *skb,
 static inline void __net_timestamp(struct sk_buff *skb)
 {
 	skb->tstamp = ktime_get_real();
-	skb->mono_delivery_time = 0;
+	skb->tstamp_type = SKB_CLOCK_REALTIME;
 }
 
 static inline ktime_t net_timedelta(ktime_t t)
@@ -4188,10 +4194,36 @@ static inline ktime_t net_timedelta(ktime_t t)
 }
 
 static inline void skb_set_delivery_time(struct sk_buff *skb, ktime_t kt,
-					 bool mono)
+					 u8 tstamp_type)
 {
 	skb->tstamp = kt;
-	skb->mono_delivery_time = kt && mono;
+
+	if (kt)
+		skb->tstamp_type = tstamp_type;
+	else
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
+}
+
+static inline void skb_set_delivery_type_by_clockid(struct sk_buff *skb,
+						    ktime_t kt, clockid_t clockid)
+{
+	u8 tstamp_type = SKB_CLOCK_REALTIME;
+
+	switch (clockid) {
+	case CLOCK_REALTIME:
+		break;
+	case CLOCK_MONOTONIC:
+		tstamp_type = SKB_CLOCK_MONOTONIC;
+		break;
+	case CLOCK_TAI:
+		tstamp_type = SKB_CLOCK_TAI;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		kt = 0;
+	}
+
+	skb_set_delivery_time(skb, kt, tstamp_type);
 }
 
 DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
@@ -4201,8 +4233,8 @@ DECLARE_STATIC_KEY_FALSE(netstamp_needed_key);
  */
 static inline void skb_clear_delivery_time(struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time) {
-		skb->mono_delivery_time = 0;
+	if (skb->tstamp_type) {
+		skb->tstamp_type = SKB_CLOCK_REALTIME;
 		if (static_branch_unlikely(&netstamp_needed_key))
 			skb->tstamp = ktime_get_real();
 		else
@@ -4212,7 +4244,7 @@ static inline void skb_clear_delivery_time(struct sk_buff *skb)
 
 static inline void skb_clear_tstamp(struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time)
+	if (skb->tstamp_type)
 		return;
 
 	skb->tstamp = 0;
@@ -4220,7 +4252,7 @@ static inline void skb_clear_tstamp(struct sk_buff *skb)
 
 static inline ktime_t skb_tstamp(const struct sk_buff *skb)
 {
-	if (skb->mono_delivery_time)
+	if (skb->tstamp_type)
 		return 0;
 
 	return skb->tstamp;
@@ -4228,7 +4260,7 @@ static inline ktime_t skb_tstamp(const struct sk_buff *skb)
 
 static inline ktime_t skb_tstamp_cond(const struct sk_buff *skb, bool cond)
 {
-	if (!skb->mono_delivery_time && skb->tstamp)
+	if (skb->tstamp_type != SKB_CLOCK_MONOTONIC && skb->tstamp)
 		return skb->tstamp;
 
 	if (static_branch_unlikely(&netstamp_needed_key) || cond)