renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 12:43:55 +08:00
Code
411aba3c12
linux-next/drivers/android/binderfs.c

595 lines
14 KiB
C
Raw Normal View History

binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/compiler_types.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/gfp.h>
#include <linux/idr.h>
#include <linux/init.h>
#include <linux/ipc_namespace.h>
#include <linux/kdev_t.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/magic.h>
#include <linux/major.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/parser.h>
#include <linux/radix-tree.h>
#include <linux/sched.h>
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
#include <linux/seq_file.h>
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
#include <linux/slab.h>
#include <linux/spinlock_types.h>
#include <linux/stddef.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include <linux/user_namespace.h>
#include <linux/xarray.h>
#include <uapi/asm-generic/errno-base.h>
#include <uapi/linux/android/binder.h>
binderfs: rename header to binderfs.h It doesn't make sense to call the header binder_ctl.h when its sole existence is tied to binderfs. So give it a sensible name. Users will far more easily remember binderfs.h than binder_ctl.h. Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-11 07:25:41 +08:00
#include <uapi/linux/android/binderfs.h>
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
#include "binder_internal.h"
#define FIRST_INODE 1
#define SECOND_INODE 2
#define INODE_OFFSET 3
#define INTSTRLEN 21
#define BINDERFS_MAX_MINOR (1U << MINORBITS)
binderfs: reserve devices for initial mount The binderfs instance in the initial ipc namespace will always have a reserve of 4 binder devices unless explicitly capped by specifying a lower value via the "max" mount option. This ensures when binder devices are removed (on accident or on purpose) they can always be recreated without risking that all minor numbers have already been used up. Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-11 18:19:40 +08:00
/* Ensure that the initial ipc namespace always has devices available. */
#define BINDERFS_MAX_MINOR_CAPPED (BINDERFS_MAX_MINOR - 4)
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
static dev_t binderfs_dev;
static DEFINE_MUTEX(binderfs_minors_mutex);
static DEFINE_IDA(binderfs_minors);
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
/**
* binderfs_mount_opts - mount options for binderfs
* @max: maximum number of allocatable binderfs binder devices
*/
struct binderfs_mount_opts {
int max;
};
enum {
Opt_max,
Opt_err
};
static const match_table_t tokens = {
{ Opt_max, "max=%d" },
{ Opt_err, NULL }
};
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
/**
* binderfs_info - information about a binderfs mount
* @ipc_ns: The ipc namespace the binderfs mount belongs to.
* @control_dentry: This records the dentry of this binderfs mount
* binder-control device.
* @root_uid: uid that needs to be used when a new binder device is
* created.
* @root_gid: gid that needs to be used when a new binder device is
* created.
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
* @mount_opts: The mount options in use.
* @device_count: The current number of allocated binder devices.
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
*/
struct binderfs_info {
struct ipc_namespace *ipc_ns;
struct dentry *control_dentry;
kuid_t root_uid;
kgid_t root_gid;
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
struct binderfs_mount_opts mount_opts;
int device_count;
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
};
static inline struct binderfs_info *BINDERFS_I(const struct inode *inode)
{
return inode->i_sb->s_fs_info;
}
bool is_binderfs_device(const struct inode *inode)
{
if (inode->i_sb->s_magic == BINDERFS_SUPER_MAGIC)
return true;
return false;
}
/**
* binderfs_binder_device_create - allocate inode from super block of a
* binderfs mount
* @ref_inode: inode from wich the super block will be taken
* @userp: buffer to copy information about new device for userspace to
* @req: struct binderfs_device as copied from userspace
*
* This function allocated a new binder_device and reserves a new minor
* number for it.
* Minor numbers are limited and tracked globally in binderfs_minors. The
* function will stash a struct binder_device for the specific binder
* device in i_private of the inode.
* It will go on to allocate a new inode from the super block of the
* filesystem mount, stash a struct binder_device in its i_private field
* and attach a dentry to that inode.
*
* Return: 0 on success, negative errno on failure
*/
static int binderfs_binder_device_create(struct inode *ref_inode,
struct binderfs_device __user *userp,
struct binderfs_device *req)
{
int minor, ret;
struct dentry *dentry, *dup, *root;
struct binder_device *device;
size_t name_len = BINDERFS_MAX_NAME + 1;
char *name = NULL;
struct inode *inode = NULL;
struct super_block *sb = ref_inode->i_sb;
struct binderfs_info *info = sb->s_fs_info;
binderfs: reserve devices for initial mount The binderfs instance in the initial ipc namespace will always have a reserve of 4 binder devices unless explicitly capped by specifying a lower value via the "max" mount option. This ensures when binder devices are removed (on accident or on purpose) they can always be recreated without risking that all minor numbers have already been used up. Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-11 18:19:40 +08:00
bool use_reserve = (info->ipc_ns == &init_ipc_ns);
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
/* Reserve new minor number for the new device. */
mutex_lock(&binderfs_minors_mutex);
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
if (++info->device_count <= info->mount_opts.max)
binderfs: reserve devices for initial mount The binderfs instance in the initial ipc namespace will always have a reserve of 4 binder devices unless explicitly capped by specifying a lower value via the "max" mount option. This ensures when binder devices are removed (on accident or on purpose) they can always be recreated without risking that all minor numbers have already been used up. Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-11 18:19:40 +08:00
minor = ida_alloc_max(&binderfs_minors,
use_reserve ? BINDERFS_MAX_MINOR :
BINDERFS_MAX_MINOR_CAPPED,
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
GFP_KERNEL);
else
minor = -ENOSPC;
if (minor < 0) {
--info->device_count;
mutex_unlock(&binderfs_minors_mutex);
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
return minor;
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
}
mutex_unlock(&binderfs_minors_mutex);
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
ret = -ENOMEM;
device = kzalloc(sizeof(*device), GFP_KERNEL);
if (!device)
goto err;
inode = new_inode(sb);
if (!inode)
goto err;
inode->i_ino = minor + INODE_OFFSET;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
init_special_inode(inode, S_IFCHR | 0600,
MKDEV(MAJOR(binderfs_dev), minor));
inode->i_fop = &binder_fops;
inode->i_uid = info->root_uid;
inode->i_gid = info->root_gid;
name = kmalloc(name_len, GFP_KERNEL);
if (!name)
goto err;
strscpy(name, req->name, name_len);
device->binderfs_inode = inode;
device->context.binder_context_mgr_uid = INVALID_UID;
device->context.name = name;
device->miscdev.name = name;
device->miscdev.minor = minor;
mutex_init(&device->context.context_mgr_node_lock);
req->major = MAJOR(binderfs_dev);
req->minor = minor;
ret = copy_to_user(userp, req, sizeof(*req));
if (ret) {
ret = -EFAULT;
goto err;
}
root = sb->s_root;
inode_lock(d_inode(root));
dentry = d_alloc_name(root, name);
if (!dentry) {
inode_unlock(d_inode(root));
ret = -ENOMEM;
goto err;
}
/* Verify that the name userspace gave us is not already in use. */
dup = d_lookup(root, &dentry->d_name);
if (dup) {
if (d_really_is_positive(dup)) {
dput(dup);
dput(dentry);
inode_unlock(d_inode(root));
ret = -EEXIST;
goto err;
}
dput(dup);
}
inode->i_private = device;
d_add(dentry, inode);
fsnotify_create(root->d_inode, dentry);
inode_unlock(d_inode(root));
return 0;
err:
kfree(name);
kfree(device);
mutex_lock(&binderfs_minors_mutex);
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
--info->device_count;
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
ida_free(&binderfs_minors, minor);
mutex_unlock(&binderfs_minors_mutex);
iput(inode);
return ret;
}
/**
* binderfs_ctl_ioctl - handle binder device node allocation requests
*
* The request handler for the binder-control device. All requests operate on
* the binderfs mount the binder-control device resides in:
* - BINDER_CTL_ADD
* Allocate a new binder device.
*
* Return: 0 on success, negative errno on failure
*/
static long binder_ctl_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
int ret = -EINVAL;
struct inode *inode = file_inode(file);
struct binderfs_device __user *device = (struct binderfs_device __user *)arg;
struct binderfs_device device_req;
switch (cmd) {
case BINDER_CTL_ADD:
ret = copy_from_user(&device_req, device, sizeof(device_req));
if (ret) {
ret = -EFAULT;
break;
}
ret = binderfs_binder_device_create(inode, device, &device_req);
break;
default:
break;
}
return ret;
}
static void binderfs_evict_inode(struct inode *inode)
{
struct binder_device *device = inode->i_private;
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
struct binderfs_info *info = BINDERFS_I(inode);
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
clear_inode(inode);
if (!device)
return;
mutex_lock(&binderfs_minors_mutex);
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
--info->device_count;
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
ida_free(&binderfs_minors, device->miscdev.minor);
mutex_unlock(&binderfs_minors_mutex);
kfree(device->context.name);
kfree(device);
}
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
/**
* binderfs_parse_mount_opts - parse binderfs mount options
* @data: options to set (can be NULL in which case defaults are used)
*/
static int binderfs_parse_mount_opts(char *data,
struct binderfs_mount_opts *opts)
{
char *p;
opts->max = BINDERFS_MAX_MINOR;
while ((p = strsep(&data, ",")) != NULL) {
substring_t args[MAX_OPT_ARGS];
int token;
int max_devices;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_max:
if (match_int(&args[0], &max_devices) ||
(max_devices < 0 ||
(max_devices > BINDERFS_MAX_MINOR)))
return -EINVAL;
opts->max = max_devices;
break;
default:
pr_err("Invalid mount options\n");
return -EINVAL;
}
}
return 0;
}
static int binderfs_remount(struct super_block *sb, int *flags, char *data)
{
struct binderfs_info *info = sb->s_fs_info;
return binderfs_parse_mount_opts(data, &info->mount_opts);
}
static int binderfs_show_mount_opts(struct seq_file *seq, struct dentry *root)
{
struct binderfs_info *info;
info = root->d_sb->s_fs_info;
if (info->mount_opts.max <= BINDERFS_MAX_MINOR)
seq_printf(seq, ",max=%d", info->mount_opts.max);
return 0;
}
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
static const struct super_operations binderfs_super_ops = {
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
.evict_inode = binderfs_evict_inode,
.remount_fs = binderfs_remount,
.show_options = binderfs_show_mount_opts,
.statfs = simple_statfs,
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
};
static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
struct inode *inode = d_inode(old_dentry);
/* binderfs doesn't support directories. */
if (d_is_dir(old_dentry))
return -EPERM;
if (flags & ~RENAME_NOREPLACE)
return -EINVAL;
if (!simple_empty(new_dentry))
return -ENOTEMPTY;
if (d_really_is_positive(new_dentry))
simple_unlink(new_dir, new_dentry);
old_dir->i_ctime = old_dir->i_mtime = new_dir->i_ctime =
new_dir->i_mtime = inode->i_ctime = current_time(old_dir);
return 0;
}
static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
{
/*
* The control dentry is only ever touched during mount so checking it
* here should not require us to take lock.
*/
if (BINDERFS_I(dir)->control_dentry == dentry)
return -EPERM;
return simple_unlink(dir, dentry);
}
static const struct file_operations binder_ctl_fops = {
.owner = THIS_MODULE,
.open = nonseekable_open,
.unlocked_ioctl = binder_ctl_ioctl,
.compat_ioctl = binder_ctl_ioctl,
.llseek = noop_llseek,
};
/**
* binderfs_binder_ctl_create - create a new binder-control device
* @sb: super block of the binderfs mount
*
* This function creates a new binder-control device node in the binderfs mount
* referred to by @sb.
*
* Return: 0 on success, negative errno on failure
*/
static int binderfs_binder_ctl_create(struct super_block *sb)
{
int minor, ret;
struct dentry *dentry;
struct binder_device *device;
struct inode *inode = NULL;
struct dentry *root = sb->s_root;
struct binderfs_info *info = sb->s_fs_info;
device = kzalloc(sizeof(*device), GFP_KERNEL);
if (!device)
return -ENOMEM;
inode_lock(d_inode(root));
/* If we have already created a binder-control node, return. */
if (info->control_dentry) {
ret = 0;
goto out;
}
ret = -ENOMEM;
inode = new_inode(sb);
if (!inode)
goto out;
/* Reserve a new minor number for the new device. */
mutex_lock(&binderfs_minors_mutex);
minor = ida_alloc_max(&binderfs_minors, BINDERFS_MAX_MINOR, GFP_KERNEL);
mutex_unlock(&binderfs_minors_mutex);
if (minor < 0) {
ret = minor;
goto out;
}
inode->i_ino = SECOND_INODE;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
init_special_inode(inode, S_IFCHR | 0600,
MKDEV(MAJOR(binderfs_dev), minor));
inode->i_fop = &binder_ctl_fops;
inode->i_uid = info->root_uid;
inode->i_gid = info->root_gid;
device->binderfs_inode = inode;
device->miscdev.minor = minor;
dentry = d_alloc_name(root, "binder-control");
if (!dentry)
goto out;
inode->i_private = device;
info->control_dentry = dentry;
d_add(dentry, inode);
inode_unlock(d_inode(root));
return 0;
out:
inode_unlock(d_inode(root));
kfree(device);
iput(inode);
return ret;
}
static const struct inode_operations binderfs_dir_inode_operations = {
.lookup = simple_lookup,
.rename = binderfs_rename,
.unlink = binderfs_unlink,
};
static int binderfs_fill_super(struct super_block *sb, void *data, int silent)
{
struct binderfs_info *info;
int ret = -ENOMEM;
struct inode *inode = NULL;
binderfs: make each binderfs mount a new instance When currently mounting binderfs in the same ipc namespace twice: mount -t binder binder /A mount -t binder binder /B then the binderfs instances mounted on /A and /B will be the same, i.e. they will have the same superblock. This was the first approach that seemed reasonable. However, this leads to some problems and inconsistencies: /* private binderfs instance in same ipc namespace */ There is no way for a user to request a private binderfs instance in the same ipc namespace. This request has been made in a private mail to me by two independent people. /* bind-mounts */ If users want the same binderfs instance to appear in multiple places they can use bind mounts. So there is no value in having a request for a new binderfs mount giving them the same instance. /* unexpected behavior */ It's surprising that request to mount binderfs is not giving the user a new instance like tmpfs, devpts, ramfs, and others do. /* past mistakes */ Other pseudo-filesystems once made the same mistakes of giving back the same superblock when actually requesting a new mount (cf. devpts's deprecated "newinstance" option). We should not make the same mistake. Once we've committed to always giving back the same superblock in the same IPC namespace with the next kernel release we will not be able to make that change so better to do it now. /* kdbusfs */ It was pointed out to me that kdbusfs - which is conceptually closely related to binderfs - also allowed users to get a private kdbusfs instance in the same IPC namespace by making each mount of kdbusfs a separate instance. I think that makes a lot of sense. Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-06 22:05:41 +08:00
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
get_ipc_ns(ipc_ns);
sb->s_blocksize = PAGE_SIZE;
sb->s_blocksize_bits = PAGE_SHIFT;
/*
* The binderfs filesystem can be mounted by userns root in a
* non-initial userns. By default such mounts have the SB_I_NODEV flag
* set in s_iflags to prevent security issues where userns root can
* just create random device nodes via mknod() since it owns the
* filesystem mount. But binderfs does not allow to create any files
* including devices nodes. The only way to create binder devices nodes
* is through the binder-control device which userns root is explicitly
* allowed to do. So removing the SB_I_NODEV flag from s_iflags is both
* necessary and safe.
*/
sb->s_iflags &= ~SB_I_NODEV;
sb->s_iflags |= SB_I_NOEXEC;
sb->s_magic = BINDERFS_SUPER_MAGIC;
sb->s_op = &binderfs_super_ops;
sb->s_time_gran = 1;
info = kzalloc(sizeof(struct binderfs_info), GFP_KERNEL);
if (!info)
goto err_without_dentry;
binderfs: implement "max" mount option Since binderfs can be mounted by userns root in non-initial user namespaces some precautions are in order. First, a way to set a maximum on the number of binder devices that can be allocated per binderfs instance and second, a way to reserve a reasonable chunk of binderfs devices for the initial ipc namespace. A first approach as seen in [1] used sysctls similiar to devpts but was shown to be flawed (cf. [2] and [3]) since some aspects were unneeded. This is an alternative approach which avoids sysctls completely and instead switches to a single mount option. Starting with this commit binderfs instances can be mounted with a limit on the number of binder devices that can be allocated. The max=<count> mount option serves as a per-instance limit. If max=<count> is set then only <count> number of binder devices can be allocated in this binderfs instance. This allows to safely bind-mount binderfs instances into unprivileged user namespaces since userns root in a non-initial user namespace cannot change the mount option as long as it does not own the mount namespace the binderfs mount was created in and hence cannot drain the host of minor device numbers [1]: https://lore.kernel.org/lkml/20181221133909.18794-1-christian@brauner.io/ [2]; https://lore.kernel.org/lkml/20181221163316.GA8517@kroah.com/ [3]: https://lore.kernel.org/lkml/CAHRSSEx+gDVW4fKKK8oZNAir9G5icJLyodO8hykv3O0O1jt2FQ@mail.gmail.com/ [4]: https://lore.kernel.org/lkml/20181221192044.5yvfnuri7gdop4rs@brauner.io/ Cc: Todd Kjos <tkjos@google.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-02 19:32:18 +08:00
ret = binderfs_parse_mount_opts(data, &info->mount_opts);
if (ret)
goto err_without_dentry;
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
info->ipc_ns = ipc_ns;
info->root_gid = make_kgid(sb->s_user_ns, 0);
if (!gid_valid(info->root_gid))
info->root_gid = GLOBAL_ROOT_GID;
info->root_uid = make_kuid(sb->s_user_ns, 0);
if (!uid_valid(info->root_uid))
info->root_uid = GLOBAL_ROOT_UID;
sb->s_fs_info = info;
inode = new_inode(sb);
if (!inode)
goto err_without_dentry;
inode->i_ino = FIRST_INODE;
inode->i_fop = &simple_dir_operations;
inode->i_mode = S_IFDIR | 0755;
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
inode->i_op = &binderfs_dir_inode_operations;
set_nlink(inode, 2);
sb->s_root = d_make_root(inode);
if (!sb->s_root)
goto err_without_dentry;
ret = binderfs_binder_ctl_create(sb);
if (ret)
goto err_with_dentry;
return 0;
err_with_dentry:
dput(sb->s_root);
sb->s_root = NULL;
err_without_dentry:
put_ipc_ns(ipc_ns);
iput(inode);
kfree(info);
return ret;
}
static struct dentry *binderfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name,
void *data)
{
binderfs: make each binderfs mount a new instance When currently mounting binderfs in the same ipc namespace twice: mount -t binder binder /A mount -t binder binder /B then the binderfs instances mounted on /A and /B will be the same, i.e. they will have the same superblock. This was the first approach that seemed reasonable. However, this leads to some problems and inconsistencies: /* private binderfs instance in same ipc namespace */ There is no way for a user to request a private binderfs instance in the same ipc namespace. This request has been made in a private mail to me by two independent people. /* bind-mounts */ If users want the same binderfs instance to appear in multiple places they can use bind mounts. So there is no value in having a request for a new binderfs mount giving them the same instance. /* unexpected behavior */ It's surprising that request to mount binderfs is not giving the user a new instance like tmpfs, devpts, ramfs, and others do. /* past mistakes */ Other pseudo-filesystems once made the same mistakes of giving back the same superblock when actually requesting a new mount (cf. devpts's deprecated "newinstance" option). We should not make the same mistake. Once we've committed to always giving back the same superblock in the same IPC namespace with the next kernel release we will not be able to make that change so better to do it now. /* kdbusfs */ It was pointed out to me that kdbusfs - which is conceptually closely related to binderfs - also allowed users to get a private kdbusfs instance in the same IPC namespace by making each mount of kdbusfs a separate instance. I think that makes a lot of sense. Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-06 22:05:41 +08:00
return mount_nodev(fs_type, flags, data, binderfs_fill_super);
binder: implement binderfs As discussed at Linux Plumbers Conference 2018 in Vancouver [1] this is the implementation of binderfs. /* Abstract */ binderfs is a backwards-compatible filesystem for Android's binder ipc mechanism. Each ipc namespace will mount a new binderfs instance. Mounting binderfs multiple times at different locations in the same ipc namespace will not cause a new super block to be allocated and hence it will be the same filesystem instance. Each new binderfs mount will have its own set of binder devices only visible in the ipc namespace it has been mounted in. All devices in a new binderfs mount will follow the scheme binder%d and numbering will always start at 0. /* Backwards compatibility */ Devices requested in the Kconfig via CONFIG_ANDROID_BINDER_DEVICES for the initial ipc namespace will work as before. They will be registered via misc_register() and appear in the devtmpfs mount. Specifically, the standard devices binder, hwbinder, and vndbinder will all appear in their standard locations in /dev. Mounting or unmounting the binderfs mount in the initial ipc namespace will have no effect on these devices, i.e. they will neither show up in the binderfs mount nor will they disappear when the binderfs mount is gone. /* binder-control */ Each new binderfs instance comes with a binder-control device. No other devices will be present at first. The binder-control device can be used to dynamically allocate binder devices. All requests operate on the binderfs mount the binder-control device resides in. Assuming a new instance of binderfs has been mounted at /dev/binderfs via mount -t binderfs binderfs /dev/binderfs. Then a request to create a new binder device can be made as illustrated in [2]. Binderfs devices can simply be removed via unlink(). /* Implementation details */ - dynamic major number allocation: When binderfs is registered as a new filesystem it will dynamically allocate a new major number. The allocated major number will be returned in struct binderfs_device when a new binder device is allocated. - global minor number tracking: Minor are tracked in a global idr struct that is capped at BINDERFS_MAX_MINOR. The minor number tracker is protected by a global mutex. This is the only point of contention between binderfs mounts. - struct binderfs_info: Each binderfs super block has its own struct binderfs_info that tracks specific details about a binderfs instance: - ipc namespace - dentry of the binder-control device - root uid and root gid of the user namespace the binderfs instance was mounted in - mountable by user namespace root: binderfs can be mounted by user namespace root in a non-initial user namespace. The devices will be owned by user namespace root. - binderfs binder devices without misc infrastructure: New binder devices associated with a binderfs mount do not use the full misc_register() infrastructure. The misc_register() infrastructure can only create new devices in the host's devtmpfs mount. binderfs does however only make devices appear under its own mountpoint and thus allocates new character device nodes from the inode of the root dentry of the super block. This will have the side-effect that binderfs specific device nodes do not appear in sysfs. This behavior is similar to devpts allocated pts devices and has no effect on the functionality of the ipc mechanism itself. [1]: https://goo.gl/JL2tfX [2]: program to allocate a new binderfs binder device: #define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <sys/types.h> #include <unistd.h> #include <linux/android/binder_ctl.h> int main(int argc, char *argv[]) { int fd, ret, saved_errno; size_t len; struct binderfs_device device = { 0 }; if (argc < 2) exit(EXIT_FAILURE); len = strlen(argv[1]); if (len > BINDERFS_MAX_NAME) exit(EXIT_FAILURE); memcpy(device.name, argv[1], len); fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); if (fd < 0) { printf("%s - Failed to open binder-control device\n", strerror(errno)); exit(EXIT_FAILURE); } ret = ioctl(fd, BINDER_CTL_ADD, &device); saved_errno = errno; close(fd); errno = saved_errno; if (ret < 0) { printf("%s - Failed to allocate new binder device\n", strerror(errno)); exit(EXIT_FAILURE); } printf("Allocated new binder device with major %d, minor %d, and " "name %s\n", device.major, device.minor, device.name); exit(EXIT_SUCCESS); } Cc: Martijn Coenen <maco@android.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2018-12-14 20:11:14 +08:00
}
static void binderfs_kill_super(struct super_block *sb)
{
struct binderfs_info *info = sb->s_fs_info;
if (info && info->ipc_ns)
put_ipc_ns(info->ipc_ns);
kfree(info);
kill_litter_super(sb);
}
static struct file_system_type binder_fs_type = {
.name = "binder",
.mount = binderfs_mount,
.kill_sb = binderfs_kill_super,
.fs_flags = FS_USERNS_MOUNT,
};
static int __init init_binderfs(void)
{
int ret;
/* Allocate new major number for binderfs. */
ret = alloc_chrdev_region(&binderfs_dev, 0, BINDERFS_MAX_MINOR,
"binder");
if (ret)
return ret;
ret = register_filesystem(&binder_fs_type);
if (ret) {
unregister_chrdev_region(binderfs_dev, BINDERFS_MAX_MINOR);
return ret;
}
return ret;
}
device_initcall(init_binderfs);
Copy Permalink