From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753452Ab3HEN7w (ORCPT ); Mon, 5 Aug 2013 09:59:52 -0400 Received: from hydra.sisk.pl ([212.160.235.94]:56605 "EHLO hydra.sisk.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752645Ab3HEN7v (ORCPT ); Mon, 5 Aug 2013 09:59:51 -0400 From: "Rafael J. Wysocki" To: ACPI Devel Maling List Cc: LKML , Linux PM list Subject: [PATCH] ACPI / PM: Walk physical_node_list under physical_node_lock Date: Mon, 05 Aug 2013 16:10:08 +0200 Message-ID: <4934962.0gqQfGrEzP@vostro.rjw.lan> User-Agent: KMail/4.9.5 (Linux/3.11.0-rc4+; KDE/4.9.5; x86_64; ; ) MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="utf-8" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Rafael J. Wysocki The list of physical devices corresponding to an ACPI device object is walked by acpi_system_wakeup_device_seq_show() and physical_device_enable_wakeup() without taking that object's physical_node_lock mutex. Since each of those functions may be run at any time as a result of a user space action, the lack of appropriate locking in them may lead to a kernel crash if that happens during device hot-add or hot-remove involving the device object in question. Fix the issue by modifying acpi_system_wakeup_device_seq_show() and physical_device_enable_wakeup() to use physical_node_lock as appropriate. Signed-off-by: Rafael J. Wysocki Cc: All --- This is urgent stuff, so if anyone has any objections against this or sees any problems with it, please let me know immediately. Thanks, Rafael --- drivers/acpi/proc.c | 8 ++++++++ 1 file changed, 8 insertions(+) Index: linux-pm/drivers/acpi/proc.c =================================================================== --- linux-pm.orig/drivers/acpi/proc.c +++ linux-pm/drivers/acpi/proc.c @@ -311,6 +311,8 @@ acpi_system_wakeup_device_seq_show(struc dev->pnp.bus_id, (u32) dev->wakeup.sleep_state); + mutex_lock(&dev->physical_node_lock); + if (!dev->physical_node_count) { seq_printf(seq, "%c%-8s\n", dev->wakeup.flags.run_wake ? '*' : ' ', @@ -338,6 +340,8 @@ acpi_system_wakeup_device_seq_show(struc put_device(ldev); } } + + mutex_unlock(&dev->physical_node_lock); } mutex_unlock(&acpi_device_lock); return 0; @@ -347,12 +351,16 @@ static void physical_device_enable_wakeu { struct acpi_device_physical_node *entry; + mutex_lock(&adev->physical_node_lock); + list_for_each_entry(entry, &adev->physical_node_list, node) if (entry->dev && device_can_wakeup(entry->dev)) { bool enable = !device_may_wakeup(entry->dev); device_set_wakeup_enable(entry->dev, enable); } + + mutex_unlock(&adev->physical_node_lock); } static ssize_t