Merge branch 'cgroup-helpers'

Daniel Borkmann says:

====================
This adds various straight-forward helper improvements and additions to BPF
cgroup based connect(), sendmsg(), recvmsg() and bind-related hooks which
would allow to implement more fine-grained policies and improve current load
balancer limitations we're seeing. For details please see individual patches.
I've tested them on Kubernetes & Cilium and also added selftests for the small
verifier extension. Thanks!
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

2 files changed, 139 insertions, 1 deletions

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 5d01c5c7e598..222ba11966e3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2950,6 +2950,37 @@ union bpf_attr {
  *		restricted to raw_tracepoint bpf programs.
  *	Return
  *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * 	Description
+ * 		Retrieve the cookie (generated by the kernel) of the network
+ * 		namespace the input *ctx* is associated with. The network
+ * 		namespace cookie remains stable for its lifetime and provides
+ * 		a global identifier that can be assumed unique. If *ctx* is
+ * 		NULL, then the helper returns the cookie for the initial
+ * 		network namespace. The cookie itself is very similar to that
+ * 		of bpf_get_socket_cookie() helper, but for network namespaces
+ * 		instead of sockets.
+ * 	Return
+ * 		A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * 	Description
+ * 		Return id of cgroup v2 that is ancestor of the cgroup associated
+ * 		with the current task at the *ancestor_level*. The root cgroup
+ * 		is at *ancestor_level* zero and each step down the hierarchy
+ * 		increments the level. If *ancestor_level* == level of cgroup
+ * 		associated with the current task, then return value will be the
+ * 		same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * 		The helper is useful to implement policies based on cgroups
+ * 		that are upper in hierarchy than immediate cgroup associated
+ * 		with the current task.
+ *
+ * 		The format of returned id and helper limitations are same as in
+ * 		**bpf_get_current_cgroup_id**\ ().
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3073,7 +3104,9 @@ union bpf_attr {
 	FN(jiffies64),			\
 	FN(read_branch_records),	\
 	FN(get_ns_current_pid_tgid),	\
-	FN(xdp_output),
+	FN(xdp_output),			\
+	FN(get_netns_cookie),		\
+	FN(get_current_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/testing/selftests/bpf/verifier/ctx.c b/tools/testing/selftests/bpf/verifier/ctx.c
index 92762c08f5e3..93d6b1641481 100644
--- a/tools/testing/selftests/bpf/verifier/ctx.c
+++ b/tools/testing/selftests/bpf/verifier/ctx.c
@@ -91,3 +91,108 @@
 	.result = REJECT,
 	.errstr = "variable ctx access var_off=(0x0; 0x4)",
 },
+{
+	"pass ctx or null check, 1: ctx",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+	.result = ACCEPT,
+},
+{
+	"pass ctx or null check, 2: null",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+	.result = ACCEPT,
+},
+{
+	"pass ctx or null check, 3: 1",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+	.result = REJECT,
+	.errstr = "R1 type=inv expected=ctx",
+},
+{
+	"pass ctx or null check, 4: ctx - const",
+	.insns = {
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG,
+	.result = REJECT,
+	.errstr = "dereference of modified ctx ptr",
+},
+{
+	"pass ctx or null check, 5: null (connect)",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+	.expected_attach_type = BPF_CGROUP_INET4_CONNECT,
+	.result = ACCEPT,
+},
+{
+	"pass ctx or null check, 6: null (bind)",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_netns_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+	.result = ACCEPT,
+},
+{
+	"pass ctx or null check, 7: ctx (bind)",
+	.insns = {
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_socket_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+	.result = ACCEPT,
+},
+{
+	"pass ctx or null check, 8: null (bind)",
+	.insns = {
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_socket_cookie),
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
+	.expected_attach_type = BPF_CGROUP_INET4_POST_BIND,
+	.result = REJECT,
+	.errstr = "R1 type=inv expected=ctx",
+},