blktrace: fix debugfs use after free20200608-blktrace-fixes-v2

On commit 6ac93117ab00 ("blktrace: use existing disk debugfs directory")
merged on v4.12 Omar fixed the original blktrace code for request-based
drivers (multiqueue). This however left in place a possible crash, if you
happen to abuse blktrace while racing to remove / add a device.

We used to use asynchronous removal of the request_queue, and with that
the issue was easier to reproduce. Now that we have reverted to
synchronous removal of the request_queue, the issue is still possible to
reproduce, its however just a bit more difficult.

We essentially run two instances of break-blktrace which add/remove
a loop device, and setup a blktrace and just never tear the blktrace
down. We do this twice in parallel. This is easily reproduced with the
script run_0004.sh from break-blktrace [0].

We can end up with two types of panics each reflecting where we
race, one a failed blktrace setup:

[  252.426751] debugfs: Directory 'loop0' with parent 'block' already present!
[  252.432265] BUG: kernel NULL pointer dereference, address: 00000000000000a0
[  252.436592] #PF: supervisor write access in kernel mode
[  252.439822] #PF: error_code(0x0002) - not-present page
[  252.442967] PGD 0 P4D 0
[  252.444656] Oops: 0002 [#1] SMP NOPTI
[  252.446972] CPU: 10 PID: 1153 Comm: break-blktrace Tainted: G            E     5.7.0-rc2-next-20200420+ #164
[  252.452673] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
[  252.456343] RIP: 0010:down_write+0x15/0x40
[  252.458146] Code: eb ca e8 ae 22 8d ff cc cc cc cc cc cc cc cc cc cc cc cc
               cc cc 0f 1f 44 00 00 55 48 89 fd e8 52 db ff ff 31 c0 ba 01 00
               00 00 <f0> 48 0f b1 55 00 75 0f 48 8b 04 25 c0 8b 01 00 48 89
               45 08 5d
[  252.463638] RSP: 0018:ffffa626415abcc8 EFLAGS: 00010246
[  252.464950] RAX: 0000000000000000 RBX: ffff958c25f0f5c0 RCX: ffffff8100000000
[  252.466727] RDX: 0000000000000001 RSI: ffffff8100000000 RDI: 00000000000000a0
[  252.468482] RBP: 00000000000000a0 R08: 0000000000000000 R09: 0000000000000001
[  252.470014] R10: 0000000000000000 R11: ffff958d1f9227ff R12: 0000000000000000
[  252.471473] R13: ffff958c25ea5380 R14: ffffffff8cce15f1 R15: 00000000000000a0
[  252.473346] FS:  00007f2e69dee540(0000) GS:ffff958c2fc80000(0000) knlGS:0000000000000000
[  252.475225] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  252.476267] CR2: 00000000000000a0 CR3: 0000000427d10004 CR4: 0000000000360ee0
[  252.477526] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  252.478776] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  252.479866] Call Trace:
[  252.480322]  simple_recursive_removal+0x4e/0x2e0
[  252.481078]  ? debugfs_remove+0x60/0x60
[  252.481725]  ? relay_destroy_buf+0x77/0xb0
[  252.482662]  debugfs_remove+0x40/0x60
[  252.483518]  blk_remove_buf_file_callback+0x5/0x10
[  252.484328]  relay_close_buf+0x2e/0x60
[  252.484930]  relay_open+0x1ce/0x2c0
[  252.485520]  do_blk_trace_setup+0x14f/0x2b0
[  252.486187]  __blk_trace_setup+0x54/0xb0
[  252.486803]  blk_trace_ioctl+0x90/0x140
[  252.487423]  ? do_sys_openat2+0x1ab/0x2d0
[  252.488053]  blkdev_ioctl+0x4d/0x260
[  252.488636]  block_ioctl+0x39/0x40
[  252.489139]  ksys_ioctl+0x87/0xc0
[  252.489675]  __x64_sys_ioctl+0x16/0x20
[  252.490380]  do_syscall_64+0x52/0x180
[  252.491032]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

And the other on the device removal:

[  128.528940] debugfs: Directory 'loop0' with parent 'block' already present!
[  128.615325] BUG: kernel NULL pointer dereference, address: 00000000000000a0
[  128.619537] #PF: supervisor write access in kernel mode
[  128.622700] #PF: error_code(0x0002) - not-present page
[  128.625842] PGD 0 P4D 0
[  128.627585] Oops: 0002 [#1] SMP NOPTI
[  128.629871] CPU: 12 PID: 544 Comm: break-blktrace Tainted: G            E     5.7.0-rc2-next-20200420+ #164
[  128.635595] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
[  128.640471] RIP: 0010:down_write+0x15/0x40
[  128.643041] Code: eb ca e8 ae 22 8d ff cc cc cc cc cc cc cc cc cc cc cc cc
               cc cc 0f 1f 44 00 00 55 48 89 fd e8 52 db ff ff 31 c0 ba 01 00
               00 00 <f0> 48 0f b1 55 00 75 0f 65 48 8b 04 25 c0 8b 01 00 48 89
               45 08 5d
[  128.650180] RSP: 0018:ffffa9c3c05ebd78 EFLAGS: 00010246
[  128.651820] RAX: 0000000000000000 RBX: ffff8ae9a6370240 RCX: ffffff8100000000
[  128.653942] RDX: 0000000000000001 RSI: ffffff8100000000 RDI: 00000000000000a0
[  128.655720] RBP: 00000000000000a0 R08: 0000000000000002 R09: ffff8ae9afd2d3d0
[  128.657400] R10: 0000000000000056 R11: 0000000000000000 R12: 0000000000000000
[  128.659099] R13: 0000000000000000 R14: 0000000000000003 R15: 00000000000000a0
[  128.660500] FS:  00007febfd995540(0000) GS:ffff8ae9afd00000(0000) knlGS:0000000000000000
[  128.662204] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  128.663426] CR2: 00000000000000a0 CR3: 0000000420042003 CR4: 0000000000360ee0
[  128.664776] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  128.666022] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  128.667282] Call Trace:
[  128.667801]  simple_recursive_removal+0x4e/0x2e0
[  128.668663]  ? debugfs_remove+0x60/0x60
[  128.669368]  debugfs_remove+0x40/0x60
[  128.669985]  blk_trace_free+0xd/0x50
[  128.670593]  __blk_trace_remove+0x27/0x40
[  128.671274]  blk_trace_shutdown+0x30/0x40
[  128.671935]  blk_release_queue+0x95/0xf0
[  128.672589]  kobject_put+0xa5/0x1b0
[  128.673188]  disk_release+0xa2/0xc0
[  128.673786]  device_release+0x28/0x80
[  128.674376]  kobject_put+0xa5/0x1b0
[  128.674915]  loop_remove+0x39/0x50 [loop]
[  128.675511]  loop_control_ioctl+0x113/0x130 [loop]
[  128.676199]  ksys_ioctl+0x87/0xc0
[  128.676708]  __x64_sys_ioctl+0x16/0x20
[  128.677274]  do_syscall_64+0x52/0x180
[  128.677823]  entry_SYSCALL_64_after_hwframe+0x44/0xa9

The common theme here is:

debugfs: Directory 'loop0' with parent 'block' already present

This crash happens because of how blktrace uses the debugfs directory
where it places its files. Upon init we always create the same directory
which would be needed by blktrace but we only do this for make_request
drivers (multiqueue) block drivers, but never for request-based block
drivers. Furthermore, that directory is only created on init for the
entire disk. This means that if you use blktrace on a partition, we'll
always be creating a new directory regardless of whether or not you
are doing blktrace on a make_request driver (multiqueue) or a
request-based block drivers.

These directory creations are only associated with a path, and so
when a debugfs_remove() is called it removes everything in its way.
A device removal will remove all blktrace files, and so if a blktrace
is still present a cleanup of blktrace files later will end up trying
to remove dentries pointing to NULL.

We can fix the UAF by using a debugfs directory which moving forward
will always be accessible if debugfs is enabled for both make_request
drivers (multiqueue) and request-based block drivers, *and* for all
partitions upon creation. This ensures that removal of the directories
only happens on device removal and removes the race of the files
underneath an active blktrace.

We special-case a solution for scsi-generic as well which got blktrace
support added by Christof via commit 6da127ad0918 ("blktrace: Add
blktrace ioctls to SCSI generic devices") so upstream since v2.6.25.
scsi-generic drives use a character device, however behind the scenes
we have a scsi device with a request_queue. How this is used varies
by class of driver (TYPE_DISK, TYPE_TAPE, etc).  We simply create its
a scsi-generic dedicated debugfs_dir and have blktrace use that when
this interface is used.

This goes tested with:

  o nvme partitions
  o ISCSI with tgt, and blktracing against scsi-generic with:
    o block
    o tape
    o cdrom
    o media changer
  o blktests

This patch is part of the work which disputes the severity of
CVE-2019-19770 which shows this issue is not a core debugfs issue, but
a misuse of debugfs within blktace.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Nicolai Stange <nstange@suse.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: "James E.J. Bottomley" <jejb@linux.ibm.com>
Cc: yu kuai <yukuai3@huawei.com>
Reported-by: syzbot+603294af2d01acfdd6da@syzkaller.appspotmail.com
Fixes: 6ac93117ab00 ("blktrace: use existing disk debugfs directory")
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>

6 files changed, 32 insertions, 23 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index e9456a45ec1eba..06d060ea31c84b 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -48,9 +48,7 @@
 #include "blk-pm.h"
 #include "blk-rq-qos.h"
 
-#ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
-#endif
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
 EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
@@ -1817,9 +1815,7 @@ int __init blk_dev_init(void)
 	blk_requestq_cachep = kmem_cache_create("request_queue",
 			sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
 
-#ifdef CONFIG_DEBUG_FS
 	blk_debugfs_root = debugfs_create_dir("block", NULL);
-#endif
 
 	return 0;
 }
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index b3f2ba483992d2..bda9378eab9029 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -823,9 +823,6 @@ void blk_mq_debugfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
-	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
-					    blk_debugfs_root);
-
 	debugfs_create_files(q->debugfs_dir, q, blk_mq_debugfs_queue_attrs);
 
 	/*
@@ -856,9 +853,7 @@ void blk_mq_debugfs_register(struct request_queue *q)
 
 void blk_mq_debugfs_unregister(struct request_queue *q)
 {
-	debugfs_remove_recursive(q->debugfs_dir);
 	q->sched_debugfs_dir = NULL;
-	q->debugfs_dir = NULL;
 }
 
 static void blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 5d0fc165a03680..957a6f581d6c7e 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -11,6 +11,7 @@
 #include <linux/blktrace_api.h>
 #include <linux/blk-mq.h>
 #include <linux/blk-cgroup.h>
+#include <linux/debugfs.h>
 
 #include "blk.h"
 #include "blk-mq.h"
@@ -905,6 +906,7 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_trace_shutdown(q);
 
+	debugfs_remove_recursive(q->debugfs_dir);
 	if (queue_is_mq(q))
 		blk_mq_debugfs_unregister(q);
 
@@ -976,6 +978,9 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+					    blk_debugfs_root);
+
 	if (queue_is_mq(q)) {
 		__blk_mq_register_dev(dev, q);
 		blk_mq_debugfs_register(q);
diff --git a/block/blk.h b/block/blk.h
index 0a94ec68af32b1..8ba31be9e942af 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -12,9 +12,7 @@
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
 
-#ifdef CONFIG_DEBUG_FS
 extern struct dentry *blk_debugfs_root;
-#endif
 
 struct blk_flush_queue {
 	unsigned int		flush_queue_delayed:1;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 34a379ffc6f9dc..2aed23040931f7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -569,8 +569,8 @@ struct request_queue {
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
 
-#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*debugfs_dir;
+#ifdef CONFIG_BLK_DEBUG_FS
 	struct dentry		*sched_debugfs_dir;
 	struct dentry		*rqos_debugfs_dir;
 #endif
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index d63096d60383ab..57e2ac0da50eb8 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -488,9 +488,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
-
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -515,6 +512,32 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt)
 		return -ENOMEM;
 
+	/*
+	 * If we're working on a partition or scsi-generic devices, the
+	 * respective debugfs directory is not created for them on init, and so
+	 * we must create it for them. This is only used for blktrace purposes
+	 * for the lifetime of the blktrace.
+	 */
+	if ((bdev && bdev != bdev->bd_contains) || unlikely(!bdev)) {
+		dir = debugfs_create_dir(buts->name, blk_debugfs_root);
+		bt->dir = dir;
+	} else {
+		dir = q->debugfs_dir;
+	}
+
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
+		goto err;
+	}
+
+
 	ret = -ENOMEM;
 	bt->sequence = alloc_percpu(unsigned long);
 	if (!bt->sequence)
@@ -524,12 +547,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
-		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
-
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -565,8 +582,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;