Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933623AbbDPIFf (ORCPT ); Thu, 16 Apr 2015 04:05:35 -0400 Received: from cantor2.suse.de ([195.135.220.15]:41555 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752642AbbDPIEz (ORCPT ); Thu, 16 Apr 2015 04:04:55 -0400 From: NeilBrown To: Kishon Vijay Abraham I Date: Thu, 16 Apr 2015 18:03:04 +1000 Subject: [PATCH 1/6] phy: twl4030-usb: make runtime pm more reliable. Cc: Tony Lindgren , linux-kernel@vger.kernel.org, GTA04 owners , NeilBrown , Pavel Machek , linux-omap@vger.kernel.org Message-ID: <20150416080304.23307.91491.stgit@notabene.brown> In-Reply-To: <20150416075945.23307.24424.stgit@notabene.brown> References: <20150416075945.23307.24424.stgit@notabene.brown> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3238 Lines: 100 From: NeilBrown A construct like: if (pm_runtime_suspended(twl->dev)) pm_runtime_get_sync(twl->dev); is against the spirit of the runtime_pm interface as it makes the internal refcounting useless. In this case it is also racy, particularly as 'put_autosuspend' is used to drop a reference. When that happens a timer is started and the device is runtime-suspended after the timeout. If the above code runs in this window, the device will not be found to be suspended so no pm_runtime reference is taken. When the timer expires the device will be suspended, which is against the intention of the code. So be more direct is taking and dropping references. If twl->linkstat is VBUS_VALID or ID_GROUND, then hold a pm_runtime reference, otherwise don't. Define "cable_present()" to test for this condition. Tested-by: Tony Lindgren Signed-off-by: NeilBrown --- drivers/phy/phy-twl4030-usb.c | 29 ++++++++++++++++++++--------- 1 file changed, 20 insertions(+), 9 deletions(-) diff --git a/drivers/phy/phy-twl4030-usb.c b/drivers/phy/phy-twl4030-usb.c index bc42d6a8939f..3078f80bf520 100644 --- a/drivers/phy/phy-twl4030-usb.c +++ b/drivers/phy/phy-twl4030-usb.c @@ -144,6 +144,16 @@ #define PMBR1 0x0D #define GPIO_USB_4PIN_ULPI_2430C (3 << 0) +/* + * If VBUS is valid or ID is ground, then we know a + * cable is present and we need to be runtime-enabled + */ +static inline bool cable_present(enum omap_musb_vbus_id_status stat) +{ + return stat == OMAP_MUSB_VBUS_VALID || + stat == OMAP_MUSB_ID_GROUND; +} + struct twl4030_usb { struct usb_phy phy; struct device *dev; @@ -536,8 +546,10 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) mutex_lock(&twl->lock); if (status >= 0 && status != twl->linkstat) { + status_changed = + cable_present(twl->linkstat) != + cable_present(status); twl->linkstat = status; - status_changed = true; } mutex_unlock(&twl->lock); @@ -553,15 +565,11 @@ static irqreturn_t twl4030_usb_irq(int irq, void *_twl) * USB_LINK_VBUS state. musb_hdrc won't care until it * starts to handle softconnect right. */ - if ((status == OMAP_MUSB_VBUS_VALID) || - (status == OMAP_MUSB_ID_GROUND)) { - if (pm_runtime_suspended(twl->dev)) - pm_runtime_get_sync(twl->dev); + if (cable_present(status)) { + pm_runtime_get_sync(twl->dev); } else { - if (pm_runtime_active(twl->dev)) { - pm_runtime_mark_last_busy(twl->dev); - pm_runtime_put_autosuspend(twl->dev); - } + pm_runtime_mark_last_busy(twl->dev); + pm_runtime_put_autosuspend(twl->dev); } omap_musb_mailbox(status); } @@ -767,6 +775,9 @@ static int twl4030_usb_remove(struct platform_device *pdev) /* disable complete OTG block */ twl4030_usb_clear_bits(twl, POWER_CTRL, POWER_CTRL_OTG_ENAB); + + if (cable_present(twl->linkstat)) + pm_runtime_put_noidle(twl->dev); pm_runtime_mark_last_busy(twl->dev); pm_runtime_put(twl->dev); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/