bpf: Add file mode configuration into bpf maps

Introduce the map read/write flags to the eBPF syscalls that returns the
map fd. The flags is used to set up the file mode when construct a new
file descriptor for bpf maps. To not break the backward capability, the
f_flags is set to O_RDWR if the flag passed by syscall is 0. Otherwise
it should be O_RDONLY or O_WRONLY. When the userspace want to modify or
read the map content, it will check the file mode to see if it is
allowed to make the change.

Signed-off-by: Chenbo Feng <fengc@google.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/bpf.h

@@ -315,11 +315,11 @@ void bpf_map_area_free(void *base);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
-int bpf_map_new_fd(struct bpf_map *map);
+int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
 int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname);
+int bpf_obj_get_user(const char __user *pathname, int flags);
 
 int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
 int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
@@ -338,6 +338,8 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
 				void *key, void *value, u64 map_flags);
 int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
 
+int bpf_get_file_flag(int flags);
+
 /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
  * forced to use 'long' read/writes to try to atomically copy long counters.
  * Best-effort only.  No barriers here, since it _will_ race with concurrent
@@ -421,7 +423,7 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
 {
 }
 
-static inline int bpf_obj_get_user(const char __user *pathname)
+static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	return -EOPNOTSUPP;
 }

include/uapi/linux/bpf.h

@@ -218,6 +218,10 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
+/* Flags for accessing BPF object */
+#define BPF_F_RDONLY		(1U << 3)
+#define BPF_F_WRONLY		(1U << 4)
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -260,6 +264,7 @@ union bpf_attr {
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
 		__aligned_u64	pathname;
 		__u32		bpf_fd;
+		__u32		file_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_PROG_ATTACH/DETACH commands */
@@ -287,6 +292,7 @@ union bpf_attr {
 			__u32		map_id;
 		};
 		__u32		next_id;
+		__u32		open_flags;
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_GET_INFO_BY_FD */

kernel/bpf/arraymap.c

@@ -19,6 +19,9 @@
 
 #include "map_in_map.h"
 
+#define ARRAY_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
 	int i;
@@ -56,7 +59,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size == 0 || attr->map_flags & ~BPF_F_NUMA_NODE ||
+	    attr->value_size == 0 ||
+	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return ERR_PTR(-EINVAL);
 

kernel/bpf/devmap.c

@@ -50,6 +50,9 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 
+#define DEV_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct bpf_dtab_netdev {
 	struct net_device *dev;
 	struct bpf_dtab *dtab;
@@ -80,7 +83,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	dtab = kzalloc(sizeof(*dtab), GFP_USER);

kernel/bpf/hashtab.c

@@ -19,7 +19,8 @@
 #include "map_in_map.h"
 
 #define HTAB_CREATE_FLAG_MASK						\
-	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE)
+	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
+	 BPF_F_RDONLY | BPF_F_WRONLY)
 
 struct bucket {
 	struct hlist_nulls_head head;

kernel/bpf/inode.c

@@ -295,7 +295,7 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname)
 }
 
 static void *bpf_obj_do_get(const struct filename *pathname,
-			    enum bpf_type *type)
+			    enum bpf_type *type, int flags)
 {
 	struct inode *inode;
 	struct path path;
@@ -307,7 +307,7 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 		return ERR_PTR(ret);
 
 	inode = d_backing_inode(path.dentry);
-	ret = inode_permission(inode, MAY_WRITE);
+	ret = inode_permission(inode, ACC_MODE(flags));
 	if (ret)
 		goto out;
 
@@ -326,18 +326,23 @@ static void *bpf_obj_do_get(const struct filename *pathname,
 	return ERR_PTR(ret);
 }
 
-int bpf_obj_get_user(const char __user *pathname)
+int bpf_obj_get_user(const char __user *pathname, int flags)
 {
 	enum bpf_type type = BPF_TYPE_UNSPEC;
 	struct filename *pname;
 	int ret = -ENOENT;
+	int f_flags;
 	void *raw;
 
+	f_flags = bpf_get_file_flag(flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	pname = getname(pathname);
 	if (IS_ERR(pname))
 		return PTR_ERR(pname);
 
-	raw = bpf_obj_do_get(pname, &type);
+	raw = bpf_obj_do_get(pname, &type, f_flags);
 	if (IS_ERR(raw)) {
 		ret = PTR_ERR(raw);
 		goto out;
@@ -346,7 +351,7 @@ int bpf_obj_get_user(const char __user *pathname)
 	if (type == BPF_TYPE_PROG)
 		ret = bpf_prog_new_fd(raw);
 	else if (type == BPF_TYPE_MAP)
-		ret = bpf_map_new_fd(raw);
+		ret = bpf_map_new_fd(raw, f_flags);
 	else
 		goto out;
 

kernel/bpf/lpm_trie.c

@@ -495,7 +495,8 @@ static int trie_delete_elem(struct bpf_map *map, void *_key)
 #define LPM_KEY_SIZE_MAX	LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
 #define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
 
-#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE)
+#define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE |	\
+				 BPF_F_RDONLY | BPF_F_WRONLY)
 
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {

kernel/bpf/sockmap.c

@@ -40,6 +40,9 @@
 #include <linux/list.h>
 #include <net/strparser.h>
 
+#define SOCK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct bpf_stab {
 	struct bpf_map map;
 	struct sock **sock_map;
@@ -489,7 +492,7 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~BPF_F_NUMA_NODE)
+	    attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	if (attr->value_size > KMALLOC_MAX_SIZE)

kernel/bpf/stackmap.c

@@ -11,6 +11,9 @@
 #include <linux/perf_event.h>
 #include "percpu_freelist.h"
 
+#define STACK_CREATE_FLAG_MASK \
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
 struct stack_map_bucket {
 	struct pcpu_freelist_node fnode;
 	u32 hash;
@@ -60,7 +63,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
-	if (attr->map_flags & ~BPF_F_NUMA_NODE)
+	if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
 	/* check sanity of attributes */

kernel/bpf/syscall.c

@@ -34,6 +34,8 @@
 #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)
 #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map))
 
+#define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)
+
 DEFINE_PER_CPU(int, bpf_prog_active);
 static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
@@ -294,17 +296,48 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
+static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,
+			      loff_t *ppos)
+{
+	/* We need this handler such that alloc_file() enables
+	 * f_mode with FMODE_CAN_READ.
+	 */
+	return -EINVAL;
+}
+
+static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,
+			       size_t siz, loff_t *ppos)
+{
+	/* We need this handler such that alloc_file() enables
+	 * f_mode with FMODE_CAN_WRITE.
+	 */
+	return -EINVAL;
+}
+
 static const struct file_operations bpf_map_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_map_show_fdinfo,
 #endif
 	.release	= bpf_map_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
 };
 
-int bpf_map_new_fd(struct bpf_map *map)
+int bpf_map_new_fd(struct bpf_map *map, int flags)
 {
 	return anon_inode_getfd("bpf-map", &bpf_map_fops, map,
-				O_RDWR | O_CLOEXEC);
+				flags | O_CLOEXEC);
+}
+
+int bpf_get_file_flag(int flags)
+{
+	if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))
+		return -EINVAL;
+	if (flags & BPF_F_RDONLY)
+		return O_RDONLY;
+	if (flags & BPF_F_WRONLY)
+		return O_WRONLY;
+	return O_RDWR;
 }
 
 /* helper macro to check that unused fields 'union bpf_attr' are zero */
@@ -344,12 +377,17 @@ static int map_create(union bpf_attr *attr)
 {
 	int numa_node = bpf_map_attr_numa_node(attr);
 	struct bpf_map *map;
+	int f_flags;
 	int err;
 
 	err = CHECK_ATTR(BPF_MAP_CREATE);
 	if (err)
 		return -EINVAL;
 
+	f_flags = bpf_get_file_flag(attr->map_flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	if (numa_node != NUMA_NO_NODE &&
 	    ((unsigned int)numa_node >= nr_node_ids ||
 	     !node_online(numa_node)))
@@ -375,7 +413,7 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map;
 
-	err = bpf_map_new_fd(map);
+	err = bpf_map_new_fd(map, f_flags);
 	if (err < 0) {
 		/* failed to allocate fd.
 		 * bpf_map_put() is needed because the above
@@ -490,6 +528,11 @@ static int map_lookup_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -570,6 +613,11 @@ static int map_update_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -659,6 +707,11 @@ static int map_delete_elem(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	key = memdup_user(ukey, map->key_size);
 	if (IS_ERR(key)) {
 		err = PTR_ERR(key);
@@ -702,6 +755,11 @@ static int map_get_next_key(union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
+	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
 	if (ukey) {
 		key = memdup_user(ukey, map->key_size);
 		if (IS_ERR(key)) {
@@ -908,6 +966,8 @@ static const struct file_operations bpf_prog_fops = {
 	.show_fdinfo	= bpf_prog_show_fdinfo,
 #endif
 	.release	= bpf_prog_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
 };
 
 int bpf_prog_new_fd(struct bpf_prog *prog)
@@ -1117,11 +1177,11 @@ static int bpf_prog_load(union bpf_attr *attr)
 	return err;
 }
 
-#define BPF_OBJ_LAST_FIELD bpf_fd
+#define BPF_OBJ_LAST_FIELD file_flags
 
 static int bpf_obj_pin(const union bpf_attr *attr)
 {
-	if (CHECK_ATTR(BPF_OBJ))
+	if (CHECK_ATTR(BPF_OBJ) || attr->file_flags != 0)
 		return -EINVAL;
 
 	return bpf_obj_pin_user(attr->bpf_fd, u64_to_user_ptr(attr->pathname));
@@ -1129,10 +1189,12 @@ static int bpf_obj_pin(const union bpf_attr *attr)
 
 static int bpf_obj_get(const union bpf_attr *attr)
 {
-	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0)
+	if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 ||
+	    attr->file_flags & ~BPF_OBJ_FLAG_MASK)
 		return -EINVAL;
 
-	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname));
+	return bpf_obj_get_user(u64_to_user_ptr(attr->pathname),
+				attr->file_flags);
 }
 
 #ifdef CONFIG_CGROUP_BPF
@@ -1392,20 +1454,26 @@ static int bpf_prog_get_fd_by_id(const union bpf_attr *attr)
 	return fd;
 }
 
-#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD map_id
+#define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags
 
 static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 {
 	struct bpf_map *map;
 	u32 id = attr->map_id;
+	int f_flags;
 	int fd;
 
-	if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID))
+	if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) ||
+	    attr->open_flags & ~BPF_OBJ_FLAG_MASK)
 		return -EINVAL;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	f_flags = bpf_get_file_flag(attr->open_flags);
+	if (f_flags < 0)
+		return f_flags;
+
 	spin_lock_bh(&map_idr_lock);
 	map = idr_find(&map_idr, id);
 	if (map)
@@ -1417,7 +1485,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
-	fd = bpf_map_new_fd(map);
+	fd = bpf_map_new_fd(map, f_flags);
 	if (fd < 0)
 		bpf_map_put(map);
 

net/netfilter/xt_bpf.c

@@ -56,7 +56,7 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
 	int retval, fd;
 
 	set_fs(KERNEL_DS);
-	fd = bpf_obj_get_user(path);
+	fd = bpf_obj_get_user(path, 0);
 	set_fs(oldfs);
 	if (fd < 0)
 		return fd;