| Message ID | 20210528140446.278076-1-thomas.petazzoni@bootlin.com |
|---|---|
| State | New |
| Headers | show |
| Series | usb: musb: fix MUSB_QUIRK_B_DISCONNECT_99 handling | expand |
On 28/05/2021 16:04:46+0200, Thomas Petazzoni wrote: > In commit 92af4fc6ec33 ("usb: musb: Fix suspend with devices > connected for a64"), the logic to support the > MUSB_QUIRK_B_DISCONNECT_99 quirk was modified to only conditionally > schedule the musb->irq_work delayed work. > > This commit badly breaks ECM Gadget on AM335X. Indeed, with this > commit, one can observe massive packet loss: > > $ ping 192.168.0.100 > ... > 15 packets transmitted, 3 received, 80% packet loss, time 14316ms > > Reverting this commit brings back a properly functioning ECM > Gadget. An analysis of the commit seems to indicate that a mistake was > made: the previous code was not falling through into the > MUSB_QUIRK_B_INVALID_VBUS_91, but now it is, unless the condition is > taken. > > Changing the logic to be as it was before the problematic commit *and* > only conditionally scheduling musb->irq_work resolves the regression: > > $ ping 192.168.0.100 > ... > 64 packets transmitted, 64 received, 0% packet loss, time 64475ms > > Fixes: 92af4fc6ec33 ("usb: musb: Fix suspend with devices connected for a64") > Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com> Tested-by: Alexandre Belloni <alexandre.belloni@bootlin.com> > Cc: stable@vger.kernel.org > --- > drivers/usb/musb/musb_core.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c > index 8f09a387b773..4c8f0112481f 100644 > --- a/drivers/usb/musb/musb_core.c > +++ b/drivers/usb/musb/musb_core.c > @@ -2009,9 +2009,8 @@ static void musb_pm_runtime_check_session(struct musb *musb) > schedule_delayed_work(&musb->irq_work, > msecs_to_jiffies(1000)); > musb->quirk_retries--; > - break; > } > - fallthrough; > + break; > case MUSB_QUIRK_B_INVALID_VBUS_91: > if (musb->quirk_retries && !musb->flush_irq_work) { > musb_dbg(musb, > -- > 2.31.1 >
* Alexandre Belloni <alexandre.belloni@bootlin.com> [210528 15:35]: > On 28/05/2021 16:04:46+0200, Thomas Petazzoni wrote: > > In commit 92af4fc6ec33 ("usb: musb: Fix suspend with devices > > connected for a64"), the logic to support the > > MUSB_QUIRK_B_DISCONNECT_99 quirk was modified to only conditionally > > schedule the musb->irq_work delayed work. > > > > This commit badly breaks ECM Gadget on AM335X. Indeed, with this > > commit, one can observe massive packet loss: > > > > $ ping 192.168.0.100 > > ... > > 15 packets transmitted, 3 received, 80% packet loss, time 14316ms > > > > Reverting this commit brings back a properly functioning ECM > > Gadget. An analysis of the commit seems to indicate that a mistake was > > made: the previous code was not falling through into the > > MUSB_QUIRK_B_INVALID_VBUS_91, but now it is, unless the condition is > > taken. > > > > Changing the logic to be as it was before the problematic commit *and* > > only conditionally scheduling musb->irq_work resolves the regression: > > > > $ ping 192.168.0.100 > > ... > > 64 packets transmitted, 64 received, 0% packet loss, time 64475ms > > > > Fixes: 92af4fc6ec33 ("usb: musb: Fix suspend with devices connected for a64") > > Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com> > Tested-by: Alexandre Belloni <alexandre.belloni@bootlin.com> Ouch, sorry about that one. And thanks for fixing it: Acked-by: Tony Lindgren <tony@atomide.com>
On Fri, May 28, 2021 at 04:04:46PM +0200, Thomas Petazzoni wrote: > In commit 92af4fc6ec33 ("usb: musb: Fix suspend with devices > connected for a64"), the logic to support the > MUSB_QUIRK_B_DISCONNECT_99 quirk was modified to only conditionally > schedule the musb->irq_work delayed work. > > This commit badly breaks ECM Gadget on AM335X. Indeed, with this > commit, one can observe massive packet loss: > > $ ping 192.168.0.100 > ... > 15 packets transmitted, 3 received, 80% packet loss, time 14316ms > > Reverting this commit brings back a properly functioning ECM > Gadget. An analysis of the commit seems to indicate that a mistake was > made: the previous code was not falling through into the > MUSB_QUIRK_B_INVALID_VBUS_91, but now it is, unless the condition is > taken. > > Changing the logic to be as it was before the problematic commit *and* > only conditionally scheduling musb->irq_work resolves the regression: > > $ ping 192.168.0.100 > ... > 64 packets transmitted, 64 received, 0% packet loss, time 64475ms > > Fixes: 92af4fc6ec33 ("usb: musb: Fix suspend with devices connected for a64") > Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com> > Cc: stable@vger.kernel.org > --- > drivers/usb/musb/musb_core.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c > index 8f09a387b773..4c8f0112481f 100644 > --- a/drivers/usb/musb/musb_core.c > +++ b/drivers/usb/musb/musb_core.c > @@ -2009,9 +2009,8 @@ static void musb_pm_runtime_check_session(struct musb *musb) > schedule_delayed_work(&musb->irq_work, > msecs_to_jiffies(1000)); > musb->quirk_retries--; > - break; > } > - fallthrough; > + break; > case MUSB_QUIRK_B_INVALID_VBUS_91: > if (musb->quirk_retries && !musb->flush_irq_work) { > musb_dbg(musb, > -- > 2.31.1 Tested-by: Drew Fustini <drew@beagleboard.org> This patches fixes the problem on the BeagleBone Black (AM3358) where the USB gadget interfaces would frequently reset. For example: configfs-gadget gadget: init rndis configfs-gadget gadget: RNDIS RX/TX early activation ... usb0: qlen 10 configfs-gadget gadget: rndis_open rndis_set_param_medium: 0 4259840 usb0: eth_start rndis_set_param_dev: configfs-gadget gadget: set_config: interface 2 (Mass Storage Function) requested delayed status configfs-gadget gadget: delayed_status count 1 configfs-gadget gadget: reset ncm control 3 configfs-gadget gadget: init ncm ctrl 3 configfs-gadget gadget: notify speed 425984000 configfs-gadget gadget: reset acm ttyGS0 configfs-gadget gadget: activate acm ttyGS0 configfs-gadget gadget: acm ttyGS0 serial state 0000 configfs-gadget gadget: usb_composite_setup_continue configfs-gadget gadget: usb_composite_setup_continue: Completing delayed status configfs-gadget gadget: rndis req21.00 v0000 i0000 l24 rndis_msg_parser: RNDIS_MSG_INIT configfs-gadget gadget: rndis reqa1.01 v0000 i0000 l1025 configfs-gadget gadget: rndis req21.00 v0000 i0000 l32 gen_ndis_query_resp: RNDIS_OID_GEN_PHYSICAL_MEDIUM configfs-gadget gadget: rndis reqa1.01 v0000 i0000 l1025 configfs-gadget gadget: rndis req21.00 v0000 i0000 l76 gen_ndis_query_resp: RNDIS_OID_802_3_PERMANENT_ADDRESS configfs-gadget gadget: rndis reqa1.01 v0000 i0000 l1025 configfs-gadget gadget: rndis req21.00 v0000 i0000 l32 gen_ndis_set_resp: RNDIS_OID_GEN_CURRENT_PACKET_FILTER 0000002d configfs-gadget gadget: rndis reqa1.01 v0000 i0000 l1025 configfs-gadget gadget: init ncm configfs-gadget gadget: activate ncm usb1: qlen 10 configfs-gadget gadget: ncm_open usb1: eth_start configfs-gadget gadget: reset ncm usb1: gether_disconnect configfs-gadget gadget: ncm reqa1.80 v0000 i0003 l28 configfs-gadget gadget: non-CRC mode selected configfs-gadget gadget: ncm req21.8a v0000 i0003 l0 configfs-gadget gadget: NCM16 selected configfs-gadget gadget: ncm req21.84 v0000 i0003 l0 configfs-gadget gadget: init ncm configfs-gadget gadget: activate ncm usb1: qlen 10 configfs-gadget gadget: ncm_open usb1: eth_start configfs-gadget gadget: acm ttyGS0 req21.20 v0000 i0005 l7 configfs-gadget gadget: notify speed 425984000 configfs-gadget gadget: notify connect true I have posted dmesg log without the patch [1] where this happens often and the dmesg log with the patch [2] where it does happen at all. Thank you for fixing this! Drew [1] https://gist.github.com/pdp7/bd61e5f78545de182605992254d3eeee [2] https://gist.github.com/pdp7/95b0f34fa1d423d4764984b400c562cf
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 8f09a387b773..4c8f0112481f 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2009,9 +2009,8 @@ static void musb_pm_runtime_check_session(struct musb *musb) schedule_delayed_work(&musb->irq_work, msecs_to_jiffies(1000)); musb->quirk_retries--; - break; } - fallthrough; + break; case MUSB_QUIRK_B_INVALID_VBUS_91: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb,
In commit 92af4fc6ec33 ("usb: musb: Fix suspend with devices connected for a64"), the logic to support the MUSB_QUIRK_B_DISCONNECT_99 quirk was modified to only conditionally schedule the musb->irq_work delayed work. This commit badly breaks ECM Gadget on AM335X. Indeed, with this commit, one can observe massive packet loss: $ ping 192.168.0.100 ... 15 packets transmitted, 3 received, 80% packet loss, time 14316ms Reverting this commit brings back a properly functioning ECM Gadget. An analysis of the commit seems to indicate that a mistake was made: the previous code was not falling through into the MUSB_QUIRK_B_INVALID_VBUS_91, but now it is, unless the condition is taken. Changing the logic to be as it was before the problematic commit *and* only conditionally scheduling musb->irq_work resolves the regression: $ ping 192.168.0.100 ... 64 packets transmitted, 64 received, 0% packet loss, time 64475ms Fixes: 92af4fc6ec33 ("usb: musb: Fix suspend with devices connected for a64") Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com> Cc: stable@vger.kernel.org --- drivers/usb/musb/musb_core.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)