Skip to contentSkip to conversation

HID: Support Varmilo Keyboards' media hotkeys

PATCH Superseded Frank Yang 2 participants 5 messages Jul 29, 2020 – Oct 23, 2020 HID

lore
Share & tools
lore

Frank Yang

author
#0 lore raw

PATCH 1/1 HID: Support Varmilo Keyboards' media hotkeys

The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor.

More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary.

Some notes:

* There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant.

* The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem?

---
 drivers/hid/Kconfig       |  6 ++++
 drivers/hid/Makefile      |  1 +
 drivers/hid/hid-ids.h     |  2 ++
 drivers/hid/hid-varmilo.c | 58 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 67 insertions(+)
 create mode 100644 drivers/hid/hid-varmilo.c
drivers/hid/Kconfig +6 -0
index 443c5cbbde04..c9f0c9b79158 100644
@@ -441,6 +441,12 @@ config HID_WALTOP
 	---help---
 	Support for Waltop tablets.
 
+config HID_VARMILO
+	tristate "Varmilo Keyboards"
+	depends on HID
+	help
+	  Support for Varmilo keyboards.
+
 config HID_VIEWSONIC
 	tristate "ViewSonic/Signotec"
 	depends on HID
drivers/hid/Makefile +1 -0
index d8ea4b8c95af..e90a98090452 100644
@@ -124,6 +124,7 @@ obj-$(CONFIG_HID_LED)		+= hid-led.o
 obj-$(CONFIG_HID_XINMO)		+= hid-xinmo.o
 obj-$(CONFIG_HID_ZEROPLUS)	+= hid-zpff.o
 obj-$(CONFIG_HID_ZYDACRON)	+= hid-zydacron.o
+obj-$(CONFIG_HID_VARMILO)	+= hid-varmilo.o
 obj-$(CONFIG_HID_VIEWSONIC)	+= hid-viewsonic.o
 
 wacom-objs			:= wacom_wac.o wacom_sys.o
drivers/hid/hid-ids.h +2 -0
index 874fc3791f3b..955be22fc69d 100644
@@ -1189,6 +1189,8 @@
 #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0709	0x0709
 #define USB_DEVICE_ID_UNITEC_USB_TOUCH_0A19	0x0a19
 
+#define USB_DEVICE_ID_VARMILO_VA104M_07B1   0X07b1
+
 #define USB_VENDOR_ID_VELLEMAN		0x10cf
 #define USB_DEVICE_ID_VELLEMAN_K8055_FIRST	0x5500
 #define USB_DEVICE_ID_VELLEMAN_K8055_LAST	0x5503
drivers/hid/hid-varmilo.c new file +58 -0

58 lines not on this page · raw message

Signature · 1 line
2.17.1
maintainer
#1 lore raw
Quoted 25 lines · Frank Yang

The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor.

More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary.

Some notes:

* There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant.

* The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem?

Quoted 6 lines
---
 drivers/hid/Kconfig       |  6 ++++
 drivers/hid/Makefile      |  1 +
 drivers/hid/hid-ids.h     |  2 ++
 drivers/hid/hid-varmilo.c | 58 +++++++++++++++++++++++++++++++++++++++

Hi Frank,

thanks for the patch.

Given the fact that the device presents itself with CYPRESS VID (0x04b4, 'officially' assigned to cypress), can we avoid creating extra driver, and rather extend hid-cypress.c with this quirk, please?

Thanks,

Signature · 2 lines
Jiri Kosina
SUSE Labs
author
#2 lore raw
Quoted 36 lines · Jiri Kosina
Quoted 25 lines · Frank Yang

The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor.

More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary.

Some notes:

* There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant.

* The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem?

Quoted 6 lines
---
 drivers/hid/Kconfig       |  6 ++++
 drivers/hid/Makefile      |  1 +
 drivers/hid/hid-ids.h     |  2 ++
 drivers/hid/hid-varmilo.c | 58 +++++++++++++++++++++++++++++++++++++++

Hi Frank,

Quoted 12 lines

thanks for the patch.

Given the fact that the device presents itself with CYPRESS VID (0x04b4, 'officially' assigned to cypress), can we avoid creating extra driver, and rather extend hid-cypress.c with this quirk, please?

Thanks,

Signature · 2 lines
Jiri Kosina
SUSE Labs

Hi Jiri,

thanks for your comment.

As you stated, I have sent the updated patch which extends hid-cypress.c instead of creating new driver.

Thanks,

Frank

author
#3 lore raw

PATCH v2 1/1 HID: Support Varmilo Keyboards' media hotkeys

In reply to Frank Yang

The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor.

More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary.

Some notes:

* There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant.

* The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem?

---
Changes since v1:
- Extend hid-cypress.c instead of creating new drivers for varmilo, since the device reports the VID of Cypress (0x04b4). Suggested by: Jiri Kosina <[email protected]>

 drivers/hid/hid-cypress.c | 44 ++++++++++++++++++++++++++++++++++-----
 drivers/hid/hid-ids.h     |  2 ++
 2 files changed, 41 insertions(+), 5 deletions(-)
drivers/hid/hid-cypress.c +39 -5
index a50ba4a4a1d7..b88f889b3932 100644
@@ -23,19 +23,17 @@
 #define CP_2WHEEL_MOUSE_HACK		0x02
 #define CP_2WHEEL_MOUSE_HACK_ON		0x04
 
+#define VA_INVAL_LOGICAL_BOUNDARY	0x08
+
 /*
  * Some USB barcode readers from cypress have usage min and usage max in
  * the wrong order
  */
-static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc,
 		unsigned int *rsize)
 {
-	unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
 	unsigned int i;
 
-	if (!(quirks & CP_RDESC_SWAPPED_MIN_MAX))
-		return rdesc;
-
 	if (*rsize < 4)
 		return rdesc;
 
@@ -48,6 +46,40 @@ static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 	return rdesc;
 }
 
+static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize)
+{
+	/*
+	 * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly
+	 * reports Logical Minimum of its Consumer Control device as 572
+	 * (0x02 0x3c). Fix this by setting its Logical Minimum to zero.
+	 */
+	if (*rsize == 25 &&
+			rdesc[0] == 0x05 && rdesc[1] == 0x0c &&
+			rdesc[2] == 0x09 && rdesc[3] == 0x01 &&
+			rdesc[6] == 0x19 && rdesc[7] == 0x00 &&
+			rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) {
+		hid_info(hdev,
+			 "fixing up varmilo VA104M consumer control report descriptor\n");
+		rdesc[12] = 0x00;
+		rdesc[13] = 0x00;
+	}
+	return rdesc;
+}
+
+static __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int *rsize)
+{
+	unsigned long quirks = (unsigned long)hid_get_drvdata(hdev);
+
+	if (quirks & CP_RDESC_SWAPPED_MIN_MAX)
+		rdesc = cp_rdesc_fixup(hdev, rdesc, rsize);
+	if (quirks & VA_INVAL_LOGICAL_BOUNDARY)
+		rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize);
+
+	return rdesc;
+}
+
 static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi,
 		struct hid_field *field, struct hid_usage *usage,
 		unsigned long **bit, int *max)
@@ -128,6 +160,8 @@ static const struct hid_device_id cp_devices[] = {
 		.driver_data = CP_RDESC_SWAPPED_MIN_MAX },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE),
 		.driver_data = CP_2WHEEL_MOUSE_HACK },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1),
+		.driver_data = VA_INVAL_LOGICAL_BOUNDARY },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, cp_devices);
drivers/hid/hid-ids.h +2 -0
index 874fc3791f3b..dbca98da8aa5 100644
@@ -331,6 +331,8 @@
 #define USB_DEVICE_ID_CYPRESS_BARCODE_4	0xed81
 #define USB_DEVICE_ID_CYPRESS_TRUETOUCH	0xc001
 
+#define USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1   0X07b1
+
 #define USB_VENDOR_ID_DATA_MODUL	0x7374
 #define USB_VENDOR_ID_DATA_MODUL_EASYMAXTOUCH	0x1201
 
Signature · 1 line
2.17.1
maintainer
#4 lore raw
Quoted 6 lines · Frank Yang

The Varmilo VA104M Keyboard (04b4:07b1, reported as Varmilo Z104M) exposes media control hotkeys as a USB HID consumer control device, but these keys do not work in the current (5.8-rc1) kernel due to the incorrect HID report descriptor. Fix the problem by modifying the internal HID report descriptor.

Quoted 6 lines

More specifically, the keyboard report descriptor specifies the logical boundary as 572~10754 (0x023c ~ 0x2a02) while the usage boundary is specified as 0~10754 (0x00 ~ 0x2a02). This results in an incorrect interpretation of input reports, causing inputs to be ignored. By setting the Logical Minimum to zero, we align the logical boundary with the Usage ID boundary.

Thanks, I have now applied the patch.

Quoted 11 lines

Some notes:

* There seem to be multiple variants of the VA104M keyboard. This patch specifically targets 04b4:07b1 variant.

* The device works out-of-the-box on Windows platform with the generic consumer control device driver (hidserv.inf). This suggests that Windows either ignores the Logical Minimum/Logical Maximum or interprets the Usage ID assignment differently from the linux implementation; Maybe there are other devices out there that only works on Windows due to this problem?

This is not the first time I came across this issue, but I'd find it rather suprising if wondows HID driver would just be completely ignoring LogicalMin/LogicalMax values ... perhaps it treats some values as specific?

Signature · 2 lines
Jiri Kosina
SUSE Labs