[PATCH v2] Bluetooth: Really fix registering hci with duplicate name

[PATCH v2] Bluetooth: Really fix registering hci with duplicate name

[Sasha Levin]

Commit fc50744 ("Bluetooth: Fix registering hci with duplicate name") didn't
fully fix the duplicate naming issue with devices, and duplicate device names
could still be created:

[  142.484097] device: 'hci1': device_add
[...]
[  150.545263] device: 'hci1': device_add
[  150.550128] kobject: 'hci1' (ffff880014cc4e58): kobject_add_internal: parent: 'bluetooth', set: 'devices'
[  150.558979] ------------[ cut here ]------------
[  150.561438] WARNING: at fs/sysfs/dir.c:529 sysfs_add_one+0xb0/0xd0()
[  150.572974] Hardware name: Bochs
[  150.580502] sysfs: cannot create duplicate filename '/devices/virtual/bluetooth/hci1'
[  150.584444] Pid: 7563, comm: trinity-child1 Tainted: G        W    3.4.0-next-20120524-sasha #296
[...]

Instead of the weird logic and the attempt at keeping the device list sorted,
just use an IDA.

Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
---

Changes from v1:

 - Address comments by Marcel.
 - Remove errornous mutex lock.

 net/bluetooth/hci_core.c |   41 ++++++++++++++++++++++++-----------------
 1 files changed, 24 insertions(+), 17 deletions(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 9c586fb..440329b 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -26,6 +26,7 @@
 /* Bluetooth HCI core. */
 
 #include <linux/export.h>
+#include <linux/idr.h>
 
 #include <linux/rfkill.h>
 
@@ -46,6 +47,9 @@ DEFINE_RWLOCK(hci_dev_list_lock);
 LIST_HEAD(hci_cb_list);
 DEFINE_RWLOCK(hci_cb_list_lock);
 
+/* HCI ID Numbering */
+static DEFINE_IDA(hci_index_ida);
+
 /* ---- HCI notifications ---- */
 
 static void hci_notify(struct hci_dev *hdev, int event)
@@ -1689,37 +1693,35 @@ EXPORT_SYMBOL(hci_free_dev);
 /* Register HCI device */
 int hci_register_dev(struct hci_dev *hdev)
 {
-	struct list_head *head, *p;
 	int id, error;
 
 	if (!hdev->open || !hdev->close)
 		return -EINVAL;
 
-	write_lock(&hci_dev_list_lock);
-
 	/* Do not allow HCI_AMP devices to register at index 0,
 	 * so the index can be used as the AMP controller ID.
 	 */
-	id = (hdev->dev_type == HCI_BREDR) ? 0 : 1;
-	head = &hci_dev_list;
-
-	/* Find first available device id */
-	list_for_each(p, &hci_dev_list) {
-		int nid = list_entry(p, struct hci_dev, list)->id;
-		if (nid > id)
-			break;
-		if (nid == id)
-			id++;
-		head = p;
+	switch (hdev->dev_type) {
+	case HCI_BREDR:
+		id = ida_simple_get(&hci_index_ida, 0, 0, GFP_KERNEL);
+		break;
+	case HCI_AMP:
+		id = ida_simple_get(&hci_index_ida, 1, 0, GFP_KERNEL);
+		break;
+	default:
+		return -EINVAL;
 	}
 
+	if (id < 0)
+		return id;
+
 	sprintf(hdev->name, "hci%d", id);
 	hdev->id = id;
 
 	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
 
-	list_add(&hdev->list, head);
-
+	write_lock(&hci_dev_list_lock);
+	list_add(&hdev->list, &hci_dev_list);
 	write_unlock(&hci_dev_list_lock);
 
 	hdev->workqueue = alloc_workqueue(hdev->name, WQ_HIGHPRI | WQ_UNBOUND |
@@ -1755,6 +1757,7 @@ int hci_register_dev(struct hci_dev *hdev)
 err_wqueue:
 	destroy_workqueue(hdev->workqueue);
 err:
+	ida_simple_remove(&hci_index_ida, hdev->id);
 	write_lock(&hci_dev_list_lock);
 	list_del(&hdev->list);
 	write_unlock(&hci_dev_list_lock);
@@ -1766,12 +1769,14 @@ EXPORT_SYMBOL(hci_register_dev);
 /* Unregister HCI device */
 void hci_unregister_dev(struct hci_dev *hdev)
 {
-	int i;
+	int i, id;
 
 	BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
 
 	set_bit(HCI_UNREGISTER, &hdev->dev_flags);
 
+	id = hdev->id;
+
 	write_lock(&hci_dev_list_lock);
 	list_del(&hdev->list);
 	write_unlock(&hci_dev_list_lock);
@@ -1812,6 +1817,8 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	hci_dev_unlock(hdev);
 
 	hci_dev_put(hdev);
+
+	ida_simple_remove(&hci_index_ida, id);
 }
 EXPORT_SYMBOL(hci_unregister_dev);
 
-- 
1.7.8.6

Re: [PATCH v2] Bluetooth: Really fix registering hci with duplicate name

[Marcel Holtmann]

Hi Sasha,

> Commit fc50744 ("Bluetooth: Fix registering hci with duplicate name") didn't
> fully fix the duplicate naming issue with devices, and duplicate device names
> could still be created:
> 
> [  142.484097] device: 'hci1': device_add
> [...]
> [  150.545263] device: 'hci1': device_add
> [  150.550128] kobject: 'hci1' (ffff880014cc4e58): kobject_add_internal: parent: 'bluetooth', set: 'devices'
> [  150.558979] ------------[ cut here ]------------
> [  150.561438] WARNING: at fs/sysfs/dir.c:529 sysfs_add_one+0xb0/0xd0()
> [  150.572974] Hardware name: Bochs
> [  150.580502] sysfs: cannot create duplicate filename '/devices/virtual/bluetooth/hci1'
> [  150.584444] Pid: 7563, comm: trinity-child1 Tainted: G        W    3.4.0-next-20120524-sasha #296
> [...]
> 
> Instead of the weird logic and the attempt at keeping the device list sorted,
> just use an IDA.
> 
> Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
> ---
> 
> Changes from v1:
> 
>  - Address comments by Marcel.
>  - Remove errornous mutex lock.
> 
>  net/bluetooth/hci_core.c |   41 ++++++++++++++++++++++++-----------------
>  1 files changed, 24 insertions(+), 17 deletions(-)

thanks for addressing this. Patch has been applied to bluetooth-next
tree.

Regards

Marcel

Re: [PATCH v2] Bluetooth: Really fix registering hci with duplicate name

[Andrei Emeltchenko]

Hi,

On Mon, May 28, 2012 at 05:47:48AM +0200, Marcel Holtmann wrote:
> Hi Sasha,
> 
> > Commit fc50744 ("Bluetooth: Fix registering hci with duplicate name") didn't
> > fully fix the duplicate naming issue with devices, and duplicate device names
> > could still be created:
> > 
> > [  142.484097] device: 'hci1': device_add
> > [...]
> > [  150.545263] device: 'hci1': device_add
> > [  150.550128] kobject: 'hci1' (ffff880014cc4e58): kobject_add_internal: parent: 'bluetooth', set: 'devices'
> > [  150.558979] ------------[ cut here ]------------
> > [  150.561438] WARNING: at fs/sysfs/dir.c:529 sysfs_add_one+0xb0/0xd0()
> > [  150.572974] Hardware name: Bochs
> > [  150.580502] sysfs: cannot create duplicate filename '/devices/virtual/bluetooth/hci1'
> > [  150.584444] Pid: 7563, comm: trinity-child1 Tainted: G        W    3.4.0-next-20120524-sasha #296
> > [...]
> > 
> > Instead of the weird logic and the attempt at keeping the device list sorted,
> > just use an IDA.
> > 
> > Signed-off-by: Sasha Levin <levinsasha928-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> > ---
> > 
> > Changes from v1:
> > 
> >  - Address comments by Marcel.
> >  - Remove errornous mutex lock.
> > 
> >  net/bluetooth/hci_core.c |   41 ++++++++++++++++++++++++-----------------
> >  1 files changed, 24 insertions(+), 17 deletions(-)
> 
> thanks for addressing this. Patch has been applied to bluetooth-next
> tree.

The patch looks OK but I start to notice kmemleak messages like
shown below:

...
unreferenced object 0xf46e4ed8 (size 148):
  comm "modprobe", pid 656, jiffies 4294900233 (age 4661.940s)
  hex dump (first 32 bytes):
    00 00 00 00 40 4e 6e f4 00 00 00 00 00 00 00 00  ....@Nn.........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<c154dfcc>] kmemleak_alloc+0x3c/0xa0
    [<c1132c7a>] kmem_cache_alloc+0x14a/0x190
    [<c12af2dd>] idr_pre_get+0x5d/0x80
    [<c12af3e5>] ida_pre_get+0x15/0x90
    [<c12af497>] ida_simple_get+0x37/0xe0
    [<f8369b79>] 0xf8369b79
    [<f81be63e>] 0xf81be63e
    [<c13f2a5e>] usb_probe_interface+0xce/0x210
    [<c13733cb>] driver_probe_device+0x8b/0x370
    [<c1373749>] __driver_attach+0x99/0xa0
    [<c1371902>] bus_for_each_dev+0x42/0x70
    [<c1372ea1>] driver_attach+0x21/0x30
    [<c1372a47>] bus_add_driver+0x1c7/0x2e0
    [<c1373bf6>] driver_register+0x66/0x110
    [<c13f1acb>] usb_register_driver+0x7b/0x140
    [<f8005017>] 0xf8005017
unreferenced object 0xf454c260 (size 148):
  comm "modprobe", pid 656, jiffies 4294900233 (age 4661.940s)
  hex dump (first 32 bytes):
    00 00 00 00 d8 4e 6e f4 00 00 00 00 00 00 00 00  .....Nn.........
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<c154dfcc>] kmemleak_alloc+0x3c/0xa0
    [<c1132c7a>] kmem_cache_alloc+0x14a/0x190
    [<c12af2dd>] idr_pre_get+0x5d/0x80
    [<c12af3e5>] ida_pre_get+0x15/0x90
    [<c12af497>] ida_simple_get+0x37/0xe0
    [<f8369b79>] 0xf8369b79
    [<f81be63e>] 0xf81be63e
    [<c13f2a5e>] usb_probe_interface+0xce/0x210
    [<c13733cb>] driver_probe_device+0x8b/0x370
    [<c1373749>] __driver_attach+0x99/0xa0
    [<c1371902>] bus_for_each_dev+0x42/0x70
    [<c1372ea1>] driver_attach+0x21/0x30
    [<c1372a47>] bus_add_driver+0x1c7/0x2e0
    [<c1373bf6>] driver_register+0x66/0x110
    [<c13f1acb>] usb_register_driver+0x7b/0x140
    [<f8005017>] 0xf8005017
...

Best regards 
Andrei Emeltchenko