bpf: Sysctl hook
Containerized applications may run as root and it may create problems
for whole host. Specifically such applications may change a sysctl and
affect applications in other containers.
Furthermore in existing infrastructure it may not be possible to just
completely disable writing to sysctl, instead such a process should be
gradual with ability to log what sysctl are being changed by a
container, investigate, limit the set of writable sysctl to currently
used ones (so that new ones can not be changed) and eventually reduce
this set to zero.
The patch introduces new program type BPF_PROG_TYPE_CGROUP_SYSCTL and
attach type BPF_CGROUP_SYSCTL to solve these problems on cgroup basis.
New program type has access to following minimal context:
struct bpf_sysctl {
__u32 write;
};
Where @write indicates whether sysctl is being read (= 0) or written (=
1).
Helpers to access sysctl name and value will be introduced separately.
BPF_CGROUP_SYSCTL attach point is added to sysctl code right before
passing control to ctl_table->proc_handler so that BPF program can
either allow or deny access to sysctl.
Suggested-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index a4c644c..b1c45da 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -17,6 +17,8 @@
struct bpf_prog;
struct bpf_sock_ops_kern;
struct bpf_cgroup_storage;
+struct ctl_table;
+struct ctl_table_header;
#ifdef CONFIG_CGROUP_BPF
@@ -109,6 +111,10 @@
int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
short access, enum bpf_attach_type type);
+int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
+ struct ctl_table *table, int write,
+ enum bpf_attach_type type);
+
static inline enum bpf_cgroup_storage_type cgroup_storage_type(
struct bpf_map *map)
{
@@ -253,6 +259,17 @@
\
__ret; \
})
+
+
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) \
+({ \
+ int __ret = 0; \
+ if (cgroup_bpf_enabled) \
+ __ret = __cgroup_bpf_run_filter_sysctl(head, table, write, \
+ BPF_CGROUP_SYSCTL); \
+ __ret; \
+})
+
int cgroup_bpf_prog_attach(const union bpf_attr *attr,
enum bpf_prog_type ptype, struct bpf_prog *prog);
int cgroup_bpf_prog_detach(const union bpf_attr *attr,
@@ -321,6 +338,7 @@
#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
#define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_SYSCTL(head, table, write) ({ 0; })
#define for_each_cgroup_storage_type(stype) for (; false; )