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>

1 files changed, 8 insertions, 17 deletions

diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 210940bd0457..cdfc87629efb 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -79,6 +79,7 @@
 #include <asm/cacheflush.h>
 
 #include "binder_alloc.h"
+#include "binder_internal.h"
 #include "binder_trace.h"
 
 static HLIST_HEAD(binder_deferred_list);
@@ -249,20 +250,6 @@ static struct binder_transaction_log_entry *binder_transaction_log_add(
 	return e;
 }
 
-struct binder_context {
-	struct binder_node *binder_context_mgr_node;
-	struct mutex context_mgr_node_lock;
-
-	kuid_t binder_context_mgr_uid;
-	const char *name;
-};
-
-struct binder_device {
-	struct hlist_node hlist;
-	struct miscdevice miscdev;
-	struct binder_context context;
-};
-
 /**
  * struct binder_work - work enqueued on a worklist
  * @entry:             node enqueued on list
@@ -5024,8 +5011,12 @@ static int binder_open(struct inode *nodp, struct file *filp)
 	proc->tsk = current->group_leader;
 	INIT_LIST_HEAD(&proc->todo);
 	proc->default_priority = task_nice(current);
-	binder_dev = container_of(filp->private_data, struct binder_device,
-				  miscdev);
+	/* binderfs stashes devices in i_private */
+	if (is_binderfs_device(nodp))
+		binder_dev = nodp->i_private;
+	else
+		binder_dev = container_of(filp->private_data,
+					  struct binder_device, miscdev);
 	proc->context = &binder_dev->context;
 	binder_alloc_init(&proc->alloc);
 
@@ -5816,7 +5807,7 @@ static int transaction_log_show(struct seq_file *m, void *unused)
 	return 0;
 }
 
-static const struct file_operations binder_fops = {
+const struct file_operations binder_fops = {
 	.owner = THIS_MODULE,
 	.poll = binder_poll,
 	.unlocked_ioctl = binder_ioctl,