bpf: Add __sk_buff->delivery_time_type and bpf_skb_set_skb_delivery_time()

* __sk_buff->delivery_time_type:
This patch adds __sk_buff->delivery_time_type.  It tells if the
delivery_time is stored in __sk_buff->tstamp or not.

It will be most useful for ingress to tell if the __sk_buff->tstamp
has the (rcv) timestamp or delivery_time.  If delivery_time_type
is 0 (BPF_SKB_DELIVERY_TIME_NONE), it has the (rcv) timestamp.

Two non-zero types are defined for the delivery_time_type,
BPF_SKB_DELIVERY_TIME_MONO and BPF_SKB_DELIVERY_TIME_UNSPEC.  For UNSPEC,
it can only happen in egress because only mono delivery_time can be
forwarded to ingress now.  The clock of UNSPEC delivery_time
can be deduced from the skb->sk->sk_clockid which is how
the sch_etf doing it also.

* Provide forwarded delivery_time to tc-bpf@ingress:
With the help of the new delivery_time_type, the tc-bpf has a way
to tell if the __sk_buff->tstamp has the (rcv) timestamp or
the delivery_time.  During bpf load time, the verifier will learn if
the bpf prog has accessed the new __sk_buff->delivery_time_type.
If it does, it means the tc-bpf@ingress is expecting the
skb->tstamp could have the delivery_time.  The kernel will then
read the skb->tstamp as-is during bpf insn rewrite without
checking the skb->mono_delivery_time.  This is done by adding a
new prog->delivery_time_access bit.  The same goes for
writing skb->tstamp.

* bpf_skb_set_delivery_time():
The bpf_skb_set_delivery_time() helper is added to allow setting both
delivery_time and the delivery_time_type at the same time.  If the
tc-bpf does not need to change the delivery_time_type, it can directly
write to the __sk_buff->tstamp as the existing tc-bpf has already been
doing.  It will be most useful at ingress to change the
__sk_buff->tstamp from the (rcv) timestamp to
a mono delivery_time and then bpf_redirect_*().

bpf only has mono clock helper (bpf_ktime_get_ns), and
the current known use case is the mono EDT for fq, and
only mono delivery time can be kept during forward now,
so bpf_skb_set_delivery_time() only supports setting
BPF_SKB_DELIVERY_TIME_MONO.  It can be extended later when use cases
come up and the forwarding path also supports other clock bases.

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

2 files changed, 42 insertions, 2 deletions

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1cb1af917617..9bf26307247f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -572,7 +572,8 @@ struct bpf_prog {
 				has_callchain_buf:1, /* callchain buffer allocated? */
 				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
 				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
-				call_get_func_ip:1; /* Do we call get_func_ip() */
+				call_get_func_ip:1, /* Do we call get_func_ip() */
+				delivery_time_access:1; /* Accessed __sk_buff->delivery_time_type */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	enum bpf_attach_type	expected_attach_type; /* For some prog types */
 	u32			len;		/* Number of filter blocks */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index afe3d0d7f5f2..4eebea830613 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5086,6 +5086,37 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure. On error
  *		*dst* buffer is zeroed out.
+ *
+ * long bpf_skb_set_delivery_time(struct sk_buff *skb, u64 dtime, u32 dtime_type)
+ *	Description
+ *		Set a *dtime* (delivery time) to the __sk_buff->tstamp and also
+ *		change the __sk_buff->delivery_time_type to *dtime_type*.
+ *
+ *		When setting a delivery time (non zero *dtime*) to
+ *		__sk_buff->tstamp, only BPF_SKB_DELIVERY_TIME_MONO *dtime_type*
+ *		is supported.  It is the only delivery_time_type that will be
+ *		kept after bpf_redirect_*().
+ *
+ *		If there is no need to change the __sk_buff->delivery_time_type,
+ *		the delivery time can be directly written to __sk_buff->tstamp
+ *		instead.
+ *
+ *		*dtime* 0 and *dtime_type* BPF_SKB_DELIVERY_TIME_NONE
+ *		can be used to clear any delivery time stored in
+ *		__sk_buff->tstamp.
+ *
+ *		Only IPv4 and IPv6 skb->protocol are supported.
+ *
+ *		This function is most useful when it needs to set a
+ *		mono delivery time to __sk_buff->tstamp and then
+ *		bpf_redirect_*() to the egress of an iface.  For example,
+ *		changing the (rcv) timestamp in __sk_buff->tstamp at
+ *		ingress to a mono delivery time and then bpf_redirect_*()
+ *		to sch_fq@phy-dev.
+ *	Return
+ *		0 on success.
+ *		**-EINVAL** for invalid input
+ *		**-EOPNOTSUPP** for unsupported delivery_time_type and protocol
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5280,6 +5311,7 @@ union bpf_attr {
 	FN(xdp_load_bytes),		\
 	FN(xdp_store_bytes),		\
 	FN(copy_from_user_task),	\
+	FN(skb_set_delivery_time),      \
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -5469,6 +5501,12 @@ union {					\
 	__u64 :64;			\
 } __attribute__((aligned(8)))
 
+enum {
+	BPF_SKB_DELIVERY_TIME_NONE,
+	BPF_SKB_DELIVERY_TIME_UNSPEC,
+	BPF_SKB_DELIVERY_TIME_MONO,
+};
+
 /* user accessible mirror of in-kernel sk_buff.
  * new fields can only be added to the end of this structure
  */
@@ -5509,7 +5547,8 @@ struct __sk_buff {
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
 	__u32 gso_size;
-	__u32 :32;		/* Padding, future use. */
+	__u8  delivery_time_type;
+	__u32 :24;		/* Padding, future use. */
 	__u64 hwtstamp;
 };