On Thu, Jul 02, 2015 at 02:55:34PM +0200, Krzysztof Opasiak wrote: > > > On 07/02/2015 02:45 PM, Michal Nazarewicz wrote: > >>On Thu, Jul 02, 2015 at 12:51:54PM +0200, Gregory CLEMENT wrote: > >>>When I use configs to configure the mass storage function for the > >>>gadget, and when the device is plugged under Windows, then the > >>>partition that I expose is well managed, but I also see 7 other gadget > >>>in the device manager with error. > >>> > >>>This seven bogus gadget seems to be the 7 other LUN that are not > >>>used. Indeed if I apply this dirty patch: > >>> > >>>diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c > >>>index 3cc109f..2b4ae98 100644 > >>>--- a/drivers/usb/gadget/function/f_mass_storage.c > >>>+++ b/drivers/usb/gadget/function/f_mass_storage.c > >>>@@ -3511,7 +3511,8 @@ static struct usb_function_instance *fsg_alloc_inst(void) > >>> rc = PTR_ERR(opts->common); > >>> goto release_opts; > >>> } > >>>- rc = fsg_common_set_nluns(opts->common, FSG_MAX_LUNS); > >>>+// rc = fsg_common_set_nluns(opts->common, FSG_MAX_LUNS); > >>>+ rc = fsg_common_set_nluns(opts->common, 1); > >>> if (rc) > >>> goto release_opts; > >>> > >>>Then there is no more gadget error under Windows. As the value of > >>>FSG_MAX_LUNS is 8 and in my configuration I only use one partition, > >>>then it makes sens that I see 7 bogus gadgets. > >>> > >>>I also saw that in the legacy driver, it was possible to modify the > >>>number of LUN using the module parameter file_count. > > > >On Thu, Jul 02 2015, Felipe Balbi wrote: > >>This has been reported. Michal was working on a fix, but the patch > >>hasn't been applied yet. > > > >I’ve came up with [1], which you should feel free to test, but then > >Krzysztof came along with [2], which among other things addressed the > >LUN count issue, and I kind of stopped working on the issue waiting for > >his follow up. > > Sorry that it took so much time. I have been quite busy with some other > things. I will send fixed version of that series in a few hours. I'm taking Michal's patch as a quick fix for the -rc though. That patch is simple enough to get in and solves the issue at hand. -- balbi
Attachment:
signature.asc
Description: Digital signature
