bpf: Keep the (rcv) timestamp behavior for the existing tc-bpf@ingress

The current tc-bpf@ingress reads and writes the __sk_buff->tstamp
as a (rcv) timestamp which currently could either be 0 (not available)
or ktime_get_real().  This patch is to backward compatible with the
(rcv) timestamp expectation at ingress.  If the skb->tstamp has
the delivery_time, the bpf insn rewrite will read 0 for tc-bpf
running at ingress as it is not available.  When writing at ingress,
it will also clear the skb->mono_delivery_time bit.

/* BPF_READ: a = __sk_buff->tstamp */
if (!skb->tc_at_ingress || !skb->mono_delivery_time)
	a = skb->tstamp;
else
	a = 0

/* BPF_WRITE: __sk_buff->tstamp = a */
if (skb->tc_at_ingress)
	skb->mono_delivery_time = 0;
skb->tstamp = a;

[ A note on the BPF_CGROUP_INET_INGRESS which can also access
  skb->tstamp.  At that point, the skb is delivered locally
  and skb_clear_delivery_time() has already been done,
  so the skb->tstamp will only have the (rcv) timestamp. ]

If the tc-bpf@egress writes 0 to skb->tstamp, the skb->mono_delivery_time
has to be cleared also.  It could be done together during
convert_ctx_access().  However, the latter patch will also expose
the skb->mono_delivery_time bit as __sk_buff->delivery_time_type.
Changing the delivery_time_type in the background may surprise
the user, e.g. the 2nd read on __sk_buff->delivery_time_type
may need a READ_ONCE() to avoid compiler optimization.  Thus,
in expecting the needs in the latter patch, this patch does a
check on !skb->tstamp after running the tc-bpf and clears the
skb->mono_delivery_time bit if needed.  The earlier discussion
on v4 [0].

The bpf insn rewrite requires the skb's mono_delivery_time bit and
tc_at_ingress bit.  They are moved up in sk_buff so that bpf rewrite
can be done at a fixed offset.  tc_skip_classify is moved together with
tc_at_ingress.  To get one bit for mono_delivery_time, csum_not_inet is
moved down and this bit is currently used by sctp.

[0]: https://lore.kernel.org/bpf/20220217015043.khqwqklx45c4m4se@kafai-mbp.dhcp.thefacebook.com/

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 12 insertions, 6 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4b5b926a81f2..5445860e1ba6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -941,8 +941,12 @@ struct sk_buff {
 	__u8			vlan_present:1;	/* See PKT_VLAN_PRESENT_BIT */
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
-	__u8			csum_not_inet:1;
 	__u8			dst_pending_confirm:1;
+	__u8			mono_delivery_time:1;
+#ifdef CONFIG_NET_CLS_ACT
+	__u8			tc_skip_classify:1;
+	__u8			tc_at_ingress:1;
+#endif
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
@@ -954,10 +958,6 @@ struct sk_buff {
 	__u8			offload_fwd_mark:1;
 	__u8			offload_l3_fwd_mark:1;
 #endif
-#ifdef CONFIG_NET_CLS_ACT
-	__u8			tc_skip_classify:1;
-	__u8			tc_at_ingress:1;
-#endif
 	__u8			redirected:1;
 #ifdef CONFIG_NET_REDIRECT
 	__u8			from_ingress:1;
@@ -969,7 +969,7 @@ struct sk_buff {
 	__u8			decrypted:1;
 #endif
 	__u8			slow_gro:1;
-	__u8			mono_delivery_time:1;
+	__u8			csum_not_inet:1;
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
@@ -1047,10 +1047,16 @@ struct sk_buff {
 /* if you move pkt_vlan_present around you also must adapt these constants */
 #ifdef __BIG_ENDIAN_BITFIELD
 #define PKT_VLAN_PRESENT_BIT	7
+#define TC_AT_INGRESS_MASK		(1 << 0)
+#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 2)
 #else
 #define PKT_VLAN_PRESENT_BIT	0
+#define TC_AT_INGRESS_MASK		(1 << 7)
+#define SKB_MONO_DELIVERY_TIME_MASK	(1 << 5)
 #endif
 #define PKT_VLAN_PRESENT_OFFSET	offsetof(struct sk_buff, __pkt_vlan_present_offset)
+#define TC_AT_INGRESS_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset)
+#define SKB_MONO_DELIVERY_TIME_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset)
 
 #ifdef __KERNEL__
 /*