From patchwork Sat Mar 23 23:57:16 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rafael Wysocki X-Patchwork-Id: 2325381 Return-Path: X-Original-To: patchwork-linux-acpi@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork1.kernel.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by patchwork1.kernel.org (Postfix) with ESMTP id 4000E3FC8A for ; Sat, 23 Mar 2013 23:49:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752471Ab3CWXt4 (ORCPT ); Sat, 23 Mar 2013 19:49:56 -0400 Received: from hydra.sisk.pl ([212.160.235.94]:37102 "EHLO hydra.sisk.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752457Ab3CWXtz (ORCPT ); Sat, 23 Mar 2013 19:49:55 -0400 Received: from vostro.rjw.lan (afcg217.neoplus.adsl.tpnet.pl [95.49.58.217]) by hydra.sisk.pl (Postfix) with ESMTPSA id 2612CE3F37; Sun, 24 Mar 2013 00:48:43 +0100 (CET) From: "Rafael J. Wysocki" To: ACPI Devel Maling List Cc: Linux PM list , LKML , Len Brown , Aaron Lu Subject: [PATCH] ACPI / PM: Fix potential problem in acpi_device_get_power() Date: Sun, 24 Mar 2013 00:57:16 +0100 Message-ID: <6380949.vJPdL9PvJh@vostro.rjw.lan> User-Agent: KMail/4.9.5 (Linux/3.9.0-rc3+; KDE/4.9.5; x86_64; ; ) MIME-Version: 1.0 Sender: linux-acpi-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-acpi@vger.kernel.org From: Rafael J. Wysocki Theoretically, in some situations acpi_device_get_power() may return an incorrect result, because the settings of the power resources depended on by the device may indicate a power state shallower than the actual power state of the device. Say that two devices, A and B, depend on two power resources, X and Y, in such a way that _PR0 for both A and B list both X and Y and _PR3 for both A and B list power resource Y alone. Also suppose that _PS0 and _PS3 are present for both A and B. Then, if devices A and B are initially in D0, power resources X and Y are initially "on" and their reference counters are equal to 2. To put device A into power state D3hot the kernel will decrement the reference counter of power resource X, but that power resource won't be turned off, because it is still in use by device B (its reference counter is equal to 1). Next, _PS3 will be executed for device A. Afterward the configuration of the power resources will indicate that device A is in power state D0 (both X and Y are "on"), but in fact it is in D3hot (because _PS3 has been executed for it). In that situation, if acpi_device_get_power() is called to get the power state of device A, it will first execute _PSC for it which should return 3. That will cause acpi_device_get_power() to run acpi_power_get_inferred_state() for device A and the resultant power state will be D0, which is incorrect. To fix that change acpi_device_get_power() to first execute acpi_power_get_inferred_state() for the given device (if it depends on power resources) and to evaluate _PSC for it subsequently, so that the result inferred from the power resources configuration can be amended by the _PSC return value. Signed-off-by: Rafael J. Wysocki --- drivers/acpi/device_pm.c | 39 ++++++++++++++++++++++++--------------- 1 file changed, 24 insertions(+), 15 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Index: linux-pm/drivers/acpi/device_pm.c =================================================================== --- linux-pm.orig/drivers/acpi/device_pm.c +++ linux-pm/drivers/acpi/device_pm.c @@ -145,27 +145,36 @@ int acpi_device_get_power(struct acpi_de } /* - * Get the device's power state either directly (via _PSC) or - * indirectly (via power resources). + * Get the device's power state from power resources settings and _PSC, + * if available. */ + if (device->power.flags.power_resources) { + int error = acpi_power_get_inferred_state(device, &result); + if (error) + return error; + } if (device->power.flags.explicit_get) { + acpi_handle handle = device->handle; unsigned long long psc; - acpi_status status = acpi_evaluate_integer(device->handle, - "_PSC", NULL, &psc); + acpi_status status; + + status = acpi_evaluate_integer(handle, "_PSC", NULL, &psc); if (ACPI_FAILURE(status)) return -ENODEV; - result = psc; - } - /* The test below covers ACPI_STATE_UNKNOWN too. */ - if (result <= ACPI_STATE_D2) { - ; /* Do nothing. */ - } else if (device->power.flags.power_resources) { - int error = acpi_power_get_inferred_state(device, &result); - if (error) - return error; - } else if (result == ACPI_STATE_D3_HOT) { - result = ACPI_STATE_D3; + /* + * The power resources settings may indicate a power state + * shallower than the actual power state of the device. + * + * Moreover, on systems predating ACPI 4.0, if the device + * doesn't depend on any power resources and _PSC returns 3, + * that means "power off". We need to maintain compatibility + * with those systems. + */ + if (psc > result && psc < ACPI_STATE_D3_COLD) + result = psc; + else if (result == ACPI_STATE_UNKNOWN) + result = psc > ACPI_STATE_D2 ? ACPI_STATE_D3_COLD : psc; } /*