bpf: per-cgroup lsm flavor

Allow attaching to lsm hooks in the cgroup context.

Attaching to per-cgroup LSM works exactly like attaching
to other per-cgroup hooks. New BPF_LSM_CGROUP is added
to trigger new mode; the actual lsm hook we attach to is
signaled via existing attach_btf_id.

For the hooks that have 'struct socket' or 'struct sock' as its first
argument, we use the cgroup associated with that socket. For the rest,
we use 'current' cgroup (this is all on default hierarchy == v2 only).
Note that for some hooks that work on 'struct sock' we still
take the cgroup from 'current' because some of them work on the socket
that hasn't been properly initialized yet.

Behind the scenes, we allocate a shim program that is attached
to the trampoline and runs cgroup effective BPF programs array.
This shim has some rudimentary ref counting and can be shared
between several programs attaching to the same lsm hook from
different cgroups.

Note that this patch bloats cgroup size because we add 211
cgroup_bpf_attach_type(s) for simplicity sake. This will be
addressed in the subsequent patch.

Also note that we only add non-sleepable flavor for now. To enable
sleepable use-cases, bpf_prog_run_array_cg has to grab trace rcu,
shim programs have to be freed via trace rcu, cgroup_bpf.effective
should be also trace-rcu-managed + maybe some other changes that
I'm not aware of.

Reviewed-by: Martin KaFai Lau <[email protected]>
Signed-off-by: Stanislav Fomichev <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

arch/x86/net/bpf_jit_comp.c

@@ -1770,6 +1770,10 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 			   struct bpf_tramp_link *l, int stack_size,
 			   int run_ctx_off, bool save_ret)
 {
+	void (*exit)(struct bpf_prog *prog, u64 start,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit;
+	u64 (*enter)(struct bpf_prog *prog,
+		     struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter;
 	u8 *prog = *pprog;
 	u8 *jmp_insn;
 	int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie);
@@ -1788,15 +1792,21 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	 */
 	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off);
 
+	if (p->aux->sleepable) {
+		enter = __bpf_prog_enter_sleepable;
+		exit = __bpf_prog_exit_sleepable;
+	} else if (p->expected_attach_type == BPF_LSM_CGROUP) {
+		enter = __bpf_prog_enter_lsm_cgroup;
+		exit = __bpf_prog_exit_lsm_cgroup;
+	}
+
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p);
 	/* arg2: lea rsi, [rbp - ctx_cookie_off] */
 	EMIT4(0x48, 0x8D, 0x75, -run_ctx_off);
 
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_enter_sleepable :
-		      __bpf_prog_enter, prog))
-			return -EINVAL;
+	if (emit_call(&prog, enter, prog))
+		return -EINVAL;
 	/* remember prog start time returned by __bpf_prog_enter */
 	emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0);
 
@@ -1840,10 +1850,8 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6);
 	/* arg3: lea rdx, [rbp - run_ctx_off] */
 	EMIT4(0x48, 0x8D, 0x55, -run_ctx_off);
-	if (emit_call(&prog,
-		      p->aux->sleepable ? __bpf_prog_exit_sleepable :
-		      __bpf_prog_exit, prog))
-			return -EINVAL;
+	if (emit_call(&prog, exit, prog))
+		return -EINVAL;
 
 	*pprog = prog;
 	return 0;

include/linux/bpf-cgroup-defs.h

@@ -10,6 +10,12 @@
 
 struct bpf_prog_array;
 
+#ifdef CONFIG_BPF_LSM
+#define CGROUP_LSM_NUM 211 /* will be addressed in the next patch */
+#else
+#define CGROUP_LSM_NUM 0
+#endif
+
 enum cgroup_bpf_attach_type {
 	CGROUP_BPF_ATTACH_TYPE_INVALID = -1,
 	CGROUP_INET_INGRESS = 0,
@@ -35,6 +41,8 @@ enum cgroup_bpf_attach_type {
 	CGROUP_INET4_GETSOCKNAME,
 	CGROUP_INET6_GETSOCKNAME,
 	CGROUP_INET_SOCK_RELEASE,
+	CGROUP_LSM_START,
+	CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1,
 	MAX_CGROUP_BPF_ATTACH_TYPE
 };
 

include/linux/bpf-cgroup.h

@@ -23,6 +23,13 @@ struct ctl_table;
 struct ctl_table_header;
 struct task_struct;
 
+unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
+				       const struct bpf_insn *insn);
+unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
+					 const struct bpf_insn *insn);
+unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
+					  const struct bpf_insn *insn);
+
 #ifdef CONFIG_CGROUP_BPF
 
 #define CGROUP_ATYPE(type) \

include/linux/bpf.h

@@ -794,6 +794,10 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start, struct bpf_tramp_
 u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start,
 				       struct bpf_tramp_run_ctx *run_ctx);
+u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
+					struct bpf_tramp_run_ctx *run_ctx);
+void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
+					struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
 void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
 
@@ -1060,6 +1064,7 @@ struct bpf_prog_aux {
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
 	u32 verified_insns;
+	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
 #ifdef CONFIG_SECURITY
@@ -1167,6 +1172,11 @@ struct bpf_tramp_link {
 	u64 cookie;
 };
 
+struct bpf_shim_tramp_link {
+	struct bpf_tramp_link link;
+	struct bpf_trampoline *trampoline;
+};
+
 struct bpf_tracing_link {
 	struct bpf_tramp_link link;
 	enum bpf_attach_type attach_type;
@@ -1245,6 +1255,9 @@ struct bpf_dummy_ops {
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 			    union bpf_attr __user *uattr);
 #endif
+int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+				    int cgroup_atype);
+void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog);
 #else
 static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
 {
@@ -1268,6 +1281,14 @@ static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
 {
 	return -EINVAL;
 }
+static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+						  int cgroup_atype)
+{
+	return -EOPNOTSUPP;
+}
+static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
+{
+}
 #endif
 
 struct bpf_array {
@@ -2368,6 +2389,8 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
 extern const struct bpf_func_proto bpf_loop_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
+extern const struct bpf_func_proto bpf_set_retval_proto;
+extern const struct bpf_func_proto bpf_get_retval_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);
@@ -2485,6 +2508,7 @@ int bpf_arch_text_invalidate(void *dst, size_t len);
 
 struct btf_id_set;
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
+int btf_id_set_index(const struct btf_id_set *set, u32 id);
 
 #define MAX_BPRINTF_VARARGS		12
 

include/linux/bpf_lsm.h

@@ -42,6 +42,9 @@ extern const struct bpf_func_proto bpf_inode_storage_get_proto;
 extern const struct bpf_func_proto bpf_inode_storage_delete_proto;
 void bpf_inode_storage_free(struct inode *inode);
 
+int bpf_lsm_hook_idx(u32 btf_id);
+void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func);
+
 #else /* !CONFIG_BPF_LSM */
 
 static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
@@ -65,6 +68,16 @@ static inline void bpf_inode_storage_free(struct inode *inode)
 {
 }
 
+static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
+					   bpf_func_t *bpf_func)
+{
+}
+
+static inline int bpf_lsm_hook_idx(u32 btf_id)
+{
+	return -EINVAL;
+}
+
 #endif /* CONFIG_BPF_LSM */
 
 #endif /* _LINUX_BPF_LSM_H */

include/linux/btf_ids.h

@@ -179,7 +179,8 @@ extern struct btf_id_set name;
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP, udp_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UDP6, udp6_sock)			\
 	BTF_SOCK_TYPE(BTF_SOCK_TYPE_UNIX, unix_sock)			\
-	BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock)
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_MPTCP, mptcp_sock)			\
+	BTF_SOCK_TYPE(BTF_SOCK_TYPE_SOCKET, socket)
 
 enum {
 #define BTF_SOCK_TYPE(name, str) name,

include/uapi/linux/bpf.h

@@ -998,6 +998,7 @@ enum bpf_attach_type {
 	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	BPF_PERF_EVENT,
 	BPF_TRACE_KPROBE_MULTI,
+	BPF_LSM_CGROUP,
 	__MAX_BPF_ATTACH_TYPE
 };
 

kernel/bpf/bpf_lsm.c

@@ -16,6 +16,7 @@
 #include <linux/bpf_local_storage.h>
 #include <linux/btf_ids.h>
 #include <linux/ima.h>
+#include <linux/bpf-cgroup.h>
 
 /* For every LSM hook that allows attachment of BPF programs, declare a nop
  * function where a BPF program can be attached.
@@ -35,6 +36,44 @@ BTF_SET_START(bpf_lsm_hooks)
 #undef LSM_HOOK
 BTF_SET_END(bpf_lsm_hooks)
 
+/* List of LSM hooks that should operate on 'current' cgroup regardless
+ * of function signature.
+ */
+BTF_SET_START(bpf_lsm_current_hooks)
+/* operate on freshly allocated sk without any cgroup association */
+BTF_ID(func, bpf_lsm_sk_alloc_security)
+BTF_ID(func, bpf_lsm_sk_free_security)
+BTF_SET_END(bpf_lsm_current_hooks)
+
+void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
+			     bpf_func_t *bpf_func)
+{
+	const struct btf_param *args;
+
+	if (btf_type_vlen(prog->aux->attach_func_proto) < 1 ||
+	    btf_id_set_contains(&bpf_lsm_current_hooks,
+				prog->aux->attach_btf_id)) {
+		*bpf_func = __cgroup_bpf_run_lsm_current;
+		return;
+	}
+
+	args = btf_params(prog->aux->attach_func_proto);
+
+#ifdef CONFIG_NET
+	if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCKET])
+		*bpf_func = __cgroup_bpf_run_lsm_socket;
+	else if (args[0].type == btf_sock_ids[BTF_SOCK_TYPE_SOCK])
+		*bpf_func = __cgroup_bpf_run_lsm_sock;
+	else
+#endif
+		*bpf_func = __cgroup_bpf_run_lsm_current;
+}
+
+int bpf_lsm_hook_idx(u32 btf_id)
+{
+	return btf_id_set_index(&bpf_lsm_hooks, btf_id);
+}
+
 int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog,
 			const struct bpf_prog *prog)
 {
@@ -158,6 +197,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL;
 	case BPF_FUNC_get_attach_cookie:
 		return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL;
+	case BPF_FUNC_get_local_storage:
+		return prog->expected_attach_type == BPF_LSM_CGROUP ?
+			&bpf_get_local_storage_proto : NULL;
+	case BPF_FUNC_set_retval:
+		return prog->expected_attach_type == BPF_LSM_CGROUP ?
+			&bpf_set_retval_proto : NULL;
+	case BPF_FUNC_get_retval:
+		return prog->expected_attach_type == BPF_LSM_CGROUP ?
+			&bpf_get_retval_proto : NULL;
 	default:
 		return tracing_prog_func_proto(func_id, prog);
 	}

kernel/bpf/btf.c

@@ -5363,6 +5363,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 
 	if (arg == nr_args) {
 		switch (prog->expected_attach_type) {
+		case BPF_LSM_CGROUP:
 		case BPF_LSM_MAC:
 		case BPF_TRACE_FEXIT:
 			/* When LSM programs are attached to void LSM hooks
@@ -6842,6 +6843,16 @@ static int btf_id_cmp_func(const void *a, const void *b)
 	return *pa - *pb;
 }
 
+int btf_id_set_index(const struct btf_id_set *set, u32 id)
+{
+	const u32 *p;
+
+	p = bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func);
+	if (!p)
+		return -1;
+	return p - set->ids;
+}
+
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id)
 {
 	return bsearch(&id, set->ids, set->cnt, sizeof(u32), btf_id_cmp_func) != NULL;