Merge branch 'add-validation-for-bpf_set_retval-helper'

Xu Kuohai says:

====================
Add validation for bpf_set_retval helper

From: Xu Kuohai <xukuohai@huawei.com>

The bpf_set_retval() helper is used by cgroup BPF programs to set the
return value of the kernel hook. The argument type for this helper is
ARG_ANYTHING. This allows setting a positive value, which no cgroup
hook expects and can cause issues, such as the kernel panic reported
in [1].

This series adds validation for the argument of the bpf_set_retval()
helper.

For BPF_LSM_CGROUP, the same validation as BPF_LSM_MAC is enforced,
i.e. validate the argument against the LSM hook specific range, which
is returned by bpf_lsm_get_retval_range().

For all other cgroup program types, restrict the argument to
[-MAX_ERRNO, 0], which matches the kernel convention of 0 for success
and negative errno for error.

BPF_CGROUP_GETSOCKOPT is an exception from this restriction, since valid
getsockopt implementations may return positive values (e.g. optlen), as
allowed by commit c4dcfdd406 ("bpf: Move getsockopt retval to struct
bpf_cg_run_ctx").

[1] https://lore.kernel.org/all/567d3206-74a5-44e5-99c6-779c425f399e@std.uestc.edu.cn

v5:
- Use resolve_prog_type(env->prog) instead of env->prog->type for prog type checks
- Target bpf-next tree

v4: https://lore.kernel.org/bpf/20260604130458.617765-1-xukuohai@huaweicloud.com
- Remove the return value limit for BPF_CGROUP_GETSOCKOPT type
- Refine the range of return value of bpf_get_retval helper

v3: https://lore.kernel.org/bpf/20260530101239.590395-1-xukuohai@huaweicloud.com/
- Mark R1 as precise to prevent validation bypass via branch pruning (sashiko)

v2: https://lore.kernel.org/bpf/20260530055557.549474-1-xukuohai@huaweicloud.com/
- Extend validation from LSM cgroup BPF type to all cgroup BPF types (sashiko)

v1: https://lore.kernel.org/bpf/20260523085806.417723-1-xukuohai@huaweicloud.com/
====================

Link: https://patch.msgid.link/20260605140243.664590-1-xukuohai@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

kernel/bpf/verifier.c

@@ -9770,7 +9770,9 @@ static int do_refine_retval_range(struct bpf_verifier_env *env,
 				  int func_id,
 				  struct bpf_call_arg_meta *meta)
 {
+	struct bpf_retval_range range;
 	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
+	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 
 	if (ret_type != RET_INTEGER)
 		return 0;
@@ -9790,6 +9792,29 @@ static int do_refine_retval_range(struct bpf_verifier_env *env,
 		reg_set_urange32(ret_reg, 0, nr_cpu_ids - 1);
 		reg_bounds_sync(ret_reg);
 		break;
+	case BPF_FUNC_get_retval:
+		/*
+		 * bpf_get_retval may see arbitrary value passed by bpf_prog_run_array_cg for
+		 * CGROUP_GETSOCKOPT type.
+		 */
+		if (prog_type == BPF_PROG_TYPE_CGROUP_SOCKOPT &&
+		    env->prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT)
+			break;
+
+		if (prog_type == BPF_PROG_TYPE_LSM &&
+		    env->prog->expected_attach_type == BPF_LSM_CGROUP) {
+			if (!env->prog->aux->attach_func_proto->type)
+				break;
+			bpf_lsm_get_retval_range(env->prog, &range);
+		} else {
+			range.minval = -MAX_ERRNO;
+			range.maxval = 0;
+		}
+
+		reg_set_srange64(ret_reg, range.minval, range.maxval);
+		reg_set_srange32(ret_reg, range.minval, range.maxval);
+		reg_bounds_sync(ret_reg);
+		break;
 	}
 
 	return reg_bounds_sanity_check(env, ret_reg, "retval");
@@ -10259,6 +10284,24 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		}
 		break;
 	case BPF_FUNC_set_retval:
+	{
+		struct bpf_retval_range range = {
+			.minval = -MAX_ERRNO,
+			.maxval = 0,
+			.return_32bit = true
+		};
+		struct bpf_reg_state *r1 = &regs[BPF_REG_1];
+
+		if (r1->type != SCALAR_VALUE) {
+			verbose(env, "R1 is not a scalar\n");
+			return -EINVAL;
+		}
+
+		/* CGROUP_GETSOCKOPT is allowed to return arbitrary value */
+		if (prog_type == BPF_PROG_TYPE_CGROUP_SOCKOPT &&
+		    env->prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT)
+			break;
+
 		if (prog_type == BPF_PROG_TYPE_LSM &&
 		    env->prog->expected_attach_type == BPF_LSM_CGROUP) {
 			if (!env->prog->aux->attach_func_proto->type) {
@@ -10268,8 +10311,20 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 				verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
 				return -EINVAL;
 			}
+			bpf_lsm_get_retval_range(env->prog, &range);
 		}
+
+		err = mark_chain_precision(env, BPF_REG_1);
+		if (err)
+			return err;
+
+		if (!retval_range_within(range, r1)) {
+			verbose_invalid_scalar(env, r1, range, "At bpf_set_retval", "R1");
+			return -EINVAL;
+		}
+
 		break;
+	}
 	case BPF_FUNC_dynptr_write:
 	{
 		enum bpf_dynptr_type dynptr_type = meta.dynptr.type;

tools/testing/selftests/bpf/prog_tests/verifier.c

@@ -117,6 +117,7 @@
 #include "verifier_xdp.skel.h"
 #include "verifier_xdp_direct_packet_access.skel.h"
 #include "verifier_bits_iter.skel.h"
+#include "verifier_set_retval.skel.h"
 #include "verifier_lsm.skel.h"
 #include "verifier_jit_inline.skel.h"
 #include "irq.skel.h"
@@ -266,6 +267,7 @@ void test_verifier_xadd(void)                 { RUN(verifier_xadd); }
 void test_verifier_xdp(void)                  { RUN(verifier_xdp); }
 void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); }
 void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); }
+void test_verifier_set_retval(void)            { RUN(verifier_set_retval); }
 void test_verifier_lsm(void)                  { RUN(verifier_lsm); }
 void test_irq(void)			      { RUN(irq); }
 void test_verifier_mtu(void)		      { RUN(verifier_mtu); }

tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c

@@ -5,6 +5,7 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include <errno.h>
+#include "err.h"
 
 extern int tcp_memory_per_cpu_fw_alloc __ksym;
 extern int udp_memory_per_cpu_fw_alloc __ksym;
@@ -97,6 +98,7 @@ int sock_create(struct bpf_sock *ctx)
 	return 1;
 
 err:
+	set_if_not_errno_or_zero(err, -EFAULT);
 	bpf_set_retval(err);
 	return 0;
 }

tools/testing/selftests/bpf/progs/verifier_set_retval.c

@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+
+SEC("lsm_cgroup/socket_create")
+__description("lsm_cgroup bpf_set_retval success")
+__success
+int BPF_PROG(lsm_cgroup_set_retval_zero_valid, int family, int type, int protocol, int kern)
+{
+	bpf_set_retval(0);
+	return 0;
+}
+
+SEC("lsm_cgroup/socket_create")
+__description("lsm_cgroup bpf_set_retval valid errno")
+__success
+int BPF_PROG(lsm_cgroup_set_retval_negative_valid, int family, int type, int protocol, int kern)
+{
+	bpf_set_retval(-12);
+	return 0;
+}
+
+SEC("lsm_cgroup/socket_create")
+__description("lsm_cgroup bpf_set_retval invalid negative value")
+__failure __msg("should have been in [-4095, 0]")
+int BPF_PROG(lsm_cgroup_set_retval_negative_invalid, int family, int type, int protocol, int kern)
+{
+	bpf_set_retval(-4096);
+	return 0;
+}
+
+SEC("lsm_cgroup/socket_create")
+__description("lsm_cgroup bpf_set_retval invalid positive value")
+__failure __msg("should have been in [-4095, 0]")
+int BPF_PROG(lsm_cgroup_set_retval_positive_invalid, int family, int type, int protocol, int kern)
+{
+	bpf_set_retval(1);
+	return 0;
+}
+
+SEC("cgroup/dev")
+__description("cgroup_device bpf_set_retval success")
+__success
+int cgroup_dev_set_retval_0(struct bpf_cgroup_dev_ctx *ctx)
+{
+	bpf_set_retval(0);
+	return 1;
+}
+
+SEC("cgroup/dev")
+__description("cgroup_device bpf_set_retval valid errno")
+__success
+int cgroup_dev_set_retval_neg_maxerrno(struct bpf_cgroup_dev_ctx *ctx)
+{
+	bpf_set_retval(-4095);
+	return 1;
+}
+
+SEC("cgroup/dev")
+__description("cgroup_device bpf_set_retval invalid positive value")
+__failure __msg("should have been in [-4095, 0]")
+int cgroup_dev_set_retval_1(struct bpf_cgroup_dev_ctx *ctx)
+{
+	bpf_set_retval(1);
+	return 1;
+}
+
+SEC("cgroup/dev")
+__description("cgroup_device bpf_set_retval invalid negative value")
+__failure __msg("should have been in [-4095, 0]")
+int cgroup_dev_set_retval_neg_4096(struct bpf_cgroup_dev_ctx *ctx)
+{
+	bpf_set_retval(-4096);
+	return 1;
+}
+
+SEC("cgroup/dev")
+__description("bpf_set_retval bounds check survives state pruning")
+__failure __msg("should have been in [-4095, 0]")
+__naked int cgroup_dev_set_retval_pruning_bypass(struct bpf_cgroup_dev_ctx *ctx)
+{
+	asm volatile (
+		"call %[bpf_get_prandom_u32];"
+		"if r0 != 0 goto 1f;"
+		"r0 = r0;"
+		"r0 = r0;"
+		"r0 = r0;"
+		"r0 = r0;"
+		"goto 2f;"
+	"1:"
+		"call %[bpf_get_prandom_u32];"
+	"2:"
+		"r1 = r0;"
+		"call %[bpf_set_retval];"
+		"r0 = 1;"
+		"exit;"
+		:
+		: __imm(bpf_get_prandom_u32),
+		  __imm(bpf_set_retval)
+		: __clobber_common
+	);
+}
+
+char _license[] SEC("license") = "GPL";