bpf: Create BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY

Create new macro BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY() to be used by
__cgroup_bpf_run_filter_skb for EGRESS BPF progs so BPF programs can
request cwr for TCP packets.

Current cgroup skb programs can only return 0 or 1 (0 to drop the
packet. This macro changes the behavior so the low order bit
indicates whether the packet should be dropped (0) or not (1)
and the next bit is used for congestion notification (cn).

Hence, new allowed return values of CGROUP EGRESS BPF programs are:
  0: drop packet
  1: keep packet
  2: drop packet and call cwr
  3: keep packet and call cwr

This macro then converts it to one of NET_XMIT values or -EPERM
that has the effect of dropping the packet with no cn.
  0: NET_XMIT_SUCCESS  skb should be transmitted (no cn)
  1: NET_XMIT_DROP     skb should be dropped and cwr called
  2: NET_XMIT_CN       skb should be transmitted and cwr called
  3: -EPERM            skb should be dropped (no cn)

Note that when more than one BPF program is called, the packet is
dropped if at least one of programs requests it be dropped, and
there is cn if at least one program returns cn.

Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 50 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ff3e00ff84d2..2cc58fc0f413 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -552,6 +552,56 @@ _out:							\
 		_ret;					\
 	 })
 
+/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
+ * so BPF programs can request cwr for TCP packets.
+ *
+ * Current cgroup skb programs can only return 0 or 1 (0 to drop the
+ * packet. This macro changes the behavior so the low order bit
+ * indicates whether the packet should be dropped (0) or not (1)
+ * and the next bit is a congestion notification bit. This could be
+ * used by TCP to call tcp_enter_cwr()
+ *
+ * Hence, new allowed return values of CGROUP EGRESS BPF programs are:
+ *   0: drop packet
+ *   1: keep packet
+ *   2: drop packet and cn
+ *   3: keep packet and cn
+ *
+ * This macro then converts it to one of the NET_XMIT or an error
+ * code that is then interpreted as drop packet (and no cn):
+ *   0: NET_XMIT_SUCCESS  skb should be transmitted
+ *   1: NET_XMIT_DROP     skb should be dropped and cn
+ *   2: NET_XMIT_CN       skb should be transmitted and cn
+ *   3: -EPERM            skb should be dropped
+ */
+#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func)		\
+	({						\
+		struct bpf_prog_array_item *_item;	\
+		struct bpf_prog *_prog;			\
+		struct bpf_prog_array *_array;		\
+		u32 ret;				\
+		u32 _ret = 1;				\
+		u32 _cn = 0;				\
+		preempt_disable();			\
+		rcu_read_lock();			\
+		_array = rcu_dereference(array);	\
+		_item = &_array->items[0];		\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			ret = func(_prog, ctx);		\
+			_ret &= (ret & 1);		\
+			_cn |= (ret & 2);		\
+			_item++;			\
+		}					\
+		rcu_read_unlock();			\
+		preempt_enable();			\
+		if (_ret)				\
+			_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS);	\
+		else					\
+			_ret = (_cn ? NET_XMIT_DROP : -EPERM);		\
+		_ret;					\
+	})
+
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
 	__BPF_PROG_RUN_ARRAY(array, ctx, func, false)