[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAPTae5LOresaK3Epd4R_ifpx2kw21tubQDENg4OMrhJWsar-oA@mail.gmail.com>
Date: Tue, 13 Feb 2024 02:09:16 -0800
From: Badhri Jagan Sridharan <badhri@...gle.com>
To: Mark Brown <broonie@...nel.org>
Cc: Guenter Roeck <linux@...ck-us.net>, Heikki Krogerus <heikki.krogerus@...ux.intel.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>, Gábor Stefanik <netrolller.3d@...il.com>,
rdbabiera@...gle.com, amitsd@...gle.com, linux-usb@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] usb: typec: tpcm: Fix issues with power being removed
during reset
Hi Mark,
While HI-Zing CC pins disrupts power for batteryless devices, not
Hi-Zing CC pins would prevent clean error recovery for self powered
devices which is why "usb: typec: tcpm: fix cc role at port reset" was reverted.
Please note that the breakage in error recovery behavior is a
regression as well.
Hi-Zing CC pins would make the port partner recognize it as disconnect
and will result in bringup the connection back cleanly.
How about leveraging "self-powered" device tree property and Hi-Zing
CC pins only when using "self-powered" ?
This should help devices which don't have batteries while NOT regressing
the error recovery behavior for the self powered devices.
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -4897,7 +4897,11 @@ static void run_state_machine(struct tcpm_port *port)
break;
case PORT_RESET:
tcpm_reset_port(port);
- tcpm_set_cc(port, TYPEC_CC_OPEN);
+ if (port->self_powered)
+ tcpm_set_cc(port, TYPEC_CC_OPEN);
+ else
+ tcpm_set_cc(port, tcpm_default_state(port) ==
SNK_UNATTACHED ?
+ TYPEC_CC_RD : tcpm_rp_cc(port));
tcpm_set_state(port, PORT_RESET_WAIT_OFF,
PD_T_ERROR_RECOVERY);
Thanks,
Badhri
On Mon, Feb 12, 2024 at 10:42 AM Mark Brown <broonie@...nel.org> wrote:
>
> Since the merge of b717dfbf73e8 ("Revert "usb: typec: tcpm: fix
> cc role at port reset"") into mainline the LibreTech Renegade
> Elite/Firefly has died during boot, the main symptom observed in testing
> is a sudden stop in console output. Gábor Stefanik identified in review
> that the patch would cause power to be removed from devices without
> batteries (like this board), observing that while the patch is correct
> according to the spec this appears to be an oversight in the spec.
>
> Given that the change makes previously working systems unusable let's
> revert it, there was some discussion of identifying systems that have
> alternative power and implementing the standards conforming behaviour in
> only that case.
>
> Fixes: b717dfbf73e8 ("Revert "usb: typec: tcpm: fix cc role at port reset"")
> Signed-off-by: Mark Brown <broonie@...nel.org>
> ---
> drivers/usb/typec/tcpm/tcpm.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
> index f7d7daa60c8d..a0978ed1a257 100644
> --- a/drivers/usb/typec/tcpm/tcpm.c
> +++ b/drivers/usb/typec/tcpm/tcpm.c
> @@ -4876,7 +4876,8 @@ static void run_state_machine(struct tcpm_port *port)
> break;
> case PORT_RESET:
> tcpm_reset_port(port);
> - tcpm_set_cc(port, TYPEC_CC_OPEN);
> + tcpm_set_cc(port, tcpm_default_state(port) == SNK_UNATTACHED ?
> + TYPEC_CC_RD : tcpm_rp_cc(port));
> tcpm_set_state(port, PORT_RESET_WAIT_OFF,
> PD_T_ERROR_RECOVERY);
> break;
>
> ---
> base-commit: 841c35169323cd833294798e58b9bf63fa4fa1de
> change-id: 20240212-usb-fix-renegade-837d35cfc0c2
>
> Best regards,
> --
> Mark Brown <broonie@...nel.org>
>
Powered by blists - more mailing lists