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>

3 files changed, 65 insertions, 10 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index cfcf9b4d1ec2..5072733743e9 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -8859,6 +8859,65 @@ static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si,
 	return insn;
 }
 
+static struct bpf_insn *bpf_convert_tstamp_read(const struct bpf_insn *si,
+						struct bpf_insn *insn)
+{
+	__u8 value_reg = si->dst_reg;
+	__u8 skb_reg = si->src_reg;
+
+#ifdef CONFIG_NET_CLS_ACT
+	__u8 tmp_reg = BPF_REG_AX;
+
+	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK);
+	*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 5);
+	/* @ingress, read __sk_buff->tstamp as the (rcv) timestamp,
+	 * so check the skb->mono_delivery_time.
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
+			      SKB_MONO_DELIVERY_TIME_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
+				SKB_MONO_DELIVERY_TIME_MASK);
+	*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 2);
+	/* skb->mono_delivery_time is set, read 0 as the (rcv) timestamp. */
+	*insn++ = BPF_MOV64_IMM(value_reg, 0);
+	*insn++ = BPF_JMP_A(1);
+#endif
+
+	*insn++ = BPF_LDX_MEM(BPF_DW, value_reg, skb_reg,
+			      offsetof(struct sk_buff, tstamp));
+	return insn;
+}
+
+static struct bpf_insn *bpf_convert_tstamp_write(const struct bpf_insn *si,
+						 struct bpf_insn *insn)
+{
+	__u8 value_reg = si->src_reg;
+	__u8 skb_reg = si->dst_reg;
+
+#ifdef CONFIG_NET_CLS_ACT
+	__u8 tmp_reg = BPF_REG_AX;
+
+	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg, TC_AT_INGRESS_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg, TC_AT_INGRESS_MASK);
+	*insn++ = BPF_JMP32_IMM(BPF_JEQ, tmp_reg, 0, 3);
+	/* Writing __sk_buff->tstamp at ingress as the (rcv) timestamp.
+	 * Clear the skb->mono_delivery_time.
+	 */
+	*insn++ = BPF_LDX_MEM(BPF_B, tmp_reg, skb_reg,
+			      SKB_MONO_DELIVERY_TIME_OFFSET);
+	*insn++ = BPF_ALU32_IMM(BPF_AND, tmp_reg,
+				~SKB_MONO_DELIVERY_TIME_MASK);
+	*insn++ = BPF_STX_MEM(BPF_B, skb_reg, tmp_reg,
+			      SKB_MONO_DELIVERY_TIME_OFFSET);
+#endif
+
+	/* skb->tstamp = tstamp */
+	*insn++ = BPF_STX_MEM(BPF_DW, skb_reg, value_reg,
+			      offsetof(struct sk_buff, tstamp));
+	return insn;
+}
+
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				  const struct bpf_insn *si,
 				  struct bpf_insn *insn_buf,
@@ -9167,17 +9226,9 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 		BUILD_BUG_ON(sizeof_field(struct sk_buff, tstamp) != 8);
 
 		if (type == BPF_WRITE)
-			*insn++ = BPF_STX_MEM(BPF_DW,
-					      si->dst_reg, si->src_reg,
-					      bpf_target_off(struct sk_buff,
-							     tstamp, 8,
-							     target_size));
+			insn = bpf_convert_tstamp_write(si, insn);
 		else
-			*insn++ = BPF_LDX_MEM(BPF_DW,
-					      si->dst_reg, si->src_reg,
-					      bpf_target_off(struct sk_buff,
-							     tstamp, 8,
-							     target_size));
+			insn = bpf_convert_tstamp_read(si, insn);
 		break;
 
 	case offsetof(struct __sk_buff, gso_segs):
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index a77d8908e737..fea2d78b9ddc 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -53,6 +53,8 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
 		bpf_compute_data_pointers(skb);
 		filter_res = bpf_prog_run(filter, skb);
 	}
+	if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+		skb->mono_delivery_time = 0;
 	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
 		skb_orphan(skb);
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index df19a847829e..c85b85a192bf 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -102,6 +102,8 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			bpf_compute_data_pointers(skb);
 			filter_res = bpf_prog_run(prog->filter, skb);
 		}
+		if (unlikely(!skb->tstamp && skb->mono_delivery_time))
+			skb->mono_delivery_time = 0;
 
 		if (prog->exts_integrated) {
 			res->class   = 0;