From: YiFei Zhu <zhuyifei@google.com>
Date: Thu, 16 Dec 2021 02:04:27 +0000
Subject: bpf: Add cgroup helpers bpf_{get,set}_retval to get/set syscall
return value
Patch-mainline: v5.18-rc1
Git-commit: b44123b4a3dcad4664d3a0f72c011ffd4c9c4d93
References: jsc#PED-1377
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>
Acked-by: Shung-Hsi Yu <shung-hsi.yu@suse.com>
---
include/linux/bpf.h | 10 ++++++----
include/uapi/linux/bpf.h | 18 ++++++++++++++++++
kernel/bpf/cgroup.c | 38 +++++++++++++++++++++++++++++++++++++-
tools/include/uapi/linux/bpf.h | 18 ++++++++++++++++++
4 files changed, 79 insertions(+), 5 deletions(-)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1304,7 +1304,7 @@ BPF_PROG_RUN_ARRAY_CG_FLAGS(const struct
while ((prog = READ_ONCE(item->prog))) {
run_ctx.prog_item = item;
func_ret = run_prog(prog, ctx);
- if (!(func_ret & 1))
+ if (!(func_ret & 1) && !IS_ERR_VALUE((long)run_ctx.retval))
run_ctx.retval = -EPERM;
*(ret_flags) |= (func_ret >> 1);
item++;
@@ -1334,7 +1334,7 @@ BPF_PROG_RUN_ARRAY_CG(const struct bpf_p
old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
while ((prog = READ_ONCE(item->prog))) {
run_ctx.prog_item = item;
- if (!run_prog(prog, ctx))
+ if (!run_prog(prog, ctx) && !IS_ERR_VALUE((long)run_ctx.retval))
run_ctx.retval = -EPERM;
item++;
}
@@ -1394,7 +1394,7 @@ out:
* 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
+ * 3: -err skb should be dropped
*/
#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \
({ \
@@ -1403,10 +1403,12 @@ out:
u32 _ret; \
_ret = BPF_PROG_RUN_ARRAY_CG_FLAGS(array, ctx, func, 0, &_flags); \
_cn = _flags & BPF_RET_SET_CN; \
+ if (_ret && !IS_ERR_VALUE((long)_ret)) \
+ _ret = -EFAULT; \
if (!_ret) \
_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \
else \
- _ret = (_cn ? NET_XMIT_DROP : -EPERM); \
+ _ret = (_cn ? NET_XMIT_DROP : _ret); \
_ret; \
})
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5033,6 +5033,22 @@ union bpf_attr {
*
* Return
* The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5221,6 +5237,8 @@ union bpf_attr {
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(get_retval), \
+ FN(set_retval), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1008,7 +1008,7 @@ int cgroup_bpf_prog_query(const union bp
* 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.
@@ -1044,6 +1044,8 @@ int __cgroup_bpf_run_filter_skb(struct s
} 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);
@@ -1169,6 +1171,36 @@ int __cgroup_bpf_check_dev_permission(sh
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)
{
@@ -1181,6 +1213,10 @@ cgroup_base_func_proto(enum bpf_func_id
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);
}
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5036,6 +5036,22 @@ union bpf_attr {
*
* Return
* The number of arguments of the traced function.
+ *
+ * int bpf_get_retval(void)
+ * Description
+ * Get the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * The syscall's return value.
+ *
+ * int bpf_set_retval(int retval)
+ * Description
+ * Set the syscall's return value that will be returned to userspace.
+ *
+ * This helper is currently supported by cgroup programs only.
+ * Return
+ * 0 on success, or a negative error in case of failure.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -5224,6 +5240,8 @@ union bpf_attr {
FN(get_func_arg), \
FN(get_func_ret), \
FN(get_func_arg_cnt), \
+ FN(get_retval), \
+ FN(set_retval), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper