Skip to contentSkip to conversation

Allow any MIDI endpoint to drive use of interrupt transfer on newer Roland devices

PATCH RESEND In review [email protected] 2 participants 6 messages Oct 11, 2015

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH RESEND 1/1 Allow any MIDI endpoint to drive use of interrupt transfer on newer Roland devices

From: "Keith A. Milner" <[email protected]>

This patch enables interrupt transfer mode for MIDI ports on newer Boss/Roland devices such as the GT-100/001 which support interrupt transfer on both IN and OUT MIDI endpoints. Previously this wasn't being enabled for these devices as the code was specifically looking for the scenario where the IN endpoint supported interrupt transfer and the OUT endpoint was bulk transfer. Newer devices support interrupt transfer for both endpoints.

This has been tested on Boss devices GT-001, BR-80 and JS-8 and Roland VS-20.

It would benefit from some regresison testing with other devices if possible.

sound/usb/midi.c +7 -2
index b901f46..d50c649 100644
@@ -1860,9 +1860,14 @@ static void snd_usbmidi_switch_roland_altsetting(struct snd_usb_midi* umidi)
 
 	hostif = &intf->altsetting[1];
 	intfd = get_iface_desc(hostif);
+       /* If either or both of the endpoints support interrupt transfer,
+        * then use the alternate setting
+        */
 	if (intfd->bNumEndpoints != 2 ||
-	    (get_endpoint(hostif, 0)->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) != USB_ENDPOINT_XFER_BULK ||
-	    (get_endpoint(hostif, 1)->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) != USB_ENDPOINT_XFER_INT)
+	     !((get_endpoint(hostif, 0)->bmAttributes
+			& USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT ||
+	      (get_endpoint(hostif, 1)->bmAttributes
+			& USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT))
 		return;
 
 	snd_printdd(KERN_INFO "switching to altsetting %d with int ep\n",
Signature · 1 line
1.9.1
#1 lore raw
Quoted 11 lines · On Sun, 11 Oct 2015 16:19:48 +0200, [email protected] wrote:

From: "Keith A. Milner" <[email protected]>

This patch enables interrupt transfer mode for MIDI ports on newer Boss/Roland devices such as the GT-100/001 which support interrupt transfer on both IN and OUT MIDI endpoints. Previously this wasn't being enabled for these devices as the code was specifically looking for the scenario where the IN endpoint supported interrupt transfer and the OUT endpoint was bulk transfer. Newer devices support interrupt transfer for both endpoints.

Quoted 7 lines

This has been tested on Boss devices GT-001, BR-80 and JS-8 and Roland VS-20.

It would benefit from some regresison testing with other devices if possible.

Thanks, now it looks much better.

But the patch didn't apply cleanly to the latest kernel, so I had to adjust manually. At the next time, please try to align with the latest kernel tree.

Takashi

Quoted 25 lines
sound/usb/midi.c +7 -2
index b901f46..d50c649 100644
@@ -1860,9 +1860,14 @@ static void snd_usbmidi_switch_roland_altsetting(struct snd_usb_midi* umidi)
 
 	hostif = &intf->altsetting[1];
 	intfd = get_iface_desc(hostif);
+       /* If either or both of the endpoints support interrupt transfer,
+        * then use the alternate setting
+        */
 	if (intfd->bNumEndpoints != 2 ||
-	    (get_endpoint(hostif, 0)->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) != USB_ENDPOINT_XFER_BULK ||
-	    (get_endpoint(hostif, 1)->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) != USB_ENDPOINT_XFER_INT)
+	     !((get_endpoint(hostif, 0)->bmAttributes
+			& USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT ||
+	      (get_endpoint(hostif, 1)->bmAttributes
+			& USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT))
 		return;
 
 	snd_printdd(KERN_INFO "switching to altsetting %d with int ep\n",
Signature · 1 line
1.9.1
#2 lore raw
Quoted 5 lines · On Sunday 11 Oct 2015 18:21:48 Takashi Iwai wrote:

Thanks, now it looks much better.

But the patch didn't apply cleanly to the latest kernel, so I had to adjust manually. At the next time, please try to align with the latest kernel tree.

Thanks.

Which tree should I be using for this? I rebased against the git repository described in http://www.alsa-project.org/main/index.php/GIT_Server#Occasional_Developers

Is this not the correct on?

Cheers,

Keith

#3 lore raw
Quoted 9 lines · Keith A. Milner
Quoted 5 lines · On Sunday 11 Oct 2015 18:21:48 Takashi Iwai wrote:

Thanks, now it looks much better.

But the patch didn't apply cleanly to the latest kernel, so I had to adjust manually. At the next time, please try to align with the latest kernel tree.

Quoted 6 lines

Thanks.

Which tree should I be using for this? I rebased against the git repository described in http://www.alsa-project.org/main/index.php/GIT_Server#Occasional_Developers

Is this not the correct on?

The information looks obsoleted... For sending a patch, please base either on the latest Linus tree or my sound git tree for-next branch:
git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git

In anyway, I already applied your patch, so you don't have to rebase the patch again.

Takashi

#4 lore raw
Quoted 4 lines · On Sunday 11 Oct 2015 19:44:53 Takashi Iwai wrote:

The information looks obsoleted... For sending a patch, please base either on the latest Linus tree or my sound git tree for-next branch:
git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git

Thanks. This may explain some of the issues I had.

Is there a way to get this documentation updated to reflect the current situation?

Quoted 2 lines

In anyway, I already applied your patch, so you don't have to rebase the patch again.

OK, I will start with a fresh tree. I have some other small patches I'm looking to contribute.

Cheers,

Keith

#5 lore raw
Quoted 11 lines · Keith A. Milner
Quoted 4 lines · On Sunday 11 Oct 2015 19:44:53 Takashi Iwai wrote:

The information looks obsoleted... For sending a patch, please base either on the latest Linus tree or my sound git tree for-next branch:
git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git

Thanks. This may explain some of the issues I had.

Is there a way to get this documentation updated to reflect the current situation?

It's a Wiki, so everyone should be able to edit :)

Quoted 5 lines
Quoted 2 lines

In anyway, I already applied your patch, so you don't have to rebase the patch again.

OK, I will start with a fresh tree. I have some other small patches I'm looking to contribute.

Great, I'm looking forward to seeing them.

Takashi