bpf: muli prog support for cgroup-bpf

index d41d40ac3efd..102e56fbb6de 100644
@@ -14,27 +14,42 @@ struct bpf_sock_ops_kern;
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+struct bpf_prog_list {
+	struct list_head node;
+	struct bpf_prog *prog;
+};
+
+struct bpf_prog_array;
+
 struct cgroup_bpf {
-	/*
-	 * Store two sets of bpf_prog pointers, one for programs that are
-	 * pinned directly to this cgroup, and one for those that are effective
-	 * when this cgroup is accessed.
+	/* array of effective progs in this cgroup */
+	struct bpf_prog_array __rcu *effective[MAX_BPF_ATTACH_TYPE];
+
+	/* attached progs to this cgroup and attach flags
+	 * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will
+	 * have either zero or one element
+	 * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS
 	 */
-	struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
-	struct bpf_prog __rcu *effective[MAX_BPF_ATTACH_TYPE];
-	bool disallow_override[MAX_BPF_ATTACH_TYPE];
+	struct list_head progs[MAX_BPF_ATTACH_TYPE];
+	u32 flags[MAX_BPF_ATTACH_TYPE];
+
+	/* temp storage for effective prog array used by prog_attach/detach */
+	struct bpf_prog_array __rcu *inactive;
 };
 
 void cgroup_bpf_put(struct cgroup *cgrp);
-void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
+int cgroup_bpf_inherit(struct cgroup *cgrp);
 
-int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
-			struct bpf_prog *prog, enum bpf_attach_type type,
-			bool overridable);
+int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+			enum bpf_attach_type type, u32 flags);
 
-/* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, bool overridable);
+/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,

@@ -96,8 +111,7 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 
 struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
-static inline void cgroup_bpf_inherit(struct cgroup *cgrp,
-				      struct cgroup *parent) {}
+static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })

index 252f4bc9eb25..a6964b75f070 100644
@@ -241,6 +241,38 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr);
 
+/* an array of programs to be executed under rcu_lock.
+ *
+ * Typical usage:
+ * ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
+ *
+ * the structure returned by bpf_prog_array_alloc() should be populated
+ * with program pointers and the last pointer must be NULL.
+ * The user has to keep refcnt on the program and make sure the program
+ * is removed from the array before bpf_prog_put().
+ * The 'struct bpf_prog_array *' should only be replaced with xchg()
+ * since other cpus are walking the array of pointers in parallel.
+ */
+struct bpf_prog_array {
+	struct rcu_head rcu;
+	struct bpf_prog *progs[0];
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+
+#define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
+	({						\
+		struct bpf_prog **_prog;		\
+		u32 _ret = 1;				\
+		rcu_read_lock();			\
+		_prog = rcu_dereference(array)->progs;	\
+		for (; *_prog; _prog++)			\
+			_ret &= func(*_prog, ctx);	\
+		rcu_read_unlock();			\
+		_ret;					\
+	 })
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 

index 911d454af107..2d2db394b0ca 100644
@@ -481,7 +481,7 @@ struct sk_filter {
 	struct bpf_prog	*prog;
 };
 
-#define BPF_PROG_RUN(filter, ctx)  (*filter->bpf_func)(ctx, filter->insnsi)
+#define BPF_PROG_RUN(filter, ctx)  (*(filter)->bpf_func)(ctx, (filter)->insnsi)
 
 #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN
 

50 lines not on this page · raw message

538 lines not on this page · raw message

index 917cc04a0a94..6b49e1991ae7 100644
@@ -1381,6 +1381,37 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
 
+/* to avoid allocating empty bpf_prog_array for cgroups that
+ * don't have bpf program attached use one global 'empty_prog_array'
+ * It will not be modified the caller of bpf_prog_array_alloc()
+ * (since caller requested prog_cnt == 0)
+ * that pointer should be 'freed' by bpf_prog_array_free()
+ */
+static struct {
+	struct bpf_prog_array hdr;
+	struct bpf_prog *null_prog;
+} empty_prog_array = {
+	.null_prog = NULL,
+};
+
+struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+{
+	if (prog_cnt)
+		return kzalloc(sizeof(struct bpf_prog_array) +
+			       sizeof(struct bpf_prog *) * (prog_cnt + 1),
+			       flags);
+
+	return &empty_prog_array.hdr;
+}
+
+void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
+{
+	if (!progs ||
+	    progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr)
+		return;
+	kfree_rcu(progs, rcu);
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;

index b927da66f653..51bee695d32c 100644
@@ -1168,6 +1168,9 @@ static int sockmap_get_from_fd(const union bpf_attr *attr, bool attach)
 	return 0;
 }
 
+#define BPF_F_ATTACH_MASK \
+	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
+
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;

@@ -1181,7 +1184,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
 		return -EINVAL;
 
-	if (attr->attach_flags & ~BPF_F_ALLOW_OVERRIDE)
+	if (attr->attach_flags & ~BPF_F_ATTACH_MASK)
 		return -EINVAL;
 
 	switch (attr->attach_type) {

@@ -1212,8 +1215,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return PTR_ERR(cgrp);
 	}
 
-	ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
-				attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+				attr->attach_flags);
 	if (ret)
 		bpf_prog_put(prog);
 	cgroup_put(cgrp);

@@ -1225,6 +1228,8 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
+	enum bpf_prog_type ptype;
+	struct bpf_prog *prog;
 	struct cgroup *cgrp;
 	int ret;
 

@@ -1237,23 +1242,33 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
+		ptype = BPF_PROG_TYPE_CGROUP_SKB;
+		break;
 	case BPF_CGROUP_INET_SOCK_CREATE:
+		ptype = BPF_PROG_TYPE_CGROUP_SOCK;
+		break;
 	case BPF_CGROUP_SOCK_OPS:
-		cgrp = cgroup_get_from_fd(attr->target_fd);
-		if (IS_ERR(cgrp))
-			return PTR_ERR(cgrp);
-
-		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
-		cgroup_put(cgrp);
+		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		ret = sockmap_get_from_fd(attr, false);
-		break;
+		return sockmap_get_from_fd(attr, false);
 	default:
 		return -EINVAL;
 	}
 
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		prog = NULL;
+
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	if (prog)
+		bpf_prog_put(prog);
+	cgroup_put(cgrp);
 	return ret;
 }
 

index d6551cd45238..57eb866ae78d 100644
@@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags)
 	if (ret)
 		goto destroy_root;
 
+	ret = cgroup_bpf_inherit(root_cgrp);
+	WARN_ON_ONCE(ret);
+
 	trace_cgroup_setup_root(root);
 
 	/*

@@ -4713,6 +4716,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	cgrp->self.parent = &parent->self;
 	cgrp->root = root;
 	cgrp->level = level;
+	ret = cgroup_bpf_inherit(cgrp);
+	if (ret)
+		goto out_idr_free;
 
 	for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) {
 		cgrp->ancestor_ids[tcgrp->level] = tcgrp->id;

@@ -4747,13 +4753,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent)
 	if (!cgroup_on_dfl(cgrp))
 		cgrp->subtree_control = cgroup_control(cgrp);
 
-	if (parent)
-		cgroup_bpf_inherit(cgrp, parent);
-
 	cgroup_propagate_control(cgrp);
 
 	return cgrp;
 
+out_idr_free:
+	cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
 out_cancel_ref:
 	percpu_ref_exit(&cgrp->self.refcnt);
 out_free_cgrp:

@@ -5736,14 +5741,23 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd)
 #endif	/* CONFIG_SOCK_CGROUP_DATA */
 
 #ifdef CONFIG_CGROUP_BPF
-int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
-		      enum bpf_attach_type type, bool overridable)
+int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_attach(cgrp, prog, type, flags);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, u32 flags)
 {
-	struct cgroup *parent = cgroup_parent(cgrp);
 	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
+	ret = __cgroup_bpf_detach(cgrp, prog, type, flags);
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }

index 102e56fbb6de..359b6f5d3d90 100644
@@ -44,12 +44,16 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 			enum bpf_attach_type type, u32 flags);
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 			enum bpf_attach_type type, u32 flags);
+int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		       union bpf_attr __user *uattr);
 
 /* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */
 int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type, u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type, u32 flags);
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		     union bpf_attr __user *uattr);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,

index a6964b75f070..a67daea731ab 100644
@@ -260,6 +260,9 @@ struct bpf_prog_array {
 
 struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+				__u32 __user *prog_ids, u32 cnt);
 
 #define BPF_PROG_RUN_ARRAY(array, ctx, func)		\
 	({						\

index 762f74bc6c47..cb2b9f95160a 100644
@@ -92,6 +92,7 @@ enum bpf_cmd {
 	BPF_PROG_GET_FD_BY_ID,
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
+	BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {

@@ -211,6 +212,9 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 #define BPF_OBJ_NAME_LEN 16U
 
 union bpf_attr {

@@ -289,6 +293,15 @@ union bpf_attr {
 		__u32		info_len;
 		__aligned_u64	info;
 	} info;
+
+	struct { /* anonymous struct used by BPF_PROG_QUERY command */
+		__u32		target_fd;	/* container object to query */
+		__u32		attach_type;
+		__u32		query_flags;
+		__u32		attach_flags;
+		__aligned_u64	prog_ids;
+		__u32		prog_cnt;
+	} query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:

52 lines not on this page · raw message

index 6b49e1991ae7..eba966c09053 100644
@@ -1412,6 +1412,44 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
 	kfree_rcu(progs, rcu);
 }
 
+int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+{
+	struct bpf_prog **prog;
+	u32 cnt = 0;
+
+	rcu_read_lock();
+	prog = rcu_dereference(progs)->progs;
+	for (; *prog; prog++)
+		cnt++;
+	rcu_read_unlock();
+	return cnt;
+}
+
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+				__u32 __user *prog_ids, u32 cnt)
+{
+	struct bpf_prog **prog;
+	u32 i = 0, id;
+
+	rcu_read_lock();
+	prog = rcu_dereference(progs)->progs;
+	for (; *prog; prog++) {
+		id = (*prog)->aux->id;
+		if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
+			rcu_read_unlock();
+			return -EFAULT;
+		}
+		if (++i == cnt) {
+			prog++;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	if (*prog)
+		return -ENOSPC;
+	return 0;
+}
+
 static void bpf_prog_free_deferred(struct work_struct *work)
 {
 	struct bpf_prog_aux *aux;

index 51bee695d32c..0048cb24ba7b 100644
@@ -1272,6 +1272,37 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	return ret;
 }
 
+#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
+
+static int bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+	if (CHECK_ATTR(BPF_PROG_QUERY))
+		return -EINVAL;
+	if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE)
+		return -EINVAL;
+
+	switch (attr->query.attach_type) {
+	case BPF_CGROUP_INET_INGRESS:
+	case BPF_CGROUP_INET_EGRESS:
+	case BPF_CGROUP_INET_SOCK_CREATE:
+	case BPF_CGROUP_SOCK_OPS:
+		break;
+	default:
+		return -EINVAL;
+	}
+	cgrp = cgroup_get_from_fd(attr->query.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+	ret = cgroup_bpf_query(cgrp, attr, uattr);
+	cgroup_put(cgrp);
+	return ret;
+}
 #endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration

@@ -1568,6 +1599,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_PROG_DETACH:
 		err = bpf_prog_detach(&attr);
 		break;
+	case BPF_PROG_QUERY:
+		err = bpf_prog_query(&attr, uattr);
+		break;
 #endif
 	case BPF_PROG_TEST_RUN:
 		err = bpf_prog_test_run(&attr, uattr);

index 57eb866ae78d..269512b94a94 100644
@@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	mutex_unlock(&cgroup_mutex);
 	return ret;
 }
+int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
+		     union bpf_attr __user *uattr)
+{
+	int ret;
+
+	mutex_lock(&cgroup_mutex);
+	ret = __cgroup_bpf_query(cgrp, attr, uattr);
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
 #endif /* CONFIG_CGROUP_BPF */

index 4cf9b72c59a0..52b022310f6a 100644
@@ -3073,6 +3073,43 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static int check_return_code(struct bpf_verifier_env *env)
+{
+	struct bpf_reg_state *reg;
+	struct tnum range = tnum_range(0, 1);
+
+	switch (env->prog->type) {
+	case BPF_PROG_TYPE_CGROUP_SKB:
+	case BPF_PROG_TYPE_CGROUP_SOCK:
+	case BPF_PROG_TYPE_SOCK_OPS:
+		break;
+	default:
+		return 0;
+	}
+
+	reg = &env->cur_state.regs[BPF_REG_0];
+	if (reg->type != SCALAR_VALUE) {
+		verbose("At program exit the register R0 is not a known value (%s)\n",
+			reg_type_str[reg->type]);
+		return -EINVAL;
+	}
+
+	if (!tnum_in(range, reg->var_off)) {
+		verbose("At program exit the register R0 ");
+		if (!tnum_is_unknown(reg->var_off)) {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose("has value %s", tn_buf);
+		} else {
+			verbose("has unknown scalar value");
+		}
+		verbose(" should have been 0 or 1\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* non-recursive DFS pseudo code
  * 1  procedure DFS-iterative(G,v):
  * 2      label v as discovered

@@ -3863,6 +3900,9 @@ static int do_check(struct bpf_verifier_env *env)
 					return -EACCES;
 				}
 
+				err = check_return_code(env);
+				if (err)
+					return err;
 process_bpf_exit:
 				insn_idx = pop_stack(env, &prev_insn_idx);
 				if (insn_idx < 0) {

78 lines not on this page · raw message

index daf624e4c720..d4b6ba8292ee 100644
@@ -291,6 +291,18 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
+{
+	union bpf_attr attr;
+
+	bzero(&attr, sizeof(attr));
+	attr.target_fd	 = target_fd;
+	attr.attach_bpf_fd = prog_fd;
+	attr.attach_type = type;
+
+	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration)

index 118d00535a0d..afd64727c9cf 100644
@@ -66,6 +66,7 @@ int bpf_obj_get(const char *pathname);
 int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type,
 		    unsigned int flags);
 int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type);
+int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type);
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration);

index 9d1be9426401..88bdcf4b1670 100644
@@ -56,7 +56,7 @@ int setup_cgroup_environment(void)
 		return 1;
 	}
 
-	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL)) {
+	if (mount("none", CGROUP_MOUNT_PATH, "cgroup2", 0, NULL) && errno != EBUSY) {
 		log_err("mount cgroup2");
 		return 1;
 	}

@@ -163,7 +163,7 @@ int create_and_get_cgroup(char *path)
 
 	format_cgroup_path(cgroup_path, path);
 	if (mkdir(cgroup_path, 0777) && errno != EEXIST) {
-		log_err("mkdiring cgroup");
+		log_err("mkdiring cgroup %s .. %s", path, cgroup_path);
 		return 0;
 	}
 

206 lines not on this page · raw message

index 6d2137b4cf38..cb2b9f95160a 100644
@@ -92,6 +92,7 @@ enum bpf_cmd {
 	BPF_PROG_GET_FD_BY_ID,
 	BPF_MAP_GET_FD_BY_ID,
 	BPF_OBJ_GET_INFO_BY_FD,
+	BPF_PROG_QUERY,
 };
 
 enum bpf_map_type {

@@ -143,11 +144,47 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
-/* If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
- * to the given target_fd cgroup the descendent cgroup will be able to
- * override effective bpf program that was inherited from this cgroup
+/* cgroup-bpf attach flags used in BPF_PROG_ATTACH command
+ *
+ * NONE(default): No further bpf programs allowed in the subtree.
+ *
+ * BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program,
+ * the program in this cgroup yields to sub-cgroup program.
+ *
+ * BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program,
+ * that cgroup program gets run in addition to the program in this cgroup.
+ *
+ * Only one program is allowed to be attached to a cgroup with
+ * NONE or BPF_F_ALLOW_OVERRIDE flag.
+ * Attaching another program on top of NONE or BPF_F_ALLOW_OVERRIDE will
+ * release old program and attach the new one. Attach flags has to match.
+ *
+ * Multiple programs are allowed to be attached to a cgroup with
+ * BPF_F_ALLOW_MULTI flag. They are executed in FIFO order
+ * (those that were attached first, run first)
+ * The programs of sub-cgroup are executed first, then programs of
+ * this cgroup and then programs of parent cgroup.
+ * When children program makes decision (like picking TCP CA or sock bind)
+ * parent program has a chance to override it.
+ *
+ * A cgroup with MULTI or OVERRIDE flag allows any attach flags in sub-cgroups.
+ * A cgroup with NONE doesn't allow any programs in sub-cgroups.
+ * Ex1:
+ * cgrp1 (MULTI progs A, B) ->
+ *    cgrp2 (OVERRIDE prog C) ->
+ *      cgrp3 (MULTI prog D) ->
+ *        cgrp4 (OVERRIDE prog E) ->
+ *          cgrp5 (NONE prog F)
+ * the event in cgrp5 triggers execution of F,D,A,B in that order.
+ * if prog F is detached, the execution is E,D,A,B
+ * if prog F and D are detached, the execution is E,A,B
+ * if prog F, E and D are detached, the execution is C,A,B
+ *
+ * All eligible programs are executed regardless of return code from
+ * earlier programs.
  */
 #define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+#define BPF_F_ALLOW_MULTI	(1U << 1)
 
 /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the
  * verifier will perform strict alignment checking as if the kernel

@@ -175,6 +212,9 @@ enum bpf_attach_type {
 /* Specify numa node during map creation */
 #define BPF_F_NUMA_NODE		(1U << 2)
 
+/* flags for BPF_PROG_QUERY */
+#define BPF_F_QUERY_EFFECTIVE	(1U << 0)
+
 #define BPF_OBJ_NAME_LEN 16U
 
 union bpf_attr {

@@ -253,6 +293,15 @@ union bpf_attr {
 		__u32		info_len;
 		__aligned_u64	info;
 	} info;
+
+	struct { /* anonymous struct used by BPF_PROG_QUERY command */
+		__u32		target_fd;	/* container object to query */
+		__u32		attach_type;
+		__u32		query_flags;
+		__u32		attach_flags;
+		__aligned_u64	prog_ids;
+		__u32		prog_cnt;
+	} query;
 } __attribute__((aligned(8)));
 
 /* BPF helper function descriptions:

index d4b6ba8292ee..5128677e4117 100644
@@ -303,6 +303,26 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type)
 	return sys_bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
 }
 
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt)
+{
+	union bpf_attr attr;
+	int ret;
+
+	bzero(&attr, sizeof(attr));
+	attr.query.target_fd	= target_fd;
+	attr.query.attach_type	= type;
+	attr.query.query_flags	= query_flags;
+	attr.query.prog_cnt	= *prog_cnt;
+	attr.query.prog_ids	= ptr_to_u64(prog_ids);
+
+	ret = sys_bpf(BPF_PROG_QUERY, &attr, sizeof(attr));
+	if (attach_flags)
+		*attach_flags = attr.query.attach_flags;
+	*prog_cnt = attr.query.prog_cnt;
+	return ret;
+}
+
 int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size,
 		      void *data_out, __u32 *size_out, __u32 *retval,
 		      __u32 *duration)

index afd64727c9cf..6534889e2b2f 100644
@@ -75,5 +75,6 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id);
 int bpf_prog_get_fd_by_id(__u32 id);
 int bpf_map_get_fd_by_id(__u32 id);
 int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len);
-
+int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags,
+		   __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt);
 #endif

index 9a9f6836e5e9..3e8232cc04a8 100644
@@ -236,6 +236,7 @@ static int prog_load_cnt(int verdict, int val)
 
 static int test_multiprog(void)
 {
+	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
 	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
 	int drop_prog, allow_prog[6] = {}, rc = 0;
 	unsigned long long value;

@@ -304,6 +305,32 @@ static int test_multiprog(void)
 	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
 	assert(value == 1 + 2 + 8 + 32);
 
+	/* query the number of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      NULL, NULL, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	/* retrieve prog_ids of effective progs in cg5 */
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 4);
+	assert(attach_flags == 0);
+	saved_prog_id = prog_ids[0];
+	/* check enospc handling */
+	prog_ids[0] = 0;
+	prog_cnt = 2;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == -1 &&
+	       errno == ENOSPC);
+	assert(prog_cnt == 4);
+	/* check that prog_ids are returned even when buffer is too small */
+	assert(prog_ids[0] == saved_prog_id);
+	/* retrieve prog_id of single attached prog in cg5 */
+	prog_ids[0] = 0;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 1);
+	assert(prog_ids[0] == saved_prog_id);
+
 	/* detach bottom program and ping again */
 	if (bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS)) {
 		log_err("Detaching prog from cg5");

@@ -341,6 +368,15 @@ static int test_multiprog(void)
 	assert(system(PING_CMD) == 0);
 	assert(bpf_map_lookup_elem(map_fd, &key, &value) == 0);
 	assert(value == 1 + 2 + 4);
+
+	prog_cnt = 4;
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, BPF_F_QUERY_EFFECTIVE,
+			      &attach_flags, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 3);
+	assert(attach_flags == 0);
+	assert(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0,
+			      NULL, prog_ids, &prog_cnt) == 0);
+	assert(prog_cnt == 0);
 	goto out;
 err:
 	rc = 1;