[v3,bpf-next,2/4] bpf: implement bpf_prog replacement for an active bpf_cgroup_link

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index d2d969669564..c11b413d5b1a 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -100,6 +100,8 @@  int __cgroup_bpf_attach(struct cgroup *cgrp,
 int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 			struct bpf_cgroup_link *link,
 			enum bpf_attach_type type);
+int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link,
+			 struct bpf_prog *new_prog);
 int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		       union bpf_attr __user *uattr);
 
@@ -110,6 +112,8 @@  int cgroup_bpf_attach(struct cgroup *cgrp,
 		      u32 flags);
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type);
+int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog,
+		       struct bpf_prog *new_prog);
 int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 		     union bpf_attr __user *uattr);
 
@@ -350,6 +354,7 @@  int cgroup_bpf_prog_query(const union bpf_attr *attr,
 #else
 
 struct bpf_prog;
+struct bpf_link;
 struct cgroup_bpf {};
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}
@@ -373,6 +378,13 @@  static inline int cgroup_bpf_link_attach(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline int cgroup_bpf_replace(struct bpf_link *link,
+				     struct bpf_prog *old_prog,
+				     struct bpf_prog *new_prog)
+{
+	return -EINVAL;
+}
+
 static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 					union bpf_attr __user *uattr)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8b3f1c098ac0..6241cbcd2a64 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@  enum bpf_cmd {
 	BPF_MAP_UPDATE_BATCH,
 	BPF_MAP_DELETE_BATCH,
 	BPF_LINK_CREATE,
+	BPF_LINK_UPDATE,
 };
 
 enum bpf_map_type {
@@ -577,6 +578,17 @@  union bpf_attr {
 		__u32		attach_type;	/* attach type */
 		__u32		flags;		/* extra flags */
 	} link_create;
+
+	struct { /* struct used by BPF_LINK_UPDATE command */
+		__u32		link_fd;	/* link fd */
+		/* new program fd to update link with */
+		__u32		new_prog_fd;
+		__u32		flags;		/* extra flags */
+		/* expected link's program fd; is specified only if
+		 * BPF_F_REPLACE flag is set in flags */
+		__u32		old_prog_fd;
+	} link_update;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index c24029937431..80676fc00d81 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -500,6 +500,86 @@  int __cgroup_bpf_attach(struct cgroup *cgrp,
 	return err;
 }
 
+/* Swap updated BPF program for given link in effective program arrays across
+ * all descendant cgroups. This function is guaranteed to succeed.
+ */
+static void replace_effective_prog(struct cgroup *cgrp,
+				   enum bpf_attach_type type,
+				   struct bpf_cgroup_link *link)
+{
+	struct bpf_prog_array_item *item;
+	struct cgroup_subsys_state *css;
+	struct bpf_prog_array *progs;
+	struct bpf_prog_list *pl;
+	struct list_head *head;
+	struct cgroup *cg;
+	int pos;
+
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		if (percpu_ref_is_zero(&desc->bpf.refcnt))
+			continue;
+
+		/* find position of link in effective progs array */
+		for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) {
+			if (pos && !(cg->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+				continue;
+
+			head = &cg->bpf.progs[type];
+			list_for_each_entry(pl, head, node) {
+				if (!prog_list_prog(pl))
+					continue;
+				if (pl->link == link)
+					goto found;
+				pos++;
+			}
+		}
+found:
+		BUG_ON(!cg);
+		progs = rcu_dereference_protected(
+				desc->bpf.effective[type],
+				lockdep_is_held(&cgroup_mutex));
+		item = &progs->items[pos];
+		WRITE_ONCE(item->prog, link->link.prog);
+	}
+}
+
+/**
+ * __cgroup_bpf_replace() - Replace link's program and propagate the change
+ *                          to descendants
+ * @cgrp: The cgroup which descendants to traverse
+ * @link: A link for which to replace BPF program
+ * @type: Type of attach operation
+ *
+ * Must be called with cgroup_mutex held.
+ */
+int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link,
+			 struct bpf_prog *new_prog)
+{
+	struct list_head *progs = &cgrp->bpf.progs[link->type];
+	struct bpf_prog *old_prog;
+	struct bpf_prog_list *pl;
+	bool found = false;
+
+	if (link->link.prog->type != new_prog->type)
+		return -EINVAL;
+
+	list_for_each_entry(pl, progs, node) {
+		if (pl->link == link) {
+			found = true;
+			break;
+		}
+	}
+	if (!found)
+		return -ENOENT;
+
+	old_prog = xchg(&link->link.prog, new_prog);
+	replace_effective_prog(cgrp, link->type, link);
+	bpf_prog_put(old_prog);
+	return 0;
+}
+
 static struct bpf_prog_list *find_detach_entry(struct list_head *progs,
 					       struct bpf_prog *prog,
 					       struct bpf_cgroup_link *link,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 05412b83ed6c..43f7201b68c2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3593,6 +3593,55 @@  static int link_create(union bpf_attr *attr)
 	return ret;
 }
 
+#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd
+
+static int link_update(union bpf_attr *attr)
+{
+	struct bpf_prog *old_prog = NULL, *new_prog;
+	struct bpf_link *link;
+	u32 flags;
+	int ret;
+
+	if (CHECK_ATTR(BPF_LINK_UPDATE))
+		return -EINVAL;
+
+	flags = attr->link_update.flags;
+	if (flags & ~BPF_F_REPLACE)
+		return -EINVAL;
+
+	link = bpf_link_get_from_fd(attr->link_update.link_fd);
+	if (IS_ERR(link))
+		return PTR_ERR(link);
+
+	new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
+	if (IS_ERR(new_prog))
+		return PTR_ERR(new_prog);
+
+	if (flags & BPF_F_REPLACE) {
+		old_prog = bpf_prog_get(attr->link_update.old_prog_fd);
+		if (IS_ERR(old_prog)) {
+			ret = PTR_ERR(old_prog);
+			old_prog = NULL;
+			goto out_put_progs;
+		}
+	}
+
+#ifdef CONFIG_CGROUP_BPF
+	if (link->ops == &bpf_cgroup_link_lops) {
+		ret = cgroup_bpf_replace(link, old_prog, new_prog);
+		goto out_put_progs;
+	}
+#endif
+	ret = -EINVAL;
+
+out_put_progs:
+	if (old_prog)
+		bpf_prog_put(old_prog);
+	if (ret)
+		bpf_prog_put(new_prog);
+	return ret;
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -3706,6 +3755,9 @@  SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_LINK_CREATE:
 		err = link_create(&attr);
 		break;
+	case BPF_LINK_UPDATE:
+		err = link_update(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 219624fba9ba..915dda3f7f19 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6317,6 +6317,33 @@  int cgroup_bpf_attach(struct cgroup *cgrp,
 	return ret;
 }
 
+int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *old_prog,
+		       struct bpf_prog *new_prog)
+{
+	struct bpf_cgroup_link *cg_link;
+	int ret;
+
+	if (link->ops != &bpf_cgroup_link_lops)
+		return -EINVAL;
+
+	cg_link = container_of(link, struct bpf_cgroup_link, link);
+
+	mutex_lock(&cgroup_mutex);
+	/* link might have been auto-released by dying cgroup, so fail */
+	if (!cg_link->cgroup) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+	if (old_prog && link->prog != old_prog) {
+		ret = -EPERM;
+		goto out_unlock;
+	}
+	ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog);
+out_unlock:
+	mutex_unlock(&cgroup_mutex);
+	return ret;
+}
+
 int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		      enum bpf_attach_type type)
 {