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 <[e-mail]>
Signed-off-by: Stanislav Fomichev <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Alexei Starovoitov <[e-mail]>

arch/x86/net/bpf_jit_comp.c

···
 			   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);
···
 	 */
 	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);
 
···
 	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

···
 
 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,
···
 	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

···
 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

···
 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);
 
···
 	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
···
 	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;
···
 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)
 {
···
 						     void *value)
 {
 	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
 
···
 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);
···
 
 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

···
 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)
···
 
 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 */

include/linux/btf_ids.h

···
 	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

···
 	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

···
 #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.
···
 #include <linux/lsm_hook_defs.h>
 #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)
···
 		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

···
 
 	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
···
 	const int *pa = a, *pb = 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)

kernel/bpf/cgroup.c

···
 #include <linux/string.h>
 #include <linux/bpf.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/bpf_lsm.h>
+#include <linux/bpf_verifier.h>
 #include <net/sock.h>
 #include <net/bpf_sk_storage.h>
 
···
 	migrate_enable();
 	return run_ctx.retval;
 }
+
+unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx,
+				       const struct bpf_insn *insn)
+{
+	const struct bpf_prog *shim_prog;
+	struct sock *sk;
+	struct cgroup *cgrp;
+	int ret = 0;
+	u64 *args;
+
+	args = (u64 *)ctx;
+	sk = (void *)(unsigned long)args[0];
+	/*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/
+	shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi));
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	if (likely(cgrp))
+		ret = bpf_prog_run_array_cg(&cgrp->bpf,
+					    shim_prog->aux->cgroup_atype,
+					    ctx, bpf_prog_run, 0, NULL);
+	return ret;
+}
+
+unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx,
+					 const struct bpf_insn *insn)
+{
+	const struct bpf_prog *shim_prog;
+	struct socket *sock;
+	struct cgroup *cgrp;
+	int ret = 0;
+	u64 *args;
+
+	args = (u64 *)ctx;
+	sock = (void *)(unsigned long)args[0];
+	/*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/
+	shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi));
+
+	cgrp = sock_cgroup_ptr(&sock->sk->sk_cgrp_data);
+	if (likely(cgrp))
+		ret = bpf_prog_run_array_cg(&cgrp->bpf,
+					    shim_prog->aux->cgroup_atype,
+					    ctx, bpf_prog_run, 0, NULL);
+	return ret;
+}
+
+unsigned int __cgroup_bpf_run_lsm_current(const void *ctx,
+					  const struct bpf_insn *insn)
+{
+	const struct bpf_prog *shim_prog;
+	struct cgroup *cgrp;
+	int ret = 0;
+
+	/*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/
+	shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi));
+
+	/* We rely on trampoline's __bpf_prog_enter_lsm_cgroup to grab RCU read lock. */
+	cgrp = task_dfl_cgroup(current);
+	if (likely(cgrp))
+		ret = bpf_prog_run_array_cg(&cgrp->bpf,
+					    shim_prog->aux->cgroup_atype,
+					    ctx, bpf_prog_run, 0, NULL);
+	return ret;
+}
+
+#ifdef CONFIG_BPF_LSM
+static enum cgroup_bpf_attach_type
+bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id)
+{
+	if (attach_type != BPF_LSM_CGROUP)
+		return to_cgroup_bpf_attach_type(attach_type);
+	return CGROUP_LSM_START + bpf_lsm_hook_idx(attach_btf_id);
+}
+#else
+static enum cgroup_bpf_attach_type
+bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id)
+{
+	if (attach_type != BPF_LSM_CGROUP)
+		return to_cgroup_bpf_attach_type(attach_type);
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_BPF_LSM */
 
 void cgroup_bpf_offline(struct cgroup *cgrp)
 {
···
 
 		hlist_for_each_entry_safe(pl, pltmp, progs, node) {
 			hlist_del(&pl->node);
-			if (pl->prog)
+			if (pl->prog) {
+				if (pl->prog->expected_attach_type == BPF_LSM_CGROUP)
+					bpf_trampoline_unlink_cgroup_shim(pl->prog);
 				bpf_prog_put(pl->prog);
-			if (pl->link)
+			}
+			if (pl->link) {
+				if (pl->link->link.prog->expected_attach_type == BPF_LSM_CGROUP)
+					bpf_trampoline_unlink_cgroup_shim(pl->link->link.prog);
 				bpf_cgroup_link_auto_detach(pl->link);
+			}
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key[atype]);
 		}
···
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
 	struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {};
+	struct bpf_prog *new_prog = prog ? : link->link.prog;
 	enum cgroup_bpf_attach_type atype;
 	struct bpf_prog_list *pl;
 	struct hlist_head *progs;
···
 		/* replace_prog implies BPF_F_REPLACE, and vice versa */
 		return -EINVAL;
 
-	atype = to_cgroup_bpf_attach_type(type);
+	atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id);
 	if (atype < 0)
 		return -EINVAL;
 
···
 	bpf_cgroup_storages_assign(pl->storage, storage);
 	cgrp->bpf.flags[atype] = saved_flags;
 
+	if (type == BPF_LSM_CGROUP) {
+		err = bpf_trampoline_link_cgroup_shim(new_prog, atype);
+		if (err)
+			goto cleanup;
+	}
+
 	err = update_effective_progs(cgrp, atype);
 	if (err)
-		goto cleanup;
+		goto cleanup_trampoline;
 
-	if (old_prog)
+	if (old_prog) {
+		if (type == BPF_LSM_CGROUP)
+			bpf_trampoline_unlink_cgroup_shim(old_prog);
 		bpf_prog_put(old_prog);
-	else
+	} else {
 		static_branch_inc(&cgroup_bpf_enabled_key[atype]);
+	}
 	bpf_cgroup_storages_link(new_storage, cgrp, type);
 	return 0;
+
+cleanup_trampoline:
+	if (type == BPF_LSM_CGROUP)
+		bpf_trampoline_unlink_cgroup_shim(new_prog);
 
 cleanup:
 	if (old_prog) {
···
 	struct hlist_head *progs;
 	bool found = false;
 
-	atype = to_cgroup_bpf_attach_type(link->type);
+	atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id);
 	if (atype < 0)
 		return -EINVAL;
 
···
 	struct bpf_prog *old_prog;
 	struct bpf_prog_list *pl;
 	struct hlist_head *progs;
+	u32 attach_btf_id = 0;
 	u32 flags;
 
-	atype = to_cgroup_bpf_attach_type(type);
+	if (prog)
+		attach_btf_id = prog->aux->attach_btf_id;
+	if (link)
+		attach_btf_id = link->link.prog->aux->attach_btf_id;
+
+	atype = bpf_cgroup_atype_find(type, attach_btf_id);
 	if (atype < 0)
 		return -EINVAL;
 
···
 	if (hlist_empty(progs))
 		/* last program was detached, reset flags to zero */
 		cgrp->bpf.flags[atype] = 0;
-	if (old_prog)
+	if (old_prog) {
+		if (type == BPF_LSM_CGROUP)
+			bpf_trampoline_unlink_cgroup_shim(old_prog);
 		bpf_prog_put(old_prog);
+	}
 	static_branch_dec(&cgroup_bpf_enabled_key[atype]);
 	return 0;
 }
···
 
 	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
 				    cg_link->type));
+	if (cg_link->type == BPF_LSM_CGROUP)
+		bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog);
 
 	cg = cg_link->cgroup;
 	cg_link->cgroup = NULL;
···
 	return ctx->retval;
 }
 
-static const struct bpf_func_proto bpf_get_retval_proto = {
+const struct bpf_func_proto bpf_get_retval_proto = {
 	.func		= bpf_get_retval,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
···
 	return 0;
 }
 
-static const struct bpf_func_proto bpf_set_retval_proto = {
+const struct bpf_func_proto bpf_set_retval_proto = {
 	.func		= bpf_set_retval,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,

kernel/bpf/core.c

···
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
 const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
 const struct bpf_func_proto bpf_seq_printf_btf_proto __weak;
+const struct bpf_func_proto bpf_set_retval_proto __weak;
+const struct bpf_func_proto bpf_get_retval_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {

kernel/bpf/syscall.c

···
 		return BPF_PROG_TYPE_SK_LOOKUP;
 	case BPF_XDP:
 		return BPF_PROG_TYPE_XDP;
+	case BPF_LSM_CGROUP:
+		return BPF_PROG_TYPE_LSM;
 	default:
 		return BPF_PROG_TYPE_UNSPEC;
 	}
···
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_LSM:
+		if (ptype == BPF_PROG_TYPE_LSM &&
+		    prog->expected_attach_type != BPF_LSM_CGROUP)
+			return -EINVAL;
+
 		ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 		break;
 	default:
···
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
 	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_LSM:
 		return cgroup_bpf_prog_detach(attr, ptype);
 	default:
 		return -EINVAL;
···
 			ret = bpf_raw_tp_link_attach(prog, NULL);
 		else if (prog->expected_attach_type == BPF_TRACE_ITER)
 			ret = bpf_iter_link_attach(attr, uattr, prog);
+		else if (prog->expected_attach_type == BPF_LSM_CGROUP)
+			ret = cgroup_bpf_link_attach(attr, prog);
 		else
 			ret = bpf_tracing_prog_attach(prog,
 						      attr->link_create.target_fd,

kernel/bpf/trampoline.c

···
 #include <linux/rcupdate_wait.h>
 #include <linux/module.h>
 #include <linux/static_call.h>
+#include <linux/bpf_verifier.h>
+#include <linux/bpf_lsm.h>
 
 /* dummy _ops. The verifier will operate on target program's ops. */
 const struct bpf_verifier_ops bpf_extension_verifier_ops = {
···
 	return err;
 }
 
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+static void bpf_shim_tramp_link_release(struct bpf_link *link)
+{
+	struct bpf_shim_tramp_link *shim_link =
+		container_of(link, struct bpf_shim_tramp_link, link.link);
+
+	/* paired with 'shim_link->trampoline = tr' in bpf_trampoline_link_cgroup_shim */
+	if (!shim_link->trampoline)
+		return;
+
+	WARN_ON_ONCE(bpf_trampoline_unlink_prog(&shim_link->link, shim_link->trampoline));
+	bpf_trampoline_put(shim_link->trampoline);
+}
+
+static void bpf_shim_tramp_link_dealloc(struct bpf_link *link)
+{
+	struct bpf_shim_tramp_link *shim_link =
+		container_of(link, struct bpf_shim_tramp_link, link.link);
+
+	kfree(shim_link);
+}
+
+static const struct bpf_link_ops bpf_shim_tramp_link_lops = {
+	.release = bpf_shim_tramp_link_release,
+	.dealloc = bpf_shim_tramp_link_dealloc,
+};
+
+static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog,
+						     bpf_func_t bpf_func,
+						     int cgroup_atype)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_prog *p;
+
+	shim_link = kzalloc(sizeof(*shim_link), GFP_USER);
+	if (!shim_link)
+		return NULL;
+
+	p = bpf_prog_alloc(1, 0);
+	if (!p) {
+		kfree(shim_link);
+		return NULL;
+	}
+
+	p->jited = false;
+	p->bpf_func = bpf_func;
+
+	p->aux->cgroup_atype = cgroup_atype;
+	p->aux->attach_func_proto = prog->aux->attach_func_proto;
+	p->aux->attach_btf_id = prog->aux->attach_btf_id;
+	p->aux->attach_btf = prog->aux->attach_btf;
+	btf_get(p->aux->attach_btf);
+	p->type = BPF_PROG_TYPE_LSM;
+	p->expected_attach_type = BPF_LSM_MAC;
+	bpf_prog_inc(p);
+	bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
+		      &bpf_shim_tramp_link_lops, p);
+
+	return shim_link;
+}
+
+static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
+						    bpf_func_t bpf_func)
+{
+	struct bpf_tramp_link *link;
+	int kind;
+
+	for (kind = 0; kind < BPF_TRAMP_MAX; kind++) {
+		hlist_for_each_entry(link, &tr->progs_hlist[kind], tramp_hlist) {
+			struct bpf_prog *p = link->link.prog;
+
+			if (p->bpf_func == bpf_func)
+				return container_of(link, struct bpf_shim_tramp_link, link);
+		}
+	}
+
+	return NULL;
+}
+
+int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
+				    int cgroup_atype)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_attach_target_info tgt_info = {};
+	struct bpf_trampoline *tr;
+	bpf_func_t bpf_func;
+	u64 key;
+	int err;
+
+	err = bpf_check_attach_target(NULL, prog, NULL,
+				      prog->aux->attach_btf_id,
+				      &tgt_info);
+	if (err)
+		return err;
+
+	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
+					 prog->aux->attach_btf_id);
+
+	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
+	tr = bpf_trampoline_get(key, &tgt_info);
+	if (!tr)
+		return  -ENOMEM;
+
+	mutex_lock(&tr->mutex);
+
+	shim_link = cgroup_shim_find(tr, bpf_func);
+	if (shim_link) {
+		/* Reusing existing shim attached by the other program. */
+		bpf_link_inc(&shim_link->link.link);
+
+		mutex_unlock(&tr->mutex);
+		bpf_trampoline_put(tr); /* bpf_trampoline_get above */
+		return 0;
+	}
+
+	/* Allocate and install new shim. */
+
+	shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype);
+	if (!shim_link) {
+		err = -ENOMEM;
+		goto err;
+	}
+
+	err = __bpf_trampoline_link_prog(&shim_link->link, tr);
+	if (err)
+		goto err;
+
+	shim_link->trampoline = tr;
+	/* note, we're still holding tr refcnt from above */
+
+	mutex_unlock(&tr->mutex);
+
+	return 0;
+err:
+	mutex_unlock(&tr->mutex);
+
+	if (shim_link)
+		bpf_link_put(&shim_link->link.link);
+
+	/* have to release tr while _not_ holding its mutex */
+	bpf_trampoline_put(tr); /* bpf_trampoline_get above */
+
+	return err;
+}
+
+void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog)
+{
+	struct bpf_shim_tramp_link *shim_link = NULL;
+	struct bpf_trampoline *tr;
+	bpf_func_t bpf_func;
+	u64 key;
+
+	key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf,
+					 prog->aux->attach_btf_id);
+
+	bpf_lsm_find_cgroup_shim(prog, &bpf_func);
+	tr = bpf_trampoline_lookup(key);
+	if (WARN_ON_ONCE(!tr))
+		return;
+
+	mutex_lock(&tr->mutex);
+	shim_link = cgroup_shim_find(tr, bpf_func);
+	mutex_unlock(&tr->mutex);
+
+	if (shim_link)
+		bpf_link_put(&shim_link->link.link);
+
+	bpf_trampoline_put(tr); /* bpf_trampoline_lookup above */
+}
+#endif
+
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info)
 {
···
 
 	update_prog_stats(prog, start);
 	__this_cpu_dec(*(prog->active));
+	migrate_enable();
+	rcu_read_unlock();
+}
+
+u64 notrace __bpf_prog_enter_lsm_cgroup(struct bpf_prog *prog,
+					struct bpf_tramp_run_ctx *run_ctx)
+	__acquires(RCU)
+{
+	/* Runtime stats are exported via actual BPF_LSM_CGROUP
+	 * programs, not the shims.
+	 */
+	rcu_read_lock();
+	migrate_disable();
+
+	run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
+	return NO_START_TIME;
+}
+
+void notrace __bpf_prog_exit_lsm_cgroup(struct bpf_prog *prog, u64 start,
+					struct bpf_tramp_run_ctx *run_ctx)
+	__releases(RCU)
+{
+	bpf_reset_run_ctx(run_ctx->saved_run_ctx);
+
 	migrate_enable();
 	rcu_read_unlock();
 }

kernel/bpf/verifier.c

···
 				reg_type_str(env, regs[BPF_REG_1].type));
 			return -EACCES;
 		}
+		break;
+	case BPF_FUNC_set_retval:
+		if (env->prog->expected_attach_type == BPF_LSM_CGROUP) {
+			if (!env->prog->aux->attach_func_proto->type) {
+				/* Make sure programs that attach to void
+				 * hooks don't try to modify return value.
+				 */
+				verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
+				return -EINVAL;
+			}
+		}
+		break;
 	}
 
 	if (err)
···
 	case BPF_PROG_TYPE_SK_LOOKUP:
 		range = tnum_range(SK_DROP, SK_PASS);
 		break;
+
+	case BPF_PROG_TYPE_LSM:
+		if (env->prog->expected_attach_type != BPF_LSM_CGROUP) {
+			/* Regular BPF_PROG_TYPE_LSM programs can return
+			 * any value.
+			 */
+			return 0;
+		}
+		if (!env->prog->aux->attach_func_proto->type) {
+			/* Make sure programs that attach to void
+			 * hooks don't try to modify return value.
+			 */
+			range = tnum_range(1, 1);
+		}
+		break;
+
 	case BPF_PROG_TYPE_EXT:
 		/* freplace program can return anything as its return value
 		 * depends on the to-be-replaced kernel func or bpf program.
···
 
 	if (!tnum_in(range, reg->var_off)) {
 		verbose_invalid_scalar(env, reg, &range, "program exit", "R0");
+		if (prog->expected_attach_type == BPF_LSM_CGROUP &&
+		    !prog->aux->attach_func_proto->type)
+			verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
 		return -EINVAL;
 	}
 
···
 		fallthrough;
 	case BPF_MODIFY_RETURN:
 	case BPF_LSM_MAC:
+	case BPF_LSM_CGROUP:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 		if (!btf_type_is_func(t)) {

tools/include/uapi/linux/bpf.h

···
 	BPF_SK_REUSEPORT_SELECT_OR_MIGRATE,
 	BPF_PERF_EVENT,
 	BPF_TRACE_KPROBE_MULTI,
+	BPF_LSM_CGROUP,
 	__MAX_BPF_ATTACH_TYPE
 };