linux/drivers/android/binderfs.c

795 lines
19 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 13:11:14 +01:00
/* 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/namei.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 13:11:14 +01:00
#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 12:32:18 +01:00
#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 13:11:14 +01:00
#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>
#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 13:11:14 +01:00
#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)
/* 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 13:11:14 +01:00
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 12:32:18 +01:00
enum {
Opt_max,
Opt_stats_mode,
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 12:32:18 +01:00
Opt_err
};
enum binderfs_stats_mode {
STATS_NONE,
STATS_GLOBAL,
};
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 12:32:18 +01:00
static const match_table_t tokens = {
{ Opt_max, "max=%d" },
{ Opt_stats_mode, "stats=%s" },
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 12:32:18 +01:00
{ 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 13:11:14 +01:00
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 allocates a new binder_device and reserves a new minor
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 13:11:14 +01:00
* 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, *root;
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 13:11:14 +01:00
struct binder_device *device;
char *name = NULL;
size_t name_len;
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 13:11:14 +01:00
struct inode *inode = NULL;
struct super_block *sb = ref_inode->i_sb;
struct binderfs_info *info = sb->s_fs_info;
#if defined(CONFIG_IPC_NS)
bool use_reserve = (info->ipc_ns == &init_ipc_ns);
#else
bool use_reserve = true;
#endif
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 13:11:14 +01:00
/* 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 12:32:18 +01:00
if (++info->device_count <= info->mount_opts.max)
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 12:32:18 +01:00
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 13:11:14 +01:00
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 12:32:18 +01:00
}
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 13:11:14 +01:00
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;
req->name[BINDERFS_MAX_NAME] = '\0'; /* NUL-terminate */
name_len = strlen(req->name);
/* Make sure to include terminating NUL byte */
name = kmemdup(req->name, name_len + 1, GFP_KERNEL);
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 13:11:14 +01:00
if (!name)
goto err;
binder: prevent UAF for binderfs devices II commit f0fe2c0f050d31babcad7d65f1d550d462a40064 upstream. This is a necessary follow up to the first fix I proposed and we merged in 2669b8b0c79 ("binder: prevent UAF for binderfs devices"). I have been overly optimistic that the simple fix I proposed would work. But alas, ihold() + iput() won't work since the inodes won't survive the destruction of the superblock. So all we get with my prior fix is a different race with a tinier race-window but it doesn't solve the issue. Fwiw, the problem lies with generic_shutdown_super(). It even has this cozy Al-style comment: if (!list_empty(&sb->s_inodes)) { printk("VFS: Busy inodes after unmount of %s. " "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); } On binder_release(), binder_defer_work(proc, BINDER_DEFERRED_RELEASE) is called which punts the actual cleanup operation to a workqueue. At some point, binder_deferred_func() will be called which will end up calling binder_deferred_release() which will retrieve and cleanup the binder_context attach to this struct binder_proc. If we trace back where this binder_context is attached to binder_proc we see that it is set in binder_open() and is taken from the struct binder_device it is associated with. This obviously assumes that the struct binder_device that context is attached to is _never_ freed. While that might be true for devtmpfs binder devices it is most certainly wrong for binderfs binder devices. So, assume binder_open() is called on a binderfs binder devices. We now stash away the struct binder_context associated with that struct binder_devices: proc->context = &binder_dev->context; /* binderfs stashes devices in i_private */ if (is_binderfs_device(nodp)) { binder_dev = nodp->i_private; info = nodp->i_sb->s_fs_info; binder_binderfs_dir_entry_proc = info->proc_log_dir; } else { . . . proc->context = &binder_dev->context; Now let's assume that the binderfs instance for that binder devices is shutdown via umount() and/or the mount namespace associated with it goes away. As long as there is still an fd open for that binderfs binder device things are fine. But let's assume we now close the last fd for that binderfs binder device. Now binder_release() is called and punts to the workqueue. Assume that the workqueue has quite a bit of stuff to do and doesn't get to cleaning up the struct binder_proc and the associated struct binder_context with it for that binderfs binder device right away. In the meantime, the VFS is killing the super block and is ultimately calling sb->evict_inode() which means it will call binderfs_evict_inode() which does: static void binderfs_evict_inode(struct inode *inode) { struct binder_device *device = inode->i_private; struct binderfs_info *info = BINDERFS_I(inode); clear_inode(inode); if (!S_ISCHR(inode->i_mode) || !device) return; mutex_lock(&binderfs_minors_mutex); --info->device_count; ida_free(&binderfs_minors, device->miscdev.minor); mutex_unlock(&binderfs_minors_mutex); kfree(device->context.name); kfree(device); } thereby freeing the struct binder_device including struct binder_context. Now the workqueue finally has time to get around to cleaning up struct binder_proc and is now trying to access the associate struct binder_context. Since it's already freed it will OOPs. Fix this by introducing a refounct on binder devices. This is an alternative fix to 51d8a7eca677 ("binder: prevent UAF read in print_binder_transaction_log_entry()"). Fixes: 3ad20fe393b3 ("binder: implement binderfs") Fixes: 2669b8b0c798 ("binder: prevent UAF for binderfs devices") Fixes: 03e2e07e3814 ("binder: Make transaction_log available in binderfs") Related : 51d8a7eca677 ("binder: prevent UAF read in print_binder_transaction_log_entry()") Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Link: https://lore.kernel.org/r/20200303164340.670054-1-christian.brauner@ubuntu.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-03-03 17:43:40 +01:00
refcount_set(&device->ref, 1);
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 13:11:14 +01:00
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;
if (userp && copy_to_user(userp, req, sizeof(*req))) {
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 13:11:14 +01:00
ret = -EFAULT;
goto err;
}
root = sb->s_root;
inode_lock(d_inode(root));
/* look it up */
dentry = lookup_one_len(name, root, name_len);
if (IS_ERR(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 13:11:14 +01:00
inode_unlock(d_inode(root));
ret = PTR_ERR(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 13:11:14 +01:00
goto err;
}
if (d_really_is_positive(dentry)) {
/* already exists */
dput(dentry);
inode_unlock(d_inode(root));
ret = -EEXIST;
goto err;
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 13:11:14 +01:00
}
inode->i_private = device;
binderfs: switch from d_add() to d_instantiate() In a previous commit we switched from a d_alloc_name() + d_lookup() combination to setup a new dentry and find potential duplicates to the more idiomatic lookup_one_len(). As far as I understand, this also means we need to switch from d_add() to d_instantiate() since lookup_one_len() will create a new dentry when it doesn't find an existing one and add the new dentry to the hash queues. So we only need to call d_instantiate() to connect the dentry to the inode and turn it into a positive dentry. If we were to use d_add() we sure see stack traces like the following indicating that adding the same dentry twice over the same inode: [ 744.441889] CPU: 4 PID: 2849 Comm: landscape-sysin Not tainted 5.0.0-rc1-brauner-binderfs #243 [ 744.441889] Hardware name: Dell DCS XS24-SC2 /XS24-SC2 , BIOS S59_3C20 04/07/2011 [ 744.441889] RIP: 0010:__d_lookup_rcu+0x76/0x190 [ 744.441889] Code: 89 75 c0 49 c1 e9 20 49 89 fd 45 89 ce 41 83 e6 07 42 8d 04 f5 00 00 00 00 89 45 c8 eb 0c 48 8b 1b 48 85 db 0f 84 81 00 00 00 <44> 8b 63 fc 4c 3b 6b 10 75 ea 48 83 7b 08 00 74 e3 41 83 e4 fe 41 [ 744.441889] RSP: 0018:ffffb8c984e27ad0 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 [ 744.441889] RAX: 0000000000000038 RBX: ffff9407ef770c08 RCX: ffffb8c980011000 [ 744.441889] RDX: ffffb8c984e27b54 RSI: ffffb8c984e27ce0 RDI: ffff9407e6689600 [ 744.441889] RBP: ffffb8c984e27b28 R08: ffffb8c984e27ba4 R09: 0000000000000007 [ 744.441889] R10: ffff9407e5c4f05c R11: 973f3eb9d84a94e5 R12: 0000000000000002 [ 744.441889] R13: ffff9407e6689600 R14: 0000000000000007 R15: 00000007bfef7a13 [ 744.441889] FS: 00007f0db13bb740(0000) GS:ffff9407f3b00000(0000) knlGS:0000000000000000 [ 744.441889] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 744.441889] CR2: 00007f0dacc51024 CR3: 000000032961a000 CR4: 00000000000006e0 [ 744.441889] Call Trace: [ 744.441889] lookup_fast+0x53/0x300 [ 744.441889] walk_component+0x49/0x350 [ 744.441889] ? inode_permission+0x63/0x1a0 [ 744.441889] link_path_walk.part.33+0x1bc/0x5a0 [ 744.441889] ? path_init+0x190/0x310 [ 744.441889] path_lookupat+0x95/0x210 [ 744.441889] filename_lookup+0xb6/0x190 [ 744.441889] ? __check_object_size+0xb8/0x1b0 [ 744.441889] ? strncpy_from_user+0x50/0x1a0 [ 744.441889] user_path_at_empty+0x36/0x40 [ 744.441889] ? user_path_at_empty+0x36/0x40 [ 744.441889] vfs_statx+0x76/0xe0 [ 744.441889] __do_sys_newstat+0x3d/0x70 [ 744.441889] __x64_sys_newstat+0x16/0x20 [ 744.441889] do_syscall_64+0x5a/0x120 [ 744.441889] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 744.441889] RIP: 0033:0x7f0db0ec2775 [ 744.441889] Code: 00 00 00 75 05 48 83 c4 18 c3 e8 26 55 02 00 66 0f 1f 44 00 00 83 ff 01 48 89 f0 77 30 48 89 c7 48 89 d6 b8 04 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 03 f3 c3 90 48 8b 15 e1 b6 2d 00 f7 d8 64 89 [ 744.441889] RSP: 002b:00007ffc36bc9388 EFLAGS: 00000246 ORIG_RAX: 0000000000000004 [ 744.441889] RAX: ffffffffffffffda RBX: 00007ffc36bc9300 RCX: 00007f0db0ec2775 [ 744.441889] RDX: 00007ffc36bc9400 RSI: 00007ffc36bc9400 RDI: 00007f0dad26f050 [ 744.441889] RBP: 0000000000c0bc60 R08: 0000000000000000 R09: 0000000000000001 [ 744.441889] R10: 0000000000000000 R11: 0000000000000246 R12: 00007ffc36bc9400 [ 744.441889] R13: 0000000000000001 R14: 00000000ffffff9c R15: 0000000000c0bc60 Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Christian Brauner <christian@brauner.io> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-01-21 11:48:08 +01:00
d_instantiate(dentry, 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 13:11:14 +01:00
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 12:32:18 +01:00
--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 13:11:14 +01:00
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 12:32:18 +01:00
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 13:11:14 +01:00
clear_inode(inode);
if (!S_ISCHR(inode->i_mode) || !device)
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 13:11:14 +01:00
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 12:32:18 +01:00
--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 13:11:14 +01:00
ida_free(&binderfs_minors, device->miscdev.minor);
mutex_unlock(&binderfs_minors_mutex);
binder: prevent UAF for binderfs devices II commit f0fe2c0f050d31babcad7d65f1d550d462a40064 upstream. This is a necessary follow up to the first fix I proposed and we merged in 2669b8b0c79 ("binder: prevent UAF for binderfs devices"). I have been overly optimistic that the simple fix I proposed would work. But alas, ihold() + iput() won't work since the inodes won't survive the destruction of the superblock. So all we get with my prior fix is a different race with a tinier race-window but it doesn't solve the issue. Fwiw, the problem lies with generic_shutdown_super(). It even has this cozy Al-style comment: if (!list_empty(&sb->s_inodes)) { printk("VFS: Busy inodes after unmount of %s. " "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); } On binder_release(), binder_defer_work(proc, BINDER_DEFERRED_RELEASE) is called which punts the actual cleanup operation to a workqueue. At some point, binder_deferred_func() will be called which will end up calling binder_deferred_release() which will retrieve and cleanup the binder_context attach to this struct binder_proc. If we trace back where this binder_context is attached to binder_proc we see that it is set in binder_open() and is taken from the struct binder_device it is associated with. This obviously assumes that the struct binder_device that context is attached to is _never_ freed. While that might be true for devtmpfs binder devices it is most certainly wrong for binderfs binder devices. So, assume binder_open() is called on a binderfs binder devices. We now stash away the struct binder_context associated with that struct binder_devices: proc->context = &binder_dev->context; /* binderfs stashes devices in i_private */ if (is_binderfs_device(nodp)) { binder_dev = nodp->i_private; info = nodp->i_sb->s_fs_info; binder_binderfs_dir_entry_proc = info->proc_log_dir; } else { . . . proc->context = &binder_dev->context; Now let's assume that the binderfs instance for that binder devices is shutdown via umount() and/or the mount namespace associated with it goes away. As long as there is still an fd open for that binderfs binder device things are fine. But let's assume we now close the last fd for that binderfs binder device. Now binder_release() is called and punts to the workqueue. Assume that the workqueue has quite a bit of stuff to do and doesn't get to cleaning up the struct binder_proc and the associated struct binder_context with it for that binderfs binder device right away. In the meantime, the VFS is killing the super block and is ultimately calling sb->evict_inode() which means it will call binderfs_evict_inode() which does: static void binderfs_evict_inode(struct inode *inode) { struct binder_device *device = inode->i_private; struct binderfs_info *info = BINDERFS_I(inode); clear_inode(inode); if (!S_ISCHR(inode->i_mode) || !device) return; mutex_lock(&binderfs_minors_mutex); --info->device_count; ida_free(&binderfs_minors, device->miscdev.minor); mutex_unlock(&binderfs_minors_mutex); kfree(device->context.name); kfree(device); } thereby freeing the struct binder_device including struct binder_context. Now the workqueue finally has time to get around to cleaning up struct binder_proc and is now trying to access the associate struct binder_context. Since it's already freed it will OOPs. Fix this by introducing a refounct on binder devices. This is an alternative fix to 51d8a7eca677 ("binder: prevent UAF read in print_binder_transaction_log_entry()"). Fixes: 3ad20fe393b3 ("binder: implement binderfs") Fixes: 2669b8b0c798 ("binder: prevent UAF for binderfs devices") Fixes: 03e2e07e3814 ("binder: Make transaction_log available in binderfs") Related : 51d8a7eca677 ("binder: prevent UAF read in print_binder_transaction_log_entry()") Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Link: https://lore.kernel.org/r/20200303164340.670054-1-christian.brauner@ubuntu.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-03-03 17:43:40 +01:00
if (refcount_dec_and_test(&device->ref)) {
kfree(device->context.name);
kfree(device);
}
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 13:11:14 +01:00
}
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 12:32:18 +01:00
/**
* 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, *stats;
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 12:32:18 +01:00
opts->max = BINDERFS_MAX_MINOR;
opts->stats_mode = STATS_NONE;
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 12:32:18 +01:00
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;
case Opt_stats_mode:
if (!capable(CAP_SYS_ADMIN))
return -EINVAL;
stats = match_strdup(&args[0]);
if (!stats)
return -ENOMEM;
if (strcmp(stats, "global") != 0) {
kfree(stats);
return -EINVAL;
}
opts->stats_mode = STATS_GLOBAL;
kfree(stats);
break;
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 12:32:18 +01:00
default:
pr_err("Invalid mount options\n");
return -EINVAL;
}
}
return 0;
}
static int binderfs_remount(struct super_block *sb, int *flags, char *data)
{
int prev_stats_mode, ret;
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 12:32:18 +01:00
struct binderfs_info *info = sb->s_fs_info;
prev_stats_mode = info->mount_opts.stats_mode;
ret = binderfs_parse_mount_opts(data, &info->mount_opts);
if (ret)
return ret;
if (prev_stats_mode != info->mount_opts.stats_mode) {
pr_err("Binderfs stats mode cannot be changed during a remount\n");
info->mount_opts.stats_mode = prev_stats_mode;
return -EINVAL;
}
return 0;
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 12:32:18 +01:00
}
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);
if (info->mount_opts.stats_mode == STATS_GLOBAL)
seq_printf(seq, ",stats=global");
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 12:32:18 +01:00
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 13:11:14 +01:00
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 12:32:18 +01:00
.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 13:11:14 +01:00
};
static inline bool is_binderfs_control_device(const struct dentry *dentry)
{
struct binderfs_info *info = dentry->d_sb->s_fs_info;
return info->control_dentry == 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 13:11:14 +01:00
static int binderfs_rename(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
if (is_binderfs_control_device(old_dentry) ||
is_binderfs_control_device(new_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 13:11:14 +01:00
return -EPERM;
return simple_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
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 13:11:14 +01:00
}
static int binderfs_unlink(struct inode *dir, struct dentry *dentry)
{
if (is_binderfs_control_device(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 13:11:14 +01:00
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;
#if defined(CONFIG_IPC_NS)
bool use_reserve = (info->ipc_ns == &init_ipc_ns);
#else
bool use_reserve = true;
#endif
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 13:11:14 +01:00
device = kzalloc(sizeof(*device), GFP_KERNEL);
if (!device)
return -ENOMEM;
/* 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,
use_reserve ? BINDERFS_MAX_MINOR :
BINDERFS_MAX_MINOR_CAPPED,
GFP_KERNEL);
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 13:11:14 +01:00
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;
binderfs: use refcount for binder control devices too [ Upstream commit 211b64e4b5b6bd5fdc19cd525c2cc9a90e6b0ec9 ] Binderfs binder-control devices are cleaned up via binderfs_evict_inode too() which will use refcount_dec_and_test(). However, we missed to set the refcount for binderfs binder-control devices and so we underflowed when the binderfs instance got unmounted. Pretty obvious oversight and should have been part of the more general UAF fix. The good news is that having test cases (suprisingly) helps. Technically, we could detect that we're about to cleanup the binder-control dentry in binderfs_evict_inode() and then simply clean it up. But that makes the assumption that the binder driver itself will never make use of a binderfs binder-control device after the binderfs instance it belongs to has been unmounted and the superblock for it been destroyed. While it is unlikely to ever come to this let's be on the safe side. Performance-wise this also really doesn't matter since the binder-control device is only every really when creating the binderfs filesystem or creating additional binder devices. Both operations are pretty rare. Fixes: f0fe2c0f050d ("binder: prevent UAF for binderfs devices II") Link: https://lore.kernel.org/r/CA+G9fYusdfg7PMfC9Xce-xLT7NiyKSbgojpK35GOm=Pf9jXXrA@mail.gmail.com Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org> Cc: stable@vger.kernel.org Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Todd Kjos <tkjos@google.com> Link: https://lore.kernel.org/r/20200311105309.1742827-1-christian.brauner@ubuntu.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-03-11 11:53:09 +01:00
refcount_set(&device->ref, 1);
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 13:11:14 +01:00
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);
return 0;
out:
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 struct inode *binderfs_make_inode(struct super_block *sb, int mode)
{
struct inode *ret;
ret = new_inode(sb);
if (ret) {
ret->i_ino = iunique(sb, BINDERFS_MAX_MINOR + INODE_OFFSET);
ret->i_mode = mode;
ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret);
}
return ret;
}
static struct dentry *binderfs_create_dentry(struct dentry *parent,
const char *name)
{
struct dentry *dentry;
dentry = lookup_one_len(name, parent, strlen(name));
if (IS_ERR(dentry))
return dentry;
/* Return error if the file/dir already exists. */
if (d_really_is_positive(dentry)) {
dput(dentry);
return ERR_PTR(-EEXIST);
}
return dentry;
}
void binderfs_remove_file(struct dentry *dentry)
{
struct inode *parent_inode;
parent_inode = d_inode(dentry->d_parent);
inode_lock(parent_inode);
if (simple_positive(dentry)) {
dget(dentry);
simple_unlink(parent_inode, dentry);
d_delete(dentry);
dput(dentry);
}
inode_unlock(parent_inode);
}
struct dentry *binderfs_create_file(struct dentry *parent, const char *name,
const struct file_operations *fops,
void *data)
{
struct dentry *dentry;
struct inode *new_inode, *parent_inode;
struct super_block *sb;
parent_inode = d_inode(parent);
inode_lock(parent_inode);
dentry = binderfs_create_dentry(parent, name);
if (IS_ERR(dentry))
goto out;
sb = parent_inode->i_sb;
new_inode = binderfs_make_inode(sb, S_IFREG | 0444);
if (!new_inode) {
dput(dentry);
dentry = ERR_PTR(-ENOMEM);
goto out;
}
new_inode->i_fop = fops;
new_inode->i_private = data;
d_instantiate(dentry, new_inode);
fsnotify_create(parent_inode, dentry);
out:
inode_unlock(parent_inode);
return dentry;
}
static struct dentry *binderfs_create_dir(struct dentry *parent,
const char *name)
{
struct dentry *dentry;
struct inode *new_inode, *parent_inode;
struct super_block *sb;
parent_inode = d_inode(parent);
inode_lock(parent_inode);
dentry = binderfs_create_dentry(parent, name);
if (IS_ERR(dentry))
goto out;
sb = parent_inode->i_sb;
new_inode = binderfs_make_inode(sb, S_IFDIR | 0755);
if (!new_inode) {
dput(dentry);
dentry = ERR_PTR(-ENOMEM);
goto out;
}
new_inode->i_fop = &simple_dir_operations;
new_inode->i_op = &simple_dir_inode_operations;
set_nlink(new_inode, 2);
d_instantiate(dentry, new_inode);
inc_nlink(parent_inode);
fsnotify_mkdir(parent_inode, dentry);
out:
inode_unlock(parent_inode);
return dentry;
}
static int init_binder_logs(struct super_block *sb)
{
struct dentry *binder_logs_root_dir, *dentry, *proc_log_dir;
struct binderfs_info *info;
int ret = 0;
binder_logs_root_dir = binderfs_create_dir(sb->s_root,
"binder_logs");
if (IS_ERR(binder_logs_root_dir)) {
ret = PTR_ERR(binder_logs_root_dir);
goto out;
}
dentry = binderfs_create_file(binder_logs_root_dir, "stats",
&binder_stats_fops, NULL);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto out;
}
dentry = binderfs_create_file(binder_logs_root_dir, "state",
&binder_state_fops, NULL);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto out;
}
dentry = binderfs_create_file(binder_logs_root_dir, "transactions",
&binder_transactions_fops, NULL);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto out;
}
dentry = binderfs_create_file(binder_logs_root_dir,
"transaction_log",
&binder_transaction_log_fops,
&binder_transaction_log);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto out;
}
dentry = binderfs_create_file(binder_logs_root_dir,
"failed_transaction_log",
&binder_transaction_log_fops,
&binder_transaction_log_failed);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto out;
}
proc_log_dir = binderfs_create_dir(binder_logs_root_dir, "proc");
if (IS_ERR(proc_log_dir)) {
ret = PTR_ERR(proc_log_dir);
goto out;
}
info = sb->s_fs_info;
info->proc_log_dir = proc_log_dir;
out:
return ret;
}
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 13:11:14 +01:00
static int binderfs_fill_super(struct super_block *sb, void *data, int silent)
{
int ret;
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 13:11:14 +01:00
struct binderfs_info *info;
struct inode *inode = NULL;
struct binderfs_device device_info = { 0 };
const char *name;
size_t len;
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 13:11:14 +01:00
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;
sb->s_fs_info = kzalloc(sizeof(struct binderfs_info), GFP_KERNEL);
if (!sb->s_fs_info)
return -ENOMEM;
info = sb->s_fs_info;
info->ipc_ns = get_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 13:11:14 +01:00
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 12:32:18 +01:00
ret = binderfs_parse_mount_opts(data, &info->mount_opts);
if (ret)
return ret;
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 12:32:18 +01:00
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 13:11:14 +01:00
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;
inode = new_inode(sb);
if (!inode)
return -ENOMEM;
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 13:11:14 +01:00
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)
return -ENOMEM;
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 13:11:14 +01:00
ret = binderfs_binder_ctl_create(sb);
if (ret)
return ret;
name = binder_devices_param;
for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
strscpy(device_info.name, name, len + 1);
ret = binderfs_binder_device_create(inode, NULL, &device_info);
if (ret)
return ret;
name += len;
if (*name == ',')
name++;
}
if (info->mount_opts.stats_mode == STATS_GLOBAL)
return init_binder_logs(sb);
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 13:11:14 +01:00
}
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 15:05:41 +01:00
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 13:11:14 +01:00
}
static void binderfs_kill_super(struct super_block *sb)
{
struct binderfs_info *info = sb->s_fs_info;
kill_litter_super(sb);
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 13:11:14 +01:00
if (info && info->ipc_ns)
put_ipc_ns(info->ipc_ns);
kfree(info);
}
static struct file_system_type binder_fs_type = {
.name = "binder",
.mount = binderfs_mount,
.kill_sb = binderfs_kill_super,
.fs_flags = FS_USERNS_MOUNT,
};
int __init init_binderfs(void)
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 13:11:14 +01:00
{
int ret;
const char *name;
size_t len;
/* Verify that the default binderfs device names are valid. */
name = binder_devices_param;
for (len = strcspn(name, ","); len > 0; len = strcspn(name, ",")) {
if (len > BINDERFS_MAX_NAME)
return -E2BIG;
name += len;
if (*name == ',')
name++;
}
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 13:11:14 +01:00
/* 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;
}