From 2669b8b0c798fbe1a31d49e07aa33233d469ad9b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 21 Feb 2020 19:01:24 +0100 Subject: binder: prevent UAF for binderfs devices 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 holding an additional reference to the inode that is only released once the workqueue is done cleaning up struct binder_proc. This is an easy alternative to introducing separate refcounting on struct binder_device which we can always do later if it becomes necessary. This is an alternative fix to 51d8a7eca677 ("binder: prevent UAF read in print_binder_transaction_log_entry()"). Fixes: 3ad20fe393b3 ("binder: implement binderfs") 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 Acked-by: Todd Kjos Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/android/binder.c') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a6b2082c24f8..3069a0bad50f 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5221,7 +5221,7 @@ static int binder_open(struct inode *nodp, struct file *filp) proc->default_priority = task_nice(current); /* binderfs stashes devices in i_private */ if (is_binderfs_device(nodp)) { - binder_dev = nodp->i_private; + binder_dev = binderfs_device_get(nodp->i_private); info = nodp->i_sb->s_fs_info; binder_binderfs_dir_entry_proc = info->proc_log_dir; } else { @@ -5405,6 +5405,7 @@ static int binder_node_release(struct binder_node *node, int refs) static void binder_deferred_release(struct binder_proc *proc) { struct binder_context *context = proc->context; + struct binder_device *device; struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, active_transactions; @@ -5484,6 +5485,8 @@ static void binder_deferred_release(struct binder_proc *proc) outgoing_refs, active_transactions); binder_proc_dec_tmpref(proc); + device = container_of(proc->context, struct binder_device, context); + binderfs_device_put(device); } static void binder_deferred_func(struct work_struct *work) -- cgit From f0fe2c0f050d31babcad7d65f1d550d462a40064 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Tue, 3 Mar 2020 17:43:40 +0100 Subject: binder: prevent UAF for binderfs devices II 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 Acked-by: Todd Kjos Link: https://lore.kernel.org/r/20200303164340.670054-1-christian.brauner@ubuntu.com Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'drivers/android/binder.c') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 3069a0bad50f..e47c8a4c83db 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5221,13 +5221,14 @@ static int binder_open(struct inode *nodp, struct file *filp) proc->default_priority = task_nice(current); /* binderfs stashes devices in i_private */ if (is_binderfs_device(nodp)) { - binder_dev = binderfs_device_get(nodp->i_private); + binder_dev = nodp->i_private; info = nodp->i_sb->s_fs_info; binder_binderfs_dir_entry_proc = info->proc_log_dir; } else { binder_dev = container_of(filp->private_data, struct binder_device, miscdev); } + refcount_inc(&binder_dev->ref); proc->context = &binder_dev->context; binder_alloc_init(&proc->alloc); @@ -5422,6 +5423,12 @@ static void binder_deferred_release(struct binder_proc *proc) context->binder_context_mgr_node = NULL; } mutex_unlock(&context->context_mgr_node_lock); + device = container_of(proc->context, struct binder_device, context); + if (refcount_dec_and_test(&device->ref)) { + kfree(context->name); + kfree(device); + } + proc->context = NULL; binder_inner_proc_lock(proc); /* * Make sure proc stays alive after we @@ -5485,8 +5492,6 @@ static void binder_deferred_release(struct binder_proc *proc) outgoing_refs, active_transactions); binder_proc_dec_tmpref(proc); - device = container_of(proc->context, struct binder_device, context); - binderfs_device_put(device); } static void binder_deferred_func(struct work_struct *work) @@ -6080,6 +6085,7 @@ static int __init init_binder_device(const char *name) binder_device->miscdev.minor = MISC_DYNAMIC_MINOR; binder_device->miscdev.name = name; + refcount_set(&binder_device->ref, 1); binder_device->context.binder_context_mgr_uid = INVALID_UID; binder_device->context.name = name; mutex_init(&binder_device->context.context_mgr_node_lock); -- cgit