From mboxrd@z Thu Jan 1 00:00:00 1970 From: Kevin Hilman Subject: Re: [PATCH] gpio/omap: fix irq loss while in idle with debounce on Date: Tue, 26 Jun 2012 21:11:08 -0500 Message-ID: <87y5n9tsg3.fsf@ti.com> References: <1339873285-8700-1-git-send-email-notasas@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from na3sys009aog133.obsmtp.com ([74.125.149.82]:60668 "EHLO na3sys009aog133.obsmtp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751087Ab2F0CLM (ORCPT ); Tue, 26 Jun 2012 22:11:12 -0400 Received: by gglu4 with SMTP id u4so553089ggl.19 for ; Tue, 26 Jun 2012 19:11:00 -0700 (PDT) In-Reply-To: <1339873285-8700-1-git-send-email-notasas@gmail.com> (Grazvydas Ignotas's message of "Sat, 16 Jun 2012 22:01:25 +0300") Sender: linux-omap-owner@vger.kernel.org List-Id: linux-omap@vger.kernel.org To: Grazvydas Ignotas Cc: linux-omap@vger.kernel.org, Grant Likely , Linus Walleij Grazvydas Ignotas writes: > It seems that currently GPIO module is not working correctly during idle > when debounce is enabled - the system almost never responds to button > presses (observed on OMAP3530 ES2.1 and OMAP3630 ES1.2 pandora boards). > Even though wakeups are probably working, it seems that the GPIO module > itself is unable to detect input events and generate interrupts. > OMAP35x TRM also states that: > "If the debounce clock is inactive, the debounce cell gates all > input signals and thus cannot be used." > > So whenever we are disabling debounce clocks (for PM or other reasons), > be sure the module's debounce feature is disabled too. > > Cc: Kevin Hilman > Signed-off-by: Grazvydas Ignotas This looks right, thanks for the patch. I will queue it up for v3.6 and get it some broader testing before sending to Grant. Kevin > --- > drivers/gpio/gpio-omap.c | 10 ++++++++++ > 1 files changed, 10 insertions(+), 0 deletions(-) > > diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c > index c4ed172..ff213e7 100644 > --- a/drivers/gpio/gpio-omap.c > +++ b/drivers/gpio/gpio-omap.c > @@ -174,12 +174,22 @@ static inline void _gpio_dbck_enable(struct gpio_bank *bank) > if (bank->dbck_enable_mask && !bank->dbck_enabled) { > clk_enable(bank->dbck); > bank->dbck_enabled = true; > + > + __raw_writel(bank->dbck_enable_mask, > + bank->base + bank->regs->debounce_en); > } > } > > static inline void _gpio_dbck_disable(struct gpio_bank *bank) > { > if (bank->dbck_enable_mask && bank->dbck_enabled) { > + /* > + * Disable debounce before cutting it's clock. If debounce is > + * enabled but the clock is not, GPIO module seems to be unable > + * to detect events and generate interrupts at least on OMAP3. > + */ > + __raw_writel(0, bank->base + bank->regs->debounce_en); > + > clk_disable(bank->dbck); > bank->dbck_enabled = false; > }