From b8a75eaddae9410767c7d95a1c5f3a547aae7b81 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 15 Mar 2020 18:34:49 +0100 Subject: [PATCH 1/2] HID: lg-g15: Do not fail the probe when we fail to disable F# emulation By default the G1-G12 keys on the Logitech gaming keyboards send F1 - F12 when in "generic HID" mode. The first thing the hid-lg-g15 driver does is disable this behavior. We have received a bugreport that this does not work when the keyboard is connected through an Aten KVM switch. Using a gaming keyboard with a KVM is a bit weird setup, but still we can try to fail a bit more gracefully here. On the G510 keyboards the same USB-interface which is used for the gaming keys is also used for the media-keys. Before this commit we would call hid_hw_stop() on failure to disable the F# emulation and then exit the probe method with an error code. This not only causes us to not handle the gaming-keys, but this also breaks the media keys which is a regression compared to the situation when these keyboards where handled by the generic hidinput driver. This commit changes the error handling to clear the hiddev drvdata (to disable our .raw_event handler) and then returning from the probe method with success. The net result of this is that, when connected through a KVM, things work as well as they did before the hid-lg-g15 driver was introduced. Fixes: ad4203f5a243 ("HID: lg-g15: Add support for the G510 keyboards' gaming keys") BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1806321 Signed-off-by: Hans de Goede Signed-off-by: Jiri Kosina --- drivers/hid/hid-lg-g15.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index 8a9268a5c66a..ad4b5412a9f4 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -803,8 +803,10 @@ static int lg_g15_probe(struct hid_device *hdev, const struct hid_device_id *id) } if (ret < 0) { - hid_err(hdev, "Error disabling keyboard emulation for the G-keys\n"); - goto error_hw_stop; + hid_err(hdev, "Error %d disabling keyboard emulation for the G-keys, falling back to generic hid-input driver\n", + ret); + hid_set_drvdata(hdev, NULL); + return 0; } /* Get initial brightness levels */ From 2e1b9e1edff7fe19d37f0a5993ac03c5389af809 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sat, 21 Mar 2020 07:40:48 +0100 Subject: [PATCH 2/2] HID: rmi: Simplify an error handling path in 'rmi_hid_read_block()' The 'RMI_READ_REQUEST_PENDING' bit is already cleared in the error handling path. There is no need to reset it twice. Signed-off-by: Christophe JAILLET Signed-off-by: Jiri Kosina --- drivers/hid/hid-rmi.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hid/hid-rmi.c b/drivers/hid/hid-rmi.c index 9ce22acdfaca..8cffa84c9650 100644 --- a/drivers/hid/hid-rmi.c +++ b/drivers/hid/hid-rmi.c @@ -217,7 +217,6 @@ static int rmi_hid_read_block(struct rmi_transport_dev *xport, u16 addr, ret = rmi_write_report(hdev, data->writeReport, data->output_report_size); if (ret != data->output_report_size) { - clear_bit(RMI_READ_REQUEST_PENDING, &data->flags); dev_err(&hdev->dev, "failed to write request output report (%d)\n", ret);