Merge branch 'eBPF-based-device-cgroup-controller'

Roman Gushchin says:

====================
eBPF-based device cgroup controller

This patchset introduces an eBPF-based device controller for cgroup v2.

Patches (1) and (2) are a preparational work required to share some code
  with the existing device controller implementation.
Patch (3) is the main patch, which introduces a new bpf prog type
  and all necessary infrastructure.
Patch (4) moves cgroup_helpers.c/h to use them by patch (4).
Patch (5) implements an example of eBPF program which controls access
  to device files and corresponding userspace test.

v3:
  Renamed constants introduced by patch (3) to BPF_DEVCG_*

v2:
  Added patch (1).

v1:
  https://lkml.org/lkml/2017/11/1/363
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf-cgroup.h

@@ -67,6 +67,9 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 				     struct bpf_sock_ops_kern *sock_ops,
 				     enum bpf_attach_type type);
 
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+				      short access, enum bpf_attach_type type);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -112,6 +115,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	}								       \
 	__ret;								       \
 })
+
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access)	      \
+({									      \
+	int __ret = 0;							      \
+	if (cgroup_bpf_enabled)						      \
+		__ret = __cgroup_bpf_check_dev_permission(type, major, minor, \
+							  access,	      \
+							  BPF_CGROUP_DEVICE); \
+									      \
+	__ret;								      \
+})
 #else
 
 struct cgroup_bpf {};
@@ -122,6 +136,7 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; })
 
 #endif /* CONFIG_CGROUP_BPF */
 

include/linux/bpf_types.h

@@ -19,6 +19,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
 BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
 BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
 #endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
+#endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)

include/linux/device_cgroup.h

@@ -1,17 +1,76 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/fs.h>
+#include <linux/bpf-cgroup.h>
+
+#define DEVCG_ACC_MKNOD 1
+#define DEVCG_ACC_READ  2
+#define DEVCG_ACC_WRITE 4
+#define DEVCG_ACC_MASK (DEVCG_ACC_MKNOD | DEVCG_ACC_READ | DEVCG_ACC_WRITE)
+
+#define DEVCG_DEV_BLOCK 1
+#define DEVCG_DEV_CHAR  2
+#define DEVCG_DEV_ALL   4  /* this represents all devices */
 
 #ifdef CONFIG_CGROUP_DEVICE
-extern int __devcgroup_inode_permission(struct inode *inode, int mask);
-extern int devcgroup_inode_mknod(int mode, dev_t dev);
+extern int __devcgroup_check_permission(short type, u32 major, u32 minor,
+					short access);
+#else
+static inline int __devcgroup_check_permission(short type, u32 major, u32 minor,
+					       short access)
+{ return 0; }
+#endif
+
+#if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
+static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
+					     short access)
+{
+	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
+
+	if (rc)
+		return -EPERM;
+
+	return __devcgroup_check_permission(type, major, minor, access);
+}
+
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 {
+	short type, access = 0;
+
 	if (likely(!inode->i_rdev))
 		return 0;
-	if (!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode))
+
+	if (S_ISBLK(inode->i_mode))
+		type = DEVCG_DEV_BLOCK;
+	else if (S_ISCHR(inode->i_mode))
+		type = DEVCG_DEV_CHAR;
+	else
+		return 0;
+
+	if (mask & MAY_WRITE)
+		access |= DEVCG_ACC_WRITE;
+	if (mask & MAY_READ)
+		access |= DEVCG_ACC_READ;
+
+	return devcgroup_check_permission(type, imajor(inode), iminor(inode),
+					  access);
+}
+
+static inline int devcgroup_inode_mknod(int mode, dev_t dev)
+{
+	short type;
+
+	if (!S_ISBLK(mode) && !S_ISCHR(mode))
 		return 0;
-	return __devcgroup_inode_permission(inode, mask);
+
+	if (S_ISBLK(mode))
+		type = DEVCG_DEV_BLOCK;
+	else
+		type = DEVCG_DEV_CHAR;
+
+	return devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
+					  DEVCG_ACC_MKNOD);
 }
+
 #else
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 { return 0; }

include/uapi/linux/bpf.h

@@ -132,6 +132,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_LWT_XMIT,
 	BPF_PROG_TYPE_SOCK_OPS,
 	BPF_PROG_TYPE_SK_SKB,
+	BPF_PROG_TYPE_CGROUP_DEVICE,
 };
 
 enum bpf_attach_type {
@@ -141,6 +142,7 @@ enum bpf_attach_type {
 	BPF_CGROUP_SOCK_OPS,
 	BPF_SK_SKB_STREAM_PARSER,
 	BPF_SK_SKB_STREAM_VERDICT,
+	BPF_CGROUP_DEVICE,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -991,4 +993,17 @@ struct bpf_perf_event_value {
 	__u64 running;
 };
 
+#define BPF_DEVCG_ACC_MKNOD	(1ULL << 0)
+#define BPF_DEVCG_ACC_READ	(1ULL << 1)
+#define BPF_DEVCG_ACC_WRITE	(1ULL << 2)
+
+#define BPF_DEVCG_DEV_BLOCK	(1ULL << 0)
+#define BPF_DEVCG_DEV_CHAR	(1ULL << 1)
+
+struct bpf_cgroup_dev_ctx {
+	__u32 access_type; /* (access << 16) | type */
+	__u32 major;
+	__u32 minor;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

kernel/bpf/cgroup.c

@@ -522,3 +522,70 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 	return ret == 1 ? 0 : -EPERM;
 }
 EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops);
+
+int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
+				      short access, enum bpf_attach_type type)
+{
+	struct cgroup *cgrp;
+	struct bpf_cgroup_dev_ctx ctx = {
+		.access_type = (access << 16) | dev_type,
+		.major = major,
+		.minor = minor,
+	};
+	int allow = 1;
+
+	rcu_read_lock();
+	cgrp = task_dfl_cgroup(current);
+	allow = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx,
+				   BPF_PROG_RUN);
+	rcu_read_unlock();
+
+	return !allow;
+}
+EXPORT_SYMBOL(__cgroup_bpf_check_dev_permission);
+
+static const struct bpf_func_proto *
+cgroup_dev_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_map_lookup_elem:
+		return &bpf_map_lookup_elem_proto;
+	case BPF_FUNC_map_update_elem:
+		return &bpf_map_update_elem_proto;
+	case BPF_FUNC_map_delete_elem:
+		return &bpf_map_delete_elem_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_trace_printk:
+		if (capable(CAP_SYS_ADMIN))
+			return bpf_get_trace_printk_proto();
+	default:
+		return NULL;
+	}
+}
+
+static bool cgroup_dev_is_valid_access(int off, int size,
+				       enum bpf_access_type type,
+				       struct bpf_insn_access_aux *info)
+{
+	if (type == BPF_WRITE)
+		return false;
+
+	if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx))
+		return false;
+	/* The verifier guarantees that size > 0. */
+	if (off % size != 0)
+		return false;
+	if (size != sizeof(__u32))
+		return false;
+
+	return true;
+}
+
+const struct bpf_prog_ops cg_dev_prog_ops = {
+};
+
+const struct bpf_verifier_ops cg_dev_verifier_ops = {
+	.get_func_proto		= cgroup_dev_func_proto,
+	.is_valid_access	= cgroup_dev_is_valid_access,
+};

kernel/bpf/syscall.c

@@ -1326,6 +1326,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	case BPF_CGROUP_SOCK_OPS:
 		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
+	case BPF_CGROUP_DEVICE:
+		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
 		return sockmap_get_from_fd(attr, true);
@@ -1378,6 +1381,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	case BPF_CGROUP_SOCK_OPS:
 		ptype = BPF_PROG_TYPE_SOCK_OPS;
 		break;
+	case BPF_CGROUP_DEVICE:
+		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
 		return sockmap_get_from_fd(attr, false);
@@ -1420,6 +1426,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	case BPF_CGROUP_INET_EGRESS:
 	case BPF_CGROUP_INET_SOCK_CREATE:
 	case BPF_CGROUP_SOCK_OPS:
+	case BPF_CGROUP_DEVICE:
 		break;
 	default:
 		return -EINVAL;

kernel/bpf/verifier.c

@@ -3124,6 +3124,7 @@ static int check_return_code(struct bpf_verifier_env *env)
 	case BPF_PROG_TYPE_CGROUP_SKB:
 	case BPF_PROG_TYPE_CGROUP_SOCK:
 	case BPF_PROG_TYPE_SOCK_OPS:
+	case BPF_PROG_TYPE_CGROUP_DEVICE:
 		break;
 	default:
 		return 0;

samples/bpf/Makefile

@@ -46,6 +46,7 @@ hostprogs-y += syscall_tp
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o
+CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o
 
 test_lru_dist-objs := test_lru_dist.o $(LIBBPF)
 sock_example-objs := sock_example.o $(LIBBPF)
@@ -69,13 +70,13 @@ map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o
 test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o
 test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o
 test_cgrp2_attach-objs := $(LIBBPF) test_cgrp2_attach.o
-test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o cgroup_helpers.o
+test_cgrp2_attach2-objs := $(LIBBPF) test_cgrp2_attach2.o $(CGROUP_HELPERS)
 test_cgrp2_sock-objs := $(LIBBPF) test_cgrp2_sock.o
 test_cgrp2_sock2-objs := bpf_load.o $(LIBBPF) test_cgrp2_sock2.o
 xdp1-objs := bpf_load.o $(LIBBPF) xdp1_user.o
 # reuse xdp1 source intentionally
 xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o
-test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) cgroup_helpers.o \
+test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) $(CGROUP_HELPERS) \
 				       test_current_task_under_cgroup_user.o
 trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o
 sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o