bpf: Add cgroup helpers bpf_{get,set}_retval to get/set syscall return value

The helpers continue to use int for retval because all the hooks
are int-returning rather than long-returning. The return value of
bpf_set_retval is int for future-proofing, in case in the future
there may be errors trying to set the retval.

After the previous patch, if a program rejects a syscall by
returning 0, an -EPERM will be generated no matter if the retval
is already set to -err. This patch change it being forced only if
retval is not -err. This is because we want to support, for
example, invoking bpf_set_retval(-EINVAL) and return 0, and have
the syscall return value be -EINVAL not -EPERM.

For BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY, the prior behavior is
that, if the return value is NET_XMIT_DROP, the packet is silently
dropped. We preserve this behavior for backward compatibility
reasons, so even if an errno is set, the errno does not return to
caller. However, setting a non-err to retval cannot propagate so
this is not allowed and we return a -EFAULT in that case.

Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/b4013fd5d16bed0b01977c1fafdeae12e1de61fb.1639619851.git.zhuyifei@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 37 insertions, 1 deletions

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index b6fad0bbf5a7..279ebbed75a5 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1044,7 +1044,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  *   NET_XMIT_DROP       (1)	- drop packet and notify TCP to call cwr
  *   NET_XMIT_CN         (2)	- continue with packet output and notify TCP
  *				  to call cwr
- *   -EPERM			- drop packet
+ *   -err			- drop packet
  *
  * For ingress packets, this function will return -EPERM if any
  * attached program was found and if it returned != 1 during execution.
@@ -1080,6 +1080,8 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk,
 	} else {
 		ret = BPF_PROG_RUN_ARRAY_CG(cgrp->bpf.effective[atype], skb,
 					    __bpf_prog_run_save_cb, 0);
+		if (ret && !IS_ERR_VALUE((long)ret))
+			ret = -EFAULT;
 	}
 	bpf_restore_data_end(skb, saved_data_end);
 	__skb_pull(skb, offset);
@@ -1205,6 +1207,36 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 	return ret;
 }
 
+BPF_CALL_0(bpf_get_retval)
+{
+	struct bpf_cg_run_ctx *ctx =
+		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+	return ctx->retval;
+}
+
+static const struct bpf_func_proto bpf_get_retval_proto = {
+	.func		= bpf_get_retval,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
+BPF_CALL_1(bpf_set_retval, int, retval)
+{
+	struct bpf_cg_run_ctx *ctx =
+		container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
+
+	ctx->retval = retval;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_set_retval_proto = {
+	.func		= bpf_set_retval,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1217,6 +1249,10 @@ cgroup_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_current_cgroup_id_proto;
 	case BPF_FUNC_perf_event_output:
 		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_retval:
+		return &bpf_get_retval_proto;
+	case BPF_FUNC_set_retval:
+		return &bpf_set_retval_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}