BACKPORT: bpf: introduce BPF_F_ALLOW_OVERRIDE flag

If BPF_F_ALLOW_OVERRIDE flag is used in BPF_PROG_ATTACH command
to the given cgroup the descendent cgroup will be able to override
effective bpf program that was inherited from this cgroup.
By default it's not passed, therefore override is disallowed.

Examples:
1.
prog X attached to /A with default
prog Y fails to attach to /A/B and /A/B/C
Everything under /A runs prog X

2.
prog X attached to /A with allow_override.
prog Y fails to attach to /A/B with default (non-override)
prog M attached to /A/B with allow_override.
Everything under /A/B runs prog M only.

3.
prog X attached to /A with allow_override.
prog Y fails to attach to /A with default.
The user has to detach first to switch the mode.

In the future this behavior may be extended with a chain of
non-overridable programs.

Also fix the bug where detach from cgroup where nothing is attached
was not throwing error. Return ENOENT in such case.

Add several testcases and adjust libbpf.

Fixes: 3007098494be ("cgroup: add support for eBPF programs")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

Fixes: Change-Id: I3df35d8d3b1261503f9b5bcd90b18c9358f1ac28
       ("cgroup: add support for eBPF programs")
[AmitP: Refactored original patch for android-4.9 where libbpf sources
        are in samples/bpf/ and test_cgrp2_attach2, test_cgrp2_sock,
        and test_cgrp2_sock2 sample tests do not exist.]
(cherry picked from commit 7f677633379b4abb3281cdbe7e7006f049305c03)
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>

8 files changed, 84 insertions, 31 deletions

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 0cf1adf..ace92fc 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -21,20 +21,19 @@ struct cgroup_bpf {
 	 */
 	struct bpf_prog *prog[MAX_BPF_ATTACH_TYPE];
 	struct bpf_prog *effective[MAX_BPF_ATTACH_TYPE];
+	bool disallow_override[MAX_BPF_ATTACH_TYPE];
 };
 
 void cgroup_bpf_put(struct cgroup *cgrp);
 void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent);
 
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type);
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool overridable);
 
 /* Wrapper for __cgroup_bpf_update() protected by cgroup_mutex */
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type);
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable);
 
 int __cgroup_bpf_run_filter(struct sock *sk,
 			    struct sk_buff *skb,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 14eaf2d..b2d5be9 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -109,6 +109,12 @@ 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
+ */
+#define BPF_F_ALLOW_OVERRIDE	(1U << 0)
+
 #define BPF_PSEUDO_MAP_FD	1
 
 /* flags for BPF_MAP_UPDATE_ELEM command */
@@ -157,6 +163,7 @@ union bpf_attr {
 		__u32		target_fd;	/* container object to attach to */
 		__u32		attach_bpf_fd;	/* eBPF program to attach */
 		__u32		attach_type;
+		__u32		attach_flags;
 	};
 } __attribute__((aligned(8)));
 
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index d05c292..a38d7cd 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -52,6 +52,7 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
 		e = rcu_dereference_protected(parent->bpf.effective[type],
 					      lockdep_is_held(&cgroup_mutex));
 		rcu_assign_pointer(cgrp->bpf.effective[type], e);
+		cgrp->bpf.disallow_override[type] = parent->bpf.disallow_override[type];
 	}
 }
 
@@ -82,30 +83,63 @@ void cgroup_bpf_inherit(struct cgroup *cgrp, struct cgroup *parent)
  *
  * Must be called with cgroup_mutex held.
  */
-void __cgroup_bpf_update(struct cgroup *cgrp,
-			 struct cgroup *parent,
-			 struct bpf_prog *prog,
-			 enum bpf_attach_type type)
+int __cgroup_bpf_update(struct cgroup *cgrp, struct cgroup *parent,
+			struct bpf_prog *prog, enum bpf_attach_type type,
+			bool new_overridable)
 {
-	struct bpf_prog *old_prog, *effective;
+	struct bpf_prog *old_prog, *effective = NULL;
 	struct cgroup_subsys_state *pos;
+	bool overridable = true;
 
-	old_prog = xchg(cgrp->bpf.prog + type, prog);
+	if (parent) {
+		overridable = !parent->bpf.disallow_override[type];
+		effective = rcu_dereference_protected(parent->bpf.effective[type],
+						      lockdep_is_held(&cgroup_mutex));
+	}
+
+	if (prog && effective && !overridable)
+		/* if parent has non-overridable prog attached, disallow
+		 * attaching new programs to descendent cgroup
+		 */
+		return -EPERM;
+
+	if (prog && effective && overridable != new_overridable)
+		/* if parent has overridable prog attached, only
+		 * allow overridable programs in descendent cgroup
+		 */
+		return -EPERM;
 
-	effective = (!prog && parent) ?
-		rcu_dereference_protected(parent->bpf.effective[type],
-					  lockdep_is_held(&cgroup_mutex)) :
-		prog;
+	old_prog = cgrp->bpf.prog[type];
+
+	if (prog) {
+		overridable = new_overridable;
+		effective = prog;
+		if (old_prog &&
+		    cgrp->bpf.disallow_override[type] == new_overridable)
+			/* disallow attaching non-overridable on top
+			 * of existing overridable in this cgroup
+			 * and vice versa
+			 */
+			return -EPERM;
+	}
+
+	if (!prog && !old_prog)
+		/* report error when trying to detach and nothing is attached */
+		return -ENOENT;
+
+	cgrp->bpf.prog[type] = prog;
 
 	css_for_each_descendant_pre(pos, &cgrp->self) {
 		struct cgroup *desc = container_of(pos, struct cgroup, self);
 
 		/* skip the subtree if the descendant has its own program */
-		if (desc->bpf.prog[type] && desc != cgrp)
+		if (desc->bpf.prog[type] && desc != cgrp) {
 			pos = css_rightmost_descendant(pos);
-		else
+		} else {
 			rcu_assign_pointer(desc->bpf.effective[type],
 					   effective);
+			desc->bpf.disallow_override[type] = !overridable;
+		}
 	}
 
 	if (prog)
@@ -115,6 +149,7 @@ void __cgroup_bpf_update(struct cgroup *cgrp,
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
+	return 0;
 }
 
 /**
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e13157f..9ab0479 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -826,12 +826,13 @@ static int bpf_obj_get(const union bpf_attr *attr)
 
 #ifdef CONFIG_CGROUP_BPF
 
-#define BPF_PROG_ATTACH_LAST_FIELD attach_type
+#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
 static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	struct bpf_prog *prog;
 	struct cgroup *cgrp;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -839,6 +840,9 @@ 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)
+		return -EINVAL;
+
 	switch (attr->attach_type) {
 	case BPF_CGROUP_INET_INGRESS:
 	case BPF_CGROUP_INET_EGRESS:
@@ -853,7 +857,10 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 			return PTR_ERR(cgrp);
 		}
 
-		cgroup_bpf_update(cgrp, prog, attr->attach_type);
+		ret = cgroup_bpf_update(cgrp, prog, attr->attach_type,
+					attr->attach_flags & BPF_F_ALLOW_OVERRIDE);
+		if (ret)
+			bpf_prog_put(prog);
 		cgroup_put(cgrp);
 		break;
 
@@ -861,7 +868,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 
 #define BPF_PROG_DETACH_LAST_FIELD attach_type
@@ -869,6 +876,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	struct cgroup *cgrp;
+	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -883,7 +891,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		if (IS_ERR(cgrp))
 			return PTR_ERR(cgrp);
 
-		cgroup_bpf_update(cgrp, NULL, attr->attach_type);
+		ret = cgroup_bpf_update(cgrp, NULL, attr->attach_type, false);
 		cgroup_put(cgrp);
 		break;
 
@@ -891,7 +899,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	return 0;
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 70e1f48..5671c80 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -6500,15 +6500,16 @@ static __init int cgroup_namespaces_init(void)
 subsys_initcall(cgroup_namespaces_init);
 
 #ifdef CONFIG_CGROUP_BPF
-void cgroup_bpf_update(struct cgroup *cgrp,
-		       struct bpf_prog *prog,
-		       enum bpf_attach_type type)
+int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog,
+		      enum bpf_attach_type type, bool overridable)
 {
 	struct cgroup *parent = cgroup_parent(cgrp);
+	int ret;
 
 	mutex_lock(&cgroup_mutex);
-	__cgroup_bpf_update(cgrp, parent, prog, type);
+	ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable);
 	mutex_unlock(&cgroup_mutex);
+	return ret;
 }
 #endif /* CONFIG_CGROUP_BPF */
 
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
index 9ce707b..9cbc786 100644
--- a/samples/bpf/libbpf.c
+++ b/samples/bpf/libbpf.c
@@ -104,12 +104,14 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 	return syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
 }
 
-int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
+int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type,
+		    unsigned int flags)
 {
 	union bpf_attr attr = {
 		.target_fd = target_fd,
 		.attach_bpf_fd = prog_fd,
 		.attach_type = type,
+		.attach_flags  = flags;
 	};
 
 	return syscall(__NR_bpf, BPF_PROG_ATTACH, &attr, sizeof(attr));
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
index d0a799a..b06cf5a 100644
--- a/samples/bpf/libbpf.h
+++ b/samples/bpf/libbpf.h
@@ -15,7 +15,8 @@ int bpf_prog_load(enum bpf_prog_type prog_type,
 		  const struct bpf_insn *insns, int insn_len,
 		  const char *license, int kern_version);
 
-int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type);
+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_obj_pin(int fd, const char *pathname);
diff --git a/samples/bpf/test_cgrp2_attach.c b/samples/bpf/test_cgrp2_attach.c
index 63ef208..9de4896 100644
--- a/samples/bpf/test_cgrp2_attach.c
+++ b/samples/bpf/test_cgrp2_attach.c
@@ -124,7 +124,7 @@ int main(int argc, char **argv)
 	ret = bpf_prog_detach(cg_fd, type);
 	printf("bpf_prog_detach() returned '%s' (%d)\n", strerror(errno), errno);
 
-	ret = bpf_prog_attach(prog_fd, cg_fd, type);
+	ret = bpf_prog_attach(prog_fd, cg_fd, type, 0);
 	if (ret < 0) {
 		printf("Failed to attach prog to cgroup: '%s'\n",
 		       strerror(errno));